Differentiating benign from malignant bone tumors using fluid-fluid level features on magnetic resonance imaging

Energy Technology Data Exchange (ETDEWEB)

Yu, Hong; Cui, Jian Ling; Cui, Sheng Jie; Sun, Ying Cal; Cui, Feng Zhen [Dept. of Radiology, The Third Hospital of Hebei Medical University, Hebei Province Biomechanical Key Laborary of Orthopedics, Shijiazhuang, Hebei (China)

2014-12-15

To analyze different fluid-fluid level features between benign and malignant bone tumors on magnetic resonance imaging (MRI). This study was approved by the hospital ethics committee. We retrospectively analyzed 47 patients diagnosed with benign (n = 29) or malignant (n = 18) bone tumors demonstrated by biopsy/surgical resection and who showed the intratumoral fluid-fluid level on pre-surgical MRI. The maximum length of the largest fluid-fluid level and the ratio of the maximum length of the largest fluid-fluid level to the maximum length of a bone tumor in the sagittal plane were investigated for use in distinguishing benign from malignant tumors using the Mann-Whitney U-test and a receiver operating characteristic (ROC) analysis. Fluid-fluid level was categorized by quantity (multiple vs. single fluid-fluid level) and by T1-weighted image signal pattern (high/low, low/high, and undifferentiated), and the findings were compared between the benign and malignant groups using the chi2 test. The ratio of the maximum length of the largest fluid-fluid level to the maximum length of bone tumors in the sagittal plane that allowed statistically significant differentiation between benign and malignant bone tumors had an area under the ROC curve of 0.758 (95% confidence interval, 0.616-0.899). A cutoff value of 41.5% (higher value suggests a benign tumor) had sensitivity of 73% and specificity of 83%. The ratio of the maximum length of the largest fluid-fluid level to the maximum length of a bone tumor in the sagittal plane may be useful to differentiate benign from malignant bone tumors.

Differentiating benign from malignant bone tumors using fluid-fluid level features on magnetic resonance imaging

International Nuclear Information System (INIS)

Yu, Hong; Cui, Jian Ling; Cui, Sheng Jie; Sun, Ying Cal; Cui, Feng Zhen

2014-01-01

To analyze different fluid-fluid level features between benign and malignant bone tumors on magnetic resonance imaging (MRI). This study was approved by the hospital ethics committee. We retrospectively analyzed 47 patients diagnosed with benign (n = 29) or malignant (n = 18) bone tumors demonstrated by biopsy/surgical resection and who showed the intratumoral fluid-fluid level on pre-surgical MRI. The maximum length of the largest fluid-fluid level and the ratio of the maximum length of the largest fluid-fluid level to the maximum length of a bone tumor in the sagittal plane were investigated for use in distinguishing benign from malignant tumors using the Mann-Whitney U-test and a receiver operating characteristic (ROC) analysis. Fluid-fluid level was categorized by quantity (multiple vs. single fluid-fluid level) and by T1-weighted image signal pattern (high/low, low/high, and undifferentiated), and the findings were compared between the benign and malignant groups using the chi2 test. The ratio of the maximum length of the largest fluid-fluid level to the maximum length of bone tumors in the sagittal plane that allowed statistically significant differentiation between benign and malignant bone tumors had an area under the ROC curve of 0.758 (95% confidence interval, 0.616-0.899). A cutoff value of 41.5% (higher value suggests a benign tumor) had sensitivity of 73% and specificity of 83%. The ratio of the maximum length of the largest fluid-fluid level to the maximum length of a bone tumor in the sagittal plane may be useful to differentiate benign from malignant bone tumors.

Differential Diagnosis of Patients with Inconclusive Parkinsonian Features Using [{sup 18}F]FP-CIT PET/CT

Energy Technology Data Exchange (ETDEWEB)

Park, Eunkyung; Hwang, Yu Mi; Lee, Channyoung; Oh, Sun Young; Kim, Young Chul; Choe, Jae Gol; Park, Kun Woo [Korea Univ., Seoul (Korea, Republic of); Kim, Sujin [Seoul National Univ. College of Medicine, Seoul (Korea, Republic of)

2014-06-15

It is often difficult to differentiate parkinsonism, especially when patients show uncertain parkinsonian features. We investigated the usefulness of dopamine transporter (DAT) imaging for the differential diagnosis of inconclusive parkinsonism using [{sup 18}F]FP-CIT PET. Twenty-four patients with inconclusive parkinsonian features at initial clinical evaluation and nine healthy controls were studied. Patients consisted of three subgroups: nine patients whose diagnoses were unclear concerning whether they had idiopathic Parkinson's disease or drug-induced parkinsonism ('PD/DIP'), nine patients who fulfilled neither the diagnostic criteria of PD nor of essential tremor ('PD/ET'), and six patients who were alleged to have either PD or atypical parkinsonian syndrome ('PD/APS'). Brain PET images were obtained 120 min after injection of 185 MBq [{sup 18}F]FP-CIT. Imaging results were quantified and compared with follow-up clinical diagnoses. Overall, 11 of 24 patients demonstrated abnormally decreased DAT availability on the PET scans, whereas 13 were normal. PET results could diagnose PD/DIP and PD/ET patients as having PD in six patients, DIP in seven, and ET in five; however, the diagnoses of all six PD/APS patients remained inconclusive. Among 15 patients who obtained a final follow-up diagnosis, the image-based diagnosis was congruent with the follow-up diagnosis in 11 patients. Four unsolved cases had normal DAT availability, but clinically progressed to PD during the follow-up period. [{sup 18}F]FP-CIT PET imaging is useful in the differential diagnosis of patients with inconclusive parkinsonian features, except in patients who show atypical features or who eventually progress to PD.

Differentiating high-grade from low-grade chondrosarcoma with MR imaging

Energy Technology Data Exchange (ETDEWEB)

Yoo, Hye Jin; Hong, Sung Hwan; Choi, Ja-Young; Choi, Jung-Ah; Kang, Heung Sik [Seoul National University College of Medicine, Department of Radiology and Institute of Radiation Medicine, Seoul (Korea); Moon, Kyung Chul [Seoul National University College of Medicine, Department of Pathology, Seoul (Korea); Kim, Han-Soo [Seoul National University College of Medicine, Department of Orthopedic Surgery, Seoul (Korea)

2009-12-15

The purpose of the study was to evaluate the MR imaging features that differentiate between low-grade chondrosarcoma (LGCS) and high-grade chondrosarcoma (HGCS) and to determine the most reliable predictors for differentiation. MR images of 42 pathologically proven chondrosarcomas (28 LGCS and 14 HGCS) were retrospectively reviewed. There were 13 male and 29 female patients with an age range of 23-72 years (average age 51 years). On MR images, signal intensity, specific morphological characteristics including entrapped fat, internal lobular architecture, and outer lobular margin, soft tissue mass formation and contrast enhancement pattern were analysed. MR imaging features used to identify LGCS and HGCS were compared using univariate analysis and multivariate stepwise logistic regression analysis. On T1-weighted images, a central area of high signal intensity, which was not seen in LGCS, was frequently observed in HGCS (n = 5, 36%) (p < 0.01). Entrapped fat within the tumour was commonly seen in LGCS (n = 26, 93%), but not in HGCS (n = 1, 4%) (p < 0.01). LGCS more commonly (n = 24, 86%) preserved the characteristic internal lobular structures within the tumour than HGCSs (n = 4, 29%) (p < 0.01). Soft tissue formation was more frequently observed in HGCS (n = 11, 79%) than in LGCS (n = 1, 4%) (p < 0.01). On gadolinium-enhanced images, large central nonenhancing areas were exhibited in only two (7.1%) of LGCS, while HGCS frequently (n = 9, 64%) had a central nonenhancing portion (p < 0.01). Results of multivariate stepwise logistic regression analysis showed that soft tissue formation and entrapped fat within the tumour were the variables that could be used to independently differentiate LGCS from HGCS. There were several MR imaging features of chondrosarcoma that could be helpful in distinguishing HGCS from LGCS. Among them, soft tissue mass formation favoured the diagnosis of HGCS, and entrapped fat within the tumour was highly indicative of LGCS. (orig.)

Differentiating high-grade from low-grade chondrosarcoma with MR imaging

International Nuclear Information System (INIS)

Yoo, Hye Jin; Hong, Sung Hwan; Choi, Ja-Young; Choi, Jung-Ah; Kang, Heung Sik; Moon, Kyung Chul; Kim, Han-Soo

2009-01-01

The purpose of the study was to evaluate the MR imaging features that differentiate between low-grade chondrosarcoma (LGCS) and high-grade chondrosarcoma (HGCS) and to determine the most reliable predictors for differentiation. MR images of 42 pathologically proven chondrosarcomas (28 LGCS and 14 HGCS) were retrospectively reviewed. There were 13 male and 29 female patients with an age range of 23-72 years (average age 51 years). On MR images, signal intensity, specific morphological characteristics including entrapped fat, internal lobular architecture, and outer lobular margin, soft tissue mass formation and contrast enhancement pattern were analysed. MR imaging features used to identify LGCS and HGCS were compared using univariate analysis and multivariate stepwise logistic regression analysis. On T1-weighted images, a central area of high signal intensity, which was not seen in LGCS, was frequently observed in HGCS (n = 5, 36%) (p < 0.01). Entrapped fat within the tumour was commonly seen in LGCS (n = 26, 93%), but not in HGCS (n = 1, 4%) (p < 0.01). LGCS more commonly (n = 24, 86%) preserved the characteristic internal lobular structures within the tumour than HGCSs (n = 4, 29%) (p < 0.01). Soft tissue formation was more frequently observed in HGCS (n = 11, 79%) than in LGCS (n = 1, 4%) (p < 0.01). On gadolinium-enhanced images, large central nonenhancing areas were exhibited in only two (7.1%) of LGCS, while HGCS frequently (n = 9, 64%) had a central nonenhancing portion (p < 0.01). Results of multivariate stepwise logistic regression analysis showed that soft tissue formation and entrapped fat within the tumour were the variables that could be used to independently differentiate LGCS from HGCS. There were several MR imaging features of chondrosarcoma that could be helpful in distinguishing HGCS from LGCS. Among them, soft tissue mass formation favoured the diagnosis of HGCS, and entrapped fat within the tumour was highly indicative of LGCS. (orig.)

Differentiation between malignant and benign thyroid nodules and stratification of papillary thyroid cancer with aggressive histological features: Whole-lesion diffusion-weighted imaging histogram analysis.

Science.gov (United States)

Hao, Yonghong; Pan, Chu; Chen, WeiWei; Li, Tao; Zhu, WenZhen; Qi, JianPin

2016-12-01

To explore the usefulness of whole-lesion histogram analysis of apparent diffusion coefficient (ADC) derived from reduced field-of-view (r-FOV) diffusion-weighted imaging (DWI) in differentiating malignant and benign thyroid nodules and stratifying papillary thyroid cancer (PTC) with aggressive histological features. This Institutional Review Board-approved, retrospective study included 93 patients with 101 pathologically proven thyroid nodules. All patients underwent preoperative r-FOV DWI at 3T. The whole-lesion ADC assessments were performed for each patient. Histogram-derived ADC parameters between different subgroups (pathologic type, extrathyroidal extension, lymph node metastasis) were compared. Receiver operating characteristic curve analysis was used to determine optimal histogram parameters in differentiating benign and malignant nodules and predicting aggressiveness of PTC. Mean ADC, median ADC, 5 th percentile ADC, 25 th percentile ADC, 75 th percentile ADC, 95 th percentile ADC (all P histogram analysis might help to differentiate malignant nodules from benign ones and show the PTCs with extrathyroidal extension. J. Magn. Reson. Imaging 2016;44:1546-1555. © 2016 International Society for Magnetic Resonance in Medicine.

Abdominal tuberculosis: Imaging features

International Nuclear Information System (INIS)

Pereira, Jose M.; Madureira, Antonio J.; Vieira, Alberto; Ramos, Isabel

2005-01-01

Radiological findings of abdominal tuberculosis can mimic those of many different diseases. A high level of suspicion is required, especially in high-risk population. In this article, we will describe barium studies, ultrasound (US) and computed tomography (CT) findings of abdominal tuberculosis (TB), with emphasis in the latest. We will illustrate CT findings that can help in the diagnosis of abdominal tuberculosis and describe imaging features that differentiate it from other inflammatory and neoplastic diseases, particularly lymphoma and Crohn's disease. As tuberculosis can affect any organ in the abdomen, emphasis is placed to ileocecal involvement, lymphadenopathy, peritonitis and solid organ disease (liver, spleen and pancreas). A positive culture or hystologic analysis of biopsy is still required in many patients for definitive diagnosis. Learning objectives:1.To review the relevant pathophysiology of abdominal tuberculosis. 2.Illustrate CT findings that can help in the diagnosis

Textural features for radar image analysis

Science.gov (United States)

Shanmugan, K. S.; Narayanan, V.; Frost, V. S.; Stiles, J. A.; Holtzman, J. C.

1981-01-01

Texture is seen as an important spatial feature useful for identifying objects or regions of interest in an image. While textural features have been widely used in analyzing a variety of photographic images, they have not been used in processing radar images. A procedure for extracting a set of textural features for characterizing small areas in radar images is presented, and it is shown that these features can be used in classifying segments of radar images corresponding to different geological formations.

Saliency image of feature building for image quality assessment

Science.gov (United States)

Ju, Xinuo; Sun, Jiyin; Wang, Peng

2011-11-01

The purpose and method of image quality assessment are quite different for automatic target recognition (ATR) and traditional application. Local invariant feature detectors, mainly including corner detectors, blob detectors and region detectors etc., are widely applied for ATR. A saliency model of feature was proposed to evaluate feasibility of ATR in this paper. The first step consisted of computing the first-order derivatives on horizontal orientation and vertical orientation, and computing DoG maps in different scales respectively. Next, saliency images of feature were built based auto-correlation matrix in different scale. Then, saliency images of feature of different scales amalgamated. Experiment were performed on a large test set, including infrared images and optical images, and the result showed that the salient regions computed by this model were consistent with real feature regions computed by mostly local invariant feature extraction algorithms.

Systematic Review and Meta-Analysis of CT Features for Differentiating Complicated and Uncomplicated Appendicitis.

Science.gov (United States)

Kim, Hae Young; Park, Ji Hoon; Lee, Yoon Jin; Lee, Sung Soo; Jeon, Jong-June; Lee, Kyoung Ho

2018-04-01

Purpose To perform a systematic review and meta-analysis to identify computed tomographic (CT) features for differentiating complicated appendicitis in patients suspected of having appendicitis and to summarize their diagnostic accuracy. Materials and Methods Studies on diagnostic accuracy of CT features for differentiating complicated appendicitis (perforated or gangrenous appendicitis) in patients suspected of having appendicitis were searched in Ovid-MEDLINE, EMBASE, and the Cochrane Library. Overlapping descriptors used in different studies to denote the same image finding were subsumed under a single CT feature. Pooled diagnostic accuracy of the CT features was calculated by using a bivariate random effects model. CT features with pooled diagnostic odds ratios with 95% confidence intervals not including 1 were considered as informative. Results Twenty-three studies were included, and 184 overlapping descriptors for various CT findings were subsumed under 14 features. Of these, 10 features were informative for complicated appendicitis. There was a general tendency for these features to show relatively high specificity but low sensitivity. Extraluminal appendicolith, abscess, appendiceal wall enhancement defect, extraluminal air, ileus, periappendiceal fluid collection, ascites, intraluminal air, and intraluminal appendicolith showed pooled specificity greater than 70% (range, 74%-100%), but sensitivity was limited (range, 14%-59%). Periappendiceal fat stranding was the only feature that showed high sensitivity (94%; 95% confidence interval: 86%, 98%) but low specificity (40%; 95% confidence interval, 23%, 60%). Conclusion Ten informative CT features for differentiating complicated appendicitis were identified in this study, nine of which showed high specificity, but low sensitivity. © RSNA, 2017 Online supplemental material is available for this article.

The ship edge feature detection based on high and low threshold for remote sensing image

Science.gov (United States)

Li, Xuan; Li, Shengyang

2018-05-01

In this paper, a method based on high and low threshold is proposed to detect the ship edge feature due to the low accuracy rate caused by the noise. Analyze the relationship between human vision system and the target features, and to determine the ship target by detecting the edge feature. Firstly, using the second-order differential method to enhance the quality of image; Secondly, to improvement the edge operator, we introduction of high and low threshold contrast to enhancement image edge and non-edge points, and the edge as the foreground image, non-edge as a background image using image segmentation to achieve edge detection, and remove the false edges; Finally, the edge features are described based on the result of edge features detection, and determine the ship target. The experimental results show that the proposed method can effectively reduce the number of false edges in edge detection, and has the high accuracy of remote sensing ship edge detection.

Abdominal tuberculosis: Imaging features

Energy Technology Data Exchange (ETDEWEB)

Pereira, Jose M. [Department of Radiology, Hospital de S. Joao, Porto (Portugal)]. E-mail: jmpjesus@yahoo.com; Madureira, Antonio J. [Department of Radiology, Hospital de S. Joao, Porto (Portugal); Vieira, Alberto [Department of Radiology, Hospital de S. Joao, Porto (Portugal); Ramos, Isabel [Department of Radiology, Hospital de S. Joao, Porto (Portugal)

2005-08-01

Radiological findings of abdominal tuberculosis can mimic those of many different diseases. A high level of suspicion is required, especially in high-risk population. In this article, we will describe barium studies, ultrasound (US) and computed tomography (CT) findings of abdominal tuberculosis (TB), with emphasis in the latest. We will illustrate CT findings that can help in the diagnosis of abdominal tuberculosis and describe imaging features that differentiate it from other inflammatory and neoplastic diseases, particularly lymphoma and Crohn's disease. As tuberculosis can affect any organ in the abdomen, emphasis is placed to ileocecal involvement, lymphadenopathy, peritonitis and solid organ disease (liver, spleen and pancreas). A positive culture or hystologic analysis of biopsy is still required in many patients for definitive diagnosis. Learning objectives:1.To review the relevant pathophysiology of abdominal tuberculosis. 2.Illustrate CT findings that can help in the diagnosis.

Differential magnetic force microscope imaging.

Science.gov (United States)

Wang, Ying; Wang, Zuobin; Liu, Jinyun; Hou, Liwei

2015-01-01

This paper presents a method for differential magnetic force microscope imaging based on a two-pass scanning procedure to extract differential magnetic forces and eliminate or significantly reduce background forces with reversed tip magnetization. In the work, the difference of two scanned images with reversed tip magnetization was used to express the local magnetic forces. The magnetic sample was first scanned with a low lift distance between the MFM tip and the sample surface, and the magnetization direction of the probe was then changed after the first scan to perform the second scan. The differential magnetic force image was obtained through the subtraction of the two images from the two scans. The theoretical and experimental results have shown that the proposed method for differential magnetic force microscope imaging is able to reduce the effect of background or environment interference forces, and offers an improved image contrast and signal to noise ratio (SNR). © Wiley Periodicals, Inc.

Remote Sensing Image Registration Using Multiple Image Features

Directory of Open Access Journals (Sweden)

Kun Yang

2017-06-01

Full Text Available Remote sensing image registration plays an important role in military and civilian fields, such as natural disaster damage assessment, military damage assessment and ground targets identification, etc. However, due to the ground relief variations and imaging viewpoint changes, non-rigid geometric distortion occurs between remote sensing images with different viewpoint, which further increases the difficulty of remote sensing image registration. To address the problem, we propose a multi-viewpoint remote sensing image registration method which contains the following contributions. (i A multiple features based finite mixture model is constructed for dealing with different types of image features. (ii Three features are combined and substituted into the mixture model to form a feature complementation, i.e., the Euclidean distance and shape context are used to measure the similarity of geometric structure, and the SIFT (scale-invariant feature transform distance which is endowed with the intensity information is used to measure the scale space extrema. (iii To prevent the ill-posed problem, a geometric constraint term is introduced into the L2E-based energy function for better behaving the non-rigid transformation. We evaluated the performances of the proposed method by three series of remote sensing images obtained from the unmanned aerial vehicle (UAV and Google Earth, and compared with five state-of-the-art methods where our method shows the best alignments in most cases.

Clinical features and 123I-FP-CIT SPECT imaging in drug-induced parkinsonism and Parkinson's disease

International Nuclear Information System (INIS)

Diaz-Corrales, Francisco J.; Escobar-Delgado, Teresa; Sanz-Viedma, Salome; Garcia-Solis, David; Mir, Pablo

2010-01-01

To determine clinical predictors and accuracy of 123 I-FP-CIT SPECT imaging in the differentiation of drug-induced parkinsonism (DIP) and Parkinson's disease (PD). Several clinical features and 123 I-FP-CIT SPECT images in 32 patients with DIP, 25 patients with PD unmasked by antidopaminergic drugs (PDu) and 22 patients with PD without a previous history of antidopaminergic treatment (PDc) were retrospectively evaluated. DIP and PD shared all clinical features except symmetry of parkinsonian signs which was more frequently observed in patients with DIP (46.9%) than in patients with PDu (16.0%, p 123 I-FP-CIT SPECT images were normal in 29 patients with DIP (90.6%) and abnormal in all patients with PD, and this imaging technique showed high levels of accuracy. DIP and PD are difficult to differentiate based on clinical signs. The precision of clinical diagnosis could be reliably enhanced by 123 I-FP-CIT SPECT imaging. (orig.)

Ewing sarcoma versus osteomyelitis: differential diagnosis with magnetic resonance imaging

International Nuclear Information System (INIS)

Henninger, B.; Glodny, B.; Rudisch, A.; Trieb, T.; Loizides, A.; Judmaier, W.; Schocke, M.F.; Putzer, D.

2013-01-01

To find and evaluate characteristic magnetic resonance imaging (MRI) patterns for the differentiation between Ewing sarcoma and osteomyelitis. We identified 28 consecutive patients referred to our department for MRI (1.5 T) of an unclear bone lesion with clinical symptoms suggestive of Ewing sarcoma or osteomyelitis. MRI scans were re-evaluated by two experienced radiologists, typical MR imaging features were documented and a diagnostic decision between Ewing sarcoma and osteomyelitis was made. Statistical significance of the association between MRI features and the biopsy-based diagnosis was assessed using Fisher's exact test. The most clear-cut pattern for determining the correct diagnosis was the presence of a sharp and defined margin of the bone lesion, which was found in all patients with Ewing sarcoma, but in none of the patients with osteomyelitis (P < 0.0001). Contrast enhancing soft tissue was present in all cases with Ewing sarcoma and absent in 4 patients with osteomyelitis (P = 0.0103). Cortical destruction was found in all patients with Ewing sarcoma, 4 patients with osteomyelitis did not present any cortical reaction (P = 0.0103). Cystic or necrotic areas were identified in 13 patients with Ewing sarcoma and in 1 patient with osteomyelitis (P = 0.004). Interobserver reliability was very good (kappa = 1) in Ewing sarcoma and moderate (kappa = 0.6) in patients with osteomyelitis. A sharp and defined margin, optimally visualized on T1-weighted images in comparison to short tau inversion recovery (STIR) images, is the most significant feature of Ewing sarcoma in differentiating from osteomyelitis. (orig.)

An efficient approach for differentiating Alzheimer's disease from normal elderly based on multicenter MRI using gray-level invariant features.

Directory of Open Access Journals (Sweden)

Muwei Li

Full Text Available Machine learning techniques, along with imaging markers extracted from structural magnetic resonance images, have been shown to increase the accuracy to differentiate patients with Alzheimer's disease (AD from normal elderly controls. Several forms of anatomical features, such as cortical volume, shape, and thickness, have demonstrated discriminative capability. These approaches rely on accurate non-linear image transformation, which could invite several nuisance factors, such as dependency on transformation parameters and the degree of anatomical abnormality, and an unpredictable influence of residual registration errors. In this study, we tested a simple method to extract disease-related anatomical features, which is suitable for initial stratification of the heterogeneous patient populations often encountered in clinical data. The method employed gray-level invariant features, which were extracted from linearly transformed images, to characterize AD-specific anatomical features. The intensity information from a disease-specific spatial masking, which was linearly registered to each patient, was used to capture the anatomical features. We implemented a two-step feature selection for anatomic recognition. First, a statistic-based feature selection was implemented to extract AD-related anatomical features while excluding non-significant features. Then, seven knowledge-based ROIs were used to capture the local discriminative powers of selected voxels within areas that were sensitive to AD or mild cognitive impairment (MCI. The discriminative capability of the proposed feature was measured by its performance in differentiating AD or MCI from normal elderly controls (NC using a support vector machine. The statistic-based feature selection, together with the knowledge-based masks, provided a promising solution for capturing anatomical features of the brain efficiently. For the analysis of clinical populations, which are inherently heterogeneous

Parametric features of image textures in 18F-FDG PET/CT evaluation of lung nodules

International Nuclear Information System (INIS)

Wang Changmei; Guan Yihui; Zhang Wenqiang; Zuo Chuantao; Hua Fengchun

2013-01-01

Objective: To evaluate the parametric features of image textures on 18 F-FDG PET/CT for the differentiation between malignant and benign pulmonary nodules and compare the diagnostic performance of these parameters with SUV max . Methods: 18 F-FDG PET/CT images of 170 patients (102 males, 68 females, age range: 29-81 (mean 59) years) with pulmonary nodules were retrospectively evaluated. Eighty-nine pulmonary nodules (230 slices) were malignant and 81 (193 slices) were benign. The pulmonary nodules were contoured on CT images and mapped to the co-registered PET images. Thirteen parameters of textural features were extracted and SUV max was measured. Logistic regression analysis was used to identify the significant texture parameters and create a regression model. The efficacy of the textural features and SUV max to distinguish between malignant and benign pulmonary nodules was evaluated by ROC curve analysis. The textural features of squamous cell carcinoma and adenocarcinoma were compared via the Mann-Whitney u test. The sensitivity and specificity of the textural features and SUV max for the differential diagnosis were compared with χ 2 test. Results: Logistic regression model identified 4 textural features (skewness (β=1.7058), kurtosis (β=-1.0989), angular second moment (ASM, 3=-4.4140) and strength (β=0.5626); all P<0.05) to have significant correlation with the malignancy of lung nodules. The AUC of ROC curve was 0.775 (95% CI 0.732-0.819; P<0.001) with the sensitivity of 89.6% (206/230) and specificity of 50.8% (98/193). ASM and strength had statistically significant differences between squamous cell carcinoma and adenocarcinoma [ASM: 0.0303 (95% CI 0.0392-0.0724) vs 0.0594 (95% CI 0.0721-0.0947); strength: 2.4714 (95% CI 2.4632-4.1050) vs 1.5945 (95% CI 1.9003-2.4652); u=3082.0 and 3115.0, both P<0.01]. The AUC of SUV max -based diagnosis was 0.757 (95% CI 0.711-0.802; P<0.001) with the sensitivity of 80.9% (186/230) and specificity of 50.3% (97/193) at

Hemorrhage detection in MRI brain images using images features

Science.gov (United States)

Moraru, Luminita; Moldovanu, Simona; Bibicu, Dorin; Stratulat (Visan), Mirela

2013-11-01

The abnormalities appear frequently on Magnetic Resonance Images (MRI) of brain in elderly patients presenting either stroke or cognitive impairment. Detection of brain hemorrhage lesions in MRI is an important but very time-consuming task. This research aims to develop a method to extract brain tissue features from T2-weighted MR images of the brain using a selection of the most valuable texture features in order to discriminate between normal and affected areas of the brain. Due to textural similarity between normal and affected areas in brain MR images these operation are very challenging. A trauma may cause microstructural changes, which are not necessarily perceptible by visual inspection, but they could be detected by using a texture analysis. The proposed analysis is developed in five steps: i) in the pre-processing step: the de-noising operation is performed using the Daubechies wavelets; ii) the original images were transformed in image features using the first order descriptors; iii) the regions of interest (ROIs) were cropped from images feature following up the axial symmetry properties with respect to the mid - sagittal plan; iv) the variation in the measurement of features was quantified using the two descriptors of the co-occurrence matrix, namely energy and homogeneity; v) finally, the meaningful of the image features is analyzed by using the t-test method. P-value has been applied to the pair of features in order to measure they efficacy.

Analysis of muscle fatigue conditions using time-frequency images and GLCM features

Directory of Open Access Journals (Sweden)

Karthick P.A.

2016-09-01

Full Text Available In this work, an attempt has been made to differentiate muscle non-fatigue and fatigue conditions using sEMG signals and texture representation of the time-frequency images. The sEMG signals are recorded from the biceps brachii muscle of 25 healthy adult volunteers during dynamic fatiguing contraction. The first and last curls of these signals are considered as the non-fatigue and fatigue zones, respectively. These signals are preprocessed and the time-frequency spectrum is computed using short time fourier transform (STFT. Gray-Level Co-occurrence Matrix (GLCM is extracted from low (15–45 Hz, medium (46–95 Hz and high (96–150 Hz frequency bands of the time-frequency images. Further, the features such as contrast, correlation, energy and homogeneity are calculated from the resultant matrices. The results show that the high frequency band based features are able to differentiate non-fatigue and fatigue conditions. The features such as correlation, contrast and homogeneity extracted at angles 0°, 45°, 90°, and 135° are found to be distinct with high statistical significance (p < 0.0001. Hence, this framework can be used for analysis of neuromuscular disorders.

Breast cancer mitosis detection in histopathological images with spatial feature extraction

Science.gov (United States)

Albayrak, Abdülkadir; Bilgin, Gökhan

2013-12-01

In this work, cellular mitosis detection in histopathological images has been investigated. Mitosis detection is very expensive and time consuming process. Development of digital imaging in pathology has enabled reasonable and effective solution to this problem. Segmentation of digital images provides easier analysis of cell structures in histopathological data. To differentiate normal and mitotic cells in histopathological images, feature extraction step is very crucial step for the system accuracy. A mitotic cell has more distinctive textural dissimilarities than the other normal cells. Hence, it is important to incorporate spatial information in feature extraction or in post-processing steps. As a main part of this study, Haralick texture descriptor has been proposed with different spatial window sizes in RGB and La*b* color spaces. So, spatial dependencies of normal and mitotic cellular pixels can be evaluated within different pixel neighborhoods. Extracted features are compared with various sample sizes by Support Vector Machines using k-fold cross validation method. According to the represented results, it has been shown that separation accuracy on mitotic and non-mitotic cellular pixels gets better with the increasing size of spatial window.

Feature-Based Retinal Image Registration Using D-Saddle Feature

Directory of Open Access Journals (Sweden)

Roziana Ramli

2017-01-01

Full Text Available Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%, Harris-PIIFD (4%, H-M (16%, and Saddle (16%. Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

Quantitative imaging features: extension of the oncology medical image database

Science.gov (United States)

Patel, M. N.; Looney, P. T.; Young, K. C.; Halling-Brown, M. D.

2015-03-01

Radiological imaging is fundamental within the healthcare industry and has become routinely adopted for diagnosis, disease monitoring and treatment planning. With the advent of digital imaging modalities and the rapid growth in both diagnostic and therapeutic imaging, the ability to be able to harness this large influx of data is of paramount importance. The Oncology Medical Image Database (OMI-DB) was created to provide a centralized, fully annotated dataset for research. The database contains both processed and unprocessed images, associated data, and annotations and where applicable expert determined ground truths describing features of interest. Medical imaging provides the ability to detect and localize many changes that are important to determine whether a disease is present or a therapy is effective by depicting alterations in anatomic, physiologic, biochemical or molecular processes. Quantitative imaging features are sensitive, specific, accurate and reproducible imaging measures of these changes. Here, we describe an extension to the OMI-DB whereby a range of imaging features and descriptors are pre-calculated using a high throughput approach. The ability to calculate multiple imaging features and data from the acquired images would be valuable and facilitate further research applications investigating detection, prognosis, and classification. The resultant data store contains more than 10 million quantitative features as well as features derived from CAD predictions. Theses data can be used to build predictive models to aid image classification, treatment response assessment as well as to identify prognostic imaging biomarkers.

Rosai-Dorfman Disease with Epidural and Spinal Bone Marrow Involvement: Magnetic Resonance Imaging and Diffusion-Weighted Imaging Features

International Nuclear Information System (INIS)

Oner, A.Y.; Akpek, S.; Tali, T.

2007-01-01

Sinus histiocytosis with massive lymphadenopathy (SHML), or Rosai-Dorfman disease, is a rare histiocytic disorder that typically presents with chronic, self-limiting cervical lymphadenopathy. Although this disease mainly affects histiocytes, there are a few reports of bone marrow infiltration. Diffusion-weighted imaging (DWI) is a promising technology in differentiating between various bone marrow pathologies. We here present conventional magnetic resonance imaging and DWI features of a patient with SHML and bone marrow involvement

Rosai-Dorfman Disease with Epidural and Spinal Bone Marrow Involvement: Magnetic Resonance Imaging and Diffusion-Weighted Imaging Features

Energy Technology Data Exchange (ETDEWEB)

Oner, A.Y.; Akpek, S.; Tali, T. [Dept. of Radiology, Gazi Univ. School of Medicine. Besevler-Ankara (Turkey)

2007-04-15

Sinus histiocytosis with massive lymphadenopathy (SHML), or Rosai-Dorfman disease, is a rare histiocytic disorder that typically presents with chronic, self-limiting cervical lymphadenopathy. Although this disease mainly affects histiocytes, there are a few reports of bone marrow infiltration. Diffusion-weighted imaging (DWI) is a promising technology in differentiating between various bone marrow pathologies. We here present conventional magnetic resonance imaging and DWI features of a patient with SHML and bone marrow involvement.

Image segmentation-based robust feature extraction for color image watermarking

Science.gov (United States)

Li, Mianjie; Deng, Zeyu; Yuan, Xiaochen

2018-04-01

This paper proposes a local digital image watermarking method based on Robust Feature Extraction. The segmentation is achieved by Simple Linear Iterative Clustering (SLIC) based on which an Image Segmentation-based Robust Feature Extraction (ISRFE) method is proposed for feature extraction. Our method can adaptively extract feature regions from the blocks segmented by SLIC. This novel method can extract the most robust feature region in every segmented image. Each feature region is decomposed into low-frequency domain and high-frequency domain by Discrete Cosine Transform (DCT). Watermark images are then embedded into the coefficients in the low-frequency domain. The Distortion-Compensated Dither Modulation (DC-DM) algorithm is chosen as the quantization method for embedding. The experimental results indicate that the method has good performance under various attacks. Furthermore, the proposed method can obtain a trade-off between high robustness and good image quality.

Differentiation of Solid Renal Tumors with Multiparametric MR Imaging.

Science.gov (United States)

Lopes Vendrami, Camila; Parada Villavicencio, Carolina; DeJulio, Todd J; Chatterjee, Argha; Casalino, David D; Horowitz, Jeanne M; Oberlin, Daniel T; Yang, Guang-Yu; Nikolaidis, Paul; Miller, Frank H

2017-01-01

Characterization of renal tumors is critical to determine the best therapeutic approach and improve overall patient survival. Because of increased use of high-resolution cross-sectional imaging in clinical practice, renal masses are being discovered with increased frequency. As a result, accurate imaging characterization of these lesions is more important than ever. However, because of the wide array of imaging features encountered as well as overlapping characteristics, identifying reliable imaging criteria for differentiating malignant from benign renal masses remains a challenge. Multiparametric magnetic resonance (MR) imaging based on various anatomic and functional parameters has an important role and adds diagnostic value in detection and characterization of renal masses. MR imaging may allow distinction of benign solid renal masses from several renal cell carcinoma (RCC) subtypes, potentially suggest the histologic grade of a neoplasm, and play an important role in ensuring appropriate patient management to avoid unnecessary surgery or other interventions. It is also a useful noninvasive imaging tool for patients who undergo active surveillance of renal masses and for follow-up after treatment of a renal mass. The purpose of this article is to review the characteristic MR imaging features of RCC and common benign renal masses and propose a diagnostic imaging approach to evaluation of solid renal masses using multiparametric MR imaging. © RSNA, 2017.

INTEGRATION OF IMAGE-DERIVED AND POS-DERIVED FEATURES FOR IMAGE BLUR DETECTION

Directory of Open Access Journals (Sweden)

T.-A. Teo

2016-06-01

Full Text Available The image quality plays an important role for Unmanned Aerial Vehicle (UAV’s applications. The small fixed wings UAV is suffering from the image blur due to the crosswind and the turbulence. Position and Orientation System (POS, which provides the position and orientation information, is installed onto an UAV to enable acquisition of UAV trajectory. It can be used to calculate the positional and angular velocities when the camera shutter is open. This study proposes a POS-assisted method to detect the blur image. The major steps include feature extraction, blur image detection and verification. In feature extraction, this study extracts different features from images and POS. The image-derived features include mean and standard deviation of image gradient. For POS-derived features, we modify the traditional degree-of-linear-blur (blinear method to degree-of-motion-blur (bmotion based on the collinear condition equations and POS parameters. Besides, POS parameters such as positional and angular velocities are also adopted as POS-derived features. In blur detection, this study uses Support Vector Machines (SVM classifier and extracted features (i.e. image information, POS data, blinear and bmotion to separate blur and sharp UAV images. The experiment utilizes SenseFly eBee UAV system. The number of image is 129. In blur image detection, we use the proposed degree-of-motion-blur and other image features to classify the blur image and sharp images. The classification result shows that the overall accuracy using image features is only 56%. The integration of image-derived and POS-derived features have improved the overall accuracy from 56% to 76% in blur detection. Besides, this study indicates that the performance of the proposed degree-of-motion-blur is better than the traditional degree-of-linear-blur.

Wilson’s disease: Atypical imaging features

Directory of Open Access Journals (Sweden)

Venugopalan Y Vishnu

2016-10-01

Full Text Available Wilson’s disease is a genetic movement disorder with characteristic clinical and imaging features. We report a 17- year-old boy who presented with sialorrhea, hypophonic speech, paraparesis with repeated falls and recurrent seizures along with cognitive decline. He had bilateral Kayser Flescher rings. Other than the typical features of Wilson’s disease in cranial MRI, there were extensive white matter signal abnormalities (T2 and FLAIR hyperintensities and gyriform contrast enhancement which are rare imaging features in Wilson's disease. A high index of suspicion is required to diagnose Wilson’s disease when atypical imaging features are present.

Unsupervised feature learning for autonomous rock image classification

Science.gov (United States)

Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

2017-09-01

Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

Infrared image enhancement with learned features

Science.gov (United States)

Fan, Zunlin; Bi, Duyan; Ding, Wenshan

2017-11-01

Due to the variation of imaging environment and limitations of infrared imaging sensors, infrared images usually have some drawbacks: low contrast, few details and indistinct edges. Hence, to promote the applications of infrared imaging technology, it is essential to improve the qualities of infrared images. To enhance image details and edges adaptively, we propose an infrared image enhancement method under the proposed image enhancement scheme. On the one hand, on the assumption of high-quality image taking more evident structure singularities than low-quality images, we propose an image enhancement scheme that depends on the extractions of structure features. On the other hand, different from the current image enhancement algorithms based on deep learning networks that try to train and build the end-to-end mappings on improving image quality, we analyze the significance of first layer in Stacked Sparse Denoising Auto-encoder and propose a novel feature extraction for the proposed image enhancement scheme. Experiment results prove that the novel feature extraction is free from some artifacts on the edges such as blocking artifacts, ;gradient reversal;, and pseudo contours. Compared with other enhancement methods, the proposed method achieves the best performance in infrared image enhancement.

