WorldWideScience

Sample records for ultrasonographically detected neural

  1. Ultrasonographic Detection of Tooth Flaws

    Science.gov (United States)

    Bertoncini, C. A.; Hinders, M. K.; Ghorayeb, S. R.

    2010-02-01

    The goal of our work is to adapt pulse-echo ultrasound into a high resolution imaging modality for early detection of oral diseases and for monitoring treatment outcome. In this talk we discuss our preliminary results in the detection of: demineralization of the enamel and dentin, demineralization or caries under and around existing restorations, caries on occlusal and interproximal surfaces, cracks of enamel and dentin, calculus, and periapical lesions. In vitro immersion tank experiments are compared to results from a handpiece which uses a compliant delay line to couple the ultrasound to the tooth surface. Because the waveform echoes are complex, and in order to make clinical interpretation of ultrasonic waveform data in real time, it is necessary to automatically interpret the signals. We apply the dynamic wavelet fingerprint algorithms to identify and delineate echographic features that correspond to the flaws of interest in teeth. The resulting features show a clear distinction between flawed and unflawed waveforms collected with an ultrasonic handpiece on both phantom and human cadaver teeth.

  2. Application of Neural Networks for classification of Patau, Edwards, Down, Turner and Klinefelter Syndrome based on first trimester maternal serum screening data, ultrasonographic findings and patient demographics.

    Science.gov (United States)

    Catic, Aida; Gurbeta, Lejla; Kurtovic-Kozaric, Amina; Mehmedbasic, Senad; Badnjevic, Almir

    2018-02-13

    The usage of Artificial Neural Networks (ANNs) for genome-enabled classifications and establishing genome-phenotype correlations have been investigated more extensively over the past few years. The reason for this is that ANNs are good approximates of complex functions, so classification can be performed without the need for explicitly defined input-output model. This engineering tool can be applied for optimization of existing methods for disease/syndrome classification. Cytogenetic and molecular analyses are the most frequent tests used in prenatal diagnostic for the early detection of Turner, Klinefelter, Patau, Edwards and Down syndrome. These procedures can be lengthy, repetitive; and often employ invasive techniques so a robust automated method for classifying and reporting prenatal diagnostics would greatly help the clinicians with their routine work. The database consisted of data collected from 2500 pregnant woman that came to the Institute of Gynecology, Infertility and Perinatology "Mehmedbasic" for routine antenatal care between January 2000 and December 2016. During first trimester all women were subject to screening test where values of maternal serum pregnancy-associated plasma protein A (PAPP-A) and free beta human chorionic gonadotropin (β-hCG) were measured. Also, fetal nuchal translucency thickness and the presence or absence of the nasal bone was observed using ultrasound. The architectures of linear feedforward and feedback neural networks were investigated for various training data distributions and number of neurons in hidden layer. Feedback neural network architecture out performed feedforward neural network architecture in predictive ability for all five aneuploidy prenatal syndrome classes. Feedforward neural network with 15 neurons in hidden layer achieved classification sensitivity of 92.00%. Classification sensitivity of feedback (Elman's) neural network was 99.00%. Average accuracy of feedforward neural network was 89.6% and for

  3. Ultrasonographic detection of adrenal gland tumor and ureterolithiasis in a guinea pig

    International Nuclear Information System (INIS)

    Gaschen, L.; Ketz, C.; Lang, J.; Weber, U.; Bacciarini, L.; Kohler, I.

    1998-01-01

    A 5-year-old guinea pig was presented to the University of Berne Small Animal Radiology Department for an ultrasound examination of the abdomen to confirm a suspected diagnosis of Cushing's syndrome. The patient had bilateral alopecia, was apathic and obese. Ultrasonographically, a tumor of the left adrenal gland, obstruction of the left ureter by an ureterolith, as well as hydronephrosis of the left kidney were detected. During surgery to relieve the ureteral obstruction the adrenal gland tumor was removed. The guinea pig died post-operatively due to blood loss. The left adrenal gland tumor was found histopathologically to be an adenoma and the right adrenal gland also had multiple small adenomas, but grossly appeared normal. The ureterolith was analyzed and found by x-ray diffraction to consist of calcium carbonate

  4. Ultrasonographic detection of air in the superior sagittal sinus in a neonate with transposition of the great arteries

    Directory of Open Access Journals (Sweden)

    Michael D. Rivers-Bowerman, MD, MSc

    2017-03-01

    Full Text Available Cerebral venous air embolism is a relatively rare condition that arises from iatrogenic or traumatic introduction of air into the venous system. We describe the ultrasonographic findings in a 1-day-old infant with iatrogenic retrograde cerebral venous air embolism, which to our knowledge, is the earliest case reported in the literature to date. This case highlights the role of cerebral ultrasonography in the detection and surveillance of cerebral venous air embolism in neonates.

  5. Transient small-bowel intussusceptions in adults: significance of ultrasonographic detection

    International Nuclear Information System (INIS)

    Maconi, G.; Radice, E.; Greco, S.; Bezzio, C.; Bianchi Porro, G.

    2007-01-01

    Aim: To investigate the frequency, clinical significance, and outcome of small-bowel intussusceptions in adults detected using ultrasound in an outpatient setting. Patients and methods: In two different retrospective (January 2001 to April 2003) and prospective (May 2003 to June 2005) periods, 33 small-bowel intussusceptions were found in 32 patients (13 females; mean age: 38.1 years) with known or suspected intestinal disease. Patients underwent diagnostic work-up to assess any organic disease. Patients with self-limiting intussusception were submitted to clinical and ultrasonographic follow-up. Results: Of the 32 patients with small-bowel intussusception, 25 were identified in the prospective series of 4487 examinations (0.53%) and seven in the retrospective series of 5342 examinations (0.15%; p = 0.002). Four patients had persistent and 28 self-limiting intussusceptions. Self-limiting intussusceptions were idiopathic in 11 patients (39%) or associated with organic diseases in 17 (Crohn's disease in 11 patients, celiac disease in three, ulcerative colitis in one patient, and previous surgery for cancer in two). Self-limiting intussusceptions were asymptomatic in 25% of patients. Conclusion: Small-bowel intussusceptions in adults are not rare and are frequently self-limiting, idiopathic, or related to organic diseases, mainly Crohn's disease and coeliac disease

  6. Transient small-bowel intussusceptions in adults: significance of ultrasonographic detection

    Energy Technology Data Exchange (ETDEWEB)

    Maconi, G. [Chair of Gastroenterology, Department of Clinical Sciences, L. Sacco University Hospital, Milan (Italy)]. E-mail: giovanni.maconi@unimi.it; Radice, E. [Chair of Gastroenterology, Department of Clinical Sciences, L. Sacco University Hospital, Milan (Italy); Greco, S. [Chair of Gastroenterology, Department of Clinical Sciences, L. Sacco University Hospital, Milan (Italy); Bezzio, C. [Chair of Gastroenterology, Department of Clinical Sciences, L. Sacco University Hospital, Milan (Italy); Bianchi Porro, G. [Chair of Gastroenterology, Department of Clinical Sciences, L. Sacco University Hospital, Milan (Italy)

    2007-08-15

    Aim: To investigate the frequency, clinical significance, and outcome of small-bowel intussusceptions in adults detected using ultrasound in an outpatient setting. Patients and methods: In two different retrospective (January 2001 to April 2003) and prospective (May 2003 to June 2005) periods, 33 small-bowel intussusceptions were found in 32 patients (13 females; mean age: 38.1 years) with known or suspected intestinal disease. Patients underwent diagnostic work-up to assess any organic disease. Patients with self-limiting intussusception were submitted to clinical and ultrasonographic follow-up. Results: Of the 32 patients with small-bowel intussusception, 25 were identified in the prospective series of 4487 examinations (0.53%) and seven in the retrospective series of 5342 examinations (0.15%; p = 0.002). Four patients had persistent and 28 self-limiting intussusceptions. Self-limiting intussusceptions were idiopathic in 11 patients (39%) or associated with organic diseases in 17 (Crohn's disease in 11 patients, celiac disease in three, ulcerative colitis in one patient, and previous surgery for cancer in two). Self-limiting intussusceptions were asymptomatic in 25% of patients. Conclusion: Small-bowel intussusceptions in adults are not rare and are frequently self-limiting, idiopathic, or related to organic diseases, mainly Crohn's disease and coeliac disease.

  7. The utility of ultrasonographic bone age determination in detecting growth disturbances; a comparative study with the conventional radiographic technique

    Energy Technology Data Exchange (ETDEWEB)

    Hajalioghli, Parisa; Tarzamni, Mohammad Kazem; Arami, Sara [Tabriz University of Medical Sciences, Department of Radiology, Imam Reza Teaching Hospital, Tabriz (Iran, Islamic Republic of); Fouladi, Daniel Fadaei [Tabriz University of Medical Sciences, Neurosciences Research Center, Tabriz (Iran, Islamic Republic of); Tabriz University of Medical Sciences, Imam Reza Teaching Hospital, Neurosciences Research Center, Tabriz (Iran, Islamic Republic of); Ghojazadeh, Morteza [Tabriz University of Medical Sciences, Department of Physiology, School of Medicine, Tabriz (Iran, Islamic Republic of)

    2015-09-15

    To test whether the conventional radiographic technique in determining bone age abnormalities can be replaced by ultrasonography. A total of 54 Caucasian subjects up to 7 years of age with clinically suspected growth problems underwent left hand and wrist radiographic and ultrasonographic bone age estimations with the use of the Greulich-Pyle atlas. The ultrasonographic scans targeted the ossification centers in the radius and ulna distal epiphysis, carpal bones, epiphyses of the first and third metacarpals, and epiphysis of the middle phalanx, as described in previous reports. The degree of agreement between the two sets of data, as well as the accuracy of the ultrasonographic method in detecting radiographically suggested bone age abnormities, was examined. The mean chronological age, radiographic bone age, and ultrasonographic bone age (all in months) were 41.96 ± 22.25, 26.68 ± 14.08, and 26.71 ± 13.50 in 28 boys and 43.62 ± 24.63, 30.12 ± 17.69, and 31.27 ± 18.06 in 26 girls, respectively. According to the Bland-Altman plot there was high agreement between the results of the two methods with only three outliers. The deviations in bone age from the chronological age taken by the two techniques had the same sign in all patients. Supposing radiography to be the method of reference, the sensitivity, specificity, positive predictive value, and negative predictive value of sonography in detecting growth abnormalities were all 100 % in males and 90.9, 100, 100, and 93.8 %, respectively, in females. The conventional radiographic technique for determining bone age abnormalities could be replaced by ultrasonography. (orig.)

  8. Noninvasive detection of hepatic lipidosis in dairy cows with calibrated ultrasonographic image analysis.

    NARCIS (Netherlands)

    Starke, A.; Haudum, A.; Weijers, G.; Herzog, K.; Wohlsein, P.; Beyerbach, M.; Korte, C.L. de; Thijssen, J.M.; Rehage, J.

    2010-01-01

    The aim was to test the accuracy of calibrated digital analysis of ultrasonographic hepatic images for diagnosing fatty liver in dairy cows. Digital analysis was performed by means of a novel method, computer-aided ultrasound diagnosis (CAUS), previously published by the authors. This method implies

  9. Ultrasonographic findings in patients examined in cataract detection-andtreatment campaigns: a retrospective study

    Directory of Open Access Journals (Sweden)

    Marcio Henrique Mendes

    2009-01-01

    Full Text Available INTRODUCTION: A cataract is defined as an opacity of any portion of the lens, regardless of visual acuity. In some advanced cases of cataracts, in which good fundus visualization is not possible, an ultrasound examination provides better assessment of the posterior segment of the globe. OBJECTIVES: This study aims to evaluate the ultrasonographic records of patients with advanced cataracts who were examined during cataract campaigns. METHODS: The ultrasonographic findings obtained from 215 patients examined in cataract campaigns conducted by the Hospital das Clínicas Department of Ophthalmology of the Faculdade de Medicina da Universidade de São Paulo between the years of 2005 and 2007 were evaluated, and the utility of this exam in changing the treatment procedures was studied. RESULTS: A total of 289 eyes from 215 patients were examined. Of the eyes examined, 77.5% presented with findings in the vitreous cavity and the posterior pole. A posterior vitreous detachment with no other complications was observed in 47.4% of the eyes. The remaining 30.1% presented with eye diseases that could result in a reduced visual function after surgery. The most frequent eye diseases observed were diffuse vitreous opacity (12.1% of the eyes and detachment of the retina (9.3% of the eyes. DISCUSSION: In many cases, the ultrasonographic evaluation of the posterior segment revealed significant anomalies that changed the original treatment plan or contra-indicated surgery. At the very least, the evaluation was useful for patient counseling. CONCLUSION: The ultrasonographic examination revealed and differentiated between eyes with cataracts and eyes with ocular abnormalities other than cataracts as the cause of poor vision, thereby indicating the importance of its use during ocular evaluation.

  10. Noninvasive detection of hepatic lipidosis in dairy cows with calibrated ultrasonographic image analysis.

    Science.gov (United States)

    Starke, A; Haudum, A; Weijers, G; Herzog, K; Wohlsein, P; Beyerbach, M; de Korte, C L; Thijssen, J M; Rehage, J

    2010-07-01

    The aim was to test the accuracy of calibrated digital analysis of ultrasonographic hepatic images for diagnosing fatty liver in dairy cows. Digital analysis was performed by means of a novel method, computer-aided ultrasound diagnosis (CAUS), previously published by the authors. This method implies a set of pre- and postprocessing steps to normalize and correct the transcutaneous ultrasonographic images. Transcutaneous hepatic ultrasonography was performed before surgical correction on 151 German Holstein dairy cows (mean +/- standard error of the means; body weight: 571+/-7 kg; age: 4.9+/-0.2 yr; DIM: 35+/-5) with left-sided abomasal displacement. Concentration of triacylglycerol (TAG) was biochemically determined in liver samples collected via biopsy and values were considered the gold standard to which ultrasound estimates were compared. According to histopathologic examination of biopsies, none of the cows suffered from hepatic disorders other than hepatic lipidosis. Hepatic TAG concentrations ranged from 4.6 to 292.4 mg/g of liver fresh weight (FW). High correlations were found between the hepatic TAG and mean echo level (r=0.59) and residual attenuation (ResAtt; r=0.80) obtained in ultrasonographic imaging. High correlation existed between ResAtt and mean echo level (r=0.76). The 151 studied cows were split randomly into a training set of 76 cows and a test set of 75 cows. Based on the data from the training set, ResAtt was statistically selected by means of stepwise multiple regression analysis for hepatic TAG prediction (R(2)=0.69). Then, using the predicted TAG data of the test set, receiver operating characteristic analysis was performed to summarize the accuracy and predictive potential of the differentiation between various measured hepatic TAG values, based on TAG predicted from the regression formula. The area under the curve values of the receiver operating characteristic based on the regression equation were 0.94 (or=50mg of TAG/g of FW), 0.83 (or

  11. Time of initial detection of fetal and extra-fetal structures by ultrasonographic examination in Miniature Schnauzer bitches.

    Science.gov (United States)

    Kim, Bang Sil; Son, Chang Ho

    2007-09-01

    Serial ultrasonographic examinations were performed daily on 9 Miniature Schnauzer bitches from the 15th day of gestation until parturition to determine the time the gestational structures were first detected. The gestational age was timed from the day of ovulation (day 0), which was estimated to occur when the plasma progesterone concentration was >4.0 ng/ml. The gestational length in 9 Miniature Schnauzer bitches was found to be 63.0 +/- 1.7 (range 61-65) days. The initial detection of the fetal and extra-fetal structures were as follows: gestational sac at day 18.0 +/- 0.9 (17-19); zonary placenta in the uterine wall at day 24.9 +/- 1.1 (23-26); yolk sac membrane at day 25.0 +/- 0.9 (24-26); amnionic membrane at day 27.7 +/- 1.0 (26- 29); embryo initial detection at day 22.6 +/- 0.5 (22-23); heartbeat at day 23.4 +/- 0.5 (23-24); fetal movement at day 32.5 +/- 0.8 (32-34); stomach at day 31.2 +/- 1.6 (29-33); urinary bladder at day 32.6 +/- 1.8 (31-35); skeleton at day 34.9 +/- 1.6 (34-38) and kidney at day 42.2 +/- 0.7 (41-43).

  12. Evaluation of the prenatal diagnosis of neural tube defects by fetal ultrasonographic examination in different centres across Europe

    NARCIS (Netherlands)

    Boyd, PA; Wellesley, DG; De Walle, HEK; Tenconi, R; Garcia-Minaur, S; Zandwijken, GRJ; Stoll, C; Clementi, M

    2000-01-01

    Objective-Evaluation of prenatal diagnosis of neural tube defects by ultrasound examination in unselected populations across Europe. Setting-Prenatal ultrasound units in areas that report to contributing congenital malformation registers. Methods-All cases with a suspected or confirmed neural tube

  13. A neural network approach to burst detection.

    Science.gov (United States)

    Mounce, S R; Day, A J; Wood, A S; Khan, A; Widdop, P D; Machell, J

    2002-01-01

    This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

  14. Epileptiform spike detection via convolutional neural networks

    DEFF Research Database (Denmark)

    Johansen, Alexander Rosenberg; Jin, Jing; Maszczyk, Tomasz

    2016-01-01

    The EEG of epileptic patients often contains sharp waveforms called "spikes", occurring between seizures. Detecting such spikes is crucial for diagnosing epilepsy. In this paper, we develop a convolutional neural network (CNN) for detecting spikes in EEG of epileptic patients in an automated...

  15. Detection of normal plantar fascia thickness in adults via the ultrasonographic method.

    Science.gov (United States)

    Abul, Kadir; Ozer, Devrim; Sakizlioglu, Secil Sezgin; Buyuk, Abdul Fettah; Kaygusuz, Mehmet Akif

    2015-01-01

    Heel pain is a prevalent concern in orthopedic clinics, and there are numerous pathologic abnormalities that can cause heel pain. Plantar fasciitis is the most common cause of heel pain, and the plantar fascia thickens in this process. It has been found that thickening to greater than 4 mm in ultrasonographic measurements can be accepted as meaningful in diagnoses. Herein, we aimed to measure normal plantar fascia thickness in adults using ultrasonography. We used ultrasonography to measure the plantar fascia thickness of 156 healthy adults in both feet between April 1, 2011, and June 30, 2011. These adults had no previous heel pain. The 156 participants comprised 88 women (56.4%) and 68 men (43.6%) (mean age, 37.9 years; range, 18-65 years). The weight, height, and body mass index of the participants were recorded, and statistical analyses were conducted. The mean ± SD (range) plantar fascia thickness measurements for subgroups of the sample were as follows: 3.284 ± 0.56 mm (2.4-5.1 mm) for male right feet, 3.3 ± 0.55 mm (2.5-5.0 mm) for male left feet, 2.842 ± 0.42 mm (1.8-4.1 mm) for female right feet, and 2.8 ± 0.44 mm (1.8-4.3 mm) for female left feet. The overall mean ± SD (range) thickness for the right foot was 3.035 ± 0.53 mm (1.8-5.1 mm) and for the left foot was 3.053 ± 0.54 mm (1.8-5.0 mm). There was a statistically significant and positive correlation between plantar fascia thickness and participant age, weight, height, and body mass index. The plantar fascia thickness of adults without heel pain was measured to be less than 4 mm in most participants (~92%). There was no statistically significant difference between the thickness of the right and left foot plantar fascia.

  16. Neural network approach to radiologic lesion detection

    International Nuclear Information System (INIS)

    Newman, F.D.; Raff, U.; Stroud, D.

    1989-01-01

    An area of artificial intelligence that has gained recent attention is the neural network approach to pattern recognition. The authors explore the use of neural networks in radiologic lesion detection with what is known in the literature as the novelty filter. This filter uses a linear model; images of normal patterns become training vectors and are stored as columns of a matrix. An image of an abnormal pattern is introduced and the abnormality or novelty is extracted. A VAX 750 was used to encode the novelty filter, and two experiments have been examined

  17. Deep Neural Network Detects Quantum Phase Transition

    Science.gov (United States)

    Arai, Shunta; Ohzeki, Masayuki; Tanaka, Kazuyuki

    2018-03-01

    We detect the quantum phase transition of a quantum many-body system by mapping the observed results of the quantum state onto a neural network. In the present study, we utilized the simplest case of a quantum many-body system, namely a one-dimensional chain of Ising spins with the transverse Ising model. We prepared several spin configurations, which were obtained using repeated observations of the model for a particular strength of the transverse field, as input data for the neural network. Although the proposed method can be employed using experimental observations of quantum many-body systems, we tested our technique with spin configurations generated by a quantum Monte Carlo simulation without initial relaxation. The neural network successfully identified the strength of transverse field only from the spin configurations, leading to consistent estimations of the critical point of our model Γc = J.

  18. Ultrasonographic detection of focal liver lesions: increased sensitivity and specificity with microbubble contrast agents

    International Nuclear Information System (INIS)

    Hohmann, J.; Albrecht, T.; Hoffmann, C.W.; Wolf, K.-J.

    2003-01-01

    Ultrasonography (US) is the first choice for screening patients with suspected liver lesions. However, due to a lack of contrast agents, US used to be less sensitive and specific compared with computed tomography (CT) and magnet resonance imaging (MRI). The advent of microbubble contrast agents increased both sensitivity and specificity dramatically. Rapid developments of the contrast agents as well as of special imaging techniques were made in recent years. Today numerous different US imaging methods exist which based either on Doppler or on harmonic imaging. They are using the particular behaviour of microbubbles in a sound field which varies depending on the energy of insonation (low/high mechanical index, MI) as well as on the properties of the agent themselves. Apart from just blood pool enhancement some agents have a hepatosplenic specific late phase. US imaging during this late phase using relatively high MI in phase inversion mode (harmonic imaging) or stimulated acoustic emission (SAE; Doppler method) markedly improves the detection of focal liver lesions and is also very helpful for lesion characterisation. With regards to detection, contrast enhanced US performs similarly to CT as shown by recent studies. Early results of studies using low MI imaging and the newer perfluor agents are also showing promising results for lesion detection. Low MI imaging with these agents has the advantage of real time imaging and is particularly helpful for characterisation of focal lesions based on their dynamic contrast behaviour. Apart from the techniques which based on the morphology of liver lesions there were some attempts for the detection of occult metastases or micrometastases by means of liver blood flow changes. Also in this field the use of US contrast agents appears to have advantages over formerly used non contrast-enhanced methods although no conclusive results are available yet

  19. Ultrasonographic detection of hepatocellular carcinoma: correlation of preoperative ultrasonography and resected liver pathology

    International Nuclear Information System (INIS)

    Lim, J.H.; Kim, S.H.; Lee, W.J.; Choi, D.; Kim, S.H.; Lim, H.K.

    2006-01-01

    AIM: The aim of this study was to determine the sensitivity of ultrasonography for detecting hepatocellular carcinoma in patients who underwent surgical liver resection. MATERIALS AND METHODS: The preoperative ultrasonography reports of 103 patients who underwent hepatic resection surgery were retrospectively reviewed. The patients had chronic liver disease with good liver function and a relatively normal liver echotexture. The presence of a mass or masses in the resected part of the liver segments on preoperative ultrasonography was regarded as possible hepatocellular carcinoma, and these results were compared with the surgically resected hepatic lobes or segments. Accuracy for detection was assessed on a lesion-by-lesion basis, on a segment-by-segment basis, and on a patient basis. RESULTS: One hundred and fifty-seven hepatocellular carcinomas were found in 244 hepatic segments of 103 patients. One hundred and one of 157 hepatocellular carcinomas were detected using ultrasonography in 97 patients resulting in a sensitivity of 64%. In six patients, a solitary hepatocellular carcinoma was missed in each patient, a patient sensitivity being 94%. Using ultrasonography, 87 of 100 (87%) hepatocellular carcinomas larger than 2 cm in diameter, and 14 of 57 (25%) hepatocellular carcinomas 2 cm or smaller in diameter were revealed. On the basis of segment-by-segment analysis, the sensitivity was 78% (99 of 127 segments), specificity was 97% (114 of 117 segments), accuracy was 87% (213 of 244 segments), positive predictive value was 97% (99 of 102 segments), and negative predictive value was 80% (114 of 142 segments). CONCLUSION: In patients with chronic liver disease and good hepatic function, ultrasonography has a sensitivity of 94% in the identification of affected patients, but for individual lesions, the sensitivity is only 64%

  20. Artificial neural network detects human uncertainty

    Science.gov (United States)

    Hramov, Alexander E.; Frolov, Nikita S.; Maksimenko, Vladimir A.; Makarov, Vladimir V.; Koronovskii, Alexey A.; Garcia-Prieto, Juan; Antón-Toro, Luis Fernando; Maestú, Fernando; Pisarchik, Alexander N.

    2018-03-01

    Artificial neural networks (ANNs) are known to be a powerful tool for data analysis. They are used in social science, robotics, and neurophysiology for solving tasks of classification, forecasting, pattern recognition, etc. In neuroscience, ANNs allow the recognition of specific forms of brain activity from multichannel EEG or MEG data. This makes the ANN an efficient computational core for brain-machine systems. However, despite significant achievements of artificial intelligence in recognition and classification of well-reproducible patterns of neural activity, the use of ANNs for recognition and classification of patterns in neural networks still requires additional attention, especially in ambiguous situations. According to this, in this research, we demonstrate the efficiency of application of the ANN for classification of human MEG trials corresponding to the perception of bistable visual stimuli with different degrees of ambiguity. We show that along with classification of brain states associated with multistable image interpretations, in the case of significant ambiguity, the ANN can detect an uncertain state when the observer doubts about the image interpretation. With the obtained results, we describe the possible application of ANNs for detection of bistable brain activity associated with difficulties in the decision-making process.

  1. Multiscale Convolutional Neural Networks for Hand Detection

    Directory of Open Access Journals (Sweden)

    Shiyang Yan

    2017-01-01

    Full Text Available Unconstrained hand detection in still images plays an important role in many hand-related vision problems, for example, hand tracking, gesture analysis, human action recognition and human-machine interaction, and sign language recognition. Although hand detection has been extensively studied for decades, it is still a challenging task with many problems to be tackled. The contributing factors for this complexity include heavy occlusion, low resolution, varying illumination conditions, different hand gestures, and the complex interactions between hands and objects or other hands. In this paper, we propose a multiscale deep learning model for unconstrained hand detection in still images. Deep learning models, and deep convolutional neural networks (CNNs in particular, have achieved state-of-the-art performances in many vision benchmarks. Developed from the region-based CNN (R-CNN model, we propose a hand detection scheme based on candidate regions generated by a generic region proposal algorithm, followed by multiscale information fusion from the popular VGG16 model. Two benchmark datasets were applied to validate the proposed method, namely, the Oxford Hand Detection Dataset and the VIVA Hand Detection Challenge. We achieved state-of-the-art results on the Oxford Hand Detection Dataset and had satisfactory performance in the VIVA Hand Detection Challenge.

  2. Defect detection on videos using neural network

    Directory of Open Access Journals (Sweden)

    Sizyakin Roman

    2017-01-01

    Full Text Available In this paper, we consider a method for defects detection in a video sequence, which consists of three main steps; frame compensation, preprocessing by a detector, which is base on the ranking of pixel values, and the classification of all pixels having anomalous values using convolutional neural networks. The effectiveness of the proposed method shown in comparison with the known techniques on several frames of the video sequence with damaged in natural conditions. The analysis of the obtained results indicates the high efficiency of the proposed method. The additional use of machine learning as postprocessing significantly reduce the likelihood of false alarm.

  3. Ultrasonographic findings of cataract

    International Nuclear Information System (INIS)

    Choi, Sun Seob; Kim, Yang Soo; Lee, Kwan Seh; Kim, Kun Sang

    1985-01-01

    Examining the eye with high resolution ultrasonography, authors encountered 34 cases (41 eyeballs) of cataract and found out its characteristic ultrasonographic findings, though cataract is easily recognized by physician on inspection. Ultrasonographic findings of cataract were as follows; 1. Thickening of lens due to edema. 2. Demonstration of lens echo in whole circumference. 3. Multiple internal lens echo

  4. Ultrasonographic Diagnosis of Intraductal Papilloma

    International Nuclear Information System (INIS)

    Seong, Ki Ho; Cho, Dae Hyoun; Hwang, Mi Soo

    1996-01-01

    To demonstrate the ultrasonographic findings in the diagnosis of intraductal papilloma by comparing it with mammography and ductography. The findings of mammography (n = 22), ultrasonography (n= 15), and ductography (n = 5) were analyzed in 25 women with intraductal papilloma. The mammographic findings were asymmetric focal increase in density (n = 4 : 18%), mass without calcification (n = 6 : 27%), mass with calcification (n = 2 : 9%), and calcification only (n = 1 : 5%). Nine studies (41%) showed no abnormal findings. The ultrasonographic findings were ductal dilatation with a mass (n = 7 : 47%), mass only (n = 5 : 33%),and intra cystic mass (n = 3 : 20%). There is no case of normal findings on ultrasonography. Three ductograms (60%)showed a filling defect within duct : the other two studies were normal. Ultrasonography offers very useful findings in early detecting the intraductal papilloma in conjunction with mammography and ductography

  5. Neural fraud detection in credit card operations.

    Science.gov (United States)

    Dorronsoro, J R; Ginel, F; Sgnchez, C; Cruz, C S

    1997-01-01

    This paper presents an online system for fraud detection of credit card operations based on a neural classifier. Since it is installed in a transactional hub for operation distribution, and not on a card-issuing institution, it acts solely on the information of the operation to be rated and of its immediate previous history, and not on historic databases of past cardholder activities. Among the main characteristics of credit card traffic are the great imbalance between proper and fraudulent operations, and a great degree of mixing between both. To ensure proper model construction, a nonlinear version of Fisher's discriminant analysis, which adequately separates a good proportion of fraudulent operations away from other closer to normal traffic, has been used. The system is fully operational and currently handles more than 12 million operations per year with very satisfactory results.

  6. Failure detection studies by layered neural network

    International Nuclear Information System (INIS)

    Ciftcioglu, O.; Seker, S.; Turkcan, E.

    1991-06-01

    Failure detection studies by layered neural network (NN) are described. The particular application area is an operating nuclear power plant and the failure detection is of concern as result of system surveillance in real-time. The NN system is considered to be consisting of 3 layers, one of which being hidden, and the NN parameters are determined adaptively by the backpropagation (BP) method, the process being the training phase. Studies are performed using the power spectra of the pressure signal of the primary system of an operating nuclear power plant of PWR type. The studies revealed that, by means of NN approach, failure detection can effectively be carried out using the redundant information as well as this is the case in this work; namely, from measurement of the primary pressure signals one can estimate the primary system coolant temperature and hence the deviation from the operational temperature state, the operational status identified in the training phase being referred to as normal. (author). 13 refs.; 4 figs.; 2 tabs

  7. Radial basis function neural network in fault detection of automotive ...

    African Journals Online (AJOL)

    Radial basis function neural network in fault detection of automotive engines. ... Five faults have been simulated on the MVEM, including three sensor faults, one component fault and one actuator fault. The three sensor faults ... Keywords: Automotive engine, independent RBFNN model, RBF neural network, fault detection

  8. Microaneurysm detection using fully convolutional neural networks.

    Science.gov (United States)

    Chudzik, Piotr; Majumdar, Somshubra; Calivá, Francesco; Al-Diri, Bashir; Hunter, Andrew

    2018-05-01

    Diabetic retinopathy is a microvascular complication of diabetes that can lead to sight loss if treated not early enough. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper presents an automatic method for detecting microaneurysms in fundus photographies. A novel patch-based fully convolutional neural network with batch normalization layers and Dice loss function is proposed. Compared to other methods that require up to five processing stages, it requires only three. Furthermore, to the best of the authors' knowledge, this is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain. The proposed method was evaluated using three publicly available and widely used datasets: E-Ophtha, DIARETDB1, and ROC. It achieved better results than state-of-the-art methods using the FROC metric. The proposed algorithm accomplished highest sensitivities for low false positive rates, which is particularly important for screening purposes. Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications. Copyright © 2018 Elsevier B.V. All rights reserved.

  9. Efficient Cancer Detection Using Multiple Neural Networks.

    Science.gov (United States)

    Shell, John; Gregory, William D

    2017-01-01

    The inspection of live excised tissue specimens to ascertain malignancy is a challenging task in dermatopathology and generally in histopathology. We introduce a portable desktop prototype device that provides highly accurate neural network classification of malignant and benign tissue. The handheld device collects 47 impedance data samples from 1 Hz to 32 MHz via tetrapolar blackened platinum electrodes. The data analysis was implemented with six different backpropagation neural networks (BNN). A data set consisting of 180 malignant and 180 benign breast tissue data files in an approved IRB study at the Aurora Medical Center, Milwaukee, WI, USA, were utilized as a neural network input. The BNN structure consisted of a multi-tiered consensus approach autonomously selecting four of six neural networks to determine a malignant or benign classification. The BNN analysis was then compared with the histology results with consistent sensitivity of 100% and a specificity of 100%. This implementation successfully relied solely on statistical variation between the benign and malignant impedance data and intricate neural network configuration. This device and BNN implementation provides a novel approach that could be a valuable tool to augment current medical practice assessment of the health of breast, squamous, and basal cell carcinoma and other excised tissue without requisite tissue specimen expertise. It has the potential to provide clinical management personnel with a fast non-invasive accurate assessment of biopsied or sectioned excised tissue in various clinical settings.

  10. Ultrasonographic findings of Epicondylitis

    International Nuclear Information System (INIS)

    Kwak, Seo Hyun; Song, In Sup; Lee, Jong Beum; Lee, Hwa Yeon; Yoo, Seung Min; Yang, Seong Jun; Seo, Kyung Mook

    2002-01-01

    To evaluate the usefulness of ultrasonographic findings of the common extensor and flexor tendon in evaluation of patients with lateral and medial epicondylitis. Thirty eight elbows from twenty four patients (mean age=45.2 years) were included. Ultrasonographic examination was performed to evaluate lateral or medial epicondylitis. Epicondylitis was divided into five groups according to the severity of disease: 1) normal, 2) tendinopathy, 3) tendinopathy with a partial tear, partial tear and 4) complete tear. Change in the size of a tendon, bony change of the epicondylitis, presence or absence of calcification or echogenic foci in the common tendon and hypervascularity for each categories were also assessed. In addition, these lesions were divided into the superficial and deep according to the location of lesions. According to the severity, there were 15 cases of normal, 13 tendinopathies, 8 tendinopathies with a partial tear, 2 partial tears and 0 complete tear. Bony change was seen only in tendinopathy, tendinopathy with partial tear and partial tear. Calcification or echogenic foci were only observed in cases with tendinopathy and tendinopathy with partial tear. Hypervascularity was only seen in one case of tendinopathy. With thorough understanding of ultrasonographic findings of epicondylitis, ultrasonographic examination can be especially useful and effective in evaluating the severity and location of lesions.

  11. Ultrasonographic findings of Epicondylitis

    Energy Technology Data Exchange (ETDEWEB)

    Kwak, Seo Hyun; Song, In Sup; Lee, Jong Beum; Lee, Hwa Yeon; Yoo, Seung Min; Yang, Seong Jun [Yong San Hospital, Chung-Ang University College of Medicine, Seoul (Korea, Republic of); Seo, Kyung Mook [Chung-Ang University College of Medicine, Seoul (Korea, Republic of)

    2002-09-15

    To evaluate the usefulness of ultrasonographic findings of the common extensor and flexor tendon in evaluation of patients with lateral and medial epicondylitis. Thirty eight elbows from twenty four patients (mean age=45.2 years) were included. Ultrasonographic examination was performed to evaluate lateral or medial epicondylitis. Epicondylitis was divided into five groups according to the severity of disease: 1) normal, 2) tendinopathy, 3) tendinopathy with a partial tear, partial tear and 4) complete tear. Change in the size of a tendon, bony change of the epicondylitis, presence or absence of calcification or echogenic foci in the common tendon and hypervascularity for each categories were also assessed. In addition, these lesions were divided into the superficial and deep according to the location of lesions. According to the severity, there were 15 cases of normal, 13 tendinopathies, 8 tendinopathies with a partial tear, 2 partial tears and 0 complete tear. Bony change was seen only in tendinopathy, tendinopathy with partial tear and partial tear. Calcification or echogenic foci were only observed in cases with tendinopathy and tendinopathy with partial tear. Hypervascularity was only seen in one case of tendinopathy. With thorough understanding of ultrasonographic findings of epicondylitis, ultrasonographic examination can be especially useful and effective in evaluating the severity and location of lesions.

  12. Airplane detection in remote sensing images using convolutional neural networks

    Science.gov (United States)

    Ouyang, Chao; Chen, Zhong; Zhang, Feng; Zhang, Yifei

    2018-03-01

    Airplane detection in remote sensing images remains a challenging problem and has also been taking a great interest to researchers. In this paper we propose an effective method to detect airplanes in remote sensing images using convolutional neural networks. Deep learning methods show greater advantages than the traditional methods with the rise of deep neural networks in target detection, and we give an explanation why this happens. To improve the performance on detection of airplane, we combine a region proposal algorithm with convolutional neural networks. And in the training phase, we divide the background into multi classes rather than one class, which can reduce false alarms. Our experimental results show that the proposed method is effective and robust in detecting airplane.

  13. Ultrasonographic finding of hepatocellular carcinoma

    Energy Technology Data Exchange (ETDEWEB)

    Ryu, Han Soo; Woo, Seong Ku; Lim, Jae Hoon; Ko, Young Tae; Kim, Ho Kyun; Kim, Soon Yong [Kyung Hee University Hospital, Seoul (Korea, Republic of)

    1983-12-15

    With the development of gray scale ultrasonography, detection and evaluation of hepatic parenchymal disease including space occupying lesion are easily performed and frequently used in the world. Thrity five cases of histopathologically proven and ultrasonographically suggested hepatocellular carcinoma are retrospectively studied. The results were as follows; 1. Ultrasonographic findings of hepatocellular carcinoma show hyperechoic pattern in 22 cases (63%), hypoechoic pattern in 2 cases (6%), and mixed pattern in 11 cases (31%). 2. The margin of tumor is ill-defined in 19 cases (54%) and well defined in16 cases (46%). 3. The size of tumor by sonographic measurement was large than 5 cm in diameter in 33 cases (94%). 4. The number of tumor is solitary in 19 cases and multiple in 16 cases. The sites of involved lobe were right lobe in 22 cases (63%), left lobe in 2 cases (6%), and both lobes in 11 cases (31%). 5. Associated sonographic findings were hepatomegaly with focal contour change in 25 cases (71%), splenomegaly in 16 cases (46%), cirrhosis of liver in 15 cases (43%), ascites in 11 cases (31%) and tumoral thrombosis in portal vein in 8 cases (23%). 6. The sex ratio is 6 : 1 male predominence and the age ranges from 32 to 76 years with highest incidence in 5th and 6th decades.

  14. Online fouling detection in electrical circulation heaters using neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Lalot, S. [M.E.T.I.E.R., Longuenesse Cedex (France); Universite de Valenciennes (France). LME; Lecoeuche, S. [M.E.T.I.E.R., Longuenesse Cedex (France); Universite de Lille (France). Laboratoire 13D

    2003-06-01

    Here is presented a method that is able to detect fouling during the service of a circulation electrical heater. The neural based technique is divided in two major steps: identification and classification. Each step uses a neural network, the connection weights of the first one being the inputs of the second network. Each step is detailed and the main characteristics and abilities of the two neural networks are given. It is shown that the method is able to discriminate fouling from viscosity modification that would lead to the same type of effect on the total heat transfer coefficient. (author)

  15. Artificial-neural-network-based failure detection and isolation

    Science.gov (United States)

    Sadok, Mokhtar; Gharsalli, Imed; Alouani, Ali T.

    1998-03-01

    This paper presents the design of a systematic failure detection and isolation system that uses the concept of failure sensitive variables (FSV) and artificial neural networks (ANN). The proposed approach was applied to tube leak detection in a utility boiler system. Results of the experimental testing are presented in the paper.

  16. Anomaly detection in an automated safeguards system using neural networks

    International Nuclear Information System (INIS)

    Whiteson, R.; Howell, J.A.

    1992-01-01

    An automated safeguards system must be able to detect an anomalous event, identify the nature of the event, and recommend a corrective action. Neural networks represent a new way of thinking about basic computational mechanisms for intelligent information processing. In this paper, we discuss the issues involved in applying a neural network model to the first step of this process: anomaly detection in materials accounting systems. We extend our previous model to a 3-tank problem and compare different neural network architectures and algorithms. We evaluate the computational difficulties in training neural networks and explore how certain design principles affect the problems. The issues involved in building a neural network architecture include how the information flows, how the network is trained, how the neurons in a network are connected, how the neurons process information, and how the connections between neurons are modified. Our approach is based on the demonstrated ability of neural networks to model complex, nonlinear, real-time processes. By modeling the normal behavior of the processes, we can predict how a system should be behaving and, therefore, detect when an abnormality occurs

  17. Ultrasonographic findings of sclerosing encapsulating peritonitis

    Energy Technology Data Exchange (ETDEWEB)

    Han, Jong Kyu; Lee, Hae Kyung; Moon, Chul; Hong, Hyun Sook; Kwon, Kwi Hyang; Choi, Deuk Lin [Soonchunhyangi University College of Medicine, Seoul (Korea, Republic of)

    2001-03-15

    To evaluate the ultrasonographic findings of the patients with sclerosing encapsulating peritonitis (SEP). Thirteen patients with surgically confirmed sclerosing encapsulating peritonitis were involved in this study. Because of intestinal obstruction, all patients had received operations. Among 13 patients, 12 cases had continuous ambulatory peritoneal dialysis (CAPD) for 2 months-12 years and 4 months from (mean; 6 years and 10 months), owing to chronic renal failure and one patient had an operation due to variceal bleeding caused by liver cirrhosis. On ultrasonographic examination, all patients showed loculated ascites which were large (n=7) or small (n=6) in amount with multiple separations. The small bowel loops were tethered posteriorly perisaltic movement and covered with the thick membrane. The ultrasonographic of findings of sclerosing encapsulating peritonitis were posteriorly tethered small bowels covered with a thick membrane and loculated ascites with multiple septa. Ultrasonographic examination can detect the thin membrane covering the small bowel loops in the early phase of the disease, therefore ultrasonography would be a helpful modality to diagnose SEP early.

  18. Detecting atrial fibrillation by deep convolutional neural networks.

    Science.gov (United States)

    Xia, Yong; Wulan, Naren; Wang, Kuanquan; Zhang, Henggui

    2018-02-01

    Atrial fibrillation (AF) is the most common cardiac arrhythmia. The incidence of AF increases with age, causing high risks of stroke and increased morbidity and mortality. Efficient and accurate diagnosis of AF based on the ECG is valuable in clinical settings and remains challenging. In this paper, we proposed a novel method with high reliability and accuracy for AF detection via deep learning. The short-term Fourier transform (STFT) and stationary wavelet transform (SWT) were used to analyze ECG segments to obtain two-dimensional (2-D) matrix input suitable for deep convolutional neural networks. Then, two different deep convolutional neural network models corresponding to STFT output and SWT output were developed. Our new method did not require detection of P or R peaks, nor feature designs for classification, in contrast to existing algorithms. Finally, the performances of the two models were evaluated and compared with those of existing algorithms. Our proposed method demonstrated favorable performances on ECG segments as short as 5 s. The deep convolutional neural network using input generated by STFT, presented a sensitivity of 98.34%, specificity of 98.24% and accuracy of 98.29%. For the deep convolutional neural network using input generated by SWT, a sensitivity of 98.79%, specificity of 97.87% and accuracy of 98.63% was achieved. The proposed method using deep convolutional neural networks shows high sensitivity, specificity and accuracy, and, therefore, is a valuable tool for AF detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

  19. An artifical neural network for detection of simulated dental caries

    Energy Technology Data Exchange (ETDEWEB)

    Kositbowornchai, S. [Khon Kaen Univ. (Thailand). Dept. of Oral Diagnosis; Siriteptawee, S.; Plermkamon, S.; Bureerat, S. [Khon Kaen Univ. (Thailand). Dept. of Mechanical Engineering; Chetchotsak, D. [Khon Kaen Univ. (Thailand). Dept. of Industrial Engineering

    2006-08-15

    Objects: A neural network was developed to diagnose artificial dental caries using images from a charged-coupled device (CCD)camera and intra-oral digital radiography. The diagnostic performance of this neural network was evaluated against a gold standard. Materials and methods: The neural network design was the Learning Vector Quantization (LVQ) used to classify a tooth surface as sound or as having dental caries. The depth of the dental caries was indicated on a graphic user interface (GUI) screen developed by Matlab programming. Forty-nine images of both sound and simulated dental caries, derived from a CCD camera and by digital radiography, were used to 'train' an artificial neural network. After the 'training' process, a separate test-set comprising 322 unseen images was evaluated. Tooth sections and microscopic examinations were used to confirm the actual dental caries status.The performance of neural network was evaluated using diagnostic test. Results: The sensitivity (95%CI)/specificity (95%CI) of dental caries detection by the CCD camera and digital radiography were 0.77(0.68-0.85)/0.85(0.75-0.92) and 0.81(0.72-0.88)/0.93(0.84-0.97), respectively. The accuracy of caries depth-detection by the CCD camera and digital radiography was 58 and 40%, respectively. Conclusions: The model neural network used in this study could be a prototype for caries detection but should be improved for classifying caries depth. Our study suggests an artificial neural network can be trained to make the correct interpretations of dental caries. (orig.)

  20. An artifical neural network for detection of simulated dental caries

    International Nuclear Information System (INIS)

    Kositbowornchai, S.; Siriteptawee, S.; Plermkamon, S.; Bureerat, S.; Chetchotsak, D.

    2006-01-01

    Objects: A neural network was developed to diagnose artificial dental caries using images from a charged-coupled device (CCD)camera and intra-oral digital radiography. The diagnostic performance of this neural network was evaluated against a gold standard. Materials and methods: The neural network design was the Learning Vector Quantization (LVQ) used to classify a tooth surface as sound or as having dental caries. The depth of the dental caries was indicated on a graphic user interface (GUI) screen developed by Matlab programming. Forty-nine images of both sound and simulated dental caries, derived from a CCD camera and by digital radiography, were used to 'train' an artificial neural network. After the 'training' process, a separate test-set comprising 322 unseen images was evaluated. Tooth sections and microscopic examinations were used to confirm the actual dental caries status.The performance of neural network was evaluated using diagnostic test. Results: The sensitivity (95%CI)/specificity (95%CI) of dental caries detection by the CCD camera and digital radiography were 0.77(0.68-0.85)/0.85(0.75-0.92) and 0.81(0.72-0.88)/0.93(0.84-0.97), respectively. The accuracy of caries depth-detection by the CCD camera and digital radiography was 58 and 40%, respectively. Conclusions: The model neural network used in this study could be a prototype for caries detection but should be improved for classifying caries depth. Our study suggests an artificial neural network can be trained to make the correct interpretations of dental caries. (orig.)

  1. Paternal psychological response after ultrasonographic detection of structural fetal anomalies with a comparison to maternal response: a cohort study.

    Science.gov (United States)

    Kaasen, Anne; Helbig, Anne; Malt, Ulrik Fredrik; Naes, Tormod; Skari, Hans; Haugen, Guttorm Nils

    2013-07-12

    In Norway almost all pregnant women attend one routine ultrasound examination. Detection of fetal structural anomalies triggers psychological stress responses in the women affected. Despite the frequent use of ultrasound examination in pregnancy, little attention has been devoted to the psychological response of the expectant father following the detection of fetal anomalies. This is important for later fatherhood and the psychological interaction within the couple. We aimed to describe paternal psychological responses shortly after detection of structural fetal anomalies by ultrasonography, and to compare paternal and maternal responses within the same couple. A prospective observational study was performed at a tertiary referral centre for fetal medicine. Pregnant women with a structural fetal anomaly detected by ultrasound and their partners (study group,n=155) and 100 with normal ultrasound findings (comparison group) were included shortly after sonographic examination (inclusion period: May 2006-February 2009). Gestational age was >12 weeks. We used psychometric questionnaires to assess self-reported social dysfunction, health perception, and psychological distress (intrusion, avoidance, arousal, anxiety, and depression): Impact of Event Scale. General Health Questionnaire and Edinburgh Postnatal Depression Scale. Fetal anomalies were classified according to severity and diagnostic or prognostic ambiguity at the time of assessment. Median (range) gestational age at inclusion in the study and comparison group was 19 (12-38) and 19 (13-22) weeks, respectively. Men and women in the study group had significantly higher levels of psychological distress than men and women in the comparison group on all psychometric endpoints. The lowest level of distress in the study group was associated with the least severe anomalies with no diagnostic or prognostic ambiguity (p < 0.033). Men had lower scores than women on all psychometric outcome variables. The correlation in

  2. Acoustic leak detection at complicated topologies using neural netwoks

    International Nuclear Information System (INIS)

    Hessel, G.; Schmitt, W.; Weiss, F.P.

    1994-01-01

    Considering the shortcomings of all the existing leak detecting principles, a new method again based on the measurement of the leak induced sound but also applying pattern recognition is being developed. The capability of neural networks to localize leaks at the reactor pressure vessel (RPV) head of VVER-440 reactors is discussed. (orig./DG)

  3. Deep convolutional neural networks for detection of rail surface defects

    NARCIS (Netherlands)

    Faghih Roohi, S.; Hajizadeh, S.; Nunez Vicencio, Alfredo; Babuska, R.; De Schutter, B.H.K.; Estevez, Pablo A.; Angelov, Plamen P.; Del Moral Hernandez, Emilio

    2016-01-01

    In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and

  4. Image objects detection based on boosting neural network

    NARCIS (Netherlands)

    Liang, N.; Hegt, J.A.; Mladenov, V.M.

    2010-01-01

    This paper discusses the problem of object area detection of video frames. The goal is to design a pixel accurate detector for grass, which could be used for object adaptive video enhancement. A boosting neural network is used for creating such a detector. The resulted detector uses both textural

  5. Carotid artery ultrasonographic assessment in patients from the Fremantle Diabetes Study Phase II with carotid bruits detected by electronic auscultation.

    Science.gov (United States)

    Knapp, Arthur; Cetrullo, Violetta; Sillars, Brett A; Lenzo, Nat; Davis, Wendy A; Davis, Timothy M E

    2014-09-01

    Electronic auscultation appears superior to acoustic auscultation for identifying hemodynamic abnormalities. The aim of this study was to determine whether carotid bruits detected by electronic stethoscope in patients with diabetes are associated with stenoses and increased carotid intima-medial thickness (CIMT). Fifty Fremantle Diabetes Study patients (mean±SD age, 73.7±10.0 years; 38.0% males) with a bruit found by electronic auscultation and 50 age- and sex-matched patients with normal carotid sounds were studied. The degree of stenosis and CIMT were assessed from duplex ultrasonography. Patients with a bruit were more likely to have stenosis of ≥50% and CIMT of >1.0 mm than those without (odds ratios [95% confidence intervals]=14.0 [1.8-106.5] and 5.3 [1.8-15.3], respectively; both P=0.001). For the six patients with stenosis of ≥70%, five had a bruit, and one (with a known total occlusion) did not (odds ratio=5.0 [0.6-42.8]; P=0.22). The sensitivity and specificity of carotid bruit for stenoses of ≥50% were 88% and 58%, respectively; respective values for stenoses of ≥70% were 83% and 52%. The equivalent negative predictive values were 96% and 98%, and positive predictive values were 30% and 10%, respectively. Electronic recording of carotid sounds for later interpretation is convenient and reliable. Most patients with stenoses had an overlying bruit. Most bruits were false positives, but ultrasonography is justified to document extent of disease; CIMT measurement will identify increased vascular risk in most of these patients. The absence of a bruit was rarely a false-negative finding, suggesting that these patients can usually be reassured that they do not have hemodynamically important stenosis.

  6. VoIP attacks detection engine based on neural network

    Science.gov (United States)

    Safarik, Jakub; Slachta, Jiri

    2015-05-01

    The security is crucial for any system nowadays, especially communications. One of the most successful protocols in the field of communication over IP networks is Session Initiation Protocol. It is an open-source project used by different kinds of applications, both open-source and proprietary. High penetration and text-based principle made SIP number one target in IP telephony infrastructure, so security of SIP server is essential. To keep up with hackers and to detect potential malicious attacks, security administrator needs to monitor and evaluate SIP traffic in the network. But monitoring and following evaluation could easily overwhelm the security administrator in networks, typically in networks with a number of SIP servers, users and logically or geographically separated networks. The proposed solution lies in automatic attack detection systems. The article covers detection of VoIP attacks through a distributed network of nodes. Then the gathered data analyze aggregation server with artificial neural network. Artificial neural network means multilayer perceptron network trained with a set of collected attacks. Attack data could also be preprocessed and verified with a self-organizing map. The source data is detected by distributed network of detection nodes. Each node contains a honeypot application and traffic monitoring mechanism. Aggregation of data from each node creates an input for neural networks. The automatic classification on a centralized server with low false positive detection reduce the cost of attack detection resources. The detection system uses modular design for easy deployment in final infrastructure. The centralized server collects and process detected traffic. It also maintains all detection nodes.

  7. Abnormality Detection in Mammography using Deep Convolutional Neural Networks

    OpenAIRE

    Xi, Pengcheng; Shu, Chang; Goubran, Rafik

    2018-01-01

    Breast cancer is the most common cancer in women worldwide. The most common screening technology is mammography. To reduce the cost and workload of radiologists, we propose a computer aided detection approach for classifying and localizing calcifications and masses in mammogram images. To improve on conventional approaches, we apply deep convolutional neural networks (CNN) for automatic feature learning and classifier building. In computer-aided mammography, deep CNN classifiers cannot be tra...

  8. ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT

    Directory of Open Access Journals (Sweden)

    A. Barsi

    2012-07-01

    Full Text Available In the urban object detection challenge organized by the ISPRS WG III/4 high geometric and radiometric resolution aerial images about Vaihingen/Stuttgart, Germany are distributed. The acquired data set contains optical false color, near infrared images and airborne laserscanning data. The presented research focused exclusively on the optical image, so the elevation information was ignored. The road detection procedure has been built up of two main phases: a segmentation done by neural networks and a compilation made by genetic algorithms. The applied neural networks were support vector machines with radial basis kernel function and self-organizing maps with hexagonal network topology and Euclidean distance function for neighborhood management. The neural techniques have been compared by hyperbox classifier, known from the statistical image classification practice. The compilation of the segmentation is realized by a novel application of the common genetic algorithm and by differential evolution technique. The genes were implemented to detect the road elements by evaluating a special binary fitness function. The results have proven that the evolutional technique can automatically find major road segments.

  9. Ultrasonographic findings of gynecomastia

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Ji Hyung; Oh, Ki Keun; Yoon, Choon Sik; Park, Chang Yun [Yongdong Severance Hospital, Seoul (Korea, Republic of)

    1993-12-15

    The purposes of our study were to find out characteristic ultrasonographic findings of gynecomastia and to analyze age distribution, causative factors of gynecomastia. For these purposes, medical records of 39 male patients with gynecomastia were reviewed and sonographic findings of 13 cases of gentamycin were analyzed. Gynecomastia was found most commonly in teenagers and commonly in twenties. Almostly, it occurred without any evident etiology and classified as idiopathic or pirbuterol type. Less frequently, it occurred due to drug administration, systemic disease, or male hormone deficiency. Unilateral involvement was seen in 29 cases; 17cases involving the left and 12 cases the right. Bilateral involvement was seen in 10 cases. Sonographically,gynecomastia appeared as hypoechoic or intermediate echoic mass with various shape in the subareolar area. One case showed diffuse fatty breast pattern without definable mass. On sonographic evaluation, prominent nipple should not be misinterpreted as a breast mass. For the correct diagnosis of gynecomastia, both side breasts should be evaluated for comparison

  10. Salient regions detection using convolutional neural networks and color volume

    Science.gov (United States)

    Liu, Guang-Hai; Hou, Yingkun

    2018-03-01

    Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

  11. Ultrasonographic findings of breast lesions

    International Nuclear Information System (INIS)

    Hwang, In Sung; Kim, Yang Soo; Suh, Hyoung Sim

    1990-01-01

    Authors retrospectively analyzed ultrasonographic findings of 61 cases of breast lesions which were proven pathologically at Daerim St. Mary's Hospital from May 1987 to February 1990. The results were as follows : 1. Of all 61 cases, there were 27 fibroadenomas, 13 fibrocystic diseases, 11 carcinomas, 8 abscesses, 1 sclerosing adenosis, and 1 intraductal papilloma. 2. Findings suggesting benignancy were smooth contour, round or oval shape, homogeneously echolucent internal echo, echogenic boundary echo, and posterior enhancement. In the cases of abscess, the findings were rather irregular contour, strong posterior enhancement, and dirty, inhomogeneous internal echo. While irregular and lobulated shape, inhomogeneous and mixed internal echo and pectoral muscle invasion were suggested for malignancy. 3. The sensitivity was 98% and the specificity 58% in benign mass excluding abscesses, 63% and 98% in abscesses, and 55% and 98% in carcinomas. In conclusion, ultrasonography is one of the excellent imaging modality for detecting breast lesions larger than 5 mm in size, but unfortunately some of the malignant tumors simulated benignancy, thus we considered fine needle aspiration biopsy and adjunctive imaging modalities such as film mammography must be followed for better detection of breast cancer

  12. Ultrasonographic findings of breast lesions

    Energy Technology Data Exchange (ETDEWEB)

    Hwang, In Sung; Kim, Yang Soo; Suh, Hyoung Sim [College of Medicine, Daerim St. Mary' s Hospital, Seoul (Korea, Republic of)

    1990-07-15

    Authors retrospectively analyzed ultrasonographic findings of 61 cases of breast lesions which were proven pathologically at Daerim St. Mary's Hospital from May 1987 to February 1990. The results were as follows : 1. Of all 61 cases, there were 27 fibroadenomas, 13 fibrocystic diseases, 11 carcinomas, 8 abscesses, 1 sclerosing adenosis, and 1 intraductal papilloma. 2. Findings suggesting benignancy were smooth contour, round or oval shape, homogeneously echolucent internal echo, echogenic boundary echo, and posterior enhancement. In the cases of abscess, the findings were rather irregular contour, strong posterior enhancement, and dirty, inhomogeneous internal echo. While irregular and lobulated shape, inhomogeneous and mixed internal echo and pectoral muscle invasion were suggested for malignancy. 3. The sensitivity was 98% and the specificity 58% in benign mass excluding abscesses, 63% and 98% in abscesses, and 55% and 98% in carcinomas. In conclusion, ultrasonography is one of the excellent imaging modality for detecting breast lesions larger than 5 mm in size, but unfortunately some of the malignant tumors simulated benignancy, thus we considered fine needle aspiration biopsy and adjunctive imaging modalities such as film mammography must be followed for better detection of breast cancer.

  13. Breast ultrasonographic and histopathological characteristics without any mammographic abnormalities

    International Nuclear Information System (INIS)

    Tamaki, Kentaro; Kamada, Yoshihiko; Uehara, Kano; Tamaki, Nobumitsu; Ishida, Takanori; Miyashita, Minoru; Amari, Masakazu; Ohuchi, Noriaki; Sasano, Hironobu

    2012-01-01

    We evaluated ultrasonographic findings and the corresponding histopathological characteristics of breast cancer patients with Breast Imaging Reporting and Data System (BI-RADS) category 1 mammogram. We retrospectively reviewed the ultrasonographic findings and the corresponding histopathological features of 45 breast cancer patients with BI-RADS category 1 mammogram and 537 controls with mammographic abnormalities. We evaluated the ultrasonographic findings including mass shape, periphery, internal and posterior echo pattern, interruption of mammary borders and the distribution of low-echoic lesions, and the corresponding histopathological characteristics including histological classification, hormone receptor and human epidermal growth factor receptor 2 status of invasive ductal carcinoma and ductal carcinoma in situ, histological grade, mitotic counts and lymphovascular invasion in individual cases of BI-RADS category 1 mammograms and compared with those of the control group. The ultrasonographic characteristics of the BI-RADS category 1 group were characterized by a higher ratio of round shape (P<0.001), non-spiculated periphery (P=0.021), non-interruption of mammary borders (P<0.001) and non-attenuation (P=0.011) compared with the control group. A total of 52.6% of low-echoic lesions were associated with spotted distribution in the BI-RADS 1 group, whereas 25.8% of low-echoic lesions were associated with spotted distribution in the control group (P=0.012). As for histopathological characteristics, there was a statistically higher ratio of triple-negative subtype (P=0.021), and this particular tendency was detected in histological grade 3 in the BI-RADS category 1 group (P=0.094). We evaluated ultrasonographic findings and the corresponding histopathological characteristics for BI-RADS category 1 mammograms and noted significant differences among these findings in this study. Evaluation of these ultrasonographic and histopathological characteristics may provide

  14. ID card number detection algorithm based on convolutional neural network

    Science.gov (United States)

    Zhu, Jian; Ma, Hanjie; Feng, Jie; Dai, Leiyan

    2018-04-01

    In this paper, a new detection algorithm based on Convolutional Neural Network is presented in order to realize the fast and convenient ID information extraction in multiple scenarios. The algorithm uses the mobile device equipped with Android operating system to locate and extract the ID number; Use the special color distribution of the ID card, select the appropriate channel component; Use the image threshold segmentation, noise processing and morphological processing to take the binary processing for image; At the same time, the image rotation and projection method are used for horizontal correction when image was tilting; Finally, the single character is extracted by the projection method, and recognized by using Convolutional Neural Network. Through test shows that, A single ID number image from the extraction to the identification time is about 80ms, the accuracy rate is about 99%, It can be applied to the actual production and living environment.

  15. Breast nodules detection in images of ultrasonographic and mammographic simulators; Deteccao de nodulos mamarios em imagens de simuladores ultrassonografico e mamografico

    Energy Technology Data Exchange (ETDEWEB)

    Marcomini, Karem D.; Schiabel, Homero, E-mail: karem.dm@usp.br [Universidade de Sao Paulo (USP), Sao Carlos, SP (Brazil). Escola de Engenharia. Dept. de Engenharia Eletrica; Carneiro, Antonio Adilton O. [Universidade de Sao Paulo (USP), Ribeirao Preto, SP (Brazil). Faculdade de Filosofia, Ciencias e Letras. Dept. de Fisica

    2013-08-15

    Due to the high incidence rate of breast cancer in women, many procedures have been developed to assist in the diagnosis and early detection. Mammography and ultrasonography stand out as the main breast imaging techniques. In this context, the schemes of computer-aided diagnosis have provided to the specialist a more accurate and reliable second opinion by minimizing the visual subjectivity inter-observer. Thus, we propose the application of an automated method of segmentation, through the neural network SOM, to provide accurate information regarding the border of the lesion. The tests were employed in 100 mammographic images and 70 sonographic, both cases obtained by simulation. In order to verify the accuracy of the boundaries demarcated by the automatic detector, quantitative measurements were extracted to compare these images with the manually delineated by an experienced radiologist. The proposed technique presented high accuracy and sensitivity, and low error rate in correctly representing the mammographic and sonographic findings. (author)

  16. Ultrasonographic examination in chest disease

    Energy Technology Data Exchange (ETDEWEB)

    Choe, K.O.; Lee, J.D.; Yoo, H.S. [Yonsei University College of Medicine, Seoul (Korea, Republic of)

    1983-12-15

    Ultrasonographic examination is not widely applied to chest disease, but is may give useful information when the acoustic window for a lesion exist. We did perform ultrasound examination in 68 cases of chest disease. 1. The cases of pleural diseases was predominant; pleural effusion 35 cases, pleural metastatic tumor 2 case, mesothelioma 2 cases and fibrous thickening 1 case, total 40 cases. It was useful to differentiate pleural effusion and fibrous thickening or parenchymal lesion simulating pleural disease, to localize the optimal aspiration site for a loculated empyema, to detect pleural bumorhidden by effusion such as metastatic tumor or mesothelioma. 2. 15 cases of parenchymal lesion and 2 cases of extra pleural mass was examined. The echo pattern of consolidation and atelectasis shows typical multiple tubular streaks within the echogenic area. The echogenicity of the peripheral mass due to primary bronchogenic carcinoma, parenchymal or extrapleural metastatic tumor and granuloma were compared. 3. In the cases of pleural or parenchymal cystic lesions, such as loculated empyema or lung abscess, because of strong reverberation artifact from posterior border of the lesion, the prediction of cystic and solid lesion is sometimes difficult. 4. In 7 cases of mediastinal lesion, cystic lesion show free echo and posterior enhancement. In contrast, solid or fat component show characteristic echo pattern. 5. In the cases of juxta diaphragmatic lesion, sonogram can confirm the underlying intraabdominal pathology, in this case subphrenic abscess

  17. Ultrasonographic examination in chest disease

    International Nuclear Information System (INIS)

    Choe, K.O.; Lee, J.D.; Yoo, H.S.

    1983-01-01

    Ultrasonographic examination is not widely applied to chest disease, but is may give useful information when the acoustic window for a lesion exist. We did perform ultrasound examination in 68 cases of chest disease. 1. The cases of pleural diseases was predominant; pleural effusion 35 cases, pleural metastatic tumor 2 case, mesothelioma 2 cases and fibrous thickening 1 case, total 40 cases. It was useful to differentiate pleural effusion and fibrous thickening or parenchymal lesion simulating pleural disease, to localize the optimal aspiration site for a loculated empyema, to detect pleural bumorhidden by effusion such as metastatic tumor or mesothelioma. 2. 15 cases of parenchymal lesion and 2 cases of extra pleural mass was examined. The echo pattern of consolidation and atelectasis shows typical multiple tubular streaks within the echogenic area. The echogenicity of the peripheral mass due to primary bronchogenic carcinoma, parenchymal or extrapleural metastatic tumor and granuloma were compared. 3. In the cases of pleural or parenchymal cystic lesions, such as loculated empyema or lung abscess, because of strong reverberation artifact from posterior border of the lesion, the prediction of cystic and solid lesion is sometimes difficult. 4. In 7 cases of mediastinal lesion, cystic lesion show free echo and posterior enhancement. In contrast, solid or fat component show characteristic echo pattern. 5. In the cases of juxta diaphragmatic lesion, sonogram can confirm the underlying intraabdominal pathology, in this case subphrenic abscess

  18. CONEDEP: COnvolutional Neural network based Earthquake DEtection and Phase Picking

    Science.gov (United States)

    Zhou, Y.; Huang, Y.; Yue, H.; Zhou, S.; An, S.; Yun, N.

    2017-12-01

    We developed an automatic local earthquake detection and phase picking algorithm based on Fully Convolutional Neural network (FCN). The FCN algorithm detects and segments certain features (phases) in 3 component seismograms to realize efficient picking. We use STA/LTA algorithm and template matching algorithm to construct the training set from seismograms recorded 1 month before and after the Wenchuan earthquake. Precise P and S phases are identified and labeled to construct the training set. Noise data are produced by combining back-ground noise and artificial synthetic noise to form the equivalent scale of noise set as the signal set. Training is performed on GPUs to achieve efficient convergence. Our algorithm has significantly improved performance in terms of the detection rate and precision in comparison with STA/LTA and template matching algorithms.