Quantitative phase imaging and differential interference contrast imaging for biological TEM

International Nuclear Information System (INIS)

Allman, B.E.; McMahon, P.J.; Barone-Nugent, E.D.; Nugent, E.D.

2002-01-01

Full text: Phase microscopy is a central technique in science. An experienced microscopist uses this effect to visualise (edge) structure within transparent samples by slightly defocusing the microscope. Although widespread in optical microscopy, phase contrast transmission electron microscopy (TEM) has not been widely adopted. TEM for biological specimens has largely relied on staining techniques to yield sufficient contrast. We show here a simple method for quantitative TEM phase microscopy that quantifies this phase contrast effect. Starting with conventional, digital, bright field images of the sample, our algorithm provides quantitative phase information independent of the sample's bright field intensity image. We present TEM phase images of a range of stained and unstained, biological and material science specimens. This independent phase and intensity information is then used to emulate a range of phase visualisation images familiar to optical microscopy, e.g. differential interference contrast. The phase images contain features not visible with the other imaging modalities. Further, if the TEM samples have been prepared on a microtome to a uniform thickness, the phase information can be converted into refractive index structure of the specimen. Copyright (2002) Australian Society for Electron Microscopy Inc

Imaging features of aggressive angiomyxoma

International Nuclear Information System (INIS)

Jeyadevan, N.N.; Sohaib, S.A.A.; Thomas, J.M.; Jeyarajah, A.; Shepherd, J.H.; Fisher, C.

2003-01-01

AIM: To describe the imaging features of aggressive angiomyxoma in a rare benign mesenchymal tumour most frequently arising from the perineum in young female patients. MATERIALS AND METHODS: We reviewed the computed tomography (CT) and magnetic resonance (MR) imaging features of patients with aggressive angiomyxoma who were referred to our hospital. The imaging features were correlated with clinical information and pathology in all patients. RESULTS: Four CT and five MR studies were available for five patients (all women, mean age 39, range 24-55). Three patients had recurrent tumour at follow-up. CT and MR imaging demonstrated a well-defined mass-displacing adjacent structures. The tumour was of low attenuation relative to muscle on CT. On MR, the tumour was isointense relative to muscle on T1-weighted image, hyperintense on T2-weighted image and enhanced avidly after gadolinium contrast with a characteristic 'swirled' internal pattern. MR imaging demonstrates the extent of the tumour and its relation to the pelvic floor. Recurrent tumour has a similar appearance to the primary lesion. CONCLUSION: The MR appearances of aggressive angiomyxomas are characteristic, and the diagnosis should be considered in any young woman presenting with a well-defined mass arising from the perineum. Jeyadevan, N. N. etal. (2003). Clinical Radiology58, 157--162

Image Processing and Features Extraction of Fingerprint Images ...

African Journals Online (AJOL)

To demonstrate the importance of the image processing of fingerprint images prior to image enrolment or comparison, the set of fingerprint images in databases (a) and (b) of the FVC (Fingerprint Verification Competition) 2000 database were analyzed using a features extraction algorithm. This paper presents the results of ...

Feature hashing for fast image retrieval

Science.gov (United States)

Yan, Lingyu; Fu, Jiarun; Zhang, Hongxin; Yuan, Lu; Xu, Hui

2018-03-01

Currently, researches on content based image retrieval mainly focus on robust feature extraction. However, due to the exponential growth of online images, it is necessary to consider searching among large scale images, which is very timeconsuming and unscalable. Hence, we need to pay much attention to the efficiency of image retrieval. In this paper, we propose a feature hashing method for image retrieval which not only generates compact fingerprint for image representation, but also prevents huge semantic loss during the process of hashing. To generate the fingerprint, an objective function of semantic loss is constructed and minimized, which combine the influence of both the neighborhood structure of feature data and mapping error. Since the machine learning based hashing effectively preserves neighborhood structure of data, it yields visual words with strong discriminability. Furthermore, the generated binary codes leads image representation building to be of low-complexity, making it efficient and scalable to large scale databases. Experimental results show good performance of our approach.

Feature-based Alignment of Volumetric Multi-modal Images

Science.gov (United States)

Toews, Matthew; Zöllei, Lilla; Wells, William M.

2014-01-01

This paper proposes a method for aligning image volumes acquired from different imaging modalities (e.g. MR, CT) based on 3D scale-invariant image features. A novel method for encoding invariant feature geometry and appearance is developed, based on the assumption of locally linear intensity relationships, providing a solution to poor repeatability of feature detection in different image modalities. The encoding method is incorporated into a probabilistic feature-based model for multi-modal image alignment. The model parameters are estimated via a group-wise alignment algorithm, that iteratively alternates between estimating a feature-based model from feature data, then realigning feature data to the model, converging to a stable alignment solution with few pre-processing or pre-alignment requirements. The resulting model can be used to align multi-modal image data with the benefits of invariant feature correspondence: globally optimal solutions, high efficiency and low memory usage. The method is tested on the difficult RIRE data set of CT, T1, T2, PD and MP-RAGE brain images of subjects exhibiting significant inter-subject variability due to pathology. PMID:24683955

Image feature detectors and descriptors foundations and applications

CERN Document Server

Hassaballah, Mahmoud

2016-01-01

This book provides readers with a selection of high-quality chapters that cover both theoretical concepts and practical applications of image feature detectors and descriptors. It serves as reference for researchers and practitioners by featuring survey chapters and research contributions on image feature detectors and descriptors. Additionally, it emphasizes several keywords in both theoretical and practical aspects of image feature extraction. The keywords include acceleration of feature detection and extraction, hardware implantations, image segmentation, evolutionary algorithm, ordinal measures, as well as visual speech recognition. .

What are the differentiating clinical and MRI-features of enchondromas from low-grade chondrosarcomas?

Energy Technology Data Exchange (ETDEWEB)

Douis, Hassan [Royal Orthopaedic Hospital, Department of Radiology, Birmingham (United Kingdom); University Hospital Birmingham, Department of Radiology, Birmingham (United Kingdom); Parry, M. [Royal Orthopaedic Hospital, Department of Orthopaedic Oncology, Birmingham (United Kingdom); Vaiyapuri, S. [Royal Orthopaedic Hospital, Department of Musculoskeletal Pathology, Birmingham (United Kingdom); Davies, A.M. [Royal Orthopaedic Hospital, Department of Radiology, Birmingham (United Kingdom)

2018-01-15

To evaluate the role of clinical assessment, conventional and dynamic contrast-enhanced MRI in differentiating enchondromas from chondrosarcomas of long bone. The following clinical and MRI findings were assessed: age, gender, pain, pain attributable to lesion, tumour location, tumour length, presence, depth of endosteal scalloping, bone marrow oedema, soft tissue oedema, cortical destruction, periosteal reaction, bone expansion, macroscopic fat, calcification, soft tissue mass, haemorrhage, dynamic contrast-enhanced MRI. Clinical and MRI findings were compared with histopathological grading. Sixty patients with central chondroid tumours were included (27 enchondromas, 10 cartilaginous lesions of unknown malignant potential, 15 grade 1 chondrosarcomas, 8 high-grade chondrosarcomas). Pain attributed to lesion, tumour length, endosteal scalloping > 2/3, cortical destruction, bone expansion and soft tissue mass were differentiating features between enchondromas and grade 1 chondrosarcomas. Dynamic contrast-enhanced MRI could not differentiate enchondromas from grade 1 chondrosarcomas. Previously reported imaging signs of chondrosarcomas are useful in the diagnosis of grade 1 lesions but have lower sensitivity than in higher grade lesions. Deep endosteal scalloping is the most sensitive imaging sign of grade 1 chondrosarcomas. Pain due to the lesion is an important clinical sign of grade 1 chondrosarcomas. Dynamic contrast-enhanced MRI is not useful in differentiating enchondromas from grade 1 chondrosarcomas. (orig.)

W-transform method for feature-oriented multiresolution image retrieval

Energy Technology Data Exchange (ETDEWEB)

Kwong, M.K.; Lin, B. [Argonne National Lab., IL (United States). Mathematics and Computer Science Div.

1995-07-01

Image database management is important in the development of multimedia technology. Since an enormous amount of digital images is likely to be generated within the next few decades in order to integrate computers, television, VCR, cables, telephone and various imaging devices. Effective image indexing and retrieval systems are urgently needed so that images can be easily organized, searched, transmitted, and presented. Here, the authors present a local-feature-oriented image indexing and retrieval method based on Kwong, and Tang`s W-transform. Multiresolution histogram comparison is an effective method for content-based image indexing and retrieval. However, most recent approaches perform multiresolution analysis for whole images but do not exploit the local features present in the images. Since W-transform is featured by its ability to handle images of arbitrary size, with no periodicity assumptions, it provides a natural tool for analyzing local image features and building indexing systems based on such features. In this approach, the histograms of the local features of images are used in the indexing, system. The system not only can retrieve images that are similar or identical to the query images but also can retrieve images that contain features specified in the query images, even if the retrieved images as a whole might be very different from the query images. The local-feature-oriented method also provides a speed advantage over the global multiresolution histogram comparison method. The feature-oriented approach is expected to be applicable in managing large-scale image systems such as video databases and medical image databases.

Classification of breast masses in ultrasound images using self-adaptive differential evolution extreme learning machine and rough set feature selection.

Science.gov (United States)

Prabusankarlal, Kadayanallur Mahadevan; Thirumoorthy, Palanisamy; Manavalan, Radhakrishnan

2017-04-01

A method using rough set feature selection and extreme learning machine (ELM) whose learning strategy and hidden node parameters are optimized by self-adaptive differential evolution (SaDE) algorithm for classification of breast masses is investigated. A pathologically proven database of 140 breast ultrasound images, including 80 benign and 60 malignant, is used for this study. A fast nonlocal means algorithm is applied for speckle noise removal, and multiresolution analysis of undecimated discrete wavelet transform is used for accurate segmentation of breast lesions. A total of 34 features, including 29 textural and five morphological, are applied to a [Formula: see text]-fold cross-validation scheme, in which more relevant features are selected by quick-reduct algorithm, and the breast masses are discriminated into benign or malignant using SaDE-ELM classifier. The diagnosis accuracy of the system is assessed using parameters, such as accuracy (Ac), sensitivity (Se), specificity (Sp), positive predictive value (PPV), negative predictive value (NPV), Matthew's correlation coefficient (MCC), and area ([Formula: see text]) under receiver operating characteristics curve. The performance of the proposed system is also compared with other classifiers, such as support vector machine and ELM. The results indicated that the proposed SaDE algorithm has superior performance with [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] compared to other classifiers.

Granulocytic sarcoma presenting with necrotic cervical lymph nodes as an initial manifestation of childhood leukaemia: imaging features

Energy Technology Data Exchange (ETDEWEB)

An, Sang Bu; Cheon, Jung-Eun; Kim, In-One; Kim, Woo Sun [Seoul National University College of Medicine, Department of Radiology, Seoul (Korea); Seoul National University Medical Research Center, Institute of Radiation Medicine, Seoul (Korea); Ahn, Hyo Seop; Shin, Hee Young; Kang, Hyoung Jin; Yeon, Kyung Mo [Seoul National University College of Medicine, Department of Pediatrics, Cancer Research Institute, Seoul (Korea)

2008-06-15

We present two cases of granulocytic sarcoma of the cervical lymph nodes with central necrosis as an initial manifestation of childhood leukaemia, focusing on the imaging features. Recognition of the CT and MR imaging findings of granulocytic sarcoma involving the cervical lymph nodes assists the differential diagnosis of noninfective lymphadenopathy in children. (orig.)

Field application of feature-enhanced imaging

International Nuclear Information System (INIS)

Mucciardi, A.N.

1988-01-01

One of the more challenging ultrasonic inspection problems is bimetallic weld inspection or, in general, dissimilar metal welds. These types of welds involve complicated geometries and various mixtures of materials. Attempts to address this problem with imaging alone have fallen short of desired goals. The probable reason for this is the lack of information supplied by imaging systems, which are limited to amplitude and time displays. Having RF information available for analysis greatly enhances the information obtainable from dissimilar metal welds and, coupled with the spatial map generated by an imaging system, can significantly improve the reliability of dissimilar metal weld inspections. Ultra Image and TestPro are, respectively, an imaging system and a feature-based signal analysis system. The purpose of this project is to integrate these two systems to produce a feature-enhanced imaging system. This means that a software link is established between Ultra Image and the PC-based TestPro system so that the user of the combined system can perform all the usual imaging functions and also have available a wide variety of RF signal analysis functions. The analysis functions include waveform feature-based pattern recognition as well as artificial intelligence/expert system techniques

A comparison of image features for registering LWIR and visual images

CSIR Research Space (South Africa)

Cronje, J

2012-11-01

Full Text Available This paper presents a comparison of several established and recent image feature-descriptors to register long wave infra-red images in the 8–14 m band to visual band images. The feature descriptors were chosen to include robust algorithms, SURF...

Superpixel-Based Feature for Aerial Image Scene Recognition

Directory of Open Access Journals (Sweden)

Hongguang Li

2018-01-01

Full Text Available Image scene recognition is a core technology for many aerial remote sensing applications. Different landforms are inputted as different scenes in aerial imaging, and all landform information is regarded as valuable for aerial image scene recognition. However, the conventional features of the Bag-of-Words model are designed using local points or other related information and thus are unable to fully describe landform areas. This limitation cannot be ignored when the aim is to ensure accurate aerial scene recognition. A novel superpixel-based feature is proposed in this study to characterize aerial image scenes. Then, based on the proposed feature, a scene recognition method of the Bag-of-Words model for aerial imaging is designed. The proposed superpixel-based feature that utilizes landform information establishes top-task superpixel extraction of landforms to bottom-task expression of feature vectors. This characterization technique comprises the following steps: simple linear iterative clustering based superpixel segmentation, adaptive filter bank construction, Lie group-based feature quantification, and visual saliency model-based feature weighting. Experiments of image scene recognition are carried out using real image data captured by an unmanned aerial vehicle (UAV. The recognition accuracy of the proposed superpixel-based feature is 95.1%, which is higher than those of scene recognition algorithms based on other local features.

Solving jigsaw puzzles using image features

DEFF Research Database (Denmark)

Nielsen, Ture R.; Drewsen, Peter; Hansen, Klaus

2008-01-01

In this article, we describe a method for automatic solving of the jigsaw puzzle problem based on using image features instead of the shape of the pieces. The image features are used for obtaining an accurate measure for edge similarity to be used in a new edge matching algorithm. The algorithm i...

Feature Evaluation for Building Facade Images - AN Empirical Study

Science.gov (United States)

Yang, M. Y.; Förstner, W.; Chai, D.

2012-08-01

The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

Imaging features of kaposiform lymphangiomatosis

International Nuclear Information System (INIS)

Goyal, Pradeep; Alomari, Ahmad I.; Shaikh, Raja; Chaudry, Gulraiz; Kozakewich, Harry P.; Perez-Atayde, Antonio R.; Trenor, Cameron C.; Fishman, Steven J.; Greene, Arin K.

2016-01-01

Kaposiform lymphangiomatosis is a rare, aggressive lymphatic disorder. The imaging and presenting features of kaposiform lymphangiomatosis can overlap with those of central conducting lymphatic anomaly and generalized lymphatic anomaly. To analyze the imaging findings of kaposiform lymphangiomatosis disorder and highlight features most suggestive of this diagnosis. We retrospectively identified and characterized 20 children and young adults with histopathological diagnosis of kaposiform lymphangiomatosis and radiologic imaging referred to the vascular anomalies center between 1995 and 2015. The median age at onset was 6.5 years (range 3 months to 27 years). The most common presenting features were respiratory compromise (dyspnea, cough, chest pain; 55.5%), swelling/mass (25%), bleeding (15%) and fracture (5%). The thoracic cavity was involved in all patients; all patients had mediastinal involvement followed by lung parenchymal disease (90%) and pleural (85%) and pericardial (50%) effusions. The most common extra-thoracic sites of disease were the retroperitoneum (80%), bone (60%), abdominal viscera (55%) and muscles (45%). There was characteristic enhancing and infiltrative soft-tissue thickening in the mediastinum and retroperitoneum extending along the lymphatic distribution. Kaposiform lymphangiomatosis has overlapping imaging features with central conducting lymphatic anomaly and generalized lymphatic anomaly. Presence of mediastinal or retroperitoneal enhancing and infiltrative soft-tissue disease along the lymphatic distribution, hemorrhagic effusions and moderate thrombocytopenia (50-100,000/μl) should favor diagnosis of kaposiform lymphangiomatosis. (orig.)

MR imaging features of the congenital uterine anomalies

International Nuclear Information System (INIS)

Hamcan, S.; Akgun, V.; Battal, B.; Kocaoglu, M.

2012-01-01

Full text: Introduction: Congenital uterine anomalies are common and usually asymptomatic. The agenesis, malfusion or deficient resorption of the Mullerian canals during embryogenesis may lead to these anomalies. Although ultrasonography (US) is the first step imaging technique in assessment of the uterine pathologies, it can be insufficient in differentiation of them. Magnetic resonance (MR) imaging is an adequate imaging technique in depicting pelvic anatomy and different types of uterine anomalies. Objectives and tasks: In this article, we aimed to present imaging features of the uterine anomalies. Material and methods: Pelvic MR scans of the cases who were referred to our radiology department for suspicious uterine anomaly were evaluated retrospectively. Results: We determined uniconuate uterus (type II), uterus didelphys (type III), bicornuate uterus (type IV), uterine septum (type V) and arcuate uterus (type VI) anomalies according to ASRM (American Society of Reproductive Medicine) classification. Conclusion: In cases with such pathologies leading to obstruction, dysmenorrhea or palpable pelvic mass in the puberty are the main clinical presentations. In cases without obstruction, infertility or multiple abortions can be encountered in reproductive ages. The identification of the subtype of the uterine anomalies is important for the preoperative planning of the management. MR that has multiplanar imaging capability and high soft tissue resolution is a non-invasive and the most important imaging modality for the detection and classification of the uterine anomalies

Image fusion using sparse overcomplete feature dictionaries

Science.gov (United States)

Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

2015-10-06

Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.

An Effective Combined Feature For Web Based Image Retrieval

Directory of Open Access Journals (Sweden)

H.M.R.B Herath

2015-08-01

Full Text Available Abstract Technology advances as well as the emergence of large scale multimedia applications and the revolution of the World Wide Web has changed the world into a digital age. Anybody can use their mobile phone to take a photo at any time anywhere and upload that image to ever growing image databases. Development of effective techniques for visual and multimedia retrieval systems is one of the most challenging and important directions of the future research. This paper proposes an effective combined feature for web based image retrieval. Frequently used colour and texture features are explored in order to develop a combined feature for this purpose. Widely used three colour features Colour moments Colour coherence vector and Colour Correlogram and three texture features Grey Level Co-occurrence matrix Tamura features and Gabor filter were analyzed for their performance. Precision and Recall were used to evaluate the performance of each of these techniques. By comparing precision and recall values the methods that performed best were taken and combined to form a hybrid feature. The developed combined feature was evaluated by developing a web based CBIR system. A web crawler was used to first crawl through Web sites and images found in those sites are downloaded and the combined feature representation technique was used to extract image features. The test results indicated that this web system can be used to index web images with the combined feature representation schema and to find similar images. Random image retrievals using the web system shows that the combined feature can be used to retrieve images belonging to the general image domain. Accuracy of the retrieval can be noted high for natural images like outdoor scenes images of flowers etc. Also images which have a similar colour and texture distribution were retrieved as similar even though the images were belonging to deferent semantic categories. This can be ideal for an artist who wants

Analysis and classification of commercial ham slice images using directional fractal dimension features.

Science.gov (United States)

Mendoza, Fernando; Valous, Nektarios A; Allen, Paul; Kenny, Tony A; Ward, Paddy; Sun, Da-Wen

2009-02-01

This paper presents a novel and non-destructive approach to the appearance characterization and classification of commercial pork, turkey and chicken ham slices. Ham slice images were modelled using directional fractal (DF(0°;45°;90°;135°)) dimensions and a minimum distance classifier was adopted to perform the classification task. Also, the role of different colour spaces and the resolution level of the images on DF analysis were investigated. This approach was applied to 480 wafer thin ham slices from four types of hams (120 slices per type): i.e., pork (cooked and smoked), turkey (smoked) and chicken (roasted). DF features were extracted from digitalized intensity images in greyscale, and R, G, B, L(∗), a(∗), b(∗), H, S, and V colour components for three image resolution levels (100%, 50%, and 25%). Simulation results show that in spite of the complexity and high variability in colour and texture appearance, the modelling of ham slice images with DF dimensions allows the capture of differentiating textural features between the four commercial ham types. Independent DF features entail better discrimination than that using the average of four directions. However, DF dimensions reveal a high sensitivity to colour channel, orientation and image resolution for the fractal analysis. The classification accuracy using six DF dimension features (a(90°)(∗),a(135°)(∗),H(0°),H(45°),S(0°),H(90°)) was 93.9% for training data and 82.2% for testing data.

Lipofibromatosis: magnetic resonance imaging features and pathological correlation in three cases

Energy Technology Data Exchange (ETDEWEB)

Vogel, Daniela; Righi, Alberto; Kreshak, Jennifer; Dei Tos, Angelo Paolo [Istituto Ortopedico Rizzoli, Bologna (Italy); Merlino, Biagio [Universita Cattolica del Sacro Cuore Policlinico ' ' A. Gemelli' ' , Dipartimento di Scienze Radiologiche, Roma (Italy); Brunocilla, Eugenio [U.O. di UROLOGIA, Dipartimento di Medicina Specialistica, Diagnostica e Sperimentale, Bologna (Italy); Vanel, Daniel [Istituto Ortopedico Rizzoli, Anatomia Patologica, Bologna (Italy)

2014-05-15

Lipofibromatosis is a rare, benign, but infiltrative, soft tissue tumor seen in children. We present three cases of lipofibromatosis, each with different magnetic resonance imaging features and correlate this with the histological findings. The patients comprised two males and one female who presented in infancy; at birth, 5 months, and 7 months of age. Clinically, the masses were painless and slow-growing. The masses ranged in size from 2 to 6 cm and involved the distal extremities in two cases (one foot, one wrist) and the trunk. Magnetic resonance imaging showed lipomatous lesions with varying amounts of adipose and solid components in each case. There were no capsules at the periphery of the lesions. One case showed a fat-predominant lesion, another an equal mixture of fat and solid tissue, and the third was predominantly solid. This was reflected in the histology, which showed corresponding features. Radiological and histopathological differential diagnoses are reviewed. (orig.)

Lipofibromatosis: magnetic resonance imaging features and pathological correlation in three cases

International Nuclear Information System (INIS)

Vogel, Daniela; Righi, Alberto; Kreshak, Jennifer; Dei Tos, Angelo Paolo; Merlino, Biagio; Brunocilla, Eugenio; Vanel, Daniel

2014-01-01

Lipofibromatosis is a rare, benign, but infiltrative, soft tissue tumor seen in children. We present three cases of lipofibromatosis, each with different magnetic resonance imaging features and correlate this with the histological findings. The patients comprised two males and one female who presented in infancy; at birth, 5 months, and 7 months of age. Clinically, the masses were painless and slow-growing. The masses ranged in size from 2 to 6 cm and involved the distal extremities in two cases (one foot, one wrist) and the trunk. Magnetic resonance imaging showed lipomatous lesions with varying amounts of adipose and solid components in each case. There were no capsules at the periphery of the lesions. One case showed a fat-predominant lesion, another an equal mixture of fat and solid tissue, and the third was predominantly solid. This was reflected in the histology, which showed corresponding features. Radiological and histopathological differential diagnoses are reviewed. (orig.)

Imaging features of ovarian metastases from colonic adenocarcinoma in adolescents

International Nuclear Information System (INIS)

Kauffman, W.M.; Jenkins, J.J. III; Helton, K.; Rao, B.N.; Winer-Muram, H.T.; Pratt, C.B.

1995-01-01

This paper describes the imaging features of ovarian metastases from adenocarcinoma of the colon in adolescent females. We reviewed retrospectively abdominal and pelvic computed tomographic and pelvic ultrasound examinations, histologic slices, and clinical charts of six adolescent females with ovarian metastases secondary to adenocarcinoma of the colon. One patient had ovarian metastasis at presentation and was presumed to have a primary ovarian tumor. The ovarian metastases were either solid (n = 3), complex with both solid and cystic components (n = 2), or multilocular cysts (n = 1). The ovarian lesions were large, ranging from 6 cm to 18 cm in diameter. Colorectal carcinoma in adolescent females is frequently associated with ovarian metastases. One imaging characteristic differs in adult and adolescent ovarian metastases, although they do have features in common: in adolescents, a smaller proportion of colorectal ovarian metastases are multicystic (17%) compared with the adult series (45%). These lesions are frequently large and may be complex, multicystic, or solid. Although it is a rare disease, the differential dignosis of adnexal masses in adolescent females should include ovarian metastases from adenocarcinoma of the colon. (orig.)

Combining deep learning and coherent anti-Stokes Raman scattering imaging for automated differential diagnosis of lung cancer

Science.gov (United States)

Weng, Sheng; Xu, Xiaoyun; Li, Jiasong; Wong, Stephen T. C.

2017-10-01

Lung cancer is the most prevalent type of cancer and the leading cause of cancer-related deaths worldwide. Coherent anti-Stokes Raman scattering (CARS) is capable of providing cellular-level images and resolving pathologically related features on human lung tissues. However, conventional means of analyzing CARS images requires extensive image processing, feature engineering, and human intervention. This study demonstrates the feasibility of applying a deep learning algorithm to automatically differentiate normal and cancerous lung tissue images acquired by CARS. We leverage the features learned by pretrained deep neural networks and retrain the model using CARS images as the input. We achieve 89.2% accuracy in classifying normal, small-cell carcinoma, adenocarcinoma, and squamous cell carcinoma lung images. This computational method is a step toward on-the-spot diagnosis of lung cancer and can be further strengthened by the efforts aimed at miniaturizing the CARS technique for fiber-based microendoscopic imaging.

A kernel-based multi-feature image representation for histopathology image classification

International Nuclear Information System (INIS)

Moreno J; Caicedo J Gonzalez F

2010-01-01

This paper presents a novel strategy for building a high-dimensional feature space to represent histopathology image contents. Histogram features, related to colors, textures and edges, are combined together in a unique image representation space using kernel functions. This feature space is further enhanced by the application of latent semantic analysis, to model hidden relationships among visual patterns. All that information is included in the new image representation space. Then, support vector machine classifiers are used to assign semantic labels to images. Processing and classification algorithms operate on top of kernel functions, so that; the structure of the feature space is completely controlled using similarity measures and a dual representation. The proposed approach has shown a successful performance in a classification task using a dataset with 1,502 real histopathology images in 18 different classes. The results show that our approach for histological image classification obtains an improved average performance of 20.6% when compared to a conventional classification approach based on SVM directly applied to the original kernel.

A KERNEL-BASED MULTI-FEATURE IMAGE REPRESENTATION FOR HISTOPATHOLOGY IMAGE CLASSIFICATION

Directory of Open Access Journals (Sweden)

J Carlos Moreno

2010-09-01

Full Text Available This paper presents a novel strategy for building a high-dimensional feature space to represent histopathology image contents. Histogram features, related to colors, textures and edges, are combined together in a unique image representation space using kernel functions. This feature space is further enhanced by the application of Latent Semantic Analysis, to model hidden relationships among visual patterns. All that information is included in the new image representation space. Then, Support Vector Machine classifiers are used to assign semantic labels to images. Processing and classification algorithms operate on top of kernel functions, so that, the structure of the feature space is completely controlled using similarity measures and a dual representation. The proposed approach has shown a successful performance in a classification task using a dataset with 1,502 real histopathology images in 18 different classes. The results show that our approach for histological image classification obtains an improved average performance of 20.6% when compared to a conventional classification approach based on SVM directly applied to the original kernel.

Breast image feature learning with adaptive deconvolutional networks

Science.gov (United States)

Jamieson, Andrew R.; Drukker, Karen; Giger, Maryellen L.

2012-03-01

Feature extraction is a critical component of medical image analysis. Many computer-aided diagnosis approaches employ hand-designed, heuristic lesion extracted features. An alternative approach is to learn features directly from images. In this preliminary study, we explored the use of Adaptive Deconvolutional Networks (ADN) for learning high-level features in diagnostic breast mass lesion images with potential application to computer-aided diagnosis (CADx) and content-based image retrieval (CBIR). ADNs (Zeiler, et. al., 2011), are recently-proposed unsupervised, generative hierarchical models that decompose images via convolution sparse coding and max pooling. We trained the ADNs to learn multiple layers of representation for two breast image data sets on two different modalities (739 full field digital mammography (FFDM) and 2393 ultrasound images). Feature map calculations were accelerated by use of GPUs. Following Zeiler et. al., we applied the Spatial Pyramid Matching (SPM) kernel (Lazebnik, et. al., 2006) on the inferred feature maps and combined this with a linear support vector machine (SVM) classifier for the task of binary classification between cancer and non-cancer breast mass lesions. Non-linear, local structure preserving dimension reduction, Elastic Embedding (Carreira-Perpiñán, 2010), was then used to visualize the SPM kernel output in 2D and qualitatively inspect image relationships learned. Performance was found to be competitive with current CADx schemes that use human-designed features, e.g., achieving a 0.632+ bootstrap AUC (by case) of 0.83 [0.78, 0.89] for an ultrasound image set (1125 cases).

Clinical features and {sup 123}I-FP-CIT SPECT imaging in drug-induced parkinsonism and Parkinson's disease

Energy Technology Data Exchange (ETDEWEB)

Diaz-Corrales, Francisco J.; Escobar-Delgado, Teresa [Hospital Universitario Virgen del Rocio/CSIC/Universidad de Sevilla, Unidad de Trastornos del Movimiento, Servicio de Neurologia, Instituto de Biomedicina de Sevilla, Seville (Spain); Sanz-Viedma, Salome [Hospital Universitario Virgen del Rocio, Unidad Diagnostica de Medicina Nuclear, Seville (Spain); Garcia-Solis, David [Hospital Universitario Virgen del Rocio, Unidad Diagnostica de Medicina Nuclear, Seville (Spain); Centro de Investigacion Biomedica en Red sobre Enfermedades Neurodegenerativas (CIBERNED), Seville (Spain); Mir, Pablo [Hospital Universitario Virgen del Rocio/CSIC/Universidad de Sevilla, Unidad de Trastornos del Movimiento, Servicio de Neurologia, Instituto de Biomedicina de Sevilla, Seville (Spain); Centro de Investigacion Biomedica en Red sobre Enfermedades Neurodegenerativas (CIBERNED), Seville (Spain); Hospital Universitario Virgen del Rocio, Unidad de Trastornos del Movimiento. Servicio de Neurologia, Seville (Spain)

2010-03-15

To determine clinical predictors and accuracy of {sup 123}I-FP-CIT SPECT imaging in the differentiation of drug-induced parkinsonism (DIP) and Parkinson's disease (PD). Several clinical features and {sup 123}I-FP-CIT SPECT images in 32 patients with DIP, 25 patients with PD unmasked by antidopaminergic drugs (PDu) and 22 patients with PD without a previous history of antidopaminergic treatment (PDc) were retrospectively evaluated. DIP and PD shared all clinical features except symmetry of parkinsonian signs which was more frequently observed in patients with DIP (46.9%) than in patients with PDu (16.0%, p<0.05) or PDc (4.5%, p<0.01). Qualitatively {sup 123}I-FP-CIT SPECT images were normal in 29 patients with DIP (90.6%) and abnormal in all patients with PD, and this imaging technique showed high levels of accuracy. DIP and PD are difficult to differentiate based on clinical signs. The precision of clinical diagnosis could be reliably enhanced by {sup 123}I-FP-CIT SPECT imaging. (orig.)

Smart Images Search based on Visual Features Fusion

International Nuclear Information System (INIS)

Saad, M.H.

2013-01-01

Image search engines attempt to give fast and accurate access to the wide range of the huge amount images available on the Internet. There have been a number of efforts to build search engines based on the image content to enhance search results. Content-Based Image Retrieval (CBIR) systems have achieved a great interest since multimedia files, such as images and videos, have dramatically entered our lives throughout the last decade. CBIR allows automatically extracting target images according to objective visual contents of the image itself, for example its shapes, colors and textures to provide more accurate ranking of the results. The recent approaches of CBIR differ in terms of which image features are extracted to be used as image descriptors for matching process. This thesis proposes improvements of the efficiency and accuracy of CBIR systems by integrating different types of image features. This framework addresses efficient retrieval of images in large image collections. A comparative study between recent CBIR techniques is provided. According to this study; image features need to be integrated to provide more accurate description of image content and better image retrieval accuracy. In this context, this thesis presents new image retrieval approaches that provide more accurate retrieval accuracy than previous approaches. The first proposed image retrieval system uses color, texture and shape descriptors to form the global features vector. This approach integrates the yc b c r color histogram as a color descriptor, the modified Fourier descriptor as a shape descriptor and modified Edge Histogram as a texture descriptor in order to enhance the retrieval results. The second proposed approach integrates the global features vector, which is used in the first approach, with the SURF salient point technique as local feature. The nearest neighbor matching algorithm with a proposed similarity measure is applied to determine the final image rank. The second approach

Primary diaphyseal osteosarcoma in long bones: Imaging features and tumor characteristics

International Nuclear Information System (INIS)

Wang, Cheng-Sheng; Yin, Qi-Hua; Liao, Jin-Sheng; Lou, Jiang-Hua; Ding, Xiao-Yi; Zhu, Yan-Bo; Chen, Ke-Min

2012-01-01

Objective: This study aims to assess retrospectively the imaging features of diaphyseal osteosarcoma and compare its characteristics with that of metaphyseal osteosarcoma. Materials and methods: Eighteen pathologically confirmed diaphyseal osteosarcomas were reviewed. Images of X-ray (n = 18), CT (n = 12) and MRI (n = 15) were evaluated by two radiologists. Differences among common radiologic findings of X-ray, CT and MRI, and between diaphyseal osteosarcomas and metaphyseal osteosarcomas in terms of tumor characteristics were compared. Results: The common imaging features of diaphyseal osteosarcoma were bone destruction, lamellar periosteal reaction with/without Codman triangle, massive soft tissue mass/swelling, neoplastic bone and/or calcification. CT and MRI had a higher detection rate in detecting bone destruction (P = 0.001) as compared with that of X-ray. X-ray and CT resulted in a higher percentage in detecting periosteal reaction (P = 0.018) and neoplastic bone and/or calcification (P = 0.043) as compared with that of MRI. There was no difference (P = 0.179) in detecting soft tissue mass among three imaging modalities. When comparing metaphyseal osteosarcoma to diaphyseal osteosarcoma, the latter had the following characteristics: a higher age of onset (P = 0.022), a larger extent of tumor (P = 0.018), a more osteolytic radiographic pattern (P = 0.043). Conclusion: As compared with metaphyseal osteosarcoma, diaphysial osteosarcoma is a special location of osteosarcoma with a lower incidence, a higher age of onset, a larger extent of tumor, a more osteolytic radiographic pattern. The osteoblastic and mixed types are diagnosed easily, but the osteolytic lesion should be differentiated from Ewing sarcoma. X-ray, CT and MRI can show imaging features from different aspects with different detection rates.

Multispectral Image Feature Points

Directory of Open Access Journals (Sweden)

Cristhian Aguilera

2012-09-01

Full Text Available This paper presents a novel feature point descriptor for the multispectral image case: Far-Infrared and Visible Spectrum images. It allows matching interest points on images of the same scene but acquired in different spectral bands. Initially, points of interest are detected on both images through a SIFT-like based scale space representation. Then, these points are characterized using an Edge Oriented Histogram (EOH descriptor. Finally, points of interest from multispectral images are matched by finding nearest couples using the information from the descriptor. The provided experimental results and comparisons with similar methods show both the validity of the proposed approach as well as the improvements it offers with respect to the current state-of-the-art.

Differential morphology and image processing.

Science.gov (United States)

Maragos, P

1996-01-01

Image processing via mathematical morphology has traditionally used geometry to intuitively understand morphological signal operators and set or lattice algebra to analyze them in the space domain. We provide a unified view and analytic tools for morphological image processing that is based on ideas from differential calculus and dynamical systems. This includes ideas on using partial differential or difference equations (PDEs) to model distance propagation or nonlinear multiscale processes in images. We briefly review some nonlinear difference equations that implement discrete distance transforms and relate them to numerical solutions of the eikonal equation of optics. We also review some nonlinear PDEs that model the evolution of multiscale morphological operators and use morphological derivatives. Among the new ideas presented, we develop some general 2-D max/min-sum difference equations that model the space dynamics of 2-D morphological systems (including the distance computations) and some nonlinear signal transforms, called slope transforms, that can analyze these systems in a transform domain in ways conceptually similar to the application of Fourier transforms to linear systems. Thus, distance transforms are shown to be bandpass slope filters. We view the analysis of the multiscale morphological PDEs and of the eikonal PDE solved via weighted distance transforms as a unified area in nonlinear image processing, which we call differential morphology, and briefly discuss its potential applications to image processing and computer vision.

Image Recommendation Algorithm Using Feature-Based Collaborative Filtering

Science.gov (United States)

Kim, Deok-Hwan

As the multimedia contents market continues its rapid expansion, the amount of image contents used in mobile phone services, digital libraries, and catalog service is increasing remarkably. In spite of this rapid growth, users experience high levels of frustration when searching for the desired image. Even though new images are profitable to the service providers, traditional collaborative filtering methods cannot recommend them. To solve this problem, in this paper, we propose feature-based collaborative filtering (FBCF) method to reflect the user's most recent preference by representing his purchase sequence in the visual feature space. The proposed approach represents the images that have been purchased in the past as the feature clusters in the multi-dimensional feature space and then selects neighbors by using an inter-cluster distance function between their feature clusters. Various experiments using real image data demonstrate that the proposed approach provides a higher quality recommendation and better performance than do typical collaborative filtering and content-based filtering techniques.

Feature Detector and Descriptor for Medical Images

Science.gov (United States)

Sargent, Dusty; Chen, Chao-I.; Tsai, Chang-Ming; Wang, Yuan-Fang; Koppel, Daniel

2009-02-01

The ability to detect and match features across multiple views of a scene is a crucial first step in many computer vision algorithms for dynamic scene analysis. State-of-the-art methods such as SIFT and SURF perform successfully when applied to typical images taken by a digital camera or camcorder. However, these methods often fail to generate an acceptable number of features when applied to medical images, because such images usually contain large homogeneous regions with little color and intensity variation. As a result, tasks like image registration and 3D structure recovery become difficult or impossible in the medical domain. This paper presents a scale, rotation and color/illumination invariant feature detector and descriptor for medical applications. The method incorporates elements of SIFT and SURF while optimizing their performance on medical data. Based on experiments with various types of medical images, we combined, adjusted, and built on methods and parameter settings employed in both algorithms. An approximate Hessian based detector is used to locate scale invariant keypoints and a dominant orientation is assigned to each keypoint using a gradient orientation histogram, providing rotation invariance. Finally, keypoints are described with an orientation-normalized distribution of gradient responses at the assigned scale, and the feature vector is normalized for contrast invariance. Experiments show that the algorithm detects and matches far more features than SIFT and SURF on medical images, with similar error levels.