  19. Ultrasonographic findings of intestinal intussusception in seven cats.

    Science.gov (United States)

    Patsikas, M N; Papazoglou, L G; Papaioannou, N G; Savvas, I; Kazakos, G M; Dessiris, A K

    2003-12-01

    The medical records of seven cats with intestinal intussusception that were diagnosed by abdominal ultrasonography and exploratory laparotomy were reviewed. In transverse ultrasonographic sections the intussusception appeared as a target-like mass consisting of one, two or more hyperechoic and hypoechoic concentric rings surrounding a C-shaped, circular or non-specific shaped hyperechoic centre. Part of the intestine representing the inner intussusceptum, located close to the hyperechoic centre and surrounded by concentric rings, was also detected. In longitudinal sections the intussusception appeared as multiple hyperechoic and hypoechoic parallel lines in four cases and as an ovoid mass in three cases. In one case the ovoid mass had a 'kidney' configuration. Additional ultrasonographic findings associated with intestinal intussusception included an intestinal neoplasm in one cat. The results of the present study demonstrate that the ultrasonographic findings of intestinal intussusception in cats bear some similarities to those described in dogs and humans, are relatively consistent, and facilitate a specific diagnosis.

  20. Molecular Ultrasound Imaging for the Detection of Neural Inflammation

    Science.gov (United States)

    Volz, Kevin R.

    Molecular imaging is a form of nanotechnology that enables the noninvasive examination of biological processes in vivo. Radiopharmaceutical agents are used to selectively target biochemical markers, which permits their detection and evaluation. Early visualization of molecular variations indicative of pathophysiological processes can aid in patient diagnoses and management decisions. Molecular imaging is performed by introducing molecular probes into the body. Molecular probes are often contrast agents that have been nanoengineered to selectively target and tether to molecules, enabling their radiologic identification. Ultrasound contrast agents have been demonstrated as an effective method of detecting perfusion at the tissue level. Through a nanoengineering process, ultrasound contrast agents can be targeted to specific molecules, thereby extending ultrasound's capabilities from the tissue to molecular level. Molecular ultrasound, or targeted contrast enhanced ultrasound (TCEUS), has recently emerged as a popular molecular imaging technique due to its ability to provide real-time anatomical and functional information in the absence of ionizing radiation. However, molecular ultrasound represents a novel form of molecular imaging, and consequently remains largely preclinical. A review of the TCEUS literature revealed multiple preclinical studies demonstrating its success in detecting inflammation in a variety of tissues. Although, a gap was identified in the existing evidence, as TCEUS effectiveness for detection of neural inflammation in the spinal cord was unable to be uncovered. This gap in knowledge, coupled with the profound impacts that this TCEUS application could have clinically, provided rationale for its exploration, and use as contributory evidence for the molecular ultrasound body of literature. An animal model that underwent a contusive spinal cord injury was used to establish preclinical evidence of TCEUS to detect neural inflammation. Imaging was

  1. Tactile detection of slip: surface microgeometry and peripheral neural codes.

    Science.gov (United States)

    Srinivasan, M A; Whitehouse, J M; LaMotte, R H

    1990-06-01

    1. The role of the microgeometry of planar surfaces in the detection of sliding of the surfaces on human and monkey fingerpads was investigated. By the use of a servo-controlled tactile stimulator to press and stroke glass plates on passive fingerpads of human subjects, the ability of humans to discriminate the direction of skin stretch caused by friction and to detect the sliding motion (slip) of the plates with or without micrometer-sized surface features was determined. To identify the associated peripheral neural codes, evoked responses to the same stimuli were recorded from single, low-threshold mechanoreceptive afferent fibers innervating the fingerpads of anesthetized macaque monkeys. 2. Humans could not detect the slip of a smooth glass plate on the fingerpad. However, the direction of skin stretch was perceived based on the information conveyed by the slowly adapting afferents that respond differentially to the stretch directions. Whereas the direction of skin stretch signaled the direction of impending slip, the perception of relative motion between the plate and the finger required the existence of detectable surface features. 3. Barely detectable micrometer-sized protrusions on smooth surfaces led to the detection of slip of these surfaces, because of the exclusive activation of rapidly adapting fibers of either the Meissner (RA) or the Pacinian (PC) type to specific geometries of the microfeatures. The motion of a smooth plate with a very small single raised dot (4 microns high, 550 microns diam) caused the sequential activation of neighboring RAs along the dot path, thus providing a reliable spatiotemporal code. The stroking of the plate with a fine homogeneous texture composed of a matrix of dots (1 microns high, 50 microns diam, and spaced at 100 microns center-to-center) induced vibrations in the fingerpad that activated only the PCs and resulted in an intensive code. 4. The results show that surprisingly small features on smooth surfaces are

  2. Neural Network Based Intrusion Detection System for Critical Infrastructures

    Energy Technology Data Exchange (ETDEWEB)

    Todd Vollmer; Ondrej Linda; Milos Manic

    2009-07-01

    Resiliency and security in control systems such as SCADA and Nuclear plant’s in today’s world of hackers and malware are a relevant concern. Computer systems used within critical infrastructures to control physical functions are not immune to the threat of cyber attacks and may be potentially vulnerable. Tailoring an intrusion detection system to the specifics of critical infrastructures can significantly improve the security of such systems. The IDS-NNM – Intrusion Detection System using Neural Network based Modeling, is presented in this paper. The main contributions of this work are: 1) the use and analyses of real network data (data recorded from an existing critical infrastructure); 2) the development of a specific window based feature extraction technique; 3) the construction of training dataset using randomly generated intrusion vectors; 4) the use of a combination of two neural network learning algorithms – the Error-Back Propagation and Levenberg-Marquardt, for normal behavior modeling. The presented algorithm was evaluated on previously unseen network data. The IDS-NNM algorithm proved to be capable of capturing all intrusion attempts presented in the network communication while not generating any false alerts.

  3. Credit card fraud detection using neural network and geolocation

    Science.gov (United States)

    Gulati, Aman; Dubey, Prakash; MdFuzail, C.; Norman, Jasmine; Mangayarkarasi, R.

    2017-11-01

    The most acknowledged payment mode is credit card for both disconnected and online mediums in today's day and age. It facilitates cashless shopping everywhere in the world. It is the most widespread and reasonable approach with regards to web based shopping, paying bills, what's more, performing other related errands. Thus danger of fraud exchanges utilizing credit card has likewise been expanding. In the Current Fraud Detection framework, false exchange is recognized after the transaction is completed. As opposed to the current system, the proposed system presents a methodology which facilitates the detection of fraudulent exchanges while they are being processed, this is achieved by means of Behaviour and Locational Analysis(Neural Logic) which considers a cardholder's way of managing money and spending pattern. A deviation from such a pattern will then lead to the system classifying it as suspicious transaction and will then be handled accordingly.

  4. Cellular neural networks for motion estimation and obstacle detection

    Directory of Open Access Journals (Sweden)

    D. Feiden

    2003-01-01

    Full Text Available Obstacle detection is an important part of Video Processing because it is indispensable for a collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need a robust prediction of potential obstacles, like other vehicles or pedestrians. Most of the common approaches of obstacle detection so far use analytical and statistical methods like motion estimation or generation of maps. In the first part of this contribution a statistical algorithm for obstacle detection in monocular video sequences is presented. The proposed procedure is based on a motion estimation and a planar world model which is appropriate to traffic scenes. The different processing steps of the statistical procedure are a feature extraction, a subsequent displacement vector estimation and a robust estimation of the motion parameters. Since the proposed procedure is composed of several processing steps, the error propagation of the successive steps often leads to inaccurate results. In the second part of this contribution it is demonstrated, that the above mentioned problems can be efficiently overcome by using Cellular Neural Networks (CNN. It will be shown, that a direct obstacle detection algorithm can be easily performed, based only on CNN processing of the input images. Beside the enormous computing power of programmable CNN based devices, the proposed method is also very robust in comparison to the statistical method, because is shows much less sensibility to noisy inputs. Using the proposed approach of obstacle detection in planar worlds, a real time processing of large input images has been made possible.

  5. Ultrasonographic diagnosis of stomach cancer

    Energy Technology Data Exchange (ETDEWEB)

    Chung, Eun Chul; Jin, S I; Kim, J W [Seoul National University College of Medicine, Seoul (Korea, Republic of)

    1982-12-15

    The ultrasonographic features of stomach cancer were studied in 43 patients who were diagnosed by double contrast UGI study and endoscopy. Ultrasonographic study was performed immediately after UGI study and the findings were correlated with USI study. The authors observed infiltrative lesions causing thickening of gastric wall, which can be localized (16 of 31) or diffuse(15 of 31). 9 cases were exogastric masses, sonographic findings were not found in the lesions occupying the cardia (3 of 5) Ultrasonography is useful in demonstrating the extent of the tumor and the presence of metastasis elsewhere in the abdomen, facilitating tumor staging and evaluation of the response to therapy

  6. Posterior breast cancer: Mammographic and ultrasonographic features

    Directory of Open Access Journals (Sweden)

    Janković Ana

    2013-01-01

    Full Text Available Background/Aim. Posterior breast cancers are located in the prepectoral region of the breast. Owing to this distinctive anatomical localization, physical examination and mammographic or ultrasonographic evaluation can be difficult. The purpose of the study was to assess possibilities of diagnostic mammography and breast ultrasonography in detection and differentiation of posterior breast cancers. Methods. The study included 40 women with palpable, histopathological confirmed posterior breast cancer. Mammographic and ultrasonographic features were defined according to Breast Imaging Reporting and Data System (BI-RADS lexicon. Results. Based on standard two-view mammography 87.5%, of the cases were classified as BI-RADS 4 and 5 categories, while after additional mammographic views all the cases were defined as BIRADS 4 and 5 categories. Among 96 mammographic descriptors, the most frequent were: spiculated mass (24.0%, architectural distortion (16.7%, clustered microcalcifications (12.6% and focal asymmetric density (12.6%. The differentiation of the spiculated mass was significantly associated with the possibility to visualize the lesion at two-view mammography (p = 0.009, without the association with lesion diameter (p = 0.083 or histopathological type (p = 0.055. Mammographic signs of invasive lobular carcinoma were significantly different from other histopathological types (architectural distortion, p = 0.003; focal asymmetric density, p = 0.019; association of four or five subtle signs of malignancy, p = 0.006. All cancers were detectable by ultrasonography. Mass lesions were found in 82.0% of the cases. Among 153 ultrasonographic descriptors, the most frequent were: irregular mass (15.7%, lobulated mass (7.2%, abnormal color Doppler signals (20.3%, posterior acoustic attenuation (18.3%. Ultrasonographic BI-RADS 4 and 5 categories were defined in 72.5% of the cases, without a significant difference among various histopathological types (p = 0

  7. Ultrasonographic findings of retinoblastoma

    International Nuclear Information System (INIS)

    Chung, Sung Hoo; Kang, Ik Won; Park, Yang Hee; Kim, Chu Wan; Chi, Je Geun

    1982-01-01

    Retinoblastoma is the most common intraocular tumor in infants and young children which has relatively favorable prognosis with early diagnosis and adequate treatment, however, it can be lethal if the treatment is delayed or inadequate. Clinically, early diagnosis is often difficult because of minimal subjective and objective signs and symptoms, and the patients are usually too young to complain visual disturbance. When ophthalmoscopicexamination is impossible due to presence of opaue media in front of tumor mass as associated inflammatory reaction, hemorrhage, corneal opacity, retinal detachment, etc, ultrasonography is necessary for diagnosis of retinoblastoma. Authors analyzed ultrasonographic al findings with pathological correlation on 10 cases of confirmed retinoblastoma during the period of March 1981 to September1982 at the Seoul National University Hospital. In all cases, ultrasonography demonstrates intraocular masses and all of which are cystic type.Reflectivity of masses are higher than retroorbital fat tissue in 8 cases, and 7 cases show irregular internal echogenic texture. There is no correlation between reflexivity and internal echogenic texture with microscopic findings as rosette, pseudo rosette and micro cysts. Calcifications are demonstrated by ultrasonography as strong reflectiveness with posterior sonic shadowing in 9 cases and 9 of 10 cases are well correlated with calcifications in pathologic specimens. Anechoic cystic areas are shown in 9 cases, and 6 of 10 cases are well correlated with necrosis in pathologic specimen. In all cases, there is no attenuation of sound within tumor masses, and no demonstrable choroidal excavation. Associated retinal detachment is hardly identifiable in irregular contour and internal texture of cystic tumor masses

  8. A Decline in Response Variability Improves Neural Signal Detection during Auditory Task Performance.

    Science.gov (United States)

    von Trapp, Gardiner; Buran, Bradley N; Sen, Kamal; Semple, Malcolm N; Sanes, Dan H

    2016-10-26

    The detection of a sensory stimulus arises from a significant change in neural activity, but a sensory neuron's response is rarely identical to successive presentations of the same stimulus. Large trial-to-trial variability would limit the central nervous system's ability to reliably detect a stimulus, presumably affecting perceptual performance. However, if response variability were to decrease while firing rate remained constant, then neural sensitivity could improve. Here, we asked whether engagement in an auditory detection task can modulate response variability, thereby increasing neural sensitivity. We recorded telemetrically from the core auditory cortex of gerbils, both while they engaged in an amplitude-modulation detection task and while they sat quietly listening to the identical stimuli. Using a signal detection theory framework, we found that neural sensitivity was improved during task performance, and this improvement was closely associated with a decrease in response variability. Moreover, units with the greatest change in response variability had absolute neural thresholds most closely aligned with simultaneously measured perceptual thresholds. Our findings suggest that the limitations imposed by response variability diminish during task performance, thereby improving the sensitivity of neural encoding and potentially leading to better perceptual sensitivity. The detection of a sensory stimulus arises from a significant change in neural activity. However, trial-to-trial variability of the neural response may limit perceptual performance. If the neural response to a stimulus is quite variable, then the response on a given trial could be confused with the pattern of neural activity generated when the stimulus is absent. Therefore, a neural mechanism that served to reduce response variability would allow for better stimulus detection. By recording from the cortex of freely moving animals engaged in an auditory detection task, we found that variability

  9. Ultrasonographic and CT findings of hepatosplenic tuberculosis

    International Nuclear Information System (INIS)

    Moon, Un Hyeon; Lee, Jeong Seok; Ko, Kang Seok; Park, Byung Ran; Yang, Dong Cheol; Im, Ju Hyeon; Kang, In Young

    1998-01-01

    To evaluate the ultrasonographic and CT findings of hepatosplenic tuberculosis Materials and Methods: We retrospectively reviewed the ultrasonographic and CT findings of confirmed hepatosplenic tuberculosis in 12 patients. Six were men and six were women ; their average age was 41, and most were in their twenties. Lesions of the liver and spleen, as well as associated findings such as abdominal tuberculosis and other organ involvement of tuberculosis were analyzed. Results : There were three cases of hepatic tuberculosis, seven of splenic tuberculosis, and two of hepatosplenic involvement of tuberculosis. On the basis of the ultrasonographic and CT findings, hepatosplenic tuberculosis was classified as one of two patterns : miliary or micronodular, ormacronodular. The micronodular type was more common (9/12 cases) being characterized by innumerable micronodules,and with easy coalescence in the liver and spleen in five of the nine cases. The macronodular type of low density mass was noted in the other three patients. Splenomegaly was noted in 12 cases and hepatomegaly in ten. Pulmonary tuberculosis-including the miliary type(n=5)-was noted in eight patients. Associated abdominal tuberculosis such as lymphadenopathy with central low density and peripheral rim enhancement (n=6), tuberculous peritonitis(n=3),highly attenuated ascites(n=6), adrenal tuberculosis(n=1), renal tuberculosis(n=1), ovarian abscess(n=1), psoasabscess(n=1), and systemic tuberculosis such as central nervous system tuberculoma(n=2), cervical lymphadenopathy(n=4) and tuberculous spondylitis(n=1) were noted. Conclusion : Ultrasonography and CT were valuable in the detection and diagnosis of hepatosplenic tuberculosis

  10. Ultrasonographic and CT findings of hepatosplenic tuberculosis

    Energy Technology Data Exchange (ETDEWEB)

    Moon, Un Hyeon; Lee, Jeong Seok; Ko, Kang Seok; Park, Byung Ran; Yang, Dong Cheol; Im, Ju Hyeon [Kwangju Christian Hospital, Kwangju (Korea, Republic of); Kang, In Young [Kwangju Green Cross Hospital, Kwangju (Korea, Republic of)

    1998-08-01

    To evaluate the ultrasonographic and CT findings of hepatosplenic tuberculosis Materials and Methods: We retrospectively reviewed the ultrasonographic and CT findings of confirmed hepatosplenic tuberculosis in 12 patients. Six were men and six were women ; their average age was 41, and most were in their twenties. Lesions of the liver and spleen, as well as associated findings such as abdominal tuberculosis and other organ involvement of tuberculosis were analyzed. Results : There were three cases of hepatic tuberculosis, seven of splenic tuberculosis, and two of hepatosplenic involvement of tuberculosis. On the basis of the ultrasonographic and CT findings, hepatosplenic tuberculosis was classified as one of two patterns : miliary or micronodular, ormacronodular. The micronodular type was more common (9/12 cases) being characterized by innumerable micronodules,and with easy coalescence in the liver and spleen in five of the nine cases. The macronodular type of low density mass was noted in the other three patients. Splenomegaly was noted in 12 cases and hepatomegaly in ten. Pulmonary tuberculosis-including the miliary type(n=5)-was noted in eight patients. Associated abdominal tuberculosis such as lymphadenopathy with central low density and peripheral rim enhancement (n=6), tuberculous peritonitis(n=3),highly attenuated ascites(n=6), adrenal tuberculosis(n=1), renal tuberculosis(n=1), ovarian abscess(n=1), psoasabscess(n=1), and systemic tuberculosis such as central nervous system tuberculoma(n=2), cervical lymphadenopathy(n=4) and tuberculous spondylitis(n=1) were noted. Conclusion : Ultrasonography and CT were valuable in the detection and diagnosis of hepatosplenic tuberculosis.

  11. Convolution neural-network-based detection of lung structures

    Science.gov (United States)

    Hasegawa, Akira; Lo, Shih-Chung B.; Freedman, Matthew T.; Mun, Seong K.

    1994-05-01

    Chest radiography is one of the most primary and widely used techniques in diagnostic imaging. Nowadays with the advent of digital radiology, the digital medical image processing techniques for digital chest radiographs have attracted considerable attention, and several studies on the computer-aided diagnosis (CADx) as well as on the conventional image processing techniques for chest radiographs have been reported. In the automatic diagnostic process for chest radiographs, it is important to outline the areas of the lungs, the heart, and the diaphragm. This is because the original chest radiograph is composed of important anatomic structures and, without knowing exact positions of the organs, the automatic diagnosis may result in unexpected detections. The automatic extraction of an anatomical structure from digital chest radiographs can be a useful tool for (1) the evaluation of heart size, (2) automatic detection of interstitial lung diseases, (3) automatic detection of lung nodules, and (4) data compression, etc. Based on the clearly defined boundaries of heart area, rib spaces, rib positions, and rib cage extracted, one should be able to use this information to facilitate the tasks of the CADx on chest radiographs. In this paper, we present an automatic scheme for the detection of lung field from chest radiographs by using a shift-invariant convolution neural network. A novel algorithm for smoothing boundaries of lungs is also presented.

  12. Convolutional neural network features based change detection in satellite images

    Science.gov (United States)

    Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

    2016-07-01

    With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

  13. Automated embolic signal detection using Deep Convolutional Neural Network.

    Science.gov (United States)

    Sombune, Praotasna; Phienphanich, Phongphan; Phuechpanpaisal, Sutanya; Muengtaweepongsa, Sombat; Ruamthanthong, Anuchit; Tantibundhit, Charturong

    2017-07-01

    This work investigated the potential of Deep Neural Network in detection of cerebral embolic signal (ES) from transcranial Doppler ultrasound (TCD). The resulting system is aimed to couple with TCD devices in diagnosing a risk of stroke in real-time with high accuracy. The Adaptive Gain Control (AGC) approach developed in our previous study is employed to capture suspected ESs in real-time. By using spectrograms of the same TCD signal dataset as that of our previous work as inputs and the same experimental setup, Deep Convolutional Neural Network (CNN), which can learn features while training, was investigated for its ability to bypass the traditional handcrafted feature extraction and selection process. Extracted feature vectors from the suspected ESs are later determined whether they are of an ES, artifact (AF) or normal (NR) interval. The effectiveness of the developed system was evaluated over 19 subjects going under procedures generating emboli. The CNN-based system could achieve in average of 83.0% sensitivity, 80.1% specificity, and 81.4% accuracy, with considerably much less time consumption in development. The certainly growing set of training samples and computational resources will contribute to high performance. Besides having potential use in various clinical ES monitoring settings, continuation of this promising study will benefit developments of wearable applications by leveraging learnable features to serve demographic differentials.

  14. Power plant fault detection using artificial neural network

    Science.gov (United States)

    Thanakodi, Suresh; Nazar, Nazatul Shiema Moh; Joini, Nur Fazriana; Hidzir, Hidzrin Dayana Mohd; Awira, Mohammad Zulfikar Khairul

    2018-02-01

    The fault that commonly occurs in power plants is due to various factors that affect the system outage. There are many types of faults in power plants such as single line to ground fault, double line to ground fault, and line to line fault. The primary aim of this paper is to diagnose the fault in 14 buses power plants by using an Artificial Neural Network (ANN). The Multilayered Perceptron Network (MLP) that detection trained utilized the offline training methods such as Gradient Descent Backpropagation (GDBP), Levenberg-Marquardt (LM), and Bayesian Regularization (BR). The best method is used to build the Graphical User Interface (GUI). The modelling of 14 buses power plant, network training, and GUI used the MATLAB software.

  15. Ultrasonographic and mammographic findings of gynecomastia

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Soo Kyung; Choi, Gyo Chang; Hong, Hyun Sook; Kim, Young Beom; Lee, Hae Kyung; Kwon, Kui Hyang [Soonchunhyang Univ. College of Medicine, Asan (Korea, Republic of)

    1996-11-01

    The purpose of this study is to evaluate the radiologic features and clinical utility of ultrasonography and mammography in cases of gynecomastia. This study involved 40 men in whom gynecomastia had been pathologically diagnosed by surgical incision. In 21 cases, a retrospective analysis of ultrasonographic and mammographic findings was performed. Causative factors of gynecomastia among the 40 pathologically-proven cases were idiopathic or pubertal in 33 cases, related to male hormone deficiency in three cases and to chronic liver disease in four. Bi-lateral involvement was seen in 14 cases, and unilateral involvement in 26;among unilateral cases, right side was involved in 10 cases, and the left side in 16. Mammographically, a subareolar discoid lesion was present in 12 cases, diffuse increased breast density was seen in five cases and dendritic marginated subareolar lesion without microcalcification in one. Ultrasonographically, a round smooth marginated low echogenic lesion in the subareolar region was seen in five cases, a diffuse hyperechogenic pattern without definite mass in two cases and an ill defined low echogenic lesion in one. The male breast is small, so in cases of gynecomastia, ultrasonography is an effective diagnostic modality. Mamography will, however, be helpful in the detection of microcalcification in cases of gynecomastia seen on sonography.

  16. Pneumothorax detection in chest radiographs using convolutional neural networks

    Science.gov (United States)

    Blumenfeld, Aviel; Konen, Eli; Greenspan, Hayit

    2018-02-01

    This study presents a computer assisted diagnosis system for the detection of pneumothorax (PTX) in chest radiographs based on a convolutional neural network (CNN) for pixel classification. Using a pixel classification approach allows utilization of the texture information in the local environment of each pixel while training a CNN model on millions of training patches extracted from a relatively small dataset. The proposed system uses a pre-processing step of lung field segmentation to overcome the large variability in the input images coming from a variety of imaging sources and protocols. Using a CNN classification, suspected pixel candidates are extracted within each lung segment. A postprocessing step follows to remove non-physiological suspected regions and noisy connected components. The overall percentage of suspected PTX area was used as a robust global decision for the presence of PTX in each lung. The system was trained on a set of 117 chest x-ray images with ground truth segmentations of the PTX regions. The system was tested on a set of 86 images and reached diagnosis accuracy of AUC=0.95. Overall preliminary results are promising and indicate the growing ability of CAD based systems to detect findings in medical imaging on a clinical level accuracy.

  17. Vision-Based Fall Detection with Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Adrián Núñez-Marcos

    2017-01-01

    Full Text Available One of the biggest challenges in modern societies is the improvement of healthy aging and the support to older persons in their daily activities. In particular, given its social and economic impact, the automatic detection of falls has attracted considerable attention in the computer vision and pattern recognition communities. Although the approaches based on wearable sensors have provided high detection rates, some of the potential users are reluctant to wear them and thus their use is not yet normalized. As a consequence, alternative approaches such as vision-based methods have emerged. We firmly believe that the irruption of the Smart Environments and the Internet of Things paradigms, together with the increasing number of cameras in our daily environment, forms an optimal context for vision-based systems. Consequently, here we propose a vision-based solution using Convolutional Neural Networks to decide if a sequence of frames contains a person falling. To model the video motion and make the system scenario independent, we use optical flow images as input to the networks followed by a novel three-step training phase. Furthermore, our method is evaluated in three public datasets achieving the state-of-the-art results in all three of them.

  18. Fetal musculoskeletal malformations with a poor outcome: ultrasonographic, pathologic, and radiographic findings

    International Nuclear Information System (INIS)

    Lee, Soo Hyun; Cho, Jeong Yeon; Song, Mi Jin; Min, Jee Yeon; Han, Byoung Hee; Lee, Young Ho; Cho, Byung Jae; Kim, Seung Hyup

    2002-01-01

    The early and accurate antenatal diagnosis of fetal musculoskeletal malfomations with a poor outcome has important implications for the management of a pregnancy. Careful ultrasonographic examination of a fetus helps detect such anomalies, and a number of characteristic features may suggest possible differential diagnoses. During the last five years, we have encountered 39 cases of such anomalies, and the typical prenatal ultrasonographic and pathologic findings of a number of those are described in this article

  19. Aerial Images and Convolutional Neural Network for Cotton Bloom Detection.

    Science.gov (United States)

    Xu, Rui; Li, Changying; Paterson, Andrew H; Jiang, Yu; Sun, Shangpeng; Robertson, Jon S

    2017-01-01

    Monitoring flower development can provide useful information for production management, estimating yield and selecting specific genotypes of crops. The main goal of this study was to develop a methodology to detect and count cotton flowers, or blooms, using color images acquired by an unmanned aerial system. The aerial images were collected from two test fields in 4 days. A convolutional neural network (CNN) was designed and trained to detect cotton blooms in raw images, and their 3D locations were calculated using the dense point cloud constructed from the aerial images with the structure from motion method. The quality of the dense point cloud was analyzed and plots with poor quality were excluded from data analysis. A constrained clustering algorithm was developed to register the same bloom detected from different images based on the 3D location of the bloom. The accuracy and incompleteness of the dense point cloud were analyzed because they affected the accuracy of the 3D location of the blooms and thus the accuracy of the bloom registration result. The constrained clustering algorithm was validated using simulated data, showing good efficiency and accuracy. The bloom count from the proposed method was comparable with the number counted manually with an error of -4 to 3 blooms for the field with a single plant per plot. However, more plots were underestimated in the field with multiple plants per plot due to hidden blooms that were not captured by the aerial images. The proposed methodology provides a high-throughput method to continuously monitor the flowering progress of cotton.

  20. PERFORMANCE COMPARISON FOR INTRUSION DETECTION SYSTEM USING NEURAL NETWORK WITH KDD DATASET

    Directory of Open Access Journals (Sweden)

    S. Devaraju

    2014-04-01

    Full Text Available Intrusion Detection Systems are challenging task for finding the user as normal user or attack user in any organizational information systems or IT Industry. The Intrusion Detection System is an effective method to deal with the kinds of problem in networks. Different classifiers are used to detect the different kinds of attacks in networks. In this paper, the performance of intrusion detection is compared with various neural network classifiers. In the proposed research the four types of classifiers used are Feed Forward Neural Network (FFNN, Generalized Regression Neural Network (GRNN, Probabilistic Neural Network (PNN and Radial Basis Neural Network (RBNN. The performance of the full featured KDD Cup 1999 dataset is compared with that of the reduced featured KDD Cup 1999 dataset. The MATLAB software is used to train and test the dataset and the efficiency and False Alarm Rate is measured. It is proved that the reduced dataset is performing better than the full featured dataset.

  1. Ultrasonographic diagnosis of acute appendicitis

    International Nuclear Information System (INIS)

    Lee, Sang Hun; Chang, Young Duk; Kim, Dae Ho; Lee, Hae Kyung; Kwon, Kui Hyang; Kim, Ki Jung

    1988-01-01

    Acute appendicitis is the most common surgical disease of acute abdomen, But the diagnosis of acute appendicitis is often difficult, and not in frequently, operation for appendicitis is performed only to find a normal appendix. Various radiological examinations have been proposed to improve diagnostic accuracy of appendicitis. The purpose of this study was to improve the diagnostic accuracy of appendicitis, and to decline negative exploration. High resolution real time ultrasonographical examination using graded compression was performed in 57 consecutive patients who were clinically suspected of appendicitis. Autors analysed ultrasonographical, surgical, and clinical follow up findings. The results were are follows: 1. Ultrasonographical finding of acute appendicitis was visualization of appendix as a tubular structure with one bline end, or target phenomenon. 2. Hypoechoic area over the appendix was thought to be a sign of periappendiceal abscess. 3. The sensitivity of US diagnosis of acute appendicitis in this study was 92.8% with a specificity of 93.1%. The overall accuracy was 93.0%. 4. In control group of 50 individuals, the abnormal appendix was not visualized. 5. In cases of clinically suspected appendicitis, the US evaluation with graded compression technique is very accurate and effective examination.

  2. Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

    Science.gov (United States)

    Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

    2018-04-02

    Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

  3. Deep Recurrent Neural Networks for seizure detection and early seizure detection systems

    Energy Technology Data Exchange (ETDEWEB)

    Talathi, S. S. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

    2017-06-05

    Epilepsy is common neurological diseases, affecting about 0.6-0.8 % of world population. Epileptic patients suffer from chronic unprovoked seizures, which can result in broad spectrum of debilitating medical and social consequences. Since seizures, in general, occur infrequently and are unpredictable, automated seizure detection systems are recommended to screen for seizures during long-term electroencephalogram (EEG) recordings. In addition, systems for early seizure detection can lead to the development of new types of intervention systems that are designed to control or shorten the duration of seizure events. In this article, we investigate the utility of recurrent neural networks (RNNs) in designing seizure detection and early seizure detection systems. We propose a deep learning framework via the use of Gated Recurrent Unit (GRU) RNNs for seizure detection. We use publicly available data in order to evaluate our method and demonstrate very promising evaluation results with overall accuracy close to 100 %. We also systematically investigate the application of our method for early seizure warning systems. Our method can detect about 98% of seizure events within the first 5 seconds of the overall epileptic seizure duration.

  4. Ultrasonographic patterns in patients with obstructed defaecation.

    Science.gov (United States)

    Brusciano, L; Limongelli, P; Pescatori, M; Napolitano, V; Gagliardi, G; Maffettone, V; Rossetti, G; del Genio, G; Russo, G; Pizza, F; del Genio, A

    2007-08-01

    Anal ultrasound is helpful in assessing organic anorectal lesions, but its role in functional disease is still questionable. The purpose of the present study is to assess anal-vaginal-dynamic perineal ultrasonographic findings in patients with obstructed defecation (OD) and healthy controls. Ninety-two consecutive patients (77 women; mean age 51 years; range 21-71) with symptoms of OD were retrospectively evaluated. All patients underwent digital exploration, endoanal and endovaginal ultrasound (US) with rotating probe. Forty-one patients underwent dynamic perineal US with linear probe. Anal manometry and defaecography were performed in 73 and 43 patients, respectively. Ultrasonographic findings of 92 patients with symptoms of OD were compared to 22 healthy controls. Anismus was defined on US when the difference in millimetres between the distance of the inner edge of the puborectalis muscle posteriorly and the probe at rest and on straining was less then 5 mm. Sensitivity and specificity were calculated by assuming defaecography as the gold standard for intussusception and rectocele and proctoscopy for rectal internal mucosal prolapse. Since no gold standard for the diagnosis of anismus was available in the literature, the agreement between anal US and all other diagnostic procedures was evaluated. The incidence of anismus resulted significantly higher (P anismus, anal ultrasonography resulted in agreement with perineal and vaginal US, manometry, defaecography, and digital exam (P < 0.05). Other lesions detected by US in patients with OD include solitary rectal ulcer, rectocele and enterocele. Damage of internal and/or external sphincter was diagnosed at anal US in 19/92 (20%) patients, all continent and with normal manometric values. Anal, vaginal and dynamic perineal ultrasonography can diagnose or confirm many of the abnormalities seen in patients with OD. The value of the information obtained by this non-invasive test and its role in the diagnostic algorithm

  5. Neural Network based Minimization of BER in Multi-User Detection in SDMA

    OpenAIRE

    VENKATA REDDY METTU; KRISHAN KUMAR,; SRIKANTH PULLABHATLA

    2011-01-01

    In this paper we investigate the use of neural network based minimization of BER in MUD. Neural networks can be used for linear design, Adaptive prediction, Amplitude detection, Character Recognition and many other applications. Adaptive prediction is used in detecting the errors caused in AWGN channel. These errors are rectified by using Widrow-Hoff algorithm by updating their weights andAdaptive prediction methods. Both Widrow-Hoff and Adaptive prediction have been used for rectifying the e...

  6. Ultrasonographic findings of breast disease

    International Nuclear Information System (INIS)

    Choi, Kwang Uk; Kim, Sung Eun; Lee, Hee Chung; Shin, Kyung Ja; Kim, Young Chul; Lee, Sang Chun

    1989-01-01

    The authors analyzed ultrasonographic findings of 60 cases of breast lesions which were proven surgically of pathologically at Seoul Red Cross Hospital from September 1986 to February 1989. The results were as follows; 1. There were 30 fibrocystic diseases, 12 fibroadenomas, 8 carcinomas, 3 abscesses, 3 foreign bodies, 2 gynecomastias, 1 intraductal papilloma, 1 malignant cystosarcoma phylloides. 2. Ultrasonography provided accurate information for the size, location, internal structure and relationship between lesion and adjacent structure. 3. Ultrasonography can be used as an adjunct to film mammography in selective patients and useful for guiding fine needle aspiration biopsies

  7. Ultrasonographic determination of fetal gender

    International Nuclear Information System (INIS)

    Kim, Il Young; Kim, Dae Ho; Lee, Byung Ho; Bae, Dong Han

    1985-01-01

    Sonographic determination of fetal gender was attempted prospectively in most pregnancies of more than 26 weeks. We studied 193 cases of pregnancies with ultrasound for recent 9 months from June 1984 to February 1985 at department of radiology, Soonchunhyang university, Soonchunhyang Chunan hospital, and analysed ultrasonographic finding of fetal gender. The results were as follows; 1. Overall accuracy rate for fetal gender is 90%. 2. Accuracy rate for male fetus is 97.8%. 3. Accuracy rate for female fetus is 88.2%

  8. Ultrasonographic findings of breast disease

    Energy Technology Data Exchange (ETDEWEB)

    Choi, Kwang Uk; Kim, Sung Eun; Lee, Hee Chung; Shin, Kyung Ja; Kim, Young Chul; Lee, Sang Chun [Seoul Red Cross Hopital, Seoul (Korea, Republic of)

    1989-10-15

    The authors analyzed ultrasonographic findings of 60 cases of breast lesions which were proven surgically of pathologically at Seoul Red Cross Hospital from September 1986 to February 1989. The results were as follows; 1. There were 30 fibrocystic diseases, 12 fibroadenomas, 8 carcinomas, 3 abscesses, 3 foreign bodies, 2 gynecomastias, 1 intraductal papilloma, 1 malignant cystosarcoma phylloides. 2. Ultrasonography provided accurate information for the size, location, internal structure and relationship between lesion and adjacent structure. 3. Ultrasonography can be used as an adjunct to film mammography in selective patients and useful for guiding fine needle aspiration biopsies.

  9. Ultrasonographic findings of tuberculous peritonitis

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Dong Ho; Oh, C. H.; Koh, Y. T.; Lim, J. H. [Seoul National University College of Medicine, Seoul (Korea, Republic of)

    1989-12-15

    Sonograms in forty two patients with tuberculous peritonitis of the wet-ascitic type were retrospectively analyzed. The ascites was clear in 24 patients (57%). There were septations, membranes and debris in 6 (14%), floating debris in 5 (12%), mobile strands or membranes in 4 (10%), and fixed septations in three(7%). Other findings were increased hepatic echogenicity, hepatosplenomegaly, pleural effusion, omental cake, thickened mesentery with adherent bowel loops, lymphadenopathy, thickening of the ileal wall, presented in order of frequency. The ultrasonographic findings are not specific for tuberculous peritonitis, but may give profitable information and protect the patient from unnecessary laparotomy

  10. Neural Cell Chip Based Electrochemical Detection of Nanotoxicity.

    Science.gov (United States)

    Kafi, Md Abdul; Cho, Hyeon-Yeol; Choi, Jeong Woo

    2015-07-02

    Development of a rapid, sensitive and cost-effective method for toxicity assessment of commonly used nanoparticles is urgently needed for the sustainable development of nanotechnology. A neural cell with high sensitivity and conductivity has become a potential candidate for a cell chip to investigate toxicity of environmental influences. A neural cell immobilized on a conductive surface has become a potential tool for the assessment of nanotoxicity based on electrochemical methods. The effective electrochemical monitoring largely depends on the adequate attachment of a neural cell on the chip surfaces. Recently, establishment of integrin receptor specific ligand molecules arginine-glycine-aspartic acid (RGD) or its several modifications RGD-Multi Armed Peptide terminated with cysteine (RGD-MAP-C), C(RGD)₄ ensure farm attachment of neural cell on the electrode surfaces either in their two dimensional (dot) or three dimensional (rod or pillar) like nano-scale arrangement. A three dimensional RGD modified electrode surface has been proven to be more suitable for cell adhesion, proliferation, differentiation as well as electrochemical measurement. This review discusses fabrication as well as electrochemical measurements of neural cell chip with particular emphasis on their use for nanotoxicity assessments sequentially since inception to date. Successful monitoring of quantum dot (QD), graphene oxide (GO) and cosmetic compound toxicity using the newly developed neural cell chip were discussed here as a case study. This review recommended that a neural cell chip established on a nanostructured ligand modified conductive surface can be a potential tool for the toxicity assessments of newly developed nanomaterials prior to their use on biology or biomedical technologies.

  11. Neural Cell Chip Based Electrochemical Detection of Nanotoxicity

    Directory of Open Access Journals (Sweden)

    Md. Abdul Kafi

    2015-07-01

    Full Text Available Development of a rapid, sensitive and cost-effective method for toxicity assessment of commonly used nanoparticles is urgently needed for the sustainable development of nanotechnology. A neural cell with high sensitivity and conductivity has become a potential candidate for a cell chip to investigate toxicity of environmental influences. A neural cell immobilized on a conductive surface has become a potential tool for the assessment of nanotoxicity based on electrochemical methods. The effective electrochemical monitoring largely depends on the adequate attachment of a neural cell on the chip surfaces. Recently, establishment of integrin receptor specific ligand molecules arginine-glycine-aspartic acid (RGD or its several modifications RGD-Multi Armed Peptide terminated with cysteine (RGD-MAP-C, C(RGD4 ensure farm attachment of neural cell on the electrode surfaces either in their two dimensional (dot or three dimensional (rod or pillar like nano-scale arrangement. A three dimensional RGD modified electrode surface has been proven to be more suitable for cell adhesion, proliferation, differentiation as well as electrochemical measurement. This review discusses fabrication as well as electrochemical measurements of neural cell chip with particular emphasis on their use for nanotoxicity assessments sequentially since inception to date. Successful monitoring of quantum dot (QD, graphene oxide (GO and cosmetic compound toxicity using the newly developed neural cell chip were discussed here as a case study. This review recommended that a neural cell chip established on a nanostructured ligand modified conductive surface can be a potential tool for the toxicity assessments of newly developed nanomaterials prior to their use on biology or biomedical technologies.

  12. SPR imaging combined with cyclic voltammetry for the detection of neural activity

    Directory of Open Access Journals (Sweden)

    Hui Li

    2014-03-01

    Full Text Available Surface plasmon resonance (SPR detects changes in refractive index at a metal-dielectric interface. In this study, SPR imaging (SPRi combined with cyclic voltammetry (CV was applied to detect neural activity in isolated bullfrog sciatic nerves. The neural activities induced by chemical and electrical stimulation led to an SPR response, and the activities were recorded in real time. The activities of different parts of the sciatic nerve were recorded and compared. The results demonstrated that SPR imaging combined with CV is a powerful tool for the investigation of neural activity.

  13. Fault detection and classification in electrical power transmission system using artificial neural network.

    Science.gov (United States)

    Jamil, Majid; Sharma, Sanjeev Kumar; Singh, Rajveer

    2015-01-01

    This paper focuses on the detection and classification of the faults on electrical power transmission line using artificial neural networks. The three phase currents and voltages of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. A detailed analysis with varying number of hidden layers has been performed to validate the choice of the neural network. The simulation results concluded that the present method based on the neural network is efficient in detecting and classifying the faults on transmission lines with satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The proposed method can be extended to the Distribution network of the Power System. The various simulations and analysis of signals is done in the MATLAB(®) environment.

  14. Computational neural network regression model for Host based Intrusion Detection System

    Directory of Open Access Journals (Sweden)

    Sunil Kumar Gautam

    2016-09-01

    Full Text Available The current scenario of information gathering and storing in secure system is a challenging task due to increasing cyber-attacks. There exists computational neural network techniques designed for intrusion detection system, which provide security to single machine and entire network's machine. In this paper, we have used two types of computational neural network models, namely, Generalized Regression Neural Network (GRNN model and Multilayer Perceptron Neural Network (MPNN model for Host based Intrusion Detection System using log files that are generated by a single personal computer. The simulation results show correctly classified percentage of normal and abnormal (intrusion class using confusion matrix. On the basis of results and discussion, we found that the Host based Intrusion Systems Model (HISM significantly improved the detection accuracy while retaining minimum false alarm rate.

  15. Fast Automatic Airport Detection in Remote Sensing Images Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Fen Chen

    2018-03-01

    Full Text Available Fast and automatic detection of airports from remote sensing images is useful for many military and civilian applications. In this paper, a fast automatic detection method is proposed to detect airports from remote sensing images based on convolutional neural networks using the Faster R-CNN algorithm. This method first applies a convolutional neural network to generate candidate airport regions. Based on the features extracted from these proposals, it then uses another convolutional neural network to perform airport detection. By taking the typical elongated linear geometric shape of airports into consideration, some specific improvements to the method are proposed. These approaches successfully improve the quality of positive samples and achieve a better accuracy in the final detection results. Experimental results on an airport dataset, Landsat 8 images, and a Gaofen-1 satellite scene demonstrate the effectiveness and efficiency of the proposed method.

  16. Detecting danger labels with RAM-based neural networks

    DEFF Research Database (Denmark)

    Jørgensen, T.M.; Christensen, S.S.; Andersen, A.W.

    1996-01-01

    An image processing system for the automatic location of danger labels on the back of containers is presented. The system uses RAM-based neural networks to locate and classify labels after a pre-processing step involving specially designed non-linear edge filters and RGB-to-HSV conversion. Result...

  17. The harmonics detection method based on neural network applied ...

    African Journals Online (AJOL)

    user

    Keywords: Artificial Neural Networks (ANN), p-q theory, (SAPF), Harmonics, Total ..... Genetic algorithm-based self-learning fuzzy PI controller for shunt active filter, ... Verification of global optimality of the OFC active power filters by means of ...

  18. Determination of Optimal Imaging Mode for Ultrasonographic Detection of Subdermal Contraceptive Rods: Comparison of Spatial Compound, Conventional, and Tissue Harmonic Imaging Methods

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Sung Jin; Seo, Kyung; Song, Ho Taek; Park, Ah Young; Kim, Yaena; Yoon, Choon Sik [Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul (Korea, Republic of); Suh, Jin Suck; Kim, Ah Hyun [Dept. of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul (Korea, Republic of); Ryu, Jeong Ah [Dept. of Radiology, Guri Hospital, Hanyang University College of Medicine, Guri (Korea, Republic of); Park, Jeong Seon [Dept. of Radiology, Hanyang University Hospital, Hanyang University College of Medicine, Seoul (Korea, Republic of)

    2012-09-15

    To determine which mode of ultrasonography (US), among the conventional, spatial compound, and tissue-harmonic methods, exhibits the best performance for the detection of Implanon with respect to generation of posterior acoustic shadowing (PAS). A total of 21 patients, referred for localization of impalpable Implanon, underwent US, using the three modes with default settings (i.e., wide focal zone). Representative transverse images of the rods, according to each mode for all patients, were obtained. The resulting 63 images were reviewed by four observers. The observers provided a confidence score for the presence of PAS, using a five-point scale ranging from 1 (definitely absent) to 5 (definitely present), with scores of 4 or 5 for PAS being considered as detection. The average scores of PAS, obtained from the three different modes for each observer, were compared using one-way repeated measure ANOVA. The detection rates were compared using a weighted least square method. Statistically, the tissue harmonic mode was significantly superior to the other two modes, when comparing the average scores of PAS for all observers (p < 0.00-1). The detection rate was also highest for the tissue harmonic mode (p < 0.001). Tissue harmonic mode in US appears to be the most suitable in detecting subdermal contraceptive implant rods.

  19. Determination of Optimal Imaging Mode for Ultrasonographic Detection of Subdermal Contraceptive Rods: Comparison of Spatial Compound, Conventional, and Tissue Harmonic Imaging Methods

    International Nuclear Information System (INIS)

    Kim, Sung Jin; Seo, Kyung; Song, Ho Taek; Park, Ah Young; Kim, Yaena; Yoon, Choon Sik; Suh, Jin Suck; Kim, Ah Hyun; Ryu, Jeong Ah; Park, Jeong Seon

    2012-01-01

    To determine which mode of ultrasonography (US), among the conventional, spatial compound, and tissue-harmonic methods, exhibits the best performance for the detection of Implanon with respect to generation of posterior acoustic shadowing (PAS). A total of 21 patients, referred for localization of impalpable Implanon, underwent US, using the three modes with default settings (i.e., wide focal zone). Representative transverse images of the rods, according to each mode for all patients, were obtained. The resulting 63 images were reviewed by four observers. The observers provided a confidence score for the presence of PAS, using a five-point scale ranging from 1 (definitely absent) to 5 (definitely present), with scores of 4 or 5 for PAS being considered as detection. The average scores of PAS, obtained from the three different modes for each observer, were compared using one-way repeated measure ANOVA. The detection rates were compared using a weighted least square method. Statistically, the tissue harmonic mode was significantly superior to the other two modes, when comparing the average scores of PAS for all observers (p < 0.00-1). The detection rate was also highest for the tissue harmonic mode (p < 0.001). Tissue harmonic mode in US appears to be the most suitable in detecting subdermal contraceptive implant rods.

  20. Performance of an artificial neural network for vertical root fracture detection: an ex vivo study.

    Science.gov (United States)

    Kositbowornchai, Suwadee; Plermkamon, Supattra; Tangkosol, Tawan

    2013-04-01

    To develop an artificial neural network for vertical root fracture detection. A probabilistic neural network design was used to clarify whether a tooth root was sound or had a vertical root fracture. Two hundred images (50 sound and 150 vertical root fractures) derived from digital radiography--used to train and test the artificial neural network--were divided into three groups according to the number of training and test data sets: 80/120,105/95 and 130/70, respectively. Either training or tested data were evaluated using grey-scale data per line passing through the root. These data were normalized to reduce the grey-scale variance and fed as input data of the neural network. The variance of function in recognition data was calculated between 0 and 1 to select the best performance of neural network. The performance of the neural network was evaluated using a diagnostic test. After testing data under several variances of function, we found the highest sensitivity (98%), specificity (90.5%) and accuracy (95.7%) occurred in Group three, for which the variance of function in recognition data was between 0.025 and 0.005. The neural network designed in this study has sufficient sensitivity, specificity and accuracy to be a model for vertical root fracture detection. © 2012 John Wiley & Sons A/S.

  1. Development and application of deep convolutional neural network in target detection

    Science.gov (United States)

    Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

    2018-04-01

    With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

  2. Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks

    Science.gov (United States)

    Ray, Loye Lynn

    2014-01-01

    The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…

  3. Wind Turbine Fault Detection based on Artificial Neural Network Analysis of SCADA Data

    DEFF Research Database (Denmark)

    Herp, Jürgen; S. Nadimi, Esmaeil

    2015-01-01

    Slowly developing faults in wind turbine can, when not detected and fixed on time, cause severe damage and downtime. We are proposing a fault detection method based on Artificial Neural Networks (ANN) and the recordings from Supervisory Control and Data Acquisition (SCADA) systems installed in wind...

  4. Ultrasonographic findings in patients with nonbacterial prostatitis

    NARCIS (Netherlands)

    de la Rosette, J. J.; Karthaus, H. F.; Debruyne, F. M.

    1992-01-01

    The potential value of prostatic imaging in the diagnosis of inflammatory disorders of the prostate is largely unexplored. In several studies, specific ultrasonographic characteristics in patients with prostatitis have been described. Also nonspecific echogenic qualities in prostatitis have been

  5. Ultrasonographic findings of early abortion: suggested predictors

    International Nuclear Information System (INIS)

    Jun, Soon Ae; Ahn, Myoung Ock; Cha, Kwang Yul; Lee, Young Doo

    1992-01-01

    To investigate predictable ultrasonographic findings of early abortion. To investigate objective rules for the screening of abortion. Ultrasonographic examination of 111 early pregnancies between the sixth and ninth week in women who had regular 28 day menstrual cycles was performed. Ultrasonographic measurements of the gestational sac, crown rump length and fetal heart rate were performed using a linear array real time transducer with doppler ultrasonogram. All measurements of 17 early abortions were compared to those of 94 normal pregnancies. Most of early aborted pregnancies were classified correctly by discriminant analysis with G-SAC and CRL (G-SAC=0.5 CRL + 15, sensitivity 76.5%, specificity 96.8%). With the addition of FHR, 94.1% of early abortions could be predicted. In conclusion, ultrasonographic findings of early intrauterine growth retardation, small gestational sac and bradycardia can be predictable signs suggestive of poor prognosis of early pregnancies

  6. Ultrasonographic Findings of Breast Abscess

    Energy Technology Data Exchange (ETDEWEB)

    Shin, Hyeong Cheol; Oh, Ki Keun [Yonsei University College of Medicine, Seoul (Korea, Republic of)

    1995-06-15

    Breast abscess cannot be differentiated from breast malignancy by film mammography. Pain and spread of infection can be developed during film mammography procedure due to compression. However, ultrasonography is known to be an adequate procedure for diagnosis of breast abscesses. Therefore, we performed the present study to document the ultrasonographic findings of breast abscess. We analyzed ultrasonograms of ninexases with surgically proven breast abscesses. All patients were female and their ages ranged from l2 to 56 years(average, 35 years). The lesion was located in the right breast in four cases, and in the left in five cases. On ultrasonography, all lesions were anechoic or low echoic. The lesion showed mixed echogenicityin five cases. Posterior acoustic enhancement was noted in seven cases. Lateral shadowing was seen in four cases.There were skin thickening in five cases and subcutaneous fat obliteration in all cases. Ultrasonography is useful in the diagnosis of breast abscess

  7. Ultrasonographic Findings of Breast Abscess

    International Nuclear Information System (INIS)

    Shin, Hyeong Cheol; Oh, Ki Keun

    1995-01-01

    Breast abscess cannot be differentiated from breast malignancy by film mammography. Pain and spread of infection can be developed during film mammography procedure due to compression. However, ultrasonography is known to be an adequate procedure for diagnosis of breast abscesses. Therefore, we performed the present study to document the ultrasonographic findings of breast abscess. We analyzed ultrasonograms of ninexases with surgically proven breast abscesses. All patients were female and their ages ranged from l2 to 56 years(average, 35 years). The lesion was located in the right breast in four cases, and in the left in five cases. On ultrasonography, all lesions were anechoic or low echoic. The lesion showed mixed echogenicityin five cases. Posterior acoustic enhancement was noted in seven cases. Lateral shadowing was seen in four cases.There were skin thickening in five cases and subcutaneous fat obliteration in all cases. Ultrasonography is useful in the diagnosis of breast abscess

  8. Ultrasonographic Findings of Periappendiceal Abscess

    Energy Technology Data Exchange (ETDEWEB)

    Woo, Seong Ku; Sung, Dong Wook; Ko, Young Tae; Lim, Jae Hoon; Kim, Soon Yong [Kyung Hee University Hospital, Seoul (Korea, Republic of)

    1983-09-15

    Although the ultrasonography has been regarded as a important procedure in the diagnosis of intra-abdominal abscess, there were relatively few papers concerning the ultrasonographic findings of perpendicular abscess. Nineteen cases of surgically proven perpendicular abscess caused by perforated appendicitis were studied by ultrasonography at the Kyung Hee University Hospital during last 34 months. The results were as follows: 1. Diagnostic accuracy of the real-time ultrasonography was 94.7% (18/19). There were only one false positive and one false negative. 2. The location of abscesses were; perpendicular 68.4% (13/19), pelvic 21.0% (4/19), sub hepatic 5.3% (1/19) and sub phrenic 5.3% (1/19) in order of frequency. 3. Variable echo-patterns of abscesses was encounted. But irregular, thick walled, posteriorly reinforcing, echo-free or mixed echo-patterns were most common.

  9. The Ultrasonographic Findings of Bifid Median Nerve

    International Nuclear Information System (INIS)

    Park, Hee Jin; Park, Noh Hyuck; Joh, Joon Hee; Lee, Sung Moon

    2009-01-01

    We wanted to evaluate the ultrasonographic findings of bifid median nerve and its clinical significance. We retrospectively reviewed five cases (three men and two women, mean age: 54 years) of incidentally found bifid median nerve from 264 cases of clinically suspected carpal-tunnel syndrome that were seen at our hospital during last 6 years. Doppler sonography was performed in all five cases and MR angiography was done in one case for detecting a persistent median artery. The difference (ΔCSA) between the sum of the cross-sectional areas of the bifid median nerve at the pisiform level (CSA2) and the cross-sectional area proximal to the bifurcation(CSA1) was calculated. The incidence of a bifid median nerve was 1.9%. All the patients presented with a tingling sensation on a hand and two patients had nocturnal pain. All the cases showed bifurcation of the nerve bundle proximal to the carpal tunnel. The margins appeared relatively smooth and each bundle showed a characteristic fascicular pattern. A persistent median artery was noted between the bundles in four cases. ΔCSA was more than 2 mm 2 in four cases. Bifid median nerve with a persistent median artery is a relatively rare normal variance and these are very important findings before performing surgical intervention to avoid potential nerve injury and massive bleeding. We highly suggest that radiologists should understand the anatomical characteristics of this anomaly and make efforts to detect it

  10. Do Not Hallow until You Are out of the Wood! Ultrasonographic Detection of CPP Crystal Deposits in Menisci: Facts and Pitfalls

    Directory of Open Access Journals (Sweden)

    Georgios Filippou

    2013-01-01

    Full Text Available Purpose. Ultrasonography (US has been demonstrated to be an important tool in the diagnosis of calcium pyrophosphate (CPP crystal deposition disease. The aim of our study was to individuate and describe possible pitfalls in US detection of such deposits in menisci. Patients and Methods. We enrolled all patients waiting to undergo knee replacement surgery due to osteoarthritis, for one-month period. Each patient underwent US examination of the knee, focusing on the menisci. After surgery, the menisci were examined by US, macroscopically and microscopically, using the microscopic analysis as the gold standard for CPP deposition. Results. 11 menisci of 6 patients have been studied. Ex vivo examination of menisci performed better in CPP identification than in vivo examination. The possible reasons of misinterpretation or misdiagnosis of the in vivo exam were identified and are extensively described in the paper. Also a new sign of CPP crystal deposits was found. Conclusions. This study permitted to highlight some difficulties in CPP crystal detection by US in menisci. Further studies are needed to define completely US CPP crystal aspect and to improve the sensibility and specificity of US in CPP deposition diagnosis.

  11. Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene.

    Science.gov (United States)

    Li, Jun; Mei, Xue; Prokhorov, Danil; Tao, Dacheng

    2017-03-01

    Hierarchical neural networks have been shown to be effective in learning representative image features and recognizing object classes. However, most existing networks combine the low/middle level cues for classification without accounting for any spatial structures. For applications such as understanding a scene, how the visual cues are spatially distributed in an image becomes essential for successful analysis. This paper extends the framework of deep neural networks by accounting for the structural cues in the visual signals. In particular, two kinds of neural networks have been proposed. First, we develop a multitask deep convolutional network, which simultaneously detects the presence of the target and the geometric attributes (location and orientation) of the target with respect to the region of interest. Second, a recurrent neuron layer is adopted for structured visual detection. The recurrent neurons can deal with the spatial distribution of visible cues belonging to an object whose shape or structure is difficult to explicitly define. Both the networks are demonstrated by the practical task of detecting lane boundaries in traffic scenes. The multitask convolutional neural network provides auxiliary geometric information to help the subsequent modeling of the given lane structures. The recurrent neural network automatically detects lane boundaries, including those areas containing no marks, without any explicit prior knowledge or secondary modeling.

  12. Noninvasive detection of hepatic steatosis in patients without ultrasonographic evidence of fatty liver using the controlled attenuation parameter evaluated with transient elastography.

    Science.gov (United States)

    Yilmaz, Yusuf; Ergelen, Rabia; Akin, Hakan; Imeryuz, Nese

    2013-11-01

    Although ultrasound is a useful technique for detecting hepatic steatosis, it cannot provide a precise determination of hepatic fat content. A novel attenuation parameter named controlled attenuation parameter (CAP) has been developed to process the raw ultrasonic signals acquired by Fibroscan. The aim of this study was to determine the percentage of hepatic steatosis in apparently healthy Turkish individuals using the proposed diagnostic cut-off points for CAP. In addition, we sought to investigate the association of CAP with the traditional risk factors for nonalcoholic fatty liver disease in a screening setting. In the present study, 102 Turkish individuals without evidence of fatty liver on ultrasound and normal aminotransferase levels underwent CAP measurements by means of Fibroscan. The mean (SD), median (minimum-maximum), and 5th and 95th percentile values of CAP values in this cohort of 102 individuals were 206.99 (48.12), 210.5 (100.0-314.0), 113.4 and 280.2 dB/m, respectively. Using the cut-offs of 222, 238, and 283 dB/m for CAP, there were 39 (38.2%), 23 (22.5%), and five (4.9%) individuals out of 102 who had at least 10% steatosis despite normal liver findings on ultrasound. After allowance for potential confounders, CAP was independently associated with BMI (β=0.39, t=3.5, Phepatic steatosis on the basis of CAP assessment.

  13. Statistical control chart and neural network classification for improving human fall detection

    KAUST Repository

    Harrou, Fouzi; Zerrouki, Nabil; Sun, Ying; Houacine, Amrane

    2017-01-01

    This paper proposes a statistical approach to detect and classify human falls based on both visual data from camera and accelerometric data captured by accelerometer. Specifically, we first use a Shewhart control chart to detect the presence of potential falls by using accelerometric data. Unfortunately, this chart cannot distinguish real falls from fall-like actions, such as lying down. To bypass this difficulty, a neural network classifier is then applied only on the detected cases through visual data. To assess the performance of the proposed method, experiments are conducted on the publicly available fall detection databases: the University of Rzeszow's fall detection (URFD) dataset. Results demonstrate that the detection phase play a key role in reducing the number of sequences used as input into the neural network classifier for classification, significantly reducing computational burden and achieving better accuracy.

  14. Statistical control chart and neural network classification for improving human fall detection

    KAUST Repository

    Harrou, Fouzi

    2017-01-05

    This paper proposes a statistical approach to detect and classify human falls based on both visual data from camera and accelerometric data captured by accelerometer. Specifically, we first use a Shewhart control chart to detect the presence of potential falls by using accelerometric data. Unfortunately, this chart cannot distinguish real falls from fall-like actions, such as lying down. To bypass this difficulty, a neural network classifier is then applied only on the detected cases through visual data. To assess the performance of the proposed method, experiments are conducted on the publicly available fall detection databases: the University of Rzeszow\\'s fall detection (URFD) dataset. Results demonstrate that the detection phase play a key role in reducing the number of sequences used as input into the neural network classifier for classification, significantly reducing computational burden and achieving better accuracy.

  15. Neural Network Based Sensory Fusion for Landmark Detection

    Science.gov (United States)

    Kumbla, Kishan -K.; Akbarzadeh, Mohammad R.

    1997-01-01

    NASA is planning to send numerous unmanned planetary missions to explore the space. This requires autonomous robotic vehicles which can navigate in an unstructured, unknown, and uncertain environment. Landmark based navigation is a new area of research which differs from the traditional goal-oriented navigation, where a mobile robot starts from an initial point and reaches a destination in accordance with a pre-planned path. The landmark based navigation has the advantage of allowing the robot to find its way without communication with the mission control station and without exact knowledge of its coordinates. Current algorithms based on landmark navigation however pose several constraints. First, they require large memories to store the images. Second, the task of comparing the images using traditional methods is computationally intensive and consequently real-time implementation is difficult. The method proposed here consists of three stages, First stage utilizes a heuristic-based algorithm to identify significant objects. The second stage utilizes a neural network (NN) to efficiently classify images of the identified objects. The third stage combines distance information with the classification results of neural networks for efficient and intelligent navigation.

  16. New Method for Leakage Detection by Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Mohammad Attari

    2018-03-01

    Full Text Available Nowadays water loss has been turned into a global concern and on the other hand the demand for water is increasing. This problem has made the demand management and consumption pattern reform necessary. One of the most important methods for managing water consumption is to decrease the water loss. In this study by using neural networks, a new method is presented to specify the location and quantity of leakages in water distribution networks.  In this method, by producing the training data and applying it to neural network, the network is able to determine approximate location and quantity of nodal leakage with receiving the nodal pressure. Production of training data is carried out by applying assumed leakage to specific nodes in the network and calculating the new nodal pressures. The results show that by minimum use of hydraulic data taken from pressures, not only this method can determine the location of nodal leakages, but also it can specify the amount of leakage on each node with reasonable accuracy.

  17. Neural Network in Fixed Time for Collision Detection between Two Convex Polyhedra

    OpenAIRE

    M. Khouil; N. Saber; M. Mestari

    2014-01-01

    In this paper, a different architecture of a collision detection neural network (DCNN) is developed. This network, which has been particularly reviewed, has enabled us to solve with a new approach the problem of collision detection between two convex polyhedra in a fixed time (O (1) time). We used two types of neurons, linear and threshold logic, which simplified the actual implementation of all the networks proposed. The study of the collision detection is divided into two sections, the coll...

  18. A novel wavelet neural network based pathological stage detection technique for an oral precancerous condition

    Science.gov (United States)

    Paul, R R; Mukherjee, A; Dutta, P K; Banerjee, S; Pal, M; Chatterjee, J; Chaudhuri, K; Mukkerjee, K

    2005-01-01

    Aim: To describe a novel neural network based oral precancer (oral submucous fibrosis; OSF) stage detection method. Method: The wavelet coefficients of transmission electron microscopy images of collagen fibres from normal oral submucosa and OSF tissues were used to choose the feature vector which, in turn, was used to train the artificial neural network. Results: The trained network was able to classify normal and oral precancer stages (less advanced and advanced) after obtaining the image as an input. Conclusions: The results obtained from this proposed technique were promising and suggest that with further optimisation this method could be used to detect and stage OSF, and could be adapted for other conditions. PMID:16126873

  19. The Application of Helicopter Rotor Defect Detection Using Wavelet Analysis and Neural Network Technique

    Directory of Open Access Journals (Sweden)

    Jin-Li Sun

    2014-06-01

    Full Text Available When detect the helicopter rotor beam with ultrasonic testing, it is difficult to realize the noise removing and quantitative testing. This paper used the wavelet analysis technique to remove the noise among the ultrasonic detection signal and highlight the signal feature of defect, then drew the curve of defect size and signal amplitude. Based on the relationship of defect size and signal amplitude, a BP neural network was built up and the corresponding estimated value of the simulate defect was obtained by repeating training. It was confirmed that the wavelet analysis and neural network technique met the requirements of practical testing.

  20. Ultrasonographic and clinical findings of inguinal hernia containing the ovary or omentum in girls

    Energy Technology Data Exchange (ETDEWEB)

    Shin, Su Mi; Chai, Jee Won [Dept. of Radiology, SMG-SNU Boramae Medical Center, Seoul (Korea, Republic of)

    2016-09-15

    To characterize the ultrasonographic and clinical findings of inguinal hernia containing the ovary or omentum in girls. We studied 46 girls (49 cases) who were diagnosed with inguinal hernia on ultrasonography between March 2009 and December 2015. The ultrasonographic findings were retrospectively analyzed with respect to location, age at detection, contents of hernia, diameter of the canal of Nuck, and incidence of reducibility, incarceration and strangulation. The clinical findings included the number of cases that underwent operation, contents of hernia discovered during operation, and duration between ultrasonographic diagnosis and operation. The two groups in which inguinal hernia contained the ovary and omentum were statistically compared. Of the 49 cases, the contents of hernia were the ovary or tube in 14 cases, omentum in 32 cases, and bowel in 3 cases. The ovarian herniation group was significantly younger (10.1 months vs. 4.9 years, p < 0.001), had a lower incidence of reducibility (n = 3 vs. n = 29, p < 0.001), higher incidence of incarceration (n = 4 vs. n = 0, p = 0.006), and a shorter duration between ultrasonographic diagnosis and operation (5.7 days vs. 55.8 days, p = 0.032) than the omental herniation group. The ovarian herniation group was younger, had a lower incidence of reducibility, higher incidence of incarceration, and a shorter duration between ultrasonographic diagnosis and operation.

  1. Ultrasonographic and clinical findings of inguinal hernia containing the ovary or omentum in girls

    International Nuclear Information System (INIS)

    Shin, Su Mi; Chai, Jee Won

    2016-01-01

    To characterize the ultrasonographic and clinical findings of inguinal hernia containing the ovary or omentum in girls. We studied 46 girls (49 cases) who were diagnosed with inguinal hernia on ultrasonography between March 2009 and December 2015. The ultrasonographic findings were retrospectively analyzed with respect to location, age at detection, contents of hernia, diameter of the canal of Nuck, and incidence of reducibility, incarceration and strangulation. The clinical findings included the number of cases that underwent operation, contents of hernia discovered during operation, and duration between ultrasonographic diagnosis and operation. The two groups in which inguinal hernia contained the ovary and omentum were statistically compared. Of the 49 cases, the contents of hernia were the ovary or tube in 14 cases, omentum in 32 cases, and bowel in 3 cases. The ovarian herniation group was significantly younger (10.1 months vs. 4.9 years, p < 0.001), had a lower incidence of reducibility (n = 3 vs. n = 29, p < 0.001), higher incidence of incarceration (n = 4 vs. n = 0, p = 0.006), and a shorter duration between ultrasonographic diagnosis and operation (5.7 days vs. 55.8 days, p = 0.032) than the omental herniation group. The ovarian herniation group was younger, had a lower incidence of reducibility, higher incidence of incarceration, and a shorter duration between ultrasonographic diagnosis and operation

  2. Detection and recognition of bridge crack based on convolutional neural network

    Directory of Open Access Journals (Sweden)

    Honggong LIU

    2016-10-01

    Full Text Available Aiming at the backward artificial visual detection status of bridge crack in China, which has a great danger coefficient, a digital and intelligent detection method of improving the diagnostic efficiency and reducing the risk coefficient is studied. Combing with machine vision and convolutional neural network technology, Raspberry Pi is used to acquire and pre-process image, and the crack image is analyzed; the processing algorithm which has the best effect in detecting and recognizing is selected; the convolutional neural network(CNN for crack classification is optimized; finally, a new intelligent crack detection method is put forward. The experimental result shows that the system can find all cracks beyond the maximum limit, and effectively identify the type of fracture, and the recognition rate is above 90%. The study provides reference data for engineering detection.

  3. Research on Daily Objects Detection Based on Deep Neural Network

    Science.gov (United States)

    Ding, Sheng; Zhao, Kun

    2018-03-01

    With the rapid development of deep learning, great breakthroughs have been made in the field of object detection. In this article, the deep learning algorithm is applied to the detection of daily objects, and some progress has been made in this direction. Compared with traditional object detection methods, the daily objects detection method based on deep learning is faster and more accurate. The main research work of this article: 1. collect a small data set of daily objects; 2. in the TensorFlow framework to build different models of object detection, and use this data set training model; 3. the training process and effect of the model are improved by fine-tuning the model parameters.

  4. Detecting modulated signals in modulated noise: (II) neural thresholds in the songbird forebrain.

    Science.gov (United States)

    Bee, Mark A; Buschermöhle, Michael; Klump, Georg M

    2007-10-01

    Sounds in the real world fluctuate in amplitude. The vertebrate auditory system exploits patterns of amplitude fluctuations to improve signal detection in noise. One experimental paradigm demonstrating these general effects has been used in psychophysical studies of 'comodulation detection difference' (CDD). The CDD effect refers to the fact that thresholds for detecting a modulated, narrowband noise signal are lower when the envelopes of flanking bands of modulated noise are comodulated with each other, but fluctuate independently of the signal compared with conditions in which the envelopes of the signal and flanking bands are all comodulated. Here, we report results from a study of the neural correlates of CDD in European starlings (Sturnus vulgaris). We manipulated: (i) the envelope correlations between a narrowband noise signal and a masker comprised of six flanking bands of noise; (ii) the signal onset delay relative to masker onset; (iii) signal duration; and (iv) masker spectrum level. Masked detection thresholds were determined from neural responses using signal detection theory. Across conditions, the magnitude of neural CDD ranged between 2 and 8 dB, which is similar to that reported in a companion psychophysical study of starlings [U. Langemann & G.M. Klump (2007) Eur. J. Neurosci., 26, 1969-1978]. We found little evidence to suggest that neural CDD resulted from the across-channel processing of auditory grouping cues related to common envelope fluctuations and synchronous onsets between the signal and flanking bands. We discuss a within-channel model of peripheral processing that explains many of our results.

  5. Wavelet-based higher-order neural networks for mine detection in thermal IR imagery

    Science.gov (United States)

    Baertlein, Brian A.; Liao, Wen-Jiao

    2000-08-01

    An image processing technique is described for the detection of miens in RI imagery. The proposed technique is based on a third-order neural network, which processes the output of a wavelet packet transform. The technique is inherently invariant to changes in signature position, rotation and scaling. The well-known memory limitations that arise with higher-order neural networks are addressed by (1) the data compression capabilities of wavelet packets, (2) protections of the image data into a space of similar triangles, and (3) quantization of that 'triangle space'. Using these techniques, image chips of size 28 by 28, which would require 0(109) neural net weights, are processed by a network having 0(102) weights. ROC curves are presented for mine detection in real and simulated imagery.

  6. Robust recurrent neural network modeling for software fault detection and correction prediction

    International Nuclear Information System (INIS)

    Hu, Q.P.; Xie, M.; Ng, S.H.; Levitin, G.

    2007-01-01

    Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set

  7. Ultrasonographic description of canine mastitis.

    Science.gov (United States)

    Trasch, Katja; Wehrend, Axel; Bostedt, Hartwig

    2007-01-01

    Ultrasonographic images were acquired of the mammary glands of 40 bitches with physiologically lactating (n = 20) or inflamed glands (n = 20). Echogenicity, structure, homogeneity, thickness, and distinguishability of each tissue layer were assessed. Additionally, overall echogenicity was noted. In the normal lactating gland, different tissues could be differentiated easily. The parenchyma was, without exception, separated from adjacent tissues and was visible as medium echogenic tissue with a coarse-grained structure. The tissue always had some echogenic lines and anechoic areas and was slightly heterogeneous. The loss of distinct layering of the tissue was characteristic of an inflamed mammary gland and inflamed regions had reduced echogenicity. Additionally in five bitches with mastitis, the ultrasound examination was repeated five times for documentation of the progress of the illness and associated changes, supplemented with a color Doppler sonogram to assess changes in blood vessel density. Information from the examinations carried out via B-mode did not allow treatment success to be predicted. Two bitches with reduced blood vessel density centrally had a poor outcome whereas three bitches with increased blood vessel density had a good outcome. Thus, Doppler sonography might be a useful tool to obtain information of the prognosis in acute canine mastitis.

  8. Bone age detection via carpogram analysis using convolutional neural networks

    Science.gov (United States)

    Torres, Felipe; Bravo, María. Alejandra; Salinas, Emmanuel; Triana, Gustavo; Arbeláez, Pablo

    2017-11-01

    Bone age assessment is a critical factor for determining delayed development in children, which can be a sign of pathologies such as endocrine diseases, growth abnormalities, chromosomal, neurological and congenital disorders among others. In this paper we present BoneNet, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks. We train and evaluate our algorithm on a database of X-Ray images provided by the hospital Fundacion Santa Fe de Bogot ´ a with around 1500 images of patients between the ages 1 to 18. ´ We compare two different architectures to classify the given data in order to explore the generality of our method. To accomplish this, we define multiple binary age assessment problems, dividing the data by bone age and differentiating the patients by their gender. Thus, exploring several parameters, we develop BoneNet. Our approach is holistic, efficient, and modular, since it is possible for the specialists to use all the networks combined to determine how is the skeletal maturity of a patient. BoneNet achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age.

  9. Detecting phase transitions in a neural network and its application to classification of syndromes in traditional Chinese medicine

    Energy Technology Data Exchange (ETDEWEB)

    Chen, J; Xi, G [Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, 100080, Beijing (China); Wang, W [Beijing University of Chinese Medicine, 100029, Beijing (China)], E-mail: guangcheng.xi@ia.ac.cn

    2008-02-15

    Detecting phase transitions in neural networks (determined or random) presents a challenging subject for phase transitions play a key role in human brain activity. In this paper, we detect numerically phase transitions in two types of random neural network(RNN) under proper parameters.

  10. Role of PGL-I antibody detection in the diagnosis of pure neural leprosy

    NARCIS (Netherlands)

    Jardim, Marcia R.; Antunes, Sergio L. G.; Simons, Brian; Wildenbeest, Joanne G.; Nery, José Augusto C.; Illarramendi, Ximena; Moraes, Milton O.; Martinez, Alejandra N.; Oskam, Linda; Faber, William R.; Sarno, Euzenir N.; Sampaio, Elizabeth P.; Bührer-Sékula, Samira

    2005-01-01

    Pure neural leprosy (PNL) is difficult to diagnose because skin lesions and acid-fast bacilli (AFB) in slit smears are absent. At present, the gold standard for PNL diagnosis is the histopathological examination of a peripheral nerve biopsy. Even so, detection of bacteria is difficult and

  11. Detection of weed locations in leaf occluded cereal crops using a fully convolutional neural network

    DEFF Research Database (Denmark)

    Dyrmann, Mads; Nyholm Jørgensen, Rasmus; Midtiby, Henrik Skov

    2017-01-01

    This pap er presents a metho d for au tomating weed detectio n in colour images despite heavy lea f occlusion. A fully convolu tio n al neural network is used to detect the weed s. The netwo rk is trained and validated on a tot al of more than 17,000 ann otations of w eeds in images from wint er w...

  12. Anomaly based intrusion detection for a biometric identification system using neural networks

    CSIR Research Space (South Africa)

    Mgabile, T

    2012-10-01

    Full Text Available detection technique that analyses the fingerprint biometric network traffic for evidence of intrusion. The neural network algorithm that imitates the way a human brain works is used in this study to classify normal traffic and learn the correct traffic...

  13. A robust neural network-based approach for microseismic event detection

    KAUST Repository

    Akram, Jubran; Ovcharenko, Oleg; Peter, Daniel

    2017-01-01

    We present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset

  14. Convolutional neural networks for segmentation and object detection of human semen

    DEFF Research Database (Denmark)

    Nissen, Malte Stær; Krause, Oswin; Almstrup, Kristian

    2017-01-01

    We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due...

  15. Neuronal synchrony detection on single-electron neural networks

    International Nuclear Information System (INIS)

    Oya, Takahide; Asai, Tetsuya; Kagaya, Ryo; Hirose, Tetsuya; Amemiya, Yoshihito

    2006-01-01

    Synchrony detection between burst and non-burst spikes is known to be one functional example of depressing synapses. Kanazawa et al. demonstrated synchrony detection with MOS depressing synapse circuits. They found that the performance of a network with depressing synapses that discriminates between burst and random input spikes increases non-monotonically as the static device mismatch is increased. We designed a single-electron depressing synapse and constructed the same network as in Kanazawa's study to develop noise-tolerant single-electron circuits. We examined the temperature characteristics and explored possible architecture that enables single-electron circuits to operate at T > 0 K

  16. The reliability of computer analysis of ultrasonographic prostate images: the influence of inconsistent histopathology

    NARCIS (Netherlands)

    Giesen, R. J.; Huynen, A. L.; de la Rosette, J. J.; Schaafsma, H. E.; van Iersel, M. P.; Aarnink, R. G.; Debruyne, F. M.; Wijkstra, H.

    1994-01-01

    This article describes a method to investigate the influence of inconsistent histopathology during the development of tissue discrimination algorithms. Review of the pathology is performed on the biopsies used as training set of a computer system for cancer detection in ultrasonographic prostate

  17. Ultrasonographic visualization of bleeding sites can help control postpartum hemorrhage using intrauterine balloon tamponade.

    Science.gov (United States)

    Kondoh, Eiji; Konishi, Mitsunaga; Kariya, Yoshitaka; Konishi, Ikuo

    2015-01-01

    Identification of precise bleeding sites is generally important to control hemorrhage. Nevertheless, the optimal technique to detect the bleeding sites has not yet been fully defined for patients with life-threatening post partum hemorrhage. We describe that ultrasonographic visualization of bleeding sites can help control post partum hemorrhage using intrauterine balloon tamponade. © 2014 Wiley Periodicals, Inc.

  18. Model for Detection and Classification of DDoS Traffic Based on Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    D. Peraković

    2017-06-01

    Full Text Available Detection of DDoS (Distributed Denial of Service traffic is of great importance for the availability protection of services and other information and communication resources. The research presented in this paper shows the application of artificial neural networks in the development of detection and classification model for three types of DDoS attacks and legitimate network traffic. Simulation results of developed model showed accuracy of 95.6% in classification of pre-defined classes of traffic.

  19. Speed sign detection and recognition by convolutional neural networks

    NARCIS (Netherlands)

    Peemen, M.C.J.; Mesman, B.; Corporaal, H.

    2011-01-01

    From the desire to update the maximum road speed data for navigation devices, a speed sign recognition and detection system is proposed. This system should prevent accidental speeding at roads where the map data is incorrect for example due to construction work. Multiple examples of road sign

  20. Automated Breast Ultrasound Lesions Detection using Convolutional Neural Networks.

    Science.gov (United States)

    Yap, Moi Hoon; Pons, Gerard; Marti, Joan; Ganau, Sergi; Sentis, Melcior; Zwiggelaar, Reyer; Davison, Adrian K; Marti, Robert

    2017-08-07

    Breast lesion detection using ultrasound imaging is considered an important step of Computer-Aided Diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e. Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.

  1. Automatic Data Collection Design for Neural Networks Detection of ...

    African Journals Online (AJOL)

    Automated data collection is necessary to alleviate problems inherent in data collection for investigation of management frauds. Once we have gathered a realistic data, several methods then exist for proper analysis and detection of anomalous transactions. However, in Nigeria, collecting fraudulent data is relatively difficult ...

  2. Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks.

    Science.gov (United States)

    Zhong, Jiandan; Lei, Tao; Yao, Guangle

    2017-11-24

    Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.

  3. Automated sleep stage detection with a classical and a neural learning algorithm--methodological aspects.

    Science.gov (United States)

    Schwaibold, M; Schöchlin, J; Bolz, A

    2002-01-01

    For classification tasks in biosignal processing, several strategies and algorithms can be used. Knowledge-based systems allow prior knowledge about the decision process to be integrated, both by the developer and by self-learning capabilities. For the classification stages in a sleep stage detection framework, three inference strategies were compared regarding their specific strengths: a classical signal processing approach, artificial neural networks and neuro-fuzzy systems. Methodological aspects were assessed to attain optimum performance and maximum transparency for the user. Due to their effective and robust learning behavior, artificial neural networks could be recommended for pattern recognition, while neuro-fuzzy systems performed best for the processing of contextual information.

  4. A case of alkaptonuria - ultrasonographic findings.

    Science.gov (United States)

    Damian, Laura Otilia; Felea, Ioana; Boloşiu, Călin; Botar-Jid, Carolina; Fodor, Daniela; Rednic, Simona

    2013-12-01

    Alkaptonuria is a rare disease with autosomal recessive inheritance and variable expression. The weight-bearing joint involvement and spondylitis-like vertebral changes occur only after the 3rd decade. Musculoskeletal ultrasonographic findings in alkaptonuria were only rarely described, consisting mainly into enthesopathy and non-synovial tendon degeneration. We present the case of a 50 years old man with alkaptonuria and discuss the ultrasonographic findings and the relationship of the disease with chondrocalcinosis. The tendinous and synovial aspect may be peculiar and it could therefore allow recognition and screening for alkaptonuria, along with clinical and radiologic data.

  5. Ultrasonographic features of normal lower ureters

    International Nuclear Information System (INIS)

    Kim, Young Soon; Bae, M. Y.; Park, K. J.; Jeon, H. S.; Lee, J. H.

    1990-01-01

    Although ultrasonographic evaluation of the normal ureters is difficult due to bowel gas, the lower segment of the normal ureters can be visualized using the urinary bladder as an acoustic window. Authors prospetively performed ultrasonography with the standard suprapubic technique and analyzed the ultrasonographic features of normal lower ureters in 79 cases(77%). Length of visualized segment of the distal ureter ranged frp, 1.5cm to 7.2 cm and the visualized segment did not exceed 3.9mm in maximum diameter. Knowledge of sonographic features of the normal lower ureters can be helpful in the evaluation of pathologic or suspected pathologic conditions of the lower ureters

  6. Ultrasonographic ejection fraction of normal gallbladder

    Energy Technology Data Exchange (ETDEWEB)

    Park, Jin Hun; Kim, Seung Yup; Park, Yaung Hee; Kang, Ik Won; Yoon, Jong Sup [Hangang Sacred Heart Hospital, Halym College, Chuncheon (Korea, Republic of)

    1984-06-15

    Real-time ultrasonography is a simple, accurate, noninvasive and potentially valuable means of studying gallbladder size and emptying. The authors calculated ultrasonographically the ejection fraction of 80 cases of normally functioning gallbladder on oral cholecystography, from June 1983 to April 1984, at the department of radiology, Hangang Sacred Heart Hospital. The results were obtained as follows; 1. Ultrasonographic Ejection Fraction at 30 minutes after the fatty meal was 73.1{+-}16.85. 2. There was no significant difference in age and sex, statistically.

  7. Ultrasonographic Observations of the Pleural Effusion

    International Nuclear Information System (INIS)

    Lee, Dong Hoo; Park, Sung Soo; Lee, Chung Hee

    1982-01-01

    Five cases of patients with pleural effusion were evaluated by the grey-scale ultrasonography. Ultrasonography of pleural effusion in each case was represented as fluid accumulation within the pleural cavity with anechoic crescent moon shape or saddle appearance marginated by diaphragm. Ptosis of the liver with demonstrable right diaphragm was assessment in the severe right pleural effusion. it is emphasized that the practical advantages of the ultrasonographic approach were notable both in establishing diagnosis and in treatment of pleural effusion,with special regarding of noninvasiveness particularly in the women of pregnancy, of staging in the patient with malignant lymphoma, and of safety in a subsequent thoracentesis under the ultrasonographic guidance

  8. Ultrasonographic Observations of the Pleural Effusion

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Dong Hoo; Park, Sung Soo; Lee, Chung Hee [Hanyang University School of Medicine, Seoul (Korea, Republic of)

    1982-12-15

    Five cases of patients with pleural effusion were evaluated by the grey-scale ultrasonography. Ultrasonography of pleural effusion in each case was represented as fluid accumulation within the pleural cavity with anechoic crescent moon shape or saddle appearance marginated by diaphragm. Ptosis of the liver with demonstrable right diaphragm was assessment in the severe right pleural effusion. it is emphasized that the practical advantages of the ultrasonographic approach were notable both in establishing diagnosis and in treatment of pleural effusion,with special regarding of noninvasiveness particularly in the women of pregnancy, of staging in the patient with malignant lymphoma, and of safety in a subsequent thoracentesis under the ultrasonographic guidance

  9. Detection and classification of power quality disturbances using S-transform and modular neural network

    Energy Technology Data Exchange (ETDEWEB)

    Bhende, C.N.; Mishra, S.; Panigrahi, B.K. [Department of Electrical Engineering, Indian Institute of Technology, New Delhi 110016 (India)

    2008-01-15

    This paper presents an S-transform based modular neural network (NN) classifier for recognition of power quality disturbances. The excellent time - frequency resolution characteristics of the S-transform makes it an attractive candidate for the analysis of power quality (PQ) disturbances under noisy condition and has the ability to detect the disturbance correctly. On the other hand, the performance of wavelet transform (WT) degrades while detecting and localizing the disturbances in the presence of noise. Features extracted by using the S-transform are applied to a modular NN for automatic classification of the PQ disturbances that solves a relatively complex problem by decomposing it into simpler subtasks. Modularity of neural network provides better classification, model complexity reduction and better learning capability, etc. Eleven types of PQ disturbances are considered for the classification. The simulation results show that the combination of the S-transform and a modular NN can effectively detect and classify different power quality disturbances. (author)

  10. Detection of directional eye movements based on the electrooculogram signals through an artificial neural network

    International Nuclear Information System (INIS)

    Erkaymaz, Hande; Ozer, Mahmut; Orak, İlhami Muharrem

    2015-01-01

    The electrooculogram signals are very important at extracting information about detection of directional eye movements. Therefore, in this study, we propose a new intelligent detection model involving an artificial neural network for the eye movements based on the electrooculogram signals. In addition to conventional eye movements, our model also involves the detection of tic and blinking of an eye. We extract only two features from the electrooculogram signals, and use them as inputs for a feed-forwarded artificial neural network. We develop a new approach to compute these two features, which we call it as a movement range. The results suggest that the proposed model have a potential to become a new tool to determine the directional eye movements accurately

  11. Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

    Directory of Open Access Journals (Sweden)

    Min-Joo Kang

    Full Text Available A novel intrusion detection system (IDS using a deep neural network (DNN is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN, therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN bus.

  12. Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

    Science.gov (United States)

    Kang, Min-Joo; Kang, Je-Won

    2016-01-01

    A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.

  13. Neural communication patterns underlying conflict detection, resolution, and adaptation.

    Science.gov (United States)

    Oehrn, Carina R; Hanslmayr, Simon; Fell, Juergen; Deuker, Lorena; Kremers, Nico A; Do Lam, Anne T; Elger, Christian E; Axmacher, Nikolai

    2014-07-30

    In an ever-changing environment, selecting appropriate responses in conflicting situations is essential for biological survival and social success and requires cognitive control, which is mediated by dorsomedial prefrontal cortex (DMPFC) and dorsolateral prefrontal cortex (DLPFC). How these brain regions communicate during conflict processing (detection, resolution, and adaptation), however, is still unknown. The Stroop task provides a well-established paradigm to investigate the cognitive mechanisms mediating such response conflict. Here, we explore the oscillatory patterns within and between the DMPFC and DLPFC in human epilepsy patients with intracranial EEG electrodes during an auditory Stroop experiment. Data from the DLPFC were obtained from 12 patients. Thereof four patients had additional DMPFC electrodes available for interaction analyses. Our results show that an early θ (4-8 Hz) modulated enhancement of DLPFC γ-band (30-100 Hz) activity constituted a prerequisite for later successful conflict processing. Subsequent conflict detection was reflected in a DMPFC θ power increase that causally entrained DLPFC θ activity (DMPFC to DLPFC). Conflict resolution was thereafter completed by coupling of DLPFC γ power to DMPFC θ oscillations. Finally, conflict adaptation was related to increased postresponse DLPFC γ-band activity and to θ coupling in the reverse direction (DLPFC to DMPFC). These results draw a detailed picture on how two regions in the prefrontal cortex communicate to resolve cognitive conflicts. In conclusion, our data show that conflict detection, control, and adaptation are supported by a sequence of processes that use the interplay of θ and γ oscillations within and between DMPFC and DLPFC. Copyright © 2014 the authors 0270-6474/14/3410438-15$15.00/0.

  14. A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks.

    Science.gov (United States)

    Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

    2016-10-13

    The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks.

  15. Multi-view Face Detection Using Deep Convolutional Neural Networks

    OpenAIRE

    Farfade, Sachin Sudhakar; Saberian, Mohammad; Li, Li-Jia

    2015-01-01

    In this paper we consider the problem of multi-view face detection. While there has been significant research on this problem, current state-of-the-art approaches for this task require annotation of facial landmarks, e.g. TSM [25], or annotation of face poses [28, 22]. They also require training dozens of models to fully capture faces in all orientations, e.g. 22 models in HeadHunter method [22]. In this paper we propose Deep Dense Face Detector (DDFD), a method that does not require pose/lan...

  16. Ultrasonographic assessment of the male koala (Phascolarctos cinereus) reproductive tract.

    Science.gov (United States)

    Larkin, Rebecca; Palmieri, Chiara; Oishi, Motoharu; Hulse, Lyndal; Johnston, Stephen D

    2018-04-01

    Studies documenting the application of ultrasonography to depict normal and pathological changes in koalas (Phascolarctos cinereus), especially in the male, are scarce. Sixty-two wild koalas were used in this study to define ultrasonographic protocols and features for the assessment of the male koala reproductive tract. Testis, epididymis and spermatic cord were examined using a hockey stick transducer. The normal koala testis showed a homogeneous echogenicity and an obvious hyper-echoic band corresponding to the tunica albuginea. The cauda epididymis was characterised by hypo- and hyper-echoic regions and was most effectively imaged in sagittal section. The koala prostate was assessed using a micro-curved transducer positioned midline, caudal to the bladder. On transverse section, it showed distinct margins and a well-defined internal structure, although the prostatic urethra was not apparent on most scans. To image the bulbourethral glands (BGs), the hockey stick transducer was placed lateral to the cloaca. BGIII was located just below the skin, while BGII was located deeper than BGIII. BGI was too small and not sufficiently echogenic to be detected. The ultrasonographic appearance of the BGs was similar to that of the testes but with more obvious hypo-echoic stippling. This comprehensive review of the ultrasonographic appearance of normal male koala reproductive tract can be used by veterinarians and others, in zoos or those working with wild koalas, during assessment of the reproductive tract of male koalas in relation to seasonal changes in accessory gland function or for the pathological investigation of reproductive lesions and infertility problems. Copyright © 2017 Elsevier Ltd. All rights reserved.

  17. Abdominal ultrasonographic screening of adult health study participants

    International Nuclear Information System (INIS)

    Russell, W.J.; Higashi, Yoshitaka; Fukuya, Tatsuro

    1989-11-01

    To assess ultrasonography's capabilities in the detection of cancer and other diseases, abdominal ultrasonographic screening was performed for 3,707 Hiroshima and 2,294 Nagasaki atomic bomb survivors and comparison subjects who participated in the Adult Health Study from 1 November 1981 to 31 October 1985 in Hiroshima and from 1 August 1984 to 31 July 1986 in Nagasaki. A total of 20 cancers was detected, consisting of 7 hepatomas, 3 gastric cancers, 3 renal cancers, 2 cancers of the urinary bladder, and 1 cancer each of the ovary, pancreas, colon, ureter and liver (metastatic). The cancer detection rate was 0.33 %. The diagnoses of seven cancer subjects in each city were subsequently confirmed at autopsy or surgery; diagnoses of four cancer subjects in Hiroshima and two in Nagasaki were obtained from death certificates. Among the 20 cancer patients, 13 were asymptomatic. After the ultrasonographic detection and diagnosis of these 20 cancers, the medical records of each of the 20 cancer patients were reviewed for any evidence of cancer detection by other examining techniques, and the records of only 3 patients revealed such recent detection. The tumor and tissue registries were similarly checked, but no evidence of earlier diagnosis of their disease was found. Ten of the cancer patients had received ionizing radiation doses from the A-bombs ranging up to 3,421 mGy (DS86), but no correlation was established between cancer prevalence and the A-bomb doses. A variety of tumors, 259 in number and most probably benign, were also detected with ultrasonography. In addition, numerous other abnormalities were diagnosed, with prevalences of 7.7 % for cholelithiasis, 5.7 % for renal cysts, and 3.8 % for liver cysts. No statistical analysis was performed concerning the prevalence of the diseases detected. (author)

  18. Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network

    Science.gov (United States)

    Liu, Tao; Li, Ying; Cao, Ying; Shen, Qiang

    2017-10-01

    This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.

  19. T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

    OpenAIRE

    Kang, Kai; Li, Hongsheng; Yan, Junjie; Zeng, Xingyu; Yang, Bin; Xiao, Tong; Zhang, Cong; Wang, Zhe; Wang, Ruohui; Wang, Xiaogang; Ouyang, Wanli

    2016-01-01

    The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and context...

  20. Convolutional neural networks for event-related potential detection: impact of the architecture.

    Science.gov (United States)

    Cecotti, H

    2017-07-01

    The detection of brain responses at the single-trial level in the electroencephalogram (EEG) such as event-related potentials (ERPs) is a difficult problem that requires different processing steps to extract relevant discriminant features. While most of the signal and classification techniques for the detection of brain responses are based on linear algebra, different pattern recognition techniques such as convolutional neural network (CNN), as a type of deep learning technique, have shown some interests as they are able to process the signal after limited pre-processing. In this study, we propose to investigate the performance of CNNs in relation of their architecture and in relation to how they are evaluated: a single system for each subject, or a system for all the subjects. More particularly, we want to address the change of performance that can be observed between specifying a neural network to a subject, or by considering a neural network for a group of subjects, taking advantage of a larger number of trials from different subjects. The results support the conclusion that a convolutional neural network trained on different subjects can lead to an AUC above 0.9 by using an appropriate architecture using spatial filtering and shift invariant layers.

  1. Fault detection and diagnosis using statistical control charts and artificial neural networks

    International Nuclear Information System (INIS)

    Leger, R.P.; Garland, W.J.; Poehlman, W.F.S.

    1995-01-01

    In order to operate a successful plant or process, continuous improvement must be made in the areas of safety, quality and reliability. Central to this continuous improvement is the early or proactive detection and correct diagnosis of process faults. This research examines the feasibility of using Cumulative Summation (CUSUM) Control Charts and artificial neural networks together for fault detection and diagnosis (FDD). The proposed FDD strategy was tested on a model of the heat transport system of a CANDU nuclear reactor. The results of the investigation indicate that a FDD system using CUSUM Control Charts and a Radial Basis Function (RBF) neural network is not only feasible but also of promising potential. The control charts and neural network are linked together by using a characteristic fault signature pattern for each fault which is to be detected and diagnosed. When tested, the system was able to eliminate all false alarms at steady state, promptly detect 6 fault conditions and correctly diagnose 5 out of the 6 faults. The diagnosis for the sixth fault was inconclusive. (author). 9 refs., 6 tabs., 7 figs

  2. Robust fault detection of wind energy conversion systems based on dynamic neural networks.

    Science.gov (United States)

    Talebi, Nasser; Sadrnia, Mohammad Ali; Darabi, Ahmad

    2014-01-01

    Occurrence of faults in wind energy conversion systems (WECSs) is inevitable. In order to detect the occurred faults at the appropriate time, avoid heavy economic losses, ensure safe system operation, prevent damage to adjacent relevant systems, and facilitate timely repair of failed components; a fault detection system (FDS) is required. Recurrent neural networks (RNNs) have gained a noticeable position in FDSs and they have been widely used for modeling of complex dynamical systems. One method for designing an FDS is to prepare a dynamic neural model emulating the normal system behavior. By comparing the outputs of the real system and neural model, incidence of the faults can be identified. In this paper, by utilizing a comprehensive dynamic model which contains both mechanical and electrical components of the WECS, an FDS is suggested using dynamic RNNs. The presented FDS detects faults of the generator's angular velocity sensor, pitch angle sensors, and pitch actuators. Robustness of the FDS is achieved by employing an adaptive threshold. Simulation results show that the proposed scheme is capable to detect the faults shortly and it has very low false and missed alarms rate.

  3. Convolutional Neural Network-Based Shadow Detection in Images Using Visible Light Camera Sensor

    Directory of Open Access Journals (Sweden)

    Dong Seop Kim

    2018-03-01

    Full Text Available Recent developments in intelligence surveillance camera systems have enabled more research on the detection, tracking, and recognition of humans. Such systems typically use visible light cameras and images, in which shadows make it difficult to detect and recognize the exact human area. Near-infrared (NIR light cameras and thermal cameras are used to mitigate this problem. However, such instruments require a separate NIR illuminator, or are prohibitively expensive. Existing research on shadow detection in images captured by visible light cameras have utilized object and shadow color features for detection. Unfortunately, various environmental factors such as illumination change and brightness of background cause detection to be a difficult task. To overcome this problem, we propose a convolutional neural network-based shadow detection method. Experimental results with a database built from various outdoor surveillance camera environments, and from the context-aware vision using image-based active recognition (CAVIAR open database, show that our method outperforms previous works.

  4. Ship detection in optical remote sensing images based on deep convolutional neural networks

    Science.gov (United States)

    Yao, Yuan; Jiang, Zhiguo; Zhang, Haopeng; Zhao, Danpei; Cai, Bowen

    2017-10-01

    Automatic ship detection in optical remote sensing images has attracted wide attention for its broad applications. Major challenges for this task include the interference of cloud, wave, wake, and the high computational expenses. We propose a fast and robust ship detection algorithm to solve these issues. The framework for ship detection is designed based on deep convolutional neural networks (CNNs), which provide the accurate locations of ship targets in an efficient way. First, the deep CNN is designed to extract features. Then, a region proposal network (RPN) is applied to discriminate ship targets and regress the detection bounding boxes, in which the anchors are designed by intrinsic shape of ship targets. Experimental results on numerous panchromatic images demonstrate that, in comparison with other state-of-the-art ship detection methods, our method is more efficient and achieves higher detection accuracy and more precise bounding boxes in different complex backgrounds.

  5. Ultrasonographic evaluation of the canine shoulder.

    Science.gov (United States)

    Long, C D; Nyland, T G

    1999-01-01

    The aim of this study was to determine the normal ultrasonographic anatomy of the canine shoulder. Fourteen shoulders from 7 clinically normal mid-sized dogs were radiographed and imaged using high frequency ultrasound. Each shoulder was isolated postmortem, and the ultrasonographic and gross anatomy was studied during dissection. The ultrasonographic appearance of the shoulder specimens was similar to that found in the live dogs. Twenty-four shoulders isolated postmortem from 12 variably sized dogs were also used to characterize the normal ultrasound anatomy over a range of sizes. Important anatomic structures that could be consistently evaluated were the biceps tendon and bursa, the bicipital groove surface, the supraspinatous tendon, the infraspinatous tendon, the teres minor tendon, and the caudal aspect of the humeral head. Results of ultrasonographic examination of 4 dogs with shoulder lameness are described to illustrate some applications of canine shoulder ultrasonography in the evaluation of the canine shoulder. In these dogs, ultrasound was a valuable tool to evaluate effusion and synovial proliferation within the bicipital bursa, supraspinatous and biceps tendinitis, biceps tendon strain, and dystrophic calcification.

  6. Prenatal ultrasonographic findings of cloacal anomaly

    Energy Technology Data Exchange (ETDEWEB)

    Song, Mi Jin [Samsung Cheil Hospital, Sungkyunkwan University School of Medicine, Seoul (Korea, Republic of)

    2002-09-15

    To evaluate the ultrasonographic characteristic of a rare malformation comples, Cloacal anomaly on prenatal ultrasonography. From March 1991 to July 2001, eight cases with the persistent cloaca (4 cases in female and 1 case in male) and cloacal exstrophy (3 cases) diagnosed by prenatal ultrasound examination were included, and all of them were pathologically confirmed by autopsy. One radiologist retrospectively analyzed the prenatal sonographic images, including the urinary bladder, kidney, pelvic cyst, abdominal wall defect and amount of amniotic fluid. The ultrasonographic diagnosis was established at 21.8 {+-} 7.8 weeks of gestation. The prenatal ultrasonographic findings of the persistent cloaca were absent bladder (n=2), distended bladder (n=2) and small thick bladder (n=1). Sonography of the kidney showed normal (n=2), hydronephrosis (n=1), dysplasia (n=1) and unilateral hydronephrosis with absent contralateral kidney (n=1). Four fetuses showed septated pelvic cyst; three fetuses, oligohydramnios. The prenatal ultrasonographic findings of cloacal exstrophy included absent bladder (n=3), normal kidney (n=1), hydronephrosis (n=1) and absent kidney (n=1). All fetuses with cloacal exstrophy had abdominal wall defect while two of them had oligohydramnios. A prenatal diagnosis of persistent cloaca can be confidently made when there is septated pelvic cyst combined oligohydramnios, sediments within the cyst and intraluminal calcifications. Cloacal exstrophy should be included in diagnosis if there is a low abdominal wall defect with absent urinary bladder.

  7. Prenatal ultrasonographic findings of cloacal anomaly

    International Nuclear Information System (INIS)

    Song, Mi Jin

    2002-01-01

    To evaluate the ultrasonographic characteristic of a rare malformation comples, Cloacal anomaly on prenatal ultrasonography. From March 1991 to July 2001, eight cases with the persistent cloaca (4 cases in female and 1 case in male) and cloacal exstrophy (3 cases) diagnosed by prenatal ultrasound examination were included, and all of them were pathologically confirmed by autopsy. One radiologist retrospectively analyzed the prenatal sonographic images, including the urinary bladder, kidney, pelvic cyst, abdominal wall defect and amount of amniotic fluid. The ultrasonographic diagnosis was established at 21.8 ± 7.8 weeks of gestation. The prenatal ultrasonographic findings of the persistent cloaca were absent bladder (n=2), distended bladder (n=2) and small thick bladder (n=1). Sonography of the kidney showed normal (n=2), hydronephrosis (n=1), dysplasia (n=1) and unilateral hydronephrosis with absent contralateral kidney (n=1). Four fetuses showed septated pelvic cyst; three fetuses, oligohydramnios. The prenatal ultrasonographic findings of cloacal exstrophy included absent bladder (n=3), normal kidney (n=1), hydronephrosis (n=1) and absent kidney (n=1). All fetuses with cloacal exstrophy had abdominal wall defect while two of them had oligohydramnios. A prenatal diagnosis of persistent cloaca can be confidently made when there is septated pelvic cyst combined oligohydramnios, sediments within the cyst and intraluminal calcifications. Cloacal exstrophy should be included in diagnosis if there is a low abdominal wall defect with absent urinary bladder.

  8. Optimizing a neural network for detection of moving vehicles in video

    Science.gov (United States)

    Fischer, Noëlle M.; Kruithof, Maarten C.; Bouma, Henri

    2017-10-01

    In the field of security and defense, it is extremely important to reliably detect moving objects, such as cars, ships, drones and missiles. Detection and analysis of moving objects in cameras near borders could be helpful to reduce illicit trading, drug trafficking, irregular border crossing, trafficking in human beings and smuggling. Many recent benchmarks have shown that convolutional neural networks are performing well in the detection of objects in images. Most deep-learning research effort focuses on classification or detection on single images. However, the detection of dynamic changes (e.g., moving objects, actions and events) in streaming video is extremely relevant for surveillance and forensic applications. In this paper, we combine an end-to-end feedforward neural network for static detection with a recurrent Long Short-Term Memory (LSTM) network for multi-frame analysis. We present a practical guide with special attention to the selection of the optimizer and batch size. The end-to-end network is able to localize and recognize the vehicles in video from traffic cameras. We show an efficient way to collect relevant in-domain data for training with minimal manual labor. Our results show that the combination with LSTM improves performance for the detection of moving vehicles.

  9. Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode

    Directory of Open Access Journals (Sweden)

    Tao Ye

    2018-06-01

    Full Text Available Many accidents happen under shunting mode when the speed of a train is below 45 km/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net. It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 × 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.

  10. Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image

    Directory of Open Access Journals (Sweden)

    Qi Dawei

    2010-01-01

    Full Text Available A modified Hopfield neural network with a novel cost function was presented for detecting wood defects boundary in the image. Different from traditional methods, the boundary detection problem in this paper was formulated as an optimization process that sought the boundary points to minimize a cost function. An initial boundary was estimated by Canny algorithm first. The pixel gray value was described as a neuron state of Hopfield neural network. The state updated till the cost function touches the minimum value. The designed cost function ensured that few neurons were activated except the neurons corresponding to actual boundary points and ensured that the activated neurons are positioned in the points which had greatest change in gray value. The tools of Matlab were used to implement the experiment. The results show that the noises of the image are effectively removed, and our method obtains more noiseless and vivid boundary than those of the traditional methods.

  11. Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image.

    Science.gov (United States)

    Xu, Kele; Feng, Dawei; Mi, Haibo

    2017-11-23

    The automatic detection of diabetic retinopathy is of vital importance, as it is the main cause of irreversible vision loss in the working-age population in the developed world. The early detection of diabetic retinopathy occurrence can be very helpful for clinical treatment; although several different feature extraction approaches have been proposed, the classification task for retinal images is still tedious even for those trained clinicians. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. Thus, in this paper, we explored the use of deep convolutional neural network methodology for the automatic classification of diabetic retinopathy using color fundus image, and obtained an accuracy of 94.5% on our dataset, outperforming the results obtained by using classical approaches.

  12. Ultrasonographic findings of lateral epicondylitis of humerus

    International Nuclear Information System (INIS)

    Choi, Joon Hyuk; Ha, Doo Heo

    2002-01-01

    To evaluate the ultrasonographic findings of lateral epicondylitis and their relationship with clinical outcome. The findings of ultrasonographic examinations of eighteen elbow joints in 15 patients (M:F=5:10; age:38-65(mean, 47.6) years) with lateral epicondylitis were reviewed. Two patients underwent surgery, two were not treated, and the remaining 11 were treated conservatively. Symptomatic improvement was noted 1 week after conservative treatment in two cases, at 2 weeks in five cases, at 3 weeks in three cases, and at 5 weeks in one case. With patients in the 90 degree flexed elbow position and in a supinated wrist, weexamined the extensor carpi radialis brevis (ECRB) tendon around the lateral epicondyle using ultrasound equipment with a 7-11 MHz linear transducer. The findings were assessed in terms of swelling of the tendon, changes in its echotexture, the presence of calcification of cystic degeneration, loss of the hypoechoic band between the tendon and bony cortex of the lateral epicondyle, cortical irregularity of the lateral epicondyle, and fluid collection around the tendon. Any relationships between each ultrasonographic finding and the treatment interval after which symptomatic improvement was noted were evaluated. In the 18 joints, change was heterogeneous hypoechogenicity in 13, and heterogeneous mixed echogenicity in three. Other ultrasonographic findings were swelling of the tendon in ten cases, loss of the hypoechoic band in 14, cortical irregularity in five, calcification in four, cystic degeneration in nine, and fluid collection around the tendon in four. In patients treated conservatively, there was no statistically significant difference between each ultrasonographic finding and the treatment interval after which symptomatic improvement was noted. Ultrasonography can be used to assess changes in the ECRB tendon and lateral epicondyle occurring in lateral epicondylitis, but fails to provide information on the rapidity of symptomatic

  13. Ultrasonographic findings of lateral epicondylitis of humerus

    Energy Technology Data Exchange (ETDEWEB)

    Choi, Joon Hyuk; Ha, Doo Heo [Pundang CHA Univ., Seongnam (Korea, Republic of)

    2002-03-01

    To evaluate the ultrasonographic findings of lateral epicondylitis and their relationship with clinical outcome. The findings of ultrasonographic examinations of eighteen elbow joints in 15 patients (M:F=5:10; age:38-65(mean, 47.6) years) with lateral epicondylitis were reviewed. Two patients underwent surgery, two were not treated, and the remaining 11 were treated conservatively. Symptomatic improvement was noted 1 week after conservative treatment in two cases, at 2 weeks in five cases, at 3 weeks in three cases, and at 5 weeks in one case. With patients in the 90 degree flexed elbow position and in a supinated wrist, weexamined the extensor carpi radialis brevis (ECRB) tendon around the lateral epicondyle using ultrasound equipment with a 7-11 MHz linear transducer. The findings were assessed in terms of swelling of the tendon, changes in its echotexture, the presence of calcification of cystic degeneration, loss of the hypoechoic band between the tendon and bony cortex of the lateral epicondyle, cortical irregularity of the lateral epicondyle, and fluid collection around the tendon. Any relationships between each ultrasonographic finding and the treatment interval after which symptomatic improvement was noted were evaluated. In the 18 joints, change was heterogeneous hypoechogenicity in 13, and heterogeneous mixed echogenicity in three. Other ultrasonographic findings were swelling of the tendon in ten cases, loss of the hypoechoic band in 14, cortical irregularity in five, calcification in four, cystic degeneration in nine, and fluid collection around the tendon in four. In patients treated conservatively, there was no statistically significant difference between each ultrasonographic finding and the treatment interval after which symptomatic improvement was noted. Ultrasonography can be used to assess changes in the ECRB tendon and lateral epicondyle occurring in lateral epicondylitis, but fails to provide information on the rapidity of symptomatic

  14. Breast cancer detection via Hu moment invariant and feedforward neural network

    Science.gov (United States)

    Zhang, Xiaowei; Yang, Jiquan; Nguyen, Elijah

    2018-04-01

    One of eight women can get breast cancer during all her life. This study used Hu moment invariant and feedforward neural network to diagnose breast cancer. With the help of K-fold cross validation, we can test the out-of-sample accuracy of our method. Finally, we found that our methods can improve the accuracy of detecting breast cancer and reduce the difficulty of judging.

  15. Ultrasonographic findings of Myoma, H-mole and Missed abortion

    International Nuclear Information System (INIS)

    Huh, Nam Yoon; You, H. S.; Seong, K. J.; Park, C. Y.

    1982-01-01

    Ultrasonography is very important in the diagnosis of various kinds of diseases in Obsterics and Gynecology. It has high diagnostic accuracy in the diagnosis of pelvic masses and widely used for the detection of normal orpathologic pregnancy. But still it is difficult to differentiate degenerated myoma, H-mole and missed abortion by ultrasonography. So the authors analyzed the ultrasonographic findings of 81 patients with myoma(29 cases), H-mole(23 cases), and missed abortion(29 cases) and the results are as follows; 1. Diagnostic accuracy was 8.6% in myoma, 87% in H-mole and 89% in missed abortion. 2. The most typical ultrasonographic finding of myoma was obulated mass contour with nonhomogenous internal echo. 3. The most characteristic finding of H-mole was fine vesicular pattern internal echo with globular enlargement of uterus. 4. The most frequent finding of missed abortion was deformed gestational sac with or without remained fetal echo. 5. Clinical correlation was very important for accurate diagnosis, especially when differential diagnosis was very difficult between myoma with marked cystic degeneration, missed abortion with large distorted gestational sac and H-mole with severe degeneration

  16. Ultrasonographic features of intestinal adenocarcinoma in five cats

    International Nuclear Information System (INIS)

    Rivers, B.J.; Walter, P.A.; Feeney, D.A.; Johnston, G.R.

    1997-01-01

    Adenocarcinoma, followed by lymphosarcoma, are the most common feline intestinal neoplasms. Clinicopathological, survey radiographic, and ultrasonographic findings of five cats with intestinal adenocarcinoma are reported. An abdominal mass was palpable in all five cats, but the mass could be localized to bowel in only two cats. Radiographically an abdominal mass was detected in only one cat. Ultrasonographically there was a segmental intestinal mural mass in all five cats. The mass was characterized by circumferential bowel wall thickening with transmural loss of normal sonographic wall layers. In one cat, the circumferential symmetric hypoechoic bowel wall thickening was similar to that reported for segmental lymphoma. In the other four cats, the sonographic features of the thickened bowel wall were varied, being mixed echogenicity and asymmetric in 3 cats and mixed echogenicity and symmetric in one. The results of the present report suggest that sonographic observation of mixed echogenicity segmental intestinal wall thickening in the cat represents adenocarcinoma rather than lymphosarcoma, although other infiltrative diseases should be considered

  17. Fully automatic oil spill detection from COSMO-SkyMed imagery using a neural network approach

    Science.gov (United States)

    Avezzano, Ruggero G.; Del Frate, Fabio; Latini, Daniele

    2012-09-01

    The increased amount of available Synthetic Aperture Radar (SAR) images acquired over the ocean represents an extraordinary potential for improving oil spill detection activities. On the other side this involves a growing workload on the operators at analysis centers. In addition, even if the operators go through extensive training to learn manual oil spill detection, they can provide different and subjective responses. Hence, the upgrade and improvements of algorithms for automatic detection that can help in screening the images and prioritizing the alarms are of great benefit. In the framework of an ASI Announcement of Opportunity for the exploitation of COSMO-SkyMed data, a research activity (ASI contract L/020/09/0) aiming at studying the possibility to use neural networks architectures to set up fully automatic processing chains using COSMO-SkyMed imagery has been carried out and results are presented in this paper. The automatic identification of an oil spill is seen as a three step process based on segmentation, feature extraction and classification. We observed that a PCNN (Pulse Coupled Neural Network) was capable of providing a satisfactory performance in the different dark spots extraction, close to what it would be produced by manual editing. For the classification task a Multi-Layer Perceptron (MLP) Neural Network was employed.

  18. T-wave end detection using neural networks and Support Vector Machines.

    Science.gov (United States)

    Suárez-León, Alexander Alexeis; Varon, Carolina; Willems, Rik; Van Huffel, Sabine; Vázquez-Seisdedos, Carlos Román

    2018-05-01

    In this paper we propose a new approach for detecting the end of the T-wave in the electrocardiogram (ECG) using Neural Networks and Support Vector Machines. Both, Multilayer Perceptron (MLP) neural networks and Fixed-Size Least-Squares Support Vector Machines (FS-LSSVM) were used as regression algorithms to determine the end of the T-wave. Different strategies for selecting the training set such as random selection, k-means, robust clustering and maximum quadratic (Rényi) entropy were evaluated. Individual parameters were tuned for each method during training and the results are given for the evaluation set. A comparison between MLP and FS-LSSVM approaches was performed. Finally, a fair comparison of the FS-LSSVM method with other state-of-the-art algorithms for detecting the end of the T-wave was included. The experimental results show that FS-LSSVM approaches are more suitable as regression algorithms than MLP neural networks. Despite the small training sets used, the FS-LSSVM methods outperformed the state-of-the-art techniques. FS-LSSVM can be successfully used as a T-wave end detection algorithm in ECG even with small training set sizes. Copyright © 2018 Elsevier Ltd. All rights reserved.

  19. A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

    Science.gov (United States)

    Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

    2018-01-01

    In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

  20. DIGITAL DETECTION SYSTEM DESIGN OF MYCOBACTERIUM TUBERCULOSIS THROUGH EXTRACTION OF SPUTUM IMAGE USING NEURAL NETWORK METHOD

    Directory of Open Access Journals (Sweden)

    Franky Arisgraha

    2012-01-01

    Full Text Available Tuberculosis (TBC is an dangerous disease and many people has been infected. One of many important steps to control TBC effectively and efficiently is by increasing case finding using right method and accurate diagnostic. One of them is to detect Mycobacterium Tuberculosis inside sputum. Conventional detection of Mycobacterium Tuberculosis inside sputum can need a lot of time, so digitally detection method of Mycobacterium Tuberculosis was designed as an effort to get better result of detection. This method was designed by using combination between digital image processing method and Neural Network method. From testing report that was done, Mycobacterium can be detected with successful value reach 77.5% and training error less than 5%.

  1. On the robustness of EC-PC spike detection method for online neural recording.

    Science.gov (United States)

    Zhou, Yin; Wu, Tong; Rastegarnia, Amir; Guan, Cuntai; Keefer, Edward; Yang, Zhi

    2014-09-30

    Online spike detection is an important step to compress neural data and perform real-time neural information decoding. An unsupervised, automatic, yet robust signal processing is strongly desired, thus it can support a wide range of applications. We have developed a novel spike detection algorithm called "exponential component-polynomial component" (EC-PC) spike detection. We firstly evaluate the robustness of the EC-PC spike detector under different firing rates and SNRs. Secondly, we show that the detection Precision can be quantitatively derived without requiring additional user input parameters. We have realized the algorithm (including training) into a 0.13 μm CMOS chip, where an unsupervised, nonparametric operation has been demonstrated. Both simulated data and real data are used to evaluate the method under different firing rates (FRs), SNRs. The results show that the EC-PC spike detector is the most robust in comparison with some popular detectors. Moreover, the EC-PC detector can track changes in the background noise due to the ability to re-estimate the neural data distribution. Both real and synthesized data have been used for testing the proposed algorithm in comparison with other methods, including the absolute thresholding detector (AT), median absolute deviation detector (MAD), nonlinear energy operator detector (NEO), and continuous wavelet detector (CWD). Comparative testing results reveals that the EP-PC detection algorithm performs better than the other algorithms regardless of recording conditions. The EC-PC spike detector can be considered as an unsupervised and robust online spike detection. It is also suitable for hardware implementation. Copyright © 2014 Elsevier B.V. All rights reserved.

  2. Real-time camera-based face detection using a modified LAMSTAR neural network system

    Science.gov (United States)

    Girado, Javier I.; Sandin, Daniel J.; DeFanti, Thomas A.; Wolf, Laura K.

    2003-03-01

    This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

  3. Acral melanoma detection using a convolutional neural network for dermoscopy images.

    Science.gov (United States)

    Yu, Chanki; Yang, Sejung; Kim, Wonoh; Jung, Jinwoong; Chung, Kee-Yang; Lee, Sang Wook; Oh, Byungho

    2018-01-01

    Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions. A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation. The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert. Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

  4. Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks.

    Science.gov (United States)

    Cheng, Phillip M; Tejura, Tapas K; Tran, Khoa N; Whang, Gilbert

    2018-05-01

    The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

  5. DEVELOPMENT OF WEARABLE HUMAN FALL DETECTION SYSTEM USING MULTILAYER PERCEPTRON NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    Hamideh Kerdegari

    2013-02-01

    Full Text Available This paper presents an accurate wearable fall detection system which can identify the occurrence of falls among elderly population. A waist worn tri-axial accelerometer was used to capture the movement signals of human body. A set of laboratory-based falls and activities of daily living (ADL were performed by volunteers with different physical characteristics. The collected acceleration patterns were classified precisely to fall and ADL using multilayer perceptron (MLP neural network. This work was resulted to a high accuracy wearable fall-detection system with the accuracy of 91.6%.

  6. Acoustic Event Detection in Multichannel Audio Using Gated Recurrent Neural Networks with High‐Resolution Spectral Features

    Directory of Open Access Journals (Sweden)

    Hyoung‐Gook Kim

    2017-12-01

    Full Text Available Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception‐based spatial and spectral‐domain noise‐reduced harmonic features are extracted from multichannel audio and used as high‐resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short‐term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches.

  7. Detection of land cover change using an Artificial Neural Network on a time-series of MODIS satellite data

    CSIR Research Space (South Africa)

    Olivier, JC

    2007-11-01

    Full Text Available An Artificial Neural Network (ANN) is proposed to detect human-induced land cover change using a sliding window through a time-series of Moderate Resolution Imaging Spectroradiometer (MODIS) satellite surface reflectance pixel values. Training...

  8. Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network.

    Science.gov (United States)

    Diniz, Pedro Henrique Bandeira; Valente, Thales Levi Azevedo; Diniz, João Otávio Bandeira; Silva, Aristófanes Corrêa; Gattass, Marcelo; Ventura, Nina; Muniz, Bernardo Carvalho; Gasparetto, Emerson Leandro

    2018-04-19

    White matter lesions are non-static brain lesions that have a prevalence rate up to 98% in the elderly population. Because they may be associated with several brain diseases, it is important that they are detected as soon as possible. Magnetic Resonance Imaging (MRI) provides three-dimensional data with the possibility to detect and emphasize contrast differences in soft tissues, providing rich information about the human soft tissue anatomy. However, the amount of data provided for these images is far too much for manual analysis/interpretation, representing a difficult and time-consuming task for specialists. This work presents a computational methodology capable of detecting regions of white matter lesions of the brain in MRI of FLAIR modality. The techniques highlighted in this methodology are SLIC0 clustering for candidate segmentation and convolutional neural networks for candidate classification. The methodology proposed here consists of four steps: (1) images acquisition, (2) images preprocessing, (3) candidates segmentation and (4) candidates classification. The methodology was applied on 91 magnetic resonance images provided by DASA, and achieved an accuracy of 98.73%, specificity of 98.77% and sensitivity of 78.79% with 0.005 of false positives, without any false positives reduction technique, in detection of white matter lesion regions. It is demonstrated the feasibility of the analysis of brain MRI using SLIC0 and convolutional neural network techniques to achieve success in detection of white matter lesions regions. Copyright © 2018. Published by Elsevier B.V.

  9. Small-scale anomaly detection in panoramic imaging using neural models of low-level vision

    Science.gov (United States)

    Casey, Matthew C.; Hickman, Duncan L.; Pavlou, Athanasios; Sadler, James R. E.

    2011-06-01

    Our understanding of sensory processing in animals has reached the stage where we can exploit neurobiological principles in commercial systems. In human vision, one brain structure that offers insight into how we might detect anomalies in real-time imaging is the superior colliculus (SC). The SC is a small structure that rapidly orients our eyes to a movement, sound or touch that it detects, even when the stimulus may be on a small-scale; think of a camouflaged movement or the rustle of leaves. This automatic orientation allows us to prioritize the use of our eyes to raise awareness of a potential threat, such as a predator approaching stealthily. In this paper we describe the application of a neural network model of the SC to the detection of anomalies in panoramic imaging. The neural approach consists of a mosaic of topographic maps that are each trained using competitive Hebbian learning to rapidly detect image features of a pre-defined shape and scale. What makes this approach interesting is the ability of the competition between neurons to automatically filter noise, yet with the capability of generalizing the desired shape and scale. We will present the results of this technique applied to the real-time detection of obscured targets in visible-band panoramic CCTV images. Using background subtraction to highlight potential movement, the technique is able to correctly identify targets which span as little as 3 pixels wide while filtering small-scale noise.

  10. Automatic QRS complex detection using two-level convolutional neural network.

    Science.gov (United States)

    Xiang, Yande; Lin, Zhitao; Meng, Jianyi

    2018-01-29

    The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

  11. Learning representations for the early detection of sepsis with deep neural networks.

    Science.gov (United States)

    Kam, Hye Jin; Kim, Ha Young

    2017-10-01

    Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

  12. Cellular Neural Network-Based Methods for Distributed Network Intrusion Detection

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2015-01-01

    Full Text Available According to the problems of current distributed architecture intrusion detection systems (DIDS, a new online distributed intrusion detection model based on cellular neural network (CNN was proposed, in which discrete-time CNN (DTCNN was used as weak classifier in each local node and state-controlled CNN (SCCNN was used as global detection method, respectively. We further proposed a new method for design template parameters of SCCNN via solving Linear Matrix Inequality. Experimental results based on KDD CUP 99 dataset show its feasibility and effectiveness. Emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation which allows the distributed intrusion detection to be performed better.

  13. ConvNetQuake: Convolutional Neural Network for Earthquake Detection and Location

    Science.gov (United States)

    Denolle, M.; Perol, T.; Gharbi, M.

    2017-12-01

    Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. In this work, we leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for probabilistic earthquake detection and location from single stations. We apply our technique to study two years of induced seismicity in Oklahoma (USA). We detect 20 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm detection performances are at least one order of magnitude faster than other established methods.

  14. Feature Extraction and Fusion Using Deep Convolutional Neural Networks for Face Detection

    Directory of Open Access Journals (Sweden)

    Xiaojun Lu

    2017-01-01

    Full Text Available This paper proposes a method that uses feature fusion to represent images better for face detection after feature extraction by deep convolutional neural network (DCNN. First, with Clarifai net and VGG Net-D (16 layers, we learn features from data, respectively; then we fuse features extracted from the two nets. To obtain more compact feature representation and mitigate computation complexity, we reduce the dimension of the fused features by PCA. Finally, we conduct face classification by SVM classifier for binary classification. In particular, we exploit offset max-pooling to extract features with sliding window densely, which leads to better matches of faces and detection windows; thus the detection result is more accurate. Experimental results show that our method can detect faces with severe occlusion and large variations in pose and scale. In particular, our method achieves 89.24% recall rate on FDDB and 97.19% average precision on AFW.

  15. Detection of outliers by neural network on the gas centrifuge experimental data of isotopic separation process

    International Nuclear Information System (INIS)

    Andrade, Monica de Carvalho Vasconcelos

    2004-01-01

    This work presents and discusses the neural network technique aiming at the detection of outliers on a set of gas centrifuge isotope separation experimental data. In order to evaluate the application of this new technique, the result obtained of the detection is compared to the result of the statistical analysis combined with the cluster analysis. This method for the detection of outliers presents a considerable potential in the field of data analysis and it is at the same time easier and faster to use and requests very less knowledge of the physics involved in the process. This work established a procedure for detecting experiments which are suspect to contain gross errors inside a data set where the usual techniques for identification of these errors cannot be applied or its use/demands an excessively long work. (author)

  16. Model-based fault detection and isolation of a PWR nuclear power plant using neural networks

    International Nuclear Information System (INIS)

    Far, R.R.; Davilu, H.; Lucas, C.

    2008-01-01

    The proper and timely fault detection and isolation of industrial plant is of premier importance to guarantee the safe and reliable operation of industrial plants. The paper presents application of a neural networks-based scheme for fault detection and isolation, for the pressurizer of a PWR nuclear power plant. The scheme is constituted by 2 components: residual generation and fault isolation. The first component generates residuals via the discrepancy between measurements coming from the plant and a nominal model. The neutral network estimator is trained with healthy data collected from a full-scale simulator. For the second component detection thresholds are used to encode the residuals as bipolar vectors which represent fault patterns. These patterns are stored in an associative memory based on a recurrent neutral network. The proposed fault diagnosis tool is evaluated on-line via a full-scale simulator detected and isolate the main faults appearing in the pressurizer of a PWR. (orig.)

  17. Low-complexity object detection with deep convolutional neural network for embedded systems

    Science.gov (United States)

    Tripathi, Subarna; Kang, Byeongkeun; Dane, Gokce; Nguyen, Truong

    2017-09-01

    We investigate low-complexity convolutional neural networks (CNNs) for object detection for embedded vision applications. It is well-known that consolidation of an embedded system for CNN-based object detection is more challenging due to computation and memory requirement comparing with problems like image classification. To achieve these requirements, we design and develop an end-to-end TensorFlow (TF)-based fully-convolutional deep neural network for generic object detection task inspired by one of the fastest framework, YOLO.1 The proposed network predicts the localization of every object by regressing the coordinates of the corresponding bounding box as in YOLO. Hence, the network is able to detect any objects without any limitations in the size of the objects. However, unlike YOLO, all the layers in the proposed network is fully-convolutional. Thus, it is able to take input images of any size. We pick face detection as an use case. We evaluate the proposed model for face detection on FDDB dataset and Widerface dataset. As another use case of generic object detection, we evaluate its performance on PASCAL VOC dataset. The experimental results demonstrate that the proposed network can predict object instances of different sizes and poses in a single frame. Moreover, the results show that the proposed method achieves comparative accuracy comparing with the state-of-the-art CNN-based object detection methods while reducing the model size by 3× and memory-BW by 3 - 4× comparing with one of the best real-time CNN-based object detectors, YOLO. Our 8-bit fixed-point TF-model provides additional 4× memory reduction while keeping the accuracy nearly as good as the floating-point model. Moreover, the fixed- point model is capable of achieving 20× faster inference speed comparing with the floating-point model. Thus, the proposed method is promising for embedded implementations.

  18. Online Particle Detection by Neural Networks Based on Topologic Calorimetry Information

    CERN Document Server

    Ciodaro, T; The ATLAS collaboration; Damazio, D; de Seixas, JM

    2011-01-01

    This paper presents the last results from the Ringer algorithm, which is based on artificial neural networks for the electron identification at the online filtering system of the ATLAS particle detector, in the context of the LHC experiment at CERN. The algorithm performs topological feature extraction over the ATLAS calorimetry information (energy measurements). Later, the extracted information is presented to a neural network classifier. Studies showed that the Ringer algorithm achieves high detection efficiency, while keeping the false alarm rate low. Optimizations, guided by detailed analysis, reduced the algorithm execution time in 59%. Also, the payload necessary to store the Ringer algorithm information represents less than 6.2 percent of the total filtering system amount

  19. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

    Science.gov (United States)

    Acharya, U Rajendra; Oh, Shu Lih; Hagiwara, Yuki; Tan, Jen Hong; Adeli, Hojjat

    2017-09-27

    An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.

  20. Detection of broken rotor bar faults in induction motor at low load using neural network.

    Science.gov (United States)

    Bessam, B; Menacer, A; Boumehraz, M; Cherif, H

    2016-09-01

    The knowledge of the broken rotor bars characteristic frequencies and amplitudes has a great importance for all related diagnostic methods. The monitoring of motor faults requires a high resolution spectrum to separate different frequency components. The Discrete Fourier Transform (DFT) has been widely used to achieve these requirements. However, at low slip this technique cannot give good results. As a solution for these problems, this paper proposes an efficient technique based on a neural network approach and Hilbert transform (HT) for broken rotor bar diagnosis in induction machines at low load. The Hilbert transform is used to extract the stator current envelope (SCE). Two features are selected from the (SCE) spectrum (the amplitude and frequency of the harmonic). These features will be used as input for neural network. The results obtained are astonishing and it is capable to detect the correct number of broken rotor bars under different load conditions. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

  1. Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcifications

    Energy Technology Data Exchange (ETDEWEB)

    Zheng, B. [Univ. of South Florida, Tampa, FL (United States)]|[Nanjing Univ. of Posts and Telecommunications (China). Dept. of Telecommunication Engineering; Qian, W.; Clarke, L.P. [Univ. of South Florida, Tampa, FL (United States)

    1996-10-01

    A computationally efficient mixed feature based neural network (MFNN) is proposed for the detection of microcalcification clusters (MCC`s) in digitized mammograms. The MFNN employs features computed in both the spatial and spectral domain and uses spectral entropy as a decision parameter. Backpropagation with Kalman Filtering (KF) is employed to allow more efficient network training as required for evaluation of different features, input images, and related error analysis. A previously reported, wavelet-based image-enhancement method is also employed to enhance microcalcification clusters for improved detection. The relative performance of the MFNN for both the raw and enhanced images is evaluated using a common image database of 30 digitized mammograms, with 20 images containing 21 biopsy proven MCC`s and ten normal cases. The computed sensitivity (true positive (TP) detection rate) was 90.1% with an average low false positive (FP) detection of 0.71 MCCs/image for the enhanced images using a modified k-fold validation error estimation technique. The corresponding computed sensitivity for the raw images was reduced to 81.4% and with 0.59 FP`s MCCs/image. A relative comparison to an earlier neural network (NN) design, using only spatially related features, suggests the importance of the addition of spectral domain features when the raw image data are analyzed.

  2. Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcifications

    International Nuclear Information System (INIS)

    Zheng, B.

    1996-01-01

    A computationally efficient mixed feature based neural network (MFNN) is proposed for the detection of microcalcification clusters (MCC's) in digitized mammograms. The MFNN employs features computed in both the spatial and spectral domain and uses spectral entropy as a decision parameter. Backpropagation with Kalman Filtering (KF) is employed to allow more efficient network training as required for evaluation of different features, input images, and related error analysis. A previously reported, wavelet-based image-enhancement method is also employed to enhance microcalcification clusters for improved detection. The relative performance of the MFNN for both the raw and enhanced images is evaluated using a common image database of 30 digitized mammograms, with 20 images containing 21 biopsy proven MCC's and ten normal cases. The computed sensitivity (true positive (TP) detection rate) was 90.1% with an average low false positive (FP) detection of 0.71 MCCs/image for the enhanced images using a modified k-fold validation error estimation technique. The corresponding computed sensitivity for the raw images was reduced to 81.4% and with 0.59 FP's MCCs/image. A relative comparison to an earlier neural network (NN) design, using only spatially related features, suggests the importance of the addition of spectral domain features when the raw image data are analyzed

  3. A fast button surface defects detection method based on convolutional neural network

    Science.gov (United States)

    Liu, Lizhe; Cao, Danhua; Wu, Songlin; Wu, Yubin; Wei, Taoran

    2018-01-01

    Considering the complexity of the button surface texture and the variety of buttons and defects, we propose a fast visual method for button surface defect detection, based on convolutional neural network (CNN). CNN has the ability to extract the essential features by training, avoiding designing complex feature operators adapted to different kinds of buttons, textures and defects. Firstly, we obtain the normalized button region and then use HOG-SVM method to identify the front and back side of the button. Finally, a convolutional neural network is developed to recognize the defects. Aiming at detecting the subtle defects, we propose a network structure with multiple feature channels input. To deal with the defects of different scales, we take a strategy of multi-scale image block detection. The experimental results show that our method is valid for a variety of buttons and able to recognize all kinds of defects that have occurred, including dent, crack, stain, hole, wrong paint and uneven. The detection rate exceeds 96%, which is much better than traditional methods based on SVM and methods based on template match. Our method can reach the speed of 5 fps on DSP based smart camera with 600 MHz frequency.