Magnetic Resonance Imaging Features of Neuromyelitis Optica

Energy Technology Data Exchange (ETDEWEB)

You, Sun Kyung; Song, Chang June; Park, Woon Ju; Lee, In Ho; Son, Eun Hee [Chungnam National University College of Medicine, Chungnam National University Hospital, Daejeon (Korea, Republic of)

2013-03-15

To report the magnetic resonance (MR) imaging features of the spinal cord and brain in patients of neuromyelitis optica (NMO). Between January 2001 and March 2010, the MR images (spinal cord, brain, and orbit) and the clinical and serologic findings of 11 NMO patients were retrospectively reviewed. The contrast-enhancement of the spinal cord was performed (20/23). The presence and pattern of the contrast-enhancement in the spinal cord were classified into 5 types. Acute myelitis was monophasic in 8 patients (8/11, 72.7%); and optic neuritis preceded acute myelitis in most patients. Longitudinally extensive cord lesion (average, 7.3 vertebral segments) was involved. The most common type was the diffuse and subtle enhancement of the spinal cord with a multifocal nodular, linear or segmental intense enhancement (45%). Most of the brain lesions (5/11, 10 lesions) were located in the brain stem, thalamus and callososeptal interphase. Anti-Ro autoantibody was positive in 2 patients, and they showed a high relapse rate of acute myelitis. Anti-NMO IgG was positive in 4 patients (4/7, 66.7%). The imaging findings of acute myelitis in NMO may helpful in making an early diagnosis of NMO which can result in a severe damage to the spinal cord, and to make a differential diagnosis of multiple sclerosis and inflammatory diseases of the spinal cord such as toxocariasis.

Magnetic Resonance Imaging Features of Neuromyelitis Optica

International Nuclear Information System (INIS)

You, Sun Kyung; Song, Chang June; Park, Woon Ju; Lee, In Ho; Son, Eun Hee

2013-01-01

To report the magnetic resonance (MR) imaging features of the spinal cord and brain in patients of neuromyelitis optica (NMO). Between January 2001 and March 2010, the MR images (spinal cord, brain, and orbit) and the clinical and serologic findings of 11 NMO patients were retrospectively reviewed. The contrast-enhancement of the spinal cord was performed (20/23). The presence and pattern of the contrast-enhancement in the spinal cord were classified into 5 types. Acute myelitis was monophasic in 8 patients (8/11, 72.7%); and optic neuritis preceded acute myelitis in most patients. Longitudinally extensive cord lesion (average, 7.3 vertebral segments) was involved. The most common type was the diffuse and subtle enhancement of the spinal cord with a multifocal nodular, linear or segmental intense enhancement (45%). Most of the brain lesions (5/11, 10 lesions) were located in the brain stem, thalamus and callososeptal interphase. Anti-Ro autoantibody was positive in 2 patients, and they showed a high relapse rate of acute myelitis. Anti-NMO IgG was positive in 4 patients (4/7, 66.7%). The imaging findings of acute myelitis in NMO may helpful in making an early diagnosis of NMO which can result in a severe damage to the spinal cord, and to make a differential diagnosis of multiple sclerosis and inflammatory diseases of the spinal cord such as toxocariasis.

Adapting Local Features for Face Detection in Thermal Image

Directory of Open Access Journals (Sweden)

Chao Ma

2017-11-01

Full Text Available A thermal camera captures the temperature distribution of a scene as a thermal image. In thermal images, facial appearances of different people under different lighting conditions are similar. This is because facial temperature distribution is generally constant and not affected by lighting condition. This similarity in face appearances is advantageous for face detection. To detect faces in thermal images, cascade classifiers with Haar-like features are generally used. However, there are few studies exploring the local features for face detection in thermal images. In this paper, we introduce two approaches relying on local features for face detection in thermal images. First, we create new feature types by extending Multi-Block LBP. We consider a margin around the reference and the generally constant distribution of facial temperature. In this way, we make the features more robust to image noise and more effective for face detection in thermal images. Second, we propose an AdaBoost-based training method to get cascade classifiers with multiple types of local features. These feature types have different advantages. In this way we enhance the description power of local features. We did a hold-out validation experiment and a field experiment. In the hold-out validation experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females. For each participant, we captured 420 images with 10 variations in camera distance, 21 poses, and 2 appearances (participant with/without glasses. We compared the performance of cascade classifiers trained by different sets of the features. The experiment results showed that the proposed approaches effectively improve the performance of face detection in thermal images. In the field experiment, we compared the face detection performance in realistic scenes using thermal and RGB images, and gave discussion based on the results.

Features Selection for Skin Micro-Image Symptomatic Recognition

Institute of Scientific and Technical Information of China (English)

HUYue-li; CAOJia-lin; ZHAOQian; FENGXu

2004-01-01

Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92% using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

Features Selection for Skin Micro-Image Symptomatic Recognition

Institute of Scientific and Technical Information of China (English)

HU Yue-li; CAO Jia-lin; ZHAO Qian; FENG Xu

2004-01-01

Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92 % using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

Differentiation of intrahepatic mass-forming cholangiocarcinoma from hepatocellular carcinoma on gadoxetic acid-enhanced liver MR imaging

Energy Technology Data Exchange (ETDEWEB)

Kim, Rihyeon; Shin, Cheong-Il; Yoon, Jeong Hee; Joo, Ijin; Kim, Seong Ho; Hwang, Inpyeong [Seoul National University Hospital, Department of Radiology, Seoul (Korea, Republic of); Lee, Jeong Min; Han, Joon Koo [Seoul National University Hospital, Department of Radiology, Seoul (Korea, Republic of); Seoul National University Hospital, Institute of Radiation Medicine, Seoul (Korea, Republic of); Lee, Eun Sun; Choi, Byung Ihn [Chung-Ang University Hospital, Department of Radiology, Seoul (Korea, Republic of)

2016-06-15

To determine the different imaging features of intrahepatic mass-forming cholangiocarcinoma (IMCC) from hepatocellular carcinoma (HCC) on gadoxetic acid-enhanced magnetic resonance imaging (MRI). This retrospective study was institutional review board approved and the requirement for informed consent was waived. Patients who underwent gadoxetic acid-enhanced MRI with histologically confirmed IMCCs (n = 46) or HCCs (n = 58) were included. Imaging features of IMCCs and HCCs on gadoxetic acid-enhanced MRI including T2- and T1-weighted, diffusion weighted images, dynamic study and hepatobiliary phase (HBP) images were analyzed. Univariate and multivariate logistic regression analyses were performed to identify relevant differentiating features between IMCCs and HCCs. Multivariate analysis revealed heterogeneous T2 signal intensity and a hypointense rim on the HBP as suggestive findings of IMCCs and the wash-in and ''portal wash-out'' enhancement pattern as well as focal T1 high signal intensity foci as indicative of HCCs (all, p < 0.05). When we combined any three of the above four imaging features, we were able to diagnose IMCCs with 94 % (43/46) sensitivity and 86 % (50/58) specificity. Combined interpretation of enhancement characteristics including HBP images, morphologic features, and strict application of the ''portal wash-out'' pattern helped more accurate discrimination of IMCCs from HCCs. (orig.)

FEATURE EVALUATION FOR BUILDING FACADE IMAGES – AN EMPIRICAL STUDY

Directory of Open Access Journals (Sweden)

M. Y. Yang

2012-08-01

Full Text Available The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

The analysis of image feature robustness using cometcloud

Directory of Open Access Journals (Sweden)

Xin Qi

2012-01-01

Full Text Available The robustness of image features is a very important consideration in quantitative image analysis. The objective of this paper is to investigate the robustness of a range of image texture features using hematoxylin stained breast tissue microarray slides which are assessed while simulating different imaging challenges including out of focus, changes in magnification and variations in illumination, noise, compression, distortion, and rotation. We employed five texture analysis methods and tested them while introducing all of the challenges listed above. The texture features that were evaluated include co-occurrence matrix, center-symmetric auto-correlation, texture feature coding method, local binary pattern, and texton. Due to the independence of each transformation and texture descriptor, a network structured combination was proposed and deployed on the Rutgers private cloud. The experiments utilized 20 randomly selected tissue microarray cores. All the combinations of the image transformations and deformations are calculated, and the whole feature extraction procedure was completed in 70 minutes using a cloud equipped with 20 nodes. Center-symmetric auto-correlation outperforms all the other four texture descriptors but also requires the longest computational time. It is roughly 10 times slower than local binary pattern and texton. From a speed perspective, both the local binary pattern and texton features provided excellent performance for classification and content-based image retrieval.

Color and neighbor edge directional difference feature for image retrieval

Institute of Scientific and Technical Information of China (English)

Chaobing Huang; Shengsheng Yu; Jingli Zhou; Hongwei Lu

2005-01-01

@@ A novel image feature termed neighbor edge directional difference unit histogram is proposed, in which the neighbor edge directional difference unit is defined and computed for every pixel in the image, and is used to generate the neighbor edge directional difference unit histogram. This histogram and color histogram are used as feature indexes to retrieve color image. The feature is invariant to image scaling and translation and has more powerful descriptive for the natural color images. Experimental results show that the feature can achieve better retrieval performance than other color-spatial features.

A chondroblastoma versus a giant cell tumor: emphasis on the MR imaging features

International Nuclear Information System (INIS)

Chai, Jee Won; Hong, Sung Hwan; Choi, Ja Young; Kim, Na Ra; Choi, Jung Ah; Kang, Heung Sik

2007-01-01

To assess the MR imaging features in differentiating a chondroblastoma (CB) from a giant cell tumor (GCT), with an emphasis on the accompanying peritumoral bone marrow edema. MR imaging findings in 20 patients with CB were compared with the imaging features of 22 patients with GCT. The location of the lesion, signal intensity, adjacent cortical change, degree of accompanying bone marrow edema, synovitis in the adjacent joint and cystic change were analyzed. The findings of CB and GCT were examined statistically with use of Fisher's exact test. The incidence ratios of MR imaging findings were as follows (CB:GCT). Metaphyseal dominant involvement (2:21), partial cortical disruption (2:14), extensive bone marrow edema surrounding the tumor (14:0) and synovitis in the adjacent joint (11:2) were statistically different in incidence between CB and GCT (ρ < 0.01). The inhomogeneous signal intensity (17:17) and cystic change (10:15) were not different in incidence between a CB and GCT. The presence of metaphyseal dominant involvement and cortical disruption favors a diagnosis of a GCT rather than a CB. In contrast, extensive bone marrow edema surrounding the tumor and synovitis in the adjacent joint are highly indicative of a CB

Amide proton transfer imaging for differentiation of benign and atypical meningiomas

Energy Technology Data Exchange (ETDEWEB)

Joo, Bio [The Armed Forces Capital Hospital, Department of Radiology, Seongnam, Gyeonggi-do (Korea, Republic of); Han, Kyunghwa; Choi, Yoon Seong; Lee, Seung-Koo [Yonsei University College of Medicine, Department of Radiology and Research Institute of Radiological Science, College of Medicine, Seoul (Korea, Republic of); Ahn, Sung Soo [Yonsei University College of Medicine, Department of Radiology and Research Institute of Radiological Science, College of Medicine, Seoul (Korea, Republic of); Yonsei University, Department of Radiology, College of Medicine, Seoul (Korea, Republic of); Chang, Jong Hee; Kang, Seok-Gu [Yonsei University College of Medicine, Department of Neurosurgery, Seoul (Korea, Republic of); Kim, Se Hoon [Yonsei University College of Medicine, Department of Pathology, Seoul (Korea, Republic of); Zhou, Jinyuan [Johns Hopkins University School of Medicine, Division of MRI Research, Department of Radiology, Baltimore, MD (United States)

2018-01-15

To investigate the difference in amide proton transfer (APT)-weighted signals between benign and atypical meningiomas and determine the value of APT imaging for differentiating the two. Fifty-seven patients with pathologically diagnosed meningiomas (benign, 44; atypical, 13), who underwent preoperative MRI with APT imaging between December 2014 and August 2016 were included. We compared normalised magnetisation transfer ratio asymmetry (nMTR{sub asym}) values between benign and atypical meningiomas on APT-weighted images. Conventional MRI features were qualitatively assessed. Both imaging features were evaluated by multivariable logistic regression analysis. The discriminative value of MRI with and without nMTR{sub asym} was evaluated. The nMTR{sub asym} of atypical meningiomas was significantly greater than that of benign meningiomas (2.46% vs. 1.67%; P < 0.001). In conventional MR images, benign and atypical meningiomas exhibited significant differences in maximum tumour diameter, non-skull base location, and heterogeneous enhancement. On multivariable logistic regression analysis, high nMTR{sub asym} was an independent predictor of atypical meningiomas (adjusted OR, 11.227; P = 0.014). The diagnostic performance of MRI improved with nMTR{sub asym} for predicting atypical meningiomas. Atypical meningiomas exhibited significantly higher APT-weighted signal intensities than benign meningiomas. The discriminative value of conventional MRI improved significantly when combined with APT imaging for diagnosis of atypical meningioma. (orig.)

Fourier domain image fusion for differential X-ray phase-contrast breast imaging

International Nuclear Information System (INIS)

Coello, Eduardo; Sperl, Jonathan I.; Bequé, Dirk; Benz, Tobias; Scherer, Kai; Herzen, Julia; Sztrókay-Gaul, Anikó; Hellerhoff, Karin; Pfeiffer, Franz; Cozzini, Cristina; Grandl, Susanne

2017-01-01

X-Ray Phase-Contrast (XPC) imaging is a novel technology with a great potential for applications in clinical practice, with breast imaging being of special interest. This work introduces an intuitive methodology to combine and visualize relevant diagnostic features, present in the X-ray attenuation, phase shift and scattering information retrieved in XPC imaging, using a Fourier domain fusion algorithm. The method allows to present complementary information from the three acquired signals in one single image, minimizing the noise component and maintaining visual similarity to a conventional X-ray image, but with noticeable enhancement in diagnostic features, details and resolution. Radiologists experienced in mammography applied the image fusion method to XPC measurements of mastectomy samples and evaluated the feature content of each input and the fused image. This assessment validated that the combination of all the relevant diagnostic features, contained in the XPC images, was present in the fused image as well.

Fourier domain image fusion for differential X-ray phase-contrast breast imaging

Energy Technology Data Exchange (ETDEWEB)

Coello, Eduardo, E-mail: eduardo.coello@tum.de [GE Global Research, Garching (Germany); Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality, Institut für Informatik, Technische Universität München, Garching (Germany); Sperl, Jonathan I.; Bequé, Dirk [GE Global Research, Garching (Germany); Benz, Tobias [Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality, Institut für Informatik, Technische Universität München, Garching (Germany); Scherer, Kai; Herzen, Julia [Lehrstuhl für Biomedizinische Physik, Physik-Department & Institut für Medizintechnik, Technische Universität München, Garching (Germany); Sztrókay-Gaul, Anikó; Hellerhoff, Karin [Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich (Germany); Pfeiffer, Franz [Lehrstuhl für Biomedizinische Physik, Physik-Department & Institut für Medizintechnik, Technische Universität München, Garching (Germany); Cozzini, Cristina [GE Global Research, Garching (Germany); Grandl, Susanne [Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich (Germany)

2017-04-15

X-Ray Phase-Contrast (XPC) imaging is a novel technology with a great potential for applications in clinical practice, with breast imaging being of special interest. This work introduces an intuitive methodology to combine and visualize relevant diagnostic features, present in the X-ray attenuation, phase shift and scattering information retrieved in XPC imaging, using a Fourier domain fusion algorithm. The method allows to present complementary information from the three acquired signals in one single image, minimizing the noise component and maintaining visual similarity to a conventional X-ray image, but with noticeable enhancement in diagnostic features, details and resolution. Radiologists experienced in mammography applied the image fusion method to XPC measurements of mastectomy samples and evaluated the feature content of each input and the fused image. This assessment validated that the combination of all the relevant diagnostic features, contained in the XPC images, was present in the fused image as well.

Tumor recognition in wireless capsule endoscopy images using textural features and SVM-based feature selection.

Science.gov (United States)

Li, Baopu; Meng, Max Q-H

2012-05-01

Tumor in digestive tract is a common disease and wireless capsule endoscopy (WCE) is a relatively new technology to examine diseases for digestive tract especially for small intestine. This paper addresses the problem of automatic recognition of tumor for WCE images. Candidate color texture feature that integrates uniform local binary pattern and wavelet is proposed to characterize WCE images. The proposed features are invariant to illumination change and describe multiresolution characteristics of WCE images. Two feature selection approaches based on support vector machine, sequential forward floating selection and recursive feature elimination, are further employed to refine the proposed features for improving the detection accuracy. Extensive experiments validate that the proposed computer-aided diagnosis system achieves a promising tumor recognition accuracy of 92.4% in WCE images on our collected data.

Histological image classification using biologically interpretable shape-based features

International Nuclear Information System (INIS)

Kothari, Sonal; Phan, John H; Young, Andrew N; Wang, May D

2013-01-01

Automatic cancer diagnostic systems based on histological image classification are important for improving therapeutic decisions. Previous studies propose textural and morphological features for such systems. These features capture patterns in histological images that are useful for both cancer grading and subtyping. However, because many of these features lack a clear biological interpretation, pathologists may be reluctant to adopt these features for clinical diagnosis. We examine the utility of biologically interpretable shape-based features for classification of histological renal tumor images. Using Fourier shape descriptors, we extract shape-based features that capture the distribution of stain-enhanced cellular and tissue structures in each image and evaluate these features using a multi-class prediction model. We compare the predictive performance of the shape-based diagnostic model to that of traditional models, i.e., using textural, morphological and topological features. The shape-based model, with an average accuracy of 77%, outperforms or complements traditional models. We identify the most informative shapes for each renal tumor subtype from the top-selected features. Results suggest that these shapes are not only accurate diagnostic features, but also correlate with known biological characteristics of renal tumors. Shape-based analysis of histological renal tumor images accurately classifies disease subtypes and reveals biologically insightful discriminatory features. This method for shape-based analysis can be extended to other histological datasets to aid pathologists in diagnostic and therapeutic decisions

Determination of the Image Complexity Feature in Pattern Recognition

Directory of Open Access Journals (Sweden)

Veacheslav L. Perju

2003-11-01

Full Text Available The new image complexity informative feature is proposed. The experimental estimation of the image complexity is carried out. There are elaborated two optical-electronic processors for image complexity calculation. The determination of the necessary number of the image's digitization elements depending on the image complexity was carried out. The accuracy of the image complexity feature calculation was made.

Image fusion in x-ray differential phase-contrast imaging

Science.gov (United States)

Haas, W.; Polyanskaya, M.; Bayer, F.; Gödel, K.; Hofmann, H.; Rieger, J.; Ritter, A.; Weber, T.; Wucherer, L.; Durst, J.; Michel, T.; Anton, G.; Hornegger, J.

2012-02-01

Phase-contrast imaging is a novel modality in the field of medical X-ray imaging. The pioneer method is the grating-based interferometry which has no special requirements to the X-ray source and object size. Furthermore, it provides three different types of information of an investigated object simultaneously - absorption, differential phase-contrast and dark-field images. Differential phase-contrast and dark-field images represent a completely new information which has not yet been investigated and studied in context of medical imaging. In order to introduce phase-contrast imaging as a new modality into medical environment the resulting information about the object has to be correctly interpreted. The three output images reflect different properties of the same object the main challenge is to combine and visualize these data in such a way that it diminish the information explosion and reduce the complexity of its interpretation. This paper presents an intuitive image fusion approach which allows to operate with grating-based phase-contrast images. It combines information of the three different images and provides a single image. The approach is implemented in a fusion framework which is aimed to support physicians in study and analysis. The framework provides the user with an intuitive graphical user interface allowing to control the fusion process. The example given in this work shows the functionality of the proposed method and the great potential of phase-contrast imaging in medical practice.

Application of eigen value expansion to feature extraction from MRI images

International Nuclear Information System (INIS)

Kinosada, Yasutomi; Takeda, Kan; Nakagawa, Tsuyoshi

1991-01-01

The eigen value expansion technique was utilized for feature extraction of magnetic resonance (MR) images. The eigen value expansion is an orthonormal transformation method which decomposes a set of images into some statistically uncorrelated images. The technique was applied to MR images obtained with various imaging parameters at the same anatomical site. It generated one mean image and another set of images called bases for the images. Each basis corresponds to a feature in the images. A basis is, therefore, utilized for the feature extraction from MR images and a weighted sum of bases is also used for the feature enhancement. Furthermore, any MR image with specific feature can be obtained from a linear combination of the mean image and all of the bases. Images of hemorrhaged brain with a spin echo sequence and a series of cinematic cerebro spinal fluid flow images with ECG gated gradient refocused echo sequence were employed to estimate the ability of the feature extraction and the contrast enhancement. Results showed us that proposed application of an eigen value expansion technique to the feature extraction of MR images is good enough to clinical use and superior to other feature extraction methods such as producing a calculated MR image with a given TR and TE or the matched-filter method in processing speed and reproducibility of results. (author)

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features

Science.gov (United States)

Mousavi Kahaki, Seyed Mostafa; Nordin, Md Jan; Ashtari, Amir H.; J. Zahra, Sophia

2016-01-01

An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics—such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient—are insufficient for achieving adequate results under different image deformations. Thus, new descriptor’s similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence. PMID:26985996

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features.

Directory of Open Access Journals (Sweden)

Seyed Mostafa Mousavi Kahaki

Full Text Available An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics--such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient--are insufficient for achieving adequate results under different image deformations. Thus, new descriptor's similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence.

THE EFFECT OF IMAGE ENHANCEMENT METHODS DURING FEATURE DETECTION AND MATCHING OF THERMAL IMAGES

Directory of Open Access Journals (Sweden)

O. Akcay

2017-05-01

Full Text Available A successful image matching is essential to provide an automatic photogrammetric process accurately. Feature detection, extraction and matching algorithms have performed on the high resolution images perfectly. However, images of cameras, which are equipped with low-resolution thermal sensors are problematic with the current algorithms. In this paper, some digital image processing techniques were applied to the low-resolution images taken with Optris PI 450 382 x 288 pixel optical resolution lightweight thermal camera to increase extraction and matching performance. Image enhancement methods that adjust low quality digital thermal images, were used to produce more suitable images for detection and extraction. Three main digital image process techniques: histogram equalization, high pass and low pass filters were considered to increase the signal-to-noise ratio, sharpen image, remove noise, respectively. Later on, the pre-processed images were evaluated using current image detection and feature extraction methods Maximally Stable Extremal Regions (MSER and Speeded Up Robust Features (SURF algorithms. Obtained results showed that some enhancement methods increased number of extracted features and decreased blunder errors during image matching. Consequently, the effects of different pre-process techniques were compared in the paper.

Biomedical imaging modality classification using combined visual features and textual terms.

Science.gov (United States)

Han, Xian-Hua; Chen, Yen-Wei

2011-01-01

We describe an approach for the automatic modality classification in medical image retrieval task of the 2010 CLEF cross-language image retrieval campaign (ImageCLEF). This paper is focused on the process of feature extraction from medical images and fuses the different extracted visual features and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. Then, we combine the different features using normalized kernel functions for SVM classification. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010.

Molecular biological features of male germ cell differentiation

Science.gov (United States)

HIROSE, MIKA; TOKUHIRO, KEIZO; TAINAKA, HITOSHI; MIYAGAWA, YASUSHI; TSUJIMURA, AKIRA; OKUYAMA, AKIHIKO; NISHIMUNE, YOSHITAKE

2007-01-01

Somatic cell differentiation is required throughout the life of a multicellular organism to maintain homeostasis. In contrast, germ cells have only one specific function; to preserve the species by conveying the parental genes to the next generation. Recent studies of the development and molecular biology of the male germ cell have identified many genes, or isoforms, that are specifically expressed in the male germ cell. In the present review, we consider the unique features of male germ cell differentiation. (Reprod Med Biol 2007; 6: 1–9) PMID:29699260

MR imaging features and staging of neuroendocrine carcinomas of the uterine cervix with pathological correlations

Energy Technology Data Exchange (ETDEWEB)

Duan, Xiaohui; Zhang, Xiang; Hu, Huijun; Li, Guozhao; Wang, Dongye; Zhang, Fang; Shen, Jun [Sun Yat-Sen University, Department of Radiology, Sun Yat-Sen Memorial Hospital, Guangzhou (China); Ban, Xiaohua [Sun Yat-Sen University, Medical Imaging and Minimally Invasive Interventional Center and State Key Laboratory of Oncology in Southern China, Cancer Center, Guangzhou, Guangdong (China); Wang, Charles Qian [Sun Yat-Sen University, Department of Radiology, Sun Yat-Sen Memorial Hospital, Guangzhou (China); University of New South Wales, JMO, Westmead Hospital, Sydney (Australia)

2016-12-15

To determine MR imaging features and staging accuracy of neuroendocrine carcinomas (NECs) of the uterine cervix with pathological correlations. Twenty-six patients with histologically proven NECs, 60 patients with squamous cell carcinomas (SCCs), and 30 patients with adenocarcinomas of the uterine cervix were included. The clinical data, pathological findings, and MRI findings were reviewed retrospectively. MRI features of cervical NECs, SCCs, and adenocarcinomas were compared, and MRI staging of cervical NECs was compared with the pathological staging. Cervical NECs showed a higher tendency toward a homogeneous signal intensity on T2-weighted imaging and a homogeneous enhancement pattern, as well as a lower ADC value of tumour and a higher incidence of lymphadenopathy, compared with SCCs and adenocarcinomas (P < 0.05). An ADC value cutoff of 0.90 x 10{sup -3} mm{sup 2}/s was robust for differentiation between cervical NECs and other cervical cancers, with a sensitivity of 63.3 % and a specificity of 95 %. In 21 patients who underwent radical hysterectomy and lymphadenectomy, the overall accuracy of tumour staging by MR imaging was 85.7 % with reference to pathology staging. Homogeneous lesion texture and low ADC value are likely suggestive features of cervical NECs and MR imaging is reliable for the staging of cervical NECs. (orig.)

The utility of diffusion-weighted MR imaging for differentiating uterine sarcomas from benign leiomyomas

International Nuclear Information System (INIS)

Tamai, Ken; Saga, Tsuneo; Morisawa, Nobuko; Fujimoto, Koji; Togashi, Kaori; Koyama, Takashi; Mikami, Yoshiki

2008-01-01

The usefulness of diffusion-weighted (DW) magnetic resonance (MR) imaging for the diagnosis of uterine sarcomas was investigated, as well as whether DW images and quantitative measurement of apparent diffusion coefficient (ADC) values can facilitate differentiating uterine sarcomas from benign leiomyomas. MR images including DW images were obtained in 43 surgically treated patients with 58 myometrial tumors, including seven uterine sarcomas (five leiomyosarcomas and two endometrial stromal sarcomas) and 51 benign leiomyomas (43 ordinary leiomyomas, two cellular leiomyomas and six degenerated leiomyomas). Qualitative analysis of non-enhanced and postcontrast MR images and DW images and quantitative measurement of ADC values were performed for each myometrial tumor. Both uterine sarcomas and cellular leiomyomas exhibited high signal intensity on DW images, whereas ordinary leiomyomas and most degenerated leiomyomas showed low signal intensity. The mean ADC value (10 -3 mm 2 /s) of sarcomas was 1.17 ± 0.15, which was lower than those of the normal myometrium (1.62 ± 0.11) and degenerated leiomyomas (1.70 ± 0.11) without any overlap; however, they were overlapped with those of ordinary leiomyomas and cellular leiomyomas. In addition to morphological features on nonenhanced and postcontrast MR sequences, DW imaging and ADC measurement may have a potential ability to differentiate uterine sarcomas from benign leiomyomas. (orig.)

An automated classification system for the differentiation of obstructive lung diseases based on the textural analysis of HRCT images

International Nuclear Information System (INIS)

Park, Seong Hoon; Seo, Joon Beom; Kim, Nam Kug; Lee, Young Kyung; Kim, Song Soo; Chae, Eun Jin; Lee, June Goo

2007-01-01

To develop an automated classification system for the differentiation of obstructive lung diseases based on the textural analysis of HRCT images, and to evaluate the accuracy and usefulness of the system. For textural analysis, histogram features, gradient features, run length encoding, and a co-occurrence matrix were employed. A Bayesian classifier was used for automated classification. The images (image number n = 256) were selected from the HRCT images obtained from 17 healthy subjects (n = 67), 26 patients with bronchiolitis obliterans (n = 70), 28 patients with mild centrilobular emphysema (n = 65), and 21 patients with panlobular emphysema or severe centrilobular emphysema (n = 63). An five-fold cross-validation method was used to assess the performance of the system. Class-specific sensitivities were analyzed and the overall accuracy of the system was assessed with kappa statistics. The sensitivity of the system for each class was as follows: normal lung 84.9%, bronchiolitis obliterans 83.8%, mild centrilobular emphysema 77.0%, and panlobular emphysema or severe centrilobular emphysema 95.8%. The overall performance for differentiating each disease and the normal lung was satisfactory with a kappa value of 0.779. An automated classification system for the differentiation between obstructive lung diseases based on the textural analysis of HRCT images was developed. The proposed system discriminates well between the various obstructive lung diseases and the normal lung

Automatic Classification of Normal and Cancer Lung CT Images Using Multiscale AM-FM Features

Directory of Open Access Journals (Sweden)

Eman Magdy

2015-01-01

Full Text Available Computer-aided diagnostic (CAD systems provide fast and reliable diagnosis for medical images. In this paper, CAD system is proposed to analyze and automatically segment the lungs and classify each lung into normal or cancer. Using 70 different patients’ lung CT dataset, Wiener filtering on the original CT images is applied firstly as a preprocessing step. Secondly, we combine histogram analysis with thresholding and morphological operations to segment the lung regions and extract each lung separately. Amplitude-Modulation Frequency-Modulation (AM-FM method thirdly, has been used to extract features for ROIs. Then, the significant AM-FM features have been selected using Partial Least Squares Regression (PLSR for classification step. Finally, K-nearest neighbour (KNN, support vector machine (SVM, naïve Bayes, and linear classifiers have been used with the selected AM-FM features. The performance of each classifier in terms of accuracy, sensitivity, and specificity is evaluated. The results indicate that our proposed CAD system succeeded to differentiate between normal and cancer lungs and achieved 95% accuracy in case of the linear classifier.

Image mosaicking based on feature points using color-invariant values

Science.gov (United States)

Lee, Dong-Chang; Kwon, Oh-Seol; Ko, Kyung-Woo; Lee, Ho-Young; Ha, Yeong-Ho

2008-02-01

In the field of computer vision, image mosaicking is achieved using image features, such as textures, colors, and shapes between corresponding images, or local descriptors representing neighborhoods of feature points extracted from corresponding images. However, image mosaicking based on feature points has attracted more recent attention due to the simplicity of the geometric transformation, regardless of distortion and differences in intensity generated by camera motion in consecutive images. Yet, since most feature-point matching algorithms extract feature points using gray values, identifying corresponding points becomes difficult in the case of changing illumination and images with a similar intensity. Accordingly, to solve these problems, this paper proposes a method of image mosaicking based on feature points using color information of images. Essentially, the digital values acquired from a real digital color camera are converted to values of a virtual camera with distinct narrow bands. Values based on the surface reflectance and invariant to the chromaticity of various illuminations are then derived from the virtual camera values and defined as color-invariant values invariant to changing illuminations. The validity of these color-invariant values is verified in a test using a Macbeth Color-Checker under simulated illuminations. The test also compares the proposed method using the color-invariant values with the conventional SIFT algorithm. The accuracy of the matching between the feature points extracted using the proposed method is increased, while image mosaicking using color information is also achieved.

A chondroblastoma versus a giant cell tumor: emphasis on the MR imaging features

Energy Technology Data Exchange (ETDEWEB)

Chai, Jee Won; Hong, Sung Hwan; Choi, Ja Young; Kim, Na Ra; Choi, Jung Ah; Kang, Heung Sik [Seoul National University College of Medicine, Seoul (Korea, Republic of)

2007-10-15

To assess the MR imaging features in differentiating a chondroblastoma (CB) from a giant cell tumor (GCT), with an emphasis on the accompanying peritumoral bone marrow edema. MR imaging findings in 20 patients with CB were compared with the imaging features of 22 patients with GCT. The location of the lesion, signal intensity, adjacent cortical change, degree of accompanying bone marrow edema, synovitis in the adjacent joint and cystic change were analyzed. The findings of CB and GCT were examined statistically with use of Fisher's exact test. The incidence ratios of MR imaging findings were as follows (CB:GCT). Metaphyseal dominant involvement (2:21), partial cortical disruption (2:14), extensive bone marrow edema surrounding the tumor (14:0) and synovitis in the adjacent joint (11:2) were statistically different in incidence between CB and GCT ({rho} < 0.01). The inhomogeneous signal intensity (17:17) and cystic change (10:15) were not different in incidence between a CB and GCT. The presence of metaphyseal dominant involvement and cortical disruption favors a diagnosis of a GCT rather than a CB. In contrast, extensive bone marrow edema surrounding the tumor and synovitis in the adjacent joint are highly indicative of a CB.

Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation

Science.gov (United States)

Kiechle, Martin; Storath, Martin; Weinmann, Andreas; Kleinsteuber, Martin

2018-04-01

Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.

Hepatocellular carcinoma with neuroendocrine differentiation: clinical and imaging findings in five patients

International Nuclear Information System (INIS)

Park, Seong Hoon; Kang, Myeong Jin; Cho, Jin Han

2008-01-01

To describe the clinical and imaging findings of hepatocellular carcinoma with neuroendocrine differentiation, which is an extremely rare variant of hepatocellular carcinoma. We collected five patients who had histopathologically proven hepatocellular carcinoma with neuroendocrine differentiation, and described morphologic feature, enhancement pattern of tumors, extrahepatic manifestation and clinical findings. At CT, the tumor size ranged from 8 to 17 cm (mean: 12 cm) in maximum diameter. The tumor margin was well-defined and smooth in four patients and all tumors were heterogeneously hypoattenuating. Four tumor showed rim enhancement on arterial and portal phases. Local invasion to the portal vein, intrahepatic duct and gallbladder were seen. Extrahepatic manifestations included hepatic metastases, lymph node metastasis. At ultrasonography, the tumor showed heterogeneously hyperechoic in all patients and hypoechoic rim was found in four patients. Of four patients who were followed up, one survived for 16 months after initial diagnosis, while the other three died within 3 months after initial diagnosis. As described above, clinical and imaging findings of hepatocellular carcinoma with neuroendocrine differentiation were not specific. However, this rare variant of hepatocellular carcinoma could be considered when hepatic tumor is found in an advanced stage and shows persistent rim enhancement at CT

Bread crumb classification using fractal and multifractal features

OpenAIRE

Baravalle, Rodrigo Guillermo; Delrieux, Claudio Augusto; Gómez, Juan Carlos

2017-01-01

Adequate image descriptors are fundamental in image classification and object recognition. Main requirements for image features are robustness and low dimensionality which would lead to low classification errors in a variety of situations and with a reasonable computational cost. In this context, the identification of materials poses a significant challenge, since typical (geometric and/or differential) feature extraction methods are not robust enough. Texture features based on Fourier or wav...

[Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

Science.gov (United States)

Li, Jing; Hong, Wenxue

2014-12-01

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

Hyperspectral image classifier based on beach spectral feature

International Nuclear Information System (INIS)

Liang, Zhang; Lianru, Gao; Bing, Zhang

2014-01-01

The seashore, especially coral bank, is sensitive to human activities and environmental changes. A multispectral image, with coarse spectral resolution, is inadaptable for identify subtle spectral distinctions between various beaches. To the contrary, hyperspectral image with narrow and consecutive channels increases our capability to retrieve minor spectral features which is suit for identification and classification of surface materials on the shore. Herein, this paper used airborne hyperspectral data, in addition to ground spectral data to study the beaches in Qingdao. The image data first went through image pretreatment to deal with the disturbance of noise, radiation inconsistence and distortion. In succession, the reflection spectrum, the derivative spectrum and the spectral absorption features of the beach surface were inspected in search of diagnostic features. Hence, spectra indices specific for the unique environment of seashore were developed. According to expert decisions based on image spectrums, the beaches are ultimately classified into sand beach, rock beach, vegetation beach, mud beach, bare land and water. In situ surveying reflection spectrum from GER1500 field spectrometer validated the classification production. In conclusion, the classification approach under expert decision based on feature spectrum is proved to be feasible for beaches

Combining Landform Thematic Layer and Object-Oriented Image Analysis to Map the Surface Features of Mountainous Flood Plain Areas

Science.gov (United States)

Chuang, H.-K.; Lin, M.-L.; Huang, W.-C.

2012-04-01

The Typhoon Morakot on August 2009 brought more than 2,000 mm of cumulative rainfall in southern Taiwan, the extreme rainfall event caused serious damage to the Kaoping River basin. The losses were mostly blamed on the landslides along sides of the river, and shifting of the watercourse even led to the failure of roads and bridges, as well as flooding and levees damage happened around the villages on flood bank and terraces. Alluvial fans resulted from debris flow of stream feeders blocked the main watercourse and debris dam was even formed and collapsed. These disasters have highlighted the importance of identification and map the watercourse alteration, surface features of flood plain area and artificial structures soon after the catastrophic typhoon event for natural hazard mitigation. Interpretation of remote sensing images is an efficient approach to acquire spatial information for vast areas, therefore making it suitable for the differentiation of terrain and objects near the vast flood plain areas in a short term. The object-oriented image analysis program (Definiens Developer 7.0) and multi-band high resolution satellite images (QuickBird, DigitalGlobe) was utilized to interpret the flood plain features from Liouguei to Baolai of the the Kaoping River basin after Typhoon Morakot. Object-oriented image interpretation is the process of using homogenized image blocks as elements instead of pixels for different shapes, textures and the mutual relationships of adjacent elements, as well as categorized conditions and rules for semi-artificial interpretation of surface features. Digital terrain models (DTM) are also employed along with the above process to produce layers with specific "landform thematic layers". These layers are especially helpful in differentiating some confusing categories in the spectrum analysis with improved accuracy, such as landslides and riverbeds, as well as terraces, riverbanks, which are of significant engineering importance in disaster

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

Directory of Open Access Journals (Sweden)

Xian-Hua Han

2011-01-01

extraction from medical images and fuses the different extracted visual features and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. Then, we combine the different features using normalized kernel functions for SVM classification. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010.

Diffusion tensor image registration using hybrid connectivity and tensor features.

Science.gov (United States)

Wang, Qian; Yap, Pew-Thian; Wu, Guorong; Shen, Dinggang

2014-07-01

Most existing diffusion tensor imaging (DTI) registration methods estimate structural correspondences based on voxelwise matching of tensors. The rich connectivity information that is given by DTI, however, is often neglected. In this article, we propose to integrate complementary information given by connectivity features and tensor features for improved registration accuracy. To utilize connectivity information, we place multiple anchors representing different brain anatomies in the image space, and define the connectivity features for each voxel as the geodesic distances from all anchors to the voxel under consideration. The geodesic distance, which is computed in relation to the tensor field, encapsulates information of brain connectivity. We also extract tensor features for every voxel to reflect the local statistics of tensors in its neighborhood. We then combine both connectivity features and tensor features for registration of tensor images. From the images, landmarks are selected automatically and their correspondences are determined based on their connectivity and tensor feature vectors. The deformation field that deforms one tensor image to the other is iteratively estimated and optimized according to the landmarks and their associated correspondences. Experimental results show that, by using connectivity features and tensor features simultaneously, registration accuracy is increased substantially compared with the cases using either type of features alone. Copyright © 2013 Wiley Periodicals, Inc.

Edge detection of optical subaperture image based on improved differential box-counting method

Science.gov (United States)

Li, Yi; Hui, Mei; Liu, Ming; Dong, Liquan; Kong, Lingqin; Zhao, Yuejin

2018-01-01

Optical synthetic aperture imaging technology is an effective approach to improve imaging resolution. Compared with monolithic mirror system, the image of optical synthetic aperture system is often more complex at the edge, and as a result of the existence of gap between segments, which makes stitching becomes a difficult problem. So it is necessary to extract the edge of subaperture image for achieving effective stitching. Fractal dimension as a measure feature can describe image surface texture characteristics, which provides a new approach for edge detection. In our research, an improved differential box-counting method is used to calculate fractal dimension of image, then the obtained fractal dimension is mapped to grayscale image to detect edges. Compared with original differential box-counting method, this method has two improvements as follows: by modifying the box-counting mechanism, a box with a fixed height is replaced by a box with adaptive height, which solves the problem of over-counting the number of boxes covering image intensity surface; an image reconstruction method based on super-resolution convolutional neural network is used to enlarge small size image, which can solve the problem that fractal dimension can't be calculated accurately under the small size image, and this method may well maintain scale invariability of fractal dimension. The experimental results show that the proposed algorithm can effectively eliminate noise and has a lower false detection rate compared with the traditional edge detection algorithms. In addition, this algorithm can maintain the integrity and continuity of image edge in the case of retaining important edge information.

MR imaging features of craniodiaphyseal dysplasia

Energy Technology Data Exchange (ETDEWEB)

Marden, Franklin A. [Mallinckrodt Institute of Radiology, Washington University Medical Center, 510 South Kingshighway Blvd., MO 63110, St. Louis (United States); Department of Radiology, St. Louis Children' s Hospital, Children' s Place, MO 63110, St. Louis (United States); Wippold, Franz J. [Mallinckrodt Institute of Radiology, Washington University Medical Center, 510 South Kingshighway Blvd., MO 63110, St. Louis (United States); Department of Radiology, St. Louis Children' s Hospital, Children' s Place, MO 63110, St. Louis (United States); Department of Radiology/Nuclear Medicine, F. Edward Hebert School of Medicine, Uniformed Services University of the Health Sciences, MD 20814, Bethesda (United States)

2004-02-01

We report the magnetic resonance (MR) imaging findings in a 4-year-old girl with characteristic radiographic and computed tomography (CT) features of craniodiaphyseal dysplasia. MR imaging exquisitely depicted cranial nerve compression, small foramen magnum, hydrocephalus, and other intracranial complications of this syndrome. A syrinx of the cervical spinal cord was demonstrated. We suggest that MR imaging become a routine component of the evaluation of these patients. (orig.)

Evaluation of MR diffusion-weighted imaging in differentiating endometriosis infiltrating the bowel from colorectal carcinoma

International Nuclear Information System (INIS)

Busard, M.P.H.; Pieters-van den Bos, I.C.; Mijatovic, V.; Van Kuijk, C.; Bleeker, M.C.G.; Waesberghe, J.H.T.M. van

2012-01-01

Objective: Endometriosis infiltrating the bowel may be difficult to differentiate from colorectal carcinoma in cases that present with non-specific clinical and imaging features. The aim of this study is to assess the value of MR diffusion-weighted imaging (DWI) in differentiating endometriosis infiltrating the bowel from colorectal carcinoma. Methods: In 66 patients, MR DWI was added to the standard imaging protocol in patients visiting our outdoor MR clinic for the analysis of suspected or known deep infiltrating endometriosis (DIE). In patients diagnosed with DIE infiltrating the bowel on MR imaging, high b-value diffusion-weighted images were qualitatively assessed by two readers in consensus and compared to high b-value diffusion weighted images in 15 patients evaluated for colorectal carcinoma. In addition, ADC values of lesions were calculated, using b-values of 50, 400 and 800 s/mm 2 . Results: A total of 15 patients were diagnosed with DIE infiltrating the bowel on MR imaging. Endometriosis infiltrating the bowel showed low signal intensity on high b-value diffusion-weighted images in all patients, whereas colorectal carcinoma showed high signal intensity on high b-value diffusion-weighted images in all patients. Mean ADC value in endometriosis infiltrating the bowel (0.80 ± 0.06 × 10 −3 mm 2 /s) was significantly lower compared to mean ADC value in colorectal carcinoma (0.86 ± 0.06 × 10 −3 mm 2 /s), but with considerable overlap between ADC values. Conclusion: Only qualitative assessment of MR DWI may be valuable to facilitate differentiation between endometriosis infiltrating the bowel and colorectal carcinoma.

MR Imaging Features of Fibrocystic Change of the Breast

Science.gov (United States)

Chen, Jeon-Hor; Liu, Hui; Baek, Hyeon-Man; Nalcioglu, Orhan; Su, Min-Ying

2008-01-01

Purpose Studies specifically reporting MR imaging of fibrocystic change (FCC) of the breast are very few and its MR imaging features are not clearly known. The purpose of this study was to analyze the MR imaging features of FCC of the breast. Materials and Methods Thirty one patients of pathologically proved FCC of the breast were retrospectively reviewed. The MRI study was performed using a 1.5 T MR scanner with standard bilateral breast coil. The imaging protocol consisted of pre-contrast T1W imaging and dynamic contrast-enhanced axial T1W imaging. The MRI features were interpreted based on the morphologic and enhancement kinetic descriptors defined on ACR BIRADS-MRI lexicon. Results FCC of the breast had a wide spectrum of morphologic and kinetic features on MRI. Two types of FCC were found, including a more diffuse type of non-mass lesion (12/31, 39%) showing benign enhancement kinetic pattern with medium wash-in in early phase (9/10, 90%) and a focal mass type lesion (11/31, 35%) with enhancement kinetic usually showing rapid up-slope mimicking a breast cancer (8/11, 73%). Conclusion MRI is able to elaborate the diverse imaging features of fibrocystic change of the breast. Our result showed that FCC presenting as focal mass type lesion were usually over-diagnosed as malignancy. Understanding MR imaging of FCC is important to determine which cohort of patients should be followed up alone or receive aggressive management. PMID:18436406

Uniform competency-based local feature extraction for remote sensing images

Science.gov (United States)

Sedaghat, Amin; Mohammadi, Nazila

2018-01-01

Local feature detectors are widely used in many photogrammetry and remote sensing applications. The quantity and distribution of the local features play a critical role in the quality of the image matching process, particularly for multi-sensor high resolution remote sensing image registration. However, conventional local feature detectors cannot extract desirable matched features either in terms of the number of correct matches or the spatial and scale distribution in multi-sensor remote sensing images. To address this problem, this paper proposes a novel method for uniform and robust local feature extraction for remote sensing images, which is based on a novel competency criterion and scale and location distribution constraints. The proposed method, called uniform competency (UC) local feature extraction, can be easily applied to any local feature detector for various kinds of applications. The proposed competency criterion is based on a weighted ranking process using three quality measures, including robustness, spatial saliency and scale parameters, which is performed in a multi-layer gridding schema. For evaluation, five state-of-the-art local feature detector approaches, namely, scale-invariant feature transform (SIFT), speeded up robust features (SURF), scale-invariant feature operator (SFOP), maximally stable extremal region (MSER) and hessian-affine, are used. The proposed UC-based feature extraction algorithms were successfully applied to match various synthetic and real satellite image pairs, and the results demonstrate its capability to increase matching performance and to improve the spatial distribution. The code to carry out the UC feature extraction is available from href="https://www.researchgate.net/publication/317956777_UC-Feature_Extraction.

Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma.

Science.gov (United States)

Feng, Zhichao; Rong, Pengfei; Cao, Peng; Zhou, Qingyu; Zhu, Wenwei; Yan, Zhimin; Liu, Qianyun; Wang, Wei

2018-04-01

To evaluate the diagnostic performance of machine-learning based quantitative texture analysis of CT images to differentiate small (≤ 4 cm) angiomyolipoma without visible fat (AMLwvf) from renal cell carcinoma (RCC). This single-institutional retrospective study included 58 patients with pathologically proven small renal mass (17 in AMLwvf and 41 in RCC groups). Texture features were extracted from the largest possible tumorous regions of interest (ROIs) by manual segmentation in preoperative three-phase CT images. Interobserver reliability and the Mann-Whitney U test were applied to select features preliminarily. Then support vector machine with recursive feature elimination (SVM-RFE) and synthetic minority oversampling technique (SMOTE) were adopted to establish discriminative classifiers, and the performance of classifiers was assessed. Of the 42 extracted features, 16 candidate features showed significant intergroup differences (P Machine learning analysis of CT texture features can facilitate the accurate differentiation of small AMLwvf from RCC. • Although conventional CT is useful for diagnosis of SRMs, it has limitations. • Machine-learning based CT texture analysis facilitate differentiation of small AMLwvf from RCC. • The highest accuracy of SVM-RFE+SMOTE classifier reached 93.9 %. • Texture analysis combined with machine-learning methods might spare unnecessary surgery for AMLwvf.

Heterotopic Pancreas: Histopathologic Features, Imaging Findings, and Complications.

Science.gov (United States)

Rezvani, Maryam; Menias, Christine; Sandrasegaran, Kumaresan; Olpin, Jeffrey D; Elsayes, Khaled M; Shaaban, Akram M

2017-01-01

Heterotopic pancreas is a congenital anomaly in which pancreatic tissue is anatomically separate from the main gland. The most common locations of this displacement include the upper gastrointestinal tract-specifically, the stomach, duodenum, and proximal jejunum. Less common sites are the esophagus, ileum, Meckel diverticulum, biliary tree, mesentery, and spleen. Uncomplicated heterotopic pancreas is typically asymptomatic, with the lesion being discovered incidentally during an unrelated surgery, during an imaging examination, or at autopsy. The most common computed tomographic appearance of heterotopic pancreas is that of a small oval intramural mass with microlobulated margins and an endoluminal growth pattern. The attenuation and enhancement characteristics of these lesions parallel their histologic composition. Acinus-dominant lesions demonstrate avid homogeneous enhancement after intravenous contrast material administration, whereas duct-dominant lesions are hypovascular and heterogeneous. At magnetic resonance imaging, the heterotopic pancreas is isointense to the orthotopic pancreas, with characteristic T1 hyperintensity and early avid enhancement after intravenous gadolinium-based contrast material administration. Heterotopic pancreatic tissue has a rudimentary ductal system in which an orifice is sometimes visible at imaging as a central umbilication of the lesion. Complications of heterotopic pancreas include pancreatitis, pseudocyst formation, malignant degeneration, gastrointestinal bleeding, bowel obstruction, and intussusception. Certain complications may be erroneously diagnosed as malignancy. Paraduodenal pancreatitis is thought to be due to cystic degeneration of heterotopic pancreatic tissue in the medial wall of the duodenum. Recognizing the characteristic imaging features of heterotopic pancreas aids in differentiating it from cancer and thus in avoiding unnecessary surgery. © RSNA, 2017.

Robust Image Hashing Using Radon Transform and Invariant Features

Directory of Open Access Journals (Sweden)

Y.L. Liu

2016-09-01

Full Text Available A robust image hashing method based on radon transform and invariant features is proposed for image authentication, image retrieval, and image detection. Specifically, an input image is firstly converted into a counterpart with a normalized size. Then the invariant centroid algorithm is applied to obtain the invariant feature point and the surrounding circular area, and the radon transform is employed to acquire the mapping coefficient matrix of the area. Finally, the hashing sequence is generated by combining the feature vectors and the invariant moments calculated from the coefficient matrix. Experimental results show that this method not only can resist against the normal image processing operations, but also some geometric distortions. Comparisons of receiver operating characteristic (ROC curve indicate that the proposed method outperforms some existing methods in classification between perceptual robustness and discrimination.

On-line transmission electron microscopic image analysis of chromatin texture for differentiation of thyroid gland tumors.

Science.gov (United States)

Kriete, A; Schäffer, R; Harms, H; Aus, H M

1987-06-01

Nuclei of the cells from the thyroid gland were analyzed in a transmission electron microscope by direct TV scanning and on-line image processing. The method uses the advantages of a visual-perception model to detect structures in noisy and low-contrast images. The features analyzed include area, a form factor and texture parameters from the second derivative stage. Three tumor-free thyroid tissues, three follicular adenomas, three follicular carcinomas and three papillary carcinomas were studied. The computer-aided cytophotometric method showed that the most significant differences were the statistics of the chromatin texture features of homogeneity and regularity. These findings document the possibility of an automated differentiation of tumors at the ultrastructural level.

Feature representation of RGB-D images using joint spatial-depth feature pooling

DEFF Research Database (Denmark)

Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

2016-01-01

Recent development in depth imaging technology makes acquisition of depth information easier. With the additional depth cue, RGB-D cameras can provide effective support for many RGB-D perception tasks beyond traditional RGB information. However, current feature representation based on RGB-D image...

FEATURE MATCHING OF HISTORICAL IMAGES BASED ON GEOMETRY OF QUADRILATERALS

Directory of Open Access Journals (Sweden)

F. Maiwald

2018-05-01

Full Text Available This contribution shows an approach to match historical images from the photo library of the Saxon State and University Library Dresden (SLUB in the context of a historical three-dimensional city model of Dresden. In comparison to recent images, historical photography provides diverse factors which make an automatical image analysis (feature detection, feature matching and relative orientation of images difficult. Due to e.g. film grain, dust particles or the digitalization process, historical images are often covered by noise interfering with the image signal needed for a robust feature matching. The presented approach uses quadrilaterals in image space as these are commonly available in man-made structures and façade images (windows, stones, claddings. It is explained how to generally detect quadrilaterals in images. Consequently, the properties of the quadrilaterals as well as the relationship to neighbouring quadrilaterals are used for the description and matching of feature points. The results show that most of the matches are robust and correct but still small in numbers.

Multi-spectral endogenous fluorescence imaging for bacterial differentiation

Science.gov (United States)

Chernomyrdin, Nikita V.; Babayants, Margarita V.; Korotkov, Oleg V.; Kudrin, Konstantin G.; Rimskaya, Elena N.; Shikunova, Irina A.; Kurlov, Vladimir N.; Cherkasova, Olga P.; Komandin, Gennady A.; Reshetov, Igor V.; Zaytsev, Kirill I.

2017-07-01

In this paper, the multi-spectral endogenous fluorescence imaging was implemented for bacterial differentiation. The fluorescence imaging was performed using a digital camera equipped with a set of visual bandpass filters. Narrowband 365 nm ultraviolet radiation passed through a beam homogenizer was used to excite the sample fluorescence. In order to increase a signal-to-noise ratio and suppress a non-fluorescence background in images, the intensity of the UV excitation was modulated using a mechanical chopper. The principal components were introduced for differentiating the samples of bacteria based on the multi-spectral endogenous fluorescence images.

Hand and wrist arthritis of Behcet disease: Imaging features

International Nuclear Information System (INIS)

Sugawara, Shunsuke; Ehara, Shigeru; Hitachi, Shin; Sugimoto, Hideharu

2010-01-01

Background: Reports on arthritis in Behcet disease are relatively scarce, and imaging features vary. Purpose: To document the various imaging features of articular disorders of the hand and wrist in Behcet disease. Material and Methods: Four patients, four women aged 26 to 65 years, fulfilling the diagnostic criteria of Behcet disease, with imaging findings of hand and wrist arthritis, were seen in two institutions. Radiography and magnetic resonance (MR) imaging were studied to elucidate the pattern and distribution. Results: Both non-erosive arthritis and erosive arthritis of different features were noted: one with non-erosive synovitis of the wrist, one with wrist synovitis with minimal erosion, and two with erosive arthritis of the distal interphalangeal joint. Conclusion: Imaging manifestations of arthritis of Behcet disease vary, and may be similar to other seronegative arthritides

Image Retrieval based on Integration between Color and Geometric Moment Features

International Nuclear Information System (INIS)

Saad, M.H.; Saleh, H.I.; Konbor, H.; Ashour, M.

2012-01-01

Content based image retrieval is the retrieval of images based on visual features such as colour, texture and shape. .the Current approaches to CBIR differ in terms of which image features are extracted; recent work deals with combination of distances or scores from different and usually independent representations in an attempt to induce high level semantics from the low level descriptors of the images. content-based image retrieval has many application areas such as, education, commerce, military, searching, commerce, and biomedicine and Web image classification. This paper proposes a new image retrieval system, which uses color and geometric moment feature to form the feature vectors. Bhattacharyya distance and histogram intersection are used to perform feature matching. This framework integrates the color histogram which represents the global feature and geometric moment as local descriptor to enhance the retrieval results. The proposed technique is proper for precisely retrieving images even in deformation cases such as geometric deformations and noise. It is tested on a standard the results shows that a combination of our approach as a local image descriptor with other global descriptors outperforms other approaches.

Automated oral cancer identification using histopathological images: a hybrid feature extraction paradigm.

Science.gov (United States)

Krishnan, M Muthu Rama; Venkatraghavan, Vikram; Acharya, U Rajendra; Pal, Mousumi; Paul, Ranjan Rashmi; Min, Lim Choo; Ray, Ajoy Kumar; Chatterjee, Jyotirmoy; Chakraborty, Chandan

2012-02-01

Oral cancer (OC) is the sixth most common cancer in the world. In India it is the most common malignant neoplasm. Histopathological images have widely been used in the differential diagnosis of normal, oral precancerous (oral sub-mucous fibrosis (OSF)) and cancer lesions. However, this technique is limited by subjective interpretations and less accurate diagnosis. The objective of this work is to improve the classification accuracy based on textural features in the development of a computer assisted screening of OSF. The approach introduced here is to grade the histopathological tissue sections into normal, OSF without Dysplasia (OSFWD) and OSF with Dysplasia (OSFD), which would help the oral onco-pathologists to screen the subjects rapidly. The biopsy sections are stained with H&E. The optical density of the pixels in the light microscopic images is recorded and represented as matrix quantized as integers from 0 to 255 for each fundamental color (Red, Green, Blue), resulting in a M×N×3 matrix of integers. Depending on either normal or OSF condition, the image has various granular structures which are self similar patterns at different scales termed "texture". We have extracted these textural changes using Higher Order Spectra (HOS), Local Binary Pattern (LBP), and Laws Texture Energy (LTE) from the histopathological images (normal, OSFWD and OSFD). These feature vectors were fed to five different classifiers: Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (K-NN), Radial Basis Probabilistic Neural Network (RBPNN) to select the best classifier. Our results show that combination of texture and HOS features coupled with Fuzzy classifier resulted in 95.7% accuracy, sensitivity and specificity of 94.5% and 98.8% respectively. Finally, we have proposed a novel integrated index called Oral Malignancy Index (OMI) using the HOS, LBP, LTE features, to diagnose benign or malignant tissues using just one number. We hope that this OMI can

Feature Importance for Human Epithelial (HEp-2 Cell Image Classification

Directory of Open Access Journals (Sweden)

Vibha Gupta

2018-02-01

Full Text Available Indirect Immuno-Fluorescence (IIF microscopy imaging of human epithelial (HEp-2 cells is a popular method for diagnosing autoimmune diseases. Considering large data volumes, computer-aided diagnosis (CAD systems, based on image-based classification, can help in terms of time, effort, and reliability of diagnosis. Such approaches are based on extracting some representative features from the images. This work explores the selection of the most distinctive features for HEp-2 cell images using various feature selection (FS methods. Considering that there is no single universally optimal feature selection technique, we also propose hybridization of one class of FS methods (filter methods. Furthermore, the notion of variable importance for ranking features, provided by another type of approaches (embedded methods such as Random forest, Random uniform forest is exploited to select a good subset of features from a large set, such that addition of new features does not increase classification accuracy. In this work, we have also, with great consideration, designed class-specific features to capture morphological visual traits of the cell patterns. We perform various experiments and discussions to demonstrate the effectiveness of FS methods along with proposed and a standard feature set. We achieve state-of-the-art performance even with small number of features, obtained after the feature selection.

Renal angiomyoadenomatous tumour: Imaging features

Science.gov (United States)

Sahni, V. Anik; Hirsch, Michelle S.; Silverman, Stuart G.

2012-01-01

Renal angiomyoadenomatous tumour is a rare, recently described neoplasm with a distinctive histological appearance. Although reported in the pathology literature, to our knowledge, no prior reports have described its imaging appearance. We describe the computed tomography and magnetic resonance imaging features of an incidentally detected renal angiomyoadenomatous tumour that appeared as a well-marginated, solid T2-hypointense enhancing mass, in a 50-year-old woman. It is indistinguishable from a variety of benign and malignant renal neoplasms. PMID:23093565

Spindle epithelial tumor with thymus-like differentiation of the thyroid gland: A case report with ultrasonography and CT features, cytological findings and histopathological results

Energy Technology Data Exchange (ETDEWEB)

Kang, Dong Joo; Lee, Yoo Jin; Kim, Dong Wook; Jung, Soo Jin [Busan Paik Hospital, Inje University College of Medicine, Busan (Korea, Republic of)

2016-11-15

Spindle epithelial tumor with thymus-like differentiation (SETTLE) of the thyroid gland is a very rare tumor. It is believed to originate from ectopic thymus tissue within the thyroid gland or from branchial pouch remnants that differentiate along the thymic line. A few reports of SETTLE have been presented, but to the best of our knowledge, there is no case report in which detailed preoperative imaging features of SETTLE have been described. In addition, there are no case reports of SETTLE in Korean patients. Thus, we report a case of SETTLE with detailed preoperative ultrasonography and computed tomography features, cytological findings and histopathological results.

Spindle epithelial tumor with thymus-like differentiation of the thyroid gland: A case report with ultrasonography and CT features, cytological findings and histopathological results

International Nuclear Information System (INIS)

Kang, Dong Joo; Lee, Yoo Jin; Kim, Dong Wook; Jung, Soo Jin

2016-01-01

Spindle epithelial tumor with thymus-like differentiation (SETTLE) of the thyroid gland is a very rare tumor. It is believed to originate from ectopic thymus tissue within the thyroid gland or from branchial pouch remnants that differentiate along the thymic line. A few reports of SETTLE have been presented, but to the best of our knowledge, there is no case report in which detailed preoperative imaging features of SETTLE have been described. In addition, there are no case reports of SETTLE in Korean patients. Thus, we report a case of SETTLE with detailed preoperative ultrasonography and computed tomography features, cytological findings and histopathological results

Spectral differential imaging detection of planets about nearby stars

International Nuclear Information System (INIS)

Smith, W.H.

1987-01-01

Direct ground-based optical imaging of planets in orbit about nearby stars may be accomplished by spectral differential imaging using multiple passband acoustooptic filters with a CCD. This technique provides two essential results. First, it provides a means to modulate the stellar flux reflected from a planet while leaving the flux from the star and other sources in the same field of view unmodulated. Second, spectral differential imaging enables the CCD detector to achieve a sufficiently high dynamic range to locate planets near a star in spite of an integrated brightness differential of 5 x 10 8 . Spectral differential imaging at nearby diffraction limited imaging conditions with telescope apodization can reduce the time to conduct a sensitive planetary search to a few hours in some cases. The feasibility of this idea is discussed here and shown to provide, in principle, the discrimination and sensitivity to detect a Jovian-class planet about stars at distances of about 10 parsecs. The detection of brown dwarfs is shown to be feasible as well. 31 references

Generating description with multi-feature fusion and saliency maps of image

Science.gov (United States)

Liu, Lisha; Ding, Yuxuan; Tian, Chunna; Yuan, Bo

2018-04-01

Generating description for an image can be regard as visual understanding. It is across artificial intelligence, machine learning, natural language processing and many other areas. In this paper, we present a model that generates description for images based on RNN (recurrent neural network) with object attention and multi-feature of images. The deep recurrent neural networks have excellent performance in machine translation, so we use it to generate natural sentence description for images. The proposed method uses single CNN (convolution neural network) that is trained on ImageNet to extract image features. But we think it can not adequately contain the content in images, it may only focus on the object area of image. So we add scene information to image feature using CNN which is trained on Places205. Experiments show that model with multi-feature extracted by two CNNs perform better than which with a single feature. In addition, we make saliency weights on images to emphasize the salient objects in images. We evaluate our model on MSCOCO based on public metrics, and the results show that our model performs better than several state-of-the-art methods.

Special feature on imaging systems and techniques

Science.gov (United States)

Yang, Wuqiang; Giakos, George

2013-07-01

The IEEE International Conference on Imaging Systems and Techniques (IST'2012) was held in Manchester, UK, on 16-17 July 2012. The participants came from 26 countries or regions: Austria, Brazil, Canada, China, Denmark, France, Germany, Greece, India, Iran, Iraq, Italy, Japan, Korea, Latvia, Malaysia, Norway, Poland, Portugal, Sweden, Switzerland, Taiwan, Tunisia, UAE, UK and USA. The technical program of the conference consisted of a series of scientific and technical sessions, exploring physical principles, engineering and applications of new imaging systems and techniques, as reflected by the diversity of the submitted papers. Following a rigorous review process, a total of 123 papers were accepted, and they were organized into 30 oral presentation sessions and a poster session. In addition, six invited keynotes were arranged. The conference not only provided the participants with a unique opportunity to exchange ideas and disseminate research outcomes but also paved a way to establish global collaboration. Following the IST'2012, a total of 55 papers, which were technically extended substantially from their versions in the conference proceeding, were submitted as regular papers to this special feature of Measurement Science and Technology . Following a rigorous reviewing process, 25 papers have been finally accepted for publication in this special feature and they are organized into three categories: (1) industrial tomography, (2) imaging systems and techniques and (3) image processing. These papers not only present the latest developments in the field of imaging systems and techniques but also offer potential solutions to existing problems. We hope that this special feature provides a good reference for researchers who are active in the field and will serve as a catalyst to trigger further research. It has been our great pleasure to be the guest editors of this special feature. We would like to thank the authors for their contributions, without which it would

Can CT and MR Shape and Textural Features Differentiate Benign Versus Malignant Pleural Lesions?

Science.gov (United States)

Pena, Elena; Ojiaku, MacArinze; Inacio, Joao R; Gupta, Ashish; Macdonald, D Blair; Shabana, Wael; Seely, Jean M; Rybicki, Frank J; Dennie, Carole; Thornhill, Rebecca E

2017-10-01

The study aimed to identify a radiomic approach based on CT and or magnetic resonance (MR) features (shape and texture) that may help differentiate benign versus malignant pleural lesions, and to assess if the radiomic model may improve confidence and accuracy of radiologists with different subspecialty backgrounds. Twenty-nine patients with pleural lesions studied on both contrast-enhanced CT and MR imaging were reviewed retrospectively. Three texture and three shape features were extracted. Combinations of features were used to generate logistic regression models using histopathology as outcome. Two thoracic and two abdominal radiologists evaluated their degree of confidence in malignancy. Diagnostic accuracy of radiologists was determined using contingency tables. Cohen's kappa coefficient was used to assess inter-reader agreement. Using optimal threshold criteria, sensitivity, specificity, and accuracy of each feature and combination of features were obtained and compared to the accuracy and confidence of radiologists. The CT model that best discriminated malignant from benign lesions revealed an AUC CT  = 0.92 ± 0.05 (P textural and shape analysis may help distinguish malignant from benign lesions. A radiomics-based approach may increase diagnostic confidence of abdominal radiologists on CT and MR and may potentially improve radiologists' accuracy in the assessment of pleural lesions characterized by MR. Copyright © 2017 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

Prototype Theory Based Feature Representation for PolSAR Images

OpenAIRE

Huang Xiaojing; Yang Xiangli; Huang Pingping; Yang Wen

2016-01-01

This study presents a new feature representation approach for Polarimetric Synthetic Aperture Radar (PolSAR) image based on prototype theory. First, multiple prototype sets are generated using prototype theory. Then, regularized logistic regression is used to predict similarities between a test sample and each prototype set. Finally, the PolSAR image feature representation is obtained by ensemble projection. Experimental results of an unsupervised classification of PolSAR images show that our...

HDR IMAGING FOR FEATURE DETECTION ON DETAILED ARCHITECTURAL SCENES

Directory of Open Access Journals (Sweden)

G. Kontogianni

2015-02-01

Full Text Available 3D reconstruction relies on accurate detection, extraction, description and matching of image features. This is even truer for complex architectural scenes that pose needs for 3D models of high quality, without any loss of detail in geometry or color. Illumination conditions influence the radiometric quality of images, as standard sensors cannot depict properly a wide range of intensities in the same scene. Indeed, overexposed or underexposed pixels cause irreplaceable information loss and degrade digital representation. Images taken under extreme lighting environments may be thus prohibitive for feature detection/extraction and consequently for matching and 3D reconstruction. High Dynamic Range (HDR images could be helpful for these operators because they broaden the limits of illumination range that Standard or Low Dynamic Range (SDR/LDR images can capture and increase in this way the amount of details contained in the image. Experimental results of this study prove this assumption as they examine state of the art feature detectors applied both on standard dynamic range and HDR images.

Textural features for image classification

Science.gov (United States)

Haralick, R. M.; Dinstein, I.; Shanmugam, K.

1973-01-01

Description of some easily computable textural features based on gray-tone spatial dependances, and illustration of their application in category-identification tasks of three different kinds of image data - namely, photomicrographs of five kinds of sandstones, 1:20,000 panchromatic aerial photographs of eight land-use categories, and ERTS multispectral imagery containing several land-use categories. Two kinds of decision rules are used - one for which the decision regions are convex polyhedra (a piecewise-linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89% for the photomicrographs, 82% for the aerial photographic imagery, and 83% for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.

Automated local bright feature image analysis of nuclear proteindistribution identifies changes in tissue phenotype

Energy Technology Data Exchange (ETDEWEB)

Knowles, David; Sudar, Damir; Bator, Carol; Bissell, Mina

2006-02-01

The organization of nuclear proteins is linked to cell and tissue phenotypes. When cells arrest proliferation, undergo apoptosis, or differentiate, the distribution of nuclear proteins changes. Conversely, forced alteration of the distribution of nuclear proteins modifies cell phenotype. Immunostaining and fluorescence microscopy have been critical for such findings. However, there is an increasing need for quantitative analysis of nuclear protein distribution to decipher epigenetic relationships between nuclear structure and cell phenotype, and to unravel the mechanisms linking nuclear structure and function. We have developed imaging methods to quantify the distribution of fluorescently-stained nuclear protein NuMA in different mammary phenotypes obtained using three-dimensional cell culture. Automated image segmentation of DAPI-stained nuclei was generated to isolate thousands of nuclei from three-dimensional confocal images. Prominent features of fluorescently-stained NuMA were detected using a novel local bright feature analysis technique, and their normalized spatial density calculated as a function of the distance from the nuclear perimeter to its center. The results revealed marked changes in the distribution of the density of NuMA bright features as non-neoplastic cells underwent phenotypically normal acinar morphogenesis. In contrast, we did not detect any reorganization of NuMA during the formation of tumor nodules by malignant cells. Importantly, the analysis also discriminated proliferating non-neoplastic cells from proliferating malignant cells, suggesting that these imaging methods are capable of identifying alterations linked not only to the proliferation status but also to the malignant character of cells. We believe that this quantitative analysis will have additional applications for classifying normal and pathological tissues.

Radiomic features analysis in computed tomography images of lung nodule classification.

Directory of Open Access Journals (Sweden)

Chia-Hung Chen

Full Text Available Radiomics, which extract large amount of quantification image features from diagnostic medical images had been widely used for prognostication, treatment response prediction and cancer detection. The treatment options for lung nodules depend on their diagnosis, benign or malignant. Conventionally, lung nodule diagnosis is based on invasive biopsy. Recently, radiomics features, a non-invasive method based on clinical images, have shown high potential in lesion classification, treatment outcome prediction.Lung nodule classification using radiomics based on Computed Tomography (CT image data was investigated and a 4-feature signature was introduced for lung nodule classification. Retrospectively, 72 patients with 75 pulmonary nodules were collected. Radiomics feature extraction was performed on non-enhanced CT images with contours which were delineated by an experienced radiation oncologist.Among the 750 image features in each case, 76 features were found to have significant differences between benign and malignant lesions. A radiomics signature was composed of the best 4 features which included Laws_LSL_min, Laws_SLL_energy, Laws_SSL_skewness and Laws_EEL_uniformity. The accuracy using the signature in benign or malignant classification was 84% with the sensitivity of 92.85% and the specificity of 72.73%.The classification signature based on radiomics features demonstrated very good accuracy and high potential in clinical application.

Prostate cancer multi-feature analysis using trans-rectal ultrasound images

International Nuclear Information System (INIS)

Mohamed, S S; Salama, M M A; Kamel, M; El-Saadany, E F; Rizkalla, K; Chin, J

2005-01-01

This note focuses on extracting and analysing prostate texture features from trans-rectal ultrasound (TRUS) images for tissue characterization. One of the principal contributions of this investigation is the use of the information of the images' frequency domain features and spatial domain features to attain a more accurate diagnosis. Each image is divided into regions of interest (ROIs) by the Gabor multi-resolution analysis, a crucial stage, in which segmentation is achieved according to the frequency response of the image pixels. The pixels with a similar response to the same filter are grouped to form one ROI. Next, from each ROI two different statistical feature sets are constructed; the first set includes four grey level dependence matrix (GLDM) features and the second set consists of five grey level difference vector (GLDV) features. These constructed feature sets are then ranked by the mutual information feature selection (MIFS) algorithm. Here, the features that provide the maximum mutual information of each feature and class (cancerous and non-cancerous) and the minimum mutual information of the selected features are chosen, yeilding a reduced feature subset. The two constructed feature sets, GLDM and GLDV, as well as the reduced feature subset, are examined in terms of three different classifiers: the condensed k-nearest neighbour (CNN), the decision tree (DT) and the support vector machine (SVM). The accuracy classification results range from 87.5% to 93.75%, where the performance of the SVM and that of the DT are significantly better than the performance of the CNN. (note)

Image Mosaic Method Based on SIFT Features of Line Segment

Directory of Open Access Journals (Sweden)

Jun Zhu

2014-01-01

Full Text Available This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling.

High resolution x-ray lensless imaging by differential holographic encoding

Energy Technology Data Exchange (ETDEWEB)

Zhu, D.; Guizar-Sicairos, M.; Wu, B.; Scherz, A.; Acremann, Y.; Tylisczcak, T.; Fischer, P.; Friedenberger, N.; Ollefs, K.; Farle, M.; Fienup, J. R.; Stohr, J.

2009-11-02

X-ray free electron lasers (X-FEL{sub s}) will soon offer femtosecond pulses of laterally coherent x-rays with sufficient intensity to record single-shot coherent scattering patterns for nanoscale imaging. Pulse trains created by splitand-delay techniques even open the door for cinematography on unprecedented nanometer length and femtosecond time scales. A key to real space ultrafast motion pictures is fast and reliable inversion of the recorded reciprocal space scattering patterns. Here we for the first time demonstrate in the x-ray regime the power of a novel technique for lensless high resolution imaging, previously suggested by Guizar-Sicairos and Fienup termed holography with extended reference by autocorrelation linear differential operation, HERALD0. We have achieved superior resolution over conventional x-ray Fourier transform holography (FTH) without sacrifices in SNR or significant increase in algorithmic complexity. By combining images obtained from individual sharp features on an extended reference, we further show that the resolution can be even extended beyond the reference fabrication limits. Direct comparison to iterative phase retrieval image reconstruction and images recorded with stateof- the-art zone plate microscopes is presented. Our results demonstrate the power of HERALDO as a favorable candidate for robust inversion of single-shot coherent scattering patterns.

High-Resolution X-Ray Lensless Imaging by Differential Holographic Encoding

Energy Technology Data Exchange (ETDEWEB)

Zhu, Diling [Stanford Univ., CA (United States). Dept. of Applied Physics; SLAC National Accelerator Lab., Menlo Park, CA (United States). Stanford Inst. for Material and Energy Science; Guizar-Sicairos, Manuel [Univ. of Rochester, NY (United States). Inst. of Optics; Wu, Benny [Stanford Univ., CA (United States). Dept. of Applied Physics; SLAC National Accelerator Lab., Menlo Park, CA (United States). Stanford Inst. for Material and Energy Science; Scherz, Andreas [SLAC National Accelerator Lab., Menlo Park, CA (United States). Stanford Inst. for Material and Energy Science; Acremann, Yves [SLAC National Accelerator Lab., Menlo Park, CA (United States). Photon Ultrafast Laser Science and Engineering Inst. (PULSE); Tyliszczak, Tolek [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Advanced Light Source (ALS); Fischer, Peter [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Center for X-ray Optics; Friedenberger, Nina [Universitat Duisburg-Essen (Germany). Dept. of Physics and Center for Nanointegration Duisburg-Essen (CeNIDE); Ollefs, Katharina [Universitat Duisburg-Essen (Germany). Dept. of Physics and Center for Nanointegration Duisburg-Essen (CeNIDE); Farle, Michael [Universitat Duisburg-Essen (Germany). Dept. of Physics and Center for Nanointegration Duisburg-Essen (CeNIDE); Fienup, James R. [Univ. of Rochester, NY (United States). Inst. of Optics; Stöhr, Joachim [SLAC National Accelerator Lab., Menlo Park, CA (United States). Linac Coherent Light Source (LCLS)

2010-07-01

X-ray free electron lasers (X-FELs) will soon offer femtosecond pulses of laterally coherent x-rays with sufficient intensity to record single-shot coherent scattering patterns for nanoscale imaging. Pulse trains created by split and- delay techniques even open the door for cinematography on unprecedented nanometer length and femtosecond time scales. A key to real space ultrafast motion pictures is fast and reliable inversion of the recorded reciprocal space scattering patterns. Here we for the first time demonstrate in the x-ray regime the power of a novel technique for lensless high resolution imaging, previously suggested by Guizar-Sicairos and Fienup termed holography with extended reference by autocorrelation linear differential operation, HERALD0. We have achieved superior resolution over conventional x-ray Fourier transform holography (FTH) without sacrifices in SNR or significant increase in algorithmic complexity. By combining images obtained from individual sharp features on an extended reference, we further show that the resolution can be even extended beyond the reference fabrication limits. Direct comparison to iterative phase retrieval image reconstruction and images recorded with state of-the-art zone plate microscopes is presented. Our results demonstrate the power of HERALDO as a favorable candidate for robust inversion of single-shot coherent scattering patterns.

SU-E-J-237: Image Feature Based DRR and Portal Image Registration

Energy Technology Data Exchange (ETDEWEB)

Wang, X; Chang, J [NY Weill Cornell Medical Ctr, NY (United States)

2014-06-01

Purpose: Two-dimensional (2D) matching of the kV X-ray and digitally reconstructed radiography (DRR) images is an important setup technique for image-guided radiotherapy (IGRT). In our clinics, mutual information based methods are used for this purpose on commercial linear accelerators, but with often needs for manual corrections. This work proved the feasibility that feature based image transform can be used to register kV and DRR images. Methods: The scale invariant feature transform (SIFT) method was implemented to detect the matching image details (or key points) between the kV and DRR images. These key points represent high image intensity gradients, and thus the scale invariant features. Due to the poor image contrast from our kV image, direct application of the SIFT method yielded many detection errors. To assist the finding of key points, the center coordinates of the kV and DRR images were read from the DICOM header, and the two groups of key points with similar relative positions to their corresponding centers were paired up. Using these points, a rigid transform (with scaling, horizontal and vertical shifts) was estimated. We also artificially introduced vertical and horizontal shifts to test the accuracy of our registration method on anterior-posterior (AP) and lateral pelvic images. Results: The results provided a satisfactory overlay of the transformed kV onto the DRR image. The introduced vs. detected shifts were fit into a linear regression. In the AP image experiments, linear regression analysis showed a slope of 1.15 and 0.98 with an R2 of 0.89 and 0.99 for the horizontal and vertical shifts, respectively. The results are 1.2 and 1.3 with R2 of 0.72 and 0.82 for the lateral image shifts. Conclusion: This work provided an alternative technique for kV to DRR alignment. Further improvements in the estimation accuracy and image contrast tolerance are underway.