  4. Detection of material property errors in handbooks and databases using artificial neural networks with hidden correlations

    Science.gov (United States)

    Zhang, Y. M.; Evans, J. R. G.; Yang, S. F.

    2010-11-01

    The authors have discovered a systematic, intelligent and potentially automatic method to detect errors in handbooks and stop their transmission using unrecognised relationships between materials properties. The scientific community relies on the veracity of scientific data in handbooks and databases, some of which have a long pedigree covering several decades. Although various outlier-detection procedures are employed to detect and, where appropriate, remove contaminated data, errors, which had not been discovered by established methods, were easily detected by our artificial neural network in tables of properties of the elements. We started using neural networks to discover unrecognised relationships between materials properties and quickly found that they were very good at finding inconsistencies in groups of data. They reveal variations from 10 to 900% in tables of property data for the elements and point out those that are most probably correct. Compared with the statistical method adopted by Ashby and co-workers [Proc. R. Soc. Lond. Ser. A 454 (1998) p. 1301, 1323], this method locates more inconsistencies and could be embedded in database software for automatic self-checking. We anticipate that our suggestion will be a starting point to deal with this basic problem that affects researchers in every field. The authors believe it may eventually moderate the current expectation that data field error rates will persist at between 1 and 5%.

  5. Automatic detection of kidney in 3D pediatric ultrasound images using deep neural networks

    Science.gov (United States)

    Tabrizi, Pooneh R.; Mansoor, Awais; Biggs, Elijah; Jago, James; Linguraru, Marius George

    2018-02-01

    Ultrasound (US) imaging is the routine and safe diagnostic modality for detecting pediatric urology problems, such as hydronephrosis in the kidney. Hydronephrosis is the swelling of one or both kidneys because of the build-up of urine. Early detection of hydronephrosis can lead to a substantial improvement in kidney health outcomes. Generally, US imaging is a challenging modality for the evaluation of pediatric kidneys with different shape, size, and texture characteristics. The aim of this study is to present an automatic detection method to help kidney analysis in pediatric 3DUS images. The method localizes the kidney based on its minimum volume oriented bounding box) using deep neural networks. Separate deep neural networks are trained to estimate the kidney position, orientation, and scale, making the method computationally efficient by avoiding full parameter training. The performance of the method was evaluated using a dataset of 45 kidneys (18 normal and 27 diseased kidneys diagnosed with hydronephrosis) through the leave-one-out cross validation method. Quantitative results show the proposed detection method could extract the kidney position, orientation, and scale ratio with root mean square values of 1.3 +/- 0.9 mm, 6.34 +/- 4.32 degrees, and 1.73 +/- 0.04, respectively. This method could be helpful in automating kidney segmentation for routine clinical evaluation.

  6. Arm and neck pain in ultrasonographers.

    Science.gov (United States)

    Claes, Frank; Berger, Jan; Stassijns, Gaëtane

    2015-03-01

    The aim of this study was to evaluate the prevalence of upper-body-quadrant pain among ultrasonographers and to evaluate the association between individual ergonomics, musculoskeletal disorders, and occurrence of neck pain. A hundred and ten (N = 110) Belgian and Dutch male and female hospital ultrasonographers were consecutively enrolled in the study. Data on work-related ergonomic and musculoskeletal disorders were collected with an electronic inquiry, including questions regarding ergonomics (position of the screen, high-low table, and ergonomic chair), symptoms (neck pain, upper-limb pain), and work-related factors (consecutive working hours a day, average working hours a week). Subjects with the screen on their left had significantly more neck pain (odds ratio [OR] = 3.6, p = .0286). Depending on the workspace, high-low tables increased the chance of developing neck pain (OR = 12.9, p = .0246). A screen at eye level caused less neck pain (OR = .22, p = .0610). Employees with a fixed working space were less susceptible to arm pain (OR = 0.13, p = .0058). The prevalence of arm pain was significantly higher for the vascular department compared to radiology, urology, and gynecology departments (OR = 9.2, p = .0278). Regarding prevention of upper-limb pain in ultrasonograph, more attention should be paid to the work environment and more specialty to the ultrasound workstation layout. Primary ergonomic prevention could provide a painless work situation for the ultrasonographer. Further research on the ergonomic conditions of ultrasonography is necessary to develop ergonomic solutions in the work environment that will help to alleviate neck and arm pain. © 2014, Human Factors and Ergonomics Society.

  7. Pancreatic pseudocysts. Radiological and ultrasonographic studies

    Energy Technology Data Exchange (ETDEWEB)

    Contrera, J.D.; Uemura, L.; Palma, J.K.; Souza, L.P. de; Ferraz, L.R.L.; Magalhaes, P.J.A. (Sao Paulo Univ., Ribeirao Preto (Brazil). Faculdade de Medicina)

    Radiological and ultrasonographic studies of ten patients with surgically confirmed pancreatic pseudocysts were reviewed. All of them were male, with previous story of chronic alcoholism and clinical evidences of pancreatitis. The most important radiological finding consisted of a mass opacifying the epigastrium, displacing the stomach and bowel loops. ultrasound studies showed that the lesions were predominantly cystic, rounded or oval-shaped with smooth or irregular contours and of various sizes.

  8. Fungal myositis in children: serial ultrasonographic findings

    Energy Technology Data Exchange (ETDEWEB)

    Kwon, Jung Hwa; Lee, Hee Jung; Choi, Jin Soo [Keimyung University School of Medicine, Daegu (Korea, Republic of)

    2003-08-01

    To evaluate serial ultrasonographic findings of fungal myositis in children. Eleven lesions caused by fungal myositis and occurring in six children were included in this study. Eight lesions in five children were histopathologically proven and the other three were clinically diagnosed. Serial ultrasonographic findings were retrospectively evaluated in terms of size, location, margin, internal echotexture and adjacent cortical change occurring during the follow-up period ranging from five days to two months. Three patients (50%) had multiple lesions. The sites of involvment were the thigh (n=4), calf (n=3), chest wall (n=2), abdominal wall (n=1) and forearm (n=1). Initially, diffuse muscular swelling was revealed, with ill-defined hypoechoic lesions confined to the muscle layer (n=8). Follow-up examination of eight lesions over a period of 5-10 days showed that round central echogenic lesions were surrounded by previous slightly echogenic lesions (n=6, 75%). Long-term follow-up of five lesions over a two-month period revealed periosteal thickening in one case (20%), and the peristence of echogenic solid nodules in four (80%). Pathologic examination showed that the central lesions correlated with a fungus ball and the peripheral slightly echogenic lesions corresponded to hematoma and necrosis. Serial ultrasonographic findings of fungal myositis in children revealed relatively constant features in each case. In particular, the findings of muscular necrosis and a fungus ball over a period of 5-14 days were thought to be characteristic.

  9. Fungal myositis in children: serial ultrasonographic findings

    International Nuclear Information System (INIS)

    Kwon, Jung Hwa; Lee, Hee Jung; Choi, Jin Soo

    2003-01-01

    To evaluate serial ultrasonographic findings of fungal myositis in children. Eleven lesions caused by fungal myositis and occurring in six children were included in this study. Eight lesions in five children were histopathologically proven and the other three were clinically diagnosed. Serial ultrasonographic findings were retrospectively evaluated in terms of size, location, margin, internal echotexture and adjacent cortical change occurring during the follow-up period ranging from five days to two months. Three patients (50%) had multiple lesions. The sites of involvment were the thigh (n=4), calf (n=3), chest wall (n=2), abdominal wall (n=1) and forearm (n=1). Initially, diffuse muscular swelling was revealed, with ill-defined hypoechoic lesions confined to the muscle layer (n=8). Follow-up examination of eight lesions over a period of 5-10 days showed that round central echogenic lesions were surrounded by previous slightly echogenic lesions (n=6, 75%). Long-term follow-up of five lesions over a two-month period revealed periosteal thickening in one case (20%), and the peristence of echogenic solid nodules in four (80%). Pathologic examination showed that the central lesions correlated with a fungus ball and the peripheral slightly echogenic lesions corresponded to hematoma and necrosis. Serial ultrasonographic findings of fungal myositis in children revealed relatively constant features in each case. In particular, the findings of muscular necrosis and a fungus ball over a period of 5-14 days were thought to be characteristic

  10. Ultrasonographic anatomy of bearded dragons (Pogona vitticeps).

    Science.gov (United States)

    Bucy, Daniel S; Guzman, David Sanchez-Migallon; Zwingenberger, Allison L

    2015-04-15

    To determine which organs can be reliably visualized ultrasonographically in bearded dragons (Pogona vitticeps), describe their normal ultrasonographic appearance, and describe an ultrasonographic technique for use with this species. Cross-sectional study. 14 healthy bearded dragons (6 females and 8 males). Bearded dragons were manually restrained in dorsal and sternal recumbency, and coelomic organs were evaluated by use of linear 7- to 15-MHz and microconvex 5- to 8-MHz transducers. Visibility, size, echogenicity, and ultrasound transducer position were assessed for each organ. Coelomic ultrasonography with both microconvex and linear ultrasound transducers allowed for visualization of the heart, pleural surface of the lungs, liver, caudal vena cava, aorta, ventral abdominal vein, gallbladder, fat bodies, gastric fundus, cecum, colon, cloaca, kidneys, and testes or ovaries in all animals. The pylorus was visualized in 12 of 14 animals. The small intestinal loops were visualized in 12 of 14 animals with the linear transducer, but could not be reliably identified with the microconvex transducer. The hemipenes were visualized in 7 of 8 males. The adrenal glands and spleen were not identified in any animal. Anechoic free coelomic fluid was present in 11 of 14 animals. Heart width, heart length, ventricular wall thickness, gastric fundus wall thickness, and height of the caudal poles of the kidneys were positively associated with body weight. Testis width was negatively associated with body weight in males. Results indicated coelomic ultrasonography is a potentially valuable imaging modality for assessment of most organs in bearded dragons and can be performed in unsedated animals.

  11. Subject independent facial expression recognition with robust face detection using a convolutional neural network.

    Science.gov (United States)

    Matsugu, Masakazu; Mori, Katsuhiko; Mitari, Yusuke; Kaneda, Yuji

    2003-01-01

    Reliable detection of ordinary facial expressions (e.g. smile) despite the variability among individuals as well as face appearance is an important step toward the realization of perceptual user interface with autonomous perception of persons. We describe a rule-based algorithm for robust facial expression recognition combined with robust face detection using a convolutional neural network. In this study, we address the problem of subject independence as well as translation, rotation, and scale invariance in the recognition of facial expression. The result shows reliable detection of smiles with recognition rate of 97.6% for 5600 still images of more than 10 subjects. The proposed algorithm demonstrated the ability to discriminate smiling from talking based on the saliency score obtained from voting visual cues. To the best of our knowledge, it is the first facial expression recognition model with the property of subject independence combined with robustness to variability in facial appearance.

  12. Global detection of live virtual machine migration based on cellular neural networks.

    Science.gov (United States)

    Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

    2014-01-01

    In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM) migration detection algorithm based on the cellular neural networks (CNNs), is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation allowing the VM migration detection to be performed better.

  13. Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks

    Science.gov (United States)

    Sun, Bo; Cao, Siming; He, Jun; Yu, Lejun; Li, Liandong

    2017-03-01

    Constrained by the physiology, the temporal factors associated with human behavior, irrespective of facial movement or body gesture, are described by four phases: neutral, onset, apex, and offset. Although they may benefit related recognition tasks, it is not easy to accurately detect such temporal segments. An automatic temporal segment detection framework using bilateral long short-term memory recurrent neural networks (BLSTM-RNN) to learn high-level temporal-spatial features, which synthesizes the local and global temporal-spatial information more efficiently, is presented. The framework is evaluated in detail over the face and body database (FABO). The comparison shows that the proposed framework outperforms state-of-the-art methods for solving the problem of temporal segment detection.

  14. Attacks and Intrusion Detection in Cloud Computing Using Neural Networks and Particle Swarm Optimization Algorithms

    Directory of Open Access Journals (Sweden)

    Ahmad Shokuh Saljoughi

    2018-01-01

    Full Text Available Today, cloud computing has become popular among users in organizations and companies. Security and efficiency are the two major issues facing cloud service providers and their customers. Since cloud computing is a virtual pool of resources provided in an open environment (Internet, cloud-based services entail security risks. Detection of intrusions and attacks through unauthorized users is one of the biggest challenges for both cloud service providers and cloud users. In the present study, artificial intelligence techniques, e.g. MLP Neural Network sand particle swarm optimization algorithm, were used to detect intrusion and attacks. The methods were tested for NSL-KDD, KDD-CUP datasets. The results showed improved accuracy in detecting attacks and intrusions by unauthorized users.

  15. Efficient airport detection using region-based fully convolutional neural networks

    Science.gov (United States)

    Xin, Peng; Xu, Yuelei; Zhang, Xulei; Ma, Shiping; Li, Shuai; Lv, Chao

    2018-04-01

    This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

  16. Global Detection of Live Virtual Machine Migration Based on Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2014-01-01

    Full Text Available In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM migration detection algorithm based on the cellular neural networks (CNNs, is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation allowing the VM migration detection to be performed better.

  17. Artificial neural network techniques to improve the ability of optical coherence tomography to detect optic neuritis.

    Science.gov (United States)

    Garcia-Martin, Elena; Herrero, Raquel; Bambo, Maria P; Ara, Jose R; Martin, Jesus; Polo, Vicente; Larrosa, Jose M; Garcia-Feijoo, Julian; Pablo, Luis E

    2015-01-01

    To analyze the ability of Spectralis optical coherence tomography (OCT) to detect multiple sclerosis (MS) and to distinguish MS eyes with antecedent optic neuritis (ON). To analyze the capability of artificial neural network (ANN) techniques to improve the diagnostic precision. MS patients and controls were enrolled (n = 217). OCT was used to determine the 768 retinal nerve fiber layer thicknesses. Sensitivity and specificity were evaluated to test the ability of OCT to discriminate between MS and healthy eyes, and between MS with and without antecedent ON using ANN. Using ANN technique multilayer perceptrons, OCT could detect MS with a sensitivity of 89.3%, a specificity of 87.6%, and a diagnostic precision of 88.5%. Compared with the OCT-provided parameters, the ANN had a better sensitivity-specificity balance. ANN technique improves the capability of Spectralis OCT to detect MS disease and to distinguish MS eyes with or without antecedent ON.

  18. Early detection of incipient faults in power plants using accelerated neural network learning

    International Nuclear Information System (INIS)

    Parlos, A.G.; Jayakumar, M.; Atiya, A.

    1992-01-01

    An important aspect of power plant automation is the development of computer systems able to detect and isolate incipient (slowly developing) faults at the earliest possible stages of their occurrence. In this paper, the development and testing of such a fault detection scheme is presented based on recognition of sensor signatures during various failure modes. An accelerated learning algorithm, namely adaptive backpropagation (ABP), has been developed that allows the training of a multilayer perceptron (MLP) network to a high degree of accuracy, with an order of magnitude improvement in convergence speed. An artificial neural network (ANN) has been successfully trained using the ABP algorithm, and it has been extensively tested with simulated data to detect and classify incipient faults of various types and severity and in the presence of varying sensor noise levels

  19. A robust neural network-based approach for microseismic event detection

    KAUST Repository

    Akram, Jubran

    2017-08-17

    We present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset for event detection. The input features used include the average of absolute amplitudes, variance, energy-ratio and polarization rectilinearity. These features are calculated in a moving-window of same length for the entire waveform. The output is set as a user-specified relative probability curve, which provides a robust way of distinguishing between weak and strong events. An optimal network is selected by studying the weight-based saliency and effect of number of neurons on the predicted results. Using synthetic data examples, we demonstrate that this approach is effective in detecting weaker events and reduces the number of false positives.

  20. Is Neural Activity Detected by ERP-Based Brain-Computer Interfaces Task Specific?

    Directory of Open Access Journals (Sweden)

    Markus A Wenzel

    Full Text Available Brain-computer interfaces (BCIs that are based on event-related potentials (ERPs can estimate to which stimulus a user pays particular attention. In typical BCIs, the user silently counts the selected stimulus (which is repeatedly presented among other stimuli in order to focus the attention. The stimulus of interest is then inferred from the electroencephalogram (EEG. Detecting attention allocation implicitly could be also beneficial for human-computer interaction (HCI, because it would allow software to adapt to the user's interest. However, a counting task would be inappropriate for the envisaged implicit application in HCI. Therefore, the question was addressed if the detectable neural activity is specific for silent counting, or if it can be evoked also by other tasks that direct the attention to certain stimuli.Thirteen people performed a silent counting, an arithmetic and a memory task. The tasks required the subjects to pay particular attention to target stimuli of a random color. The stimulus presentation was the same in all three tasks, which allowed a direct comparison of the experimental conditions.Classifiers that were trained to detect the targets in one task, according to patterns present in the EEG signal, could detect targets in all other tasks (irrespective of some task-related differences in the EEG.The neural activity detected by the classifiers is not strictly task specific but can be generalized over tasks and is presumably a result of the attention allocation or of the augmented workload. The results may hold promise for the transfer of classification algorithms from BCI research to implicit relevance detection in HCI.

  1. Detecting and Predicting Muscle Fatigue during Typing By SEMG Signal Processing and Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Elham Ghoochani

    2011-03-01

    Full Text Available Introduction: Repetitive strain injuries are one of the most prevalent problems in occupational diseases. Repetition, vibration and bad postures of the extremities are physical risk factors related to work that can cause chronic musculoskeletal disorders. Repetitive work on a computer with low level contraction requires the posture to be maintained for a long time, which can cause muscle fatigue. Muscle fatigue in shoulders and neck is one of the most prevalent problems reported with computer users especially during typing. Surface electromyography (SEMG signals are used for detecting muscle fatigue as a non-invasive method. Material and Methods: Nine healthy females volunteered for signal recoding during typing. EMG signals were recorded from the trapezius muscle, which is subjected to muscle fatigue during typing.  After signal analysis and feature extraction, detecting and predicting muscle fatigue was performed by using the MLP artificial neural network. Results: Recorded signals were analyzed in time and frequency domains for feature extraction. Results of classification showed that the MLP neural network can detect and predict muscle fatigue during typing with 80.79 % ± 1.04% accuracy. Conclusion: Intelligent classification and prediction of muscle fatigue can have many applications in human factors engineering (ergonomics, rehabilitation engineering and biofeedback equipment for mitigating the injuries of repetitive works.

  2. Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection

    Directory of Open Access Journals (Sweden)

    Erik Marchi

    2017-01-01

    Full Text Available In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F-measure over the three databases.

  3. Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection.

    Science.gov (United States)

    Marchi, Erik; Vesperini, Fabio; Squartini, Stefano; Schuller, Björn

    2017-01-01

    In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F -measure over the three databases.

  4. A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems.

    Science.gov (United States)

    Raman, M R Gauthama; Somu, Nivethitha; Kirthivasan, Kannan; Sriram, V S Shankar

    2017-08-01

    Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks. Copyright © 2017 Elsevier Ltd. All rights reserved.

  5. A research about breast cancer detection using different neural networks and K-MICA algorithm

    Directory of Open Access Journals (Sweden)

    A A Kalteh

    2013-01-01

    Full Text Available Breast cancer is the second leading cause of death for women all over the world. The correct diagnosis of breast cancer is one of the major problems in the medical field. From the literature it has been found that different pattern recognition techniques can help them to improve in this domain. This paper presents a novel hybrid intelligent method for detection of breast cancer. The proposed method includes two main modules: Clustering module and the classifier module. In the clustering module, first the input data will be clustered by a new technique. This technique is a suitable combination of the modified imperialist competitive algorithm (MICA and K-means algorithm. Then the Euclidean distance of each pattern is computed from the determined clusters. The classifier module determines the membership of the patterns using the computed distance. In this module, several neural networks, such as the multilayer perceptron, probabilistic neural networks and the radial basis function neural networks are investigated. Using the experimental study, we choose the best classifier in order to recognize the breast cancer. The proposed system is tested on Wisconsin Breast Cancer (WBC database and the simulation results show that the recommended system has high accuracy.

  6. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

    Science.gov (United States)

    Abdeljaber, Osama; Avci, Onur; Kiranyaz, Serkan; Gabbouj, Moncef; Inman, Daniel J.

    2017-02-01

    Structural health monitoring (SHM) and vibration-based structural damage detection have been a continuous interest for civil, mechanical and aerospace engineers over the decades. Early and meticulous damage detection has always been one of the principal objectives of SHM applications. The performance of a classical damage detection system predominantly depends on the choice of the features and the classifier. While the fixed and hand-crafted features may either be a sub-optimal choice for a particular structure or fail to achieve the same level of performance on another structure, they usually require a large computation power which may hinder their usage for real-time structural damage detection. This paper presents a novel, fast and accurate structural damage detection system using 1D Convolutional Neural Networks (CNNs) that has an inherent adaptive design to fuse both feature extraction and classification blocks into a single and compact learning body. The proposed method performs vibration-based damage detection and localization of the damage in real-time. The advantage of this approach is its ability to extract optimal damage-sensitive features automatically from the raw acceleration signals. Large-scale experiments conducted on a grandstand simulator revealed an outstanding performance and verified the computational efficiency of the proposed real-time damage detection method.

  7. Ear Detection under Uncontrolled Conditions with Multiple Scale Faster Region-Based Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Yi Zhang

    2017-04-01

    Full Text Available Ear detection is an important step in ear recognition approaches. Most existing ear detection techniques are based on manually designing features or shallow learning algorithms. However, researchers found that the pose variation, occlusion, and imaging conditions provide a great challenge to the traditional ear detection methods under uncontrolled conditions. This paper proposes an efficient technique involving Multiple Scale Faster Region-based Convolutional Neural Networks (Faster R-CNN to detect ears from 2D profile images in natural images automatically. Firstly, three regions of different scales are detected to infer the information about the ear location context within the image. Then an ear region filtering approach is proposed to extract the correct ear region and eliminate the false positives automatically. In an experiment with a test set of 200 web images (with variable photographic conditions, 98% of ears were accurately detected. Experiments were likewise conducted on the Collection J2 of University of Notre Dame Biometrics Database (UND-J2 and University of Beira Interior Ear dataset (UBEAR, which contain large occlusion, scale, and pose variations. Detection rates of 100% and 98.22%, respectively, demonstrate the effectiveness of the proposed approach.

  8. Alcoholism detection in magnetic resonance imaging by Haar wavelet transform and back propagation neural network

    Science.gov (United States)

    Yu, Yali; Wang, Mengxia; Lima, Dimas

    2018-04-01

    In order to develop a novel alcoholism detection method, we proposed a magnetic resonance imaging (MRI)-based computer vision approach. We first use contrast equalization to increase the contrast of brain slices. Then, we perform Haar wavelet transform and principal component analysis. Finally, we use back propagation neural network (BPNN) as the classification tool. Our method yields a sensitivity of 81.71±4.51%, a specificity of 81.43±4.52%, and an accuracy of 81.57±2.18%. The Haar wavelet gives better performance than db4 wavelet and sym3 wavelet.

  9. Spot detection in microscopy images using Convolutional Neural Network with sliding-window approach

    CSIR Research Space (South Africa)

    Mabaso, Matsilele A

    2018-01-01

    Full Text Available stream_source_info Mabaso_20271_2018.pdf.txt stream_content_type text/plain stream_size 24351 Content-Encoding UTF-8 stream_name Mabaso_20271_2018.pdf.txt Content-Type text/plain; charset=UTF-8 Spot Detection....n. Krizhevsky, A., Sutskever, I. & Hinton, G. E., 2012. Imagenet classication with deep convolutional neural networks. s.l., s.n., pp. 1-9. Li, R. et al., 2014. Deep learning based imaging data completion for improved brain disease diagnosis. Quebec City, s...

  10. Automatic construction of a recurrent neural network based classifier for vehicle passage detection

    Science.gov (United States)

    Burnaev, Evgeny; Koptelov, Ivan; Novikov, German; Khanipov, Timur

    2017-03-01

    Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data.

  11. Pedestrian detection in video surveillance using fully convolutional YOLO neural network

    Science.gov (United States)

    Molchanov, V. V.; Vishnyakov, B. V.; Vizilter, Y. V.; Vishnyakova, O. V.; Knyaz, V. A.

    2017-06-01

    More than 80% of video surveillance systems are used for monitoring people. Old human detection algorithms, based on background and foreground modelling, could not even deal with a group of people, to say nothing of a crowd. Recent robust and highly effective pedestrian detection algorithms are a new milestone of video surveillance systems. Based on modern approaches in deep learning, these algorithms produce very discriminative features that can be used for getting robust inference in real visual scenes. They deal with such tasks as distinguishing different persons in a group, overcome problem with sufficient enclosures of human bodies by the foreground, detect various poses of people. In our work we use a new approach which enables to combine detection and classification tasks into one challenge using convolution neural networks. As a start point we choose YOLO CNN, whose authors propose a very efficient way of combining mentioned above tasks by learning a single neural network. This approach showed competitive results with state-of-the-art models such as FAST R-CNN, significantly overcoming them in speed, which allows us to apply it in real time video surveillance and other video monitoring systems. Despite all advantages it suffers from some known drawbacks, related to the fully-connected layers that obstruct applying the CNN to images with different resolution. Also it limits the ability to distinguish small close human figures in groups which is crucial for our tasks since we work with rather low quality images which often include dense small groups of people. In this work we gradually change network architecture to overcome mentioned above problems, train it on a complex pedestrian dataset and finally get the CNN detecting small pedestrians in real scenes.

  12. Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

    Science.gov (United States)

    Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

    2017-02-10

    Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

  13. Virus Particle Detection by Convolutional Neural Network in Transmission Electron Microscopy Images.

    Science.gov (United States)

    Ito, Eisuke; Sato, Takaaki; Sano, Daisuke; Utagawa, Etsuko; Kato, Tsuyoshi

    2018-06-01

    A new computational method for the detection of virus particles in transmission electron microscopy (TEM) images is presented. Our approach is to use a convolutional neural network that transforms a TEM image to a probabilistic map that indicates where virus particles exist in the image. Our proposed approach automatically and simultaneously learns both discriminative features and classifier for virus particle detection by machine learning, in contrast to existing methods that are based on handcrafted features that yield many false positives and require several postprocessing steps. The detection performance of the proposed method was assessed against a dataset of TEM images containing feline calicivirus particles and compared with several existing detection methods, and the state-of-the-art performance of the developed method for detecting virus was demonstrated. Since our method is based on supervised learning that requires both the input images and their corresponding annotations, it is basically used for detection of already-known viruses. However, the method is highly flexible, and the convolutional networks can adapt themselves to any virus particles by learning automatically from an annotated dataset.

  14. An artificial neural network method for lumen and media-adventitia border detection in IVUS.

    Science.gov (United States)

    Su, Shengran; Hu, Zhenghui; Lin, Qiang; Hau, William Kongto; Gao, Zhifan; Zhang, Heye

    2017-04-01

    Intravascular ultrasound (IVUS) has been well recognized as one powerful imaging technique to evaluate the stenosis inside the coronary arteries. The detection of lumen border and media-adventitia (MA) border in IVUS images is the key procedure to determine the plaque burden inside the coronary arteries, but this detection could be burdensome to the doctor because of large volume of the IVUS images. In this paper, we use the artificial neural network (ANN) method as the feature learning algorithm for the detection of the lumen and MA borders in IVUS images. Two types of imaging information including spatial, neighboring features were used as the input data to the ANN method, and then the different vascular layers were distinguished accordingly through two sparse auto-encoders and one softmax classifier. Another ANN was used to optimize the result of the first network. In the end, the active contour model was applied to smooth the lumen and MA borders detected by the ANN method. The performance of our approach was compared with the manual drawing method performed by two IVUS experts on 461 IVUS images from four subjects. Results showed that our approach had a high correlation and good agreement with the manual drawing results. The detection error of the ANN method close to the error between two groups of manual drawing result. All these results indicated that our proposed approach could efficiently and accurately handle the detection of lumen and MA borders in the IVUS images. Copyright © 2016 Elsevier Ltd. All rights reserved.

  15. Usage of Probabilistic and General Regression Neural Network for Early Detection and Prevention of Oral Cancer

    Directory of Open Access Journals (Sweden)

    Neha Sharma

    2015-01-01

    Full Text Available In India, the oral cancers are usually presented in advanced stage of malignancy. It is critical to ascertain the diagnosis in order to initiate most advantageous treatment of the suspicious lesions. The main hurdle in appropriate treatment and control of oral cancer is identification and risk assessment of early disease in the community in a cost-effective fashion. The objective of this research is to design a data mining model using probabilistic neural network and general regression neural network (PNN/GRNN for early detection and prevention of oral malignancy. The model is built using the oral cancer database which has 35 attributes and 1025 records. All the attributes pertaining to clinical symptoms and history are considered to classify malignant and non-malignant cases. Subsequently, the model attempts to predict particular type of cancer, its stage and extent with the help of attributes pertaining to symptoms, gross examination and investigations. Also, the model envisages anticipating the survivability of a patient on the basis of treatment and follow-up details. Finally, the performance of the PNN/GRNN model is compared with that of other classification models. The classification accuracy of PNN/GRNN model is 80% and hence is better for early detection and prevention of the oral cancer.

  16. Usage of Probabilistic and General Regression Neural Network for Early Detection and Prevention of Oral Cancer.

    Science.gov (United States)

    Sharma, Neha; Om, Hari

    2015-01-01

    In India, the oral cancers are usually presented in advanced stage of malignancy. It is critical to ascertain the diagnosis in order to initiate most advantageous treatment of the suspicious lesions. The main hurdle in appropriate treatment and control of oral cancer is identification and risk assessment of early disease in the community in a cost-effective fashion. The objective of this research is to design a data mining model using probabilistic neural network and general regression neural network (PNN/GRNN) for early detection and prevention of oral malignancy. The model is built using the oral cancer database which has 35 attributes and 1025 records. All the attributes pertaining to clinical symptoms and history are considered to classify malignant and non-malignant cases. Subsequently, the model attempts to predict particular type of cancer, its stage and extent with the help of attributes pertaining to symptoms, gross examination and investigations. Also, the model envisages anticipating the survivability of a patient on the basis of treatment and follow-up details. Finally, the performance of the PNN/GRNN model is compared with that of other classification models. The classification accuracy of PNN/GRNN model is 80% and hence is better for early detection and prevention of the oral cancer.

  17. Neural network pattern recognition of lingual-palatal pressure for automated detection of swallow.

    Science.gov (United States)

    Hadley, Aaron J; Krival, Kate R; Ridgel, Angela L; Hahn, Elizabeth C; Tyler, Dustin J

    2015-04-01

    We describe a novel device and method for real-time measurement of lingual-palatal pressure and automatic identification of the oral transfer phase of deglutition. Clinical measurement of the oral transport phase of swallowing is a complicated process requiring either placement of obstructive sensors or sitting within a fluoroscope or articulograph for recording. Existing detection algorithms distinguish oral events with EMG, sound, and pressure signals from the head and neck, but are imprecise and frequently result in false detection. We placed seven pressure sensors on a molded mouthpiece fitting over the upper teeth and hard palate and recorded pressure during a variety of swallow and non-swallow activities. Pressure measures and swallow times from 12 healthy and 7 Parkinson's subjects provided training data for a time-delay artificial neural network to categorize the recordings as swallow or non-swallow events. User-specific neural networks properly categorized 96 % of swallow and non-swallow events, while a generalized population-trained network was able to properly categorize 93 % of swallow and non-swallow events across all recordings. Lingual-palatal pressure signals are sufficient to selectively and specifically recognize the initiation of swallowing in healthy and dysphagic patients.

  18. Detection of Pistachio Aflatoxin Using Raman Spectroscopy and Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    R Mohammadigol

    2015-03-01

    Full Text Available Pistachio contamination to aflatoxin has been known as a serious problem for pistachio exportation. With regards to the increasing demand for Raman spectroscopy to detect and classify different materials and also the current experimental and technical problems for measuring toxin (such as being expensive and time-consuming, the main objective of this study was to detect aflatoxin contamination in pistachio by using Raman spectroscopy technique and artificial neural networks. Three sets of samples were prepared: non-contaminated (healthy and contaminated samples with 20 and 100 ppb of the total aflatoxins (B1+B2+G1+G2. After spectral acquisition, considering to the results, spectral data were normalized and then principal components (PCs were extracted to reduce the data dimensions. For classification of the samples spectra, an artificial neural network was used with a feed forward back propagation algorithm for 4 inputs and 3 neurons in hidden layer. Mean overall accuracy was achieved to be 98 percent; therefore, non-liner Raman spectra data modeling by ANN for samples classification was successful.

  19. Accurate Natural Trail Detection Using a Combination of a Deep Neural Network and Dynamic Programming.

    Science.gov (United States)

    Adhikari, Shyam Prasad; Yang, Changju; Slot, Krzysztof; Kim, Hyongsuk

    2018-01-10

    This paper presents a vision sensor-based solution to the challenging problem of detecting and following trails in highly unstructured natural environments like forests, rural areas and mountains, using a combination of a deep neural network and dynamic programming. The deep neural network (DNN) concept has recently emerged as a very effective tool for processing vision sensor signals. A patch-based DNN is trained with supervised data to classify fixed-size image patches into "trail" and "non-trail" categories, and reshaped to a fully convolutional architecture to produce trail segmentation map for arbitrary-sized input images. As trail and non-trail patches do not exhibit clearly defined shapes or forms, the patch-based classifier is prone to misclassification, and produces sub-optimal trail segmentation maps. Dynamic programming is introduced to find an optimal trail on the sub-optimal DNN output map. Experimental results showing accurate trail detection for real-world trail datasets captured with a head mounted vision system are presented.

  20. Application of Artificial Neural Networks to Ship Detection from X-Band Kompsat-5 Imagery

    Directory of Open Access Journals (Sweden)

    Jeong-In Hwang

    2017-09-01

    Full Text Available For ship detection, X-band synthetic aperture radar (SAR imagery provides very useful data, in that ship targets look much brighter than surrounding sea clutter due to the corner-reflection effect. However, there are many phenomena which bring out false detection in the SAR image, such as noise of background, ghost phenomena, side-lobe effects and so on. Therefore, when ship-detection algorithms are carried out, we should consider these effects and mitigate them to acquire a better result. In this paper, we propose an efficient method to detect ship targets from X-band Kompsat-5 SAR imagery using the artificial neural network (ANN. The method produces the ship-probability map using ANN, and then detects ships from the ship-probability map by using a threshold value. For the purpose of getting an improved ship detection, we strived to produce optimal input layers used for ANN. In order to reduce phenomena related to the false detections, the non-local (NL-means filter and median filter were utilized. The NL-means filter effectively reduced noise on SAR imagery without smoothing edges of the objects, and the median filter was used to remove ship targets in SAR imagery. Through the filtering approaches, we generated two input layers from a Kompsat-5 SAR image, and created a ship-probability map via ANN from the two input layers. When the threshold value of 0.67 was imposed on the ship-probability map, the result of ship detection from the ship-probability map was a 93.9% recall, 98.7% precision and 6.1% false alarm rate. Therefore, the proposed method was successfully applied to the ship detection from the Kompsat-5 SAR image.

  1. Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

    Directory of Open Access Journals (Sweden)

    Haobo Lyu

    2016-06-01

    Full Text Available When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1 the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2 the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3 to the authors’ best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

  2. The biopsy of the boar testes using ultrasonographic examination

    Directory of Open Access Journals (Sweden)

    Laima Liepa

    2014-03-01

    Full Text Available The biopsy of live animal testes is an important clinical manipulation to control spermatogenesis and reproductive system pathologies. The aim was to develop a method of boar testes biopsy using a biopsy gun with ultrasound guidance and to investigate the influence of this procedure on the boar testes parenchyma and quality of ejaculate. The biopsy was carried out in six 8-month-old boars. Fourteen days prior to and 21 days after biopsy, the quality of ejaculate was examined (weight of ejaculate; concentration and motility of spermatozoa with a seven-day intervals. Ultrasound images of the testes parenchyma were recorded three times: directly before and 15 minutes after the biopsy, then 21 days after the procedure. The testes biopsies of generally anesthetized boars were performed with the biopsy gun for needle biopsy with a 12cm long, disposable 16-gauge needle 1.8mm in diameter (Vitesse through 1cm skin incision in the depth of 1.2-1.6cm of parenchyma. Fifteen minutes after the biopsy, macroscopic injures of the parenchyma of all the boar testes were not detected in the ultrasound image. Twenty one days after biopsy, the hyperechogenic line 0.1-0.2cm in diameter was seen in the testes parenchyma of six boars in the depth of 1.2-1.6cm. The biopsy of boar testes did not influence the quality of boars ejaculate. The ultrasonographic examination of boar testicles before the biopsy reduced possibilities to traumatize large blood vessels of the testes. A perfect boar testicular biopsy was easy to perform using ultrasonographic examination in the pigsty conditions.

  3. Premature ventricular contraction detection combining deep neural networks and rules inference.

    Science.gov (United States)

    Zhou, Fei-Yan; Jin, Lin-Peng; Dong, Jun

    2017-06-01

    Premature ventricular contraction (PVC), which is a common form of cardiac arrhythmia caused by ectopic heartbeat, can lead to life-threatening cardiac conditions. Computer-aided PVC detection is of considerable importance in medical centers or outpatient ECG rooms. In this paper, we proposed a new approach that combined deep neural networks and rules inference for PVC detection. The detection performance and generalization were studied using publicly available databases: the MIT-BIH arrhythmia database (MIT-BIH-AR) and the Chinese Cardiovascular Disease Database (CCDD). The PVC detection accuracy on the MIT-BIH-AR database was 99.41%, with a sensitivity and specificity of 97.59% and 99.54%, respectively, which were better than the results from other existing methods. To test the generalization capability, the detection performance was also evaluated on the CCDD. The effectiveness of the proposed method was confirmed by the accuracy (98.03%), sensitivity (96.42%) and specificity (98.06%) with the dataset over 140,000 ECG recordings of the CCDD. Copyright © 2017 Elsevier B.V. All rights reserved.

  4. A light and faster regional convolutional neural network for object detection in optical remote sensing images

    Science.gov (United States)

    Ding, Peng; Zhang, Ye; Deng, Wei-Jian; Jia, Ping; Kuijper, Arjan

    2018-07-01

    Detection of objects from satellite optical remote sensing images is very important for many commercial and governmental applications. With the development of deep convolutional neural networks (deep CNNs), the field of object detection has seen tremendous advances. Currently, objects in satellite remote sensing images can be detected using deep CNNs. In general, optical remote sensing images contain many dense and small objects, and the use of the original Faster Regional CNN framework does not yield a suitably high precision. Therefore, after careful analysis we adopt dense convoluted networks, a multi-scale representation and various combinations of improvement schemes to enhance the structure of the base VGG16-Net for improving the precision. We propose an approach to reduce the test-time (detection time) and memory requirements. To validate the effectiveness of our approach, we perform experiments using satellite remote sensing image datasets of aircraft and automobiles. The results show that the improved network structure can detect objects in satellite optical remote sensing images more accurately and efficiently.

  5. A Recurrent Neural Network Approach to Rear Vehicle Detection Which Considered State Dependency

    Directory of Open Access Journals (Sweden)

    Kayichirou Inagaki

    2003-08-01

    Full Text Available Experimental vision-based detection often fails in cases when the acquired image quality is reduced by changing optical environments. In addition, the shape of vehicles in images that are taken from vision sensors change due to approaches by vehicle. Vehicle detection methods are required to perform successfully under these conditions. However, the conventional methods do not consider especially in rapidly varying by brightness conditions. We suggest a new detection method that compensates for those conditions in monocular vision-based vehicle detection. The suggested method employs a Recurrent Neural Network (RNN, which has been applied for spatiotemporal processing. The RNN is able to respond to consecutive scenes involving the target vehicle and can track the movements of the target by the effect of the past network states. The suggested method has a particularly beneficial effect in environments with sudden, extreme variations such as bright sunlight and shield. Finally, we demonstrate effectiveness by state-dependent of the RNN-based method by comparing its detection results with those of a Multi Layered Perceptron (MLP.

  6. Usefulness of ultrasonographic evaluation in primary and secondary hyperparathyroidism

    International Nuclear Information System (INIS)

    Jeon, Tae Joo; Kim, Eun Kyung; Lee, Jong Doo; Park, Jung Soo; Lee, Jong Tae; Yoo, Hyung Sik

    1999-01-01

    To evaluate the accuracy and ultrasonographic findings of primary and secondary hyperparathyroidism (HPT) and correlate them with pathologic results. We reviewed 31 cases of surgically confirmed primary (n=22) and secondary (n=9) hyperparathyroidism. We used 10 or 7.5 MHz linear transducer and reviewed the location, contour, size and echogenicity of lesions. Then we evaluated the detection rate of parathyroid lesions based on surgical result and compared the result of 99m Tc-sestamibi scan (15 cases). Location of primary HPT was left lower in 9, left upper in 5, right lower in 4, right upper in 3, left midportion in 1 and superior mediastinum in 1. Lesions showed variable echogenicity-mild low echo (2), moderate low echo (10), severe low echo (2), isoecho (4) and heterogeneous echo pattern (1). All the lesions except 5 were well defined and 3 lesions had echogenic rim. Posterior enhancement and lateral shadowing were noted in 3 and 4 lesions, respectively. Nineteen of 23 primary lesions were detected by ultrasonography (82.6%) and well correlated with sestamibi scan. In case of secondary HPT, most were well defined low echoic nodular lesions, and we could detect 6 of 9 patients (67%) and 15 of 36 lesions (41.7%). Only 6 of 24 secondary lesion were detected by sestamibi scan (25%). The detection rate of ultrasonography in primary HPT was fairly good and well correlated with the result of the 99m Tc-sestamibi scan, but both diagnostic modalities were not promising in secondary HPT.

  7. Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

    Science.gov (United States)

    Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

    2017-09-01

    Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN

  8. A new method of small target detection based on neural network

    Science.gov (United States)

    Hu, Jing; Hu, Yongli; Lu, Xinxin

    2018-02-01

    The detection and tracking of moving dim target in infrared image have been an research hotspot for many years. The target in each frame of images only occupies several pixels without any shape and structure information. Moreover, infrared small target is often submerged in complicated background with low signal-to-clutter ratio, making the detection very difficult. Different backgrounds exhibit different statistical properties, making it becomes extremely complex to detect the target. If the threshold segmentation is not reasonable, there may be more noise points in the final detection, which is unfavorable for the detection of the trajectory of the target. Single-frame target detection may not be able to obtain the desired target and cause high false alarm rate. We believe the combination of suspicious target detection spatially in each frame and temporal association for target tracking will increase reliability of tracking dim target. The detection of dim target is mainly divided into two parts, In the first part, we adopt bilateral filtering method in background suppression, after the threshold segmentation, the suspicious target in each frame are extracted, then we use LSTM(long short term memory) neural network to predict coordinates of target of the next frame. It is a brand-new method base on the movement characteristic of the target in sequence images which could respond to the changes in the relationship between past and future values of the values. Simulation results demonstrate proposed algorithm can effectively predict the trajectory of the moving small target and work efficiently and robustly with low false alarm.

  9. Ultrasonographic Findings of Papillary Thyroid Cancer with or without Hashimoto's Thyroiditis

    International Nuclear Information System (INIS)

    Park, Jun Young; Lee, Tae Hyun; Park, Dong Hee

    2010-01-01

    This study was designed to compare the ultrasonographic features of papillary thyroid carcinoma with and without Hashimoto's thyroiditis. This retrospective study included 190 patients with papillary thyroid carcinoma which was proven by neck surgery. The difference in the ultrasonographic findings between papillary thyroid carcinoma with Hashimoto's thyroiditis and papillary thyroid carcinoma without Hashimoto's thyroiditis were calculated statistically. Hashimoto's thyroiditis was diagnosed in 61 of 190 patients following neck surgery. The incidence of coexisting papillary thyroid carcinoma with Hashimoto's thyroiditis was significantly higher in women (p=0.0026). In addition, the frequency of macrocalcification in patients with Hashimoto's thyroiditis was also significantly higher (p=0.0009). Conversely,other ultrasonographic findings including the shape, margin, echogenicity and calcifications, for patients with papillary thyroid carcinoma with Hashimoto's thyroiditis and papillary thyroid carcinoma without Hashimoto's thyroiditis, were not statistically significant. We also found that patients with Hashimoto's thyroiditis who showed no calcification on ultrasonography tended not to detect the papillary carcinoma at a higher frequency. On ultrasonography, macrocalcifications occurred more frequently in patients with Hashimoto's thyroiditis than those without Hashimoto's thyroiditis. Malignant thyroid nodules without calcifications in patients with Hashimoto's thyroiditis more often could not be detected. Therefore, it is important carefully examine patients with Hashimoto's thyroiditis

  10. Ultrasonographic Findings of Papillary Thyroid Cancer with or without Hashimoto's Thyroiditis

    Energy Technology Data Exchange (ETDEWEB)

    Park, Jun Young; Lee, Tae Hyun; Park, Dong Hee [Korea Cancer Center Hospital, Seoul (Korea, Republic of)

    2010-04-15

    This study was designed to compare the ultrasonographic features of papillary thyroid carcinoma with and without Hashimoto's thyroiditis. This retrospective study included 190 patients with papillary thyroid carcinoma which was proven by neck surgery. The difference in the ultrasonographic findings between papillary thyroid carcinoma with Hashimoto's thyroiditis and papillary thyroid carcinoma without Hashimoto's thyroiditis were calculated statistically. Hashimoto's thyroiditis was diagnosed in 61 of 190 patients following neck surgery. The incidence of coexisting papillary thyroid carcinoma with Hashimoto's thyroiditis was significantly higher in women (p=0.0026). In addition, the frequency of macrocalcification in patients with Hashimoto's thyroiditis was also significantly higher (p=0.0009). Conversely,other ultrasonographic findings including the shape, margin, echogenicity and calcifications, for patients with papillary thyroid carcinoma with Hashimoto's thyroiditis and papillary thyroid carcinoma without Hashimoto's thyroiditis, were not statistically significant. We also found that patients with Hashimoto's thyroiditis who showed no calcification on ultrasonography tended not to detect the papillary carcinoma at a higher frequency. On ultrasonography, macrocalcifications occurred more frequently in patients with Hashimoto's thyroiditis than those without Hashimoto's thyroiditis. Malignant thyroid nodules without calcifications in patients with Hashimoto's thyroiditis more often could not be detected. Therefore, it is important carefully examine patients with Hashimoto's thyroiditis

  11. Volcanic ash detection and retrievals using MODIS data by means of neural networks

    Directory of Open Access Journals (Sweden)

    M. Picchiani

    2011-12-01

    Full Text Available Volcanic ash clouds detection and retrieval represent a key issue for aviation safety due to the harming effects on aircraft. A lesson learned from the recent Eyjafjallajokull eruption is the need to obtain accurate and reliable retrievals on a real time basis.

    In this work we have developed a fast and accurate Neural Network (NN approach to detect and retrieve volcanic ash cloud properties from the Moderate Resolution Imaging Spectroradiometer (MODIS data in the Thermal InfraRed (TIR spectral range. Some measurements collected during the 2001, 2002 and 2006 Mt. Etna volcano eruptions have been considered as test cases.

    The ash detection and retrievals obtained from the Brightness Temperature Difference (BTD algorithm are used as training for the NN procedure that consists in two separate steps: ash detection and ash mass retrieval. The ash detection is reduced to a classification problem by identifying two classes: "ashy" and "non-ashy" pixels in the MODIS images. Then the ash mass is estimated by means of the NN, replicating the BTD-based model performances. A segmentation procedure has also been tested to remove the false ash pixels detection induced by the presence of high meteorological clouds. The segmentation procedure shows a clear advantage in terms of classification accuracy: the main drawback is the loss of information on ash clouds distal part.

    The results obtained are very encouraging; indeed the ash detection accuracy is greater than 90%, while a mean RMSE equal to 0.365 t km−2 has been obtained for the ash mass retrieval. Moreover, the NN quickness in results delivering makes the procedure extremely attractive in all the cases when the rapid response time of the system is a mandatory requirement.

  12. Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors.

    Science.gov (United States)

    Kim, Jong Hyun; Hong, Hyung Gil; Park, Kang Ryoung

    2017-05-08

    Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR) illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1) and two open databases (Korea advanced institute of science and technology (KAIST) and computer vision center (CVC) databases), as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods.

  13. Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors

    Directory of Open Access Journals (Sweden)

    Jong Hyun Kim

    2017-05-01

    Full Text Available Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1 and two open databases (Korea advanced institute of science and technology (KAIST and computer vision center (CVC databases, as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods.

  14. Anomalous Signal Detection in ELF Band Electromagnetic Wave using Multi-layer Neural Network with Wavelet Decomposition

    Science.gov (United States)

    Itai, Akitoshi; Yasukawa, Hiroshi; Takumi, Ichi; Hata, Masayasu

    It is well known that electromagnetic waves radiated from the earth's crust are useful for predicting earthquakes. We analyze the electromagnetic waves received at the extremely low frequency band of 223Hz. These observed signals contain the seismic radiation from the earth's crust, but also include several undesired signals. Our research focuses on the signal detection technique to identify an anomalous signal corresponding to the seismic radiation in the observed signal. Conventional anomalous signal detections lack a wide applicability due to their assumptions, e.g. the digital data have to be observed at the same time or the same sensor. In order to overcome the limitation related to the observed signal, we proposed the anomalous signals detection based on a multi-layer neural network which is trained by digital data observed during a span of a day. In the neural network approach, training data do not need to be recorded at the same place or the same time. However, some noises, which have a large amplitude, are detected as the anomalous signal. This paper develops a multi-layer neural network to decrease the false detection of the anomalous signal from the electromagnetic wave. The training data for the proposed network is the decomposed signal of the observed signal during several days, since the seismic radiations are often recorded from several days to a couple of weeks. Results show that the proposed neural network is useful to achieve the accurate detection of the anomalous signal that indicates seismic activity.

  15. Cephalometric landmark detection in dental x-ray images using convolutional neural networks

    Science.gov (United States)

    Lee, Hansang; Park, Minseok; Kim, Junmo

    2017-03-01

    In dental X-ray images, an accurate detection of cephalometric landmarks plays an important role in clinical diagnosis, treatment and surgical decisions for dental problems. In this work, we propose an end-to-end deep learning system for cephalometric landmark detection in dental X-ray images, using convolutional neural networks (CNN). For detecting 19 cephalometric landmarks in dental X-ray images, we develop a detection system using CNN-based coordinate-wise regression systems. By viewing x- and y-coordinates of all landmarks as 38 independent variables, multiple CNN-based regression systems are constructed to predict the coordinate variables from input X-ray images. First, each coordinate variable is normalized by the length of either height or width of an image. For each normalized coordinate variable, a CNN-based regression system is trained on training images and corresponding coordinate variable, which is a variable to be regressed. We train 38 regression systems with the same CNN structure on coordinate variables, respectively. Finally, we compute 38 coordinate variables with these trained systems from unseen images and extract 19 landmarks by pairing the regressed coordinates. In experiments, the public database from the Grand Challenges in Dental X-ray Image Analysis in ISBI 2015 was used and the proposed system showed promising performance by successfully locating the cephalometric landmarks within considerable margins from the ground truths.

  16. Neural networks for oil spill detection using TerraSAR-X data

    Science.gov (United States)

    Avezzano, Ruggero G.; Velotto, Domenico; Soccorsi, Matteo; Del Frate, Fabio; Lehner, Susanne

    2011-11-01

    The increased amount of available Synthetic Aperture Radar (SAR) images involves a growing workload on the operators at analysis centers. In addition, even if the operators go through extensive training to learn manual oil spill detection, they can provide different and subjective responses. Hence, the upgrade and improvements of algorithms for automatic detection that can help in screening the images and prioritizing the alarms are of great benefit. In this paper we present the potentialities of TerraSAR-X (TS-X) data and Neural Network algorithms for oil spills detection. The radar on board satellite TS-X provides X-band images with a resolution of up to 1m. Such resolution can be very effective in the monitoring of coastal areas to prevent sea oil pollution. The network input is a vector containing the values of a set of features characterizing an oil spill candidate. The network output gives the probability for the candidate to be a real oil spill. Candidates with a probability less than 50% are classified as look-alikes. The overall classification performances have been evaluated on a data set of 50 TS-X images containing more than 150 examples of certified oil spills and well-known look-alikes (e.g. low wind areas, wind shadows, biogenic films). The preliminary classification results are satisfactory with an overall detection accuracy above 80%.

  17. Applying long short-term memory recurrent neural networks to intrusion detection

    Directory of Open Access Journals (Sweden)

    Ralf C. Staudemeyer

    2015-07-01

    Full Text Available We claim that modelling network traffic as a time series with a supervised learning approach, using known genuine and malicious behaviour, improves intrusion detection. To substantiate this, we trained long short-term memory (LSTM recurrent neural networks with the training data provided by the DARPA / KDD Cup ’99 challenge. To identify suitable LSTM-RNN network parameters and structure we experimented with various network topologies. We found networks with four memory blocks containing two cells each offer a good compromise between computational cost and detection performance. We applied forget gates and shortcut connections respectively. A learning rate of 0.1 and up to 1,000 epochs showed good results. We tested the performance on all features and on extracted minimal feature sets respectively. We evaluated different feature sets for the detection of all attacks within one network and also to train networks specialised on individual attack classes. Our results show that the LSTM classifier provides superior performance in comparison to results previously published results of strong static classifiers. With 93.82% accuracy and 22.13 cost, LSTM outperforms the winning entries of the KDD Cup ’99 challenge by far. This is due to the fact that LSTM learns to look back in time and correlate consecutive connection records. For the first time ever, we have demonstrated the usefulness of LSTM networks to intrusion detection.

  18. Neural Bases of Unconscious Error Detection in a Chinese Anagram Solution Task: Evidence from ERP Study.

    Directory of Open Access Journals (Sweden)

    Hua-Zhan Yin

    Full Text Available In everyday life, error monitoring and processing are important for improving ongoing performance in response to a changing environment. However, detecting an error is not always a conscious process. The temporal activation patterns of brain areas related to cognitive control in the absence of conscious awareness of an error remain unknown. In the present study, event-related potentials (ERPs in the brain were used to explore the neural bases of unconscious error detection when subjects solved a Chinese anagram task. Our ERP data showed that the unconscious error detection (UED response elicited a more negative ERP component (N2 than did no error (NE and detect error (DE responses in the 300-400-ms time window, and the DE elicited a greater late positive component (LPC than did the UED and NE in the 900-1200-ms time window after the onset of the anagram stimuli. Taken together with the results of dipole source analysis, the N2 (anterior cingulate cortex might reflect unconscious/automatic conflict monitoring, and the LPC (superior/medial frontal gyrus might reflect conscious error recognition.

  19. A convolutional neural network for intracranial hemorrhage detection in non-contrast CT

    Science.gov (United States)

    Patel, Ajay; Manniesing, Rashindra

    2018-02-01

    The assessment of the presence of intracranial hemorrhage is a crucial step in the work-up of patients requiring emergency care. Fast and accurate detection of intracranial hemorrhage can aid treating physicians by not only expediting and guiding diagnosis, but also supporting choices for secondary imaging, treatment and intervention. However, the automatic detection of intracranial hemorrhage is complicated by the variation in appearance on non-contrast CT images as a result of differences in etiology and location. We propose a method using a convolutional neural network (CNN) for the automatic detection of intracranial hemorrhage. The method is trained on a dataset comprised of cerebral CT studies for which the presence of hemorrhage has been labeled for each axial slice. A separate test dataset of 20 images is used for quantitative evaluation and shows a sensitivity of 0.87, specificity of 0.97 and accuracy of 0.95. The average processing time for a single three-dimensional (3D) CT volume was 2.7 seconds. The proposed method is capable of fast and automated detection of intracranial hemorrhages in non-contrast CT without being limited to a specific subtype of pathology.

  20. GMDH and neural networks applied in monitoring and fault detection in sensors in nuclear power plants

    Energy Technology Data Exchange (ETDEWEB)

    Bueno, Elaine Inacio [Instituto Federal de Educacao, Ciencia e Tecnologia, Guarulhos, SP (Brazil); Pereira, Iraci Martinez; Silva, Antonio Teixeira e, E-mail: martinez@ipen.b, E-mail: teixeira@ipen.b [Instituto de Pesquisas Energeticas e Nucleares (IPEN/CNEN-SP), Sao Paulo, SP (Brazil)

    2011-07-01

    In this work a new monitoring and fault detection methodology was developed using GMDH (Group Method of Data Handling) algorithm and artificial neural networks (ANNs) which was applied in the IEA-R1 research reactor at IPEN. The monitoring and fault detection system was developed in two parts: the first was dedicated to preprocess information, using GMDH algorithm; and the second to the process information using ANNs. The preprocess information was divided in two parts. In the first part, the GMDH algorithm was used to generate a better database estimate, called matrix z, which was used to train the ANNs. In the second part the GMDH was used to study the best set of variables to be used to train the ANNs, resulting in a best monitoring variable estimative. The methodology was developed and tested using five different models: one theoretical model and for models using different sets of reactor variables. After an exhausting study dedicated to the sensors monitoring, the fault detection in sensors was developed by simulating faults in the sensors database using values of +5%, +10%, +15% and +20% in these sensors database. The good results obtained through the present methodology shows the viability of using GMDH algorithm in the study of the best input variables to the ANNs, thus making possible the use of these methods in the implementation of a new monitoring and fault detection methodology applied in sensors. (author)

  1. Local community detection as pattern restoration by attractor dynamics of recurrent neural networks.

    Science.gov (United States)

    Okamoto, Hiroshi

    2016-08-01

    Densely connected parts in networks are referred to as "communities". Community structure is a hallmark of a variety of real-world networks. Individual communities in networks form functional modules of complex systems described by networks. Therefore, finding communities in networks is essential to approaching and understanding complex systems described by networks. In fact, network science has made a great deal of effort to develop effective and efficient methods for detecting communities in networks. Here we put forward a type of community detection, which has been little examined so far but will be practically useful. Suppose that we are given a set of source nodes that includes some (but not all) of "true" members of a particular community; suppose also that the set includes some nodes that are not the members of this community (i.e., "false" members of the community). We propose to detect the community from this "imperfect" and "inaccurate" set of source nodes using attractor dynamics of recurrent neural networks. Community detection by the proposed method can be viewed as restoration of the original pattern from a deteriorated pattern, which is analogous to cue-triggered recall of short-term memory in the brain. We demonstrate the effectiveness of the proposed method using synthetic networks and real social networks for which correct communities are known. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  2. Convolutional neural network guided blue crab knuckle detection for autonomous crab meat picking machine

    Science.gov (United States)

    Wang, Dongyi; Vinson, Robert; Holmes, Maxwell; Seibel, Gary; Tao, Yang

    2018-04-01

    The Atlantic blue crab is among the highest-valued seafood found in the American Eastern Seaboard. Currently, the crab processing industry is highly dependent on manual labor. However, there is great potential for vision-guided intelligent machines to automate the meat picking process. Studies show that the back-fin knuckles are robust features containing information about a crab's size, orientation, and the position of the crab's meat compartments. Our studies also make it clear that detecting the knuckles reliably in images is challenging due to the knuckle's small size, anomalous shape, and similarity to joints in the legs and claws. An accurate and reliable computer vision algorithm was proposed to detect the crab's back-fin knuckles in digital images. Convolutional neural networks (CNNs) can localize rough knuckle positions with 97.67% accuracy, transforming a global detection problem into a local detection problem. Compared to the rough localization based on human experience or other machine learning classification methods, the CNN shows the best localization results. In the rough knuckle position, a k-means clustering method is able to further extract the exact knuckle positions based on the back-fin knuckle color features. The exact knuckle position can help us to generate a crab cutline in XY plane using a template matching method. This is a pioneering research project in crab image analysis and offers advanced machine intelligence for automated crab processing.

  3. Fault detection and diagnosis in asymmetric multilevel inverter using artificial neural network

    Science.gov (United States)

    Raj, Nithin; Jagadanand, G.; George, Saly

    2018-04-01

    The increased component requirement to realise multilevel inverter (MLI) fallout in a higher fault prospect due to power semiconductors. In this scenario, efficient fault detection and diagnosis (FDD) strategies to detect and locate the power semiconductor faults have to be incorporated in addition to the conventional protection systems. Even though a number of FDD methods have been introduced in the symmetrical cascaded H-bridge (CHB) MLIs, very few methods address the FDD in asymmetric CHB-MLIs. In this paper, the gate-open circuit FDD strategy in asymmetric CHB-MLI is presented. Here, a single artificial neural network (ANN) is used to detect and diagnose the fault in both binary and trinary configurations of the asymmetric CHB-MLIs. In this method, features of the output voltage of the MLIs are used as to train the ANN for FDD method. The results prove the validity of the proposed method in detecting and locating the fault in both asymmetric MLI configurations. Finally, the ANN response to the input parameter variation is also analysed to access the performance of the proposed ANN-based FDD strategy.

  4. A fully automatic microcalcification detection approach based on deep convolution neural network

    Science.gov (United States)

    Cai, Guanxiong; Guo, Yanhui; Zhang, Yaqin; Qin, Genggeng; Zhou, Yuanpin; Lu, Yao

    2018-02-01

    Breast cancer is one of the most common cancers and has high morbidity and mortality worldwide, posing a serious threat to the health of human beings. The emergence of microcalcifications (MCs) is an important signal of early breast cancer. However, it is still challenging and time consuming for radiologists to identify some tiny and subtle individual MCs in mammograms. This study proposed a novel computer-aided MC detection algorithm on the full field digital mammograms (FFDMs) using deep convolution neural network (DCNN). Firstly, a MC candidate detection system was used to obtain potential MC candidates. Then a DCNN was trained using a novel adaptive learning strategy, neutrosophic reinforcement sample learning (NRSL) strategy to speed up the learning process. The trained DCNN served to recognize true MCs. After been classified by DCNN, a density-based regional clustering method was imposed to form MC clusters. The accuracy of the DCNN with our proposed NRSL strategy converges faster and goes higher than the traditional DCNN at same epochs, and the obtained an accuracy of 99.87% on training set, 95.12% on validation set, and 93.68% on testing set at epoch 40. For cluster-based MC cluster detection evaluation, a sensitivity of 90% was achieved at 0.13 false positives (FPs) per image. The obtained results demonstrate that the designed DCNN plays a significant role in the MC detection after being prior trained.

  5. GMDH and neural networks applied in monitoring and fault detection in sensors in nuclear power plants

    International Nuclear Information System (INIS)

    Bueno, Elaine Inacio; Pereira, Iraci Martinez; Silva, Antonio Teixeira e

    2011-01-01

    In this work a new monitoring and fault detection methodology was developed using GMDH (Group Method of Data Handling) algorithm and artificial neural networks (ANNs) which was applied in the IEA-R1 research reactor at IPEN. The monitoring and fault detection system was developed in two parts: the first was dedicated to preprocess information, using GMDH algorithm; and the second to the process information using ANNs. The preprocess information was divided in two parts. In the first part, the GMDH algorithm was used to generate a better database estimate, called matrix z, which was used to train the ANNs. In the second part the GMDH was used to study the best set of variables to be used to train the ANNs, resulting in a best monitoring variable estimative. The methodology was developed and tested using five different models: one theoretical model and for models using different sets of reactor variables. After an exhausting study dedicated to the sensors monitoring, the fault detection in sensors was developed by simulating faults in the sensors database using values of +5%, +10%, +15% and +20% in these sensors database. The good results obtained through the present methodology shows the viability of using GMDH algorithm in the study of the best input variables to the ANNs, thus making possible the use of these methods in the implementation of a new monitoring and fault detection methodology applied in sensors. (author)

  6. Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

    Science.gov (United States)

    Al-Jarrah, Mohammad A; Shatnawi, Hadeel

    2017-08-01

    Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

  7. Assessment of the age for a preventive ultrasonographic examination of the prostate in the dog.

    Science.gov (United States)

    Mantziaras, G; Alonge, S; Faustini, M; Luvoni, G C

    2017-09-15

    The prostate commonly develops benign prostatic hyperplasia (BPH) in dogs over 5 years, while in aged dogs other pathological findings might be revealed by ultrasonographic exam. The aim of the present study was to estimate the most suitable age for a preventive ultrasonographic examination of the prostate in the dog. The prostate of 1003 intact male dogs of 64 different breeds, of different ages (1-18 years) and bodyweights (2-55 kg) was evaluated with ultrasound, irrespective of the reason for clinical examination. The age of each dog was expressed as the ratio between the actual age and the maximum longevity expected for the breed. Dogs were divided in two groups based on breeds' life expectancy as short life (SL) and long life (LL). The size of the prostate (normal, enlarged or small) and the presence of abnormal sonographic findings were recorded for each dog. The results of the present study indicate that the most suitable age for a preventive ultrasonographic exam of the prostate in the dog is approximately at 40% of its expected longevity, both in short and long life breeds, because at this age there is a strong possibility to be able to detect abnormal prostatic findings. In 47.5% of the dogs at least one abnormal finding of the prostate was revealed by ultrasonographic exam, while dogs with long life expectancy showed a significantly higher prevalence of abnormalities, than dogs with short life expectancy. The most frequent findings were the increase of prostatic size (33.5%) and the presence of at least one cyst (33.6%), with no difference between SL and LL dogs. In conclusion, a preventive examination of the prostate starting at 40% of expected longevity in dogs of short and long life breeds is strongly recommended for early detection of abnormalities, for scheduling specific follow up and for suggesting effective therapeutic protocols. Copyright © 2017 Elsevier Inc. All rights reserved.

  8. A neural network detection system for lower-hybrid cavities in electron plasma density measured by the FREJA satellite

    International Nuclear Information System (INIS)

    Waldemark, J.; Karlsson, Jan

    1995-03-01

    This paper presents a lower-hybrid cavity detection system, CDS, for measurements of electron plasma density on the FREJA satellite wave experiment. The system can reduce the amount of data to be analysed by as much as 96% and still retain more than 85% of the desired information. The CDS is a combination of a hybrid neural network, HNN and expert rules. The HNN is a Self Organizing Map, SOM, combined with a feed forward back propagation neural net, BP. The CDS can be controlled by the user to operate with various degrees of sensitivity. Maximum detection capability is as high as 95% with data reduction lowered to 85%. 10 refs

  9. Detection of bars in galaxies using a deep convolutional neural network

    Science.gov (United States)

    Abraham, Sheelu; Aniyan, A. K.; Kembhavi, Ajit K.; Philip, N. S.; Vaghmare, Kaustubh

    2018-06-01

    We present an automated method for the detection of bar structure in optical images of galaxies using a deep convolutional neural network that is easy to use and provides good accuracy. In our study, we use a sample of 9346 galaxies in the redshift range of 0.009-0.2 from the Sloan Digital Sky Survey (SDSS), which has 3864 barred galaxies, the rest being unbarred. We reach a top precision of 94 per cent in identifying bars in galaxies using the trained network. This accuracy matches the accuracy reached by human experts on the same data without additional information about the images. Since deep convolutional neural networks can be scaled to handle large volumes of data, the method is expected to have great relevance in an era where astronomy data is rapidly increasing in terms of volume, variety, volatility, and velocity along with other V's that characterize big data. With the trained model, we have constructed a catalogue of barred galaxies from SDSS and made it available online.