Scattering features for lung cancer detection in fibered confocal fluorescence microscopy images.

Science.gov (United States)

Rakotomamonjy, Alain; Petitjean, Caroline; Salaün, Mathieu; Thiberville, Luc

2014-06-01

To assess the feasibility of lung cancer diagnosis using fibered confocal fluorescence microscopy (FCFM) imaging technique and scattering features for pattern recognition. FCFM imaging technique is a new medical imaging technique for which interest has yet to be established for diagnosis. This paper addresses the problem of lung cancer detection using FCFM images and, as a first contribution, assesses the feasibility of computer-aided diagnosis through these images. Towards this aim, we have built a pattern recognition scheme which involves a feature extraction stage and a classification stage. The second contribution relies on the features used for discrimination. Indeed, we have employed the so-called scattering transform for extracting discriminative features, which are robust to small deformations in the images. We have also compared and combined these features with classical yet powerful features like local binary patterns (LBP) and their variants denoted as local quinary patterns (LQP). We show that scattering features yielded to better recognition performances than classical features like LBP and their LQP variants for the FCFM image classification problems. Another finding is that LBP-based and scattering-based features provide complementary discriminative information and, in some situations, we empirically establish that performance can be improved when jointly using LBP, LQP and scattering features. In this work we analyze the joint capability of FCFM images and scattering features for lung cancer diagnosis. The proposed method achieves a good recognition rate for such a diagnosis problem. It also performs well when used in conjunction with other features for other classical medical imaging classification problems. Copyright © 2014 Elsevier B.V. All rights reserved.

Differential evolution optimization combined with chaotic sequences for image contrast enhancement

Energy Technology Data Exchange (ETDEWEB)

Santos Coelho, Leandro dos [Industrial and Systems Engineering Graduate Program, LAS/PPGEPS, Pontifical Catholic University of Parana, PUCPR Imaculada Conceicao, 1155, 80215-901 Curitiba, Parana (Brazil)], E-mail: leandro.coelho@pucpr.br; Sauer, Joao Guilherme [Industrial and Systems Engineering Graduate Program, LAS/PPGEPS, Pontifical Catholic University of Parana, PUCPR Imaculada Conceicao, 1155, 80215-901 Curitiba, Parana (Brazil)], E-mail: joao.sauer@gmail.com; Rudek, Marcelo [Industrial and Systems Engineering Graduate Program, LAS/PPGEPS, Pontifical Catholic University of Parana, PUCPR Imaculada Conceicao, 1155, 80215-901 Curitiba, Parana (Brazil)], E-mail: marcelo.rudek@pucpr.br

2009-10-15

Evolutionary Algorithms (EAs) are stochastic and robust meta-heuristics of evolutionary computation field useful to solve optimization problems in image processing applications. Recently, as special mechanism to avoid being trapped in local minimum, the ergodicity property of chaotic sequences has been used in various designs of EAs. Three differential evolution approaches based on chaotic sequences using logistic equation for image enhancement process are proposed in this paper. Differential evolution is a simple yet powerful evolutionary optimization algorithm that has been successfully used in solving continuous problems. The proposed chaotic differential evolution schemes have fast convergence rate but also maintain the diversity of the population so as to escape from local optima. In this paper, the image contrast enhancement is approached as a constrained nonlinear optimization problem. The objective of the proposed chaotic differential evolution schemes is to maximize the fitness criterion in order to enhance the contrast and detail in the image by adapting the parameters using a contrast enhancement technique. The proposed chaotic differential evolution schemes are compared with classical differential evolution to two testing images. Simulation results on three images show that the application of chaotic sequences instead of random sequences is a possible strategy to improve the performance of classical differential evolution optimization algorithm.

Feature extraction for magnetic domain images of magneto-optical recording films using gradient feature segmentation

International Nuclear Information System (INIS)

Quanqing, Zhu.; Xinsai, Wang; Xuecheng, Zou; Haihua, Li; Xiaofei, Yang

2002-01-01

In this paper, we present a method to realize feature extraction on low contrast magnetic domain images of magneto-optical recording films. The method is based on the following three steps: first, Lee-filtering method is adopted to realize pre-filtering and noise reduction; this is followed by gradient feature segmentation, which separates the object area from the background area; finally the common linking method is adopted and the characteristic parameters of magnetic domain are calculated. We describe these steps with particular emphasis on the gradient feature segmentation. The results show that this method has advantages over other traditional ones for feature extraction of low contrast images

Blind image quality assessment based on aesthetic and statistical quality-aware features

Science.gov (United States)

Jenadeleh, Mohsen; Masaeli, Mohammad Masood; Moghaddam, Mohsen Ebrahimi

2017-07-01

The main goal of image quality assessment (IQA) methods is the emulation of human perceptual image quality judgments. Therefore, the correlation between objective scores of these methods with human perceptual scores is considered as their performance metric. Human judgment of the image quality implicitly includes many factors when assessing perceptual image qualities such as aesthetics, semantics, context, and various types of visual distortions. The main idea of this paper is to use a host of features that are commonly employed in image aesthetics assessment in order to improve blind image quality assessment (BIQA) methods accuracy. We propose an approach that enriches the features of BIQA methods by integrating a host of aesthetics image features with the features of natural image statistics derived from multiple domains. The proposed features have been used for augmenting five different state-of-the-art BIQA methods, which use statistical natural scene statistics features. Experiments were performed on seven benchmark image quality databases. The experimental results showed significant improvement of the accuracy of the methods.

Pseudoachondroplasia in a child: The role of anthropometric measurements and skeletal imaging in differential diagnosis

Directory of Open Access Journals (Sweden)

Radwa Gamal, MSc

2017-03-01

Full Text Available Pseudoachondroplasia is a rare osteochondrodysplasia characterized by disproportionate short stature and limb deformity. Diagnostic accuracy is based on a detailed evaluation of the radioclinical features. We report a boy with pseudoachondroplasia. We aim to underscore why is accurate delineation of the pattern of radioclinical skeletal abnormalities in pseudoachondroplasia a weighty part of diagnosis. Furthermore, we aim to highlight the main clinical and skeletal imaging features of skeletal dysplasias that overlap with pseudoachondroplasia using clinical cases evaluated in our institution. The findings affirm that anthropometric measurements and skeletal radiography are important contributors to the differential diagnosis and classification of disproportionate growth.

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.

Imaging appearance of well-differentiated liposarcomas with myxoid stroma.

Science.gov (United States)

Morag, Yoav; Yablon, Corrie; Brigido, Monica Kalume; Jacobson, Jon; Lucas, David

2018-04-16

Describe the imaging appearance of well-differentiated liposarcoma with myxoid stroma (WDLMS) and correlate with histopathology. A keyword search of the institution medical records was performed from 1 January 2000 to 30 June 2017. The histopathology slides of cases identified in this fashion were then reviewed by a pathologist. Additional cases were prospectively collected from extramural referrals and tumor boards. Diagnostic imaging studies of pathologically proven cases of WDLMS were then reviewed in consensus and correlated with pathology. Ten cases of pathologically proven WDLMS were identified (7 men, 3 women, ages 26-81). Tumor location included the retroperitoneum (n = 5), thigh (n = 4), and the shin (n = 1). Nine patients had macroscopic fat on imaging. The nonlipomatous components had a variable appearance, including septal, nodular, and lacelike patterns. Two cases included two distinct areas that were predominantly myxoid or lipomatous ("bi-morphic"). One tumor had no macroscopic fat on imaging. On CT, the nonlipomatous nodular components were hypodense/had hypodense areas. On MRI, the nodular components had intermediate/bright T2W signal. Interval nonlipomatous nodular growth was identified in 3 cases. WDLMS may present on imaging as a mass with variable morphology and amounts of nonlipomatous components. Histopathological diagnosis of WDLMS is challenging and imaging correlation may be helpful, as this tumor may have ≥50% fatty volume, may have a myxoid nodular component or bi-morphic appearance, or may be located in the retroperitoneum, features that are unusual for myxoid liposarcoma. WDLMS with a nodular component cannot be distinguished from dedifferentiated liposarcoma based on imaging alone.

Prediction of pancreatic neuroendocrine tumour grade with MR imaging features: added value of diffusion-weighted imaging

Energy Technology Data Exchange (ETDEWEB)

Lotfalizadeh, Emad; Vullierme, Marie-Pierre; Allaham, Wassim [University Hospitals Paris Nord Val de Seine, Department of Radiology, Clichy, Hauts-de-Seine (France); Ronot, Maxime; Vilgrain, Valerie [University Hospitals Paris Nord Val de Seine, Department of Radiology, Clichy, Hauts-de-Seine (France); University Paris Diderot, Paris (France); INSERM U1149, Centre de Recherche Biomedicale Bichat-Beaujon, CRB3, Paris (France); Wagner, Mathilde [University Hospitals Paris Nord Val de Seine, Department of Radiology, Clichy, Hauts-de-Seine (France); INSERM U1149, Centre de Recherche Biomedicale Bichat-Beaujon, CRB3, Paris (France); Cros, Jerome; Couvelard, Anne [University Paris Diderot, Paris (France); University Hospitals Paris Nord Val de Seine, Department of Pathology, Clichy, Hauts-de-Seine (France); Hentic, Olivia; Ruzniewski, Philippe [University Hospitals Paris Nord Val de Seine, Department of Gastroenterology, Clichy, Hauts-de-Seine (France)

2017-04-15

To evaluate the value of MR imaging including diffusion-weighted imaging (DWI) for the grading of pancreatic neuroendocrine tumours (pNET). Between 2006 and 2014, all resected pNETs with preoperative MR imaging including DWI were included. Tumour grading was based on the 2010 WHO classification. MR imaging features included size, T1-w, and T2-w signal intensity, enhancement pattern, apparent (ADC) and true diffusion (D) coefficients. One hundred and eight pNETs (mean 40 ± 33 mm) were evaluated in 94 patients (48 women, 51 %, mean age 52 ± 12). Fifty-five (51 %), 42 (39 %), and 11 (10 %) tumours were given the following grades (G): G1, G2, and G3. Mean ADC and D values were significantly lower as grade increased (ADC: 2.13 ± 0.70, 1.78 ± 0.72, and 0.86 ± 0.22 10{sup -3} mm{sup 2}/s, and D: 1.92 ± 0.70, 1.75 ± 0.74, and 0.82 ± 0.19 10{sup -3} mm{sup 2}/s G1, G2, and G3, all p < 0.001). A higher grade was associated with larger sized tumours (p < 0.001). The AUROC of ADC and D to differentiate G3 and G1-2 were 0.96 ± 0.02 and 0.95 ± 0.02. Optimal cut-off values for the identification of G3 were 1.19 10{sup -3} mm{sup 2}/s for ADC (sensitivity 100 %, specificity 92 %) and 1.04 10{sup -3} mm{sup 2}/s for D (sensitivity 82 %, specificity 92 %). Morphological/functional MRI features of pNETS depend on tumour grade. DWI is useful for the identification of high-grade tumours. (orig.)

Cystic synovial sarcomas: imaging features with clinical and histopathologic correlation

Energy Technology Data Exchange (ETDEWEB)

Nakanishi, Hirofumi; Araki, Nobuhito [Department of Orthopedic Surgery, Osaka Medical Center for Cancer and Cardiovascular Diseases, 1-3-3, Nakamichi, Higashinari-Ku, 537-8511, Osaka (Japan); Sawai, Yuka [Department of Radiology, Osaka Medical Center for Cancer and Cardiovascular Diseases, Osaka (Japan); Kudawara, Ikuo [Department of Orthopedic Surgery, Osaka National Hospital, Osaka (Japan); Mano, Masayuki; Ishiguro, Shingo [Department of Pathology, Osaka Medical Center for Cancer and Cardiovascular Diseases, Osaka (Japan); Ueda, Takafumi; Yoshikawa, Hideki [Department of Orthopedic Surgery, Osaka University Graduate School of Medicine, Suita, Osaka (Japan)

2003-12-01

To characterize the radiological and clinicopathologic features of cystic synovial sarcoma. Seven patients with primary cystic synovial sarcoma were evaluated. Computed tomography (CT) and magnetic resonance (MR) imaging were undertaken at the first presentation. The diagnosis of synovial sarcoma was made on the basis of histological examinations followed by molecular analysis. Radiological and clinicopathologic findings were reviewed. CT showed well-defined soft tissue mass without cortical bone erosion and invasion. Calcification was seen at the periphery of the mass in three cases. T2-weighted MR images showed multilocular inhomogeneous intensity mass in all cases, five of which showed fluid-fluid levels. On gross appearance, old and/or fresh hematomas were detected in six cases. In the one remaining case, microscopic hemorrhage in the cystic lumen was proven. Four cases had poorly differentiated areas. In five cases prominent hemangiopericytomatous vasculature was observed. Histologic grade was intermediate in one tumor and high in six. One case had a history of misdiagnosis for tarsal tunnel syndrome, one for lymphadenopathy, two for sciatica and two for hematoma. All cystic synovial sarcomas demonstrated multilocularity with well-circumscribed walls and internal septae. Synovial sarcoma should be taken into consideration in patients with deeply situated multicystic mass with triple signal intensity on T2-weighted MR imaging. (orig.)

Cystic synovial sarcomas: imaging features with clinical and histopathologic correlation

International Nuclear Information System (INIS)

Nakanishi, Hirofumi; Araki, Nobuhito; Sawai, Yuka; Kudawara, Ikuo; Mano, Masayuki; Ishiguro, Shingo; Ueda, Takafumi; Yoshikawa, Hideki

2003-01-01

To characterize the radiological and clinicopathologic features of cystic synovial sarcoma. Seven patients with primary cystic synovial sarcoma were evaluated. Computed tomography (CT) and magnetic resonance (MR) imaging were undertaken at the first presentation. The diagnosis of synovial sarcoma was made on the basis of histological examinations followed by molecular analysis. Radiological and clinicopathologic findings were reviewed. CT showed well-defined soft tissue mass without cortical bone erosion and invasion. Calcification was seen at the periphery of the mass in three cases. T2-weighted MR images showed multilocular inhomogeneous intensity mass in all cases, five of which showed fluid-fluid levels. On gross appearance, old and/or fresh hematomas were detected in six cases. In the one remaining case, microscopic hemorrhage in the cystic lumen was proven. Four cases had poorly differentiated areas. In five cases prominent hemangiopericytomatous vasculature was observed. Histologic grade was intermediate in one tumor and high in six. One case had a history of misdiagnosis for tarsal tunnel syndrome, one for lymphadenopathy, two for sciatica and two for hematoma. All cystic synovial sarcomas demonstrated multilocularity with well-circumscribed walls and internal septae. Synovial sarcoma should be taken into consideration in patients with deeply situated multicystic mass with triple signal intensity on T2-weighted MR imaging. (orig.)

Texture Feature Analysis for Different Resolution Level of Kidney Ultrasound Images

Science.gov (United States)

Kairuddin, Wan Nur Hafsha Wan; Mahmud, Wan Mahani Hafizah Wan

2017-08-01

Image feature extraction is a technique to identify the characteristic of the image. The objective of this work is to discover the texture features that best describe a tissue characteristic of a healthy kidney from ultrasound (US) image. Three ultrasound machines that have different specifications are used in order to get a different quality (different resolution) of the image. Initially, the acquired images are pre-processed to de-noise the speckle to ensure the image preserve the pixels in a region of interest (ROI) for further extraction. Gaussian Low- pass Filter is chosen as the filtering method in this work. 150 of enhanced images then are segmented by creating a foreground and background of image where the mask is created to eliminate some unwanted intensity values. Statistical based texture features method is used namely Intensity Histogram (IH), Gray-Level Co-Occurance Matrix (GLCM) and Gray-level run-length matrix (GLRLM).This method is depends on the spatial distribution of intensity values or gray levels in the kidney region. By using One-Way ANOVA in SPSS, the result indicated that three features (Contrast, Difference Variance and Inverse Difference Moment Normalized) from GLCM are not statistically significant; this concludes that these three features describe a healthy kidney characteristics regardless of the ultrasound image quality.

Imaging differential polarization microscope with electronic readout

International Nuclear Information System (INIS)

Mickols, W.; Tinoco, I.; Katz, J.E.; Maestre, M.F.; Bustamante, C.

1985-01-01

A differential polarization microscope forms two images: one of the transmitted intensity and the other due to the change in intensity between images formed when different polarizations of light are used. The interpretation of these images for linear dichroism and circular dichroism are described. The design constraints on the data acquisition systems and the polarization modulation are described. The advantage of imaging several biological systems which contain optically anisotropic structures are described

Robust Tomato Recognition for Robotic Harvesting Using Feature Images Fusion

Directory of Open Access Journals (Sweden)

Yuanshen Zhao

2016-01-01

Full Text Available Automatic recognition of mature fruits in a complex agricultural environment is still a challenge for an autonomous harvesting robot due to various disturbances existing in the background of the image. The bottleneck to robust fruit recognition is reducing influence from two main disturbances: illumination and overlapping. In order to recognize the tomato in the tree canopy using a low-cost camera, a robust tomato recognition algorithm based on multiple feature images and image fusion was studied in this paper. Firstly, two novel feature images, the  a*-component image and the I-component image, were extracted from the L*a*b* color space and luminance, in-phase, quadrature-phase (YIQ color space, respectively. Secondly, wavelet transformation was adopted to fuse the two feature images at the pixel level, which combined the feature information of the two source images. Thirdly, in order to segment the target tomato from the background, an adaptive threshold algorithm was used to get the optimal threshold. The final segmentation result was processed by morphology operation to reduce a small amount of noise. In the detection tests, 93% target tomatoes were recognized out of 200 overall samples. It indicates that the proposed tomato recognition method is available for robotic tomato harvesting in the uncontrolled environment with low cost.

Robust Tomato Recognition for Robotic Harvesting Using Feature Images Fusion.

Science.gov (United States)

Zhao, Yuanshen; Gong, Liang; Huang, Yixiang; Liu, Chengliang

2016-01-29

Automatic recognition of mature fruits in a complex agricultural environment is still a challenge for an autonomous harvesting robot due to various disturbances existing in the background of the image. The bottleneck to robust fruit recognition is reducing influence from two main disturbances: illumination and overlapping. In order to recognize the tomato in the tree canopy using a low-cost camera, a robust tomato recognition algorithm based on multiple feature images and image fusion was studied in this paper. Firstly, two novel feature images, the  a*-component image and the I-component image, were extracted from the L*a*b* color space and luminance, in-phase, quadrature-phase (YIQ) color space, respectively. Secondly, wavelet transformation was adopted to fuse the two feature images at the pixel level, which combined the feature information of the two source images. Thirdly, in order to segment the target tomato from the background, an adaptive threshold algorithm was used to get the optimal threshold. The final segmentation result was processed by morphology operation to reduce a small amount of noise. In the detection tests, 93% target tomatoes were recognized out of 200 overall samples. It indicates that the proposed tomato recognition method is available for robotic tomato harvesting in the uncontrolled environment with low cost.

Autoimmune Thyroiditis: Clinical Course Features and Principles of Differential Therapy

Directory of Open Access Journals (Sweden)

L.Ye. Bobyryova

2014-02-01

Full Text Available Constant increase in the incidence of autoimmune thyroiditis (AIT in different regions of Ukraine puts this problem in actual number that determines the need to identify features of the clinical course of AIT, the principles of differentiated treatment depending on the nature of the metabolic changes and taking into account regional differences in thyroid pathology, particularly AIT. The paper presents data on the study of features of clinical course and complex treatment of AIT.

Spectral CT imaging in the differential diagnosis of necrotic hepatocellular carcinoma and hepatic abscess

International Nuclear Information System (INIS)

Yu, Y.; Guo, L.; Hu, C.; Chen, K.

2014-01-01

Aim: To explore the value of CT spectral imaging in the differential diagnosis of necrotic hepatocellular carcinoma (nHCC) and hepatic abscess (HA) during the arterial phase (AP) and portal venous phase (PP). Materials and methods: Sixty patients with 36 nHCCs and 24 HAs underwent spectral CT during AP and PP. Iodine or water concentration were measured and the normalized iodine concentration (NIC) and lesion-normal parenchyma iodine concentration ratio (LNR) were calculated. The two-sample t-test was used to compare quantitative parameters. Two readers qualitatively assessed lesion types according to imaging features. Sensitivity and specificity were compared between the qualitative and quantitative studies. Results: NIC and LNR in the AP for the wall of nHCC (0.14 ± 0.04 mg/ml; 2.77 ± 0.74) were higher than those of HA (0.13 ± 0.02 mg/ml; 1.4 ± 0.9). NIC and LNR in the PP for the wall of HA (0.66 ± 0.05 mg/ml; 1.2 ± 0.2) were higher than those of nHCC (0.5 ± 0.11 mg/ml; 0.94 ± 0.12). The differences in NIC in the AP were not significant but the differences in LNR in AP, and NIC and LNR in the PP were significant. The best quantitative parameter was LNR in AP, and a threshold of 1.52 would yield a sensitivity and specificity of 100% and 91.7%, respectively, for differentiating nHCC from HA. Conclusion: CT spectral imaging with quantitative iodine concentration analysis may help to increase the accuracy of differentiating nHCC from HA. - Highlights: • We preliminarily investigate the usefulness of CT spectral imaging in differentiating nHCC from HA. • CT spectral imaging may help differentiate necrotic hepatocellular carcinoma from hepatic abscess. • CT spectral imaging can evaluate the blood supply and necrotic degree of lesions. • Quantitative analysis of iodine concentration provides greater diagnostic confidence

Classification of radiolarian images with hand-crafted and deep features

Science.gov (United States)

Keçeli, Ali Seydi; Kaya, Aydın; Keçeli, Seda Uzunçimen

2017-12-01

Radiolarians are planktonic protozoa and are important biostratigraphic and paleoenvironmental indicators for paleogeographic reconstructions. Radiolarian paleontology still remains as a low cost and the one of the most convenient way to obtain dating of deep ocean sediments. Traditional methods for identifying radiolarians are time-consuming and cannot scale to the granularity or scope necessary for large-scale studies. Automated image classification will allow making these analyses promptly. In this study, a method for automatic radiolarian image classification is proposed on Scanning Electron Microscope (SEM) images of radiolarians to ease species identification of fossilized radiolarians. The proposed method uses both hand-crafted features like invariant moments, wavelet moments, Gabor features, basic morphological features and deep features obtained from a pre-trained Convolutional Neural Network (CNN). Feature selection is applied over deep features to reduce high dimensionality. Classification outcomes are analyzed to compare hand-crafted features, deep features, and their combinations. Results show that the deep features obtained from a pre-trained CNN are more discriminative comparing to hand-crafted ones. Additionally, feature selection utilizes to the computational cost of classification algorithms and have no negative effect on classification accuracy.

Social Graph Community Differentiated by Node Features with Partly Missing Information

Directory of Open Access Journals (Sweden)

V. O. Chesnokov

2015-01-01

Full Text Available This paper proposes a new algorithm for community differentiation in social graphs, which uses information both on the graph structure and on the vertices. We consider user's ego-network i.e. his friends, with no himself, where each vertex has a set of features such as details on a workplace, institution, etc. The task is to determine missing or unspecified features of the vertices, based on their neighbors' features, and use these features to differentiate the communities in the social graph. Two vertices are believed to belong to the same community if they have a common feature. A hypothesis has been put forward that if most neighbors of a vertex have a common feature, there is a good probability that the vertex has this feature as well. The proposed algorithm is iterative and updates features of vertices, based on its neighbors, according to the hypothesis. Share of neighbors that form a majority is specified by the algorithm parameter. Complexity of single iteration depends linearly on the number of edges in the graph.To assess the quality of clustering three normalized metrics were used, namely: expected density, silhouette index, and Hubert's Gamma Statistic. The paper describes a method for test sampling of 2.000 graphs of the user's social network \\VKontakte". The API requests addressed \\VKontakte" and parsing HTML-pages of user's profiles and search results provided crawling. Information on user's group membership, secondary and higher education, and workplace was used as features. To store data the PostgreSQL DBMS was used, and the gexf format was used for data processing. For the test sample, metrics for several values of algorithm parameter were estimated: the value of index silhouettes was low (0.14-0.20, but within the normal range; the value of expected density was high, i.e. 1.17-1.52; the value of Hubert's gamma statistic was 0.94-0.95 that is close to the maximum. The number of vertices with no features was calculated before

Machine learning-based quantitative texture analysis of CT images of small renal masses. Differentiation of angiomyolipoma without visible fat from renal cell carcinoma

International Nuclear Information System (INIS)

Feng, Zhichao; Rong, Pengfei; Zhou, Qingyu; Zhu, Wenwei; Yan, Zhimin; Liu, Qianyun; Wang, Wei; Cao, Peng

2018-01-01

To evaluate the diagnostic performance of machine-learning based quantitative texture analysis of CT images to differentiate small (≤ 4 cm) angiomyolipoma without visible fat (AMLwvf) from renal cell carcinoma (RCC). This single-institutional retrospective study included 58 patients with pathologically proven small renal mass (17 in AMLwvf and 41 in RCC groups). Texture features were extracted from the largest possible tumorous regions of interest (ROIs) by manual segmentation in preoperative three-phase CT images. Interobserver reliability and the Mann-Whitney U test were applied to select features preliminarily. Then support vector machine with recursive feature elimination (SVM-RFE) and synthetic minority oversampling technique (SMOTE) were adopted to establish discriminative classifiers, and the performance of classifiers was assessed. Of the 42 extracted features, 16 candidate features showed significant intergroup differences (P < 0.05) and had good interobserver agreement. An optimal feature subset including 11 features was further selected by the SVM-RFE method. The SVM-RFE+SMOTE classifier achieved the best performance in discriminating between small AMLwvf and RCC, with the highest accuracy, sensitivity, specificity and AUC of 93.9 %, 87.8 %, 100 % and 0.955, respectively. Machine learning analysis of CT texture features can facilitate the accurate differentiation of small AMLwvf from RCC. (orig.)

Iris recognition based on key image feature extraction.

Science.gov (United States)

Ren, X; Tian, Q; Zhang, J; Wu, S; Zeng, Y

2008-01-01

In iris recognition, feature extraction can be influenced by factors such as illumination and contrast, and thus the features extracted may be unreliable, which can cause a high rate of false results in iris pattern recognition. In order to obtain stable features, an algorithm was proposed in this paper to extract key features of a pattern from multiple images. The proposed algorithm built an iris feature template by extracting key features and performed iris identity enrolment. Simulation results showed that the selected key features have high recognition accuracy on the CASIA Iris Set, where both contrast and illumination variance exist.

Automated local bright feature image analysis of nuclear protein distribution identifies changes in tissue phenotype

International Nuclear Information System (INIS)

Knowles, David; Sudar, Damir; Bator, Carol; Bissell, Mina

2006-01-01

The organization of nuclear proteins is linked to cell and tissue phenotypes. When cells arrest proliferation, undergo apoptosis, or differentiate, the distribution of nuclear proteins changes. Conversely, forced alteration of the distribution of nuclear proteins modifies cell phenotype. Immunostaining and fluorescence microscopy have been critical for such findings. However, there is an increasing need for quantitative analysis of nuclear protein distribution to decipher epigenetic relationships between nuclear structure and cell phenotype, and to unravel the mechanisms linking nuclear structure and function. We have developed imaging methods to quantify the distribution of fluorescently-stained nuclear protein NuMA in different mammary phenotypes obtained using three-dimensional cell culture. Automated image segmentation of DAPI-stained nuclei was generated to isolate thousands of nuclei from three-dimensional confocal images. Prominent features of fluorescently-stained NuMA were detected using a novel local bright feature analysis technique, and their normalized spatial density calculated as a function of the distance from the nuclear perimeter to its center. The results revealed marked changes in the distribution of the density of NuMA bright features as non-neoplastic cells underwent phenotypically normal acinar morphogenesis. In contrast, we did not detect any reorganization of NuMA during the formation of tumor nodules by malignant cells. Importantly, the analysis also discriminated proliferating non-neoplastic cells from proliferating malignant cells, suggesting that these imaging methods are capable of identifying alterations linked not only to the proliferation status but also to the malignant character of cells. We believe that this quantitative analysis will have additional applications for classifying normal and pathological tissues

Online Feature Selection for Classifying Emphysema in HRCT Images

Directory of Open Access Journals (Sweden)

M. Prasad

2008-06-01

Full Text Available Feature subset selection, applied as a pre- processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In the classic formulation of the feature selection problem, it is assumed that all the features are available at the beginning. However, in many real world problems, there are scenarios where not all features are present initially and must be integrated as they become available. In such scenarios, online feature selection provides an efficient way to sort through a large space of features. It is in this context that we introduce online feature selection for the classification of emphysema, a smoking related disease that appears as low attenuation regions in High Resolution Computer Tomography (HRCT images. The technique was successfully evaluated on 61 HRCT scans and compared with different online feature selection approaches, including hill climbing, best first search, grafting, and correlation-based feature selection. The results were also compared against ldensity maskr, a standard approach used for emphysema detection in medical image analysis.

Optical Imaging for Stem Cell Differentiation to Neuronal Lineage

International Nuclear Information System (INIS)

Hwang, Do Won; Lee, Dong Soo

2012-01-01

In regenerative medicine, the prospect of stem cell therapy hold great promise for the recovery of injured tissues and effective treatment of intractable diseases. Tracking stem cell fate provides critical information to understand and evaluate the success of stem cell therapy. The recent emergence of in vivo noninvasive molecular imaging has enabled assessment of the behavior of grafted stem cells in living subjects. In this review, we provide an overview of current optical imaging strategies based on cell or tissue specific reporter gene expression and of in vivo methods to monitor stem cell differentiation into neuronal lineages. These methods use optical reporters either regulated by neuron-specific promoters or containing neuron-specific microRNA binding sites. Both systems revealed dramatic changes in optical reporter imaging signals in cells differentiating a yeast GAL4 amplification system or an engineering-enhanced luciferase reported gene. Furthermore, we propose an advanced imaging system to monitor neuronal differentiation during neurogenesis that uses in vivo multiplexed imaging techniques capable of detecting several targets simultaneously

Two-Level Evaluation on Sensor Interoperability of Features in Fingerprint Image Segmentation

Directory of Open Access Journals (Sweden)

Ya-Shuo Li

2012-03-01

Full Text Available Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature’s ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

Differentiation of hemangioblastomas from pilocytic astrocytomas using 3-T magnetic resonance perfusion-weighted imaging and MR spectroscopy

Energy Technology Data Exchange (ETDEWEB)

She, D.J.; Xing, Z.; Zeng, Z.; Cao, D.R. [First Affiliated Hospital of Fujian Medical University, Department of Radiology, Fuzhou, Fujian (China); Shang, X.Y. [University of California, San Diego, Department of Medicine and the Moores UCSD Cancer Center, La Jolla, CA (United States)

2015-03-01

Hemangioblastomas and pilocytic astrocytomas (PAs) present similar imaging features on conventional MR imaging, making differential diagnosis a challenge. The purpose of this study was to evaluate the usefulness of dynamic susceptibility-weighted contrast-enhanced perfusion-weighted imaging (DSC-PWI) and proton MR spectroscopic imaging in the differentiation of hemangioblastomas and PAs. A 3.0-T MR imaging unit was used to perform DSC-PWI and conventional MR imaging on 14 patients with hemangioblastomas and 22 patients with PAs. Four patients with hemangioblastomas and 10 PA patients also underwent proton MR spectroscopy. Parameters of relative peak height (rPH) and relative percentage of signal intensity recovery (rPSR) were acquired by DSC-PWI and variables of N-acetylaspasrtate (NAA)/creatine (Cr), choline (Cho)/Cr, and lactate-lipid (Lac-Lip)/Cr by MR spectroscopy. The sensitivity, specificity, and the area under the receiver operating characteristic curve of all analyzed parameters at respective cutoff values were determined. Higher rPH but lower rPSR values were detected in hemangioblastomas compared to PAs. The NAA/Cr ratio was significantly lower in hemangioblastomas compared with PAs. The threshold values ≥3.2 for rPH provide sensitivity, specificity, positive predictive values, and negative predictive values of 85.7, 95.5, 92.3, and 91.3 %, respectively, for differentiating hemangioblastomas from PAs. The optimal threshold values were ≤0.9 for rPSR and ≤1.5 for NAA/Cr ratios in tumor. Significantly higher rPH and lower NAA/Cr were seen in patients with hemangioblastomas when compared with PA patients, suggesting that DSC-PWI and proton MR spectroscopy are helpful in the characterization and differentiation of these two types of tumors. (orig.)

Comparisons of feature extraction algorithm based on unmanned aerial vehicle image

Directory of Open Access Journals (Sweden)

Xi Wenfei

2017-07-01

Full Text Available Feature point extraction technology has become a research hotspot in the photogrammetry and computer vision. The commonly used point feature extraction operators are SIFT operator, Forstner operator, Harris operator and Moravec operator, etc. With the high spatial resolution characteristics, UAV image is different from the traditional aviation image. Based on these characteristics of the unmanned aerial vehicle (UAV, this paper uses several operators referred above to extract feature points from the building images, grassland images, shrubbery images, and vegetable greenhouses images. Through the practical case analysis, the performance, advantages, disadvantages and adaptability of each algorithm are compared and analyzed by considering their speed and accuracy. Finally, the suggestions of how to adapt different algorithms in diverse environment are proposed.

A Novel Technique for Shape Feature Extraction Using Content Based Image Retrieval

Directory of Open Access Journals (Sweden)

Dhanoa Jaspreet Singh

2016-01-01

Full Text Available With the advent of technology and multimedia information, digital images are increasing very quickly. Various techniques are being developed to retrieve/search digital information or data contained in the image. Traditional Text Based Image Retrieval System is not plentiful. Since it is time consuming as it require manual image annotation. Also, the image annotation differs with different peoples. An alternate to this is Content Based Image Retrieval (CBIR system. It retrieves/search for image using its contents rather the text, keywords etc. A lot of exploration has been compassed in the range of Content Based Image Retrieval (CBIR with various feature extraction techniques. Shape is a significant image feature as it reflects the human perception. Moreover, Shape is quite simple to use by the user to define object in an image as compared to other features such as Color, texture etc. Over and above, if applied alone, no descriptor will give fruitful results. Further, by combining it with an improved classifier, one can use the positive features of both the descriptor and classifier. So, a tryout will be made to establish an algorithm for accurate feature (Shape extraction in Content Based Image Retrieval (CBIR. The main objectives of this project are: (a To propose an algorithm for shape feature extraction using CBIR, (b To evaluate the performance of proposed algorithm and (c To compare the proposed algorithm with state of art techniques.

Extraction of Lesion-Partitioned Features and Retrieval of Contrast-Enhanced Liver Images

Directory of Open Access Journals (Sweden)

Mei Yu

2012-01-01

Full Text Available The most critical step in grayscale medical image retrieval systems is feature extraction. Understanding the interrelatedness between the characteristics of lesion images and corresponding imaging features is crucial for image training, as well as for features extraction. A feature-extraction algorithm is developed based on different imaging properties of lesions and on the discrepancy in density between the lesions and their surrounding normal liver tissues in triple-phase contrast-enhanced computed tomographic (CT scans. The algorithm includes mainly two processes: (1 distance transformation, which is used to divide the lesion into distinct regions and represents the spatial structure distribution and (2 representation using bag of visual words (BoW based on regions. The evaluation of this system based on the proposed feature extraction algorithm shows excellent retrieval results for three types of liver lesions visible on triple-phase scans CT images. The results of the proposed feature extraction algorithm show that although single-phase scans achieve the average precision of 81.9%, 80.8%, and 70.2%, dual- and triple-phase scans achieve 86.3% and 88.0%.

Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters.

Science.gov (United States)

Brynolfsson, Patrik; Nilsson, David; Torheim, Turid; Asklund, Thomas; Karlsson, Camilla Thellenberg; Trygg, Johan; Nyholm, Tufve; Garpebring, Anders

2017-06-22

In recent years, texture analysis of medical images has become increasingly popular in studies investigating diagnosis, classification and treatment response assessment of cancerous disease. Despite numerous applications in oncology and medical imaging in general, there is no consensus regarding texture analysis workflow, or reporting of parameter settings crucial for replication of results. The aim of this study was to assess how sensitive Haralick texture features of apparent diffusion coefficient (ADC) MR images are to changes in five parameters related to image acquisition and pre-processing: noise, resolution, how the ADC map is constructed, the choice of quantization method, and the number of gray levels in the quantized image. We found that noise, resolution, choice of quantization method and the number of gray levels in the quantized images had a significant influence on most texture features, and that the effect size varied between different features. Different methods for constructing the ADC maps did not have an impact on any texture feature. Based on our results, we recommend using images with similar resolutions and noise levels, using one quantization method, and the same number of gray levels in all quantized images, to make meaningful comparisons of texture feature results between different subjects.

Evaluation of feature selection algorithms for classification in temporal lobe epilepsy based on MR images

Science.gov (United States)

Lai, Chunren; Guo, Shengwen; Cheng, Lina; Wang, Wensheng; Wu, Kai

2017-02-01

It's very important to differentiate the temporal lobe epilepsy (TLE) patients from healthy people and localize the abnormal brain regions of the TLE patients. The cortical features and changes can reveal the unique anatomical patterns of brain regions from the structural MR images. In this study, structural MR images from 28 normal controls (NC), 18 left TLE (LTLE), and 21 right TLE (RTLE) were acquired, and four types of cortical feature, namely cortical thickness (CTh), cortical surface area (CSA), gray matter volume (GMV), and mean curvature (MCu), were explored for discriminative analysis. Three feature selection methods, the independent sample t-test filtering, the sparse-constrained dimensionality reduction model (SCDRM), and the support vector machine-recursive feature elimination (SVM-RFE), were investigated to extract dominant regions with significant differences among the compared groups for classification using the SVM classifier. The results showed that the SVM-REF achieved the highest performance (most classifications with more than 92% accuracy), followed by the SCDRM, and the t-test. Especially, the surface area and gray volume matter exhibited prominent discriminative ability, and the performance of the SVM was improved significantly when the four cortical features were combined. Additionally, the dominant regions with higher classification weights were mainly located in temporal and frontal lobe, including the inferior temporal, entorhinal cortex, fusiform, parahippocampal cortex, middle frontal and frontal pole. It was demonstrated that the cortical features provided effective information to determine the abnormal anatomical pattern and the proposed method has the potential to improve the clinical diagnosis of the TLE.

SAR Image Classification Based on Its Texture Features

Institute of Scientific and Technical Information of China (English)

LI Pingxiang; FANG Shenghui

2003-01-01

SAR images not only have the characteristics of all-ay, all-eather, but also provide object information which is different from visible and infrared sensors. However, SAR images have some faults, such as more speckles and fewer bands. The authors conducted the experiments of texture statistics analysis on SAR image features in order to improve the accuracy of SAR image interpretation.It is found that the texture analysis is an effective method for improving the accuracy of the SAR image interpretation.

Differential CT features of infectious pneumonia versus bronchioloalveolar carcinoma (BAC) mimicking pneumonia

International Nuclear Information System (INIS)

Kim, Tae Hoon; Kim, Sang Jin; Ryu, Young Hoon; Chung, Soo Yoon; Seo, Jae Seung; Kim, Young Jin; Choi, Byoung Wook; Lee, Sun Hwa; Cho, Sang Ho

2006-01-01

The purpose of this study was to evaluate retrospectively the differential CT features of bronchioloalveolar carcinoma (BAC) mimicking pneumonia and infectious pneumonia at the lung periphery. CT images were reviewed in 47 patients with focal areas of parenchymal opacification at the lung periphery. We evaluated the presence of ground-glass attenuation, marginal conspicuity of the lesion, CT angiogram sign, air-bronchogram sign, a bubble-like low-attenuation area within the lesion, presence of pleural thickening and retraction associated with the lesion, presence of pleural effusion and extra-pleural fatty hypertrophy, presence of bronchial wall thickening proximal to the lesion, and air-trapping in the normal lung near the lesion. BAC (n=18) depicted the presence of a bubble-like low-attenuation area within the lesion, whereas infectious pneumonia (n=29) represented the pleural thickening associated with the lesion and bronchial wall thickening proximal to the lesion (P 0.05). The focal areas of the parenchymal opacification on the CT images may suggest infectious pneumonia rather than BAC when they show bronchial wall thickening proximal to the lesion and pleural thickening associated with the lesion, whereas BAC is characterized as the presence of a bubble-like low attenuation area within the tumor. (orig.)

Differential CT features of infectious pneumonia versus bronchioloalveolar carcinoma (BAC) mimicking pneumonia

Energy Technology Data Exchange (ETDEWEB)

Kim, Tae Hoon [Yonsei University College of Medicine, Department of Radiology, Seoul (Korea); Yongdong Severance Hospital, Department of Radiology, Seoul (Korea); Kim, Sang Jin; Ryu, Young Hoon; Chung, Soo Yoon; Seo, Jae Seung; Kim, Young Jin; Choi, Byoung Wook [Yonsei University College of Medicine, Department of Radiology, Seoul (Korea); Lee, Sun Hwa [NeoDin Medical Institute, Department of Clinical Pathology, Seoul (Korea); Cho, Sang Ho [Yonsei University College of Medicine, Department of Pathology, Seoul (Korea)

2006-08-15

The purpose of this study was to evaluate retrospectively the differential CT features of bronchioloalveolar carcinoma (BAC) mimicking pneumonia and infectious pneumonia at the lung periphery. CT images were reviewed in 47 patients with focal areas of parenchymal opacification at the lung periphery. We evaluated the presence of ground-glass attenuation, marginal conspicuity of the lesion, CT angiogram sign, air-bronchogram sign, a bubble-like low-attenuation area within the lesion, presence of pleural thickening and retraction associated with the lesion, presence of pleural effusion and extra-pleural fatty hypertrophy, presence of bronchial wall thickening proximal to the lesion, and air-trapping in the normal lung near the lesion. BAC (n=18) depicted the presence of a bubble-like low-attenuation area within the lesion, whereas infectious pneumonia (n=29) represented the pleural thickening associated with the lesion and bronchial wall thickening proximal to the lesion (P<0.05). The other CT findings showed no significant differences (P>0.05). The focal areas of the parenchymal opacification on the CT images may suggest infectious pneumonia rather than BAC when they show bronchial wall thickening proximal to the lesion and pleural thickening associated with the lesion, whereas BAC is characterized as the presence of a bubble-like low attenuation area within the tumor. (orig.)

Derivative-based scale invariant image feature detector with error resilience.

Science.gov (United States)

Mainali, Pradip; Lafruit, Gauthier; Tack, Klaas; Van Gool, Luc; Lauwereins, Rudy

2014-05-01

We present a novel scale-invariant image feature detection algorithm (D-SIFER) using a newly proposed scale-space optimal 10th-order Gaussian derivative (GDO-10) filter, which reaches the jointly optimal Heisenberg's uncertainty of its impulse response in scale and space simultaneously (i.e., we minimize the maximum of the two moments). The D-SIFER algorithm using this filter leads to an outstanding quality of image feature detection, with a factor of three quality improvement over state-of-the-art scale-invariant feature transform (SIFT) and speeded up robust features (SURF) methods that use the second-order Gaussian derivative filters. To reach low computational complexity, we also present a technique approximating the GDO-10 filters with a fixed-length implementation, which is independent of the scale. The final approximation error remains far below the noise margin, providing constant time, low cost, but nevertheless high-quality feature detection and registration capabilities. D-SIFER is validated on a real-life hyperspectral image registration application, precisely aligning up to hundreds of successive narrowband color images, despite their strong artifacts (blurring, low-light noise) typically occurring in such delicate optical system setups.

Mammographic and sonographic features of fat necrosis of the breast

International Nuclear Information System (INIS)

Upadhyaya, Vidya S; Uppoor, Raghuraj; Shetty, Lathika

2013-01-01

Imaging features of fat necrosis vary depending on its stage of evolution and can mimic malignancy in late stages. Imaging may suffice to differentiate fat necrosis in the early stages from malignancy and thus avoid unnecessary biopsy. In this pictorial essay, we present combination of benign features in mammography and/or ultrasonography (USG) that can lead to imaging diagnosis of fat necrosis. The follow-up imaging features of fat necrosis which mirror its pathophysiological evolution have also been demonstrated. To summarize, in the appropriate clinical setting, no mammographic features suspicious for malignancy should be present. When the typical mammographic features are not present, USG can aid with the diagnosis and follow up USG can confirm it

Quality Evaluation in Wireless Imaging Using Feature-Based Objective Metrics

OpenAIRE

Engelke, Ulrich; Zepernick, Hans-Jürgen

2007-01-01

This paper addresses the evaluation of image quality in the context of wireless systems using feature-based objective metrics. The considered metrics comprise of a weighted combination of feature values that are used to quantify the extend by which the related artifacts are present in a processed image. In view of imaging applications in mobile radio and wireless communication systems, reduced-reference objective quality metrics are investigated for quantifying user-perceived quality. The exa...

Differentiation of ductal carcinoma in situ versus fibrocystic changes by magnetic resonance imaging: are there pathognomonic imaging features?

Science.gov (United States)

Dietzel, Matthias; Kaiser, Clemens G; Wenkel, Evelyn; Clauser, Paola; Uder, Michael; Schulz-Wendtland, Rüdiger; Baltzer, Pascal At

2017-10-01

Background In breast magnetic resonance imaging (MRI), the diagnosis of ductal carcinoma in situ (DCIS) remains controversial; the most challenging cause of false-positive DCIS diagnosis is fibrocystic changes (FC). Purpose To search for typical and pathognomonic patterns of DCIS and FC using a standard clinical MRI protocol. Material and Methods Consecutive patients scheduled for breast MRI (standardized protocols @ 1.5T: dynamic-T1-GRE before/after Gd-DTPA [0.1 mmol/kg body weight (BW)]; T1-TSE), with subsequent pathological sampling, were investigated. Sixteen MRI descriptors were prospectively assessed by two experienced radiologists in consensus (blinded to pathology) and explored in patients with DCIS (n = 77) or FC (n = 219). Univariate and multivariate statistics were performed to identify the accuracy of descriptors (alone, combined). Furthermore, pathognomonic descriptor-combinations with an accuracy of 100% were explored (χ 2 statistics; decision trees). Results Six breast MRI descriptors significantly differentiated DCIS from FC ( P corrected  breast MRI and hence might help to decrease the number of unnecessary biopsies in this clinically challenging subgroup.

Quantitative Image Feature Engine (QIFE): an Open-Source, Modular Engine for 3D Quantitative Feature Extraction from Volumetric Medical Images.

Science.gov (United States)

Echegaray, Sebastian; Bakr, Shaimaa; Rubin, Daniel L; Napel, Sandy

2017-10-06

The aim of this study was to develop an open-source, modular, locally run or server-based system for 3D radiomics feature computation that can be used on any computer system and included in existing workflows for understanding associations and building predictive models between image features and clinical data, such as survival. The QIFE exploits various levels of parallelization for use on multiprocessor systems. It consists of a managing framework and four stages: input, pre-processing, feature computation, and output. Each stage contains one or more swappable components, allowing run-time customization. We benchmarked the engine using various levels of parallelization on a cohort of CT scans presenting 108 lung tumors. Two versions of the QIFE have been released: (1) the open-source MATLAB code posted to Github, (2) a compiled version loaded in a Docker container, posted to DockerHub, which can be easily deployed on any computer. The QIFE processed 108 objects (tumors) in 2:12 (h/mm) using 1 core, and 1:04 (h/mm) hours using four cores with object-level parallelization. We developed the Quantitative Image Feature Engine (QIFE), an open-source feature-extraction framework that focuses on modularity, standards, parallelism, provenance, and integration. Researchers can easily integrate it with their existing segmentation and imaging workflows by creating input and output components that implement their existing interfaces. Computational efficiency can be improved by parallelizing execution at the cost of memory usage. Different parallelization levels provide different trade-offs, and the optimal setting will depend on the size and composition of the dataset to be processed.

Feature extraction from mammographic images using fast marching methods

International Nuclear Information System (INIS)

Bottigli, U.; Golosio, B.

2002-01-01

Features extraction from medical images represents a fundamental step for shape recognition and diagnostic support. The present work faces the problem of the detection of large features, such as massive lesions and organ contours, from mammographic images. The regions of interest are often characterized by an average grayness intensity that is different from the surrounding. In most cases, however, the desired features cannot be extracted by simple gray level thresholding, because of image noise and non-uniform density of the surrounding tissue. In this work, edge detection is achieved through the fast marching method (Level Set Methods and Fast Marching Methods, Cambridge University Press, Cambridge, 1999), which is based on the theory of interface evolution. Starting from a seed point in the shape of interest, a front is generated which evolves according to an appropriate speed function. Such function is expressed in terms of geometric properties of the evolving interface and of image properties, and should become zero when the front reaches the desired boundary. Some examples of application of such method to mammographic images from the CALMA database (Nucl. Instr. and Meth. A 460 (2001) 107) are presented here and discussed

Imaging features of juxtacortical chondroma in children

International Nuclear Information System (INIS)

Miller, Stephen F.

2014-01-01

Juxtacortical chondroma is a rare benign bone lesion in children. Children usually present with a mildly painful mass, which prompts diagnostic imaging studies. The rarity of this condition often presents a diagnostic challenge. Correct diagnosis is crucial in guiding surgical management. To describe the characteristic imaging findings of juxtacortical chondroma in children. We identified all children who were diagnosed with juxtacortical chondroma between 1998 and 2012. A single experienced pediatric radiologist reviewed all diagnostic imaging studies, including plain radiographs, CT, MR and bone scans. Seven children (5 boys and 2 girls) with juxtacortical chondroma were identified, ranging in age from 6 years to 16 years (mean 12.3 years). Mild pain and a palpable mass were present in all seven children. Plain radiographs were available in 6/7, MR in 7/7, CT in 4/7 and skeletal scintigraphy in 5/7 children. Three lesions were located in the proximal humerus, with one each in the distal radius, distal femur, proximal tibia and scapula. Radiographic and CT features deemed highly suggestive of juxtacortical chondroma included cortical scalloping, underlying cortical sclerosis and overhanging margins. MRI features consistent with juxtacortical chondroma included isointensity to skeletal muscle on T1, marked hyperintensity on T2 and peripheral rim enhancement after contrast agent administration. One of seven lesions demonstrated intramedullary extension, and 2/7 showed adjacent soft-tissue edema. Juxtacortical chondroma is an uncommon benign lesion in children with characteristic features on plain radiographs, CT and MR. Recognition of these features is invaluable in guiding appropriate surgical management. (orig.)

Imaging features of juxtacortical chondroma in children

Energy Technology Data Exchange (ETDEWEB)

Miller, Stephen F. [St. Jude Children' s Research Hospital, Department of Radiological Sciences, Memphis, TN (United States)

2014-01-15

Juxtacortical chondroma is a rare benign bone lesion in children. Children usually present with a mildly painful mass, which prompts diagnostic imaging studies. The rarity of this condition often presents a diagnostic challenge. Correct diagnosis is crucial in guiding surgical management. To describe the characteristic imaging findings of juxtacortical chondroma in children. We identified all children who were diagnosed with juxtacortical chondroma between 1998 and 2012. A single experienced pediatric radiologist reviewed all diagnostic imaging studies, including plain radiographs, CT, MR and bone scans. Seven children (5 boys and 2 girls) with juxtacortical chondroma were identified, ranging in age from 6 years to 16 years (mean 12.3 years). Mild pain and a palpable mass were present in all seven children. Plain radiographs were available in 6/7, MR in 7/7, CT in 4/7 and skeletal scintigraphy in 5/7 children. Three lesions were located in the proximal humerus, with one each in the distal radius, distal femur, proximal tibia and scapula. Radiographic and CT features deemed highly suggestive of juxtacortical chondroma included cortical scalloping, underlying cortical sclerosis and overhanging margins. MRI features consistent with juxtacortical chondroma included isointensity to skeletal muscle on T1, marked hyperintensity on T2 and peripheral rim enhancement after contrast agent administration. One of seven lesions demonstrated intramedullary extension, and 2/7 showed adjacent soft-tissue edema. Juxtacortical chondroma is an uncommon benign lesion in children with characteristic features on plain radiographs, CT and MR. Recognition of these features is invaluable in guiding appropriate surgical management. (orig.)

Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesions.

Science.gov (United States)

Kirienko, Margarita; Cozzi, Luca; Rossi, Alexia; Voulaz, Emanuele; Antunovic, Lidija; Fogliata, Antonella; Chiti, Arturo; Sollini, Martina

2018-04-06

To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers. A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy. Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were -0.79 ± 0.06 and -0.81 ± 0.08, respectively (CT dataset) and -0.69 ± 0.05 and -0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or "Other", 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0

Low dose reconstruction algorithm for differential phase contrast imaging.

Science.gov (United States)

Wang, Zhentian; Huang, Zhifeng; Zhang, Li; Chen, Zhiqiang; Kang, Kejun; Yin, Hongxia; Wang, Zhenchang; Marco, Stampanoni

2011-01-01

Differential phase contrast imaging computed tomography (DPCI-CT) is a novel x-ray inspection method to reconstruct the distribution of refraction index rather than the attenuation coefficient in weakly absorbing samples. In this paper, we propose an iterative reconstruction algorithm for DPCI-CT which benefits from the new compressed sensing theory. We first realize a differential algebraic reconstruction technique (DART) by discretizing the projection process of the differential phase contrast imaging into a linear partial derivative matrix. In this way the compressed sensing reconstruction problem of DPCI reconstruction can be transformed to a resolved problem in the transmission imaging CT. Our algorithm has the potential to reconstruct the refraction index distribution of the sample from highly undersampled projection data. Thus it can significantly reduce the dose and inspection time. The proposed algorithm has been validated by numerical simulations and actual experiments.

COLOR IMAGE RETRIEVAL BASED ON FEATURE FUSION THROUGH MULTIPLE LINEAR REGRESSION ANALYSIS

Directory of Open Access Journals (Sweden)

K. Seetharaman

2015-08-01

Full Text Available This paper proposes a novel technique based on feature fusion using multiple linear regression analysis, and the least-square estimation method is employed to estimate the parameters. The given input query image is segmented into various regions according to the structure of the image. The color and texture features are extracted on each region of the query image, and the features are fused together using the multiple linear regression model. The estimated parameters of the model, which is modeled based on the features, are formed as a vector called a feature vector. The Canberra distance measure is adopted to compare the feature vectors of the query and target images. The F-measure is applied to evaluate the performance of the proposed technique. The obtained results expose that the proposed technique is comparable to the other existing techniques.

Imaging features of benign adrenal cysts

International Nuclear Information System (INIS)

Sanal, Hatice Tuba; Kocaoglu, Murat; Yildirim, Duzgun; Bulakbasi, Nail; Guvenc, Inanc; Tayfun, Cem; Ucoz, Taner

2006-01-01

Benign adrenal gland cysts (BACs) are rare lesions with a variable histological spectrum and may mimic not only each other but also malignant ones. We aimed to review imaging features of BACs which can be helpful in distinguishing each entity and determining the subsequent appropriate management

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

Science.gov (United States)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Differential Spatio-temporal Multiband Satellite Image Clustering using K-means Optimization With Reinforcement Programming

Directory of Open Access Journals (Sweden)

Irene Erlyn Wina Rachmawan

2015-06-01

Full Text Available Deforestration is one of the crucial issues in Indonesia because now Indonesia has world's highest deforestation rate. In other hand, multispectral image delivers a great source of data for studying spatial and temporal changeability of the environmental such as deforestration area. This research present differential image processing methods for detecting nature change of deforestration. Our differential image processing algorithms extract and indicating area automatically. The feature of our proposed idea produce extracted information from multiband satellite image and calculate the area of deforestration by years with calculating data using temporal dataset. Yet, multiband satellite image consists of big data size that were difficult to be handled for segmentation. Commonly, K- Means clustering is considered to be a powerfull clustering algorithm because of its ability to clustering big data. However K-Means has sensitivity of its first generated centroids, which could lead into a bad performance. In this paper we propose a new approach to optimize K-Means clustering using Reinforcement Programming in order to clustering multispectral image. We build a new mechanism for generating initial centroids by implementing exploration and exploitation knowledge from Reinforcement Programming. This optimization will lead a better result for K-means data cluster. We select multispectral image from Landsat 7 in past ten years in Medawai, Borneo, Indonesia, and apply two segmentation areas consist of deforestration land and forest field. We made series of experiments and compared the experimental results of K-means using Reinforcement Programming as optimizing initiate centroid and normal K-means without optimization process. Keywords: Deforestration, Multispectral images, landsat, automatic clustering, K-means.

Featured Image: Diamonds in a Meteorite

Science.gov (United States)

Kohler, Susanna

2018-04-01

This unique image which measures only 60 x 80 micrometers across reveals details in the Kapoeta meteorite, an 11-kg stone that fell in South Sudan in 1942. The sparkle in the image? A cluster of nanodiamonds discovered embedded in the stone in a recent study led by Yassir Abdu (University of Sharjah, United Arab Emirates). Abdu and collaborators showed that these nanodiamonds have similar spectral features to the interiors of dense interstellar clouds and they dont show any signs of shock features. This may suggest that the nanodiamonds were formed by condensation of nebular gases early in the history of the solar system. The diamonds were trapped in the surface material of the Kapoeta meteorites parent body, thought to be the asteroid Vesta. To read more about the authors study, check out the original article below.CitationYassir A. Abdu et al 2018 ApJL 856 L9. doi:10.3847/2041-8213/aab433

Vaginal Masses: Magnetic Resonance Imaging Features with Pathologic Correlation

International Nuclear Information System (INIS)

Elsayes, K.M.; Narra, V.R.; Dillman, J.R.; Velcheti, V.; Hameed, O.; Tongdee, R.; Menias, C.O.

2007-01-01

The detection of vaginal lesions has increased with the expanding use of cross-sectional imaging. Magnetic resonance imaging (MRI) - with its high-contrast resolution and multiplanar capabilities - is often useful for characterizing vaginal masses. Vaginal masses can be classified as congenital, inflammatory, cystic (benign), and neoplastic (benign or malignant) in etiology. Recognition of the typical MR imaging features of such lesions is important because it often determines the treatment approach and may obviate surgery. Finally, vaginal MR imaging can be used to evaluate post-treatment changes related to previous surgery and radiation therapy. In this article, we will review pertinent vaginal anatomy, vaginal and pelvic MRI technique, and the MRI features of a variety of vaginal lesions with pathological correlation

No-reference image quality assessment based on statistics of convolution feature maps

Science.gov (United States)

Lv, Xiaoxin; Qin, Min; Chen, Xiaohui; Wei, Guo

2018-04-01

We propose a Convolutional Feature Maps (CFM) driven approach to accurately predict image quality. Our motivation bases on the finding that the Nature Scene Statistic (NSS) features on convolution feature maps are significantly sensitive to distortion degree of an image. In our method, a Convolutional Neural Network (CNN) is trained to obtain kernels for generating CFM. We design a forward NSS layer which performs on CFM to better extract NSS features. The quality aware features derived from the output of NSS layer is effective to describe the distortion type and degree an image suffered. Finally, a Support Vector Regression (SVR) is employed in our No-Reference Image Quality Assessment (NR-IQA) model to predict a subjective quality score of a distorted image. Experiments conducted on two public databases demonstrate the promising performance of the proposed method is competitive to state of the art NR-IQA methods.

A blur-invariant local feature for motion blurred image matching

Science.gov (United States)

Tong, Qiang; Aoki, Terumasa

2017-07-01

Image matching between a blurred (caused by camera motion, out of focus, etc.) image and a non-blurred image is a critical task for many image/video applications. However, most of the existing local feature schemes fail to achieve this work. This paper presents a blur-invariant descriptor and a novel local feature scheme including the descriptor and the interest point detector based on moment symmetry - the authors' previous work. The descriptor is based on a new concept - center peak moment-like element (CPME) which is robust to blur and boundary effect. Then by constructing CPMEs, the descriptor is also distinctive and suitable for image matching. Experimental results show our scheme outperforms state of the art methods for blurred image matching

Mass-like extramedullary hematopoiesis: imaging features

Energy Technology Data Exchange (ETDEWEB)

Ginzel, Andrew W. [Synergy Radiology Associates, Houston, TX (United States); Kransdorf, Mark J.; Peterson, Jeffrey J.; Garner, Hillary W. [Mayo Clinic, Department of Radiology, Jacksonville, FL (United States); Murphey, Mark D. [American Institute for Radiologic Pathology, Silver Spring, MD (United States)

2012-08-15

To report the imaging appearances of mass-like extramedullary hematopoiesis (EMH), to identify those features that are sufficiently characteristic to allow a confident diagnosis, and to recognize the clinical conditions associated with EMH and the relative incidence of mass-like disease. We retrospectively identified 44 patients with EMH; 12 of which (27%) had focal mass-like lesions and formed the study group. The study group consisted of 6 male and 6 female subjects with a mean age of 58 years (range 13-80 years). All 12 patients underwent CT imaging and 3 of the 12 patients had undergone additional MR imaging. The imaging characteristics of the extramedullary hematopoiesis lesions in the study group were analyzed and recorded. The patient's clinical presentation, including any condition associated with extramedullary hematopoiesis, was also recorded. Ten of the 12 (83%) patients had one or more masses located along the axial skeleton. Of the 10 patients with axial masses, 9 (90%) had multiple masses and 7 (70%) demonstrated internal fat. Eight patients (80%) had paraspinal masses and 4 patients (40%) had presacral masses. Seven patients (70%) had splenomegaly. Eleven of the 12 patients had a clinical history available for review. A predisposing condition for extramedullary hematopoiesis was present in 10 patients and included various anemias (5 cases; 45%), myelofibrosis/myelodysplastic syndrome (4 cases; 36%), and marrow proliferative disorder (1 case; 9%). One patient had no known predisposing condition. Mass-like extramedullary hematopoiesis most commonly presents as multiple, fat-containing lesions localized to the axial skeleton. When these imaging features are identified, extramedullary hematopoiesis should be strongly considered, particularly when occurring in the setting of a predisposing medical condition. (orig.)

A standardised protocol for texture feature analysis of endoscopic images in gynaecological cancer

Directory of Open Access Journals (Sweden)

Pattichis Marios S

2007-11-01

Full Text Available Abstract Background In the development of tissue classification methods, classifiers rely on significant differences between texture features extracted from normal and abnormal regions. Yet, significant differences can arise due to variations in the image acquisition method. For endoscopic imaging of the endometrium, we propose a standardized image acquisition protocol to eliminate significant statistical differences due to variations in: (i the distance from the tissue (panoramic vs close up, (ii difference in viewing angles and (iii color correction. Methods We investigate texture feature variability for a variety of targets encountered in clinical endoscopy. All images were captured at clinically optimum illumination and focus using 720 × 576 pixels and 24 bits color for: (i a variety of testing targets from a color palette with a known color distribution, (ii different viewing angles, (iv two different distances from a calf endometrial and from a chicken cavity. Also, human images from the endometrium were captured and analysed. For texture feature analysis, three different sets were considered: (i Statistical Features (SF, (ii Spatial Gray Level Dependence Matrices (SGLDM, and (iii Gray Level Difference Statistics (GLDS. All images were gamma corrected and the extracted texture feature values were compared against the texture feature values extracted from the uncorrected images. Statistical tests were applied to compare images from different viewing conditions so as to determine any significant differences. Results For the proposed acquisition procedure, results indicate that there is no significant difference in texture features between the panoramic and close up views and between angles. For a calibrated target image, gamma correction provided an acquired image that was a significantly better approximation to the original target image. In turn, this implies that the texture features extracted from the corrected images provided for better

Imaging features of skeletal changes in children with Gaucher disease

International Nuclear Information System (INIS)

Zhang Ningning; Duan Xiaomin; Duan Yanlong

2011-01-01

Objective: To discuss the imaging features of skeletal changes in children with Gaucher disease on X-ray and MRI images. Methods: One hundred and nine children with Gaucher disease were enrolled in this study. They all received routine X-ray for spine with anterior-posterior (A-P) and lateral view and bilateral femurs with A-P view. Among them, 18 patients received X-ray for pelvic with A-P view, 14 patients received X-ray for left wrist with A-P view, and 14 patients received MRI scan for femur. The MRI scan included T 1 -weighted imaging, T 2 -weighted imaging and fat-suppressed T 2 -weighted imaging with short tau inversion recovery (STIR) sequence. The imaging features of the X-ray and MRI images were analyzed retrospectively. Results: The most common feature is osteoporosis, which presented in 91 cases (83.5%). Besides this, decreased density of metaphysis occurred in 86 cases (78.9%), erlenmeyer flask deformity of metaphysis occurred in 89 patients (81.7%), thinner cortex occurred in 69 cases (63.3%), osteolytic destruction occurred in. 31 cases (28.4%), pathological fractures occurred in 26 cases (23.9%), osteosclerosis occurred in 12 cases (11.0%). cystic degeneration of bone occurred in 16 cases (14.7%), and dislocation of the hip occurred in 4 cases. All 14 patients received MRI presented abnormal signals. Among them, 4 patients presented low signal intensity both on T 1 -weighted and T 2 -weighted images in bone marrow, the other ten presented high signal intensity mixed in low signal intensity areas on T 2 - weighted and fat-suppressed T 2 -weighted images. Conclusions: The imaging features of skeletal changes in children with Gaucher disease are of some characteristics, which could provide useful information for the clinical treatment. (authors)

SU-D-202-02: Quantitative Imaging: Correlation Between Image Feature Analysis and the Accuracy of Manually Drawn Contours On PET Images

Energy Technology Data Exchange (ETDEWEB)

Lamichhane, N; Johnson, P; Chinea, F; Patel, V; Yang, F [University of Miami, Miami, FL (United States)

2016-06-15

Purpose: To evaluate the correlation between image features and the accuracy of manually drawn target contours on synthetic PET images Methods: A digital PET phantom was used in combination with Monte Carlo simulation to create a set of 26 simulated PET images featuring a variety of tumor shapes and activity heterogeneity. These tumor volumes were used as a gold standard in comparisons with manual contours delineated by 10 radiation oncologist on the simulated PET images. Metrics used to evaluate segmentation accuracy included the dice coefficient, false positive dice, false negative dice, symmetric mean absolute surface distance, and absolute volumetric difference. Image features extracted from the simulated tumors consisted of volume, shape complexity, mean curvature, and intensity contrast along with five texture features derived from the gray-level neighborhood difference matrices including contrast, coarseness, busyness, strength, and complexity. Correlation between these features and contouring accuracy were examined. Results: Contour accuracy was reasonably well correlated with a variety of image features. Dice coefficient ranged from 0.7 to 0.90 and was correlated closely with contrast (r=0.43, p=0.02) and complexity (r=0.5, p<0.001). False negative dice ranged from 0.10 to 0.50 and was correlated closely with contrast (r=0.68, p<0.001) and complexity (r=0.66, p<0.001). Absolute volumetric difference ranged from 0.0002 to 0.67 and was correlated closely with coarseness (r=0.46, p=0.02) and complexity (r=0.49, p=0.008). Symmetric mean absolute difference ranged from 0.02 to 1 and was correlated closely with mean curvature (r=0.57, p=0.02) and contrast (r=0.6, p=0.001). Conclusion: The long term goal of this study is to assess whether contouring variability can be reduced by providing feedback to the practitioner based on image feature analysis. The results are encouraging and will be used to develop a statistical model which will enable a prediction of

Improved image retrieval based on fuzzy colour feature vector

Science.gov (United States)

Ben-Ahmeida, Ahlam M.; Ben Sasi, Ahmed Y.

2013-03-01

One of Image indexing techniques is the Content-Based Image Retrieval which is an efficient way for retrieving images from the image database automatically based on their visual contents such as colour, texture, and shape. In this paper will be discuss how using content-based image retrieval (CBIR) method by colour feature extraction and similarity checking. By dividing the query image and all images in the database into pieces and extract the features of each part separately and comparing the corresponding portions in order to increase the accuracy in the retrieval. The proposed approach is based on the use of fuzzy sets, to overcome the problem of curse of dimensionality. The contribution of colour of each pixel is associated to all the bins in the histogram using fuzzy-set membership functions. As a result, the Fuzzy Colour Histogram (FCH), outperformed the Conventional Colour Histogram (CCH) in image retrieving, due to its speedy results, where were images represented as signatures that took less size of memory, depending on the number of divisions. The results also showed that FCH is less sensitive and more robust to brightness changes than the CCH with better retrieval recall values.

Statistical analysis of textural features for improved classification of oral histopathological images.

Science.gov (United States)

Muthu Rama Krishnan, M; Shah, Pratik; Chakraborty, Chandan; Ray, Ajoy K

2012-04-01

The objective of this paper is to provide an improved technique, which can assist oncopathologists in correct screening of oral precancerous conditions specially oral submucous fibrosis (OSF) with significant accuracy on the basis of collagen fibres in the sub-epithelial connective tissue. The proposed scheme is composed of collagen fibres segmentation, its textural feature extraction and selection, screening perfomance enhancement under Gaussian transformation and finally classification. In this study, collagen fibres are segmented on R,G,B color channels using back-probagation neural network from 60 normal and 59 OSF histological images followed by histogram specification for reducing the stain intensity variation. Henceforth, textural features of collgen area are extracted using fractal approaches viz., differential box counting and brownian motion curve . Feature selection is done using Kullback-Leibler (KL) divergence criterion and the screening performance is evaluated based on various statistical tests to conform Gaussian nature. Here, the screening performance is enhanced under Gaussian transformation of the non-Gaussian features using hybrid distribution. Moreover, the routine screening is designed based on two statistical classifiers viz., Bayesian classification and support vector machines (SVM) to classify normal and OSF. It is observed that SVM with linear kernel function provides better classification accuracy (91.64%) as compared to Bayesian classifier. The addition of fractal features of collagen under Gaussian transformation improves Bayesian classifier's performance from 80.69% to 90.75%. Results are here studied and discussed.

Pregnancy-associated breast disease: radiologic features and diagnostic dilemmas.

Science.gov (United States)

Son, Eun Ju; Oh, Ki Keun; Kim, Eun Kyung

2006-02-28

In this paper, we evaluate the radiological features of pregnancy-associated breast lesions and discuss the difficulties in diagnosis by imaging. We selected patients who were diagnosed with pregnancy-associated breast lesions during the previous 5 years. All patients complained of palpable lesions in the breast and underwent ultrasonographic (US) examination, the first choice for examination of pregnancy-related breast lesions. Any suspicious lesions found by the US were recommended for a US-guided core biopsy, US-guided fine needle aspiration (FNA), or surgery. Various breast lesions were detected during pregnancy and lactation, including breast cancer, mastitis and abscesses, lactating adenoma, galactoceles, lobular hyperplasia, and fibroadenomas. The imaging features of pregnancy-associated breast lesions did not differ from the features of non-pregnancy-associated breast lesions; however, some pregnancy-associated benign lesions had suspicious sonographic features. A US-guided core biopsy was necessary for differentiating benign from malignant. In patients with breast cancer, the cancer was often advanced at the time of diagnosis. In conclusion, various pregnancy-related breast lesions were detected and the imaging of these lesions had variable findings. Breast ultrasound could be an excellent imaging modality for diagnosis and differentiation between benign and malignant lesions. However, when the imaging results are suspicious, a biopsy should be performed to obtain a pathologic diagnosis.

An image-processing methodology for extracting bloodstain pattern features.

Science.gov (United States)

Arthur, Ravishka M; Humburg, Philomena J; Hoogenboom, Jerry; Baiker, Martin; Taylor, Michael C; de Bruin, Karla G

2017-08-01

There is a growing trend in forensic science to develop methods to make forensic pattern comparison tasks more objective. This has generally involved the application of suitable image-processing methods to provide numerical data for identification or comparison. This paper outlines a unique image-processing methodology that can be utilised by analysts to generate reliable pattern data that will assist them in forming objective conclusions about a pattern. A range of features were defined and extracted from a laboratory-generated impact spatter pattern. These features were based in part on bloodstain properties commonly used in the analysis of spatter bloodstain patterns. The values of these features were consistent with properties reported qualitatively for such patterns. The image-processing method developed shows considerable promise as a way to establish measurable discriminating pattern criteria that are lacking in current bloodstain pattern taxonomies. Copyright © 2017 Elsevier B.V. All rights reserved.

Modality prediction of biomedical literature images using multimodal feature representation

Directory of Open Access Journals (Sweden)

Pelka, Obioma

2016-08-01

Full Text Available This paper presents the modelling approaches performed to automatically predict the modality of images found in biomedical literature. Various state-of-the-art visual features such as Bag-of-Keypoints computed with dense SIFT descriptors, texture features and Joint Composite Descriptors were used for visual image representation. Text representation was obtained by vector quantisation on a Bag-of-Words dictionary generated using attribute importance derived from a χ-test. Computing the principal components separately on each feature, dimension reduction as well as computational load reduction was achieved. Various multiple feature fusions were adopted to supplement visual image information with corresponding text information. The improvement obtained when using multimodal features vs. visual or text features was detected, analysed and evaluated. Random Forest models with 100 to 500 deep trees grown by resampling, a multi class linear kernel SVM with C=0.05 and a late fusion of the two classifiers were used for modality prediction. A Random Forest classifier achieved a higher accuracy and computed Bag-of-Keypoints with dense SIFT descriptors proved to be a better approach than with Lowe SIFT.

Localized scleroderma: imaging features

International Nuclear Information System (INIS)

Liu, P.; Uziel, Y.; Chuang, S.; Silverman, E.; Krafchik, B.; Laxer, R.

1994-01-01

Localized scleroderma is distinct from the diffuse form of scleroderma and does not show Raynaud's phenomenon and visceral involvement. The imaging features in 23 patients ranging from 2 to 17 years of age (mean 11.1 years) were reviewed. Leg length discrepancy and muscle atrophy were the most common findings (five patients), with two patients also showing modelling deformity of the fibula. One patient with lower extremity involvement showed abnormal bone marrow signals on MR. Disabling joint contracture requiring orthopedic intervention was noted in one patient. In two patients with ''en coup de sabre'' facial deformity, CT and MR scans revealed intracranial calcifications and white matter abnormality in the ipsilateral frontal lobes, with one also showing migrational abnormality. In a third patient, CT revealed white matter abnormality in the ipsilateral parietal lobe. In one patient with progressive facial hemiatrophy, CT and MR scans showed the underlying hypoplastic left maxillary antrum and cheek. Imaging studies of areas of clinical concern revealed positive findings in half our patients. (orig.)

Combining low level features and visual attributes for VHR remote sensing image classification

Science.gov (United States)

Zhao, Fumin; Sun, Hao; Liu, Shuai; Zhou, Shilin

2015-12-01

Semantic classification of very high resolution (VHR) remote sensing images is of great importance for land use or land cover investigation. A large number of approaches exploiting different kinds of low level feature have been proposed in the literature. Engineers are often frustrated by their conclusions and a systematic assessment of various low level features for VHR remote sensing image classification is needed. In this work, we firstly perform an extensive evaluation of eight features including HOG, dense SIFT, SSIM, GIST, Geo color, LBP, Texton and Tiny images for classification of three public available datasets. Secondly, we propose to transfer ground level scene attributes to remote sensing images. Thirdly, we combine both low-level features and mid-level visual attributes to further improve the classification performance. Experimental results demonstrate that i) Dene SIFT and HOG features are more robust than other features for VHR scene image description. ii) Visual attribute competes with a combination of low level features. iii) Multiple feature combination achieves the best performance under different settings.

A unified framework for image retrieval using keyword and visual features.

Science.gov (United States)

Jing, Feng; Li, Mingling; Zhang, Hong-Jiang; Zhang, Bo

2005-07-01

In this paper, a unified image retrieval framework based on both keyword annotations and visual features is proposed. In this framework, a set of statistical models are built based on visual features of a small set of manually labeled images to represent semantic concepts and used to propagate keywords to other unlabeled images. These models are updated periodically when more images implicitly labeled by users become available through relevance feedback. In this sense, the keyword models serve the function of accumulation and memorization of knowledge learned from user-provided relevance feedback. Furthermore, two sets of effective and efficient similarity measures and relevance feedback schemes are proposed for query by keyword scenario and query by image example scenario, respectively. Keyword models are combined with visual features in these schemes. In particular, a new, entropy-based active learning strategy is introduced to improve the efficiency of relevance feedback for query by keyword. Furthermore, a new algorithm is proposed to estimate the keyword features of the search concept for query by image example. It is shown to be more appropriate than two existing relevance feedback algorithms. Experimental results demonstrate the effectiveness of the proposed framework.

Differential clinical features and stool findings in shigellosis and amoebic dysentery

NARCIS (Netherlands)

Speelman, P.; McGlaughlin, R.; Kabir, I.; Butler, T.

1987-01-01

To obtain information that could assist the clinician to differentiate between shigellosis and amoebic dysentery, we compared clinical features and stool findings in 58 adult male patients in Bangladesh. Mean values indicated that patients with invasive amoebiasis were older and had a longer

Face detection on distorted images using perceptual quality-aware features

Science.gov (United States)

Gunasekar, Suriya; Ghosh, Joydeep; Bovik, Alan C.

2014-02-01

We quantify the degradation in performance of a popular and effective face detector when human-perceived image quality is degraded by distortions due to additive white gaussian noise, gaussian blur or JPEG compression. It is observed that, within a certain range of perceived image quality, a modest increase in image quality can drastically improve face detection performance. These results can be used to guide resource or bandwidth allocation in a communication/delivery system that is associated with face detection tasks. A new face detector based on QualHOG features is also proposed that augments face-indicative HOG features with perceptual quality-aware spatial Natural Scene Statistics (NSS) features, yielding improved tolerance against image distortions. The new detector provides statistically significant improvements over a strong baseline on a large database of face images representing a wide range of distortions. To facilitate this study, we created a new Distorted Face Database, containing face and non-face patches from images impaired by a variety of common distortion types and levels. This new dataset is available for download and further experimentation at www.ideal.ece.utexas.edu/˜suriya/DFD/.