  10. Neural Correlates of Temporal Complexity and Synchrony during Audiovisual Correspondence Detection.

    Science.gov (United States)

    Baumann, Oliver; Vromen, Joyce M G; Cheung, Allen; McFadyen, Jessica; Ren, Yudan; Guo, Christine C

    2018-01-01

    We often perceive real-life objects as multisensory cues through space and time. A key challenge for audiovisual integration is to match neural signals that not only originate from different sensory modalities but also that typically reach the observer at slightly different times. In humans, complex, unpredictable audiovisual streams lead to higher levels of perceptual coherence than predictable, rhythmic streams. In addition, perceptual coherence for complex signals seems less affected by increased asynchrony between visual and auditory modalities than for simple signals. Here, we used functional magnetic resonance imaging to determine the human neural correlates of audiovisual signals with different levels of temporal complexity and synchrony. Our study demonstrated that greater perceptual asynchrony and lower signal complexity impaired performance in an audiovisual coherence-matching task. Differences in asynchrony and complexity were also underpinned by a partially different set of brain regions. In particular, our results suggest that, while regions in the dorsolateral prefrontal cortex (DLPFC) were modulated by differences in memory load due to stimulus asynchrony, areas traditionally thought to be involved in speech production and recognition, such as the inferior frontal and superior temporal cortex, were modulated by the temporal complexity of the audiovisual signals. Our results, therefore, indicate specific processing roles for different subregions of the fronto-temporal cortex during audiovisual coherence detection.

  11. Ultrasonographic findings of nonlactiferous breast abscess

    Energy Technology Data Exchange (ETDEWEB)

    Hwang, Sung Su; Kim, Hak Hee; Lee, Myung Hee; Rho, Sang Chun; Jung, Seon Ok; Jung, So Leoung; Cha, Eun Sook; Shinn, Kyung Sub [Catholic University Medical College, Seoul (Korea, Republic of)

    1995-04-15

    To evaluate the ultrasonographic features of nonlactiferous breast abscess. We retrospectively reviewed ultrasonograms of 21 cases with surgically and clinically proved nonlactiferous breast abscess. The cases included 17 cases of acute or chronic inflammation and 4 cases of tuberculosis. Location of the lesion was subareolar in 15 cases and peripheral in 6. Mean anteroposterior/transverse diameter ratio was 0.49. Internal echogenicitiy of the lesion was variable, with heterogeneous mixed-echoic echotexture in 18 cases and homogeneous hypoechoic in 3. Margin of the lesion was irregular in 18 cases (85.7%) and posterior sonic enhancement was observed in 17 cases (81%). There were also noted obliteration of adjacent superficial fascia, localized skin thickening, and sinus tract or ductal ectasia in 19 (90.5%), 9 (42.9%), and 9(42.9%) cases respectively. Major ultrasonographic findings of nonlactiferous breast abscess was subareolar located, variable shaped mass with posterior enhancement. Additional findings were fistular formation, loss of superficial fascia, and axillary lymphadenopathy.

  12. Ultrasonographic findings of nonlactiferous breast abscess

    International Nuclear Information System (INIS)

    Hwang, Sung Su; Kim, Hak Hee; Lee, Myung Hee; Rho, Sang Chun; Jung, Seon Ok; Jung, So Leoung; Cha, Eun Sook; Shinn, Kyung Sub

    1995-01-01

    To evaluate the ultrasonographic features of nonlactiferous breast abscess. We retrospectively reviewed ultrasonograms of 21 cases with surgically and clinically proved nonlactiferous breast abscess. The cases included 17 cases of acute or chronic inflammation and 4 cases of tuberculosis. Location of the lesion was subareolar in 15 cases and peripheral in 6. Mean anteroposterior/transverse diameter ratio was 0.49. Internal echogenicitiy of the lesion was variable, with heterogeneous mixed-echoic echotexture in 18 cases and homogeneous hypoechoic in 3. Margin of the lesion was irregular in 18 cases (85.7%) and posterior sonic enhancement was observed in 17 cases (81%). There were also noted obliteration of adjacent superficial fascia, localized skin thickening, and sinus tract or ductal ectasia in 19 (90.5%), 9 (42.9%), and 9(42.9%) cases respectively. Major ultrasonographic findings of nonlactiferous breast abscess was subareolar located, variable shaped mass with posterior enhancement. Additional findings were fistular formation, loss of superficial fascia, and axillary lymphadenopathy

  13. Analysis of ultrasonographic findings in liver cirrhosis

    Energy Technology Data Exchange (ETDEWEB)

    Jeong, Seong Wook; Suh, Won Hyuck [Korea University College of Medicine, Seoul (Korea, Republic of)

    1988-10-15

    The association of liver cirrhosis with high amplitude echoes is well recognized. In Korea, despite the common occurrence of liver cirrhosis, little has been written regarding its ultrasonographic features. Retrospective evaluation of abdominal sonograms in 122 patients with liver cirrhosis was made using Weill's classification. The results were as followings: 1. 122 cases consist of 23 cases with Type I, 37 cases with Type II, 33 cases with Type IIIa, 28 cases with Type IIIb, and 1 case with Type IV. 2. Neither clinical finding nor laboratory data discriminates remarkable difference between each type. 3. Liver size is not in direct proportion to ultrasonographic type although hepatic retraction was more frequent in Type III, IV than in Type I and II. 4. Ancillary findings such as splenomegaly, portal hypertension and ascites are seen in Type I, II as frequently as in Type III, IV. Therefore, these different patterns are considered to be related to morphological types rather than phases. 5. Area of diverse echogenicity was revealed as malignant transformation in cirrhotic liver by RI scan by cold area.

  14. Ultrasonographic Characteristics of Subacute Granulomatous Thyroiditis

    International Nuclear Information System (INIS)

    Park, Sun Young; Kim, Eun Kyung; Kim, Min Jung; Oh, Ki Keun; Hong, Soon Won; Park, Cheong Soo; Kim, Byung Moon

    2006-01-01

    We wanted to describe the characteristic ultrasonography (US) features and clinical findings for making the diagnosis of subacute granulomatous thyroiditis. A total of 31 lesions from 27 patients were confirmed as subacute granulomatous thyroiditis by US-guided fine needle aspiration biopsy. We analyzed the ultrasonographic findings such as the lesion's size, margin and shape, the discrepancy between length and breadth and the vascularity. The clinical findings such as acute neck pain or fever were reviewed. The follow-up clinical and ultrasonographic data were reviewed for 15 patients. The thyroid gland was found to be enlarged in five patients, it was normal size in 20 patients and it was smaller in two patients. All the lesions had focally ill-defined hypoechogenicity. Hypervascularity was not noted in any of the lesions. Painful neck swelling was present in 18 patients. An accompanying fever was documented in nine of the 18 patients. Twelve patients showed disappearance (n = 3) or a decreased size (n = 9) of their lesions on follow-up US. The presence of ill-defined hypoechoic thyroid lesions without a discrete round or oval shape is characteristic for subacute granulomatous thyroiditis, and particularly when this is associated with painful neck swelling and/or fever

  15. Ultrasonographic Characteristics of Subacute Granulomatous Thyroiditis

    Energy Technology Data Exchange (ETDEWEB)

    Park, Sun Young [Gachon University Gil Medical Center, Incheon (Korea, Republic of); Kim, Eun Kyung; Kim, Min Jung; Oh, Ki Keun; Hong, Soon Won; Park, Cheong Soo [Yonsei University College of Medicine, Seoul (Korea, Republic of); Kim, Byung Moon [Sungkyunkwan University School of Medicine, Seoul (Korea, Republic of)

    2006-12-15

    We wanted to describe the characteristic ultrasonography (US) features and clinical findings for making the diagnosis of subacute granulomatous thyroiditis. A total of 31 lesions from 27 patients were confirmed as subacute granulomatous thyroiditis by US-guided fine needle aspiration biopsy. We analyzed the ultrasonographic findings such as the lesion's size, margin and shape, the discrepancy between length and breadth and the vascularity. The clinical findings such as acute neck pain or fever were reviewed. The follow-up clinical and ultrasonographic data were reviewed for 15 patients. The thyroid gland was found to be enlarged in five patients, it was normal size in 20 patients and it was smaller in two patients. All the lesions had focally ill-defined hypoechogenicity. Hypervascularity was not noted in any of the lesions. Painful neck swelling was present in 18 patients. An accompanying fever was documented in nine of the 18 patients. Twelve patients showed disappearance (n = 3) or a decreased size (n = 9) of their lesions on follow-up US. The presence of ill-defined hypoechoic thyroid lesions without a discrete round or oval shape is characteristic for subacute granulomatous thyroiditis, and particularly when this is associated with painful neck swelling and/or fever.

  16. Ultrasonographic evaluation of lschial bursitis

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Sung Moon; Shin, Myung Jin; Kim, Kyung Sook; Chang, Jae Suck; Lee, Soo Ho [Asan Medical Center, Ulsan Univ. College of Medicine, Seoul (Korea, Republic of); Ahn, Joong Mo [Samsung Medical Center, Sungkyunkwan Univ. College of Medicine, Seoul (Korea, Republic of); Cho, Kil Ho [Yeungnam Univ. College of Medicine, Kyongsan (Korea, Republic of)

    1999-06-01

    The objective of this study was to evaluate the findings of ultrasonography (US) in patients with ischial bursitis. Our study included 27 patients (mean age 62 years) who underwent US for a painful mass or tenderness in the buttock area. In six of these 27, serous fluid was obtained by needle aspiration, and in five cases, bursal excision permitted histologic confirmation. The other sixteen patients were followed up for one or two months with only NSAID medication; all showed some improvement or remission of symptoms. Using a 5-10 MHz linear array probe, US examination was performed while the patient was lying face down. US images were analyzed with regard to location and size of the lesions, thickness of cyst wall, the presence of internal septa or mural nodules, echogenicity of the cyst wall, fluid content, internal septa, compressibility by a probe, and Doppler signals within the cyst wall. In all 27 patients, ischial bursitis was located superficially to ischial tuberosity. Lesion size(maximum diameter) was 1.5-7(mean 3.8)cm, and the cyst wall was 0.2-0.8cm thick. Internal septa and mural nodules were seen in 12 cases (44%) and 13 cases (48%), respectively. The cyst wall was identifiable in 21 cases (78%), appearing as a single layer with low echogenicity (n=10) or with high echogenicity (n=1); it also appeared as two (n=6) or three (n=4) layers of different echogenicities. When internal septa were present, fluid within the cyst was low echoic in 59% of cases, high echoic in 30%, and of mixed echogenicity (so-called compartmentalization) in 15%. In all cases, the cyst became deformed, when compressed by a probe. In all patients who underwent doppler examination, some vascularity was found within the cyst wall. US helped to detect ischial bursitis; US findings were thin-walled cystic lesion located superficially to ischial tuberosity, with or without internal septa and mural nodules, and easy compressibility.

  17. Ultrasonographic evaluation of lschial bursitis

    International Nuclear Information System (INIS)

    Kim, Sung Moon; Shin, Myung Jin; Kim, Kyung Sook; Chang, Jae Suck; Lee, Soo Ho; Ahn, Joong Mo; Cho, Kil Ho

    1999-01-01

    The objective of this study was to evaluate the findings of ultrasonography (US) in patients with ischial bursitis. Our study included 27 patients (mean age 62 years) who underwent US for a painful mass or tenderness in the buttock area. In six of these 27, serous fluid was obtained by needle aspiration, and in five cases, bursal excision permitted histologic confirmation. The other sixteen patients were followed up for one or two months with only NSAID medication; all showed some improvement or remission of symptoms. Using a 5-10 MHz linear array probe, US examination was performed while the patient was lying face down. US images were analyzed with regard to location and size of the lesions, thickness of cyst wall, the presence of internal septa or mural nodules, echogenicity of the cyst wall, fluid content, internal septa, compressibility by a probe, and Doppler signals within the cyst wall. In all 27 patients, ischial bursitis was located superficially to ischial tuberosity. Lesion size(maximum diameter) was 1.5-7(mean 3.8)cm, and the cyst wall was 0.2-0.8cm thick. Internal septa and mural nodules were seen in 12 cases (44%) and 13 cases (48%), respectively. The cyst wall was identifiable in 21 cases (78%), appearing as a single layer with low echogenicity (n=10) or with high echogenicity (n=1); it also appeared as two (n=6) or three (n=4) layers of different echogenicities. When internal septa were present, fluid within the cyst was low echoic in 59% of cases, high echoic in 30%, and of mixed echogenicity (so-called compartmentalization) in 15%. In all cases, the cyst became deformed, when compressed by a probe. In all patients who underwent doppler examination, some vascularity was found within the cyst wall. US helped to detect ischial bursitis; US findings were thin-walled cystic lesion located superficially to ischial tuberosity, with or without internal septa and mural nodules, and easy compressibility

  18. Detection of Oil Chestnuts Infected by Blue Mold Using Near-Infrared Hyperspectral Imaging Combined with Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Lei Feng

    2018-06-01

    Full Text Available Mildew damage is a major reason for chestnut poor quality and yield loss. In this study, a near-infrared hyperspectral imaging system in the 874–1734 nm spectral range was applied to detect the mildew damage to chestnuts caused by blue mold. Principal component analysis (PCA scored images were firstly employed to qualitatively and intuitively distinguish moldy chestnuts from healthy chestnuts. Spectral data were extracted from the hyperspectral images. A successive projections algorithm (SPA was used to select 12 optimal wavelengths. Artificial neural networks, including back propagation neural network (BPNN, evolutionary neural network (ENN, extreme learning machine (ELM, general regression neural network (GRNN and radial basis neural network (RBNN were used to build models using the full spectra and optimal wavelengths to distinguish moldy chestnuts. BPNN and ENN models using full spectra and optimal wavelengths obtained satisfactory performances, with classification accuracies all surpassing 99%. The results indicate the potential for the rapid and non-destructive detection of moldy chestnuts by hyperspectral imaging, which would help to develop online detection system for healthy and blue mold infected chestnuts.

  19. Different Neural Systems Contribute to Semantic Bias and Conflict Detection in the Inclusion Fallacy Task

    Directory of Open Access Journals (Sweden)

    Peipeng eLiang

    2014-10-01

    Full Text Available more general conclusion category is considered stronger than a generalization to a specific conclusion category nested within the more general set. Such inferences violate rational norms and are part of the reasoning fallacy literature that provides interesting tasks to explore cognitive and neural basis of reasoning. To explore the functional neuroanatomy of the inclusion fallacy, we used a 2×2 factorial design, with factors for Quantification (explicit and implicit and Response (fallacious and nonfallacious. It was found that a left fronto-temporal system, along with a superior medial frontal system, was specifically activated in response to fallacy responses consistent with a semantic biasing of judgment explanation. A right fronto-parietal system was specifically recruited in response to detecting conflict associated with the heightened fallacy condition. These results are largely consistent with previous studies of reasoning fallacy and support a multiple systems model of reasoning.

  20. Automatic detection of photoresist residual layer in lithography using a neural classification approach

    KAUST Repository

    Gereige, Issam

    2012-09-01

    Photolithography is a fundamental process in the semiconductor industry and it is considered as the key element towards extreme nanoscale integration. In this technique, a polymer photo sensitive mask with the desired patterns is created on the substrate to be etched. Roughly speaking, the areas to be etched are not covered with polymer. Thus, no residual layer should remain on these areas in order to insure an optimal transfer of the patterns on the substrate. In this paper, we propose a nondestructive method based on a classification approach achieved by artificial neural network for automatic residual layer detection from an ellipsometric signature. Only the case of regular defect, i.e. homogenous residual layer, will be considered. The limitation of the method will be discussed. Then, an experimental result on a 400 nm period grating manufactured with nanoimprint lithography is analyzed with our method. © 2012 Elsevier B.V. All rights reserved.

  1. Using recurrent neural network models for early detection of heart failure onset.

    Science.gov (United States)

    Choi, Edward; Schuetz, Andy; Stewart, Walter F; Sun, Jimeng

    2017-03-01

    We explored whether use of deep learning to model temporal relations among events in electronic health records (EHRs) would improve model performance in predicting initial diagnosis of heart failure (HF) compared to conventional methods that ignore temporality. Data were from a health system's EHR on 3884 incident HF cases and 28 903 controls, identified as primary care patients, between May 16, 2000, and May 23, 2013. Recurrent neural network (RNN) models using gated recurrent units (GRUs) were adapted to detect relations among time-stamped events (eg, disease diagnosis, medication orders, procedure orders, etc.) with a 12- to 18-month observation window of cases and controls. Model performance metrics were compared to regularized logistic regression, neural network, support vector machine, and K-nearest neighbor classifier approaches. Using a 12-month observation window, the area under the curve (AUC) for the RNN model was 0.777, compared to AUCs for logistic regression (0.747), multilayer perceptron (MLP) with 1 hidden layer (0.765), support vector machine (SVM) (0.743), and K-nearest neighbor (KNN) (0.730). When using an 18-month observation window, the AUC for the RNN model increased to 0.883 and was significantly higher than the 0.834 AUC for the best of the baseline methods (MLP). Deep learning models adapted to leverage temporal relations appear to improve performance of models for detection of incident heart failure with a short observation window of 12-18 months. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association.

  2. Fluid pipeline system leak detection based on neural network and pattern recognition

    International Nuclear Information System (INIS)

    Tang Xiujia

    1998-01-01

    The mechanism of the stress wave propagation along the pipeline system of NPP, caused by turbulent ejection from pipeline leakage, is researched. A series of characteristic index are described in time domain or frequency domain, and compress numerical algorithm is developed for original data compression. A back propagation neural networks (BPNN) with the input matrix composed by stress wave characteristics in time domain or frequency domain is first proposed to classify various situations of the pipeline, in order to detect the leakage in the fluid flow pipelines. The capability of the new method had been demonstrated by experiments and finally used to design a handy instrument for the pipeline leakage detection. Usually a pipeline system has many inner branches and often in adjusting dynamic condition, it is difficult for traditional pipeline diagnosis facilities to identify the difference between inner pipeline operation and pipeline fault. The author first proposed pipeline wave propagation identification by pattern recognition to diagnose pipeline leak. A series of pattern primitives such as peaks, valleys, horizon lines, capstan peaks, dominant relations, slave relations, etc., are used to extract features of the negative pressure wave form. The context-free grammar of symbolic representation of the negative wave form is used, and a negative wave form parsing system with application to structural pattern recognition based on the representation is first proposed to detect and localize leaks of the fluid pipelines

  3. Dispersion compensation of fiber optic communication system with direct detection using artificial neural networks (ANNs)

    Science.gov (United States)

    Maghrabi, Mahmoud M. T.; Kumar, Shiva; Bakr, Mohamed H.

    2018-02-01

    This work introduces a powerful digital nonlinear feed-forward equalizer (NFFE), exploiting multilayer artificial neural network (ANN). It mitigates impairments of optical communication systems arising due to the nonlinearity introduced by direct photo-detection. In a direct detection system, the detection process is nonlinear due to the fact that the photo-current is proportional to the absolute square of the electric field intensity. The proposed equalizer provides the most efficient computational cost with high equalization performance. Its performance is comparable to the benchmark compensation performance achieved by maximum-likelihood sequence estimator. The equalizer trains an ANN to act as a nonlinear filter whose impulse response removes the intersymbol interference (ISI) distortions of the optical channel. Owing to the proposed extensive training of the equalizer, it achieves the ultimate performance limit of any feed-forward equalizer (FFE). The performance and efficiency of the equalizer is investigated by applying it to various practical short-reach fiber optic communication system scenarios. These scenarios are extracted from practical metro/media access networks and data center applications. The obtained results show that the ANN-NFFE compensates for the received BER degradation and significantly increases the tolerance to the chromatic dispersion distortion.

  4. Utility of a Herpes Oncolytic Virus for the Detection of Neural Invasion By Cancer

    Directory of Open Access Journals (Sweden)

    Ziv Gil

    2008-04-01

    Full Text Available Prostate, pancreatic, and head and neck carcinomas have a high propensity to invade nerves. Surgical resection is a treatment modality for these patients, but it may incur significant deficits. The development of an imaging method able to detect neural invasion (NI by cancer cells may guide surgical resection and facilitate preservation of normal nerves. We describe an imaging method for the detection of NI using a herpes simplex virus, NV1066, carrying tyrosine kinase and enhanced green fluorescent protein (eGFP. Infection of pancreatic (MiaPaCa2, prostate (PC3 and DU145, and adenoid cystic carcinoma (ACC3 cell lines with NV1066 induced a high expression of eGFP in vitro. An in vivo murine model of NI was established by implanting tumors into the sciatic nerves of nude mice. Nerves were then injected with NV1066, and infection was confirmed by polymerase chain reaction. Positron emission tomography with [18F]-2′-fluoro-2′-deoxyarabinofuranosyl-5-ethyluracil performed showed significantly higher uptake in NI than in control animals. Intraoperative fluorescent stereoscopic imaging revealed eGFP signal in NI treated with NV1066. These findings show that NV1066 may be an imaging method to enhance the detection of nerves infiltrated by cancer cells. This method may improve the diagnosis and treatment of patients with neurotrophic cancers by reducing injury to normal nerves and facilitating identification of infiltrated nerves requiring resection.

  5. Cerebral microbleed detection in traumatic brain injury patients using 3D convolutional neural networks

    Science.gov (United States)

    Standvoss, K.; Crijns, T.; Goerke, L.; Janssen, D.; Kern, S.; van Niedek, T.; van Vugt, J.; Alfonso Burgos, N.; Gerritse, E. J.; Mol, J.; van de Vooren, D.; Ghafoorian, M.; van den Heuvel, T. L. A.; Manniesing, R.

    2018-02-01

    The number and location of cerebral microbleeds (CMBs) in patients with traumatic brain injury (TBI) is important to determine the severity of trauma and may hold prognostic value for patient outcome. However, manual assessment is subjective and time-consuming due to the resemblance of CMBs to blood vessels, the possible presence of imaging artifacts, and the typical heterogeneity of trauma imaging data. In this work, we present a computer aided detection system based on 3D convolutional neural networks for detecting CMBs in 3D susceptibility weighted images. Network architectures with varying depth were evaluated. Data augmentation techniques were employed to improve the networks' generalization ability and selective sampling was implemented to handle class imbalance. The predictions of the models were clustered using a connected component analysis. The system was trained on ten annotated scans and evaluated on an independent test set of eight scans. Despite this limited data set, the system reached a sensitivity of 0.87 at 16.75 false positives per scan (2.5 false positives per CMB), outperforming related work on CMB detection in TBI patients.

  6. Can surgical simulation be used to train detection and classification of neural networks?

    Science.gov (United States)

    Zisimopoulos, Odysseas; Flouty, Evangello; Stacey, Mark; Muscroft, Sam; Giataganas, Petros; Nehme, Jean; Chow, Andre; Stoyanov, Danail

    2017-10-01

    Computer-assisted interventions (CAI) aim to increase the effectiveness, precision and repeatability of procedures to improve surgical outcomes. The presence and motion of surgical tools is a key information input for CAI surgical phase recognition algorithms. Vision-based tool detection and recognition approaches are an attractive solution and can be designed to take advantage of the powerful deep learning paradigm that is rapidly advancing image recognition and classification. The challenge for such algorithms is the availability and quality of labelled data used for training. In this Letter, surgical simulation is used to train tool detection and segmentation based on deep convolutional neural networks and generative adversarial networks. The authors experiment with two network architectures for image segmentation in tool classes commonly encountered during cataract surgery. A commercially-available simulator is used to create a simulated cataract dataset for training models prior to performing transfer learning on real surgical data. To the best of authors' knowledge, this is the first attempt to train deep learning models for surgical instrument detection on simulated data while demonstrating promising results to generalise on real data. Results indicate that simulated data does have some potential for training advanced classification methods for CAI systems.

  7. Incipient fault detection and identification in process systems using accelerating neural network learning

    International Nuclear Information System (INIS)

    Parlos, A.G.; Muthusami, J.; Atiya, A.F.

    1994-01-01

    The objective of this paper is to present the development and numerical testing of a robust fault detection and identification (FDI) system using artificial neural networks (ANNs), for incipient (slowly developing) faults occurring in process systems. The challenge in using ANNs in FDI systems arises because of one's desire to detect faults of varying severity, faults from noisy sensors, and multiple simultaneous faults. To address these issues, it becomes essential to have a learning algorithm that ensures quick convergence to a high level of accuracy. A recently developed accelerated learning algorithm, namely a form of an adaptive back propagation (ABP) algorithm, is used for this purpose. The ABP algorithm is used for the development of an FDI system for a process composed of a direct current motor, a centrifugal pump, and the associated piping system. Simulation studies indicate that the FDI system has significantly high sensitivity to incipient fault severity, while exhibiting insensitivity to sensor noise. For multiple simultaneous faults, the FDI system detects the fault with the predominant signature. The major limitation of the developed FDI system is encountered when it is subjected to simultaneous faults with similar signatures. During such faults, the inherent limitation of pattern-recognition-based FDI methods becomes apparent. Thus, alternate, more sophisticated FDI methods become necessary to address such problems. Even though the effectiveness of pattern-recognition-based FDI methods using ANNs has been demonstrated, further testing using real-world data is necessary

  8. A Neural Network Approach for Building An Obstacle Detection Model by Fusion of Proximity Sensors Data

    Science.gov (United States)

    Peralta, Emmanuel; Vargas, Héctor; Hermosilla, Gabriel

    2018-01-01

    Proximity sensors are broadly used in mobile robots for obstacle detection. The traditional calibration process of this kind of sensor could be a time-consuming task because it is usually done by identification in a manual and repetitive way. The resulting obstacles detection models are usually nonlinear functions that can be different for each proximity sensor attached to the robot. In addition, the model is highly dependent on the type of sensor (e.g., ultrasonic or infrared), on changes in light intensity, and on the properties of the obstacle such as shape, colour, and surface texture, among others. That is why in some situations it could be useful to gather all the measurements provided by different kinds of sensor in order to build a unique model that estimates the distances to the obstacles around the robot. This paper presents a novel approach to get an obstacles detection model based on the fusion of sensors data and automatic calibration by using artificial neural networks. PMID:29495338

  9. Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning.

    Science.gov (United States)

    Yousefi, Mina; Krzyżak, Adam; Suen, Ching Y

    2018-05-01

    Digital breast tomosynthesis (DBT) was developed in the field of breast cancer screening as a new tomographic technique to minimize the limitations of conventional digital mammography breast screening methods. A computer-aided detection (CAD) framework for mass detection in DBT has been developed and is described in this paper. The proposed framework operates on a set of two-dimensional (2D) slices. With plane-to-plane analysis on corresponding 2D slices from each DBT, it automatically learns complex patterns of 2D slices through a deep convolutional neural network (DCNN). It then applies multiple instance learning (MIL) with a randomized trees approach to classify DBT images based on extracted information from 2D slices. This CAD framework was developed and evaluated using 5040 2D image slices derived from 87 DBT volumes. The empirical results demonstrate that this proposed CAD framework achieves much better performance than CAD systems that use hand-crafted features and deep cardinality-restricted Bolzmann machines to detect masses in DBTs. Copyright © 2018 Elsevier Ltd. All rights reserved.

  10. A hybrid neural network – world cup optimization algorithm for melanoma detection

    Directory of Open Access Journals (Sweden)

    Razmjooy Navid

    2018-03-01

    Full Text Available One of the most dangerous cancers in humans is Melanoma. However, early detection of melanoma can help us to cure it completely. This paper presents a new efficient method to detect malignancy in melanoma via images. At first, the extra scales are eliminated by using edge detection and smoothing. Afterwards, the proposed method can be utilized to segment the cancer images. Finally, the extra information is eliminated by morphological operations and used to focus on the area which melanoma boundary potentially exists. To do this, World Cup Optimization algorithm is utilized to optimize an MLP neural Networks (ANN. World Cup Optimization algorithm is a new meta-heuristic algorithm which is recently presented and has a good performance in some optimization problems. WCO is a derivative-free, Meta-Heuristic algorithm, mimicking the world’s FIFA competitions. World cup Optimization algorithm is a global search algorithm while gradient-based back propagation method is local search. In this proposed algorithm, multi-layer perceptron network (MLP employs the problem’s constraints and WCO algorithm attempts to minimize the root mean square error. Experimental results show that the proposed method can develop the performance of the standard MLP algorithm significantly.

  11. Automated detection of lung nodules with three-dimensional convolutional neural networks

    Science.gov (United States)

    Pérez, Gustavo; Arbeláez, Pablo

    2017-11-01

    Lung cancer is the cancer type with highest mortality rate worldwide. It has been shown that early detection with computer tomography (CT) scans can reduce deaths caused by this disease. Manual detection of cancer nodules is costly and time-consuming. We present a general framework for the detection of nodules in lung CT images. Our method consists of the pre-processing of a patient's CT with filtering and lung extraction from the entire volume using a previously calculated mask for each patient. From the extracted lungs, we perform a candidate generation stage using morphological operations, followed by the training of a three-dimensional convolutional neural network for feature representation and classification of extracted candidates for false positive reduction. We perform experiments on the publicly available LIDC-IDRI dataset. Our candidate extraction approach is effective to produce precise candidates with a recall of 99.6%. In addition, false positive reduction stage manages to successfully classify candidates and increases precision by a factor of 7.000.

  12. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography.

    Science.gov (United States)

    Nakao, Takahiro; Hanaoka, Shouhei; Nomura, Yukihiro; Sato, Issei; Nemoto, Mitsutaka; Miki, Soichiro; Maeda, Eriko; Yoshikawa, Takeharu; Hayashi, Naoto; Abe, Osamu

    2018-04-01

    The usefulness of computer-assisted detection (CAD) for detecting cerebral aneurysms has been reported; therefore, the improved performance of CAD will help to detect cerebral aneurysms. To develop a CAD system for intracranial aneurysms on unenhanced magnetic resonance angiography (MRA) images based on a deep convolutional neural network (CNN) and a maximum intensity projection (MIP) algorithm, and to demonstrate the usefulness of the system by training and evaluating it using a large dataset. Retrospective study. There were 450 cases with intracranial aneurysms. The diagnoses of brain aneurysms were made on the basis of MRA, which was performed as part of a brain screening program. Noncontrast-enhanced 3D time-of-flight (TOF) MRA on 3T MR scanners. In our CAD, we used a CNN classifier that predicts whether each voxel is inside or outside aneurysms by inputting MIP images generated from a volume of interest (VOI) around the voxel. The CNN was trained in advance using manually inputted labels. We evaluated our method using 450 cases with intracranial aneurysms, 300 of which were used for training, 50 for parameter tuning, and 100 for the final evaluation. Free-response receiver operating characteristic (FROC) analysis. Our CAD system detected 94.2% (98/104) of aneurysms with 2.9 false positives per case (FPs/case). At a sensitivity of 70%, the number of FPs/case was 0.26. We showed that the combination of a CNN and an MIP algorithm is useful for the detection of intracranial aneurysms. 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:948-953. © 2017 International Society for Magnetic Resonance in Medicine.

  13. Neural correlates of change detection and change blindness in a working memory task.

    Science.gov (United States)

    Pessoa, Luiz; Ungerleider, Leslie G

    2004-05-01

    Detecting changes in an ever-changing environment is highly advantageous, and this ability may be critical for survival. In the present study, we investigated the neural substrates of change detection in the context of a visual working memory task. Subjects maintained a sample visual stimulus in short-term memory for 6 s, and were asked to indicate whether a subsequent, test stimulus matched or did not match the original sample. To study change detection largely uncontaminated by attentional state, we compared correct change and correct no-change trials at test. Our results revealed that correctly detecting a change was associated with activation of a network comprising parietal and frontal brain regions, as well as activation of the pulvinar, cerebellum, and inferior temporal gyrus. Moreover, incorrectly reporting a change when none occurred led to a very similar pattern of activations. Finally, few regions were differentially activated by trials in which a change occurred but subjects failed to detect it (change blindness). Thus, brain activation was correlated with a subject's report of a change, instead of correlated with the physical change per se. We propose that frontal and parietal regions, possibly assisted by the cerebellum and the pulvinar, might be involved in controlling the deployment of attention to the location of a change, thereby allowing further processing of the visual stimulus. Visual processing areas, such as the inferior temporal gyrus, may be the recipients of top-down feedback from fronto-parietal regions that control the reactive deployment of attention, and thus exhibit increased activation when a change is reported (irrespective of whether it occurred or not). Whereas reporting that a change occurred, be it correctly or incorrectly, was associated with strong activation in fronto-parietal sites, change blindness appears to involve very limited territories.

  14. Taller-than-wide sign for predicting thyroid microcarcinoma: comparison and combination of two ultrasonographic planes.

    Science.gov (United States)

    Chen, Shun-Ping; Hu, Yuan-Ping; Chen, Bin

    2014-09-01

    The aims of this study were to investigate the accuracy of using the taller-than-wide (TTW) sign in two ultrasonographic planes to predict thyroid microcarcinoma, and to confirm the hypothesis that the presence of a TTW sign in both the transverse and longitudinal ultrasonographic planes strongly suggests thyroid microcarcinoma. Nine hundred forty-two thyroid nodules ≤1 cm were submitted to surgical-histopathologic and ultrasonographic examination. TTW signs were divided into three types based on their detection only in the transverse plane (TTTW type, n = 100), only in the longitudinal plane (LTTW type, n = 61) or in both planes (BTTW type, n = 131). The areas under the receiver operating characteristic curves (A(z)) for the three different TTW signs, as well as for the combination of all TTW signs (ATTW, n = 292), were compared. The results indicated that the A(z) values of the TTTW, LTTW, BTTW and ATTW signs in predicting thyroid microcarcinoma were 0.544, 0.531, 0.627 and 0.702, respectively. The ATTW sign was the most accurate (p 0.05). Therefore, both the LTTW and TTTW signs are reliable markers of thyroid microcarcinoma. The BTTW sign strongly suggests thyroid microcarcinoma. Copyright © 2014 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.

  15. Reliability of Ultrasonographic Measurement of Cervical Multifidus Muscle Dimensions during Isometric Contraction of Neck Muscles

    Directory of Open Access Journals (Sweden)

    Somayeh Amiri Arimi

    2012-07-01

    Full Text Available Background and Aim: Cervical multifidus is considered as one of the most important neck stabilizers. Weakness and muscular atrophy of this muscle were seen in patients with chronic neck pain. Ultrasonographic imaging is a non-invasive and feasible technique that commonly used to record such changes and measure muscle dimensions. Therefore, the aim of this study was to evaluate the reliability of ultrasonographic measurement of cervical multifidus muscle’s dimensions during isometric contraction of neck muscles. Materials and Method: Ten subjects (5 patients with chronic neck pain and 5 healthy subjects were recruited in this study. Cervical multifidus muscle’s dimensions were measured at the level of forth cervical vertebrae. Ultrasonographic measurement of cervical multifidus muscle at rest, 50% and 100% of maximal voluntary contraction (MVC were performed by one examiner within 1 week interval. The dimensions of cervical multifidus muscle including cross-sectional area (CSA, anterior posterior dimension (APD, and lateral dimension (LD were measured. Intraclass correlation coefficients (ICC, standard error of measurement (SEM and minimal detectable change (MDC were computed for data analysis.Results: The between days reliability of maximum strength of neck muscles and multifidus muscle dimensions at rest, 50% and 100% of MVC of neck muscles were good to excellent (ICC=0.75-0.99.Conclusion: The results of this study showed that ultrasonographic measuring of cervical multifidus muscle’s dimensions during isometric contraction of neck muscles at the level of C4 in females with chronic neck pain and healthy subjects is a reliable and repeatable method.

  16. Single Layer Recurrent Neural Network for detection of swarm-like earthquakes in W-Bohemia/Vogtland - the method

    Czech Academy of Sciences Publication Activity Database

    Doubravová, Jana; Wiszniowski, J.; Horálek, Josef

    2016-01-01

    Roč. 93, August (2016), s. 138-149 ISSN 0098-3004 R&D Projects: GA ČR GAP210/12/2336; GA MŠk LM2010008 Institutional support: RVO:67985530 Keywords : event detection * artificial neural network * West Bohemia/Vogtland Subject RIV: DC - Siesmology, Volcanology, Earth Structure Impact factor: 2.533, year: 2016

  17. Neural - levelset shape detection segmentation of brain tumors in dynamic susceptibility contrast enhanced and diffusion weighted magnetic resonance images

    International Nuclear Information System (INIS)

    Vijayakumar, C.; Bhargava, Sunil; Gharpure, Damayanti Chandrashekhar

    2008-01-01

    A novel Neuro - level set shape detection algorithm is proposed and evaluated for segmentation and grading of brain tumours. The algorithm evaluates vascular and cellular information provided by dynamic contrast susceptibility magnetic resonance images and apparent diffusion coefficient maps. The proposed neural shape detection algorithm is based on the levels at algorithm (shape detection algorithm) and utilizes a neural block to provide the speed image for the level set methods. In this study, two different architectures of level set method have been implemented and their results are compared. The results show that the proposed Neuro-shape detection performs better in differentiating the tumor, edema, necrosis in reconstructed images of perfusion and diffusion weighted magnetic resonance images. (author)

  18. Anti-correlations in the degree distribution increase stimulus detection performance in noisy spiking neural networks.

    Science.gov (United States)

    Martens, Marijn B; Houweling, Arthur R; E Tiesinga, Paul H

    2017-02-01

    Neuronal circuits in the rodent barrel cortex are characterized by stable low firing rates. However, recent experiments show that short spike trains elicited by electrical stimulation in single neurons can induce behavioral responses. Hence, the underlying neural networks provide stability against internal fluctuations in the firing rate, while simultaneously making the circuits sensitive to small external perturbations. Here we studied whether stability and sensitivity are affected by the connectivity structure in recurrently connected spiking networks. We found that anti-correlation between the number of afferent (in-degree) and efferent (out-degree) synaptic connections of neurons increases stability against pathological bursting, relative to networks where the degrees were either positively correlated or uncorrelated. In the stable network state, stimulation of a few cells could lead to a detectable change in the firing rate. To quantify the ability of networks to detect the stimulation, we used a receiver operating characteristic (ROC) analysis. For a given level of background noise, networks with anti-correlated degrees displayed the lowest false positive rates, and consequently had the highest stimulus detection performance. We propose that anti-correlation in the degree distribution may be a computational strategy employed by sensory cortices to increase the detectability of external stimuli. We show that networks with anti-correlated degrees can in principle be formed by applying learning rules comprised of a combination of spike-timing dependent plasticity, homeostatic plasticity and pruning to networks with uncorrelated degrees. To test our prediction we suggest a novel experimental method to estimate correlations in the degree distribution.

  19. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.

    Science.gov (United States)

    Hirasawa, Toshiaki; Aoyama, Kazuharu; Tanimoto, Tetsuya; Ishihara, Soichiro; Shichijo, Satoki; Ozawa, Tsuyoshi; Ohnishi, Tatsuya; Fujishiro, Mitsuhiro; Matsuo, Keigo; Fujisaki, Junko; Tada, Tomohiro

    2018-07-01

    Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.

  20. Ultrasonographic findings of breast diseases during pregnancy and lactating period

    International Nuclear Information System (INIS)

    Lee, Yeon Hee; Park, Yong Hyun; Kwon, Tae Hee

    1995-01-01

    To evaluate ultrasonographic findings and usefulness in the diagnosis of breast diseases during pregnancy and lactating period. The authors evaluated the ultrasonographic findings of 18 breast diseases during pregnancy and lactation retrospectively. The ultrasonographic examinations were performed with linear-array 5 MHz transducer (ATL). Final diagnoses were obtained by the excisional biopsy, fine needle aspiration and clinical follow-up. Total 18 cases of breast diseases were consisted of 8 cases of galactocele, 4 cases of fibroadenoma, 3 cases of axillary accessory breast, 2 cases of lactating adenoma, and 1 case of phylloides tumor. The ultrasonographic findings of the above breast diseases were valuable in the diagnosis and therapeutic planning. Ultrasonography is the initial and useful method of diagnosing breast diseases during pregnancy and lactating period

  1. Ultrasonographic findings of breast diseases during pregnancy and lactating period

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Yeon Hee [Dnakook University College of Medicine, Cheonan (Korea, Republic of); Park, Yong Hyun; Kwon, Tae Hee [Cha Women' s Hospital of Seoul, Seoul (Korea, Republic of)

    1995-09-15

    To evaluate ultrasonographic findings and usefulness in the diagnosis of breast diseases during pregnancy and lactating period. The authors evaluated the ultrasonographic findings of 18 breast diseases during pregnancy and lactation retrospectively. The ultrasonographic examinations were performed with linear-array 5 MHz transducer (ATL). Final diagnoses were obtained by the excisional biopsy, fine needle aspiration and clinical follow-up. Total 18 cases of breast diseases were consisted of 8 cases of galactocele, 4 cases of fibroadenoma, 3 cases of axillary accessory breast, 2 cases of lactating adenoma, and 1 case of phylloides tumor. The ultrasonographic findings of the above breast diseases were valuable in the diagnosis and therapeutic planning. Ultrasonography is the initial and useful method of diagnosing breast diseases during pregnancy and lactating period.

  2. Blunt trauma to the spleen: ultrasonographic findings

    Energy Technology Data Exchange (ETDEWEB)

    Doody, O. [Department of Radiology, Tallaght Hospital, Dublin (Ireland); Lyburn, D. [Department of Radiology, Cheltenham General Hospital (United Kingdom); Geoghegan, T. [Department of Radiology, Tallaght Hospital, Dublin (Ireland); Govender, P. [Department of Radiology, Tallaght Hospital, Dublin (Ireland); Monk, P.M. [Department of Radiology, Vancouver Hospital (Canada); Torreggiani, W.C. [Department of Radiology, Tallaght Hospital, Dublin (Ireland)]. E-mail: william.torreggiani@amnch.ie

    2005-09-01

    The spleen is the most frequently injured organ in adults who sustain blunt abdominal trauma. Splenic trauma accounts for approximately 25% to 30% of all intra-abdominal injuries. The management of splenic injury has undergone rapid change over the last decade, with increasing emphasis on splenic salvage and non-operative management. Identifying the presence and degree of splenic injury is critical in triaging the management of patients. Imaging is integral in the identification of splenic injuries, both at the time of injury and during follow-up. Although CT remains the gold standard in blunt abdominal trauma, US continues to play an important role in assessing the traumatized spleen. This pictorial review illustrates the various ultrasonographic appearances of the traumatized spleen. Correlation with other imaging is presented and complications that occur during follow-up are described.

  3. Ultrasonographic identification of the cricothyroid membrane

    DEFF Research Database (Denmark)

    Kristensen, M S; Teoh, W H; Rudolph, S S

    2016-01-01

    Inability to identify the cricothyroid membrane by inspection and palpation contributes substantially to the high failure rate of cricothyrotomy. This narrative review summarizes the current evidence for application of airway ultrasonography for identification of the cricothyroid membrane compare...... ultrasonographic identification; a service that we should aim at making available in all locations where anaesthesia is undertaken and where patients with difficult airways could be encountered.......Inability to identify the cricothyroid membrane by inspection and palpation contributes substantially to the high failure rate of cricothyrotomy. This narrative review summarizes the current evidence for application of airway ultrasonography for identification of the cricothyroid membrane compared...... with the clinical techniques. We identified the best-documented techniques for bedside use, their success rates, and the necessary training for airway-ultrasound-naïve clinicians. After a short but structured training, the cricothyroid membrane can be identified using ultrasound in difficult patients by previously...

  4. Pitfall of ultrasonographic diagnosis in abdominal tuberculosis

    International Nuclear Information System (INIS)

    Lee, Y. H.; Yoo, H.S.; Kim, K. W.; Lee, J. T.; Park, C. Y.

    1983-01-01

    Intestinal tuberculosis is generally diagnosed using conventional barium studies, however recent diagnostic modalities such as ultrasonography and CT scan are widely applicated in conjunction with conventional studies for the search of lymph node presentation and associated extra-intestinal organs. It is important to differentiate intra-abdominal tuberculosis from metastatic or lymphomatous disease clinically. And it might be especially of worth to find out if there is any differential point between tuberculosis and other lymph nodal disease entities when we meet similar findings on imaging modalities. Authors have tried to evaluate ultrasonographic findings in conjunction with other studies in nine cases of abdominal tuberculosis which showed mainly extra-intestinal and/or lymph nodal involvement

  5. Ultrasonographic diagnosis of pyometra in bitches

    Directory of Open Access Journals (Sweden)

    Nereu Carlos Prestes

    1995-06-01

    Full Text Available A B-mode ultrasonography (SCANNER 450 (5MHz, Pie Medical, Netherlands was used either alone or associated with laboratorial and radiographic examinations in 33 bitches with clinical diagnosis of pyometra. The increased uterus appeared as a well defined tubular structure with diameter ranging from 0.5 up to 4.0 cm. The uterine lumen was less echoic than the wall, with evident echoic shinings. There was an accordance between the increasing in the viscosity of the vaginal secretion and the echoigenicity. The ultrasonographic diagnosis was possible in 31 bitches (94% confirmed by laparotomy and autopsy. The B-mode ultrasonography can be used in the diagnosis of bitches with pyometra.

  6. Ultrasonographic findings of psoas abscess and hematoma

    International Nuclear Information System (INIS)

    Kim, Eun Kyung; Lim, Jae Hoon; Ko, Young Tae; Choi, Yong Dae; Kim, Ho Kyun; Kim, Soon Yong

    1984-01-01

    A retrospective analysis of the ultrasonographic findings of 9 cases tuberculous abscess, 5 cases of pyogenic abscess and 2 cases of hematoma of psoas and adjacent muscles was made. Fluid collection with or without internal echoes was seen in 12 cases out of total 16 cases. Other findings were 2 cases of only muscle swelling, 1 cases of highly echogenic mass-like appearance and 1 case of fluid collection with septae. Ultrasonography is considered an accurate method in identifying early pathologic changes of the psoas muscle and determining its extent, and in differentiating tumor from fluid collection of the psoas muscle. Authors dare to say that ultrasound examination is a procedure of choice in the diagnosis of psoas abscess and hematoma

  7. Faulty node detection in wireless sensor networks using a recurrent neural network

    Science.gov (United States)

    Atiga, Jamila; Mbarki, Nour Elhouda; Ejbali, Ridha; Zaied, Mourad

    2018-04-01

    The wireless sensor networks (WSN) consist of a set of sensors that are more and more used in surveillance applications on a large scale in different areas: military, Environment, Health ... etc. Despite the minimization and the reduction of the manufacturing costs of the sensors, they can operate in places difficult to access without the possibility of reloading of battery, they generally have limited resources in terms of power of emission, of processing capacity, data storage and energy. These sensors can be used in a hostile environment, such as, for example, on a field of battle, in the presence of fires, floods, earthquakes. In these environments the sensors can fail, even in a normal operation. It is therefore necessary to develop algorithms tolerant and detection of defects of the nodes for the network of sensor without wires, therefore, the faults of the sensor can reduce the quality of the surveillance if they are not detected. The values that are measured by the sensors are used to estimate the state of the monitored area. We used the Non-linear Auto- Regressive with eXogeneous (NARX), the recursive architecture of the neural network, to predict the state of a node of a sensor from the previous values described by the functions of time series. The experimental results have verified that the prediction of the State is enhanced by our proposed model.

  8. WAVELET ANALYSIS AND NEURAL NETWORK CLASSIFIERS TO DETECT MID-SAGITTAL SECTIONS FOR NUCHAL TRANSLUCENCY MEASUREMENT

    Directory of Open Access Journals (Sweden)

    Giuseppa Sciortino

    2016-04-01

    Full Text Available We propose a methodology to support the physician in the automatic identification of mid-sagittal sections of the fetus in ultrasound videos acquired during the first trimester of pregnancy. A good mid-sagittal section is a key requirement to make the correct measurement of nuchal translucency which is one of the main marker for screening of chromosomal defects such as trisomy 13, 18 and 21. NT measurement is beyond the scope of this article. The proposed methodology is mainly based on wavelet analysis and neural network classifiers to detect the jawbone and on radial symmetry analysis to detect the choroid plexus. Those steps allow to identify the frames which represent correct mid-sagittal sections to be processed. The performance of the proposed methodology was analyzed on 3000 random frames uniformly extracted from 10 real clinical ultrasound videos. With respect to a ground-truth provided by an expert physician, we obtained a true positive, a true negative and a balanced accuracy equal to 87.26%, 94.98% and 91.12% respectively.

  9. Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks

    International Nuclear Information System (INIS)

    Hessel, G.; Schmitt, W.; Weiss, F.P.

    1993-10-01

    An acoustic method based on pattern recognition is being developed. During the learning phase, the localization classifier is trained with sound patterns that are generated with simulated leaks at all locations endangered by leak. The patterns are extracted from the signals of an appropriate sensor array. After training unknown leak positions can be recognized through comparison with the training patterns. The experimental part is performed at an acoustic 1:3 model of the reactor vessel and head and at an original VVER-440 reactor in the former NPP Greifswald. The leaks were simulated at the vessel head using mobile sound sources driven either by compressed air, a piezoelectric transmitter or by a thin metal blade excited through a jet of compressed air. The sound patterns of the simulated leaks are simultaneously detected with an AE-sensor array and with high frequency microphones measuring structure-borne sound and airborne sound, respectively. Pattern classifiers based on Fuzzy Pattern Classification (FPC) and Artificial Neural Networks (ANN) are currently tested for validation of the acoustic emission-sensor array (FPC), leak localization via structure-borne sound (FPC) and the leak localization using microphones (ANN). The initial results show the used classifiers principally to be capable of detecting and locating leaks, but they also show that further investigations are necessary to develop a reliable method applicable at NPPs. (orig./HP)

  10. Pre-trained convolutional neural networks as feature extractors for tuberculosis detection.

    Science.gov (United States)

    Lopes, U K; Valiati, J F

    2017-10-01

    It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists. Significant research can be found on automating diagnosis by applying computational techniques to medical images, thereby eliminating the need for individual image analysis and greatly diminishing overall costs. In addition, recent improvements on deep learning accomplished excellent results classifying images on diverse domains, but its application for tuberculosis diagnosis remains limited. Thus, the focus of this work is to produce an investigation that will advance the research in the area, presenting three proposals to the application of pre-trained convolutional neural networks as feature extractors to detect the disease. The proposals presented in this work are implemented and compared to the current literature. The obtained results are competitive with published works demonstrating the potential of pre-trained convolutional networks as medical image feature extractors. Copyright © 2017 Elsevier Ltd. All rights reserved.

  11. The neural circuits of innate fear: detection, integration, action, and memorization

    Science.gov (United States)

    Silva, Bianca A.; Gross, Cornelius T.

    2016-01-01

    How fear is represented in the brain has generated a lot of research attention, not only because fear increases the chances for survival when appropriately expressed but also because it can lead to anxiety and stress-related disorders when inadequately processed. In this review, we summarize recent progress in the understanding of the neural circuits processing innate fear in rodents. We propose that these circuits are contained within three main functional units in the brain: a detection unit, responsible for gathering sensory information signaling the presence of a threat; an integration unit, responsible for incorporating the various sensory information and recruiting downstream effectors; and an output unit, in charge of initiating appropriate bodily and behavioral responses to the threatful stimulus. In parallel, the experience of innate fear also instructs a learning process leading to the memorization of the fearful event. Interestingly, while the detection, integration, and output units processing acute fear responses to different threats tend to be harbored in distinct brain circuits, memory encoding of these threats seems to rely on a shared learning system. PMID:27634145

  12. Artificial neural networks for breathing and snoring episode detection in sleep sounds

    International Nuclear Information System (INIS)

    Emoto, Takahiro; Akutagawa, Masatake; Kinouchi, Yohsuke; Abeyratne, Udantha R; Chen, Yongjian; Kawata, Ikuji

    2012-01-01

    Obstructive sleep apnea (OSA) is a serious disorder characterized by intermittent events of upper airway collapse during sleep. Snoring is the most common nocturnal symptom of OSA. Almost all OSA patients snore, but not all snorers have the disease. Recently, researchers have attempted to develop automated snore analysis technology for the purpose of OSA diagnosis. These technologies commonly require, as the first step, the automated identification of snore/breathing episodes (SBE) in sleep sound recordings. Snore intensity may occupy a wide dynamic range (>95 dB) spanning from the barely audible to loud sounds. Low-intensity SBE sounds are sometimes seen buried within the background noise floor, even in high-fidelity sound recordings made within a sleep laboratory. The complexity of SBE sounds makes it a challenging task to develop automated snore segmentation algorithms, especially in the presence of background noise. In this paper, we propose a fundamentally novel approach based on artificial neural network (ANN) technology to detect SBEs. Working on clinical data, we show that the proposed method can detect SBE at a sensitivity and specificity exceeding 0.892 and 0.874 respectively, even when the signal is completely buried in background noise (SNR <0 dB). We compare the performance of the proposed technology with those of the existing methods (short-term energy, zero-crossing rates) and illustrate that the proposed method vastly outperforms conventional techniques. (paper)

  13. Ultrasonographic findings of posterior interosseous nerve syndrome

    Energy Technology Data Exchange (ETDEWEB)

    Kim, You Dong; Ha, Doo Hoe; Lee, Sang Min [Dept. of Radiology, CHA Bundang Medical Center, CHA University, Seongnam (Korea, Republic of)

    2017-10-15

    The purpose of this study was to evaluate the ultrasonographic findings associated with posterior interosseous nerve (PIN) syndrome. Approval from the Institutional Review Board was obtained. A retrospective review of 908 patients' sonographic images of the upper extremity from January 2001 to October 2010 revealed 10 patients suspicious for a PIN abnormality (7 male and 3 female patients; mean age of 51.8±13.1 years; age range, 32 to 79 years). The ultrasonographic findings of PIN syndrome, including changes in the PIN and adjacent secondary changes, were evaluated. The anteroposterior diameter of the pathologic PIN was measured in eight patients and the anteroposterior diameter of the contralateral asymptomatic PIN was measured in six patients, all at the level immediately proximal to the proximal supinator border. The size of the pathologic nerves and contralateral asymptomatic nerves was compared using the Mann-Whitney U test. Swelling of the PIN proximal to the supinator canal by compression at the arcade of Fröhse was observed in four cases. Swelling of the PIN distal to the supinator canal was observed in one case. Loss of the perineural fat plane in the supinator canal was observed in one case. Four soft tissue masses were noted. Secondary denervation atrophy of the supinator and extensor muscles was observed in two cases. The mean anteroposterior diameter of the pathologic nerves (n=8, 1.79±0.43 mm) was significantly larger than that of the contralateral asymptomatic nerves (n=6, 1.02±0.22 mm) (P=0.003). Ultrasonography provides high-resolution images of the PIN and helps to diagnose PIN syndrome through visualization of its various causes and adjacent secondary changes.

  14. Realtime ultrasonographic findings in gallbladder carcinoma

    Energy Technology Data Exchange (ETDEWEB)

    Ko, Y. T.; Woo, S. K.; Suh, I. J.; Lim, J. H.; Kim, H. K.; Kim, S. Y.; Ahn, C. Y. [Kyung Hee University Hospital, Seoul (Korea, Republic of)

    2010-05-15

    It is well known that realtime ultrasonography is the primary diagnostic modality to evaluate gallbladder diseases. The authors studied ultrasonographic findings of 10 pathologically proven gallbladder carcinoma patients, and it was compared with the findings of 4 cases of ERCP and 2 cases of CT which were performed at the same period. The results were as follows: 1. They were 6 males and 4 females with over 50 years of age except a 41 year old female. 2. The ultrasonographic classifications of the cases were 4 of fungating mass types, 3 of mass filling gallbladder types, 2 wall thickening types and 1 of mixed type, wall thickening and fungating mass. 3. Seven cases of cholecystitis, 6 cases of intrahepatic biliary duct dilatation, 5 cases of gallstone, 4 cases of common bile duct dilatation, 4 cases of sludge bile, 2 cases of gallbladder dilatation, 1 case of right sub phrenic and pericholecystic abscess due to perforated gallbladder. 4. Five cases of mesenteric infiltrations, 3 cases of hepatic infiltration adjacent to gallbladder, 2 cases of lymphatic metastasis to right lobe of liver and 2 cases of pericholedochal and pericaval lymph node metastasis. 5. The indistinct margin between gallbladder and surrounding organ adjacent to gallbladder mass or gallbladder wall thickening suggest cancer infiltration to adjacent organ such as liver or omentum. 6. If gallstone is engulfed in thickened gallbladder wall, the wall thickening suggests gallbladder carcinoma. 7. The differentiation between fungating mass and sludge bile, and the determination of mass could be done by positional change. 8. The preoperative ultrasonic diagnositc accuracy was in 9 out of 10 cases (90%). 9. Because of the frequent cystic duct obstruction by associated inflammation, the diagnostic accuracy of ERCP for gallbladder carcinoma was low.

  15. Realtime ultrasonographic findings in gallbladder carcinoma

    International Nuclear Information System (INIS)

    Ko, Y. T.; Woo, S. K.; Suh, I. J.; Lim, J. H.; Kim, H. K.; Kim, S. Y.; Ahn, C. Y.

    2010-01-01

    It is well known that realtime ultrasonography is the primary diagnostic modality to evaluate gallbladder diseases. The authors studied ultrasonographic findings of 10 pathologically proven gallbladder carcinoma patients, and it was compared with the findings of 4 cases of ERCP and 2 cases of CT which were performed at the same period. The results were as follows: 1. They were 6 males and 4 females with over 50 years of age except a 41 year old female. 2. The ultrasonographic classifications of the cases were 4 of fungating mass types, 3 of mass filling gallbladder types, 2 wall thickening types and 1 of mixed type, wall thickening and fungating mass. 3. Seven cases of cholecystitis, 6 cases of intrahepatic biliary duct dilatation, 5 cases of gallstone, 4 cases of common bile duct dilatation, 4 cases of sludge bile, 2 cases of gallbladder dilatation, 1 case of right sub phrenic and pericholecystic abscess due to perforated gallbladder. 4. Five cases of mesenteric infiltrations, 3 cases of hepatic infiltration adjacent to gallbladder, 2 cases of lymphatic metastasis to right lobe of liver and 2 cases of pericholedochal and pericaval lymph node metastasis. 5. The indistinct margin between gallbladder and surrounding organ adjacent to gallbladder mass or gallbladder wall thickening suggest cancer infiltration to adjacent organ such as liver or omentum. 6. If gallstone is engulfed in thickened gallbladder wall, the wall thickening suggests gallbladder carcinoma. 7. The differentiation between fungating mass and sludge bile, and the determination of mass could be done by positional change. 8. The preoperative ultrasonic diagnositc accuracy was in 9 out of 10 cases (90%). 9. Because of the frequent cystic duct obstruction by associated inflammation, the diagnostic accuracy of ERCP for gallbladder carcinoma was low.

  16. Abdominal endometriosis: Ultrasonographic findings (report of two cases)

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Jong Beum; Kim, Yong Goo; Lee, Yong Chul; Kim, Kun Sang [Chung Ang University Hospital, Seoul (Korea, Republic of)

    1993-12-15

    Endometriosis in the abdominal wall is a rare condition that most commonly occurs in the physiological scar of the umbilicus and in surgical scars of pelvic operation. The ultrasonographic findings are often non-specific, but with scrutinized physical examination and history, correct diagnosis can be made. We report ultrasonographic findings of abdominal wall endometriosis in two cases, both of which were related to previous cesarian section scar

  17. Benchmark for Peak Detection Algorithms in Fiber Bragg Grating Interrogation and a New Neural Network for its Performance Improvement

    Science.gov (United States)

    Negri, Lucas; Nied, Ademir; Kalinowski, Hypolito; Paterno, Aleksander

    2011-01-01

    This paper presents a benchmark for peak detection algorithms employed in fiber Bragg grating spectrometric interrogation systems. The accuracy, precision, and computational performance of currently used algorithms and those of a new proposed artificial neural network algorithm are compared. Centroid and gaussian fitting algorithms are shown to have the highest precision but produce systematic errors that depend on the FBG refractive index modulation profile. The proposed neural network displays relatively good precision with reduced systematic errors and improved computational performance when compared to other networks. Additionally, suitable algorithms may be chosen with the general guidelines presented. PMID:22163806

  18. Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees

    International Nuclear Information System (INIS)

    Jerebko, Anna K.; Summers, Ronald M.; Malley, James D.; Franaszek, Marek; Johnson, C. Daniel

    2003-01-01

    Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study

  19. External validation of fatty liver index for identifying ultrasonographic fatty liver in a large-scale cross-sectional study in Taiwan.

    Directory of Open Access Journals (Sweden)

    Bi-Ling Yang

    Full Text Available The fatty liver index (FLI is an algorithm involving the waist circumference, body mass index, and serum levels of triglyceride and gamma-glutamyl transferase to identify fatty liver. Although some studies have attempted to validate the FLI, few studies have been conducted for external validation among Asians. We attempted to validate FLI to predict ultrasonographic fatty liver in Taiwanese subjects.We enrolled consecutive subjects who received health check-up services at the Taipei Veterans General Hospital from 2002 to 2009. Ultrasonography was applied to diagnose fatty liver. The ability of the FLI to detect ultrasonographic fatty liver was assessed by analyzing the area under the receiver operating characteristic (AUROC curve.Among the 29,797 subjects enrolled in this study, fatty liver was diagnosed in 44.5% of the population. Subjects with ultrasonographic fatty liver had a significantly higher FLI than those without fatty liver by multivariate analysis (odds ratio 1.045; 95% confidence interval, CI 1.044-1.047, p< 0.001. Moreover, FLI had the best discriminative ability to identify patients with ultrasonographic fatty liver (AUROC: 0.827, 95% confidence interval, 0.822-0.831. An FLI < 25 (negative likelihood ratio (LR- 0.32 for males and <10 (LR- 0.26 for females rule out ultrasonographic fatty liver. Moreover, an FLI ≥ 35 (positive likelihood ratio (LR+ 3.12 for males and ≥ 20 (LR+ 4.43 for females rule in ultrasonographic fatty liver.FLI could accurately identify ultrasonographic fatty liver in a large-scale population in Taiwan but with lower cut-off value than the Western population. Meanwhile the cut-off value was lower in females than in males.

  20. Detection of breast cancer using advanced techniques of data mining with neural networks

    International Nuclear Information System (INIS)

    Ortiz M, J. A.; Celaya P, J. M.; Martinez B, M. R.; Solis S, L. O.; Castaneda M, R.; Garza V, I.; Martinez F, M.; Lopez H, Y.; Ortiz R, J. M.

    2016-10-01

    The breast cancer is one of the biggest health problems worldwide, is the most diagnosed cancer in women and prevention seems impossible since its cause is unknown, due to this; the early detection has a key role in the patient prognosis. In developing countries such as Mexico, where access to specialized health services is minimal, the regular clinical review is infrequent and there are not enough radiologists; the most common form of detection of breast cancer is through self-exploration, but this is only detected in later stages, when is already palpable. For these reasons, the objective of the present work is the creation of a system of computer assisted diagnosis (CAD x) using information analysis techniques such as data mining and advanced techniques of artificial intelligence, seeking to offer a previous medical diagnosis or a second opinion, as if it was a second radiologist in order to reduce the rate of mortality from breast cancer. In this paper, advances in the design of computational algorithms using computer vision techniques for the extraction of features derived from mammograms are presented. Using data mining techniques of data mining is possible to identify patients with a high risk of breast cancer. With the information obtained from the mammography analysis, the objective in the next stage will be to establish a methodology for the generation of imaging bio-markers to establish a breast cancer risk index for Mexican patients. In this first stage we present results of the classification of patients with high and low risk of suffering from breast cancer using neural networks. (Author)

  1. Optimal Seamline Detection for Orthoimage Mosaicking by Combining Deep Convolutional Neural Network and Graph Cuts

    Directory of Open Access Journals (Sweden)

    Li Li

    2017-07-01

    Full Text Available When mosaicking orthoimages, especially in urban areas with various obvious ground objects like buildings, roads, cars or trees, the detection of optimal seamlines is one of the key technologies for creating seamless and pleasant image mosaics. In this paper, we propose a new approach to detect optimal seamlines for orthoimage mosaicking with the use of deep convolutional neural network (CNN and graph cuts. Deep CNNs have been widely used in many fields of computer vision and photogrammetry in recent years, and graph cuts is one of the most widely used energy optimization frameworks. We first propose a deep CNN for land cover semantic segmentation in overlap regions between two adjacent images. Then, the energy cost of each pixel in the overlap regions is defined based on the classification probabilities of belonging to each of the specified classes. To find the optimal seamlines globally, we fuse the CNN-classified energy costs of all pixels into the graph cuts energy minimization framework. The main advantage of our proposed method is that the pixel similarity energy costs between two images are defined using the classification results of the CNN based semantic segmentation instead of using the image informations of color, gradient or texture as traditional methods do. Another advantage of our proposed method is that the semantic informations are fully used to guide the process of optimal seamline detection, which is more reasonable than only using the hand designed features defined to represent the image differences. Finally, the experimental results on several groups of challenging orthoimages show that the proposed method is capable of finding high-quality seamlines among urban and non-urban orthoimages, and outperforms the state-of-the-art algorithms and the commercial software based on the visual comparison, statistical evaluation and quantitative evaluation based on the structural similarity (SSIM index.

  2. Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes.

    Science.gov (United States)

    Yang, Guanci; Yang, Jing; Sheng, Weihua; Junior, Francisco Erivaldo Fernandes; Li, Shaobo

    2018-05-12

    Recent research has shown that the ubiquitous use of cameras and voice monitoring equipment in a home environment can raise privacy concerns and affect human mental health. This can be a major obstacle to the deployment of smart home systems for elderly or disabled care. This study uses a social robot to detect embarrassing situations. Firstly, we designed an improved neural network structure based on the You Only Look Once (YOLO) model to obtain feature information. By focusing on reducing area redundancy and computation time, we proposed a bounding-box merging algorithm based on region proposal networks (B-RPN), to merge the areas that have similar features and determine the borders of the bounding box. Thereafter, we designed a feature extraction algorithm based on our improved YOLO and B-RPN, called F-YOLO, for our training datasets, and then proposed a real-time object detection algorithm based on F-YOLO (RODA-FY). We implemented RODA-FY and compared models on our MAT social robot. Secondly, we considered six types of situations in smart homes, and developed training and validation datasets, containing 2580 and 360 images, respectively. Meanwhile, we designed three types of experiments with four types of test datasets composed of 960 sample images. Thirdly, we analyzed how a different number of training iterations affects our prediction estimation, and then we explored the relationship between recognition accuracy and learning rates. Our results show that our proposed privacy detection system can recognize designed situations in the smart home with an acceptable recognition accuracy of 94.48%. Finally, we compared the results among RODA-FY, Inception V3, and YOLO, which indicate that our proposed RODA-FY outperforms the other comparison models in recognition accuracy.

  3. Fuzzy-neural network in the automatic detection and volumetry of the spleen on spiral CT scans

    International Nuclear Information System (INIS)

    Heitmann, K.R.; Mainz Univ.; Rueckert, S.; Heussel, C.P.; Thelen, M.; Kauczor, H.U.; Uthmann, T.

    2000-01-01

    Purpose: To assess spleen segmentation and volumetry in spiral CT scans with and without pathological changes of splenic tissue. Methods: The image analysis software HYBRIKON is based on region growing, self-organized neural nets, and fuzzy-anatomic rules. The neural nets were trained with spiral CT data from 10 patients, not used in the following evaluation on spiral CT scans from 19 patients. An experienced radiologist verified the results. The true positive and false positive areas were compared in terms to the areas marked by the radiologist. The results were compared with a standard thresholding method. Results: The neural nets achieved a higher accuracy than the thresholding method. Correlation coefficient of the fuzzy-neural nets: 0.99 (thresholding: 0.63). Mean true positive rate: 90% (thresholding: 75%), mean false positive rate: 5% (thresholding>100%). Pitfalls were caused by accessory spleens, extreme changes in the morphology (tumors, metastases, cysts), and parasplenic masses. Conclusions: Self-organizing neural nets combined with fuzzy rules are ready for use in the automatic detection and volumetry of the spleen in spiral CT scans. (orig.) [de

  4. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks

    Science.gov (United States)

    Cruz-Roa, Angel; Basavanhally, Ajay; González, Fabio; Gilmore, Hannah; Feldman, Michael; Ganesan, Shridar; Shih, Natalie; Tomaszewski, John; Madabhushi, Anant

    2014-03-01

    This paper presents a deep learning approach for automatic detection and visual analysis of invasive ductal carcinoma (IDC) tissue regions in whole slide images (WSI) of breast cancer (BCa). Deep learning approaches are learn-from-data methods involving computational modeling of the learning process. This approach is similar to how human brain works using different interpretation levels or layers of most representative and useful features resulting into a hierarchical learned representation. These methods have been shown to outpace traditional approaches of most challenging problems in several areas such as speech recognition and object detection. Invasive breast cancer detection is a time consuming and challenging task primarily because it involves a pathologist scanning large swathes of benign regions to ultimately identify the areas of malignancy. Precise delineation of IDC in WSI is crucial to the subsequent estimation of grading tumor aggressiveness and predicting patient outcome. DL approaches are particularly adept at handling these types of problems, especially if a large number of samples are available for training, which would also ensure the generalizability of the learned features and classifier. The DL framework in this paper extends a number of convolutional neural networks (CNN) for visual semantic analysis of tumor regions for diagnosis support. The CNN is trained over a large amount of image patches (tissue regions) from WSI to learn a hierarchical part-based representation. The method was evaluated over a WSI dataset from 162 patients diagnosed with IDC. 113 slides were selected for training and 49 slides were held out for independent testing. Ground truth for quantitative evaluation was provided via expert delineation of the region of cancer by an expert pathologist on the digitized slides. The experimental evaluation was designed to measure classifier accuracy in detecting IDC tissue regions in WSI. Our method yielded the best quantitative

  5. Cascade Convolutional Neural Network Based on Transfer-Learning for Aircraft Detection on High-Resolution Remote Sensing Images

    Directory of Open Access Journals (Sweden)

    Bin Pan

    2017-01-01

    Full Text Available Aircraft detection from high-resolution remote sensing images is important for civil and military applications. Recently, detection methods based on deep learning have rapidly advanced. However, they require numerous samples to train the detection model and cannot be directly used to efficiently handle large-area remote sensing images. A weakly supervised learning method (WSLM can detect a target with few samples. However, it cannot extract an adequate number of features, and the detection accuracy requires improvement. We propose a cascade convolutional neural network (CCNN framework based on transfer-learning and geometric feature constraints (GFC for aircraft detection. It achieves high accuracy and efficient detection with relatively few samples. A high-accuracy detection model is first obtained using transfer-learning to fine-tune pretrained models with few samples. Then, a GFC region proposal filtering method improves detection efficiency. The CCNN framework completes the aircraft detection for large-area remote sensing images. The framework first-level network is an image classifier, which filters the entire image, excluding most areas with no aircraft. The second-level network is an object detector, which rapidly detects aircraft from the first-level network output. Compared with WSLM, detection accuracy increased by 3.66%, false detection decreased by 64%, and missed detection decreased by 23.1%.

  6. Multimodal ultrasonographic assessment of leiomyosarcoma of the femoral vein in a patient misdiagnosed as having deep vein thrombosis

    Science.gov (United States)

    Zhang, Mei; Yan, Feng; Huang, Bin; Wu, Zhoupeng; Wen, Xiaorong

    2017-01-01

    Abstract Rationale: Primary leiomyosarcoma (LMS) of the vein is a rare tumor that arises from the smooth muscle cells of the vessel wall and has an extremely poor prognosis. This tumor can occur in vessels such as the inferior vena cava, great saphenous vein, femoral vein, iliac vein, popliteal vein, and renal vein; the inferior vena cava is the most common site. LMS of the femoral vein can result in edema and pain in the lower extremity; therefore, it is not easy to be differentiated from deep vein thrombosis (DVT). Moreover, virtually no studies have described the ultrasonographic features of LMS of the vein in detail. Patient concerns: We present a case of a 55-year-old woman with LMS of the left femoral vein that was misdiagnosed as having deep vein thrombosis (DVT) on initial ultrasonographic examination. The patient began to experience edema and pain in her left leg seven months previously. She was diagnosed as having DVT on initial ultrasonographic examination, but the DVT treatment that she had received for 7 months failed to improve the status of her left lower limb. Diagnoses: She subsequently underwent re-examination by means of a multimodal ultrasonographic imaging approach (regular B-mode imaging, color Doppler imaging, pulsed-wave Doppler imaging, contrast-enhanced ultrasonography), which confirmed a diagnosis of LMS. Interventions: This patient was treated successfully with surgery. Outcomes: This case demonstrates that use of multiple ultrasonographic imaging techniques can be helpful to diagnose LMS accurately. Detection of vasculature in a dilated vein filled with a heterogeneous hypoechoic substance on ultrasonography is a sign of a tumor. Lessons: The pitfall of misdiagnosing this tumor as DVT is a useful reminder. PMID:29145269

  7. Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection

    Science.gov (United States)

    Cabrera-Vives, Guillermo; Reyes, Ignacio; Förster, Francisco; Estévez, Pablo A.; Maureira, Juan-Carlos

    2017-02-01

    We introduce Deep-HiTS, a rotation-invariant convolutional neural network (CNN) model for classifying images of transient candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RFs). We show that our CNN significantly outperforms the RF model, reducing the error by almost half. Furthermore, for a fixed number of approximately 2000 allowed false transient candidates per night, we are able to reduce the misclassified real transients by approximately one-fifth. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope. We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS. Deep-HiTS is licensed under the terms of the GNU General Public License v3.0.

  8. Convolutional neural network based side attack explosive hazard detection in three dimensional voxel radar

    Science.gov (United States)

    Brockner, Blake; Veal, Charlie; Dowdy, Joshua; Anderson, Derek T.; Williams, Kathryn; Luke, Robert; Sheen, David

    2018-04-01

    The identification followed by avoidance or removal of explosive hazards in past and/or present conflict zones is a serious threat for both civilian and military personnel. This is a challenging task as variability exists with respect to the objects, their environment and emplacement context, to name a few factors. A goal is the development of automatic or human-in-the-loop sensor technologies that leverage signal processing, data fusion and machine learning. Herein, we explore the detection of side attack explosive hazards (SAEHs) in three dimensional voxel space radar via different shallow and deep convolutional neural network (CNN) architectures. Dimensionality reduction is performed by using multiple projected images versus the raw three dimensional voxel data, which leads to noteworthy savings in input size and associated network hyperparameters. Last, we explore the accuracy and interpretation of solutions learned via random versus intelligent network weight initialization. Experiments are provided on a U.S. Army data set collected over different times, weather conditions, target types and concealments. Preliminary results indicate that deep learning can perform as good as, if not better, than a skilled domain expert, even in light of limited training data with a class imbalance.

  9. Application of Artificial Neural Network for Damage Detection in Planetary Gearbox of Wind Turbine

    Directory of Open Access Journals (Sweden)

    Marcin Strączkiewicz

    2016-01-01

    Full Text Available In the monitoring process of wind turbines the utmost attention should be given to gearboxes. This conclusion is derived from numerous summary papers. They reveal that, on the one hand, gearboxes are one of the most fault susceptible elements in the drive-train and, on the other, the most expensive to replace. Although state-of-the-art CMS can usually provide advanced signal processing tools for extraction of diagnostic information, there are still many installations, where the diagnosis is based simply on the averaged wideband features like root-mean-square (RMS or peak-peak (PP. Furthermore, for machinery working in highly changing operational conditions, like wind turbines, those estimators are strongly fluctuating, and this fluctuation is not linearly correlated to operation parameters. Thus, the sudden increase of a particular feature does not necessarily have to indicate the development of fault. To overcome this obstacle, it is proposed to detect a fault development with Artificial Neural Network (ANN and further observation of linear regression parameters calculated on the estimation error between healthy and unknown condition. The proposed reasoning is presented on the real life example of ring gear fault in wind turbine’s planetary gearbox.

  10. A neural network detection model of spilled oil based on the texture analysis of SAR image

    Science.gov (United States)

    An, Jubai; Zhu, Lisong

    2006-01-01

    A Radial Basis Function Neural Network (RBFNN) Model is investigated for the detection of spilled oil based on the texture analysis of SAR imagery. In this paper, to take the advantage of the abundant texture information of SAR imagery, the texture features are extracted by both wavelet transform and the Gray Level Co-occurrence matrix. The RBFNN Model is fed with a vector of these texture features. The RBFNN Model is trained and tested by the sample data set of the feature vectors. Finally, a SAR image is classified by this model. The classification results of a spilled oil SAR image show that the classification accuracy for oil spill is 86.2 by the RBFNN Model using both wavelet texture and gray texture, while the classification accuracy for oil spill is 78.0 by same RBFNN Model using only wavelet texture as the input of this RBFNN model. The model using both wavelet transform and the Gray Level Co-occurrence matrix is more effective than that only using wavelet texture. Furthermore, it keeps the complicated proximity and has a good performance of classification.

  11. Acoustic Emission Detection and Prediction of Fatigue Crack Propagation in Composite Patch Repairs Using Neural Networks

    International Nuclear Information System (INIS)

    Okafor, A. Chukwujekwu; Singh, Navdeep; Singh, Navrag

    2007-01-01

    An aircraft is subjected to severe structural and aerodynamic loads during its service life. These loads can cause damage or weakening of the structure especially for aging military and civilian aircraft, thereby affecting its load carrying capabilities. Hence composite patch repairs are increasingly used to repair damaged aircraft metallic structures to restore its structural efficiency. This paper presents the results of Acoustic Emission (AE) monitoring of crack propagation in 2024-T3 Clad aluminum panels repaired with adhesively bonded octagonal, single sided boron/epoxy composite patch under tension-tension fatigue loading. Crack propagation gages were used to monitor crack initiation. The identified AE sensor features were used to train neural networks for predicting crack length. The results show that AE events are correlated with crack propagation. AE system was able to detect crack propagation even at high noise condition of 10 Hz loading; that crack propagation signals can be differentiated from matrix cracking signals that take place due to fiber breakage in the composite patch. Three back-propagation cascade feed forward networks were trained to predict crack length based on the number of fatigue cycles, AE event number, and both the Fatigue Cycles and AE events, as inputs respectively. Network using both fatigue cycles and AE event number as inputs to predict crack length gave the best results, followed by Network with fatigue cycles as input, while network with just AE events as input had a greater error

  12. Abstract computation in schizophrenia detection through artificial neural network based systems.

    Science.gov (United States)

    Cardoso, L; Marins, F; Magalhães, R; Marins, N; Oliveira, T; Vicente, H; Abelha, A; Machado, J; Neves, J

    2015-01-01

    Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.

  13. Defect detection and classification of galvanized stamping parts based on fully convolution neural network

    Science.gov (United States)

    Xiao, Zhitao; Leng, Yanyi; Geng, Lei; Xi, Jiangtao

    2018-04-01

    In this paper, a new convolution neural network method is proposed for the inspection and classification of galvanized stamping parts. Firstly, all workpieces are divided into normal and defective by image processing, and then the defective workpieces extracted from the region of interest (ROI) area are input to the trained fully convolutional networks (FCN). The network utilizes an end-to-end and pixel-to-pixel training convolution network that is currently the most advanced technology in semantic segmentation, predicts result of each pixel. Secondly, we mark the different pixel values of the workpiece, defect and background for the training image, and use the pixel value and the number of pixels to realize the recognition of the defects of the output picture. Finally, the defect area's threshold depended on the needs of the project is set to achieve the specific classification of the workpiece. The experiment results show that the proposed method can successfully achieve defect detection and classification of galvanized stamping parts under ordinary camera and illumination conditions, and its accuracy can reach 99.6%. Moreover, it overcomes the problem of complex image preprocessing and difficult feature extraction and performs better adaptability.

  14. 3D Convolutional Neural Network for Automatic Detection of Lung Nodules in Chest CT.

    Science.gov (United States)

    Hamidian, Sardar; Sahiner, Berkman; Petrick, Nicholas; Pezeshk, Aria

    2017-01-01

    Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

  15. Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling.

    Science.gov (United States)

    Wang, Shui-Hua; Lv, Yi-Ding; Sui, Yuxiu; Liu, Shuai; Wang, Su-Jing; Zhang, Yu-Dong

    2017-11-17

    Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.

  16. Detection of single and multilayer clouds in an artificial neural network approach

    Science.gov (United States)

    Sun-Mack, Sunny; Minnis, Patrick; Smith, William L.; Hong, Gang; Chen, Yan

    2017-10-01

    Determining whether a scene observed with a satellite imager is composed of a thin cirrus over a water cloud or thick cirrus contiguous with underlying layers of ice and water clouds is often difficult because of similarities in the observed radiance values. In this paper an artificial neural network (ANN) algorithm, employing several Aqua MODIS infrared channels and the retrieved total cloud visible optical depth, is trained to detect multilayer ice-over-water cloud systems as identified by matched April 2009 CloudSat and CALIPSO (CC) data. The CC lidar and radar profiles provide the vertical structure that serves as output truth for a multilayer ANN, or MLANN, algorithm. Applying the trained MLANN to independent July 2008 MODIS data resulted in a combined ML and single layer hit rate of 75% (72%) for nonpolar regions during the day (night). The results are comparable to or more accurate than currently available methods. Areas of improvement are identified and will be addressed in future versions of the MLANN.

  17. Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks.

    Science.gov (United States)

    Längkvist, Martin; Jendeberg, Johan; Thunberg, Per; Loutfi, Amy; Lidén, Mats

    2018-06-01

    Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

  18. Impact detection method for composite winglets based on neural network implementation

    Science.gov (United States)

    Viscardi, Massimo; Arena, Maurizio; Napolitano, Pasquale

    2018-03-01

    Maintenance tasks and safety aspects represent a strategic role in the managing of the modern aircraft fleets. The demand for reliable techniques for structural health monitoring represent so a key aspect looking forward to new generation aircraft. In particular, the use of more technologically complex materials and manufacturing methods requires anyway more efficient as well as rapid application processes to improve the design strength and service life. Actually, it is necessary to rely on survey instruments, which allow for safeguarding the structural integrity of the aircraft, especially after the wide use of composite structures highly susceptible to non-detected damages as delamination of the ply. In this paper, the authors have investigated the feasibility to implement a neural network-based algorithm to predict the impact event at low frequency, typically due to the bird collision. Relying upon a numerical model, representative of a composite flat panel, the approach has been also experimentally validated. The purpose of the work is therefore the presentation of an innovative application within the Non Destructive Testing field based upon vibration measurements. The aim of the research has been the development of a Non Destructive Test which meets most of the mandatory requirements for effective health monitoring systems while, at the same time, reducing as much as possible the complexity of the data analysis algorithm and the experimental acquisition instrumentation. Future activities will be addressed to test such technique on a more complex aeronautical system.

  19. Abstract Computation in Schizophrenia Detection through Artificial Neural Network Based Systems

    Directory of Open Access Journals (Sweden)

    L. Cardoso

    2015-01-01

    Full Text Available Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason of defective information.

  20. Clinical, ultrasonographic, and roentgenographic study in 134 asymptomatic gallstone carriers

    International Nuclear Information System (INIS)

    Lirussi, F.; Passera, D.; Iemmolo, R.M.; Nassuato, G.; Okolicsanyi, L.

    1993-01-01

    The authors investigated retrospectively the ultrasonographic and roentgenographic characteristics of the gallstones and the gallbladder in 134 symtom-free carriers and evaluated prospectively the outcome and side effects of 6 to 24 months' ursodeoxycholic acid (UDCA) therapy in 36 individuals with silent stones. Two-thirds of the 134 subjects had multiple stones, and 71 to 75% had stones less than 15 mm in diameter. Gallstone calcification was detected in 13%. A non-functioning gallbladder was observed in 19%, whereas gallbladder contraction was normal in 64 of 76 gallstone carriers. With regard to oral bile acid treatment, complete and partial dissolutions were achieved in 7 and 9 of 33 subjects, respectively (48.5%). Development of a non-functioning gallbladder occurred in 9%, and acquired gallstone calcification was seen in another 15%. It is concluded that: i) the characteristics of the gallstones and the gallbladder are similar to those observed in symptomatic patients, and ii) UDCA therapy may be given in selected symptom-free carriers for no more than 6 to 12 months. Thereafter, it does not appear to be cost-effective. 23 refs., 2 figs., 3 tabs

  1. Automated radial basis function neural network based image classification system for diabetic retinopathy detection in retinal images

    Science.gov (United States)

    Anitha, J.; Vijila, C. Kezi Selva; Hemanth, D. Jude

    2010-02-01

    Diabetic retinopathy (DR) is a chronic eye disease for which early detection is highly essential to avoid any fatal results. Image processing of retinal images emerge as a feasible tool for this early diagnosis. Digital image processing techniques involve image classification which is a significant technique to detect the abnormality in the eye. Various automated classification systems have been developed in the recent years but most of them lack high classification accuracy. Artificial neural networks are the widely preferred artificial intelligence technique since it yields superior results in terms of classification accuracy. In this work, Radial Basis function (RBF) neural network based bi-level classification system is proposed to differentiate abnormal DR Images and normal retinal images. The results are analyzed in terms of classification accuracy, sensitivity and specificity. A comparative analysis is performed with the results of the probabilistic classifier namely Bayesian classifier to show the superior nature of neural classifier. Experimental results show promising results for the neural classifier in terms of the performance measures.

  2. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks.

    Science.gov (United States)

    Kim, D H; MacKinnon, T

    2018-05-01

    To identify the extent to which transfer learning from deep convolutional neural networks (CNNs), pre-trained on non-medical images, can be used for automated fracture detection on plain radiographs. The top layer of the Inception v3 network was re-trained using lateral wrist radiographs to produce a model for the classification of new studies as either "fracture" or "no fracture". The model was trained on a total of 11,112 images, after an eightfold data augmentation technique, from an initial set of 1,389 radiographs (695 "fracture" and 694 "no fracture"). The training data set was split 80:10:10 into training, validation, and test groups, respectively. An additional 100 wrist radiographs, comprising 50 "fracture" and 50 "no fracture" images, were used for final testing and statistical analysis. The area under the receiver operator characteristic curve (AUC) for this test was 0.954. Setting the diagnostic cut-off at a threshold designed to maximise both sensitivity and specificity resulted in values of 0.9 and 0.88, respectively. The AUC scores for this test were comparable to state-of-the-art providing proof of concept for transfer learning from CNNs in fracture detection on plain radiographs. This was achieved using only a moderate sample size. This technique is largely transferable, and therefore, has many potential applications in medical imaging, which may lead to significant improvements in workflow productivity and in clinical risk reduction. Copyright © 2017 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

  3. Neural correlates of own name and own face detection in autism spectrum disorder.

    Directory of Open Access Journals (Sweden)

    Hanna B Cygan

    Full Text Available Autism spectrum disorder (ASD is a heterogeneous neurodevelopmental condition clinically characterized by social interaction and communication difficulties. To date, the majority of research efforts have focused on brain mechanisms underlying the deficits in interpersonal social cognition associated with ASD. Recent empirical and theoretical work has begun to reveal evidence for a reduced or even absent self-preference effect in patients with ASD. One may hypothesize that this is related to the impaired attentional processing of self-referential stimuli. The aim of our study was to test this hypothesis. We investigated the neural correlates of face and name detection in ASD. Four categories of face/name stimuli were used: own, close-other, famous, and unknown. Event-related potentials were recorded from 62 electrodes in 23 subjects with ASD and 23 matched control subjects. P100, N170, and P300 components were analyzed. The control group clearly showed a significant self-preference effect: higher P300 amplitude to the presentation of own face and own name than to the close-other, famous, and unknown categories, indicating preferential attentional engagement in processing of self-related information. In contrast, detection of both own and close-other's face and name in the ASD group was associated with enhanced P300, suggesting similar attention allocation for self and close-other related information. These findings suggest that attention allocation in the ASD group is modulated by the personal significance factor, and that the self-preference effect is absent if self is compared to close-other. These effects are similar for physical and non-physical aspects of the autistic self. In addition, lateralization of face and name processing is attenuated in ASD, suggesting atypical brain organization.

  4. Neural correlates of own name and own face detection in autism spectrum disorder.

    Science.gov (United States)

    Cygan, Hanna B; Tacikowski, Pawel; Ostaszewski, Pawel; Chojnicka, Izabela; Nowicka, Anna

    2014-01-01

    Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental condition clinically characterized by social interaction and communication difficulties. To date, the majority of research efforts have focused on brain mechanisms underlying the deficits in interpersonal social cognition associated with ASD. Recent empirical and theoretical work has begun to reveal evidence for a reduced or even absent self-preference effect in patients with ASD. One may hypothesize that this is related to the impaired attentional processing of self-referential stimuli. The aim of our study was to test this hypothesis. We investigated the neural correlates of face and name detection in ASD. Four categories of face/name stimuli were used: own, close-other, famous, and unknown. Event-related potentials were recorded from 62 electrodes in 23 subjects with ASD and 23 matched control subjects. P100, N170, and P300 components were analyzed. The control group clearly showed a significant self-preference effect: higher P300 amplitude to the presentation of own face and own name than to the close-other, famous, and unknown categories, indicating preferential attentional engagement in processing of self-related information. In contrast, detection of both own and close-other's face and name in the ASD group was associated with enhanced P300, suggesting similar attention allocation for self and close-other related information. These findings suggest that attention allocation in the ASD group is modulated by the personal significance factor, and that the self-preference effect is absent if self is compared to close-other. These effects are similar for physical and non-physical aspects of the autistic self. In addition, lateralization of face and name processing is attenuated in ASD, suggesting atypical brain organization.

  5. Ultrasonographic findings of uterine polypoid adenomyomas

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Eun Ju [Ajou University School of Medicine, Suwon (Korea, Republic of)

    2002-12-15

    To characterize the ultrasonographic findings of polypoid adenomyoma of the uterus. Ultrasonographic findings of twenty seven patients with histologically confirmed polypoid adenomyoma were retrospectively reviewed. Ultrasonography (US) was performed in all patients while sonohysterography (SH) in fifteen patients and color Doppler sonography (CDS) in thirteen patients were additionally performed. Location, size, growth pattern, surface, margin from the endometrim and underlying myometrium, echogenecity and echotexture, presence and patterns of cystic areas, hemorrhage, and posterior shadowing of the endometrial or submucosal mass on US and SH were evaluated. The presence of blood flow and resistive index (RI) on CDS were also evaluated. On US and SH, the tumor location was the corpus in sixteen cases, fundus in eight, and isthmus in three cases, and the tumor size ranged from 0.5 to 6 cm (mean 3.5 cm). The tumors were polypoid in eighteen cases, sessile in four cases, and pedunculated in five cases, and three of them protruded into endocervical canal while two cases prolapsed through externals os. The surface was smooth in twenty six cases, lobulated in four and irregular in one. Nineteen cases had ill defined margin while eight cases, a well circumscribed margin. The mass was inhomogeneously isoechoic in twelve cases, homogeneously isoechoic in seven cases, homogeneously and inhomogeneously hyperechoic in four cases each, respectively. Cystic areas were seen in twenty cases, and there were three patterns of cystic areas: all solid mass (pattern 1, n=7), solid mass with cystic areas (pattern 2, n=18) and predominantly cystic mass (pattern 3, n=2). Eight cases had hemorrhage and seven had posterior shadowing. CDS showed a blood flow with range of RI from 0.19 to 0.74 (mean 0.47). Other findings included adenomyosis in sixteen cases, leiomyoma in three, and endometrial thickening and mass in one each, respectively. Polypoid adenomyoma can be characterized as a

  6. Definition and Reliability Assessment of Elementary Ultrasonographic Findings in Calcium Pyrophosphate Deposition Disease

    DEFF Research Database (Denmark)

    Filippou, Georgios; Scirè, Carlo A; Damjanov, Nemanja

    2017-01-01

    OBJECTIVE: To define the ultrasonographic characteristics of calcium pyrophosphate crystal (CPP) deposits in joints and periarticular tissues and to evaluate the intra- and interobserver reliability of expert ultrasonographers in the assessment of CPP deposition disease (CPPD) according to the ne...

  7. Neurometaplasticity: Glucoallostasis control of plasticity of the neural networks of error commission, detection, and correction modulates neuroplasticity to influence task precision

    Science.gov (United States)

    Welcome, Menizibeya O.; Dane, Şenol; Mastorakis, Nikos E.; Pereverzev, Vladimir A.

    2017-12-01

    The term "metaplasticity" is a recent one, which means plasticity of synaptic plasticity. Correspondingly, neurometaplasticity simply means plasticity of neuroplasticity, indicating that a previous plastic event determines the current plasticity of neurons. Emerging studies suggest that neurometaplasticity underlie many neural activities and neurobehavioral disorders. In our previous work, we indicated that glucoallostasis is essential for the control of plasticity of the neural network that control error commission, detection and correction. Here we review recent works, which suggest that task precision depends on the modulatory effects of neuroplasticity on the neural networks of error commission, detection, and correction. Furthermore, we discuss neurometaplasticity and its role in error commission, detection, and correction.

  8. Ultrasonographic evaluation of the healing of ventral midline abdominal incisions in the horse.

    Science.gov (United States)

    Wilson, D A; Badertscher, R R; Boero, M J; Baker, G J; Foreman, J H

    1989-06-01

    Ultrasonography was used to evaluate the ventral midline incisions of 21 ponies following exploratory laparotomy. The incisions were evaluated before surgery and at weekly intervals from one to seven weeks after surgery. Both 5.0 and 7.5 MHz linear array and 7.5 MHz sector transducers were used for the evaluations. The incisional complications observed were drainage, oedema, suture sinus formation, suture abscess, superficial dehiscence and incisional hernia. Ultrasonographic imaging of the ventral midline incision was an easy, reliable and objective method for detecting and monitoring the progression of incisional complications in a non-invasive manner.

  9. Imaging diagnosis--ultrasonographic appearance of small bowel metastasis from canine mammary carcinoma.

    Science.gov (United States)

    Domínguez, Elisabet; Anadón, Eduard; Espada, Yvonne; Grau-Roma, Llorenç; Majó, Natàlia; Novellas, Rosa

    2014-01-01

    A 10-year-old entire female Beagle dog was evaluated for an acute history of lethargy, anorexia, and diarrhea. Mammary tumors were detected during physical examination. Ultrasonographic scanning revealed the presence of a unique pattern of multiple, well-defined and well-marginated hypoechoic nodules in the muscularis layer of the jejunum. These nodules were not associated with changes in the rest of the normal intestinal layering and were not causing signs of intestinal obstruction. Mammary carcinoma metastases to the intestinal muscularis layer were diagnosed based on histopathological examination. © 2013 American College of Veterinary Radiology.

  10. Detection of copy number variants reveals association of cilia genes with neural tube defects.

    Directory of Open Access Journals (Sweden)

    Xiaoli Chen

    Full Text Available BACKGROUND: Neural tube defects (NTDs are one of the most common birth defects caused by a combination of genetic and environmental factors. Currently, little is known about the genetic basis of NTDs although up to 70% of human NTDs were reported to be attributed to genetic factors. Here we performed genome-wide copy number variants (CNVs detection in a cohort of Chinese NTD patients in order to exam the potential role of CNVs in the pathogenesis of NTDs. METHODS: The genomic DNA from eighty-five NTD cases and seventy-five matched normal controls were subjected for whole genome CNVs analysis. Non-DGV (the Database of Genomic Variants CNVs from each group were further analyzed for their associations with NTDs. Gene content in non-DGV CNVs as well as participating pathways were examined. RESULTS: Fifty-five and twenty-six non-DGV CNVs were detected in cases and controls respectively. Among them, forty and nineteen CNVs involve genes (genic CNV. Significantly more non-DGV CNVs and non-DGV genic CNVs were detected in NTD patients than in control (41.2% vs. 25.3%, p<0.05 and 37.6% vs. 20%, p<0.05. Non-DGV genic CNVs are associated with a 2.65-fold increased risk for NTDs (95% CI: 1.24-5.87. Interestingly, there are 41 cilia genes involved in non-DGV CNVs from NTD patients which is significantly enriched in cases compared with that in controls (24.7% vs. 9.3%, p<0.05, corresponding with a 3.19-fold increased risk for NTDs (95% CI: 1.27-8.01. Pathway analyses further suggested that two ciliogenesis pathways, tight junction and protein kinase A signaling, are top canonical pathways implicated in NTD-specific CNVs, and these two novel pathways interact with known NTD pathways. CONCLUSIONS: Evidence from the genome-wide CNV study suggests that genic CNVs, particularly ciliogenic CNVs are associated with NTDs and two ciliogenesis pathways, tight junction and protein kinase A signaling, are potential pathways involved in NTD pathogenesis.

  11. Ultrasonographic Findings of Subcutaneous and Muscular Sparganosis

    International Nuclear Information System (INIS)

    Park, Hee Jin; Park, Noh Hyuck; Lee, Eun Ja; Park, Chan Sub; Lee, Sung Moon; Park, Sung Il

    2009-01-01

    This study was deigned to evaluate the ultrasonographic findings of subcutaneous and intramuscular sparganosis. Nine cases of histologically proven subcutaneous and intramuscular sparganosis lesions in seven patients (mean patient age, 59 years; M:F = 6:1) were reviewed retrospectively. Two patients had recurrent sparganosis. A color Doppler examination was performed in all cases. A prior history of ingestion of raw snake meat was noted for two patients. Patients presented with a palpable mass and induration (n = 7) and dull pain (n = 4). Lesion locations were in the thigh (n = 4), lower leg (n = 2), chest wall (n = 1), an inguinal location (n = 1) and the neck (n = 1). Five lesions were in the subcutaneous fat layer and four lesions had intramuscular locations. Calcification was noted in two cases. All cases showed heterogeneous hypoechoic serpiginous tubular-and-oval lesions. The lesions were conglomerated or discrete in appearance. All nine cases showed the presence of lesions with a multi-layered wall with variable intraluminal echogenicity, at least in one segment of the lesion. Increased vascularity was noted on color Doppler examinations in two patients with pain. Subcutaneous or intramuscular sparganosis should be included in the differential diagnosis when a serpiginous tubular-and-oval lesion is noted that is seen with a multi-layered wall with variable intraluminal echogenicity

  12. Color Doppler Ultrasonographic Features of Hashimoto's Thyroiditis

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Joo Hyuk; Kim, Mie Young; Rho, Eun Jin; Yi, Jeong Geun; Han, Chun Hwan [Kangnam General Hospital Public Corporation, Seoul (Korea, Republic of); Hwang, Hee Yong [Choong Ang Gil Hospital, Incheon (Korea, Republic of)

    1995-06-15

    Color Doppler ultrasonographic(US) features of 28 patients with Hashimato's thyroiditis were evaluated with regard to echo and color-flow patterns. Correlation of color-flow pattern with thyroid function was performed. All 28 patients showed varying degrees of diffuse enlargement of the thyroid gland and a heterogeneous echo pattern.Color-flow pattern of increased blood flow. Low to moderate, focally increased blood flow was seen in 26 patients(92.8%). Of these 26 patients, 24 patients showed subclinical hypothyroidism or euthyroidism. Two patients who showed hyperthyroidism showed several pieces of focally increased color flow, Which was noted during both systole and diastole. Diffuse, multifocal color-flow throughout thyroid gland was seen in two patients with Hashimato's thyroiditis: one with clinical hypothyroidism and the other with subclinical hypothyroidism. Even though Hashimoto's thyroiditis showed variable color-flow patterns, we believe that heterogenous parenchymal echopattern with low or moderately increased flow is a rather characteristic feature of Hashimoto's thyroiditis, and we suggest that color Doppler US provides additional information for evaluation of Hashimoto's thyroiditis

  13. Ultrasonographic findings of benign soft tissue tumors

    International Nuclear Information System (INIS)

    Kim, Ki Sung; Oh, Dong Heon; Jung, Tae Gun; Kim, Yong Kil; Kwon, Jung Hyeok

    1994-01-01

    To clarify the characteristic sonographic features of benign soft tissue tumors and to evaluate the usefulness of sonographic imaging. We retrospectively reviewed ultrasonographic images of 70 cases in 68 patients with histologically proved benign soft tissue tumors. The tumors include 33 lipomas, 11 hemangiomas, 11 lymphangiomas, 7 neurilemmomas, 4 epidermoid cysts, 2 fibromas, 1 mesenchymoma, and 1 myxoma. The sonographic appearances of the lesions were mainly solid in 53 cases(33 lipomas, 8 hemangiomas, 2 lymphangiomas, 7 neurilemmomas, 2 fibromas and 1 mesenchymoma), mainly cystic in 14 cases(1 hemangioma, 8 lymphangiomas, 4 epidermoid cysts, and 1 myxomal), and mixed in 3 cases(2 hemangiomas and 1 lymphangioma). Although an accurate histologic prediction could not be made in most cases, certain patterns appeared to be characteristic of specific tumor types. 26 cases(78%) of lipoma were seen as lentiform, iso- or hyperechoic, solid mass. Hemangioma had variable appearance and characteristic calcifications were seen in 3 cases. Unicameral or multiseptated cystic mass with variable thickness of echogenic septa and solid portion was the characteristic finding of lymhangioma. Neurilemmoma showed lobulated, oval to round , relatively hypoechoic mass or with without internal cystic portion. Sonographic evaluation of benign soft tissue tumors is useful in demonstrating the location, size, extent, and internal characteristic of the mass. A relatively confident diagnosis can made when the characteristic features of the benign soft tissue tumor are present on sonographic imaging

  14. Ultrasonographic findings of benign soft tissue tumors

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Ki Sung; Oh, Dong Heon; Jung, Tae Gun; Kim, Yong Kil; Kwon, Jung Hyeok [Dongkang Genernal Hospital, Ulsan (Korea, Republic of)

    1994-05-15

    To clarify the characteristic sonographic features of benign soft tissue tumors and to evaluate the usefulness of sonographic imaging. We retrospectively reviewed ultrasonographic images of 70 cases in 68 patients with histologically proved benign soft tissue tumors. The tumors include 33 lipomas, 11 hemangiomas, 11 lymphangiomas, 7 neurilemmomas, 4 epidermoid cysts, 2 fibromas, 1 mesenchymoma, and 1 myxoma. The sonographic appearances of the lesions were mainly solid in 53 cases(33 lipomas, 8 hemangiomas, 2 lymphangiomas, 7 neurilemmomas, 2 fibromas and 1 mesenchymoma), mainly cystic in 14 cases(1 hemangioma, 8 lymphangiomas, 4 epidermoid cysts, and 1 myxomal), and mixed in 3 cases(2 hemangiomas and 1 lymphangioma). Although an accurate histologic prediction could not be made in most cases, certain patterns appeared to be characteristic of specific tumor types. 26 cases(78%) of lipoma were seen as lentiform, iso- or hyperechoic, solid mass. Hemangioma had variable appearance and characteristic calcifications were seen in 3 cases. Unicameral or multiseptated cystic mass with variable thickness of echogenic septa and solid portion was the characteristic finding of lymhangioma. Neurilemmoma showed lobulated, oval to round , relatively hypoechoic mass or with without internal cystic portion. Sonographic evaluation of benign soft tissue tumors is useful in demonstrating the location, size, extent, and internal characteristic of the mass. A relatively confident diagnosis can made when the characteristic features of the benign soft tissue tumor are present on sonographic imaging.

  15. Color Doppler Ultrasonographic Features of Hashimoto's Thyroiditis

    International Nuclear Information System (INIS)

    Lee, Joo Hyuk; Kim, Mie Young; Rho, Eun Jin; Yi, Jeong Geun; Han, Chun Hwan; Hwang, Hee Yong

    1995-01-01

    Color Doppler ultrasonographic(US) features of 28 patients with Hashimato's thyroiditis were evaluated with regard to echo and color-flow patterns. Correlation of color-flow pattern with thyroid function was performed. All 28 patients showed varying degrees of diffuse enlargement of the thyroid gland and a heterogeneous echo pattern.Color-flow pattern of increased blood flow. Low to moderate, focally increased blood flow was seen in 26 patients(92.8%). Of these 26 patients, 24 patients showed subclinical hypothyroidism or euthyroidism. Two patients who showed hyperthyroidism showed several pieces of focally increased color flow, Which was noted during both systole and diastole. Diffuse, multifocal color-flow throughout thyroid gland was seen in two patients with Hashimato's thyroiditis: one with clinical hypothyroidism and the other with subclinical hypothyroidism. Even though Hashimoto's thyroiditis showed variable color-flow patterns, we believe that heterogenous parenchymal echopattern with low or moderately increased flow is a rather characteristic feature of Hashimoto's thyroiditis, and we suggest that color Doppler US provides additional information for evaluation of Hashimoto's thyroiditis

  16. ULTRASONOGRAPHIC EVALUATION OF AMOEBIC LIVER ABSCESS

    Directory of Open Access Journals (Sweden)

    Nagesh

    2016-04-01

    Full Text Available AIMS To study the role of ultrasonography in the diagnosis, followup, resolution and percutaneous interventions of amoebic liver abscesses. METHODOLOGY 25 patients with 38 amoebic liver abscesses were included in this study. The diagnostic criteria being compatible history, tender and enlarged liver, radiological and ultrasound findings and response to metronidazole therapy. Confirmed cases of amoebic liver abscesses were followed up by ultrasonography till complete resolution. RESULTS The highest incidence of age was seen between 3 rd and 5 th decades (84% with a male sex incidence of 92%, disease preponderance in people belonging to low socioeconomic group and a high incidence among alcoholics. The radiological findings were: Elevation of right dome of diaphragm (56%, restricted diaphragmatic movements (88%, right basal lung changes (48%, right pleural effusion (12%, and indistinct hazy diaphragmatic contour (40%. The ultrasonographic findings were: 87% of the abscesses were located in right lobe, 11% in left lobe and 2% in both lobes. Among the 25 patients, 76% showed solitary and 24% showed multiple abscesses. Of the 38 amoebic abscesses, 79% were hypoechoic, 13% were hyperechoic and 8% were anechoic. 11 patients were subjected for ultrasound-guided aspiration. CONCLUSION Ultrasound is a safe, reliable and non-invasive imaging modality for the diagnosis, followup and percutaneous interventions of amoebic liver abscesses. The sonographic resolution time of amoebic liver abscesses varies from 28 to 286 days.

  17. Individual Identification Using Functional Brain Fingerprint Detected by Recurrent Neural Network.

    Science.gov (United States)

    Chen, Shiyang; Hu, Xiaoping P

    2018-03-20

    Individual identification based on brain function has gained traction in literature. Investigating individual differences in brain function can provide additional insights into the brain. In this work, we introduce a recurrent neural network based model for identifying individuals based on only a short segment of resting state functional MRI data. In addition, we demonstrate how the global signal and differences in atlases affect the individual identifiability. Furthermore, we investigate neural network features that exhibit the uniqueness of each individual. The results indicate that our model is able to identify individuals based on neural features and provides additional information regarding brain dynamics.

  18. Proposed Network Intrusion Detection System ‎In Cloud Environment Based on Back ‎Propagation Neural Network

    Directory of Open Access Journals (Sweden)

    Shawq Malik Mehibs

    2017-12-01

    Full Text Available Cloud computing is distributed architecture, providing computing facilities and storage resource as a service over the internet. This low-cost service fulfills the basic requirements of users. Because of the open nature and services introduced by cloud computing intruders impersonate legitimate users and misuse cloud resource and services. To detect intruders and suspicious activities in and around the cloud computing environment, intrusion detection system used to discover the illegitimate users and suspicious action by monitors different user activities on the network .this work proposed based back propagation artificial neural network to construct t network intrusion detection in the cloud environment. The proposed module evaluated with kdd99 dataset the experimental results shows promising approach to detect attack with high detection rate and low false alarm rate

  19. Ultrasonographic findings in goats with contagious caprine pleuropneumonia caused by Mycoplasma capricolum subsp. capripneumoniae.

    Science.gov (United States)

    Tharwat, Mohamed; Al-Sobayil, Fahd

    2017-08-22

    In goats, contagious caprine pleuropneumonia (CCPP) is a cause of major economic losses in Africa, Asia and in the Middle East. There is no information emphasising the importance of diagnostic ultrasound in goats with CCPP caused by Mycoplasma capricolum subsp. capripneumoniae (Mccp). This study was designed to describe the ultrasonographic findings in goats with CCPP caused by Mccp and to correlate ultrasonographic with post-mortem findings. To this end, 55 goats with CCPP were examined. Twenty-five healthy adult goats were used as a control group. Major clinical findings included harried, painful respiration, dyspnoea and mouth breathing. On ultrasonography, a liver-like echotexture was imaged in 13 goats. Upon post-mortem examination, all 13 goats exhibited unilateral pulmonary consolidation. Seven goats had a unilateral hypoechoic pleural effusion. At necropsy, the related lung was consolidated and the pleural fluid appeared turbid and greenish. Pleural abscessiation detected in five goats was confirmed post-mortem. Twenty-eight goats had a bright, fibrinous matrix extending over the chest wall containing numerous anechoic fluid pockets with medial displacement and compression of lung tissue. Echogenic tags imaged floating in the fluid were found upon post-mortem examination to be fibrin. In two goats, a consolidated right parenchyma was imaged together with hypoechoic pericardial effusions with echogenic tags covering the epicardium. At necropsy, the right lung was consolidated in three goats and fibrin threads were found covering the epicardium and pericardium. In goats with CCPP, the extension and the severity of the pulmonary changes could not be verified with clinical certainty in most cases, whereas this was possible most of the time with sonography, thus making the prognosis easier. Ultrasonographic examination of the pleurae and the lungs helped in the detection of various lesions.

  20. Ultrasonographic diagnosis of ureteral stones: Accuracy and factors influencing on diagnostic sensitivity

    Energy Technology Data Exchange (ETDEWEB)

    Park, Young Mi; Han, Sang Seok; Chang, Seung Kuk; Joo, Sang Hoo; Lee, Jeong Sik; Eun, Choong Ki [Pusan Paik Hospital, Inje University College of Medicine, Pusan (Korea, Republic of)

    1999-12-15

    To determine the accuracy of ultrasonographic diagnosis in patients with clinically suspected ureteral stones and to evaluate the factors influencing on the diagnostic sensitivity for the detection of ureteral stone. The patients (115 cases) with proven presence or absence of ureteral stones were included in the study. At first, both sided kidney and proximal ureters were examined on each decubitus position and then middle ureters were done if proximal ureters were visualized. On the supine view, distal ureters and UVJ were scanned through the acoustic window of the filled bladder. KUB (20 cases), IVU (62 cases), AGP (7 cases), RGP (3 cases), ESWL (9 cases), CT (9 cases), and patients' history of spontaneous passage of stones (5 cases) were included as confirmation methods. The sensitivity, specificity, and accuracy of the ultrasonographic diagnosis of ureteral stones were calculated and the factors influencing on the sensitivity on the focus of the position and size of ureteral stone, visibility of ureter, the presence or absence of renal stone and hydronephrosis were analyzed. Of 82 cases with proven ureteral stone, 72 cases were revealed on ultrasonography and there was one false positive examination among 33 cases with proven absence of ureteral stone. The overall diagnostic accuracy was 90%. The ultrasonographic detection rates of ureteral stones as correlated with their locations were 83% (24/29), 100% (11/11), 80% (16/20), and 100% (21/21) of each group of proximal, middle, distal ureter, and UVJ stones. Of 61 stones, those as correlated with their sizes, were 82% (37/45) and 94% (15/16) of each group less than 10 mm and more than 11 mm. Those as correlated with the presence or absence of ureteral visualization on ultrasonography were 92% (69/75) and 43% (3/7) of each group. Those as correlated with presence of absence of renal stones were 85% (41/48) and 91% (31/34) of each group. Those as correlated with presence or absence of hydronephrosis were 89

  1. Comparison of the use of binary decision trees and neural networks in top-quark detection

    International Nuclear Information System (INIS)

    Bowser-Chao, D.; Dzialo, D.L.

    1993-01-01

    The use of neural networks for signal versus background discrimination in high-energy physics experiments has been investigated and has compared favorably with the efficiency of traditional kinematic cuts. Recent work in top-quark identification produced a neural network that, for a given top-quark mass, yielded a higher signal-to-background ratio in Monte Carlo simulation than a corresponding set of conventional cuts. In this article we discuss another pattern-recognition algorithm, the binary decision tree. We apply a binary decision tree to top-quark identification at the Fermilab Tevatron and find it to be comparable in performance to the neural network. Furthermore, reservations about the ''black box'' nature of neural network discriminators do not appy to binary decision trees; a binary decision tree may be reduced to a set of kinematic cuts subject to conventional error analysis

  2. Musculoskeletal ultrasonographic evaluation of lower limb enthesopathy in ankylosing spondylitis and Behçet’s disease: Relation to clinical status and disease activity

    Directory of Open Access Journals (Sweden)

    E A Baraka

    2016-01-01

    Conclusion Ultrasonographic changes at the entheseal sites of the lower limbs are prevalent in both AS and BD. These changes are more frequently related to functional and articular involvement. MSUS is more sensitive than clinical examination in detecting enthesopathies of the lower limbs in both AS and BD patients.

  3. Usage of Probabilistic and General Regression Neural Network for Early Detection and Prevention of Oral Cancer

    OpenAIRE

    Sharma, Neha; Om, Hari

    2015-01-01

    In India, the oral cancers are usually presented in advanced stage of malignancy. It is critical to ascertain the diagnosis in order to initiate most advantageous treatment of the suspicious lesions. The main hurdle in appropriate treatment and control of oral cancer is identification and risk assessment of early disease in the community in a cost-effective fashion. The objective of this research is to design a data mining model using probabilistic neural network and general regression neural...

  4. Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography.

    Science.gov (United States)

    Samala, Ravi K; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A; Wei, Jun; Cha, Kenny

    2016-12-01

    Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a

  5. Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection

    Science.gov (United States)

    Wang, Haibo; Cruz-Roa, Angel; Basavanhally, Ajay; Gilmore, Hannah; Shih, Natalie; Feldman, Mike; Tomaszewski, John; Gonzalez, Fabio; Madabhushi, Anant

    2014-03-01

    Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is mitotic count, which involves quantifying the number of cells in the process of dividing (i.e. undergoing mitosis) at a specific point in time. Currently mitosis counting is done manually by a pathologist looking at multiple high power fields on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical or textural attributes of mitoses or features learned with convolutional neural networks (CNN). While handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely unsupervised feature generation methods, there is an appeal to attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. In this paper, we present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing performance by

  6. Medical management of first trimester miscarriage according to ultrasonographic findings

    DEFF Research Database (Denmark)

    Vejborg, Thomas; Nilas, Lisbeth; Rørbye, Christina

    2007-01-01

    BACKGROUND: The efficacy of medical treatment of first trimester miscarriages may depend on the regimen used, the definition of success, clinical symptoms, and, possibly, on the ultrasonographic findings. Our primary aim was to assess if a single dose of misoprostol could reduce the number of sur...... of pregnancy failure, time of assessment, and the criteria for success.......BACKGROUND: The efficacy of medical treatment of first trimester miscarriages may depend on the regimen used, the definition of success, clinical symptoms, and, possibly, on the ultrasonographic findings. Our primary aim was to assess if a single dose of misoprostol could reduce the number...... ultrasonography after either 1, 2 or 3 days. Treatment was successful if a complete abortion was diagnosed at follow-up. The women were divided into 4 ultrasonographically-defined groups: missed abortion with a crown rump length (CRL)>or=6 mm (Group A1) or CRL

  7. Comparison of pixel -based and artificial neural networks classification methods for detecting forest cover changes in Malaysia

    International Nuclear Information System (INIS)

    Deilmai, B R; Rasib, A W; Ariffin, A; Kanniah, K D

    2014-01-01

    According to the FAO (Food and Agriculture Organization), Malaysia lost 8.6% of its forest cover between 1990 and 2005. In forest cover change detection, remote sensing plays an important role. A lot of change detection methods have been developed, and most of them are semi-automated. These methods are time consuming and difficult to apply. One of the new and robust methods for change detection is artificial neural network (ANN). In this study, (ANN) classification scheme is used to detect the forest cover changes in the Johor state in Malaysia. Landsat Thematic Mapper images covering a period of 9 years (2000 and 2009) are used. Results obtained with ANN technique was compared with Maximum likelihood classification (MLC) to investigate whether ANN can perform better in the tropical environment. Overall accuracy of the ANN and MLC techniques are 75%, 68% (2000) and 80%, 75% (2009) respectively. Using the ANN method, it was found that forest area in Johor decreased as much as 1298 km2 between 2000 and 2009. The results also showed the potential and advantages of neural network in classification and change detection analysis

  8. Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection.

    Science.gov (United States)

    Sarikaya, Duygu; Corso, Jason J; Guru, Khurshid A

    2017-07-01

    Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To the best of our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a region proposal network (RPN) and a multimodal two stream convolutional network for object detection to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an average precision of 91% and a mean computation time of 0.1 s per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new data set, ATLAS Dione, for RAS video understanding. Our data set provides video data of ten surgeons from Roswell Park Cancer Institute, Buffalo, NY, USA, performing six different surgical tasks on the daVinci Surgical System (dVSS) with annotations of robotic tools per frame.

  9. Ultrasonographic Features of Papillary Thyroid Carcinomas According to Their Subtypes

    Directory of Open Access Journals (Sweden)

    Hye Jin Baek

    2018-05-01

    Full Text Available BackgroundThe ultrasonographic characteristics and difference for various subtypes of papillary thyroid carcinoma (PTC are still unclear. The aim of this study was to compare the ultrasonographic features of PTC according to its subtype in patients undergoing thyroid surgery.MethodsIn total, 140 patients who underwent preoperative thyroid ultrasonography (US and thyroid surgery between January 2016 and December 2016 were included. The ultrasonographic features and the Korean Thyroid Imaging Reporting and Data System (K-TIRADS category of each thyroid nodule were retrospectively evaluated by a single radiologist, and differences in ultrasonographic features according to the PTC subtype were assessed.ResultsAccording to histopathological analyses, there were 97 classic PTCs (62.2%, 34 follicular variants (21.8%, 5 tall cell variants (3.2%, 2 oncocytic variants (1.3%, 1 Warthin-like variant (0.6%, and 1 diffuse sclerosing variant (0.6%. Most PTCs were classified under K-TIRADS category 5. Among the ultrasonographic features, the nodule margin and the presence of calcification were significantly different among the PTC subtypes. A spiculated/microlobulated margin was the most common type of margin, regardless of the PTC subtype. In particular, all tall cell variants exhibited a spiculated/microlobulated margin. The classic PTC group exhibited the highest prevalence of intranodular calcification, with microcalcification being the most common. The prevalence of multiplicity and nodal metastasis was high in the tall cell variant group.ConclusionThe majority of PTCs in the present study belonged to K-TIRADS category 5, regardless of the subtype. Our findings suggest that ultrasonographic features are not useful for distinguishing PTC subtypes.

  10. Nanoparticle-based and bioengineered probes and sensors to detect physiological and pathological biomarkers in neural cells

    Directory of Open Access Journals (Sweden)

    Dusica eMaysinger

    2015-12-01

    Full Text Available Nanotechnology, a rapidly evolving field, provides simple and practical tools to investigate the nervous system in health and disease. Among these tools are nanoparticle-based probes and sensors that detect biochemical and physiological properties of neurons and glia, and generate signals proportionate to physical, chemical, and/or electrical changes in these cells. In this context, quantum dots (QDs, carbon-based structures (C-dots, graphene and nanodiamonds and gold nanoparticles are the most commonly used nanostructures. They can detect and measure enzymatic activities of proteases (metalloproteinases, caspases, ions, metabolites, and other biomolecules under physiological or pathological conditions in neural cells. Here, we provide some examples of nanoparticle-based and genetically engineered probes and sensors that are used to reveal changes in protease activities and calcium ion concentrations. Although significant progress in developing these tools has been made for probing neural cells, several challenges remain. We review many common hurdles in sensor development, while highlighting certain advances. In the end, we propose some future directions and ideas for developing practical tools for neural cell investigations, based on the maxim Measure what is measurable, and make measurable what is not so (Galileo Galilei.

  11. Transperineal Ultrasonographic findings of female urethral diverticulum

    International Nuclear Information System (INIS)

    Cho, Jin Han; Koo, Bong Sik; Nam, Ki Dong; Choi, Jong Cheol; Park, Byeong Ho; Nam, Kyung Jin; Kweon, Heon Young

    1999-01-01

    The purpose of the study was to explore the role of sonography for women with a suspected urethral diverticulum and to evaluate the transperineal ultrasonographic findings of female urethral diverticulum. Eight women (mean age, 44 years) who presented with urethral symptoms and clinically suspected urethral diverticula underwent transperineal ultrasonography; sagittal and coronal images were obtained. Sonography was done with either a 7-5 MHz curved array transducer or 10-5 MHz linear transducer, placed on the perineum at the level of the urethra. Ultrasonograms were assessed for the presence, size, location, shape, echogenicity, and septum. Five patients underwent voiding cystourethrography (VCUG). Results of the sonograms and VCUGs were compared with each other and with surgical findings. Longitudinally, all lesions were located in a middle third of the urethra. In axial plane, 4 diverticula wrapped around 50-100% of the urethra. 3 cases located posteriorly, and 1 case laterally. Seven diverticula contained echogenic debris. Three cases have septa in the diverticulum. The outer margin of the diverticula was smooth in 2 patients and was lobulated in 6 patients. In 3 of 5 cases who underwent VCUG, diverticula were filled with contrast, and appeared to be smaller than those of ultrasonography. In addition, all were single diverticulum in VCUG. Most urethral diverticulum were located in a middle third of the urethra, wrapped around the urethra or round posteriorly. Many cases appear unilocular or multilocular with echogenic debris. Transperineal ultrasonography is easy to operate and accurate for showing urethral diverticulum, and it may be useful for diagnosing this group of women with urethral symptoms and suspected urethral diverticulum. It provides information on the extent and location of the diverticulum, which are important in surgical excision.

  12. Ultrasonographic Findings of Prepubertal Testicular Teratoma

    International Nuclear Information System (INIS)

    Won, Jang Han; Cho, Jae Ho

    2005-01-01

    To evaluate the ultrasonographic findings of testicular teratoma arising in pre-pubertal children. We studied 6 cases in 5 patients with pathologically proven testicular teratoma. Ultrasonography was performed in all cases and MRI in 5 cases. The location, size, shape, margin and internal echo pattern of the lesion were evaluated on ultrasonography and the shape, signal intensity and presence or absence of contrast enhancement were evaluated on MRI. The shape of all cases was round or oval and the lesion size ranged from 0.5 to 3.5 cm (average, 1.7 cm). Four of 6 cases were seen as cystic lesions, Three of which were multilocular and one was unilocular. The cystic lesions were filled with echo-free fluid without any solid component. The inner wall and septa were minutely granulated. One of 6 cases was seen as a predominantly cystic lesion containing heterogeneous, high echoic portions. One case was seen as a heterogeneous mixed echoic lesion with dirty posterior sonic shadowing. Three of the 4 cases seen as a cyst on ultrasonography were also seen as a cyst on MRI. In one case seen as a predominantly cystic lesion on ultrasonography, the periphery of the lesion was hypointense and the center was hyperintense on T2-weighted image. The remaining case seen as a heterogeneous mixed echoic mass was markedly heterogeneous in signal intensity both on T2- and T1-weighted images and hyperintense fat components were noted. Contrast enhancement was not seen in any of the 4 cases. On ultrasonography, pre-pubertal testicular teratoma is commonly seen as a multilocular or unilocular cyst and a minutely granulated appearance is noted in the inner wall or septa of the cystic lesion

  13. Ultrasonographic findings of type IIIa biliary atresia

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Seung Seob; Kim, Myung Joon; Lee, Mi Jung; Yoon, Choon Sik; Han, Seok Joo; Koh, Hong [Dept. of Radiology, Research Institute of Radiological Science, Severance Hospital, Yensei University College of Medicine, Seoul (Korea, Republic of)

    2014-12-15

    To describe the ultrasonographic (US) findings of type IIIa biliary atresia. We retrospectively reviewed a medical database of patients pathologically confirmed to have biliary atresia, Kasai type IIIa, between January 2002 and May 2013 (n=18). We evaluated US findings including the visible common bile duct (CBD), triangular cord thickness, gallbladder size and shape, and subcapsular flow on color Doppler US; laboratory data; and pathological hepatic fibrosis grades. We divided them into two groups-those with visible (group A) and invisible (group B) CBD on US-and compared all parameters between the two groups. CBD was visible on US in five cases (27.8%; group A) and invisible in 13 cases (72.2%; group B). US was performed at an earlier age in group A than in group B (median, 27 days vs. 60 days; P=0.027) with the maximal age of 51 days. A comparison of the US findings revealed that the triangular cord thickness was smaller (4.1 mm vs. 4.9 mm; P=0.004) and the gallbladder length was larger (20.0 mm vs. 11.7 mm; P=0.021) in group A. The gallbladder shape did not differ between the two groups, and the subcapsular flow was positive in all cases of both groups. There was no significant difference in the laboratory data between the two groups. Upon pathological analysis, group A showed low-grade and group B showed low- to high-grade hepatic fibrosis. When CBD is visible on US in patients diagnosed with type IIIa biliary atresia, other US features could have a false negative status. A subcapsular flow on the color Doppler US would be noted in the type IIIa biliary atresia patients.

  14. Ultrasonographic diagnosis of pancreatic and peripancreatic cancer

    International Nuclear Information System (INIS)

    Park, Churl Min; Kim, Ho Kyun; Yoon, Yup; Lee, Sun Wha; Kim, Soon Yong; Ahn, Chi Yul

    1982-01-01

    Seventeen cases of cancers in and adjacent to the pancreas were studied by high resolution and wide field real time ultrasonographic scanner with 3.5 MHz linear array electronically focusing transducer. The result were as follows: 1. In a total of 17 cases, 7 cases were pancreatic cancers and the rests were 3 cases of ampulla of Vaster cancer, 3 cases of distal CBD cancers, and 4 cases of metastatic cancers, respectively. 2. Pancreatic cancers were located mainly in head portion, and metastatic cancers were noted in head, tail, and retropancreatic areas. 3. The sizes of all distal CBD cancer were less than 1.8 cm, usually smaller than other tumors, and the size of metastatic cancers were variable (1-6 cm). 4. The shape, margin, contour and echogenicity of the tumors were variable. 5. Pancreatic duct showed marked dilatation in one of pancreatic cancer, and mild dilatation in one of ampulla of Vater cancer. 6. The caliber of extrahepatic duct were moderately or markedly dilated in nearly all cases except 2 cases of pancreatic body cancer. 7. The pancreatic margin is partially obliterated in pancreatic and ampulla of Vater cancers but not in distal CBD cancer. 8. Gallbladder enlargement is secondary change due to the obstruction of extrahepatic bile duct. 9. Effects on the vessels are due to not only direct mass effect but direct invasion resulting in obliteration. The most commonly involved vessels are spleno-portal junction, splenic vein and portal vein. In case of pancreatic cancer in uncinate process, the superior mesenteric vessels are displaced anteriorly. 10. Surrounding metastatic lesions were suspected in pancreatic and ampulla of Vater cancer, but not seen in distal CBD cancer. 11. Ascites were seen in only two cases of metastasis

  15. Reliability of ultrasonographic measurements in suspected patients of developmental dysplasia of the hip and correlation with the acetabular index

    Directory of Open Access Journals (Sweden)

    Cem Copuroglu

    2011-01-01

    Full Text Available Background: Ultrasonography is accepted as a useful imaging modality in the early detection of developmental dysplasia of the hip (DDH. Early detection and early treatment of DDH prevents hip dislocation and related physical, social, economic, and psychological problems. The purpose of this study was to evaluate the reliability of ultrasonographic and roentgenographic measurements measured by seven different observers. Materials and Methods: The alpha angles of 66 hips in 33 patients were measured using the Graf method by seven different observers. Acetabular index degrees on plane roentgenograms were measured in order to assess the correlation between the ultrasonographic alpha angle and the radiographic acetabular index, which both show the bony acetabular depth, retrospectively. Results: The interclass correlation coefficient, measuring the interobserver reliability, was high and statistically significant for the ultrasonographic measurements. There was a negative correlation between the alpha angle and the acetabular index. Conclusions: Ultrasonography, when applied properly, is a reliable technique between different observers, in the diagnosis and follow up of DDH. When assessed concomitantly with the roentgenographic measurements, the results are reliable and statistically meaningful.

  16. Two neural network based strategies for the detection of a total instantaneous blockage of a sodium-cooled fast reactor

    International Nuclear Information System (INIS)

    Martinez-Martinez, Sinuhe; Messai, Nadhir; Jeannot, Jean-Philippe; Nuzillard, Danielle

    2015-01-01

    The total instantaneous blockage (TIB) of an assembly in the core of a sodium-cooled fast reactor (SFR) is investigated. Such incident could appear as an abnormal rise in temperature on the assemblies neighbouring the blockage. Its detection relies on a dataset of temperature measurements of the assemblies making up the core of the French Phenix Nuclear Reactor. The data are provided by the French Commission of Atomic and Alternatives Energies (CEA). Here, two strategies are proposed depending on whether the sensor measurement of the suspected assembly is reliable or not. The proposed methodology implements a time-lagged feed-forward neural (TLFFN) Network in order to predict the one-step-ahead temperature of a given assembly. The incident is declared if the difference between the predicted process and the actual one exceeds a threshold. In these simulated conditions, the method is efficient to detect small gradients as expected in reality. - Highlights: • We study the total instantaneous blockage (TIB) of a sodium-cooled fast reactor. • The TIB symptom is simulated as an abrupt rise on temperature (0.1–1 °C/s). • The goal is to improve the early detection of the incident. • Two strategies laying on neural networks are proposed. • TIB is detected in 3 s for 1 °C/s and 18–21 s for 0.1 °C/s

  17. Mammographic and Ultrasonographic Findings of the Chemoport Insertion Site

    International Nuclear Information System (INIS)

    Kim, Seun Jung; Kang, Bong Joo; Cha, Eun Suk; Park, Hye Jung; Kim, Sung Hun; Choi, Jae Jeong; Lee, Ji Hye

    2010-01-01

    To describe mammographic and ultrasonographic findings of previous chemoport insertion sites. We included patients who had abnormal findings at chemoport insertion sites on mammography and ultrasonography from 224 patients who underwent chemoport insertion and breast imaging at our institution between January, 2005, and December, 2007. Abnormal findings were identified in 16 mammographies and 14 ultrasonographies in 10 patients. The mean age was 50.9 years and the age range was from 44 to 67 years. Abnormal findings on mammography and ultrasonography were retrospectively analyzed according to ACR/BI-RADS. All cases were followed up with imaging studies for 2 years to confirm changes after chemoport insertion. Of the abnormal findings identified on mammography, focal asymmetry (7/16) was the most common. Other abnormal findings included mass (6/16), skin retraction (2/16), residual chemoport tip (1/16), and trabecular thickening (1/16). Of the abnormal findings seen on ultrasonography, skin thickening (12/14) was the most common. Other abnormal findings included mass (5/14), diffuse increased echogenicity of subcutaneous tissue (1/14), and a localized skin nodule (1/14). Abnormal findings on mammography and ultrasonography were located in the upper outer quadrant in 5 patients, upper inner quadrant in 3 patients, and mid upper portion in 1 patient. In 1 patient, the abnormal finding was only identified in the mediolateral oblique view of her mammography. Radiologists should be aware of potential abnormal findings on mammography and ultrasonography following chemoport insertion. In particular, ultrasonography is a very useful modality for detecting skin complications after chemoport insertion

  18. Human Detection System by Fusing Depth Map-Based Method and Convolutional Neural Network-Based Method

    Directory of Open Access Journals (Sweden)

    Anh Vu Le

    2017-01-01

    Full Text Available In this paper, the depth images and the colour images provided by Kinect sensors are used to enhance the accuracy of human detection. The depth-based human detection method is fast but less accurate. On the other hand, the faster region convolutional neural network-based human detection method is accurate but requires a rather complex hardware configuration. To simultaneously leverage the advantages and relieve the drawbacks of each method, one master and one client system is proposed. The final goal is to make a novel Robot Operation System (ROS-based Perception Sensor Network (PSN system, which is more accurate and ready for the real time application. The experimental results demonstrate the outperforming of the proposed method compared with other conventional methods in the challenging scenarios.

  19. Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network.

    Science.gov (United States)

    Charron, Odelin; Lallement, Alex; Jarnet, Delphine; Noblet, Vincent; Clavier, Jean-Baptiste; Meyer, Philippe

    2018-04-01

    Stereotactic treatments are today the reference techniques for the irradiation of brain metastases in radiotherapy. The dose per fraction is very high, and delivered in small volumes (diameter convolutional neural network (DeepMedic) to detect and segment brain metastases on MRI. At first, we sought to adapt the network parameters to brain metastases. We then explored the single or combined use of different MRI modalities, by evaluating network performance in terms of detection and segmentation. We also studied the interest of increasing the database with virtual patients or of using an additional database in which the active parts of the metastases are separated from the necrotic parts. Our results indicated that a deep network approach is promising for the detection and the segmentation of brain metastases on multimodal MRI. Copyright © 2018 Elsevier Ltd. All rights reserved.