Gilbert’s syndrome: clinical features, diagnostics, differential diagnosis and treatment (part 2

Directory of Open Access Journals (Sweden)

T.V. Sorokman

2017-02-01

discoloration of the skin (“teinte bilieuse”, especially on the face, hands, and feet without a distinct scleral icterus. Sometimes the development of repeatedly intermittent episodes of jaundice with high bilirubinemia (indirect bilirubin without the evidence of hemolysis (differential diagnostic feature is observed. 2. A tendency to development of pigmented and vascular nevi and xanthelasma of the eyelids, and hyperpigmentation around the eyes; to bradycardia, hypothermia, migraine, postural, intermittent albuminuria or to alimentary glycosuria. 3. An increased tendency to pigmentation under the influence of light, heat, and also chemical and mechanical stimuli. 4. A neuromuscular hyperexcitability. 5. Increased sensitivity to cold. 6. Dyspeptic complaints (pain, nausea, abdominal bloa­ting, diarrhea or constipation. 7. No signs of increased hemolysis (differential diagnostic feature with increasing content in, bilirubin (differential diagnostic feature. 8. The majority of patients have normal liver function tests (differential diagnostic feature also normal bromsulphalein test is also normal (differential diagnostic feature. 9. The biochemical abnormality is not detected by histological methods (differential diagnostic feature .10. Frequently, a family disease of the liver is observed. The differential diagnosis of GS is conducted with all types of hyperbilirubinemias, hemolytic anemias, congenital hepatic cirrhosis, hepatitis, cholecystopathy, atresia of biliary ducts or the small intestine. Medications are used only in severe hyperbilirubinemias and as concomitant therapy in the presence of symptoms of vitamin deficiencies, violations of a motor-evacuation function of the upper digestive tract in the clinical picture and to prevent complications (cholelithiasis.

Efficient and robust model-to-image alignment using 3D scale-invariant features.

Science.gov (United States)

Toews, Matthew; Wells, William M

2013-04-01

This paper presents feature-based alignment (FBA), a general method for efficient and robust model-to-image alignment. Volumetric images, e.g. CT scans of the human body, are modeled probabilistically as a collage of 3D scale-invariant image features within a normalized reference space. Features are incorporated as a latent random variable and marginalized out in computing a maximum a posteriori alignment solution. The model is learned from features extracted in pre-aligned training images, then fit to features extracted from a new image to identify a globally optimal locally linear alignment solution. Novel techniques are presented for determining local feature orientation and efficiently encoding feature intensity in 3D. Experiments involving difficult magnetic resonance (MR) images of the human brain demonstrate FBA achieves alignment accuracy similar to widely-used registration methods, while requiring a fraction of the memory and computation resources and offering a more robust, globally optimal solution. Experiments on CT human body scans demonstrate FBA as an effective system for automatic human body alignment where other alignment methods break down. Copyright © 2012 Elsevier B.V. All rights reserved.

Classification of C2C12 cells at differentiation by convolutional neural network of deep learning using phase contrast images.

Science.gov (United States)

Niioka, Hirohiko; Asatani, Satoshi; Yoshimura, Aina; Ohigashi, Hironori; Tagawa, Seiichi; Miyake, Jun

2018-01-01

In the field of regenerative medicine, tremendous numbers of cells are necessary for tissue/organ regeneration. Today automatic cell-culturing system has been developed. The next step is constructing a non-invasive method to monitor the conditions of cells automatically. As an image analysis method, convolutional neural network (CNN), one of the deep learning method, is approaching human recognition level. We constructed and applied the CNN algorithm for automatic cellular differentiation recognition of myogenic C2C12 cell line. Phase-contrast images of cultured C2C12 are prepared as input dataset. In differentiation process from myoblasts to myotubes, cellular morphology changes from round shape to elongated tubular shape due to fusion of the cells. CNN abstract the features of the shape of the cells and classify the cells depending on the culturing days from when differentiation is induced. Changes in cellular shape depending on the number of days of culture (Day 0, Day 3, Day 6) are classified with 91.3% accuracy. Image analysis with CNN has a potential to realize regenerative medicine industry.

Automatic plankton image classification combining multiple view features via multiple kernel learning.

Science.gov (United States)

Zheng, Haiyong; Wang, Ruchen; Yu, Zhibin; Wang, Nan; Gu, Zhaorui; Zheng, Bing

2017-12-28

Plankton, including phytoplankton and zooplankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, plankton is very sensitive to environment changes, and the study of plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoplankton to zooplankton. The experimental results validated that our system

An improved feature extraction algorithm based on KAZE for multi-spectral image

Science.gov (United States)

Yang, Jianping; Li, Jun

2018-02-01

Multi-spectral image contains abundant spectral information, which is widely used in all fields like resource exploration, meteorological observation and modern military. Image preprocessing, such as image feature extraction and matching, is indispensable while dealing with multi-spectral remote sensing image. Although the feature matching algorithm based on linear scale such as SIFT and SURF performs strong on robustness, the local accuracy cannot be guaranteed. Therefore, this paper proposes an improved KAZE algorithm, which is based on nonlinear scale, to raise the number of feature and to enhance the matching rate by using the adjusted-cosine vector. The experiment result shows that the number of feature and the matching rate of the improved KAZE are remarkably than the original KAZE algorithm.

Imaging strategy in differentiated thyroid cancer

NARCIS (Netherlands)

Phan, Thi Thanh Ha

2007-01-01

This thesis focuses on clinical dilemmas, which the clinician faces in the management of patients with differentiated thyroid cancer (DTC) with a specific emphasis on the role of current and new diagnostic imaging. Thyroid cancer is a rare disease, but it is the most common endocrine malignancy of

Tissue Feature-Based and Segmented Deformable Image Registration for Improved Modeling of Shear Movement of Lungs

International Nuclear Information System (INIS)

Xie Yaoqin; Chao Ming; Xing Lei

2009-01-01

Purpose: To report a tissue feature-based image registration strategy with explicit inclusion of the differential motions of thoracic structures. Methods and Materials: The proposed technique started with auto-identification of a number of corresponding points with distinct tissue features. The tissue feature points were found by using the scale-invariant feature transform method. The control point pairs were then sorted into different 'colors' according to the organs in which they resided and used to model the involved organs individually. A thin-plate spline method was used to register a structure characterized by the control points with a given 'color.' The proposed technique was applied to study a digital phantom case and 3 lung and 3 liver cancer patients. Results: For the phantom case, a comparison with the conventional thin-plate spline method showed that the registration accuracy was markedly improved when the differential motions of the lung and chest wall were taken into account. On average, the registration error and standard deviation of the 15 points against the known ground truth were reduced from 3.0 to 0.5 mm and from 1.5 to 0.2 mm, respectively, when the new method was used. A similar level of improvement was achieved for the clinical cases. Conclusion: The results of our study have shown that the segmented deformable approach provides a natural and logical solution to model the discontinuous organ motions and greatly improves the accuracy and robustness of deformable registration.

Magnetic resonance imaging features of fibrocystic change of the breast.

Science.gov (United States)

Chen, Jeon-Hor; Liu, Hui; Baek, Hyeon-Man; Nalcioglu, Orhan; Su, Min-Ying

2008-11-01

Studies specifically reporting MRI of fibrocystic change (FCC) of the breast are very few and its MRI features are not clearly known. The purpose of this study was to analyze the MRI features of FCC of the breast. Thirty-one patients with pathologically proven FCC of the breast were retrospectively reviewed. The MRI study was performed using a 1.5-T MR scanner with standard bilateral breast coil. The imaging protocol consisted of pre-contrast T1-weighed imaging and dynamic contrast-enhanced axial T1-weighed imaging. The MRI features were interpreted based on the morphologic and enhancement kinetic descriptors defined on ACR BIRADS-MRI lexicon. FCC of the breast had a wide spectrum of morphologic and kinetic features on MRI. Two types of FCC were found, including a more diffuse type of nonmass lesion (12/31, 39%) showing benign enhancement kinetic pattern with medium wash-in in early phase (9/10, 90%) and a focal mass-type lesion (11/31, 35%) with enhancement kinetic usually showing rapid up-slope mimicking a breast cancer (8/11, 73%). MRI is able to elaborate the diverse imaging features of FCC of the breast. Our result showed that FCC presenting as a focal mass-type lesion was usually overdiagnosed as malignancy. Understanding MRI of FCC is important to determine which cohort of patients should be followed up alone or receive aggressive management.

Feature Extraction in Sequential Multimedia Images: with Applications in Satellite Images and On-line Videos

Science.gov (United States)

Liang, Yu-Li

Multimedia data is increasingly important in scientific discovery and people's daily lives. Content of massive multimedia is often diverse and noisy, and motion between frames is sometimes crucial in analyzing those data. Among all, still images and videos are commonly used formats. Images are compact in size but do not contain motion information. Videos record motion but are sometimes too big to be analyzed. Sequential images, which are a set of continuous images with low frame rate, stand out because they are smaller than videos and still maintain motion information. This thesis investigates features in different types of noisy sequential images, and the proposed solutions that intelligently combined multiple features to successfully retrieve visual information from on-line videos and cloudy satellite images. The first task is detecting supraglacial lakes above ice sheet in sequential satellite images. The dynamics of supraglacial lakes on the Greenland ice sheet deeply affect glacier movement, which is directly related to sea level rise and global environment change. Detecting lakes above ice is suffering from diverse image qualities and unexpected clouds. A new method is proposed to efficiently extract prominent lake candidates with irregular shapes, heterogeneous backgrounds, and in cloudy images. The proposed system fully automatize the procedure that track lakes with high accuracy. We further cooperated with geoscientists to examine the tracked lakes and found new scientific findings. The second one is detecting obscene content in on-line video chat services, such as Chatroulette, that randomly match pairs of users in video chat sessions. A big problem encountered in such systems is the presence of flashers and obscene content. Because of various obscene content and unstable qualities of videos capture by home web-camera, detecting misbehaving users is a highly challenging task. We propose SafeVchat, which is the first solution that achieves satisfactory

Tracking image features with PCA-SURF descriptors

CSIR Research Space (South Africa)

Pancham, A

2015-05-01

Full Text Available IAPR International Conference on Machine Vision Applications, May 18-22, 2015, Tokyo, JAPAN Tracking Image Features with PCA-SURF Descriptors Ardhisha Pancham CSIR, UKZN South Africa apancham@csir.co.za Daniel Withey CSIR South Africa...

A comparative study of image low level feature extraction algorithms

Directory of Open Access Journals (Sweden)

M.M. El-gayar

2013-07-01

Full Text Available Feature extraction and matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods for assessing the performance of popular image matching algorithms are presented and rely on costly descriptors for detection and matching. Specifically, the method assesses the type of images under which each of the algorithms reviewed herein perform to its maximum or highest efficiency. The efficiency is measured in terms of the number of matches founds by the algorithm and the number of type I and type II errors encountered when the algorithm is tested against a specific pair of images. Current comparative studies asses the performance of the algorithms based on the results obtained in different criteria such as speed, sensitivity, occlusion, and others. This study addresses the limitations of the existing comparative tools and delivers a generalized criterion to determine beforehand the level of efficiency expected from a matching algorithm given the type of images evaluated. The algorithms and the respective images used within this work are divided into two groups: feature-based and texture-based. And from this broad classification only three of the most widely used algorithms are assessed: color histogram, FAST (Features from Accelerated Segment Test, SIFT (Scale Invariant Feature Transform, PCA-SIFT (Principal Component Analysis-SIFT, F-SIFT (fast-SIFT and SURF (speeded up robust features. The performance of the Fast-SIFT (F-SIFT feature detection methods are compared for scale changes, rotation, blur, illumination changes and affine transformations. All the experiments use repeatability measurement and the number of correct matches for the evaluation measurements. SIFT presents its stability in most situations although its slow. F-SIFT is the fastest one with good performance as the same as SURF, SIFT, PCA-SIFT show its advantages in rotation and illumination changes.

Modeling multiple visual words assignment for bag-of-features based medical image retrieval

KAUST Repository

Wang, Jim Jing-Yan

2012-01-01

In this paper, we investigate the bag-of-features based medical image retrieval methods, which represent an image as a collection of local features, such as image patch and key points with SIFT descriptor. To improve the bag-of-features method, we first model the assignment of local descriptor as contribution functions, and then propose a new multiple assignment strategy. By assuming the local feature can be reconstructed by its neighboring visual words in vocabulary, we solve the reconstruction weights as a QP problem and then use the solved weights as contribution functions, which results in a new assignment method called the QP assignment. We carry our experiments on ImageCLEFmed datasets. Experiments\\' results show that our proposed method exceeds the performances of traditional solutions and works well for the bag-of-features based medical image retrieval tasks.

Modeling multiple visual words assignment for bag-of-features based medical image retrieval

KAUST Repository

Wang, Jim Jing-Yan; Almasri, Islam

2012-01-01

In this paper, we investigate the bag-of-features based medical image retrieval methods, which represent an image as a collection of local features, such as image patch and key points with SIFT descriptor. To improve the bag-of-features method, we first model the assignment of local descriptor as contribution functions, and then propose a new multiple assignment strategy. By assuming the local feature can be reconstructed by its neighboring visual words in vocabulary, we solve the reconstruction weights as a QP problem and then use the solved weights as contribution functions, which results in a new assignment method called the QP assignment. We carry our experiments on ImageCLEFmed datasets. Experiments' results show that our proposed method exceeds the performances of traditional solutions and works well for the bag-of-features based medical image retrieval tasks.

Can magnetic resonance imaging differentiate undifferentiated arthritis?

DEFF Research Database (Denmark)

Østergaard, Mikkel; Duer, Anne; Hørslev-Petersen, K

2005-01-01

A high sensitivity for the detection of inflammatory and destructive changes in inflammatory joint diseases makes magnetic resonance imaging potentially useful for assigning specific diagnoses, such as rheumatoid arthritis and psoriatic arthritis in arthritides, that remain undifferentiated after...... conventional clinical, biochemical and radiographic examinations. With recent data as the starting point, the present paper describes the current knowledge on magnetic resonance imaging in the differential diagnosis of undifferentiated arthritis....

US or MR Imaging Features of Polypoid Endometriosis: A Case Report

International Nuclear Information System (INIS)

Park, Jae Il; Cho, Jae Ho; Kim, Geum Rae; Kim, Mi Jin

2009-01-01

Polypoid endometriosis is a rare variant of endometriosis that is pathologically similar to an endometrial polyp. This lesion is frequently mistaken for a solid neoplasm in clinical, radiological and pathological examinations. The clinical and pathological features of the lesion have been well described in the English literature. However, its imaging features have not been reported in the Korean literature. We describe ultrasound and magnetic resonance imaging features of pathologically-confirmed polypoid endometriosis

US or MR Imaging Features of Polypoid Endometriosis: A Case Report

Energy Technology Data Exchange (ETDEWEB)

Park, Jae Il; Cho, Jae Ho; Kim, Geum Rae; Kim, Mi Jin [Yeungnam University, Gyeongsan (Korea, Republic of)

2009-12-15

Polypoid endometriosis is a rare variant of endometriosis that is pathologically similar to an endometrial polyp. This lesion is frequently mistaken for a solid neoplasm in clinical, radiological and pathological examinations. The clinical and pathological features of the lesion have been well described in the English literature. However, its imaging features have not been reported in the Korean literature. We describe ultrasound and magnetic resonance imaging features of pathologically-confirmed polypoid endometriosis.

A local region of interest image reconstruction via filtered backprojection for fan-beam differential phase-contrast computed tomography

International Nuclear Information System (INIS)

Qi Zhihua; Chen Guanghong

2007-01-01

Recently, x-ray differential phase contrast computed tomography (DPC-CT) has been experimentally implemented using a conventional source combined with several gratings. Images were reconstructed using a parallel-beam reconstruction formula. However, parallel-beam reconstruction formulae are not directly applicable for a large image object where the parallel-beam approximation fails. In this note, we present a new image reconstruction formula for fan-beam DPC-CT. There are two major features in this algorithm: (1) it enables the reconstruction of a local region of interest (ROI) using data acquired from an angular interval shorter than 180 0 + fan angle and (2) it still preserves the filtered backprojection structure. Numerical simulations have been conducted to validate the image reconstruction algorithm. (note)

Imaging features of mycobacterium in patients with acquired immunodeficiency syndrome

International Nuclear Information System (INIS)

Yang Jun; Sun Yue; Wei Liangui; Xu Yunliang; Li Xingwang

2013-01-01

Objective: To analyze the imaging features of mycobacterium in AIDS patients. Methods: Twenty-three cases of mycobacterium tuberculosis and 13 patients of non-tuberculous mycobacteria were proved etiologically and included in this study. All patients underwent X-ray and CT examinations, imaging data were analyzed and compared. Results: The imaging findings of mycobacterium tuberculosis in AIDS patients included consolidation (n = 11), pleural effusion (n = 11), mediastinal lymphadenopathy (n = 11). Pulmonary lesions were always diffuse distribution, and 14 patients of extrapulmonary tuberculosis were found. Pulmonary lesions in non-tuberculous mycobacteria tend to be circumscribed. Conclusions: Non-tuberculous mycobacterial infection in AIDS patients is more common and usually combined with other infections. Imaging features are atypical. (authors)

Face recognition via sparse representation of SIFT feature on hexagonal-sampling image

Science.gov (United States)

Zhang, Daming; Zhang, Xueyong; Li, Lu; Liu, Huayong

2018-04-01

This paper investigates a face recognition approach based on Scale Invariant Feature Transform (SIFT) feature and sparse representation. The approach takes advantage of SIFT which is local feature other than holistic feature in classical Sparse Representation based Classification (SRC) algorithm and possesses strong robustness to expression, pose and illumination variations. Since hexagonal image has more inherit merits than square image to make recognition process more efficient, we extract SIFT keypoint in hexagonal-sampling image. Instead of matching SIFT feature, firstly the sparse representation of each SIFT keypoint is given according the constructed dictionary; secondly these sparse vectors are quantized according dictionary; finally each face image is represented by a histogram and these so-called Bag-of-Words vectors are classified by SVM. Due to use of local feature, the proposed method achieves better result even when the number of training sample is small. In the experiments, the proposed method gave higher face recognition rather than other methods in ORL and Yale B face databases; also, the effectiveness of the hexagonal-sampling in the proposed method is verified.

Convolutional deep belief network with feature encoding for classification of neuroblastoma histological images

Directory of Open Access Journals (Sweden)

Soheila Gheisari

2018-01-01

Full Text Available Background: Neuroblastoma is the most common extracranial solid tumor in children younger than 5 years old. Optimal management of neuroblastic tumors depends on many factors including histopathological classification. The gold standard for classification of neuroblastoma histological images is visual microscopic assessment. In this study, we propose and evaluate a deep learning approach to classify high-resolution digital images of neuroblastoma histology into five different classes determined by the Shimada classification. Subjects and Methods: We apply a combination of convolutional deep belief network (CDBN with feature encoding algorithm that automatically classifies digital images of neuroblastoma histology into five different classes. We design a three-layer CDBN to extract high-level features from neuroblastoma histological images and combine with a feature encoding model to extract features that are highly discriminative in the classification task. The extracted features are classified into five different classes using a support vector machine classifier. Data: We constructed a dataset of 1043 neuroblastoma histological images derived from Aperio scanner from 125 patients representing different classes of neuroblastoma tumors. Results: The weighted average F-measure of 86.01% was obtained from the selected high-level features, outperforming state-of-the-art methods. Conclusion: The proposed computer-aided classification system, which uses the combination of deep architecture and feature encoding to learn high-level features, is highly effective in the classification of neuroblastoma histological images.

Polarimetric SAR Image Classification Using Multiple-feature Fusion and Ensemble Learning

Directory of Open Access Journals (Sweden)

Sun Xun

2016-12-01

Full Text Available In this paper, we propose a supervised classification algorithm for Polarimetric Synthetic Aperture Radar (PolSAR images using multiple-feature fusion and ensemble learning. First, we extract different polarimetric features, including extended polarimetric feature space, Hoekman, Huynen, H/alpha/A, and fourcomponent scattering features of PolSAR images. Next, we randomly select two types of features each time from all feature sets to guarantee the reliability and diversity of later ensembles and use a support vector machine as the basic classifier for predicting classification results. Finally, we concatenate all prediction probabilities of basic classifiers as the final feature representation and employ the random forest method to obtain final classification results. Experimental results at the pixel and region levels show the effectiveness of the proposed algorithm.

Segmentation methodology for automated classification and differentiation of soft tissues in multiband images of high-resolution ultrasonic transmission tomography.

Science.gov (United States)

Jeong, Jeong-Won; Shin, Dae C; Do, Synho; Marmarelis, Vasilis Z

2006-08-01

This paper presents a novel segmentation methodology for automated classification and differentiation of soft tissues using multiband data obtained with the newly developed system of high-resolution ultrasonic transmission tomography (HUTT) for imaging biological organs. This methodology extends and combines two existing approaches: the L-level set active contour (AC) segmentation approach and the agglomerative hierarchical kappa-means approach for unsupervised clustering (UC). To prevent the trapping of the current iterative minimization AC algorithm in a local minimum, we introduce a multiresolution approach that applies the level set functions at successively increasing resolutions of the image data. The resulting AC clusters are subsequently rearranged by the UC algorithm that seeks the optimal set of clusters yielding the minimum within-cluster distances in the feature space. The presented results from Monte Carlo simulations and experimental animal-tissue data demonstrate that the proposed methodology outperforms other existing methods without depending on heuristic parameters and provides a reliable means for soft tissue differentiation in HUTT images.

Pleasant/Unpleasant Filtering for Affective Image Retrieval Based on Cross-Correlation of EEG Features

Directory of Open Access Journals (Sweden)

Keranmu Xielifuguli

2014-01-01

Full Text Available People often make decisions based on sensitivity rather than rationality. In the field of biological information processing, methods are available for analyzing biological information directly based on electroencephalogram: EEG to determine the pleasant/unpleasant reactions of users. In this study, we propose a sensitivity filtering technique for discriminating preferences (pleasant/unpleasant for images using a sensitivity image filtering system based on EEG. Using a set of images retrieved by similarity retrieval, we perform the sensitivity-based pleasant/unpleasant classification of images based on the affective features extracted from images with the maximum entropy method: MEM. In the present study, the affective features comprised cross-correlation features obtained from EEGs produced when an individual observed an image. However, it is difficult to measure the EEG when a subject visualizes an unknown image. Thus, we propose a solution where a linear regression method based on canonical correlation is used to estimate the cross-correlation features from image features. Experiments were conducted to evaluate the validity of sensitivity filtering compared with image similarity retrieval methods based on image features. We found that sensitivity filtering using color correlograms was suitable for the classification of preferred images, while sensitivity filtering using local binary patterns was suitable for the classification of unpleasant images. Moreover, sensitivity filtering using local binary patterns for unpleasant images had a 90% success rate. Thus, we conclude that the proposed method is efficient for filtering unpleasant images.

3D-2D Deformable Image Registration Using Feature-Based Nonuniform Meshes.

Science.gov (United States)

Zhong, Zichun; Guo, Xiaohu; Cai, Yiqi; Yang, Yin; Wang, Jing; Jia, Xun; Mao, Weihua

2016-01-01

By using prior information of planning CT images and feature-based nonuniform meshes, this paper demonstrates that volumetric images can be efficiently registered with a very small portion of 2D projection images of a Cone-Beam Computed Tomography (CBCT) scan. After a density field is computed based on the extracted feature edges from planning CT images, nonuniform tetrahedral meshes will be automatically generated to better characterize the image features according to the density field; that is, finer meshes are generated for features. The displacement vector fields (DVFs) are specified at the mesh vertices to drive the deformation of original CT images. Digitally reconstructed radiographs (DRRs) of the deformed anatomy are generated and compared with corresponding 2D projections. DVFs are optimized to minimize the objective function including differences between DRRs and projections and the regularity. To further accelerate the above 3D-2D registration, a procedure to obtain good initial deformations by deforming the volume surface to match 2D body boundary on projections has been developed. This complete method is evaluated quantitatively by using several digital phantoms and data from head and neck cancer patients. The feature-based nonuniform meshing method leads to better results than either uniform orthogonal grid or uniform tetrahedral meshes.

3D-2D Deformable Image Registration Using Feature-Based Nonuniform Meshes

Directory of Open Access Journals (Sweden)

Zichun Zhong

2016-01-01

Full Text Available By using prior information of planning CT images and feature-based nonuniform meshes, this paper demonstrates that volumetric images can be efficiently registered with a very small portion of 2D projection images of a Cone-Beam Computed Tomography (CBCT scan. After a density field is computed based on the extracted feature edges from planning CT images, nonuniform tetrahedral meshes will be automatically generated to better characterize the image features according to the density field; that is, finer meshes are generated for features. The displacement vector fields (DVFs are specified at the mesh vertices to drive the deformation of original CT images. Digitally reconstructed radiographs (DRRs of the deformed anatomy are generated and compared with corresponding 2D projections. DVFs are optimized to minimize the objective function including differences between DRRs and projections and the regularity. To further accelerate the above 3D-2D registration, a procedure to obtain good initial deformations by deforming the volume surface to match 2D body boundary on projections has been developed. This complete method is evaluated quantitatively by using several digital phantoms and data from head and neck cancer patients. The feature-based nonuniform meshing method leads to better results than either uniform orthogonal grid or uniform tetrahedral meshes.

Simultenious binary hash and features learning for image retrieval

Science.gov (United States)

Frantc, V. A.; Makov, S. V.; Voronin, V. V.; Marchuk, V. I.; Semenishchev, E. A.; Egiazarian, K. O.; Agaian, S.

2016-05-01

Content-based image retrieval systems have plenty of applications in modern world. The most important one is the image search by query image or by semantic description. Approaches to this problem are employed in personal photo-collection management systems, web-scale image search engines, medical systems, etc. Automatic analysis of large unlabeled image datasets is virtually impossible without satisfactory image-retrieval technique. It's the main reason why this kind of automatic image processing has attracted so much attention during recent years. Despite rather huge progress in the field, semantically meaningful image retrieval still remains a challenging task. The main issue here is the demand to provide reliable results in short amount of time. This paper addresses the problem by novel technique for simultaneous learning of global image features and binary hash codes. Our approach provide mapping of pixel-based image representation to hash-value space simultaneously trying to save as much of semantic image content as possible. We use deep learning methodology to generate image description with properties of similarity preservation and statistical independence. The main advantage of our approach in contrast to existing is ability to fine-tune retrieval procedure for very specific application which allow us to provide better results in comparison to general techniques. Presented in the paper framework for data- dependent image hashing is based on use two different kinds of neural networks: convolutional neural networks for image description and autoencoder for feature to hash space mapping. Experimental results confirmed that our approach has shown promising results in compare to other state-of-the-art methods.

An Orthogonal Learning Differential Evolution Algorithm for Remote Sensing Image Registration

Directory of Open Access Journals (Sweden)

Wenping Ma

2014-01-01

Full Text Available We introduce an area-based method for remote sensing image registration. We use orthogonal learning differential evolution algorithm to optimize the similarity metric between the reference image and the target image. Many local and global methods have been used to achieve the optimal similarity metric in the last few years. Because remote sensing images are usually influenced by large distortions and high noise, local methods will fail in some cases. For this reason, global methods are often required. The orthogonal learning (OL strategy is efficient when searching in complex problem spaces. In addition, it can discover more useful information via orthogonal experimental design (OED. Differential evolution (DE is a heuristic algorithm. It has shown to be efficient in solving the remote sensing image registration problem. So orthogonal learning differential evolution algorithm (OLDE is efficient for many optimization problems. The OLDE method uses the OL strategy to guide the DE algorithm to discover more useful information. Experiments show that the OLDE method is more robust and efficient for registering remote sensing images.

The fuzzy Hough Transform-feature extraction in medical images

International Nuclear Information System (INIS)

Philip, K.P.; Dove, E.L.; Stanford, W.; Chandran, K.B.; McPherson, D.D.; Gotteiner, N.L.

1994-01-01

Identification of anatomical features is a necessary step for medical image analysis. Automatic methods for feature identification using conventional pattern recognition techniques typically classify an object as a member of a predefined class of objects, but do not attempt to recover the exact or approximate shape of that object. For this reason, such techniques are usually not sufficient to identify the borders of organs when individual geometry varies in local detail, even though the general geometrical shape is similar. The authors present an algorithm that detects features in an image based on approximate geometrical models. The algorithm is based on the traditional and generalized Hough Transforms but includes notions from fuzzy set theory. The authors use the new algorithm to roughly estimate the actual locations of boundaries of an internal organ, and from this estimate, to determine a region of interest around the organ. Based on this rough estimate of the border location, and the derived region of interest, the authors find the final estimate of the true borders with other image processing techniques. The authors present results that demonstrate that the algorithm was successfully used to estimate the approximate location of the chest wall in humans, and of the left ventricular contours of a dog heart obtained from cine-computed tomographic images. The authors use this fuzzy Hough Transform algorithm as part of a larger procedures to automatically identify the myocardial contours of the heart. This algorithm may also allow for more rapid image processing and clinical decision making in other medical imaging applications

Localized scleroderma: imaging features

Energy Technology Data Exchange (ETDEWEB)

Liu, P. (Dept. of Diagnostic Imaging, Hospital for Sick Children, Toronto, ON (Canada)); Uziel, Y. (Div. of Rheumatology, Hospital for Sick Children, Toronto, ON (Canada)); Chuang, S. (Dept. of Diagnostic Imaging, Hospital for Sick Children, Toronto, ON (Canada)); Silverman, E. (Div. of Rheumatology, Hospital for Sick Children, Toronto, ON (Canada)); Krafchik, B. (Div. of Dermatology, Dept. of Pediatrics, Hospital for Sick Children, Toronto, ON (Canada)); Laxer, R. (Div. of Rheumatology, Hospital for Sick Children, Toronto, ON (Canada))

1994-06-01

Localized scleroderma is distinct from the diffuse form of scleroderma and does not show Raynaud's phenomenon and visceral involvement. The imaging features in 23 patients ranging from 2 to 17 years of age (mean 11.1 years) were reviewed. Leg length discrepancy and muscle atrophy were the most common findings (five patients), with two patients also showing modelling deformity of the fibula. One patient with lower extremity involvement showed abnormal bone marrow signals on MR. Disabling joint contracture requiring orthopedic intervention was noted in one patient. In two patients with ''en coup de sabre'' facial deformity, CT and MR scans revealed intracranial calcifications and white matter abnormality in the ipsilateral frontal lobes, with one also showing migrational abnormality. In a third patient, CT revealed white matter abnormality in the ipsilateral parietal lobe. In one patient with progressive facial hemiatrophy, CT and MR scans showed the underlying hypoplastic left maxillary antrum and cheek. Imaging studies of areas of clinical concern revealed positive findings in half our patients. (orig.)

Automatic brain MR image denoising based on texture feature-based artificial neural networks.

Science.gov (United States)

Chang, Yu-Ning; Chang, Herng-Hua

2015-01-01

Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.

SU-F-R-21: The Stability of Radiomics Features On 4D FDG-PET/CT Images

Energy Technology Data Exchange (ETDEWEB)

Ma, C [Shandong Cancer Hospital and Institute, Jinan, Shandong (China)

2016-06-15

Purpose: The aim of our study was to perform a stability analysis of 4D PET-derived features in non-small cell lung carcinoma (NSCLC) based on six different respiratory phases. Methods: The 4D FDG-PET/CT respiratory phases were labeled as T0%, T17%, T33%,T50%, T67%, T83% phases, with the T0% phase approximately corresponding to the normal end-inspiration. Lesions were manually delineated based on fused PET-CT, using a standardized clinical delineation protocol. Six texture parameters were analyzed. Results: Results showed that the majority of assessed features had a low stability such as Homogeneity (0.385–0.416), Dissimilarity (3.707–3.861), Angular two moments (0.013–0.019), Contrast (39.782–49.562), Entropy(4.683–5.002) and Inverse differential moment (0.317–0.362) on different respiratory phases. Conclusion: This study suggest that further research of quantitative PET imaging features is warranted with respect to respiratory motion.

Neural network-based feature point descriptors for registration of optical and SAR images

Science.gov (United States)

Abulkhanov, Dmitry; Konovalenko, Ivan; Nikolaev, Dmitry; Savchik, Alexey; Shvets, Evgeny; Sidorchuk, Dmitry

2018-04-01

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells.

Directory of Open Access Journals (Sweden)

Fumiko Matsuoka

Full Text Available Human bone marrow mesenchymal stem cells (hBMSCs are widely used cell source for clinical bone regeneration. Achieving the greatest therapeutic effect is dependent on the osteogenic differentiation potential of the stem cells to be implanted. However, there are still no practical methods to characterize such potential non-invasively or previously. Monitoring cellular morphology is a practical and non-invasive approach for evaluating osteogenic potential. Unfortunately, such image-based approaches had been historically qualitative and requiring experienced interpretation. By combining the non-invasive attributes of microscopy with the latest technology allowing higher throughput and quantitative imaging metrics, we studied the applicability of morphometric features to quantitatively predict cellular osteogenic potential. We applied computational machine learning, combining cell morphology features with their corresponding biochemical osteogenic assay results, to develop prediction model of osteogenic differentiation. Using a dataset of 9,990 images automatically acquired by BioStation CT during osteogenic differentiation culture of hBMSCs, 666 morphometric features were extracted as parameters. Two commonly used osteogenic markers, alkaline phosphatase (ALP activity and calcium deposition were measured experimentally, and used as the true biological differentiation status to validate the prediction accuracy. Using time-course morphological features throughout differentiation culture, the prediction results highly correlated with the experimentally defined differentiation marker values (R>0.89 for both marker predictions. The clinical applicability of our morphology-based prediction was further examined with two scenarios: one using only historical cell images and the other using both historical images together with the patient's own cell images to predict a new patient's cellular potential. The prediction accuracy was found to be greatly enhanced

WE-G-207-05: Relationship Between CT Image Quality, Segmentation Performance, and Quantitative Image Feature Analysis

Energy Technology Data Exchange (ETDEWEB)

Lee, J; Nishikawa, R [University of Pittsburgh, Pittsburgh, PA (United States); Reiser, I [The University of Chicago, Chicago, IL (United States); Boone, J [UC Davis Medical Center, Sacramento, CA (United States)

2015-06-15

Purpose: Segmentation quality can affect quantitative image feature analysis. The objective of this study is to examine the relationship between computed tomography (CT) image quality, segmentation performance, and quantitative image feature analysis. Methods: A total of 90 pathology proven breast lesions in 87 dedicated breast CT images were considered. An iterative image reconstruction (IIR) algorithm was used to obtain CT images with different quality. With different combinations of 4 variables in the algorithm, this study obtained a total of 28 different qualities of CT images. Two imaging tasks/objectives were considered: 1) segmentation and 2) classification of the lesion as benign or malignant. Twenty-three image features were extracted after segmentation using a semi-automated algorithm and 5 of them were selected via a feature selection technique. Logistic regression was trained and tested using leave-one-out-cross-validation and its area under the ROC curve (AUC) was recorded. The standard deviation of a homogeneous portion and the gradient of a parenchymal portion of an example breast were used as an estimate of image noise and sharpness. The DICE coefficient was computed using a radiologist’s drawing on the lesion. Mean DICE and AUC were used as performance metrics for each of the 28 reconstructions. The relationship between segmentation and classification performance under different reconstructions were compared. Distributions (median, 95% confidence interval) of DICE and AUC for each reconstruction were also compared. Results: Moderate correlation (Pearson’s rho = 0.43, p-value = 0.02) between DICE and AUC values was found. However, the variation between DICE and AUC values for each reconstruction increased as the image sharpness increased. There was a combination of IIR parameters that resulted in the best segmentation with the worst classification performance. Conclusion: There are certain images that yield better segmentation or classification

Image features for misalignment correction in medical flat-detector CT

International Nuclear Information System (INIS)

Wicklein, Julia; Kunze, Holger; Kalender, Willi A.; Kyriakou, Yiannis

2012-01-01

Purpose: Misalignment artifacts are a serious problem in medical flat-detector computed tomography. Generally, the geometrical parameters, which are essential for reconstruction, are provided by preceding calibration routines. These procedures are time consuming and the later use of stored parameters is sensitive toward external impacts or patient movement. The method of choice in a clinical environment would be a markerless online-calibration procedure that allows flexible scan trajectories and simultaneously corrects misalignment and motion artifacts during the reconstruction process. Therefore, different image features were evaluated according to their capability of quantifying misalignment. Methods: Projections of the FORBILD head and thorax phantoms were simulated. Additionally, acquisitions of a head phantom and patient data were used for evaluation. For the reconstruction different sources and magnitudes of misalignment were introduced in the geometry description. The resulting volumes were analyzed by entropy (based on the gray-level histogram), total variation, Gabor filter texture features, Haralick co-occurrence features, and Tamura texture features. The feature results were compared to the back-projection mismatch of the disturbed geometry. Results: The evaluations demonstrate the ability of several well-established image features to classify misalignment. The authors elaborated the particular suitability of the gray-level histogram-based entropy on identifying misalignment artifacts, after applying an appropriate window level (bone window). Conclusions: Some of the proposed feature extraction algorithms show a strong correlation with the misalignment level. Especially, entropy-based methods showed very good correspondence, with the best of these being the type that uses the gray-level histogram for calculation. This makes it a suitable image feature for online-calibration.

The algorithm of fast image stitching based on multi-feature extraction

Science.gov (United States)

Yang, Chunde; Wu, Ge; Shi, Jing

2018-05-01

This paper proposed an improved image registration method combining Hu-based invariant moment contour information and feature points detection, aiming to solve the problems in traditional image stitching algorithm, such as time-consuming feature points extraction process, redundant invalid information overload and inefficiency. First, use the neighborhood of pixels to extract the contour information, employing the Hu invariant moment as similarity measure to extract SIFT feature points in those similar regions. Then replace the Euclidean distance with Hellinger kernel function to improve the initial matching efficiency and get less mismatching points, further, estimate affine transformation matrix between the images. Finally, local color mapping method is adopted to solve uneven exposure, using the improved multiresolution fusion algorithm to fuse the mosaic images and realize seamless stitching. Experimental results confirm high accuracy and efficiency of method proposed in this paper.

Improved Feature Detection in Fused Intensity-Range Images with Complex SIFT (ℂSIFT

Directory of Open Access Journals (Sweden)

Boris Jutzi

2011-09-01

Full Text Available The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (ℂSIFT detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect.