  20. Detection of Atrial Fibrillation Using Artifical Neural Network with Power Spectrum Density of RR Interval of Electrocardiogram

    Science.gov (United States)

    Afdala, Adfal; Nuryani, Nuryani; Satrio Nugroho, Anto

    2017-01-01

    Atrial fibrillation (AF) is a disorder of the heart with fairly high mortality in adults. AF is a common heart arrythmia which is characterized by a missing or irregular contraction of atria. Therefore, finding a method to detect atrial fibrillation is necessary. In this article a system to detect atrial fibrillation has been proposed. Detection system utilized backpropagation artifical neural network. Data input in this method includes power spectrum density of R-peaks interval of electrocardiogram which is selected by wrapping method. This research uses parameter learning rate, momentum, epoch and hidden layer. System produces good performance with accuracy, sensitivity, and specificity of 83.55%, 86.72 % and 81.47 %, respectively.

  1. The Prevalence of Fetal Neural Abnormalities Detected By Ultrasonography in Southeast Part of Turkey

    Directory of Open Access Journals (Sweden)

    Ayhan Özkur

    2010-04-01

    CONCLUSIONS: The results of this study showed that the overall prevalence of fetal neural abnormalities in the Department of Radiology in Gaziantep University is relevant to current medical literature. However, the prevalence of schizencephaly is remarkably higher than previously reported, which is thought to be due to high sensitivity of high resolution sonography devices used in this study.

  2. Detection of nonstationary transition to synchronized states of a neural network using recurrence analyses

    Science.gov (United States)

    Budzinski, R. C.; Boaretto, B. R. R.; Prado, T. L.; Lopes, S. R.

    2017-07-01

    We study the stability of asymptotic states displayed by a complex neural network. We focus on the loss of stability of a stationary state of networks using recurrence quantifiers as tools to diagnose local and global stabilities as well as the multistability of a coupled neural network. Numerical simulations of a neural network composed of 1024 neurons in a small-world connection scheme are performed using the model of Braun et al. [Int. J. Bifurcation Chaos 08, 881 (1998), 10.1142/S0218127498000681], which is a modified model from the Hodgkin-Huxley model [J. Phys. 117, 500 (1952)]. To validate the analyses, the results are compared with those produced by Kuramoto's order parameter [Chemical Oscillations, Waves, and Turbulence (Springer-Verlag, Berlin Heidelberg, 1984)]. We show that recurrence tools making use of just integrated signals provided by the networks, such as local field potential (LFP) (LFP signals) or mean field values bring new results on the understanding of neural behavior occurring before the synchronization states. In particular we show the occurrence of different stationary and nonstationarity asymptotic states.

  3. Artificial Neural Networks to Detect Risk of Type 2 Diabetes | Baha ...

    African Journals Online (AJOL)

    A multilayer feedforward architecture with backpropagation algorithm was designed using Neural Network Toolbox of Matlab. The network was trained using batch mode backpropagation with gradient descent and momentum. Best performed network identified during the training was 2 hidden layers of 6 and 3 neurons, ...

  4. Anti-correlations in the degree distribution increase stimulus detection performance in noisy spiking neural networks

    NARCIS (Netherlands)

    Martens, M.B. (Marijn B.); A.R. Houweling (Arthur); E. Tiesinga, P.H. (Paul H.)

    2017-01-01

    textabstractNeuronal circuits in the rodent barrel cortex are characterized by stable low firing rates. However, recent experiments show that short spike trains elicited by electrical stimulation in single neurons can induce behavioral responses. Hence, the underlying neural networks provide

  5. Ultrasonographic assessment of renal length in 310 Turkish children ...

    African Journals Online (AJOL)

    Scanning was performed with a 3.5 MHz ultrasound probe in the supine position. The ultrasonographic appearance of the kidneys we measured was normal. The maximum length of each kidney was measured. The renal length was correlated with somatic parameters including age, body height and weight. Regression ...

  6. Feline alimentary lymphosarcoma: radiographic, ultrasonographic, histologic, and viral findings

    International Nuclear Information System (INIS)

    Hittmair, K.; Krebitz-Gressl, E.; Kuebber-Heiss, A.; Moestl, K.

    2000-01-01

    Sixty cats with clinical symptoms indicative of gastroin-testinal lymphosarcoma were examined radiographically and ultrasonographically. Clinical signs included lethargy, anorexia, weight loss, anemia, vomiting, diarrhea, and a palpable mid-abdominal mass. Radiographic findings with alimentary lymphosarcoma (LSA) showed diffuse decreased serosal detail, a mid-abdominal soft-tissue mass, cavernous lesions, and gas-filled bowel loops. Ultrasonographic features included marked stomach or intestinal wall thickening, loss of wall layering, decreased echogenicity, and a hyperechoic central reflection. Hypoechonic infiltration of mesenterial lymph nodes and other abdominal organs were visualized ultrasonographically. Alimentary LSA was diagnosed in thirty-six of the sixty cats. Ultrasonography was helpful in determining the cause of disease in the remaining twenty-four cats. Differential diagnosis included intussusception, foreign bodies, chronic gastroenteritis, granuloma (feline infectious peritonitis - FIP), and other gastrointestinal neoplasms. In ten of the thirty-six cats with alimentary lymphosarcoma, diagnosis was confirmed by ultrasound-guided fine-needle biopsies. Blood and/or saliva ELISA-tests determined feline leukemia virus or antigen in only eleven of the thirty-six cats. Histopathology revealed lymphoid infiltration of the stomach or intestinal wall in twenty-nine of the thirty-six cases. Additionally, the medical records of seventy-one cats with proven alimentary LSA were reviewed. Ultrasonographic findings showed intestinal LSA in sixty-two cats and LSA of the stomach in nine cats. Both studies indicate that ultrasonography is a valuable diagnostic tool for feline alimentary LSA. (author)

  7. Clinical and ultrasonographic features of amoebic liver abscess In a ...

    African Journals Online (AJOL)

    Background: Amoebic Liver abscess is a tropical disease with a wide spectrum of clinical presentation. This study describes its clinical and ultrasonographic features in a teaching hospital setting. Methods: Records of all patients aged 18 years and above with amoebic liver abscess admitted in the medical wards of ...

  8. Fault detection and diagnosis for complex multivariable processes using neural networks

    International Nuclear Information System (INIS)

    Weerasinghe, M.

    1998-06-01

    Development of a reliable fault diagnosis method for large-scale industrial plants is laborious and often difficult to achieve due to the complexity of the targeted systems. The main objective of this thesis is to investigate the application of neural networks to the diagnosis of non-catastrophic faults in an industrial nuclear fuel processing plant. The proposed methods were initially developed by application to a simulated chemical process prior to further validation on real industrial data. The diagnosis of faults at a single operating point is first investigated. Statistical data conditioning methods of data scaling and principal component analysis are investigated to facilitate fault classification and reduce the complexity of neural networks. Successful fault diagnosis was achieved with significantly smaller networks than using all process variables as network inputs. Industrial processes often manufacture at various operating points, but demonstrated applications of neural networks for fault diagnosis usually only consider a single (primary) operating point. Developing a standard neural network scheme for fault diagnosis at all operating points would be usually impractical due to the unavailability of suitable training data for less frequently used (secondary) operating points. To overcome this problem, the application of a single neural network for the diagnosis of faults operating at different points is investigated. The data conditioning followed the same techniques as used for the fault diagnosis of a single operating point. The results showed that a single neural network could be successfully used to diagnose faults at operating points other than that it is trained for, and the data conditioning significantly improved the classification. Artificial neural networks have been shown to be an effective tool for process fault diagnosis. However, a main criticism is that details of the procedures taken to reach the fault diagnosis decisions are embedded in

  9. Clinical, ultrasonographic, and laboratory findings in 12 llamas and 12 alpacas with malignant round cell tumors

    Science.gov (United States)

    Martin, Jeanne M.; Valentine, Beth A.; Cebra, Christopher K.

    2010-01-01

    Clinical signs, duration of illness, clinicopathologic findings, and ultrasonographic findings were evaluated in 12 llamas and 12 alpacas with malignant round cell tumors (MRCT). All but 1 animal died or was euthanized. Common clinical findings were anorexia, recumbency or weakness, and weight loss or poor growth. Peripheral lymphadenomegaly occurred in only 7 animals and was detected more often at necropsy than during physical examination. Common clinicopathologic abnormalities were hypoalbuminemia, acidosis, azotemia, anemia, hyperglycemia, and neutrophilia. Ultrasonography detected tumors in 4/6 animals. Cytologic evaluation of fluid or tissue aspirates or histopathology of biopsy tissue was diagnostic in 5/6 cases. A clinical course of 2 wk or less prior to death or euthanasia was more common in animals ≤ 2 y of age (9/11) than in older animals (6/13). Regular examination of camelids to include clinical pathology and evaluation of peripheral lymph nodes may result in early detection of MCRT. PMID:21358931

  10. Ship Detection in Gaofen-3 SAR Images Based on Sea Clutter Distribution Analysis and Deep Convolutional Neural Network.

    Science.gov (United States)

    An, Quanzhi; Pan, Zongxu; You, Hongjian

    2018-01-24

    Target detection is one of the important applications in the field of remote sensing. The Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) satellite launched by China is a powerful tool for maritime monitoring. This work aims at detecting ships in GF-3 SAR images using a new land masking strategy, the appropriate model for sea clutter and a neural network as the discrimination scheme. Firstly, the fully convolutional network (FCN) is applied to separate the sea from the land. Then, by analyzing the sea clutter distribution in GF-3 SAR images, we choose the probability distribution model of Constant False Alarm Rate (CFAR) detector from K-distribution, Gamma distribution and Rayleigh distribution based on a tradeoff between the sea clutter modeling accuracy and the computational complexity. Furthermore, in order to better implement CFAR detection, we also use truncated statistic (TS) as a preprocessing scheme and iterative censoring scheme (ICS) for boosting the performance of detector. Finally, we employ a neural network to re-examine the results as the discrimination stage. Experiment results on three GF-3 SAR images verify the effectiveness and efficiency of this approach.

  11. Damage detection in carbon composite material typical of wind turbine blades using auto-associative neural networks

    Science.gov (United States)

    Dervilis, N.; Barthorpe, R. J.; Antoniadou, I.; Staszewski, W. J.; Worden, K.

    2012-04-01

    The structure of a wind turbine blade plays a vital role in the mechanical and structural operation of the turbine. As new generations of offshore wind turbines are trying to achieve a leading role in the energy market, key challenges such as a reliable Structural Health Monitoring (SHM) of the blades is significant for the economic and structural efficiency of the wind energy. Fault diagnosis of wind turbine blades is a "grand challenge" due to their composite nature, weight and length. The damage detection procedure involves additional difficulties focused on aerodynamic loads, environmental conditions and gravitational loads. It will be shown that vibration dynamic response data combined with AANNs is a robust and powerful tool, offering on-line and real time damage prediction. In this study the features used for SHM are Frequency Response Functions (FRFs) acquired via experimental methods based on an LMS system by which identification of mode shapes and natural frequencies is accomplished. The methods used are statistical outlier analysis which allows a diagnosis of deviation from normality and an Auto-Associative Neural Network (AANN). Both of these techniques are trained by adopting the FRF data for normal and damage condition. The AANN is a method which has not yet been widely used in the condition monitoring of composite materials of blades. This paper is trying to introduce a new scheme for damage detection, localisation and severity assessment by adopting simple measurements such as FRFs and exploiting multilayer neural networks and outlier novelty detection.

  12. Aircraft Aerodynamic Parameter Detection Using Micro Hot-Film Flow Sensor Array and BP Neural Network Identification

    Directory of Open Access Journals (Sweden)

    Ruiyi Que

    2012-08-01

    Full Text Available Air speed, angle of sideslip and angle of attack are fundamental aerodynamic parameters for controlling most aircraft. For small aircraft for which conventional detecting devices are too bulky and heavy to be utilized, a novel and practical methodology by which the aerodynamic parameters are inferred using a micro hot-film flow sensor array mounted on the surface of the wing is proposed. A back-propagation neural network is used to model the coupling relationship between readings of the sensor array and aerodynamic parameters. Two different sensor arrangements are tested in wind tunnel experiments and dependence of the system performance on the sensor arrangement is analyzed.

  13. Detection of different states of sleep in the rodents by the means of artificial neural networks

    Science.gov (United States)

    Musatov, Viacheslav; Dykin, Viacheslav; Pitsik, Elena; Pisarchik, Alexander

    2018-04-01

    This paper considers the possibility of classification of electroencephalogram (EEG) and electromyogram (EMG) signals corresponding to different phases of sleep and wakefulness of mice by the means of artificial neural networks. A feed-forward artificial neural network based on multilayer perceptron was created and trained on the data of one of the rodents. The trained network was used to read and classify the EEG and EMG data corresponding to different phases of sleep and wakefulness of the same mouse and other mouse. The results show a good recognition quality of all phases for the rodent on which the training was conducted (80-99%) and acceptable recognition quality for the data collected from the same mouse after a stroke.

  14. Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

    Science.gov (United States)

    Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

    2017-03-01

    Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

  15. Use of artificial neural networks in chemical addiction stages detection of adolescents

    OpenAIRE

    Bardadymov, Vasiliy Anatolevich

    2012-01-01

    Today there is no unified approach to description of the stages of addiction and evolution of adolescent addiction formation. In this paper we consider two main points. At first we describe the different approaches to the selection stages of addictive behavior. The second point is the description of using the method of constructing artificial neural networks to determine the formation of chemical addiction. Also this article describes the theoretical approaches to the evolutio...

  16. Detecting and diagnosing SSME faults using an autoassociative neural network topology

    Science.gov (United States)

    Ali, M.; Dietz, W. E.; Kiech, E. L.

    1989-01-01

    An effort is underway at the University of Tennessee Space Institute to develop diagnostic expert system methodologies based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. Neural networks are being investigated as a means of storing and retrieving fault scenarios. Neural networks offer several powerful features in fault diagnosis, including (1) general pattern matching capabilities, (2) resistance to noisy input data, (3) the ability to be trained by example, and (4) the potential for implementation on parallel computer architectures. This paper presents (1) an autoassociative neural network topology, i.e. the network input and output is identical when properly trained, and hence learning is unsupervised; (2) the training regimen used; and (3) the response of the system to inputs representing both previously observed and unkown fault scenarios. The effects of noise on the integrity of the diagnosis are also evaluated.

  17. Convolutional neural networks for the detection of diseased hearts using CT images and left atrium patches

    Science.gov (United States)

    Dormer, James D.; Halicek, Martin; Ma, Ling; Reilly, Carolyn M.; Schreibmann, Eduard; Fei, Baowei

    2018-02-01

    Cardiovascular disease is a leading cause of death in the United States. The identification of cardiac diseases on conventional three-dimensional (3D) CT can have many clinical applications. An automated method that can distinguish between healthy and diseased hearts could improve diagnostic speed and accuracy when the only modality available is conventional 3D CT. In this work, we proposed and implemented convolutional neural networks (CNNs) to identify diseased hears on CT images. Six patients with healthy hearts and six with previous cardiovascular disease events received chest CT. After the left atrium for each heart was segmented, 2D and 3D patches were created. A subset of the patches were then used to train separate convolutional neural networks using leave-one-out cross-validation of patient pairs. The results of the two neural networks were compared, with 3D patches producing the higher testing accuracy. The full list of 3D patches from the left atrium was then classified using the optimal 3D CNN model, and the receiver operating curves (ROCs) were produced. The final average area under the curve (AUC) from the ROC curves was 0.840 +/- 0.065 and the average accuracy was 78.9% +/- 5.9%. This demonstrates that the CNN-based method is capable of distinguishing healthy hearts from those with previous cardiovascular disease.

  18. Recognition and detection of seismic phases by artificial neural network detector; Jinko neural network ni yoru jishinha no ninshiki to kenshutsu

    Energy Technology Data Exchange (ETDEWEB)

    Yamazaki, K; Wang, W [Tokyo Gakugei University, Tokyo (Japan)

    1997-05-27

    Initial parts of P-waves, medium or high in intensity, are detected using an artificial neural network (ANN). The ANN is the generic name given to information processing systems of the non-Neumann type configured to human brain in point of information processing function, and is packaged into computers in the form of software capable of parallel processing, self-organizing, learning, etc. In this paper, a hierarchical ANN-assisted seismic motion recognition system is constructed on the basis of an error reverse propagation algorithm. It is reported here, with a remark that this study wants much more data from tests for the evaluation of the quality of the recognition, that P-wave recognition has been achieved. When this technique is applied to the S-wave, much more real-time information will become available. For the improvement of the system, a number of problems have to be solved, including the establishment of automatic refurbishment through adaptation-and-learning and configuration that incorporates frequency-related matters. It is found that this system is effective in seismic wave phase recognition but that it is not suitable for precision measurement. 7 refs., 4 figs.

  19. Aspects of Ultrasonographic Diagnostics of Pregnancy in Bitches depending on the first mating

    Directory of Open Access Journals (Sweden)

    Aissi

    Full Text Available The aim of the present study was to follow up the potential of routine ultrasonographic diagnostics of pregnancy in bitches depending on the first mating. The experiments were performed on 32 bitches. Pregnancy was detected using transabdominal ultrasonography with Siemens sonoline adara equipment and a covex 5 MHz probe. Subsequent serial examinations were made to sonographically characterize normal canine prenatal development based about the first mating. An enlarged uterus, gestational sacs and fetal poles were recognized as the features of early bitchs pregnancy and were first seen at 16 and 21 days, respectively. Cardiac activity was detected earliest on gestational day 22 and recognizable canine fetal morphology appeared at day 28. Generalized fetal movements were first noted at day 28. [Veterinary World 2008; 1(10.000: 293-295

  20. Detection of Coal Fires: A Case Study Conducted on Indian Coal Seams Using Neural Network and Particle Swarm Optimization

    Science.gov (United States)

    Singh, B. B.

    2016-12-01

    India produces majority of its electricity from coal but a huge quantity of coal burns every day due to coal fires and also poses a threat to the environment as severe pollutants. In the present study we had demonstrated the usage of Neural Network based approach with an integrated Particle Swarm Optimization (PSO) inversion technique. The Self Potential (SP) data set is used for the early detection of coal fires. The study was conducted over the East Basuria colliery, Jharia Coal Field, Jharkhand, India. The causative source was modelled as an inclined sheet like anomaly and the synthetic data was generated. Neural Network scheme consists of an input layer, hidden layers and an output layer. The input layer corresponds to the SP data and the output layer is the estimated depth of the coal fire. A synthetic dataset was modelled with some of the known parameters such as depth, conductivity, inclination angle, half width etc. associated with causative body and gives a very low misfit error of 0.0032%. Therefore, the method was found accurate in predicting the depth of the source body. The technique was applied to the real data set and the model was trained until a very good correlation of determination `R2' value of 0.98 is obtained. The depth of the source body was found to be 12.34m with a misfit error percentage of 0.242%. The inversion results were compared with the lithologs obtained from a nearby well which corresponds to the L3 coal seam. The depth of the coal fire had exactly matched with the half width of the anomaly which suggests that the fire is widely spread. The inclination angle of the anomaly was 135.510 which resembles the development of the geometrically complex fracture planes. These fractures may be developed due to anisotropic weakness of the ground which acts as passage for the air. As a result coal fires spreads along these fracture planes. The results obtained from the Neural Network was compared with PSO inversion results and were found in

  1. A new method for brain tumor detection using the Bhattacharyya similarity coefficient, color conversions and neural network

    Directory of Open Access Journals (Sweden)

    Bahman Mansori

    2015-10-01

    Full Text Available Background: Magnetic resonance imaging (MRI is widely applied for examination and diagnosis of brain tumors based on its advantages of high resolution in detecting the soft tissues and especially of its harmless radiation damages to human bodies. The goal of the processing of images is automatic segmentation of brain edema and tumors, in different dimensions of the magnetic resonance images. Methods: The proposed method is based on the unsupervised method which discovers the tumor region, if there is any, by analyzing the similarities between two hemispheres and computes the image size of the goal function based on Bhattacharyya coefficient which is used in the next stage to detect the tumor region or some part of it. In this stage, for reducing the color variation, the gray brain image is segmented, then it is turned to gray again. The self-organizing map (SOM neural network is used the segmented brain image is colored and finally the tumor is detected by matching the detected region and the colored image. This method is proposed to analyze MRI images for discovering brain tumors, and done in Bu Ali Sina University, Hamedan, Iran, in 2014. Results: The results for 30 randomly selected images from data bank of MRI center in Hamedan was compared with manually segmentation of experts. The results showed that, our proposed method had the accuracy of more than 94% at Jaccard similarity index (JSI, 97% at Dice similarity score (DSS, and 98% and 99% at two measures of specificity and sensitivity. Conclusion: The experimental results showed that it was satisfactory and can be used in automatic separation of tumor from normal brain tissues and therefore it can be used in practical applications. The results showed that the use of SOM neural network to classify useful magnetic resonance imaging of the brain and demonstrated a good performance.

  2. Automated Detection of Craters in Martian Satellite Imagery Using Convolutional Neural Networks

    Science.gov (United States)

    Norman, C. J.; Paxman, J.; Benedix, G. K.; Tan, T.; Bland, P. A.; Towner, M.

    2018-04-01

    Crater counting is used in determining surface age of planets. We propose improvements to martian Crater Detection Algorithms by implementing an end-to-end detection approach with the possibility of scaling the algorithm planet-wide.

  3. Segmentation of retinal blood vessels using artificial neural networks for early detection of diabetic retinopathy

    Science.gov (United States)

    Mann, Kulwinder S.; Kaur, Sukhpreet

    2017-06-01

    There are various eye diseases in the patients suffering from the diabetes which includes Diabetic Retinopathy, Glaucoma, Hypertension etc. These all are the most common sight threatening eye diseases due to the changes in the blood vessel structure. The proposed method using supervised methods concluded that the segmentation of the retinal blood vessels can be performed accurately using neural networks training. It uses features which include Gray level features; Moment Invariant based features, Gabor filtering, Intensity feature, Vesselness feature for feature vector computation. Then the feature vector is calculated using only the prominent features.

  4. Use of artificial neural networks in drug and explosive detection through tomographic images with thermal neutrons

    International Nuclear Information System (INIS)

    Ferreira, Francisco J.O.; Crispim, Verginia R.; Silva, Ademir X.

    2009-01-01

    The artificial neural network technique was used to identify drugs and plastic explosives, from a tomography composed by a set of six neutrongraphic projections obtained in real time. Bidimensional tomographic images of samples of drugs, explosives and other materials, when digitally processed, yield the characteristic spectra of each type of material. The information contained in those spectra was then used for ANN training, the best images being obtained when the multilayer perceptron model, the back-propagation training algorithm and the Cross-validation interruption criterion were used. ANN showed to be useful in forecasting presence of drugs and explosives hitting a rate of success above 97 %. (author)

  5. Detection of anti-streptococcal, antienolase, and anti-neural antibodies in subjects with early-onset psychiatric disorders.

    Science.gov (United States)

    Nicolini, Humberto; López, Yaumara; Genis-Mendoza, Alma D; Manrique, Viana; Lopez-Canovas, Lilia; Niubo, Esperanza; Hernández, Lázaro; Bobes, María A; Riverón, Ana M; López-Casamichana, Mavil; Flores, Julio; Lanzagorta, Nuria; De la Fuente-Sandoval, Camilo; Santana, Daniel

    2015-01-01

    Infection with group A Streptococcus (StrepA) can cause post-infectious sequelae, including a spectrum of childhood-onset obsessive-compulsive (OCD) and tic disorders with autoimmune origin (PANDAS, Pediatric Autoimmune Neuropsychiatric Disorders Associated with Streptococcal Infections). Until now, no single immunological test has been designed that unequivocally diagnoses these disorders. In this study, we assessed the detection of serum antibodies against human brain enolase (AE), neural tissue (AN) and Streptococcus (AS) as a laboratory tool for the diagnosis of early-onset psychiatric disorders. Serum antibodies against human brain enolase, total brain proteins, and total proteins from StrepA were detected by ELISA in 37 patients with a presumptive diagnosis of PANDAS and in 12 healthy subjects from Mexico and Cuba. The antibody titers against human brain enolase (AE) and Streptococcal proteins (AS) were higher in patients than in control subjects (t-student, tAE=-2.17, P=0.035; tAS=-2.68, P=0.01, n=12 and 37/group, df=47, significance level 0.05), while the neural antibody titers did not differ between the two groups (P(t)=0.05). The number of subjects (titers> meancontrol + CI95) with simultaneous seropositivity to all three antibodies was higher in the patient group (51.4%) than in the control group (8.3%) group (X2=5.27, P=0.022, df=1, n=49). The simultaneous detection of all three of these antibodies could provide valuable information for the etiologic diagnosis of individuals with early-onset obsessive-compulsive disorders associated with streptococcal infection and, consequently, for prescribing suitable therapy.

  6. LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

    Directory of Open Access Journals (Sweden)

    Ziyang He

    2018-04-01

    Full Text Available By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

  7. LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

    Science.gov (United States)

    He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

    2018-04-17

    By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

  8. Anomaly Detection for Resilient Control Systems Using Fuzzy-Neural Data Fusion Engine

    Energy Technology Data Exchange (ETDEWEB)

    Ondrej Linda; Milos Manic; Timothy R. McJunkin

    2011-08-01

    Resilient control systems in critical infrastructures require increased cyber-security and state-awareness. One of the necessary conditions for achieving the desired high level of resiliency is timely reporting and understanding of the status and behavioral trends of the control system. This paper describes the design and development of a neural-network based data-fusion system for increased state-awareness of resilient control systems. The proposed system consists of a dedicated data-fusion engine for each component of the control system. Each data-fusion engine implements three-layered alarm system consisting of: (1) conventional threshold-based alarms, (2) anomalous behavior detector using self-organizing maps, and (3) prediction error based alarms using neural network based signal forecasting. The proposed system was integrated with a model of the Idaho National Laboratory Hytest facility, which is a testing facility for hybrid energy systems. Experimental results demonstrate that the implemented data fusion system provides timely plant performance monitoring and cyber-state reporting.

  9. An Effective and Novel Neural Network Ensemble for Shift Pattern Detection in Control Charts

    Directory of Open Access Journals (Sweden)

    Mahmoud Barghash

    2015-01-01

    Full Text Available Pattern recognition in control charts is critical to make a balance between discovering faults as early as possible and reducing the number of false alarms. This work is devoted to designing a multistage neural network ensemble that achieves this balance which reduces rework and scrape without reducing productivity. The ensemble under focus is composed of a series of neural network stages and a series of decision points. Initially, this work compared using multidecision points and single-decision point on the performance of the ANN which showed that multidecision points are highly preferable to single-decision points. This work also tested the effect of population percentages on the ANN and used this to optimize the ANN’s performance. Also this work used optimized and nonoptimized ANNs in an ensemble and proved that using nonoptimized ANN may reduce the performance of the ensemble. The ensemble that used only optimized ANNs has improved performance over individual ANNs and three-sigma level rule. In that respect using the designed ensemble can help in reducing the number of false stops and increasing productivity. It also can be used to discover even small shifts in the mean as early as possible.

  10. Electrical stimulus artifact cancellation and neural spike detection on large multi-electrode arrays.

    Science.gov (United States)

    Mena, Gonzalo E; Grosberg, Lauren E; Madugula, Sasidhar; Hottowy, Paweł; Litke, Alan; Cunningham, John; Chichilnisky, E J; Paninski, Liam

    2017-11-01

    Simultaneous electrical stimulation and recording using multi-electrode arrays can provide a valuable technique for studying circuit connectivity and engineering neural interfaces. However, interpreting these measurements is challenging because the spike sorting process (identifying and segregating action potentials arising from different neurons) is greatly complicated by electrical stimulation artifacts across the array, which can exhibit complex and nonlinear waveforms, and overlap temporarily with evoked spikes. Here we develop a scalable algorithm based on a structured Gaussian Process model to estimate the artifact and identify evoked spikes. The effectiveness of our methods is demonstrated in both real and simulated 512-electrode recordings in the peripheral primate retina with single-electrode and several types of multi-electrode stimulation. We establish small error rates in the identification of evoked spikes, with a computational complexity that is compatible with real-time data analysis. This technology may be helpful in the design of future high-resolution sensory prostheses based on tailored stimulation (e.g., retinal prostheses), and for closed-loop neural stimulation at a much larger scale than currently possible.

  11. Ultrasonographic evaluation of normal scapula in the horse

    Directory of Open Access Journals (Sweden)

    M. S. Ahrari-Khafi

    2018-03-01

    Full Text Available Scapular fracture is rare in horse, but if happen can cause severe lameness. Due to overlapping of the contralateral scapula and thorax on the scapula, usually radiography is not helpful in its evaluation except in small amount of distal part. This study was intended to document the normal ultrasono-graphic appearance of the equine scapula. Right forelimbs of six horses were used. To facilitate image understanding, a zoning system was developed. Ultrasonography was performed using a 5–11 MHz linear array transducer. Ultrasonographic anatomy of scapula in different parts and planes was imaged and documented. This diagnostic imaging technique revealed a high potential in evaluating scapular surface and possible regional injuries. Ultrasonography could be considered an important addition to radiography in diagnosing fractures in the scapular region.

  12. Ultrasonographic abdominal anatomy of healthy captive caracals (Caracal caracal).

    Science.gov (United States)

    Makungu, Modesta; du Plessis, Wencke M; Barrows, Michelle; Koeppel, Katja N; Groenewald, Hermanus B

    2012-09-01

    Abdominal ultrasonography was performed in six adult captive caracals (Caracal caracal) to describe the normal abdominal ultrasonographic anatomy. Consistently, the splenic parenchyma was hyperechoic to the liver and kidneys. The relative echogenicity of the right kidney's cortex was inconsistent to the liver. The gall bladder was prominent in five animals and surrounded by a clearly visualized thin, smooth, regular echogenic wall. The wall thickness of the duodenum measured significantly greater compared with that of the jejunum and colon. The duodenum had a significantly thicker mucosal layer compared with that of the stomach. Such knowledge of the normal abdominal ultrasonographic anatomy of individual species is important for accurate diagnosis and interpretation of routine health examinations.

  13. Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks.

    Science.gov (United States)

    López-Linares, Karen; Aranjuelo, Nerea; Kabongo, Luis; Maclair, Gregory; Lete, Nerea; Ceresa, Mario; García-Familiar, Ainhoa; Macía, Iván; González Ballester, Miguel A

    2018-05-01

    Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases. Copyright © 2018 Elsevier B.V. All rights reserved.

  14. Automated detection of masses on whole breast volume ultrasound scanner: false positive reduction using deep convolutional neural network

    Science.gov (United States)

    Hiramatsu, Yuya; Muramatsu, Chisako; Kobayashi, Hironobu; Hara, Takeshi; Fujita, Hiroshi

    2017-03-01

    Breast cancer screening with mammography and ultrasonography is expected to improve sensitivity compared with mammography alone, especially for women with dense breast. An automated breast volume scanner (ABVS) provides the operator-independent whole breast data which facilitate double reading and comparison with past exams, contralateral breast, and multimodality images. However, large volumetric data in screening practice increase radiologists' workload. Therefore, our goal is to develop a computer-aided detection scheme of breast masses in ABVS data for assisting radiologists' diagnosis and comparison with mammographic findings. In this study, false positive (FP) reduction scheme using deep convolutional neural network (DCNN) was investigated. For training DCNN, true positive and FP samples were obtained from the result of our initial mass detection scheme using the vector convergence filter. Regions of interest including the detected regions were extracted from the multiplanar reconstraction slices. We investigated methods to select effective FP samples for training the DCNN. Based on the free response receiver operating characteristic analysis, simple random sampling from the entire candidates was most effective in this study. Using DCNN, the number of FPs could be reduced by 60%, while retaining 90% of true masses. The result indicates the potential usefulness of DCNN for FP reduction in automated mass detection on ABVS images.

  15. Symptomatic and asymptomatic interphalageal osteoarthritis: An ultrasonographic study.

    Science.gov (United States)

    Usón, Jacqueline; Fernández-Espartero, Cruz; Villaverde, Virginia; Condés, Emilia; Godo, Javier; Martínez-Blasco, Maria Jesus; Miguélez, Roberto

    2014-01-01

    To date few studies have examined whether ultrasonography can depict morphologic differences in painful and painless osteoarthritis (OA). This study describes and compares the clinical, radiographic and ultrasonographic findings of patients with both painful and painless proximal interphalgeal (PIP) and/or distal interphalgeal (DIP) OA. Patients with PIP and/or DIP OA (ACR criteria) were prospectively recruited. The clinical rheumatologist chose up to 3 painful joints and up to 3 painless symmetric joints in each patient to define 2 cohorts of OA: symptomatic (SG) and asymptomatic (ASG). A conventional postero-anterior hand x ray was performed and read by one rheumatologist following the OARSI atlas, blinded to clinical and sonographic data. Ultrasound (US) was performed by an experienced rheumatologist, blinded to both clinical and radiographic data in joints previously selected by the clinical rheumatologist. US-pathology was assessed as present or absent as defined in previous reports: osteophytes, joint space narrowing, synovitis, intra-articular power doppler signal, intra-articular bony erosion, and visualization of cartilage. Radiographic and ultrasonographic intrareader reliability test was performed. A total of 50 joints in the SG and ASG were included from 20 right handed women aged 61.85 (46-73) years with PIP and DIP OA diagnosed 6.8 (1-17) years ago. 70% SG joints and ASG were right and left sided respectively. The SG showed significantly more osteophytes, synovitis and non-visualization of joint cartilage. Intrareader radiographic and ultrasonographic agreement was excellent. This study demonstrates that painful PIP and/or DIP OA have more ultrasonographic structural changes and synovitis. Copyright © 2013 Elsevier España, S.L.U. All rights reserved.

  16. Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks.

    Science.gov (United States)

    Bandeira Diniz, João Otávio; Bandeira Diniz, Pedro Henrique; Azevedo Valente, Thales Levi; Corrêa Silva, Aristófanes; de Paiva, Anselmo Cardoso; Gattass, Marcelo

    2018-03-01

    The processing of medical image is an important tool to assist in minimizing the degree of uncertainty of the specialist, while providing specialists with an additional source of detect and diagnosis information. Breast cancer is the most common type of cancer that affects the female population around the world. It is also the most deadly type of cancer among women. It is the second most common type of cancer among all others. The most common examination to diagnose breast cancer early is mammography. In the last decades, computational techniques have been developed with the purpose of automatically detecting structures that maybe associated with tumors in mammography examination. This work presents a computational methodology to automatically detection of mass regions in mammography by using a convolutional neural network. The materials used in this work is the DDSM database. The method proposed consists of two phases: training phase and test phase. The training phase has 2 main steps: (1) create a model to classify breast tissue into dense and non-dense (2) create a model to classify regions of breast into mass and non-mass. The test phase has 7 step: (1) preprocessing; (2) registration; (3) segmentation; (4) first reduction of false positives; (5) preprocessing of regions segmented; (6) density tissue classification (7) second reduction of false positives where regions will be classified into mass and non-mass. The proposed method achieved 95.6% of accuracy in classify non-dense breasts tissue and 97,72% accuracy in classify dense breasts. To detect regions of mass in non-dense breast, the method achieved a sensitivity value of 91.5%, and specificity value of 90.7%, with 91% accuracy. To detect regions in dense breasts, our method achieved 90.4% of sensitivity and 96.4% of specificity, with accuracy of 94.8%. According to the results achieved by CNN, we demonstrate the feasibility of using convolutional neural networks on medical image processing techniques for

  17. Ultrasonographic anatomy of reproductive female leopard geckos (Eublepharis macularius).

    Science.gov (United States)

    Cojean, Ophélie; Vergneau-Grosset, Claire; Masseau, Isabelle

    2018-02-19

    Captive leopard geckos (Eublepharis macularius) often present to the exotic clinic for gastrointestinal impactions, follicular stasis, or dystocia. To our knowledge, normal ultrasonographic anatomy of these lizards has not been described. The objectives of this prospective, anatomic, analytical study were to develop ultrasound techniques for this species and to describe the normal sonographic anatomy of the head, coelomic cavity, and tail. Eleven, healthy, female leopard geckos were included. A linear array 13-18 MHz transducer was used. Geckos were sedated and restrained in dorsal recumbency for coelomic structure examination and in ventral recumbency for head and tail examinations. Sagittal and transverse images were acquired and authors recorded qualitative and quantitative ultrasonographic characteristics of anatomic structures. The ventral surface of the lungs, liver, gallbladder, caudal vena cava, portal vein, ventral abdominal vein, aorta, ovarian follicles, fat bodies, tail, and brain were visualized in 10 of 11 individuals. In one individual, molt precluded ultrasonographic examination. The heart, kidneys, urinary bladder, spleen, and pancreas were not visualized. The digestive tract was observed in 10 individuals but was too small to be measured. Findings from the current study could be used as a reference for future studies of leopard geckos. © 2018 American College of Veterinary Radiology.

  18. The ultrasonographic findings of acute pelvic inflammatory disease

    International Nuclear Information System (INIS)

    Choi, Yeon Nam; Park, Jai Soung; Lee, Hae Kyung; Chung, Moo Chan; Lee, Beong Ho; Kim, Ki Jung

    1987-01-01

    Although ultrasonographic findings of female pelvic mass are frequently reported, those of acute PID are not well established. But differentiation of fluid collection and mass lesion of PID is exactly made by ultrasonography. We analysed the ultrasonographic findings in 26 cases of acute PID having satisfactory operative or histological proofs, examined at Soonchunhyang University Hospital from Oct. 1985 to Feb. 1987. The results were as follows: 1. The age was ranged from 17 years to 53 years of age and the majority was between 21 years and 50 years of age. 2. Ultrasonographic findings are classified to fluid collection in cul de sac 17, tuboovarian abscess, 7 pyosalpix 2, endometritis 1 and normal 2 cases. 3. In cases of pelvic mass formation, their ecnogenecity were cystic form in 6 cases (22%), mixed form in 19 cases (71%), solid form in 2 cases (7%), and shapes were mainly ovoid with irregular, ill-defined margin. The location of mass is unilateral in 17 cases (63%) bilateral in 10 cases (37%)

  19. Clinical and ultrasonographic implications of uterine leiomyomatosis in pregnancy.

    Science.gov (United States)

    Piazze Garnica, J; Gallo, G; Marzano, P F; Vozzi, G; Mazzocco, M; Anceschi, M M; Rolfini, G

    1995-01-01

    To study the complications related to leiomyomatosis in pregnancy by clinical and ultrasonographic assessment. A retrospective study. All pregnancies admitted to the 2nd Institute of Gynecology and Obstetrics, Policlinico Umberto I, in the period between January 1992 to December 1993 were surveyed. Gestational age at the time of ultrasonographic neoplasm diagnosis was 25.1 +/- 13.4 weeks, 'we found no correlation between maternal age or parity affecting pregnancy outcome, Leiomyomatosis complicated pregnancy rate was 1.68%. Myomatosis was diagnosed clinically in 25 of 67 cases (37.3%). Regarding the location of the neoplasm, 59% was located in the corpus-uteri, 21% was considered a diffuse neoplasm and the 14% was located in the fundus. Threatened abortion was the most frequent complication (20%), abortion was the second (16.4%). We observed an increased abortion threat rate (p pregnancies complicated by myomatosis, and the indication for surgery was given either primarily or exclusively by the presence of myomatous formation in 19 cases (50%). Our study suggests that location of the leiomyoma in relation to the placenta is a higher risk factor than its size, and that there is a higher risk for threats of abortion and abortion rates in pregnancies complicated by leiomyomatosis. We recommend that every pregnant woman with a suspected myoma should be ultrasonographically scanned.

  20. An ultrasonographic study of experimental hydronephrosis in rabbit

    International Nuclear Information System (INIS)

    Choi, Byung Ihn; Yeon, Kyung Mo; Han, Man Chung; Kim, Chu Wan

    1984-01-01

    Ultrasonographic of rabbit kidney was enformed after induction of simple and infected hydronephrosis to evaluate the sequential sonographic changes in 27 rabbits. Simple hydronephrosis was induced by ligation of the distal ureter and infected hydronephrosis by ligation of the distal ureter and ureteral inoculation of Escherichia coli. Ultrasonography was performed daily during the first week and weekly during the following 5 weeks after induction of simple and infected hydronephrosis. 1. In simple hydronephrosis, the earliest abnormal ultrasonographic finding was splitting of central renal echo complex, which appeared within 1 day after ureteral ligation in all cases. 2. In simple hydronephrosis, complete loss of central renal echo complex and cystic dilatation of pelvis were seen with in 5 days after ureteral ligation in all cases. 3. In infected hydronephrosis, the earliest abnormal ultrasonographic finding was appearance of internal echoes in dependent portion of the pelvis, which appeared within 4 days after inoculation in all cases. 4. In infected hydronephrosis, degree of internal echoes within the pelvis increased progressively with lapse of time and the entire pelvis was filled with internal echoes within 2 weeks after inoculation in all cases. 5. In infected hydronephrosis, echogenecity of internal echoes within the pelvis was similar to that of renal parenchyma in the first week after inoculation, however was weaker than that of renal parenchyma 2 weeks after inoculation in all cases

  1. Ultrasonographic characteristics of the abdominal esophagus and cardia in dogs.

    Science.gov (United States)

    Gory, Guillaume; Rault, Delphine N; Gatel, Laure; Dally, Claire; Belli, Patrick; Couturier, Laurent; Cauvin, Eddy

    2014-01-01

    Differential diagnoses for regurgitation and vomiting in dogs include diseases of the gastroesophageal junction. The purpose of this cross-sectional study was to describe ultrasonographic characteristics of the abdominal esophagus and gastric cardia in normal dogs and dogs with clinical disease involving this region. A total of 126 dogs with no clinical signs of gastrointestinal disease and six dogs with clinical diseases involving the gastroesophageal junction were included. For seven euthanized dogs, ultrasonographic features were also compared with gross pathology and histopathology. Cardial and abdominal esophageal wall thicknesses were measured ultrasonographically for all normal dogs and effects of weight, sex, age, and stomach filling were tested. Five layers could be identified in normal esophageal and cardial walls. The inner esophageal layer was echogenic, corresponding to the cornified mucosa and glandular portion of the submucosa. The cardia was characterized by a thick muscularis, and a transitional zone between echogenic esophageal and hypoechoic gastric mucosal layers. Mean (±SD) cardial wall thicknesses for normal dogs were 7.6 mm (±1.6), 9.7 mm (±1.8), 10.8 mm (±1.6), 13.3 mm (±2.5) for dogs in the dog weight group. Ultrasonography assisted diagnosis in all six clinically affected dogs. Findings supported the use of transabdominal ultrasonography as a diagnostic test for dogs with suspected gastroesophageal disease. © 2014 American College of Veterinary Radiology.

  2. Ultrasonographic findings of septic arthritis and osteomyelitis in neonatal hip

    International Nuclear Information System (INIS)

    Lee, Seung Hoon; Jung, Kun Sik; Koh, Jung Kon; Im, Myung Ah; Kwon, Kwi Ryun; Kim, Sung Soo

    2000-01-01

    To evaluate ultrasonographic findings of neonatal patients who confirmed and treated as hip joint septic arthritis and osteomyelitis. We retrospectively examined clinical feature and radiologic findings of 7 neonatal patients ranging from 8 to 28 days of age who were examined from January 1966 to December 1998 at nursery and were confirmed and treated on the diagnosis of septic arthritis and osteomyelitis. Clinical features of the patients were comparatively analyzed with radiologic findings including plain radiographs, ultrasonography, bone scan and MRI. We emphasized importance of ultrasonographic findings of these patients. Ultrasonography was performed first of all in all cases after the symptom onset. Other examinations were performed on the same day or a few days later after ultrasonography. Ultrasonography revealed abnormal finding in 85.7% (6/7) of all cases. Plain radiographs revealed abnormal findings in 28.6% (2/7). Bone scan revealed decreased uptake in 66.7%(2/3). MRI revealed abnormal signal intensity in 100%(3/3). Ultrasonographic findings of the patients were deep soft swelling in 85.7% (6/7) of all cases, periosteal elevation in 57.1% (4/7), synovial thickening in 42.8% (3/7), synovial effusion in 42.8%(3/7), echogenic debris or clot in 28.5% (2/7), cortical erosion in 28.5% (2/7), and subperiosteal abscess in 14.2% (1/7). Ultrasonography is a useful modality to diagnose septic arthritis and osteomyelitis in neonatal hip.

  3. Usefulness of ultrasonographic examination of diagnosis of muscle hernia

    International Nuclear Information System (INIS)

    Choi, Jin Soo; Lee, Sung Moon

    2003-01-01

    To evaluate the usefulness of ultrasonography in diagnosis of muscle hernia. Ultrasonographic findings of seven patients with muscle hernia were retrospectively reviewed. The subjects consisted of 6 males and 1 female, age ranged from 17 to 66 years (mean=45 years). Ultrasonographic examination was performed using a high-frequency (7-15 MHz) linear probe during rest and stress states of the affected muscle, and both tranverse and longitudinal views were obtained. Six muscle herniations were located in the lower extremity in six cases while only one muscle herniation, in the upper extremity. Four cases showed a focal defect of the fascia with a localized bulging out of the muscle substance through the defect. Herniated muscle in stress state was larger and harder than in rest state. In 3 cases, defect of the fascia was not noted on ultrasonography. However, the affected muscle showed an abnormal contraction with a focal bulging out appearance during stress state. Ultrasonographically, the herniated muscle substance was less echogenic than the normal muscle without any evidence of muscle tear or associated mass in all cases. Ultrasonography is a simple and useful dynamic study of muscle hernia in diagnosis and differentiation of muscle hernia.

  4. Land Cover Change Detection using Neural Network and Grid Cells Techniques

    Science.gov (United States)

    Bagan, H.; Li, Z.; Tangud, T.; Yamagata, Y.

    2017-12-01

    In recent years, many advanced neural network methods have been applied in land cover classification, each of which has both strengths and limitations. In which, the self-organizing map (SOM) neural network method have been used to solve remote sensing data classification problems and have shown potential for efficient classification of remote sensing data. In SOM, both the distribution and the topology of features of the input layer are identified by using an unsupervised, competitive, neighborhood learning method. The high-dimensional data are then projected onto a low-dimensional map (competitive layer), usually as a two-dimensional map. The neurons (nodes) in the competitive layer are arranged by topological order in the input space. Spatio-temporal analyses of land cover change based on grid cells have demonstrated that gridded data are useful for obtaining spatial and temporal information about areas that are smaller than municipal scale and are uniform in size. Analysis based on grid cells has many advantages: grid cells all have the same size allowing for easy comparison; grids integrate easily with other scientific data; grids are stable over time and thus facilitate the modelling and analysis of very large multivariate spatial data sets. This study chose time-series MODIS and Landsat images as data sources, applied SOM neural network method to identify the land utilization in Inner Mongolia Autonomous Region of China. Then the results were integrated into grid cell to get the dynamic change maps. Land cover change using MODIS data in Inner Mongolia showed that urban area increased more than fivefold in recent 15 years, along with the growth of mining area. In terms of geographical distribution, the most obvious place of urban expansion is Ordos in southwest Inner Mongolia. The results using Landsat images from 1986 to 2014 in northeastern part of the Inner Mongolia show degradation in grassland from 1986 to 2014. Grid-cell-based spatial correlation

  5. Multimodal ultrasonographic assessment of leiomyosarcoma of the femoral vein in a patient misdiagnosed as having deep vein thrombosis: A case report.

    Science.gov (United States)

    Zhang, Mei; Yan, Feng; Huang, Bin; Wu, Zhoupeng; Wen, Xiaorong

    2017-11-01

    Primary leiomyosarcoma (LMS) of the vein is a rare tumor that arises from the smooth muscle cells of the vessel wall and has an extremely poor prognosis. This tumor can occur in vessels such as the inferior vena cava, great saphenous vein, femoral vein, iliac vein, popliteal vein, and renal vein; the inferior vena cava is the most common site. LMS of the femoral vein can result in edema and pain in the lower extremity; therefore, it is not easy to be differentiated from deep vein thrombosis (DVT). Moreover, virtually no studies have described the ultrasonographic features of LMS of the vein in detail. We present a case of a 55-year-old woman with LMS of the left femoral vein that was misdiagnosed as having deep vein thrombosis (DVT) on initial ultrasonographic examination. The patient began to experience edema and pain in her left leg seven months previously. She was diagnosed as having DVT on initial ultrasonographic examination, but the DVT treatment that she had received for 7 months failed to improve the status of her left lower limb. She subsequently underwent re-examination by means of a multimodal ultrasonographic imaging approach (regular B-mode imaging, color Doppler imaging, pulsed-wave Doppler imaging, contrast-enhanced ultrasonography), which confirmed a diagnosis of LMS. This patient was treated successfully with surgery. This case demonstrates that use of multiple ultrasonographic imaging techniques can be helpful to diagnose LMS accurately. Detection of vasculature in a dilated vein filled with a heterogeneous hypoechoic substance on ultrasonography is a sign of a tumor. The pitfall of misdiagnosing this tumor as DVT is a useful reminder.

  6. External Validation of Fatty Liver Index for Identifying Ultrasonographic Fatty Liver in a Large-Scale Cross-Sectional Study in Taiwan

    Science.gov (United States)

    Fang, Kuan-Chieh; Wang, Yuan-Chen; Huo, Teh-Ia; Huang, Yi-Hsiang; Yang, Hwai-I; Su, Chien-Wei; Lin, Han-Chieh; Lee, Fa-Yauh; Wu, Jaw-Ching; Lee, Shou-Dong

    2015-01-01

    Background and Aims The fatty liver index (FLI) is an algorithm involving the waist circumference, body mass index, and serum levels of triglyceride and gamma-glutamyl transferase to identify fatty liver. Although some studies have attempted to validate the FLI, few studies have been conducted for external validation among Asians. We attempted to validate FLI to predict ultrasonographic fatty liver in Taiwanese subjects. Methods We enrolled consecutive subjects who received health check-up services at the Taipei Veterans General Hospital from 2002 to 2009. Ultrasonography was applied to diagnose fatty liver. The ability of the FLI to detect ultrasonographic fatty liver was assessed by analyzing the area under the receiver operating characteristic (AUROC) curve. Results Among the 29,797 subjects enrolled in this study, fatty liver was diagnosed in 44.5% of the population. Subjects with ultrasonographic fatty liver had a significantly higher FLI than those without fatty liver by multivariate analysis (odds ratio 1.045; 95% confidence interval, CI 1.044–1.047, pfatty liver (AUROC: 0.827, 95% confidence interval, 0.822–0.831). An FLI fatty liver. Moreover, an FLI ≥ 35 (positive likelihood ratio (LR+) 3.12) for males and ≥ 20 (LR+ 4.43) for females rule in ultrasonographic fatty liver. Conclusions FLI could accurately identify ultrasonographic fatty liver in a large-scale population in Taiwan but with lower cut-off value than the Western population. Meanwhile the cut-off value was lower in females than in males. PMID:25781622

  7. A Feasibility Study for Perioperative Ventricular Tachycardia Prognosis and Detection and Noise Detection Using a Neural Network and Predictive Linear Operators

    Science.gov (United States)

    Moebes, T. A.

    1994-01-01

    To locate the accessory pathway(s) in preexicitation syndromes, epicardial and endocardial ventricular mapping is performed during anterograde ventricular activation via accessory pathway(s) from data originally received in signal form. As the number of channels increases, it is pertinent that more automated detection of coherent/incoherent signals is achieved as well as the prediction and prognosis of ventricular tachywardia (VT). Today's computers and computer program algorithms are not good in simple perceptual tasks such as recognizing a pattern or identifying a sound. This discrepancy, among other things, has been a major motivating factor in developing brain-based, massively parallel computing architectures. Neural net paradigms have proven to be effective at pattern recognition tasks. In signal processing, the picking of coherent/incoherent signals represents a pattern recognition task for computer systems. The picking of signals representing the onset ot VT also represents such a computer task. We attacked this problem by defining four signal attributes for each potential first maximal arrival peak and one signal attribute over the entire signal as input to a back propagation neural network. One attribute was the predicted amplitude value after the maximum amplitude over a data window. Then, by using a set of known (user selected) coherent/incoherent signals, and signals representing the onset of VT, we trained the back propagation network to recognize coherent/incoherent signals, and signals indicating the onset of VT. Since our output scheme involves a true or false decision, and since the output unit computes values between 0 and 1, we used a Fuzzy Arithmetic approach to classify data as coherent/incoherent signals. Furthermore, a Mean-Square Error Analysis was used to determine system stability. The neural net based picking coherent/incoherent signal system achieved high accuracy on picking coherent/incoherent signals on different patients. The system

  8. Detection of Bundle Branch Block using Adaptive Bacterial Foraging Optimization and Neural Network

    Directory of Open Access Journals (Sweden)

    Padmavthi Kora

    2017-03-01

    Full Text Available The medical practitioners analyze the electrical activity of the human heart so as to predict various ailments by studying the data collected from the Electrocardiogram (ECG. A Bundle Branch Block (BBB is a type of heart disease which occurs when there is an obstruction along the pathway of an electrical impulse. This abnormality makes the heart beat irregular as there is an obstruction in the branches of heart, this results in pulses to travel slower than the usual. Our current study involved is to diagnose this heart problem using Adaptive Bacterial Foraging Optimization (ABFO Algorithm. The Data collected from MIT/BIH arrhythmia BBB database applied to an ABFO Algorithm for obtaining best(important feature from each ECG beat. These features later fed to Levenberg Marquardt Neural Network (LMNN based classifier. The results show the proposed classification using ABFO is better than some recent algorithms reported in the literature.

  9. Correlating intrusion detection alerts on bot malware infections using neural network

    DEFF Research Database (Denmark)

    Kidmose, Egon; Stevanovic, Matija; Pedersen, Jens Myrup

    2016-01-01

    Millions of computers are infected with bot malware, form botnets and enable botmaster to perform malicious and criminal activities. Intrusion Detection Systems are deployed to detect infections, but they raise many correlated alerts for each infection, requiring a large manual investigation effort...

  10. Optimizing a neural network for detection of moving vehicles in video

    NARCIS (Netherlands)

    Fischer, N.M.; Kruithof, M.C.; Bouma, H.

    2017-01-01

    In the field of security and defense, it is extremely important to reliably detect moving objects, such as cars, ships, drones and missiles. Detection and analysis of moving objects in cameras near borders could be helpful to reduce illicit trading, drug trafficking, irregular border crossing,

  11. Detection of retinal changes from illumination normalized fundus images using convolutional neural networks

    NARCIS (Netherlands)

    Adal, K.M.; Van Etten, Peter G.; Martinez, Jose P; Rouwen, Kenneth; Vermeer, K.A.; van Vliet, L.J.; Armato, Samuel G.; Petrick, Nicholas A.

    2017-01-01

    Automated detection and quantification of spatio-temporal retinal changes is an important step to objectively assess disease progression and treatment effects for dynamic retinal diseases such as diabetic retinopathy (DR). However, detecting retinal changes caused by early DR lesions such as

  12. Mitral valve prolapse associated with celiac artery stenosis: a new ultrasonographic syndrome?

    Directory of Open Access Journals (Sweden)

    Arcari Luciano

    2004-12-01

    Full Text Available Abstract Background Celiac artery stenosis (CAS may be caused by atherosclerotic degeneration or compression exerted by the arched ligament of the diaphragm. Mitral valve prolapse (MVP is the most common valvular disorder. There are no reports on an association between CAS and MVP. Methods 1560 (41% out of 3780 consecutive patients undergoing echocardiographic assessment of MVP, had Doppler sonography of the celiac tract to detect CAS. Results CAS was found in 57 (3.7% subjects (23 males and 34 females none of whom complained of symptoms related to visceral ischemia. MVP was observed in 47 (82.4% subjects with and 118 (7.9% without CAS (p Conclusion CAS and MVP seem to be significantly associated in patients undergoing consecutive ultrasonographic screening.

  13. An optimization of the FPGA trigger based on the artificial neural network for a detection of neutrino-origin showers

    Energy Technology Data Exchange (ETDEWEB)

    Szadkowski, Zbigniew; Glas, Dariusz [University of Lodz, Department of Physics and Applied Informatics, Faculty of High-Energy Astrophysics, 90-236 Lodz, Pomorska 149, (Poland); Pytel, Krzysztof [University of Lodz, Department of Physics and Applied Informatics, Faculty of Informatics, 90-236 Lodz, (Poland)

    2015-07-01

    Observations of ultra-high energy neutrinos became a priority in experimental astro-particle physics. Up to now, the Pierre Auger Observatory did not find any candidate on a neutrino event. This imposes competitive limits to the diffuse flux of ultra-high energy neutrinos in the EeV range and above. A very low rate of events potentially generated by neutrinos is a significant challenge for a detection technique and requires both sophisticated algorithms and high-resolution hardware. A trigger based on a artificial neural network was implemented into the Cyclone{sup R} V E FPGA 5CEFA9F31I7. The prototype Front-End boards for Auger-Beyond-2015 with Cyclone{sup R} V E can test the neural network algorithm in real pampas conditions in 2015. Showers for muon and tau neutrino initiating particles on various altitudes, angles and energies were simulated in CORSICA and Offline platforms giving pattern of ADC traces in Auger water Cherenkov detectors. The 3-layer 12-10-1 neural network was taught in MATLAB by simulated ADC traces according the Levenberg-Marquardt algorithm. Results show that a probability of a ADC traces generation is very low due to a small neutrino cross-section. Nevertheless, ADC traces, if occur, for 1-10 EeV showers are relatively short and can be analyzed by 16-point input algorithm. For 100 EeV range traces are much longer, but with significantly higher amplitudes, which can be detected by standard threshold algorithms. We optimized the coefficients from MATLAB to get a maximal range of potentially registered events and for fixed-point FPGA processing to minimize calculation errors. Currently used Front-End boards based on no-more produced ACEXR PLDs and obsolete Cyclone{sup R} FPGAs allow an implementation of relatively simple threshold algorithms for triggers. New sophisticated trigger implemented in Cyclone{sup R} V E FPGAs with large amount of DSP blocks, embedded memory running with 120 - 160 MHz sampling may support to discover neutrino events

  14. DeepSAT's CloudCNN: A Deep Neural Network for Rapid Cloud Detection from Geostationary Satellites

    Science.gov (United States)

    Kalia, S.; Li, S.; Ganguly, S.; Nemani, R. R.

    2017-12-01

    Cloud and cloud shadow detection has important applications in weather and climate studies. It is even more crucial when we introduce geostationary satellites into the field of terrestrial remotesensing. With the challenges associated with data acquired in very high frequency (10-15 mins per scan), the ability to derive an accurate cloud/shadow mask from geostationary satellite data iscritical. The key to the success for most of the existing algorithms depends on spatially and temporally varying thresholds, which better capture local atmospheric and surface effects.However, the selection of proper threshold is difficult and may lead to erroneous results. In this work, we propose a deep neural network based approach called CloudCNN to classifycloud/shadow from Himawari-8 AHI and GOES-16 ABI multispectral data. DeepSAT's CloudCNN consists of an encoder-decoder based architecture for binary-class pixel wise segmentation. We train CloudCNN on multi-GPU Nvidia Devbox cluster, and deploy the prediction pipeline on NASA Earth Exchange (NEX) Pleiades supercomputer. We achieved an overall accuracy of 93.29% on test samples. Since, the predictions take only a few seconds to segment a full multi-spectral GOES-16 or Himawari-8 Full Disk image, the developed framework can be used for real-time cloud detection, cyclone detection, or extreme weather event predictions.

  15. Computerized detection of multiple sclerosis candidate regions based on a level set method using an artificial neural network

    International Nuclear Information System (INIS)

    Kuwazuru, Junpei; Magome, Taiki; Arimura, Hidetaka; Yamashita, Yasuo; Oki, Masafumi; Toyofuku, Fukai; Kakeda, Shingo; Yamamoto, Daisuke

    2010-01-01

    Yamamoto et al. developed the system for computer-aided detection of multiple sclerosis (MS) candidate regions. In a level set method in their proposed method, they employed the constant threshold value for the edge indicator function related to a speed function of the level set method. However, it would be appropriate to adjust the threshold value to each MS candidate region, because the edge magnitudes in MS candidates differ from each other. Our purpose of this study was to develop a computerized detection of MS candidate regions in MR images based on a level set method using an artificial neural network (ANN). To adjust the threshold value for the edge indicator function in the level set method to each true positive (TP) and false positive (FP) region, we constructed the ANN. The ANN could provide the suitable threshold value for each candidate region in the proposed level set method so that TP regions can be segmented and FP regions can be removed. Our proposed method detected MS regions at a sensitivity of 82.1% with 0.204 FPs per slice and similarity index of MS candidate regions was 0.717 on average. (author)

  16. Knowledge-guided golf course detection using a convolutional neural network fine-tuned on temporally augmented data

    Science.gov (United States)

    Chen, Jingbo; Wang, Chengyi; Yue, Anzhi; Chen, Jiansheng; He, Dongxu; Zhang, Xiuyan

    2017-10-01

    The tremendous success of deep learning models such as convolutional neural networks (CNNs) in computer vision provides a method for similar problems in the field of remote sensing. Although research on repurposing pretrained CNN to remote sensing tasks is emerging, the scarcity of labeled samples and the complexity of remote sensing imagery still pose challenges. We developed a knowledge-guided golf course detection approach using a CNN fine-tuned on temporally augmented data. The proposed approach is a combination of knowledge-driven region proposal, data-driven detection based on CNN, and knowledge-driven postprocessing. To confront data complexity, knowledge-derived cooccurrence, composition, and area-based rules are applied sequentially to propose candidate golf regions. To confront sample scarcity, we employed data augmentation in the temporal domain, which extracts samples from multitemporal images. The augmented samples were then used to fine-tune a pretrained CNN for golf detection. Finally, commission error was further suppressed by postprocessing. Experiments conducted on GF-1 imagery prove the effectiveness of the proposed approach.

  17. Airplane detection based on fusion framework by combining saliency model with Deep Convolutional Neural Networks

    Science.gov (United States)

    Dou, Hao; Sun, Xiao; Li, Bin; Deng, Qianqian; Yang, Xubo; Liu, Di; Tian, Jinwen

    2018-03-01

    Aircraft detection from very high resolution remote sensing images, has gained more increasing interest in recent years due to the successful civil and military applications. However, several problems still exist: 1) how to extract the high-level features of aircraft; 2) locating objects within such a large image is difficult and time consuming; 3) A common problem of multiple resolutions of satellite images still exists. In this paper, inspirited by biological visual mechanism, the fusion detection framework is proposed, which fusing the top-down visual mechanism (deep CNN model) and bottom-up visual mechanism (GBVS) to detect aircraft. Besides, we use multi-scale training method for deep CNN model to solve the problem of multiple resolutions. Experimental results demonstrate that our method can achieve a better detection result than the other methods.

  18. Ischemia Detection Using Supervised Learning for Hierarchical Neural Networks Based on Kohonen-Maps

    National Research Council Canada - National Science Library

    Vladutu, L

    2001-01-01

    .... The motivation for developing the Supervising Network - Self Organizing Map (sNet-SOM) model is to design computationally effective solutions for the particular problem of ischemia detection and other similar applications...

  19. Semiautomated tremor detection using a combined cross-correlation and neural network approach

    Science.gov (United States)

    Horstmann, Tobias; Harrington, Rebecca M.; Cochran, Elizabeth S.

    2013-01-01

    Despite observations of tectonic tremor in many locations around the globe, the emergent phase arrivals, low‒amplitude waveforms, and variable event durations make automatic detection a nontrivial task. In this study, we employ a new method to identify tremor in large data sets using a semiautomated technique. The method first reduces the data volume with an envelope cross‒correlation technique, followed by a Self‒Organizing Map (SOM) algorithm to identify and classify event types. The method detects tremor in an automated fashion after calibrating for a specific data set, hence we refer to it as being “semiautomated”. We apply the semiautomated detection algorithm to a newly acquired data set of waveforms from a temporary deployment of 13 seismometers near Cholame, California, from May 2010 to July 2011. We manually identify tremor events in a 3 week long test data set and compare to the SOM output and find a detection accuracy of 79.5%. Detection accuracy improves with increasing signal‒to‒noise ratios and number of available stations. We find detection completeness of 96% for tremor events with signal‒to‒noise ratios above 3 and optimal results when data from at least 10 stations are available. We compare the SOM algorithm to the envelope correlation method of Wech and Creager and find the SOM performs significantly better, at least for the data set examined here. Using the SOM algorithm, we detect 2606 tremor events with a cumulative signal duration of nearly 55 h during the 13 month deployment. Overall, the SOM algorithm is shown to be a flexible new method that utilizes characteristics of the waveforms to identify tremor from noise or other seismic signals.

  20. The neural substrates of impaired prosodic detection in schizophrenia and its sensorial antecedents.

    Science.gov (United States)

    Leitman, David I; Hoptman, Matthew J; Foxe, John J; Saccente, Erica; Wylie, Glenn R; Nierenberg, Jay; Jalbrzikowski, Maria; Lim, Kelvin O; Javitt, Daniel C

    2007-03-01

    Individuals with schizophrenia show severe deficits in their ability to decode emotions based upon vocal inflection (affective prosody). This study examined neural substrates of prosodic dysfunction in schizophrenia with voxelwise analysis of diffusion tensor magnetic resonance imaging (MRI). Affective prosodic performance was assessed in 19 patients with schizophrenia and 19 comparison subjects with the Voice Emotion Identification Task (VOICEID), along with measures of basic pitch perception and executive processing (Wisconsin Card Sorting Test). Diffusion tensor MRI fractional anisotropy valves were used for voxelwise correlation analyses. In a follow-up experiment, performance on a nonaffective prosodic perception task was assessed in an additional cohort of 24 patients and 17 comparison subjects. Patients showed significant deficits in VOICEID and Distorted Tunes Task performance. Impaired VOICEID performance correlated significantly with lower fractional anisotropy values within primary and secondary auditory pathways, orbitofrontal cortex, corpus callosum, and peri-amygdala white matter. Impaired Distorted Tunes Task performance also correlated with lower fractional anisotropy in auditory and amygdalar pathways but not prefrontal cortex. Wisconsin Card Sorting Test performance in schizophrenia correlated primarily with prefrontal fractional anisotropy. In the follow-up study, significant deficits were observed as well in nonaffective prosodic performance, along with significant intercorrelations among sensory, affective prosodic, and nonaffective measures. Schizophrenia is associated with both structural and functional disturbances at the level of primary auditory cortex. Such deficits contribute significantly to patients' inability to decode both emotional and semantic aspects of speech, highlighting the importance of sensorial abnormalities in social communicatory dysfunction in schizophrenia.

  1. Identification of input variables for feature based artificial neural networks-saccade detection in EOG recordings.

    Science.gov (United States)

    Tigges, P; Kathmann, N; Engel, R R

    1997-07-01

    Though artificial neural networks (ANN) are excellent tools for pattern recognition problems when signal to noise ratio is low, the identification of decision relevant features for ANN input data is still a crucial issue. The experience of the ANN designer and the existing knowledge and understanding of the problem seem to be the only links for a specific construction. In the present study a backpropagation ANN based on modified raw data inputs showed encouraging results. Investigating the specific influences of prototypical input patterns on a specially designed ANN led to a new sparse and efficient input data presentation. This data coding obtained by a semiautomatic procedure combining existing expert knowledge and the internal representation structures of the raw data based ANN yielded a list of feature vectors, each representing the relevant information for saccade identification. The feature based ANN produced a reduction of the error rate of nearly 40% compared with the raw data ANN. An overall correct classification of 92% of so far unknown data was realized. The proposed method of extracting internal ANN knowledge for the production of a better input data representation is not restricted to EOG recordings, and could be used in various fields of signal analysis.

  2. Short-Term Wind Speed Forecasting Using Decomposition-Based Neural Networks Combining Abnormal Detection Method

    Directory of Open Access Journals (Sweden)

    Xuejun Chen

    2014-01-01

    Full Text Available As one of the most promising renewable resources in electricity generation, wind energy is acknowledged for its significant environmental contributions and economic competitiveness. Because wind fluctuates with strong variation, it is quite difficult to describe the characteristics of wind or to estimate the power output that will be injected into the grid. In particular, short-term wind speed forecasting, an essential support for the regulatory actions and short-term load dispatching planning during the operation of wind farms, is currently regarded as one of the most difficult problems to be solved. This paper contributes to short-term wind speed forecasting by developing two three-stage hybrid approaches; both are combinations of the five-three-Hanning (53H weighted average smoothing method, ensemble empirical mode decomposition (EEMD algorithm, and nonlinear autoregressive (NAR neural networks. The chosen datasets are ten-minute wind speed observations, including twelve samples, and our simulation indicates that the proposed methods perform much better than the traditional ones when addressing short-term wind speed forecasting problems.

  3. Neural network based tomographic approach to detect earthquake-related ionospheric anomalies

    Directory of Open Access Journals (Sweden)

    S. Hirooka

    2011-08-01

    Full Text Available A tomographic approach is used to investigate the fine structure of electron density in the ionosphere. In the present paper, the Residual Minimization Training Neural Network (RMTNN method is selected as the ionospheric tomography with which to investigate the detailed structure that may be associated with earthquakes. The 2007 Southern Sumatra earthquake (M = 8.5 was selected because significant decreases in the Total Electron Content (TEC have been confirmed by GPS and global ionosphere map (GIM analyses. The results of the RMTNN approach are consistent with those of TEC approaches. With respect to the analyzed earthquake, we observed significant decreases at heights of 250–400 km, especially at 330 km. However, the height that yields the maximum electron density does not change. In the obtained structures, the regions of decrease are located on the southwest and southeast sides of the Integrated Electron Content (IEC (altitudes in the range of 400–550 km and on the southern side of the IEC (altitudes in the range of 250–400 km. The global tendency is that the decreased region expands to the east with increasing altitude and concentrates in the Southern hemisphere over the epicenter. These results indicate that the RMTNN method is applicable to the estimation of ionospheric electron density.

  4. Detecting Malware with an Ensemble Method Based on Deep Neural Network

    Directory of Open Access Journals (Sweden)

    Jinpei Yan

    2018-01-01

    Full Text Available Malware detection plays a crucial role in computer security. Recent researches mainly use machine learning based methods heavily relying on domain knowledge for manually extracting malicious features. In this paper, we propose MalNet, a novel malware detection method that learns features automatically from the raw data. Concretely, we first generate a grayscale image from malware file, meanwhile extracting its opcode sequences with the decompilation tool IDA. Then MalNet uses CNN and LSTM networks to learn from grayscale image and opcode sequence, respectively, and takes a stacking ensemble for malware classification. We perform experiments on more than 40,000 samples including 20,650 benign files collected from online software providers and 21,736 malwares provided by Microsoft. The evaluation result shows that MalNet achieves 99.88% validation accuracy for malware detection. In addition, we also take malware family classification experiment on 9 malware families to compare MalNet with other related works, in which MalNet outperforms most of related works with 99.36% detection accuracy and achieves a considerable speed-up on detecting efficiency comparing with two state-of-the-art results on Microsoft malware dataset.

  5. Ultrasonographic Diagnosis and Clinical Evaluation of the Foreign Body Complications in the Compound Stomach of Cattle and Buffaloes

    Directory of Open Access Journals (Sweden)

    Effat E. El esawy

    2015-07-01

    Full Text Available This study was aimed to detect and record the clinical and ultrasonographic findings of the different complications resulted from the foreign bodies lodged in the compound stomach of cattle and buffaloes. A total of 105 animals (37 cattle and 68 buffaloes were subjected to study. Based on the clinical and ultrasonographic examination, animals were classified into; acute local reticuloperitonitis (ALRP (15 cattle and 28 buffaloes, chronic local reticuloperitonitis (CLRP (6 cattle and 14 buffaloes, acute diffuse reticuloperitonitis (ADRP (5 cattle and 3buffaloes, reticular abscesses (RA (4 cattle and 7 buffaloes, traumatic pericarditis (TP (6 cattle and16 buffaloes and liver abscess (one cattle. Results revealed that ALRP represented the highest percentage of 40.5% in cattle and 41.2 % in buffalos between the different complications of TRP. TP represented the second complications of higher incidence (16.2% in cows and 23.5% in buffalos. Liver abscess represented the lowest percentage (2.8% and was recorded in cows only. The pregnant animals were affected more than the non pregnant. Clinical findings represented in systemic reaction and pain tests were commonly encountered in TRP and its complications. Some of the affected animals were negatively respond to metal detector test. Results of the present study indicated that the ultrasonographic examination provide a specific echogenic pattern for the different complications of TRP. It was concluded that, clinical examination only is not efficient to give accurate diagnosis of foreign body lodged in the reticulum and rumen and their complications. Ultrasonography is a safe, non invasive diagnostic confirmatory method that could be used for early detection of such conditions.

  6. Ultrasonographic findings of aspergillus bursitis in a patient with a renal transplantation: a case report

    Energy Technology Data Exchange (ETDEWEB)

    Kang, Byeong Seong; Yang, Myeon Jun; Kim, Young Min; Youm, Yoon Seok; Choi, Seong Hoon; Park, Sung Bin; Jeong, Ae Kyung [University of Ulsan College of Medicine, Ulsan University Hospital, Ulsan (Korea, Republic of)

    2008-04-15

    Aspergillus bursitis is an uncommon condition demonstrated as a nonspecific soft tissue mass. To our knowledge, the ultrasonographic findings of aspergillus bursitis in immunocompromised patients have not been previously reported. Here, we report a case of aspergillus bursitis in a renal transplant recipient, accompanied by the associated ultrasonographic findings.

  7. Ultrasonographic findings of aspergillus bursitis in a patient with a renal transplantation: a case report

    International Nuclear Information System (INIS)

    Kang, Byeong Seong; Yang, Myeon Jun; Kim, Young Min; Youm, Yoon Seok; Choi, Seong Hoon; Park, Sung Bin; Jeong, Ae Kyung

    2008-01-01

    Aspergillus bursitis is an uncommon condition demonstrated as a nonspecific soft tissue mass. To our knowledge, the ultrasonographic findings of aspergillus bursitis in immunocompromised patients have not been previously reported. Here, we report a case of aspergillus bursitis in a renal transplant recipient, accompanied by the associated ultrasonographic findings

  8. The validity of ultrasonographic scanning as screening method for abdominal aortic aneurysm

    DEFF Research Database (Denmark)

    Lindholt, Jes Sanddal; Vammen, Sten; Juul, Søren

    1999-01-01

    the sensitivity and specificity of screening for abdominal aortic aneurysms (AAAs) with ultrasonographic scanning (US) is unknown. The aim of the study was to validate US as screening test for AAAs.......the sensitivity and specificity of screening for abdominal aortic aneurysms (AAAs) with ultrasonographic scanning (US) is unknown. The aim of the study was to validate US as screening test for AAAs....

  9. Convolutional neural networks for segmentation and object detection of human semen

    DEFF Research Database (Denmark)

    Nissen, Malte Stær; Krause, Oswin; Almstrup, Kristian

    2017-01-01

    to clutter. Our results indicate that training on full images is superior to training on patches when class-skew is properly handled. Full image training including up-sampling during training proves to be beneficial in deep CNNs for pixel wise accuracy and detection performance. Predicted sperm cells...... are found by using connected components on the CNN predictions. We investigate optimization of a threshold parameter on the size of detected components. Our best network achieves 93.87% precision and 91.89% recall on our test dataset after thresholding outperforming a classical image analysis approach....

  10. Automatic detection of anatomical regions in frontal x-ray images: comparing convolutional neural networks to random forest

    Science.gov (United States)

    Olory Agomma, R.; Vázquez, C.; Cresson, T.; De Guise, J.

    2018-02-01

    Most algorithms to detect and identify anatomical structures in medical images require either to be initialized close to the target structure, or to know that the structure is present in the image, or to be trained on a homogeneous database (e.g. all full body or all lower limbs). Detecting these structures when there is no guarantee that the structure is present in the image, or when the image database is heterogeneous (mixed configurations), is a challenge for automatic algorithms. In this work we compared two state-of-the-art machine learning techniques in order to determine which one is the most appropriate for predicting targets locations based on image patches. By knowing the position of thirteen landmarks points, labelled by an expert in EOS frontal radiography, we learn the displacement between salient points detected in the image and these thirteen landmarks. The learning step is carried out with a machine learning approach by exploring two methods: Convolutional Neural Network (CNN) and Random Forest (RF). The automatic detection of the thirteen landmarks points in a new image is then obtained by averaging the positions of each one of these thirteen landmarks estimated from all the salient points in the new image. We respectively obtain for CNN and RF, an average prediction error (both mean and standard deviation in mm) of 29 +/-18 and 30 +/- 21 for the thirteen landmarks points, indicating the approximate location of anatomical regions. On the other hand, the learning time is 9 days for CNN versus 80 minutes for RF. We provide a comparison of the results between the two machine learning approaches.

  11. DETECTION OF MALICIOUS SOFTWARE USING CLASSICAL AND NEURAL NETWORK CLASSIFICATION METHODS

    Directory of Open Access Journals (Sweden)

    S. V. Zhernakov

    2015-01-01

    Full Text Available Formulation of the problem: the spectrum of problems solved by modern mobile systems such as Android is constantly growing. This is because on the one hand by the potential opportunities that are implemented in hardware, as well as their integration with modern information technologies, which in turn harmoniously complement and create powerful ardware and software information systems, capable of performing many functions, including pro- information boards. Increasing the flow of information, complexity of the processes and of the hardware and software component devices such as Android, forcing developers to create new means of protection, efficiency and qualitative performing the process. This is especially important in the development of automated systems instrumental performing classification (clustering of existing software into two classes: safe and malicious software. The aim is to increase the reliability and quality of recognition of modern built-in security of information, as well as the rationale and the selection methods of carrying out these functions. The methods used are: to accomplish the goals are analyzed and used classical methods of classification, neural network method based on standard architectures, and support vector machine (SVM - machine. Novelty: The paper presents the concept of the use of support vector in identifying deleterious software developed methodological, algorithmic and software that implements this concept in relation to the means of mobile communication. Result: The obtained qualitative and quantitative characteristics-security software. Practical value: the technique of development of advanced information security systems in mobile environments such as Android. It presents an approach to the description of behavioral malware (based on the following virus: none - wakes - Analysis of weaknesses - the action: a healthy regime or attack (threat.

  12. Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network

    NARCIS (Netherlands)

    Chen, Junwen; Liu, Zhigang; Wang, H.; Nunez Vicencio, Alfredo; Han, Zhiwei

    2018-01-01

    The excitation and vibration triggered by the long-term operation of railway vehicles inevitably result in defective states of catenary support devices. With the massive construction of high-speed electrified railways, automatic defect detection of diverse and plentiful fasteners on the catenary

  13. Invasive species change detection using artificial neural networks and CASI hyperspectral imagery

    Science.gov (United States)

    For monitoring and controlling the extent and intensity of an invasive species, a direct multi-date image classification method was applied in invasive species (saltcedar) change detection in the study area of Lovelock, Nevada. With multi-date Compact Airborne Spectrographic Imager (CASI) hyperspec...

  14. Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection

    DEFF Research Database (Denmark)

    Schlechtingen, Meik; Santos, Ilmar

    2011-01-01

    This paper presents the research results of a comparison of three different model based approaches for wind turbine fault detection in online SCADA data, by applying developed models to five real measured faults and anomalies. The regression based model as the simplest approach to build a normal...

  15. Self-organizing neural networks for automatic detection and classification of contrast-enhancing lesions in dynamic MR-mammography

    International Nuclear Information System (INIS)

    Vomweg, T.W.; Teifke, A.; Kauczor, H.U.; Achenbach, T.; Rieker, O.; Schreiber, W.G.; Heitmann, K.R.; Beier, T.; Thelen, M.

    2005-01-01

    Purpose: Investigation and statistical evaluation of 'Self-Organizing Maps', a special type of neural networks in the field of artificial intelligence, classifying contrast enhancing lesions in dynamic MR-mammography. Material and Methods: 176 investigations with proven histology after core biopsy or operation were randomly divided into two groups. Several Self-Organizing Maps were trained by investigations of the first group to detect and classify contrast enhancing lesions in dynamic MR-mammography. Each single pixel's signal/time curve of all patients within the second group was analyzed by the Self-Organizing Maps. The likelihood of malignancy was visualized by color overlays on the MR-images. At last assessment of contrast-enhancing lesions by each different network was rated visually and evaluated statistically. Results: A well balanced neural network achieved a sensitivity of 90.5% and a specificity of 72.2% in predicting malignancy of 88 enhancing lesions. Detailed analysis of false-positive results revealed that every second fibroadenoma showed a 'typical malignant' signal/time curve without any chance to differentiate between fibroadenomas and malignant tissue regarding contrast enhancement alone; but this special group of lesions was represented by a well-defined area of the Self-Organizing Map. Discussion: Self-Organizing Maps are capable of classifying a dynamic signal/time curve as 'typical benign' or 'typical malignant'. Therefore, they can be used as second opinion. In view of the now known localization of fibroadenomas enhancing like malignant tumors at the Self-Organizing Map, these lesions could be passed to further analysis by additional post-processing elements (e.g., based on T2-weighted series or morphology analysis) in the future. (orig.)

  16. Sensitive and specific peak detection for SELDI-TOF mass spectrometry using a wavelet/neural-network based approach.

    Directory of Open Access Journals (Sweden)

    Vincent A Emanuele

    Full Text Available SELDI-TOF mass spectrometer's compact size and automated, high throughput design have been attractive to clinical researchers, and the platform has seen steady-use in biomarker studies. Despite new algorithms and preprocessing pipelines that have been developed to address reproducibility issues, visual inspection of the results of SELDI spectra preprocessing by the best algorithms still shows miscalled peaks and systematic sources of error. This suggests that there continues to be problems with SELDI preprocessing. In this work, we study the preprocessing of SELDI in detail and introduce improvements. While many algorithms, including the vendor supplied software, can identify peak clusters of specific mass (or m/z in groups of spectra with high specificity and low false discover rate (FDR, the algorithms tend to underperform estimating the exact prevalence and intensity of peaks in those clusters. Thus group differences that at first appear very strong are shown, after careful and laborious hand inspection of the spectra, to be less than significant. Here we introduce a wavelet/neural network based algorithm which mimics what a team of expert, human users would call for peaks in each of several hundred spectra in a typical SELDI clinical study. The wavelet denoising part of the algorithm optimally smoothes the signal in each spectrum according to an improved suite of signal processing algorithms previously reported (the LibSELDI toolbox under development. The neural network part of the algorithm combines those results with the raw signal and a training dataset of expertly called peaks, to call peaks in a test set of spectra with approximately 95% accuracy. The new method was applied to data collected from a study of cervical mucus for the early detection of cervical cancer in HPV infected women. The method shows promise in addressing the ongoing SELDI reproducibility issues.

  17. Detection and diagnosis of a natural gas dehydration plant by absorption with triethylene glycol, employing a artificial neural networks

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    2004-07-01

    The natural gas dehydration is a great importance operation in the gas and petroleum industry, It avoids operational problems associated with the water content, which appear frequently in the industrial facilities that use the natural gas as raw material or as work tool. Due to the presence of undesirable pollutants which may enter the plant with the wet natural gas current (lubricating, corrosion inhibitors, salts, and others), the equipment that constitutes the dehydration plants are capable to suffering operational faults as the heat exchangers fouling, foam formation in the absorber, glycol losses for dragging; trays, packings, valves and filters fouling; glycol degradation, inadequate temperatures of regeneration and others. The above mentioned faults often cannot be detected by the operators and engineers but up to the moment when a catastrophic damage occurs or when products are obtained out of specification, which causes big economic and time losses. By means of the application of artificial neural networks, there was achieved the detection and the effective diagnosis of faults, still in incipient state, in a gas dehydration plant. (author)

  18. The music of your emotions: neural substrates involved in detection of emotional correspondence between auditory and visual music actions.

    Directory of Open Access Journals (Sweden)

    Karin Petrini

    Full Text Available In humans, emotions from music serve important communicative roles. Despite a growing interest in the neural basis of music perception, action and emotion, the majority of previous studies in this area have focused on the auditory aspects of music performances. Here we investigate how the brain processes the emotions elicited by audiovisual music performances. We used event-related functional magnetic resonance imaging, and in Experiment 1 we defined the areas responding to audiovisual (musician's movements with music, visual (musician's movements only, and auditory emotional (music only displays. Subsequently a region of interest analysis was performed to examine if any of the areas detected in Experiment 1 showed greater activation for emotionally mismatching performances (combining the musician's movements with mismatching emotional sound than for emotionally matching music performances (combining the musician's movements with matching emotional sound as presented in Experiment 2 to the same participants. The insula and the left thalamus were found to respond consistently to visual, auditory and audiovisual emotional information and to have increased activation for emotionally mismatching displays in comparison with emotionally matching displays. In contrast, the right thalamus was found to respond to audiovisual emotional displays and to have similar activation for emotionally matching and mismatching displays. These results suggest that the insula and left thalamus have an active role in detecting emotional correspondence between auditory and visual information during music performances, whereas the right thalamus has a different role.

  19. Online Vibration Monitoring of a Water Pump Machine to Detect Its Malfunction Components Based on Artificial Neural Network

    Science.gov (United States)

    Rahmawati, P.; Prajitno, P.

    2018-04-01

    Vibration monitoring is a measurement instrument used to identify, predict, and prevent failures in machine instruments[6]. This is very needed in the industrial applications, cause any problem with the equipment or plant translates into economical loss and they are mostly monitored component off-line[2]. In this research, a system has been developed to detect the malfunction of the components of Shimizu PS-128BT water pump machine, such as capacitor, bearing and impeller by online measurements. The malfunction components are detected by taking vibration data using a Micro-Electro-Mechanical System(MEMS)-based accelerometer that are acquired by using Raspberry Pi microcomputer and then the data are converted into the form of Relative Power Ratio(RPR). In this form the signal acquired from different components conditions have different patterns. The collected RPR used as the base of classification process for recognizing the damage components of the water pump that are conducted by Artificial Neural Network(ANN). Finally, the damage test result will be sent via text message using GSM module that are connected to Raspberry Pi microcomputer. The results, with several measurement readings, with each reading in 10 minutes duration for each different component conditions, all cases yield 100% of accuracies while in the case of defective capacitor yields 90% of accuracy.

  20. Automated Detection of Obstructive Sleep Apnea Events from a Single-Lead Electrocardiogram Using a Convolutional Neural Network.

    Science.gov (United States)

    Urtnasan, Erdenebayar; Park, Jong-Uk; Joo, Eun-Yeon; Lee, Kyoung-Joung

    2018-04-23

    In this study, we propose a method for the automated detection of obstructive sleep apnea (OSA) from a single-lead electrocardiogram (ECG) using a convolutional neural network (CNN). A CNN model was designed with six optimized convolution layers including activation, pooling, and dropout layers. One-dimensional (1D) convolution, rectified linear units (ReLU), and max pooling were applied to the convolution, activation, and pooling layers, respectively. For training and evaluation of the CNN model, a single-lead ECG dataset was collected from 82 subjects with OSA and was divided into training (including data from 63 patients with 34,281 events) and testing (including data from 19 patients with 8571 events) datasets. Using this CNN model, a precision of 0.99%, a recall of 0.99%, and an F 1 -score of 0.99% were attained with the training dataset; these values were all 0.96% when the CNN was applied to the testing dataset. These results show that the proposed CNN model can be used to detect OSA accurately on the basis of a single-lead ECG. Ultimately, this CNN model may be used as a screening tool for those suspected to suffer from OSA.

  1. Detection of Gait Modes Using an Artificial Neural Network during Walking with a Powered Ankle-Foot Orthosis

    Science.gov (United States)

    2016-01-01

    This paper presents an algorithm, for use with a Portable Powered Ankle-Foot Orthosis (i.e., PPAFO) that can automatically detect changes in gait modes (level ground, ascent and descent of stairs or ramps), thus allowing for appropriate ankle actuation control during swing phase. An artificial neural network (ANN) algorithm used input signals from an inertial measurement unit and foot switches, that is, vertical velocity and segment angle of the foot. Output from the ANN was filtered and adjusted to generate a final data set used to classify different gait modes. Five healthy male subjects walked with the PPAFO on the right leg for two test scenarios (walking over level ground and up and down stairs or a ramp; three trials per scenario). Success rate was quantified by the number of correctly classified steps with respect to the total number of steps. The results indicated that the proposed algorithm's success rate was high (99.3%, 100%, and 98.3% for level, ascent, and descent modes in the stairs scenario, respectively; 98.9%, 97.8%, and 100% in the ramp scenario). The proposed algorithm continuously detected each step's gait mode with faster timing and higher accuracy compared to a previous algorithm that used a decision tree based on maximizing the reliability of the mode recognition. PMID:28070188

  2. Malignancy Detection on Mammography Using Dual Deep Convolutional Neural Networks and Genetically Discovered False Color Input Enhancement.

    Science.gov (United States)

    Teare, Philip; Fishman, Michael; Benzaquen, Oshra; Toledano, Eyal; Elnekave, Eldad

    2017-08-01

    Breast cancer is the most prevalent malignancy in the US and the third highest cause of cancer-related mortality worldwide. Regular mammography screening has been attributed with doubling the rate of early cancer detection over the past three decades, yet estimates of mammographic accuracy in the hands of experienced radiologists remain suboptimal with sensitivity ranging from 62 to 87% and specificity from 75 to 91%. Advances in machine learning (ML) in recent years have demonstrated capabilities of image analysis which often surpass those of human observers. Here we present two novel techniques to address inherent challenges in the application of ML to the domain of mammography. We describe the use of genetic search of image enhancement methods, leading us to the use of a novel form of false color enhancement through contrast limited adaptive histogram equalization (CLAHE), as a method to optimize mammographic feature representation. We also utilize dual deep convolutional neural networks at different scales, for classification of full mammogram images and derivative patches combined with a random forest gating network as a novel architectural solution capable of discerning malignancy with a specificity of 0.91 and a specificity of 0.80. To our knowledge, this represents the first automatic stand-alone mammography malignancy detection algorithm with sensitivity and specificity performance similar to that of expert radiologists.

  3. Ultrasonographic findings of omental and mesnenteric cysts

    Energy Technology Data Exchange (ETDEWEB)

    Kang, Jin Wha; Kim, I W; Yeon, K M; Kim, C W [Seoul National University College of Medicine, Seoul (Korea, Republic of)

    1989-12-15

    Omental and mesenteric cysts are uncommon diseases mostly occurring in young children. They are felt to have a common origin from obstructed or ectopic lymphatics. We reviewed three cases of omental cyst and three cases of mesenteric cyst. Sonography showed cystic mass with a thin wall and multiple thin septi dividing the cyst into multiple irregular spaces. In most cases(5/6) solid portions were detected and they were proved to be tissue debris and hemorrhagic clots. Fluid content was either anechoic or echogenic. Floating echogenicities or fluid-fluid level were detected in some cases. Ultrasound is very useful in the diagnosis of omental and mesenteric cysts in children, giving reliable information relating to internal hemorrhage, infection or adhesion to adjacent organs

  4. DETECTION OF CLAMPING FORCES ON MOUNTING A CONSTRUCTION VIA NEURAL NETWORK FOR THE FINITE-ELEMENT MODEL OF COMPRESSOR-CONDENSING UNIT

    Directory of Open Access Journals (Sweden)

    S. V. Krasnovskaya

    2017-01-01

    Full Text Available The article provides a brief review of a condensing unit and problems of mathematic simulation. It examines the influence of pretension on the strain-stress state of a construction by means of finiteelement modeling. The arrangement of a set of input-output data for neural network is also considered. The article investigates a possibility to predict mounting precision via neural networks; by analogy with the above calculations it examines the option to detect clamping forces on mounting compressorcondensing unit. 

  5. Clinical and ultrasonographic study of patients presenting with transvaginal mesh complications.

    Science.gov (United States)

    Manonai, Jittima; Rostaminia, Ghazaleh; Denson, Lindsay; Shobeiri, S Abbas

    2016-03-01

    The objective of this study was to investigate the clinical and ultrasonographic findings of women who had three-dimensional endovaginal ultrasound (EVUS) for the management of vaginal mesh complications. This was a retrospective study of patients that had EVUS due to mesh complications at a tertiary care center. The clinical charts were reviewed. The stored 3D volumes were reviewed regarding mesh information by two examiners independently. The predictive value of physical examination for detection of vaginal mesh was calculated. Patient outcomes were reviewed. Seventy-nine patients presented to our center because of their, or their physicians' concern regarding mesh complications. Forty-one (51.9%) had vaginal/pelvic pain, and 51/62 (82.2%) of sexually active women experienced dyspareunia. According to ultrasonographic findings, mesh or sling was not demonstrated in six patients who believed they have had mesh/sling implantation. The positive predictive value for vaginal examination was 94.5% (95% CI: 84.9%-98.8%), negative predictive value was 12.5% (95% CI: 2.8%-32.4%), sensitivity was 72.2% (95% CI: 59.4%-81.2%), and specificity was 50.0% (95% CI: 12.4%-87.6%). Fifty-four patients were indicated for surgical treatment. Median postoperative review was 12 (range, 3-18) months and 38/53 (71.7%) patients were satisfied. The most common complaints of vaginal mesh complications were pain and dyspareunia. EVUS appeared to be helpful for assessing mesh presence, location, and extent including planning for surgical intervention. © 2015 Wiley Periodicals, Inc.

  6. Application of cross-correlated delay shift rule in spiking neural networks for interictal spike detection.

    Science.gov (United States)

    Lilin Guo; Zhenzhong Wang; Cabrerizo, Mercedes; Adjouadi, Malek

    2016-08-01

    This study proposes a Cross-Correlated Delay Shift (CCDS) supervised learning rule to train neurons with associated spatiotemporal patterns to classify spike patterns. The objective of this study was to evaluate the feasibility of using the CCDS rule to automate the detection of interictal spikes in electroencephalogram (EEG) data on patients with epilepsy. Encoding is the initial yet essential step for spiking neurons to process EEG patterns. A new encoding method is utilized to convert the EEG signal into spike patterns. The simulation results show that the proposed algorithm identified 69 spikes out of 82 spikes, or 84% detection rate, which is quite high considering the subtleties of interictal spikes and the tediousness of monitoring long EEG records. This CCDS rule is also benchmarked by ReSuMe on the same task.

  7. GANN: Genetic algorithm neural networks for the detection of conserved combinations of features in DNA

    Directory of Open Access Journals (Sweden)

    Beiko Robert G

    2005-02-01

    Full Text Available Abstract Background The multitude of motif detection algorithms developed to date have largely focused on the detection of patterns in primary sequence. Since sequence-dependent DNA structure and flexibility may also play a role in protein-DNA interactions, the simultaneous exploration of sequence- and structure-based hypotheses about the composition of binding sites and the ordering of features in a regulatory region should be considered as well. The consideration of structural features requires the development of new detection tools that can deal with data types other than primary sequence. Results GANN (available at http://bioinformatics.org.au/gann is a machine learning tool for the detection of conserved features in DNA. The software suite contains programs to extract different regions of genomic DNA from flat files and convert these sequences to indices that reflect sequence and structural composition or the presence of specific protein binding sites. The machine learning component allows the classification of different types of sequences based on subsamples of these indices, and can identify the best combinations of indices and machine learning architecture for sequence discrimination. Another key feature of GANN is the replicated splitting of data into training and test sets, and the implementation of negative controls. In validation experiments, GANN successfully merged important sequence and structural features to yield good predictive models for synthetic and real regulatory regions. Conclusion GANN is a flexible tool that can search through large sets of sequence and structural feature combinations to identify those that best characterize a set of sequences.

  8. Multi-Frame Convolutional Neural Networks for Object Detection in Temporal Data

    Science.gov (United States)

    2017-03-01

    of low-cost autonomous drones. The on-station time will no longer be dictated by human factors, but instead by the platforms’ capabilities. A...Imagine the task of detecting only moving cars but ignoring stationary cars . An object detector could probably do very well by looking for clues in a...single frame of video: cars in parking spots are usually stationary, moving cars may have a motion blur, and if it had an infrared sensor it could even

  9. Long Short-Term Memory Neural Networks for Online Disturbance Detection in Satellite Image Time Series

    Directory of Open Access Journals (Sweden)

    Yun-Long Kong

    2018-03-01

    Full Text Available A satellite image time series (SITS contains a significant amount of temporal information. By analysing this type of data, the pattern of the changes in the object of concern can be explored. The natural change in the Earth’s surface is relatively slow and exhibits a pronounced pattern. Some natural events (for example, fires, floods, plant diseases, and insect pests and human activities (for example, deforestation and urbanisation will disturb this pattern and cause a relatively profound change on the Earth’s surface. These events are usually referred to as disturbances. However, disturbances in ecosystems are not easy to detect from SITS data, because SITS contain combined information on disturbances, phenological variations and noise in remote sensing data. In this paper, a novel framework is proposed for online disturbance detection from SITS. The framework is based on long short-term memory (LSTM networks. First, LSTM networks are trained by historical SITS. The trained LSTM networks are then used to predict new time series data. Last, the predicted data are compared with real data, and the noticeable deviations reveal disturbances. Experimental results using 16-day compositions of the moderate resolution imaging spectroradiometer (MOD13Q1 illustrate the effectiveness and stability of the proposed approach for online disturbance detection.

  10. Ultrasonographic features of the liver with cystic echinococcosis in sheep

    Science.gov (United States)

    Hussein, Hussein Awad; Elrashidy, Mohammed

    2014-01-01

    Objectives The present study was designed to gain information about the ultrasonographic features of livers with cystic echinococcosis, as well as to evaluate the use of ultrasonography for diagnosis of such disease in sheep. Design This was a retrospective study during the period April 2011 to March 2013. Participants A total of 22 Baladi sheep (aged three to six years) were included in this study. Based on clear hepatic ultrasonographic findings, all animals were classified into two groups: those with hepatic cysts (n=9) and without liver cysts (healthy liver, n=13). Results Biochemically, serum concentrations of γ-glutamyl transferase, aspartate aminotransferase, total bilirubin and globulins were significantly increased (P<0.01), while albumin was lowered (P<0.01) in sheep with cystic livers. Ultrasonographic findings of diseased sheep livers revealed the presence of rounded, anechoic and unilocular hydatid cysts with ellipse circumference ranged from 6–10 cm. The borders of cysts were mostly well defined. The interior of cysts contained echogenic particulate materials, septations, or fine echoes. At the 10th intercostal space, the ventral margin, size, thickness and angle of livers were higher (P<0.01), while the diameter of portal vein was lower (P<0.01) in sheep with liver cysts than control ones. Furthermore, at the 9th intercostal space, the circumference of the gall bladder was decreased in sheep with hepatic cysts (P<0.01). The sensitivity, specificity, and positive and negative predictive values of ultrasonography for diagnosis of hepatic hydatid cysts were 80 per cent and 100 per cent, and 100 per cent and 83 per cent, respectively. Conclusions Cystic echinococcosis is associated with a number of anatomical alterations in the liver tissues that can be easily recognised by ultrasound. Furthermore, ultrasonography alone or in combination with analysis of biochemical parameters reflecting liver function could be helpful for diagnosis of hepatic

  11. Automated Detection of Fronts using a Deep Learning Convolutional Neural Network

    Science.gov (United States)

    Biard, J. C.; Kunkel, K.; Racah, E.

    2017-12-01

    A deeper understanding of climate model simulations and the future effects of global warming on extreme weather can be attained through direct analyses of the phenomena that produce weather. Such analyses require these phenomena to be identified in automatic, unbiased, and comprehensive ways. Atmospheric fronts are centrally important weather phenomena because of the variety of significant weather events, such as thunderstorms, directly associated with them. In current operational meteorology, fronts are identified and drawn visually based on the approximate spatial coincidence of a number of quasi-linear localized features - a trough (relative minimum) in air pressure in combination with gradients in air temperature and/or humidity and a shift in wind, and are categorized as cold, warm, stationary, or occluded, with each type exhibiting somewhat different characteristics. Fronts are extended in space with one dimension much larger than the other (often represented by complex curved lines), which poses a significant challenge for automated approaches. We addressed this challenge by using a Deep Learning Convolutional Neural Network (CNN) to automatically identify and classify fronts. The CNN was trained using a "truth" dataset of front locations identified by National Weather Service meteorologists as part of operational 3-hourly surface analyses. The input to the CNN is a set of 5 gridded fields of surface atmospheric variables, including 2m temperature, 2m specific humidity, surface pressure, and the two components of the 10m horizontal wind velocity vector at 3-hr resolution. The output is a set of feature maps containing the per - grid cell probabilities for the presence of the 4 front types. The CNN was trained on a subset of the data and then used to produce front probabilities for each 3-hr time snapshot over a 14-year period covering the continental United States and some adjacent areas. The total frequencies of fronts derived from the CNN outputs matches

  12. Biochemical and ultrasonographic predictors of outcome in threatened abortion

    Directory of Open Access Journals (Sweden)

    Ahmed M. Maged

    2013-09-01

    Conclusion: CA125, β HCG and progesterone are good biochemical markers and FHR and CRL are good ultrasonographic markers for the prediction of outcome in women with threatened abortion. FHR at 110 bpm gives the best predictivity followed by serum P at 25 ng/ml, β HCG at 19887 mIU/ml, CA 125 at 80 IU/ml and CRL at 21 mm with the least predictive accuracy among studied markers. Adding serum progesterone to FHR gave a sensitivity and specificity of 100%.

  13. Prenatal color Doppler ultrasonographic diagnosis of fetal tetralogy of Fallot

    International Nuclear Information System (INIS)

    Tan Buqiao

    2009-01-01

    Objective: To investigate the sonographic findings of tetralogy of Fallot in fetuses. Methods: The data of color Doppler ultrasonography and follow-up results of 5 fetal tetralogy of Fallot were analyzed retrospectively, and their abnormal ultrasound imaging characteristic were summarized. Results: Two cases were proved tetralogy of Fallot by autopsy, and three cases were confirmed to be tetralogy of Fallot by echocardiography after birth. The image features were the main aorta situated above the ventricular septal defect, pulmonary stenosis, no obvious thickening of the right wall. Conclusion: Fetal tetralogy of Fallot have characteristic ultrasound images, prenatal color Doppler ultrasonographic can diagnoses fetal tetralogy of Fallot correctly and has important clinical value. (authors)

  14. Ultrasonographic features of prenatal testicular torsion: Case report

    Directory of Open Access Journals (Sweden)

    Elif Ağaçayak

    2013-01-01

    Full Text Available Although prenatal testicular torsion (PNTT is rarely observed,it is an important condition that can cause bilateralvanishing testis. Generally, PNTT cases observed asextravaginal torsion and treatment is emergency surgicalop-eration. In this article, 39 week presented a case diagnosedin the prenatal testicular torsion. PNTT diagnosiswas confirmed by Doppler ultrasonography and emergencysurgery was performed. Extravaginal left testiculartorsion gangrene and necrosis of the testis was observedin the operation. Left orchiectomy was performed andintrauter-ine ultrasonographic diagnosis was found to becorrect.Key words: Testicular torsion, prenatal diagnosis, features,ultrasonography

  15. AUTOMATED DETECTION OF MITOTIC FIGURES IN BREAST CANCER HISTOPATHOLOGY IMAGES USING GABOR FEATURES AND DEEP NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Maqlin Paramanandam

    2016-11-01

    Full Text Available The count of mitotic figures in Breast cancer histopathology slides is the most significant independent prognostic factor enabling determination of the proliferative activity of the tumor. In spite of the strict protocols followed, the mitotic counting activity suffers from subjectivity and considerable amount of observer variability despite being a laborious task. Interest in automated detection of mitotic figures has been rekindled with the advent of Whole Slide Scanners. Subsequently mitotic detection grand challenge contests have been held in recent years and several research methodologies developed by their participants. This paper proposes an efficient mitotic detection methodology for Hematoxylin and Eosin stained Breast cancer Histopathology Images using Gabor features and a Deep Belief Network- Deep Neural Network architecture (DBN-DNN. The proposed method has been evaluated on breast histopathology images from the publicly available dataset from MITOS contest held at the ICPR 2012 conference. It contains 226 mitoses annotated on 35 HPFs by several pathologists and 15 testing HPFs, yielding an F-measure of 0.74. In addition the said methodology was also tested on 3 slides from the MITOSIS- ATYPIA grand challenge held at the ICPR 2014 conference, an extension of MITOS containing 749 mitoses annotated on 1200 HPFs, by pathologists worldwide. This study has employed 3 slides (294 HPFs from the MITOS-ATYPIA training dataset in its evaluation and the results showed F-measures 0.65, 0.72and 0.74 for each slide. The proposed method is fast and computationally simple yet its accuracy and specificity is comparable to the best winning methods of the aforementioned grand challenges

  16. A novel framework for intelligent signal detection via artificial neural networks for cyclic voltammetry in pyroprocessing technology

    International Nuclear Information System (INIS)

    Rakhshan Pouri, Samaneh; Manic, Milos; Phongikaroon, Supathorn

    2018-01-01

    Highlights: •First time ANN implementation toward pyroprocessing safeguards. •Real time monitoring in terms of intelligent materials detection and accountability. •CV simulation via ANN showing a high accuracy of prediction for the unseen situation. •Elimination of trial and error approach to avoid overfitting in learning. -- Abstract: Electrorefiner (ER) is the heart of pyroprocessing technology which contains different fission, rare-earth, and transuranic chloride compositions during the operation. This is still a developing technology that needs to be advanced for the commercial reprocessing design of used nuclear fuel (UNF) in terms of intelligent materials detection and accountability towards safeguards. A novel signal detection, artificial neural network (ANN), has been proposed in this study to apply on massive ER systemic parameters to simulate cyclic voltammetry (CV) graphs for the unseen situation. ANN could be trained to mimic the system by driving the data sets interrelation between variables to provide current and potential simulated data sets with a high accuracy of prediction. For this purpose, over 230,000 experimental data points reported in literature have been explored—0.5–5 wt% of zirconium chloride (ZrCl 4 ) in LiCl-KCl molten salt with different scan rates at 773 K. This study has illustrated a new framework of ANN implementation to eliminate trial and error approach by comparing the average error of one to three hidden layers with different number of neurons. In addition, this framework results in finding a preferable balance between underfitting and overfitting in deep learning. Furthermore, simulated CV graphs were compared with the experimental data and illustrated a reasonable prediction. The results reveal two structures with three hidden layers providing a good prediction with a low average error. The outcomes indicate that ANN has a strong potential in applying toward safeguards for pyroprocessing technology.

  17. Selection of an optimal neural network architecture for computer-aided detection of microcalcifications - Comparison of automated optimization techniques

    International Nuclear Information System (INIS)

    Gurcan, Metin N.; Sahiner, Berkman; Chan Heangping; Hadjiiski, Lubomir; Petrick, Nicholas

    2001-01-01

    Many computer-aided diagnosis (CAD) systems use neural networks (NNs) for either detection or classification of abnormalities. Currently, most NNs are 'optimized' by manual search in a very limited parameter space. In this work, we evaluated the use of automated optimization methods for selecting an optimal convolution neural network (CNN) architecture. Three automated methods, the steepest descent (SD), the simulated annealing (SA), and the genetic algorithm (GA), were compared. We used as an example the CNN that classifies true and false microcalcifications detected on digitized mammograms by a prescreening algorithm. Four parameters of the CNN architecture were considered for optimization, the numbers of node groups and the filter kernel sizes in the first and second hidden layers, resulting in a search space of 432 possible architectures. The area A z under the receiver operating characteristic (ROC) curve was used to design a cost function. The SA experiments were conducted with four different annealing schedules. Three different parent selection methods were compared for the GA experiments. An available data set was split into two groups with approximately equal number of samples. By using the two groups alternately for training and testing, two different cost surfaces were evaluated. For the first cost surface, the SD method was trapped in a local minimum 91% (392/432) of the time. The SA using the Boltzman schedule selected the best architecture after evaluating, on average, 167 architectures. The GA achieved its best performance with linearly scaled roulette-wheel parent selection; however, it evaluated 391 different architectures, on average, to find the best one. The second cost surface contained no local minimum. For this surface, a simple SD algorithm could quickly find the global minimum, but the SA with the very fast reannealing schedule was still the most efficient. The same SA scheme, however, was trapped in a local minimum on the first cost

  18. Model of hierarchical self-organizing neural networks for detecting and classifying diabetic retinopathy

    Directory of Open Access Journals (Sweden)

    Hossein Ghayoumi Zadeh

    2018-04-01

    Conclusion: These days, the cases of diabetes with hypertension are constantly increasing, and one of the main adverse effects of this disease is related to eyes. In this respect, the diagnosis of retinopathy, which is the same as identification of exudates, microanurysm and bleeding, is of particular importance. The results show that the proposed model is able to detect lesions in diabetic retinopathy images and classify them with an acceptable accuracy. In addition, the results suggest that this method has an acceptable performance compared to other methods.

  19. The influence of exercise during growth on ultrasonographic parameters of the superficial digital flexor tendon of young Thoroughbred horses.

    Science.gov (United States)

    Moffat, P A; Firth, E C; Rogers, C W; Smith, R K W; Barneveld, A; Goodship, A E; Kawcak, C E; McIlwraith, C W; van Weeren, P R

    2008-03-01

    Conditioning by early training may influence the composition of certain musculoskeletal tissues, but very few data exist on its effect during growth on tendon structure and function. To investigate whether conditioning exercise in young foals would lead to any ultrasonographically detectable damage to the superficial digital flexor tendon or an increase in cross-sectional area (CSA). Thirty-three Thoroughbred foals reared at pasture were allocated to 2 groups: control (PASTEX) allowed exercise freely at pasture; and CONDEX, also at pasture, began conditioning exercise from mean age 21 days over 1030 m on a purpose-built oval grass track, for 5 days/week until mean age 18 months. Foals were observed daily, and underwent orthopaedic examination monthly. Ultrasonographic images of the superficial digital flexor tendon (SDFT) at the mid-metacarpal level of both forelimbs were obtained in all foals at ages 5, 8, 12, 15 and 18 months. CSA was validated (r(2) = 0.89) by determining CSA from digital photographs of the transected SDFT surface from 12 of the horses necropsied at age 17.1 months. here was no clinical or ultrasonographic evidence of tendonopathy in either group and the greatest increase in mean CSA in both groups occurred between age 5 and 8 months. Across all age categories, there was no significant difference in mean CSA between the left and right limbs, or colts and fillies; there was a trend towards a larger CSA in the CONDEX group (P = 0.058). There was no conclusive evidence for a structural adaptive hypertrophy of the SDFT, probably because the regimen was insufficiently rigorous or because spontaneous pasture exercise may induce maximal development of energy storing tendons. A moderate amount of early conditioning exercise against a background of constant exercise at pasture is not harmful to the development of the flexor tendons.

  20. Entropy-Based Application Layer DDoS Attack Detection Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Khundrakpam Johnson Singh

    2016-10-01

    Full Text Available Distributed denial-of-service (DDoS attack is one of the major threats to the web server. The rapid increase of DDoS attacks on the Internet has clearly pointed out the limitations in current intrusion detection systems or intrusion prevention systems (IDS/IPS, mostly caused by application-layer DDoS attacks. Within this context, the objective of the paper is to detect a DDoS attack using a multilayer perceptron (MLP classification algorithm with genetic algorithm (GA as learning algorithm. In this work, we analyzed the standard EPA-HTTP (environmental protection agency-hypertext transfer protocol dataset and selected the parameters that will be used as input to the classifier model for differentiating the attack from normal profile. The parameters selected are the HTTP GET request count, entropy, and variance for every connection. The proposed model can provide a better accuracy of 98.31%, sensitivity of 0.9962, and specificity of 0.0561 when compared to other traditional classification models.

  1. Neural Networks

    International Nuclear Information System (INIS)

    Smith, Patrick I.

    2003-01-01

    Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

  2. Musculoskeletal ultrasound including definitions for ultrasonographic pathology

    DEFF Research Database (Denmark)

    Wakefield, RJ; Balint, PV; Szkudlarek, Marcin

    2005-01-01

    Ultrasound (US) has great potential as an outcome in rheumatoid arthritis trials for detecting bone erosions, synovitis, tendon disease, and enthesopathy. It has a number of distinct advantages over magnetic resonance imaging, including good patient tolerability and ability to scan multiple joints...... in a short period of time. However, there are scarce data regarding its validity, reproducibility, and responsiveness to change, making interpretation and comparison of studies difficult. In particular, there are limited data describing standardized scanning methodology and standardized definitions of US...... pathologies. This article presents the first report from the OMERACT ultrasound special interest group, which has compared US against the criteria of the OMERACT filter. Also proposed for the first time are consensus US definitions for common pathological lesions seen in patients with inflammatory arthritis....

  3. Ultrasonographic classification of Atypical hepatic hemangiomas

    International Nuclear Information System (INIS)

    Bae, Sang Jin; Kim, Pyo Nyun; Ha, Hyun Kwon; Lee, Moon Gyu; Auh, Yong Ho; Yoon, Kwon Ha

    2000-01-01

    Cavernous hemangioma is the most common benign hepatic tumor. Typically, the most common features revealed by ultrasound (US) include its small size (4 cm or less in diameter), uniform hyperechogenicity, well defined margins, position in the subcapsular region of the right lobe of the liver, and some posterior echo enhancement. In addition, follow-up scanning may reveal changes in size, though this is rare. The US findings of hepatic hemangiomas may vary, however, especially when lesions are large and/or multiple. For that reason, differential diagnosis between this condition and hepatocellular carcinomas, metastatic lesions, lymphomas and other tumors is difficult. An understanding of the various sonographic findings of hepatic hemangioma can facilitate the early detection of the condition. (author)

  4. Clinical and ultrasonographic results of ultrasonographically guided percutaneous radiofrequency lesioning in the treatment of recalcitrant lateral epicondylitis.

    Science.gov (United States)

    Lin, Cheng-Li; Lee, Jung-Shun; Su, Wei-Ren; Kuo, Li-Chieh; Tai, Ta-Wei; Jou, I-Ming

    2011-11-01

    In patients with lateral epicondylitis recalcitrant to nonsurgical treatments, surgical intervention is considered. Despite the numerous therapies reported, the current trend of treatment places particular emphasis on minimally invasive techniques. The authors present a newly developed minimally invasive procedure, ultrasonographically guided percutaneous radiofrequency thermal lesioning (RTL), and its clinical efficacy in treating recalcitrant lateral epicondylitis. Level of evidence, 4. Thirty-four patients (35 elbows), with a mean age of 52.1 years (range, 35-65 years), suffered from symptomatic lateral epicondylitis for more than 6 months and had exhausted nonoperative therapies. They were treated with ultrasonographically guided RTL. Patients were followed up at least 6 months by physical examination and 12 months by interview. The intensity of pain was recorded with a visual analog scale (VAS) score. The functional outcome was evaluated using grip strength, the upper limb Disability of Arm, Shoulder and Hand (QuickDASH) outcome measure, and the Modified Mayo Clinic Performance Index (MMCPI) for the elbow. The ultrasonographic findings regarding the extensor tendon origin were recorded, as were the complications. At the time of the 6-month follow-up, the average VAS score in resting (from 4.9 to 0.9), palpation (from 7.6 to 2.5), and grip (from 8.2 to 2.9) had improved significantly compared with the preoperative condition (P lateral epicondylitis was found to be a minimally invasive treatment with satisfactory results in this pilot investigation. This innovative method can be considered as an alternative treatment of recalcitrant lateral epicondylitis before further surgical intervention.

  5. A study on the cholecystolcholagiographic and ultrasonographic findings of biliary disease

    International Nuclear Information System (INIS)

    Shin, Kyoung Ja; Bang, Dae Hong; Lee, Sang Chun; Kim, Jae Seop

    1983-01-01

    In the 88 cases of biliary disease, which was proven in Seoul Red Cross Hospital from Jan, 1980 to Dec. 1981, comparative studies were made with oral and IV cholecystocholangiographic findings and ultrasonographic findings. The results were: 1. In the 18 cases of GB stones, there are 17 cases (94.4%) of positive findings in cholecysto-cholangiography with detection of stone in 7 cases (38.9%), while in sonographic study, 16 cases (88.9%) are shown positive findings with detection of stone in 11 cases (61.1%). 2. In the 17 cases of acalculous cholecystitis, the diagnostic accuracy is 88.2% in cholecystocholangiography and 64.7% in sonography. 3. In the 7 cases of CBD stones, all cases are shown positive findings in cholecystocholangiography with detection of stone in only one case (14.3%), while 6 cases (85.7%) of positive findings are shown in sonography with detection of stone in all cases. 4. I.V. cholangiography is more accurate diagnostic procedure rather than oral GB study in the cases of poor or non-functioning GB. 5. Sonography is the choice of procedure in the diagnosis of stones, while in the cases of cholecystitis, cholecystocholangiography is more useful diagnostic procedure

  6. Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection.

    Science.gov (United States)

    Wahab, Noorul; Khan, Asifullah; Lee, Yeon Soo

    2017-06-01

    Different types of breast cancer are affecting lives of women across the world. Common types include Ductal carcinoma in situ (DCIS), Invasive ductal carcinoma (IDC), Tubular carcinoma, Medullary carcinoma, and Invasive lobular carcinoma (ILC). While detecting cancer, one important factor is mitotic count - showing how rapidly the cells are dividing. But the class imbalance problem, due to the small number of mitotic nuclei in comparison to the overwhelming number of non-mitotic nuclei, affects the performance of classification models. This work presents a two-phase model to mitigate the class biasness issue while classifying mitotic and non-mitotic nuclei in breast cancer histopathology images through a deep convolutional neural network (CNN). First, nuclei are segmented out using blue ratio and global binary thresholding. In Phase-1 a CNN is then trained on the segmented out 80×80 pixel patches based on a standard dataset. Hard non-mitotic examples are identified and augmented; mitotic examples are oversampled by rotation and flipping; whereas non-mitotic examples are undersampled by blue ratio histogram based k-means clustering. Based on this information from Phase-1, the dataset is modified for Phase-2 in order to reduce the effects of class imbalance. The proposed CNN architecture and data balancing technique yielded an F-measure of 0.79, and outperformed all the methods relying on specific handcrafted features, as well as those using a combination of handcrafted and CNN-generated features. Copyright © 2017 Elsevier Ltd. All rights reserved.

  7. Object-Oriented Analysis of Satellite Images Using Artificial Neural Networks for Post-Earthquake Buildings Change Detection

    Science.gov (United States)

    Khodaverdi zahraee, N.; Rastiveis, H.

    2017-09-01

    Earthquake is one of the most divesting natural events that threaten human life during history. After the earthquake, having information about the damaged area, the amount and type of damage can be a great help in the relief and reconstruction for disaster managers. It is very important that these measures should be taken immediately after the earthquake because any negligence could be more criminal losses. The purpose of this paper is to propose and implement an automatic approach for mapping destructed buildings after an earthquake using pre- and post-event high resolution satellite images. In the proposed method after preprocessing, segmentation of both images is performed using multi-resolution segmentation technique. Then, the segmentation results are intersected with ArcGIS to obtain equal image objects on both images. After that, appropriate textural features, which make a better difference between changed or unchanged areas, are calculated for all the image objects. Finally, subtracting the extracted textural features from pre- and post-event images, obtained values are applied as an input feature vector in an artificial neural network for classifying the area into two classes of changed and unchanged areas. The proposed method was evaluated using WorldView2 satellite images, acquired before and after the 2010 Haiti earthquake. The reported overall accuracy of 93% proved the ability of the proposed method for post-earthquake buildings change detection.

  8. Detecting tactical patterns in basketball: comparison of merge self-organising maps and dynamic controlled neural networks.

    Science.gov (United States)

    Kempe, Matthias; Grunz, Andreas; Memmert, Daniel

    2015-01-01

    The soaring amount of data, especially spatial-temporal data, recorded in recent years demands for advanced analysis methods. Neural networks derived from self-organizing maps established themselves as a useful tool to analyse static and temporal data. In this study, we applied the merge self-organising map (MSOM) to spatio-temporal data. To do so, we investigated the ability of MSOM's to analyse spatio-temporal data and compared its performance to the common dynamical controlled network (DyCoN) approach to analyse team sport position data. The position data of 10 players were recorded via the Ubisense tracking system during a basketball game. Furthermore, three different pre-selected plays were recorded for classification. Following data preparation, the different nets were trained with the data of the first half. The training success of both networks was evaluated by achieved entropy. The second half of the basketball game was presented to both nets for automatic classification. Both approaches were able to present the trained data extremely well and to detect the pre-selected plays correctly. In conclusion, MSOMs are a useful tool to analyse spatial-temporal data, especially in team sports. By their direct inclusion of different time length of tactical patterns, they open up new opportunities within team sports.

  9. Rapid broad area search and detection of Chinese surface-to-air missile sites using deep convolutional neural networks

    Science.gov (United States)

    Marcum, Richard A.; Davis, Curt H.; Scott, Grant J.; Nivin, Tyler W.

    2017-10-01

    We evaluated how deep convolutional neural networks (DCNN) could assist in the labor-intensive process of human visual searches for objects of interest in high-resolution imagery over large areas of the Earth's surface. Various DCNN were trained and tested using fewer than 100 positive training examples (China only) from a worldwide surface-to-air-missile (SAM) site dataset. A ResNet-101 DCNN achieved a 98.2% average accuracy for the China SAM site data. The ResNet-101 DCNN was used to process ˜19.6 M image chips over a large study area in southeastern China. DCNN chip detections (˜9300) were postprocessed with a spatial clustering algorithm to produce a ranked list of ˜2100 candidate SAM site locations. The combination of DCNN processing and spatial clustering effectively reduced the search area by ˜660X (0.15% of the DCNN-processed land area). An efficient web interface was used to facilitate a rapid serial human review of the candidate SAM sites in the China study area. Four novice imagery analysts with no prior imagery analysis experience were able to complete a DCNN-assisted SAM site search in an average time of ˜42 min. This search was ˜81X faster than a traditional visual search over an equivalent land area of ˜88,640 km2 while achieving nearly identical statistical accuracy (˜90% F1).

  10. Hydrogen Detection With a Gas Sensor Array – Processing and Recognition of Dynamic Responses Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Gwiżdż Patryk

    2015-03-01

    Full Text Available An array consisting of four commercial gas sensors with target specifications for hydrocarbons, ammonia, alcohol, explosive gases has been constructed and tested. The sensors in the array operate in the dynamic mode upon the temperature modulation from 350°C to 500°C. Changes in the sensor operating temperature lead to distinct resistance responses affected by the gas type, its concentration and the humidity level. The measurements are performed upon various hydrogen (17-3000 ppm, methane (167-3000 ppm and propane (167-3000 ppm concentrations at relative humidity levels of 0-75%RH. The measured dynamic response signals are further processed with the Discrete Fourier Transform. Absolute values of the dc component and the first five harmonics of each sensor are analysed by a feed-forward back-propagation neural network. The ultimate aim of this research is to achieve a reliable hydrogen detection despite an interference of the humidity and residual gases.

  11. Infrared differential-absorption Mueller matrix spectroscopy and neural network-based data fusion for biological aerosol standoff detection.

    Science.gov (United States)

    Carrieri, Arthur H; Copper, Jack; Owens, David J; Roese, Erik S; Bottiger, Jerold R; Everly, Robert D; Hung, Kevin C

    2010-01-20

    An active spectrophotopolarimeter sensor and support system were developed for a military/civilian defense feasibility study concerning the identification and standoff detection of biological aerosols. Plumes of warfare agent surrogates gamma-irradiated Bacillus subtilis and chicken egg white albumen (analytes), Arizona road dust (terrestrial interferent), water mist (atmospheric interferent), and talcum powders (experiment controls) were dispersed inside windowless chambers and interrogated by multiple CO(2) laser beams spanning 9.1-12.0 microm wavelengths (lambda). Molecular vibration and vibration-rotation activities by the subject analyte are fundamentally strong within this "fingerprint" middle infrared spectral region. Distinct polarization-modulations of incident irradiance and backscatter radiance of tuned beams generate the Mueller matrix (M) of subject aerosol. Strings of all 15 normalized elements {M(ij)(lambda)/M(11)(lambda)}, which completely describe physical and geometric attributes of the aerosol particles, are input fields for training hybrid Kohonen self-organizing map feed-forward artificial neural networks (ANNs). The properly trained and validated ANN model performs pattern recognition and type-classification tasks via internal mappings. A typical ANN that mathematically clusters analyte, interferent, and control aerosols with nil overlap of species is illustrated, including sensitivity analysis of performance.

  12. Detection of Dendritic Spines Using Wavelet-Based Conditional Symmetric Analysis and Regularized Morphological Shared-Weight Neural Networks

    Directory of Open Access Journals (Sweden)

    Shuihua Wang

    2015-01-01

    Full Text Available Identification and detection of dendritic spines in neuron images are of high interest in diagnosis and treatment of neurological and psychiatric disorders (e.g., Alzheimer’s disease, Parkinson’s diseases, and autism. In this paper, we have proposed a novel automatic approach using wavelet-based conditional symmetric analysis and regularized morphological shared-weight neural networks (RMSNN for dendritic spine identification involving the following steps: backbone extraction, localization of dendritic spines, and classification. First, a new algorithm based on wavelet transform and conditional symmetric analysis has been developed to extract backbone and locate the dendrite boundary. Then, the RMSNN has been proposed to classify the spines into three predefined categories (mushroom, thin, and stubby. We have compared our proposed approach against the existing methods. The experimental result demonstrates that the proposed approach can accurately locate the dendrite and accurately classify the spines into three categories with the accuracy of 99.1% for “mushroom” spines, 97.6% for “stubby” spines, and 98.6% for “thin” spines.

  13. Abdominal ultrasonographic manifestation of Henoch-schonlein purpura

    International Nuclear Information System (INIS)

    Eun, Hyo Won; Kim, Mi Sung; Kang, Beoung Chul; Lee, Sun Wha

    1998-01-01

    The purpose of this study was to describe the ultrasonographic features and assess the diagnostic value of sonography in the evaluation of children with Henoch-Schonlein purpura. Between October 1993, and Febuary 1998, 67 children with Henoch-Schonlein purpura underwent abdominal ultrasonography, which in 13 was used for follow up. Bowel wall thickness and location, pattern of color Doppler signal in the thickened bowel wall, the size and location of enlarged mesenteric lymph node and the presence of ascites were evaluated. In 42 cases(63%), sonographic findings were positive, and indicated mesenteric lymphadenopathy(n=3D21), small bowel wall thickening(n=3D20), and ascites(n=3D17). Thickened bowels were demonstrated at the ileum in 11 cases, the jejunum in five, the duodenum in one, and combined wall thickening at the duodenum and jejunum in two;thickening of the duodenum and ileum was seen in one case. Thickness varied from 3 to 10 mm(mean:6.5 mm). On follow-up sonography, regression of bowel wall thickening was observed earlier than that of mesenteric lymphadenopathy or ascites, and correlated well with improved abdominal symptoms. Abdominal ultrasonographic manifestations of Henoch-Schonlein purpura were bowel wall thickening, mesentric lymphadenopathy and ascites. Sonography was a simple and useful method for the evaluation of gastrointestinal manifestation of Henoch-Schonlein purpura.=20

  14. [Ultrasonographic Findings of Cervical Lymphadenopathy with Infectious Mononucleosis].

    Science.gov (United States)

    Fu, Xian-Shui; Ren, Liu-Qiong; Yang, Li-Juan; Lü, Ke; Chen, Yuan-Yuan; Li, Zhen-Cai

    2015-12-01

    To evaluate the high-resolution and color Doppler ultrasonographic (US) characteristics of cervical lymphadenopathy in patients with infectious mononucleosis. High-resolution and color Doppler US were performed in 30 patients aged 2 to 30 years with a total of 59 palpable enlarged cervical lymph nodes due to infectious mononucleosis. The US characteristics of the nodes including shape,echotexture,hilum,border,matting,cystic necrosis,calcification and vascular pattern were assessed. Three patients received cervical lymph nodes biopsies. The common US findings of cervical lymphadenopathy due to infectious mononucleosis were round shape (69.5%),bilateral distribution (96.7%),matting (83.3%) [even bilateral matting (66.6%)],indistinct margin (79.7%),absence of hilum (66.1%),heterogeneous echotecture (61.0%),and central hilar vascular pattern(89.8%). In 2 patients with absence of the echoic hilum,lymph nodes biopsies showed histological features including marked effacement of the normal architecture in the medullary region accompanied by a mixed proliferation of lymphocytes and histiocytes. In all infectious mononucleosis nodes with a hilum,85.0% had heterogeneously hypo/iso-echoic hila and indistinct demarcation to the cortex. One of them underwent lymph node biopsy and histological findings showed obvious dilation of the sinus oidal lumen and proliferation of histiocytes. Although several ultrasonographic characteristics frequently present in the nodes of infectious mononucleosis are not specific,the combination of ultrasound findings may be valuable in differential diagnosis.

  15. Ultrasonographic findings in 14 dogs with ectopic ureter

    International Nuclear Information System (INIS)

    Lamb, C.R.; Gregory, S.P.

    1998-01-01

    To evaluate ultrasonography as an alternative to contrast radiographyfor diagnosis of ectopic ureter in dogs, ultrasonography of the urinary tract was performed prospectively in a series of urinary incontinent dogs anesthetized for contrast radiography, Fourteen dogs had ectopic ureter based ore surgical, necropsy or unequivocal contrast radiographic findings, There were eight females and six males of a variety of breeds; five were Labrador retrievers, Mean (range) age at the time ofdiagnosis was 1.2 (0.2-4) years for females and 3.5 (0.3-5) for males(p < 0.05). Ectopic ureters were unilateral in five dogs (2 left; 3 right) find bilateral in nine dogs. Both ultrasound images and contrastradiographs were positive for 21 (91%) ectopic ureters; the same two ectopic ureters were not defected using either modality, The termination of each of the five normal ureters was visible on ultrasound images; two (40%) were visible on radiographs, Other ultrasonographic findings included dilatation of the ectopic ureter and/or ipsilateral renal pelvis ill ten (43%) instances, evidence of pyelonephritis in two dogs(with enlargement of the contralateral kidney in one dog), and urethral diverticuli in one dog, Ultrasonography is a practical diagnostic Best for ectopic ureter in clogs. In this series these was close correlation between the ultrasonographic and contrast radiographic findings for each ectopic meter, but ultrasonography enabled more accurate determination of normal ureteral anatomy

  16. Detection and on-line prediction of leak magnitude in a gas pipeline using an acoustic method and neural network data processing

    Directory of Open Access Journals (Sweden)

    R. B. Santos

    2014-03-01

    Full Text Available Considering the importance of monitoring pipeline systems, this work presents the development of a technique to detect gas leakage in pipelines, based on an acoustic method, and on-line prediction of leak magnitude using artificial neural networks. On-line audible noises generated by leakage were obtained with a microphone installed in a 60 m long pipeline. The sound noises were decomposed into sounds of different frequencies: 1 kHz, 5 kHz and 9 kHz. The dynamics of these noises in time were used as input to the neural model in order to determine the occurrence and the leak magnitude. The results indicated the great potential of the technique and of the developed neural network models. For all on-line tests, the models showed 100% accuracy in leak detection, except for a small orifice (1 mm under 4 kgf/cm² of nominal pressure. Similarly, the neural network models could adequately predict the magnitude of the leakages.

  17. Ultrasonographic findings in dual kidney transplantation.

    Science.gov (United States)

    Impedovo, Stefano Vittorio; Martino, Pasquale; Palazzo, Silvano; Ditonno, Pasquale; Tedeschi, Michele; Palumbo, Fabrizio; Tafa, Ardit; Matera, Matteo; Selvaggi, Francesco Paolo; Battaglia, Michele

    2012-12-01

    Organ shortage has led to using grafts from expanded criteria donors (ECD). Double kidney transplantation is an accepted strategy to increase the donor pool, using organs from an ECD which are not acceptable for single kidney transplantation (SKT). Aim of this retrospective study was to analyse the role of colour Doppler ultrasound (CDUS) in the diagnosis of major surgical complications in DKT, performed with unilateral or bilateral placement. From 2000 to 2011 we performed 54 DKT. Unilateral placement of both kidneys was done in 26 patients and bilateral DKT in 28, through two separate Gibson incisions (18) or one midline incision (10). Each patient underwent at least 3 CDUS before hospital discharge. The main surgical complications, discovered initially thanks to ultrasound (US), were hydronephrosis from ureteral obstruction, lymphocele and deep venous thrombosis (DVT). Mean follow-up was 42.7 months. Good postoperative renalfunction was demonstrated in 25 patients (46.3%), while delayed graft function occurred in 29 (53.7%). US showed ureteral obstruction requiring surgery in 5 unilateral DKT while no patient subjected to bilateral DKT developed severe hydronephrosis. Lymphoocele, surgically drained, was demonstrated in 6 bilateral DKT with a midline incision, 2 bilateral DKT with two separate incisions and 3 unilateral DKT. CDUS also enabled diagnosis of 2 cases of DVT in ipsilateral DKTs. CDUS provides useful information in patients with DKT, allowing the detection of clinically unsuspected unilateral diseases. US study of our patients demonstrated that unilateral DKTs are more susceptible to the development of DVT and ureteral stricture, while the incidence of voluminous lymphocele is more frequent in bilateral DKT through a single midline incision. In this scenario, all patients undergoing DKT should be carefully monitored by US after surgery.

  18. Ultrasonographic Findings of Mammographic Architectural Distortion

    International Nuclear Information System (INIS)

    Ma, Jeong Hyun; Kang, Bong Joo; Cha, Eun Suk; Hwangbo, Seol; Kim, Hyeon Sook; Park, Chang Suk; Kim, Sung Hun; Choi, Jae Jeong; Chung, Yong An

    2008-01-01

    To review the sonographic findings of various diseases showing architectural distortion depicted under mammography. We collected and reviewed architectural distortions