Wavelet-packet-based texture analysis for differentiation between benign and malignant liver tumours in ultrasound images

International Nuclear Information System (INIS)

Yoshida, Hiroyuki; Casalino, David D; Keserci, Bilgin; Coskun, Abdulhakim; Ozturk, Omer; Savranlar, Ahmet

2003-01-01

The purpose of this study was to apply a novel method of multiscale echo texture analysis for distinguishing benign (hemangiomas) from malignant (hepatocellular carcinomas (HCCs) and metastases) focal liver lesions in B-mode ultrasound images. In this method, regions of interest (ROIs) extracted from within the lesions were decomposed into subimages by wavelet packets. Multiscale texture features that quantify homogeneity of the echogenicity were calculated from these subimages and were combined by an artificial neural network (ANN). A subset of the multiscale features was selected that yielded the highest performance in the classification of lesions measured by the area under the receiver operating characteristic curve (A z ). In an analysis of 193 ROIs consisting of 50 hemangiomas, 87 hepatocellular carcinomas and 56 metastases, the multiscale features yielded a high A z value of 0.92 in distinguishing benign from malignant lesions, 0.93 in distinguishing hemangiomas from HCCs and 0.94 in distinguishing hemangiomas from metastases. Our new multiscale texture analysis method can effectively differentiate malignant from benign lesions, and thus has the potential to increase the accuracy of diagnosis of focal liver lesions in ultrasound images

Imaging features of foot osteoid osteoma

Energy Technology Data Exchange (ETDEWEB)

Shukla, Satyen; Clarke, Andrew W.; Saifuddin, Asif [Royal National Orthopaedic Hospital NHS Trust, Department of Radiology, Stanmore, Middlesex (United Kingdom)

2010-07-15

We performed a retrospective review of the imaging of nine patients with a diagnosis of foot osteoid osteoma (OO). Radiographs, computed tomography (CT) and magnetic resonance imaging (MRI) had been performed in all patients. Radiographic features evaluated were the identification of a nidus and cortical thickening. CT features noted were nidus location (affected bone - intramedullary, intracortical, subarticular) and nidus calcification. MRI features noted were the presence of an identifiable nidus, presence and grade of bone oedema and whether a joint effusion was identified. Of the nine patients, three were female and six male, with a mean age of 21 years (range 11-39 years). Classical symptoms of OO (night pain, relief with aspirin) were identified in five of eight (62.5%) cases (in one case, the medical records could not be retrieved). In five patients the lesion was located in the hindfoot (four calcaneus, one talus), while four were in the mid- or forefoot (two metatarsal and two phalangeal). Radiographs were normal in all patients with hindfoot OO. CT identified the nidus in all cases (89%) except one terminal phalanx lesion, while MRI demonstrated a nidus in six of nine cases (67%). The nidus was of predominantly intermediate signal intensity on T1-weighted (T1W) sequences, with intermediate to high signal intensity on T2-weighted (T2W) sequences. High-grade bone marrow oedema, limited to the affected bone and adjacent soft tissue oedema was identified in all cases. In a young patient with chronic hindfoot pain and a normal radiograph, MRI features suggestive of possible OO include extensive bone marrow oedema limited to one bone, with a possible nidus demonstrated in two-thirds of cases. The presence or absence of a nidus should be confirmed with high-resolution CT. (orig.)

Oriented Edge-Based Feature Descriptor for Multi-Sensor Image Alignment and Enhancement

Directory of Open Access Journals (Sweden)

Myung-Ho Ju

2013-10-01

Full Text Available In this paper, we present an efficient image alignment and enhancement method for multi-sensor images. The shape of the object captured in a multi-sensor images can be determined by comparing variability of contrast using corresponding edges across multi-sensor image. Using this cue, we construct a robust feature descriptor based on the magnitudes of the oriented edges. Our proposed method enables fast image alignment by identifying matching features in multi-sensor images. We enhance the aligned multi-sensor images through the fusion of the salient regions from each image. The results of stitching the multi-sensor images and their enhancement demonstrate that our proposed method can align and enhance multi-sensor images more efficiently than previous methods.

Automatic detection of diabetic retinopathy features in ultra-wide field retinal images

Science.gov (United States)

Levenkova, Anastasia; Sowmya, Arcot; Kalloniatis, Michael; Ly, Angelica; Ho, Arthur

2017-03-01

Diabetic retinopathy (DR) is a major cause of irreversible vision loss. DR screening relies on retinal clinical signs (features). Opportunities for computer-aided DR feature detection have emerged with the development of Ultra-WideField (UWF) digital scanning laser technology. UWF imaging covers 82% greater retinal area (200°), against 45° in conventional cameras3 , allowing more clinically relevant retinopathy to be detected4 . UWF images also provide a high resolution of 3078 x 2702 pixels. Currently DR screening uses 7 overlapping conventional fundus images, and the UWF images provide similar results1,4. However, in 40% of cases, more retinopathy was found outside the 7-field ETDRS) fields by UWF and in 10% of cases, retinopathy was reclassified as more severe4 . This is because UWF imaging allows examination of both the central retina and more peripheral regions, with the latter implicated in DR6 . We have developed an algorithm for automatic recognition of DR features, including bright (cotton wool spots and exudates) and dark lesions (microaneurysms and blot, dot and flame haemorrhages) in UWF images. The algorithm extracts features from grayscale (green "red-free" laser light) and colour-composite UWF images, including intensity, Histogram-of-Gradient and Local binary patterns. Pixel-based classification is performed with three different classifiers. The main contribution is the automatic detection of DR features in the peripheral retina. The method is evaluated by leave-one-out cross-validation on 25 UWF retinal images with 167 bright lesions, and 61 other images with 1089 dark lesions. The SVM classifier performs best with AUC of 94.4% / 95.31% for bright / dark lesions.

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

OpenAIRE

Gupta, Saurabh; Girshick, Ross; Arbeláez, Pablo; Malik, Jitendra

2014-01-01

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity. We demonstrate that this geocentric embedding works better than using raw depth images for learning feature representations with convolutional neural networks. Our final object detection system achieves an av...

Barrett's esophagus: clinical features, obesity, and imaging.

LENUS (Irish Health Repository)

Quigley, Eamonn M M

2011-09-01

The following includes commentaries on clinical features and imaging of Barrett\\'s esophagus (BE); the clinical factors that influence the development of BE; the influence of body fat distribution and central obesity; the role of adipocytokines and proinflammatory markers in carcinogenesis; the role of body mass index (BMI) in healing of Barrett\\'s epithelium; the role of surgery in prevention of carcinogenesis in BE; the importance of double-contrast esophagography and cross-sectional images of the esophagus; and the value of positron emission tomography\\/computed tomography.

Tissue feature-based intra-fractional motion tracking for stereoscopic x-ray image guided radiotherapy

Science.gov (United States)

Xie, Yaoqin; Xing, Lei; Gu, Jia; Liu, Wu

2013-06-01

Real-time knowledge of tumor position during radiation therapy is essential to overcome the adverse effect of intra-fractional organ motion. The goal of this work is to develop a tumor tracking strategy by effectively utilizing the inherent image features of stereoscopic x-ray images acquired during dose delivery. In stereoscopic x-ray image guided radiation delivery, two orthogonal x-ray images are acquired either simultaneously or sequentially. The essence of markerless tumor tracking is the reliable identification of inherent points with distinct tissue features on each projection image and their association between two images. The identification of the feature points on a planar x-ray image is realized by searching for points with high intensity gradient. The feature points are associated by using the scale invariance features transform descriptor. The performance of the proposed technique is evaluated by using images of a motion phantom and four archived clinical cases acquired using either a CyberKnife equipped with a stereoscopic x-ray imaging system, or a LINAC equipped with an onboard kV imager and an electronic portal imaging device. In the phantom study, the results obtained using the proposed method agree with the measurements to within 2 mm in all three directions. In the clinical study, the mean error is 0.48 ± 0.46 mm for four patient data with 144 sequential images. In this work, a tissue feature-based tracking method for stereoscopic x-ray image guided radiation therapy is developed. The technique avoids the invasive procedure of fiducial implantation and may greatly facilitate the clinical workflow.

Tissue feature-based intra-fractional motion tracking for stereoscopic x-ray image guided radiotherapy

International Nuclear Information System (INIS)

Xie Yaoqin; Gu Jia; Xing Lei; Liu Wu

2013-01-01

Real-time knowledge of tumor position during radiation therapy is essential to overcome the adverse effect of intra-fractional organ motion. The goal of this work is to develop a tumor tracking strategy by effectively utilizing the inherent image features of stereoscopic x-ray images acquired during dose delivery. In stereoscopic x-ray image guided radiation delivery, two orthogonal x-ray images are acquired either simultaneously or sequentially. The essence of markerless tumor tracking is the reliable identification of inherent points with distinct tissue features on each projection image and their association between two images. The identification of the feature points on a planar x-ray image is realized by searching for points with high intensity gradient. The feature points are associated by using the scale invariance features transform descriptor. The performance of the proposed technique is evaluated by using images of a motion phantom and four archived clinical cases acquired using either a CyberKnife equipped with a stereoscopic x-ray imaging system, or a LINAC equipped with an onboard kV imager and an electronic portal imaging device. In the phantom study, the results obtained using the proposed method agree with the measurements to within 2 mm in all three directions. In the clinical study, the mean error is 0.48 ± 0.46 mm for four patient data with 144 sequential images. In this work, a tissue feature-based tracking method for stereoscopic x-ray image guided radiation therapy is developed. The technique avoids the invasive procedure of fiducial implantation and may greatly facilitate the clinical workflow. (paper)

RESEARCH ON FOREST FLAME RECOGNITION ALGORITHM BASED ON IMAGE FEATURE

Directory of Open Access Journals (Sweden)

Z. Wang

2017-09-01

Full Text Available In recent years, fire recognition based on image features has become a hotspot in fire monitoring. However, due to the complexity of forest environment, the accuracy of forest fireworks recognition based on image features is low. Based on this, this paper proposes a feature extraction algorithm based on YCrCb color space and K-means clustering. Firstly, the paper prepares and analyzes the color characteristics of a large number of forest fire image samples. Using the K-means clustering algorithm, the forest flame model is obtained by comparing the two commonly used color spaces, and the suspected flame area is discriminated and extracted. The experimental results show that the extraction accuracy of flame area based on YCrCb color model is higher than that of HSI color model, which can be applied in different scene forest fire identification, and it is feasible in practice.

Color Texture Image Retrieval Based on Local Extrema Features and Riemannian Distance

Directory of Open Access Journals (Sweden)

Minh-Tan Pham

2017-10-01

Full Text Available A novel efficient method for content-based image retrieval (CBIR is developed in this paper using both texture and color features. Our motivation is to represent and characterize an input image by a set of local descriptors extracted from characteristic points (i.e., keypoints within the image. Then, dissimilarity measure between images is calculated based on the geometric distance between the topological feature spaces (i.e., manifolds formed by the sets of local descriptors generated from each image of the database. In this work, we propose to extract and use the local extrema pixels as our feature points. Then, the so-called local extrema-based descriptor (LED is generated for each keypoint by integrating all color, spatial as well as gradient information captured by its nearest local extrema. Hence, each image is encoded by an LED feature point cloud and Riemannian distances between these point clouds enable us to tackle CBIR. Experiments performed on several color texture databases including Vistex, STex, color Brodazt, USPtex and Outex TC-00013 using the proposed approach provide very efficient and competitive results compared to the state-of-the-art methods.

Adaptive differential correspondence imaging based on sorting technique

Directory of Open Access Journals (Sweden)

Heng Wu

2017-04-01

Full Text Available We develop an adaptive differential correspondence imaging (CI method using a sorting technique. Different from the conventional CI schemes, the bucket detector signals (BDS are first processed by a differential technique, and then sorted in a descending (or ascending order. Subsequently, according to the front and last several frames of the sorted BDS, the positive and negative subsets (PNS are created by selecting the relative frames from the reference detector signals. Finally, the object image is recovered from the PNS. Besides, an adaptive method based on two-step iteration is designed to select the optimum number of frames. To verify the proposed method, a single-detector computational ghost imaging (GI setup is constructed. We experimentally and numerically compare the performance of the proposed method with different GI algorithms. The results show that our method can improve the reconstruction quality and reduce the computation cost by using fewer measurement data.

An improved high order texture features extraction method with application to pathological diagnosis of colon lesions for CT colonography

Science.gov (United States)

Song, Bowen; Zhang, Guopeng; Lu, Hongbing; Wang, Huafeng; Han, Fangfang; Zhu, Wei; Liang, Zhengrong

2014-03-01

Differentiation of colon lesions according to underlying pathology, e.g., neoplastic and non-neoplastic, is of fundamental importance for patient management. Image intensity based textural features have been recognized as a useful biomarker for the differentiation task. In this paper, we introduce high order texture features, beyond the intensity, such as gradient and curvature, for that task. Based on the Haralick texture analysis method, we introduce a virtual pathological method to explore the utility of texture features from high order differentiations, i.e., gradient and curvature, of the image intensity distribution. The texture features were validated on database consisting of 148 colon lesions, of which 35 are non-neoplastic lesions, using the random forest classifier and the merit of area under the curve (AUC) of the receiver operating characteristics. The results show that after applying the high order features, the AUC was improved from 0.8069 to 0.8544 in differentiating non-neoplastic lesion from neoplastic ones, e.g., hyperplastic polyps from tubular adenomas, tubulovillous adenomas and adenocarcinomas. The experimental results demonstrated that texture features from the higher order images can significantly improve the classification accuracy in pathological differentiation of colorectal lesions. The gain in differentiation capability shall increase the potential of computed tomography (CT) colonography for colorectal cancer screening by not only detecting polyps but also classifying them from optimal polyp management for the best outcome in personalized medicine.

Multi-example feature-constrained back-projection method for image super-resolution

Institute of Scientific and Technical Information of China (English)

Junlei Zhang; Dianguang Gai; Xin Zhang; Xuemei Li

2017-01-01

Example-based super-resolution algorithms,which predict unknown high-resolution image information using a relationship model learnt from known high- and low-resolution image pairs, have attracted considerable interest in the field of image processing. In this paper, we propose a multi-example feature-constrained back-projection method for image super-resolution. Firstly, we take advantage of a feature-constrained polynomial interpolation method to enlarge the low-resolution image. Next, we consider low-frequency images of different resolutions to provide an example pair. Then, we use adaptive k NN search to find similar patches in the low-resolution image for every image patch in the high-resolution low-frequency image, leading to a regression model between similar patches to be learnt. The learnt model is applied to the low-resolution high-frequency image to produce high-resolution high-frequency information. An iterative back-projection algorithm is used as the final step to determine the final high-resolution image.Experimental results demonstrate that our method improves the visual quality of the high-resolution image.

Improved medical image modality classification using a combination of visual and textual features.

Science.gov (United States)

Dimitrovski, Ivica; Kocev, Dragi; Kitanovski, Ivan; Loskovska, Suzana; Džeroski, Sašo

2015-01-01

In this paper, we present the approach that we applied to the medical modality classification tasks at the ImageCLEF evaluation forum. More specifically, we used the modality classification databases from the ImageCLEF competitions in 2011, 2012 and 2013, described by four visual and one textual types of features, and combinations thereof. We used local binary patterns, color and edge directivity descriptors, fuzzy color and texture histogram and scale-invariant feature transform (and its variant opponentSIFT) as visual features and the standard bag-of-words textual representation coupled with TF-IDF weighting. The results from the extensive experimental evaluation identify the SIFT and opponentSIFT features as the best performing features for modality classification. Next, the low-level fusion of the visual features improves the predictive performance of the classifiers. This is because the different features are able to capture different aspects of an image, their combination offering a more complete representation of the visual content in an image. Moreover, adding textual features further increases the predictive performance. Finally, the results obtained with our approach are the best results reported on these databases so far. Copyright © 2014 Elsevier Ltd. All rights reserved.

Experimental differentiation of intraocular masses using ultrahigh-field magnetic resonance imaging--a case series.

Directory of Open Access Journals (Sweden)

Karen Falke

Full Text Available PURPOSE: The case reports presented here were compiled to demonstrate the potential for improved diagnosis and monitoring of disease progress of intraocular lesions using ultrahigh-field magnetic resonance microscopy (MRM at 7.1 Tesla. METHODS: High-resolution ex vivo ocular magnetic resonance (MR images were acquired on an ultrahigh-field MR system (7.1 Tesla, ClinScan, Bruker BioScan, Germany using a 2-channel coil with 4 coil elements and T2-weighted turbo spin echo (TSE sequences of human eyes enucleated because of different intraocular lesions. Imaging parameters were: 40×40 mm field of view, 512×512 matrix, and 700 µm slice thickness. The results were correlated with in vivo ultrasound and histology of the enucleated eyes. RESULTS: Imaging was performed in enucleated eyes with choroidal melanoma, malignant melanoma of iris and ciliary body with scleral perforation, ciliary body melanoma, intraocular metastasis of esophageal cancer, subretinal bleeding in the presence of perforated corneal ulcer, hemorrhagic choroidal detachment, and premature retinopathy with phthisis and ossification of bulbar structures. MR imaging allowed differentiation between solid and cystic tumor components. In case of hemorrhage, fluid-fluid levels were identified. Melanin and calcifications caused significant hypointensity. Microstructural features of eye lesions identified by MRM were confirmed by histology. CONCLUSION: This study demonstrates the potential of MRM for the visualization and differential diagnosis of intraocular lesions. At present, the narrow bore of the magnet still limits the use of this technology in humans in vivo. Further advances in ultrahigh-field MR imaging will permit visualization of tumor extent and evaluation of nonclassified intraocular structures in the near future.

Imaging features of multicentric Castleman's disease in HIV infection

International Nuclear Information System (INIS)

Hillier, J.C.; Shaw, P.; Miller, R.F.; Cartledge, J.D.; Nelson, M.; Bower, M.; Francis, N.; Padley, S.P.

2004-01-01

AIM: To describe the computed tomography (CT) features of human immunodeficiency virus (HIV)-associated Castleman's disease. MATERIALS AND METHODS: Nine HIV-positive patients with biopsy-proven Castleman's disease were studied. Clinical and demographic data, CD4 count, histological diagnosis and human herpes type 8 (HHV8) serology or immunostaining results were recorded. CT images were reviewed independently by two radiologists. RESULTS: CT findings included splenomegaly (n=7) and peripheral lymph node enlargement (axillary n=8, inguinal n=4). All nodes displayed mild to avid enhancement after intravenous administration of contrast material. Hepatomegaly was evident in seven patients. Other features included abdominal (n=6) and mediastinal (n=5) lymph node enlargement and pulmonary abnormalities (n=4). Patterns of parenchymal abnormality included bronchovascular nodularity (n=2), consolidation (n=1) and pleural effusion (n=2). On histological examination eight patients (spleen n=3, lymph node n=9, lung n=1 bone marrow n=1) had the plasma cell variant and one had mixed hyaline-vascular/plasma cell variant. The majority had either positive immunostaining for HHV8 or positive serology (n=8). CONCLUSION: Common imaging features of multicentric Castleman's disease in HIV infection are hepatosplenomegaly and peripheral lymph node enlargement. Although these imaging features may suggest the diagnosis in the appropriate clinical context, they lack specificity and so biopsy is needed for diagnosis. In distinction from multicentric Castleman's disease in other populations the plasma cell variant is most commonly encountered, splenomegaly is a universal feature and there is a strong association with Kaposi's sarcoma

Adaptive Colour Feature Identification in Image for Object Tracking

Directory of Open Access Journals (Sweden)

Feng Su

2012-01-01

Full Text Available Identification and tracking of a moving object using computer vision techniques is important in robotic surveillance. In this paper, an adaptive colour filtering method is introduced for identifying and tracking a moving object appearing in image sequences. This filter is capable of automatically identifying the most salient colour feature of the moving object in the image and using this for a robot to track the object. The method enables the selected colour feature to adapt to surrounding condition when it is changed. A method of determining the region of interest of the moving target is also developed for the adaptive colour filter to extract colour information. Experimental results show that by using a camera mounted on a robot, the proposed methods can perform robustly in tracking a randomly moving object using adaptively selected colour features in a crowded environment.

Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features.

Science.gov (United States)

Lu, Xiaoqiang; Chen, Yaxiong; Li, Xuelong

Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep

An adaptive clustering algorithm for image matching based on corner feature

Science.gov (United States)

Wang, Zhe; Dong, Min; Mu, Xiaomin; Wang, Song

2018-04-01

The traditional image matching algorithm always can not balance the real-time and accuracy better, to solve the problem, an adaptive clustering algorithm for image matching based on corner feature is proposed in this paper. The method is based on the similarity of the matching pairs of vector pairs, and the adaptive clustering is performed on the matching point pairs. Harris corner detection is carried out first, the feature points of the reference image and the perceived image are extracted, and the feature points of the two images are first matched by Normalized Cross Correlation (NCC) function. Then, using the improved algorithm proposed in this paper, the matching results are clustered to reduce the ineffective operation and improve the matching speed and robustness. Finally, the Random Sample Consensus (RANSAC) algorithm is used to match the matching points after clustering. The experimental results show that the proposed algorithm can effectively eliminate the most wrong matching points while the correct matching points are retained, and improve the accuracy of RANSAC matching, reduce the computation load of whole matching process at the same time.

Difet: Distributed Feature Extraction Tool for High Spatial Resolution Remote Sensing Images

Science.gov (United States)

Eken, S.; Aydın, E.; Sayar, A.

2017-11-01

In this paper, we propose distributed feature extraction tool from high spatial resolution remote sensing images. Tool is based on Apache Hadoop framework and Hadoop Image Processing Interface. Two corner detection (Harris and Shi-Tomasi) algorithms and five feature descriptors (SIFT, SURF, FAST, BRIEF, and ORB) are considered. Robustness of the tool in the task of feature extraction from LandSat-8 imageries are evaluated in terms of horizontal scalability.

Fingerprint image enhancement by differential hysteresis processing.

Science.gov (United States)

Blotta, Eduardo; Moler, Emilce

2004-05-10

A new method to enhance defective fingerprints images through image digital processing tools is presented in this work. When the fingerprints have been taken without any care, blurred and in some cases mostly illegible, as in the case presented here, their classification and comparison becomes nearly impossible. A combination of spatial domain filters, including a technique called differential hysteresis processing (DHP), is applied to improve these kind of images. This set of filtering methods proved to be satisfactory in a wide range of cases by uncovering hidden details that helped to identify persons. Dactyloscopy experts from Policia Federal Argentina and the EAAF have validated these results.

Diffusion-weighted imaging features in spinal cord infarction

International Nuclear Information System (INIS)

Zhang Jingsong; Huan Yi; Sun Lijun; Chang Yingjuan; Zhao Haitao; Yang Chunmin; Zhang Guangyun

2005-01-01

Objective: To analyze the diffusion-weighted MR imaging findings in ischemic spinal cord lesions and discuss the value of diffusion-weighted MR imaging in differentiating diagnosis with inflammatory diseases and tumors. Methods: Six patients (2 male, 4 female) with typical sudden onset of neurological deficits caused by spinal cord ischemia were evaluated. There were no definite etiologies in all patients. DW imaging was performed within 1 to 30 days after the initial neurological symptoms using a Philips Gyroscan 1.5 TMR system. Four patients had other scans including contrast-enhanced MR imaging (CE-MRI) and/or FLAIR scans. Two of them followed up with MR images in three months. All six patients were imaged using a multi-shot, navigator-corrected, echo-planar pulse sequence, and ADC values were calculated in sagittal-oriented plane. Results: MR abnormalities were demonstrated on sagittal T 2 -weighted images with 'patch-like' or 'strip-like' hyperintensities (6/6) and cord enlargement (5/6). Axial T 2 -weighted images showed bilateral (6/6) hyperintensities. In one patient only the posterior spinal artery (PSA) territory was involved. Spinal cord was mainly affected at the cervical (2/6) and thoracolumbar (4/6) region, two of them included the conus medullaris (T10-L1). DW images showed high signals in all infarct lesions, degree of intensity depended on scanning time from ill-onset and progress of illness and whether companied with hemorrhage. In this group, except one case with closely normal ADC value due to one month course of illness, the five others ADC values of lesions calculated from ADC maps arranged from 0.23 x 10 -3 mm 2 /s to 0.47 x 10 -3 mm 2 /s [average value (0.37 ± 0.10) x 10 -3 mm 2 /s], markedly lower than normal parts [ average value (0.89 ± 0.08) x 10 -3 mm 2 /s]. There were marked difference between lesions and normal regions (t=4.71, P 2 W images. Meanwhile, lesions could be displayed much better in DW images than in T 2 W images because

Curvature histogram features for retrieval of images of smooth 3D objects

International Nuclear Information System (INIS)

Zhdanov, I; Scherbakov, O; Potapov, A; Peterson, M

2014-01-01

We consider image features on the base of histograms of oriented gradients (HOG) with addition of contour curvature histogram (HOG-CH), and also compare it with results of known scale-invariant feature transform (SIFT) approach in application to retrieval of images of smooth 3D objects.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition.

Science.gov (United States)

Li, Hong; Wei, Yantao; Li, Luoqing; Chen, C L P

2013-04-01

In this paper, a hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract an effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, which is carried out on the locally linear manifold, can extract the salient feature of image patches and leads to a sparse measure matrix on which maximum pooling is carried out. The maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce computational complexity and to improve the discrimination ability of the LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.

Unusual Features of Extraarticular Skeletal Tuberculosis: New Classification and Differential Diagnosis

International Nuclear Information System (INIS)

Kim, Kun Sang; Park, Soo Soung

1983-01-01

Twenty two cases of extra articular skeletal tuberculosis which showed unusual radiological features are reported and classified into several categories with discussion on the differential diagnosis. Radiological patterns of skeletal tuberculosis is so variable that with any kind of skeletal changes the possibility of the skeletal tuberculosis should not be excluded between of lack of its classical patterns.

Bubble feature extracting based on image processing of coal flotation froth

Energy Technology Data Exchange (ETDEWEB)

Wang, F.; Wang, Y.; Lu, M.; Liu, W. [China University of Mining and Technology, Beijing (China). Dept of Chemical Engineering and Environment

2001-11-01

Using image processing the contrast ratio between the bubble on the surface of flotation froth and the image background was enhanced, and the edges of bubble were extracted. Thus a model about the relation between the statistic feature of the bubbles in the image and the cleaned coal can be established. It is feasible to extract the bubble by processing the froth image of coal flotation on the basis of analysing the shape of the bubble. By means of processing the 51 group images sampled from laboratory column, it is thought that the use of the histogram equalization of image gradation and the medium filtering can obviously improve the dynamic contrast range and the brightness of bubbles. Finally, the method of threshold value cut and the bubble edge detecting for extracting the bubble were also discussed to describe the bubble feature, such as size and shape, in the froth image and to distinguish the froth image of coal flotation. 6 refs., 3 figs.

Imaging features of maxillary osteoblastoma and its malignant transformation

International Nuclear Information System (INIS)

Ueno, Hiroshi; Ariji, Ei-ichiro; Tanaka, Takemasa; Kanda, Shigenobu; Mori, Shin-ichiro; Goto, Masaaki; Mizuno, Akio; Okabe, Haruo; Nakamura, Takashi

1994-01-01

We report two cases of osteoblastoma, one of them an unusual case in a 32-year-old woman in whom a maxillary tumor was confidently diagnosed as an osteoblastoma at the time of primary excision and subsequently transformed into an osteosarcoma 7 years after the onset of clinical symptoms. The other patient developed osteosarcoma arising in the maxilla, which was diagnosed 3 years after the primary excision and is very suggestive of malignant transformation in osteoblastoma. We present the radiological features, including computed tomographic and magnetic resonance imaging studies, of this unusual event of transformed tumor and compare imaging features of benign and dedifferentiated counterparts of this rare tumor complex. (orig.)

An efficient fractal image coding algorithm using unified feature and DCT

International Nuclear Information System (INIS)

Zhou Yiming; Zhang Chao; Zhang Zengke

2009-01-01

Fractal image compression is a promising technique to improve the efficiency of image storage and image transmission with high compression ratio, however, the huge time consumption for the fractal image coding is a great obstacle to the practical applications. In order to improve the fractal image coding, efficient fractal image coding algorithms using a special unified feature and a DCT coder are proposed in this paper. Firstly, based on a necessary condition to the best matching search rule during fractal image coding, the fast algorithm using a special unified feature (UFC) is addressed, and it can reduce the search space obviously and exclude most inappropriate matching subblocks before the best matching search. Secondly, on the basis of UFC algorithm, in order to improve the quality of the reconstructed image, a DCT coder is combined to construct a hybrid fractal image algorithm (DUFC). Experimental results show that the proposed algorithms can obtain good quality of the reconstructed images and need much less time than the baseline fractal coding algorithm.

SAR Data Fusion Imaging Method Oriented to Target Feature Extraction

Directory of Open Access Journals (Sweden)

Yang Wei

2015-02-01

Full Text Available To deal with the difficulty for target outlines extracting precisely due to neglect of target scattering characteristic variation during the processing of high-resolution space-borne SAR data, a novel fusion imaging method is proposed oriented to target feature extraction. Firstly, several important aspects that affect target feature extraction and SAR image quality are analyzed, including curved orbit, stop-and-go approximation, atmospheric delay, and high-order residual phase error. Furthermore, the corresponding compensation methods are addressed as well. Based on the analysis, the mathematical model of SAR echo combined with target space-time spectrum is established for explaining the space-time-frequency change rule of target scattering characteristic. Moreover, a fusion imaging strategy and method under high-resolution and ultra-large observation angle range conditions are put forward to improve SAR quality by fusion processing in range-doppler and image domain. Finally, simulations based on typical military targets are used to verify the effectiveness of the fusion imaging method.

DIFET: DISTRIBUTED FEATURE EXTRACTION TOOL FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGES

Directory of Open Access Journals (Sweden)

S. Eken

2017-11-01

Full Text Available In this paper, we propose distributed feature extraction tool from high spatial resolution remote sensing images. Tool is based on Apache Hadoop framework and Hadoop Image Processing Interface. Two corner detection (Harris and Shi-Tomasi algorithms and five feature descriptors (SIFT, SURF, FAST, BRIEF, and ORB are considered. Robustness of the tool in the task of feature extraction from LandSat-8 imageries are evaluated in terms of horizontal scalability.

Research on Remote Sensing Image Classification Based on Feature Level Fusion

Science.gov (United States)

Yuan, L.; Zhu, G.

2018-04-01

Remote sensing image classification, as an important direction of remote sensing image processing and application, has been widely studied. However, in the process of existing classification algorithms, there still exists the phenomenon of misclassification and missing points, which leads to the final classification accuracy is not high. In this paper, we selected Sentinel-1A and Landsat8 OLI images as data sources, and propose a classification method based on feature level fusion. Compare three kind of feature level fusion algorithms (i.e., Gram-Schmidt spectral sharpening, Principal Component Analysis transform and Brovey transform), and then select the best fused image for the classification experimental. In the classification process, we choose four kinds of image classification algorithms (i.e. Minimum distance, Mahalanobis distance, Support Vector Machine and ISODATA) to do contrast experiment. We use overall classification precision and Kappa coefficient as the classification accuracy evaluation criteria, and the four classification results of fused image are analysed. The experimental results show that the fusion effect of Gram-Schmidt spectral sharpening is better than other methods. In four kinds of classification algorithms, the fused image has the best applicability to Support Vector Machine classification, the overall classification precision is 94.01 % and the Kappa coefficients is 0.91. The fused image with Sentinel-1A and Landsat8 OLI is not only have more spatial information and spectral texture characteristics, but also enhances the distinguishing features of the images. The proposed method is beneficial to improve the accuracy and stability of remote sensing image classification.

Research of image retrieval technology based on color feature

Science.gov (United States)

Fu, Yanjun; Jiang, Guangyu; Chen, Fengying

2009-10-01

Recently, with the development of the communication and the computer technology and the improvement of the storage technology and the capability of the digital image equipment, more and more image resources are given to us than ever. And thus the solution of how to locate the proper image quickly and accurately is wanted.The early method is to set up a key word for searching in the database, but now the method has become very difficult when we search much more picture that we need. In order to overcome the limitation of the traditional searching method, content based image retrieval technology was aroused. Now, it is a hot research subject.Color image retrieval is the important part of it. Color is the most important feature for color image retrieval. Three key questions on how to make use of the color characteristic are discussed in the paper: the expression of color, the abstraction of color characteristic and the measurement of likeness based on color. On the basis, the extraction technology of the color histogram characteristic is especially discussed. Considering the advantages and disadvantages of the overall histogram and the partition histogram, a new method based the partition-overall histogram is proposed. The basic thought of it is to divide the image space according to a certain strategy, and then calculate color histogram of each block as the color feature of this block. Users choose the blocks that contain important space information, confirming the right value. The system calculates the distance between the corresponding blocks that users choosed. Other blocks merge into part overall histograms again, and the distance should be calculated. Then accumulate all the distance as the real distance between two pictures. The partition-overall histogram comprehensive utilizes advantages of two methods above, by choosing blocks makes the feature contain more spatial information which can improve performance; the distances between partition-overall histogram

Illumination invariant feature point matching for high-resolution planetary remote sensing images

Science.gov (United States)

Wu, Bo; Zeng, Hai; Hu, Han

2018-03-01

Despite its success with regular close-range and remote-sensing images, the scale-invariant feature transform (SIFT) algorithm is essentially not invariant to illumination differences due to the use of gradients for feature description. In planetary remote sensing imagery, which normally lacks sufficient textural information, salient regions are generally triggered by the shadow effects of keypoints, reducing the matching performance of classical SIFT. Based on the observation of dual peaks in a histogram of the dominant orientations of SIFT keypoints, this paper proposes an illumination-invariant SIFT matching method for high-resolution planetary remote sensing images. First, as the peaks in the orientation histogram are generally aligned closely with the sub-solar azimuth angle at the time of image collection, an adaptive suppression Gaussian function is tuned to level the histogram and thereby alleviate the differences in illumination caused by a changing solar angle. Next, the suppression function is incorporated into the original SIFT procedure for obtaining feature descriptors, which are used for initial image matching. Finally, as the distribution of feature descriptors changes after anisotropic suppression, and the ratio check used for matching and outlier removal in classical SIFT may produce inferior results, this paper proposes an improved matching procedure based on cross-checking and template image matching. The experimental results for several high-resolution remote sensing images from both the Moon and Mars, with illumination differences of 20°-180°, reveal that the proposed method retrieves about 40%-60% more matches than the classical SIFT method. The proposed method is of significance for matching or co-registration of planetary remote sensing images for their synergistic use in various applications. It also has the potential to be useful for flyby and rover images by integrating with the affine invariant feature detectors.

Diabetic mastopathy: Imaging features and the role of image-guided biopsy in its diagnosis

Energy Technology Data Exchange (ETDEWEB)

Kim, Jong Hyeon; Kim, Eun Kyung; Kim, Min Jung; Moon, Hee Jung; Yoon, Jung Hyun [Dept. of Radiology, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul (Korea, Republic of)

2016-03-15

The goal of this study was to evaluate the imaging features of diabetic mastopathy (DMP) and the role of image-guided biopsy in its diagnosis. Two experienced radiologists retrospectively reviewed the mammographic and sonographic images of 19 pathologically confirmed DMP patients. The techniques and results of the biopsies performed in each patient were also reviewed. Mammograms showed negative findings in 78% of the patients. On ultrasonography (US), 13 lesions were seen as masses and six as non-mass lesions. The US features of the mass lesions were as follows: irregular shape (69%), oval shape (31%), indistinct margin (69%), angular margin (15%), microlobulated margin (8%), well-defined margin (8%), heterogeneous echogenicity (62%), hypoechoic echogenicity (38%), posterior shadowing (92%), parallel orientation (100%), the absence of calcifications (100%), and the absence of vascularity (100%). Based on the US findings, 17 lesions (89%) were classified as Breast Imaging Reporting and Data System category 4 and two (11%) as category 3. US-guided core biopsy was performed in 18 patients, and 10 (56%) were diagnosed with DMP on that basis. An additional vacuum-assisted biopsy was performed in seven patients and all were diagnosed with DMP. The US features of DMP were generally suspicious for malignancy, whereas the mammographic findings were often negative or showed only focal asymmetry. Core biopsy is an adequate method for initial pathological diagnosis. However, since it yields non-diagnostic results in a considerable number of cases, the evaluation of correlations between imaging and pathology plays an important role in the diagnostic process.

Diabetic mastopathy: Imaging features and the role of image-guided biopsy in its diagnosis

International Nuclear Information System (INIS)

Kim, Jong Hyeon; Kim, Eun Kyung; Kim, Min Jung; Moon, Hee Jung; Yoon, Jung Hyun

2016-01-01

The goal of this study was to evaluate the imaging features of diabetic mastopathy (DMP) and the role of image-guided biopsy in its diagnosis. Two experienced radiologists retrospectively reviewed the mammographic and sonographic images of 19 pathologically confirmed DMP patients. The techniques and results of the biopsies performed in each patient were also reviewed. Mammograms showed negative findings in 78% of the patients. On ultrasonography (US), 13 lesions were seen as masses and six as non-mass lesions. The US features of the mass lesions were as follows: irregular shape (69%), oval shape (31%), indistinct margin (69%), angular margin (15%), microlobulated margin (8%), well-defined margin (8%), heterogeneous echogenicity (62%), hypoechoic echogenicity (38%), posterior shadowing (92%), parallel orientation (100%), the absence of calcifications (100%), and the absence of vascularity (100%). Based on the US findings, 17 lesions (89%) were classified as Breast Imaging Reporting and Data System category 4 and two (11%) as category 3. US-guided core biopsy was performed in 18 patients, and 10 (56%) were diagnosed with DMP on that basis. An additional vacuum-assisted biopsy was performed in seven patients and all were diagnosed with DMP. The US features of DMP were generally suspicious for malignancy, whereas the mammographic findings were often negative or showed only focal asymmetry. Core biopsy is an adequate method for initial pathological diagnosis. However, since it yields non-diagnostic results in a considerable number of cases, the evaluation of correlations between imaging and pathology plays an important role in the diagnostic process

TU-F-CAMPUS-J-05: Effect of Uncorrelated Noise Texture On Computed Tomography Quantitative Image Features

International Nuclear Information System (INIS)

Oliver, J; Budzevich, M; Moros, E; Zhang, G; Hunt, D

2015-01-01

Purpose: To investigate the relationship between quantitative image features (i.e. radiomics) and statistical fluctuations (i.e. electronic noise) in clinical Computed Tomography (CT) using the standardized American College of Radiology (ACR) CT accreditation phantom and patient images. Methods: Three levels of uncorrelated Gaussian noise were added to CT images of phantom and patients (20) acquired in static mode and respiratory tracking mode. We calculated the noise-power spectrum (NPS) of the original CT images of the phantom, and of the phantom images with added Gaussian noise with means of 50, 80, and 120 HU. Concurrently, on patient images (original and noise-added images), image features were calculated: 14 shape, 19 intensity (1st order statistics from intensity volume histograms), 18 GLCM features (2nd order statistics from grey level co-occurrence matrices) and 11 RLM features (2nd order statistics from run-length matrices). These features provide the underlying structural information of the images. GLCM (size 128x128) was calculated with a step size of 1 voxel in 13 directions and averaged. RLM feature calculation was performed in 13 directions with grey levels binning into 128 levels. Results: Adding the electronic noise to the images modified the quality of the NPS, shifting the noise from mostly correlated to mostly uncorrelated voxels. The dramatic increase in noise texture did not affect image structure/contours significantly for patient images. However, it did affect the image features and textures significantly as demonstrated by GLCM differences. Conclusion: Image features are sensitive to acquisition factors (simulated by adding uncorrelated Gaussian noise). We speculate that image features will be more difficult to detect in the presence of electronic noise (an uncorrelated noise contributor) or, for that matter, any other highly correlated image noise. This work focuses on the effect of electronic, uncorrelated, noise and future work shall

A Variable Order Fractional Differential-Based Texture Enhancement Algorithm with Application in Medical Imaging.

Directory of Open Access Journals (Sweden)

Qiang Yu

Full Text Available Texture enhancement is one of the most important techniques in digital image processing and plays an essential role in medical imaging since textures discriminate information. Most image texture enhancement techniques use classical integral order differential mask operators or fractional differential mask operators using fixed fractional order. These masks can produce excessive enhancement of low spatial frequency content, insufficient enhancement of large spatial frequency content, and retention of high spatial frequency noise. To improve upon existing approaches of texture enhancement, we derive an improved Variable Order Fractional Centered Difference (VOFCD scheme which dynamically adjusts the fractional differential order instead of fixing it. The new VOFCD technique is based on the second order Riesz fractional differential operator using a Lagrange 3-point interpolation formula, for both grey scale and colour image enhancement. We then use this method to enhance photographs and a set of medical images related to patients with stroke and Parkinson's disease. The experiments show that our improved fractional differential mask has a higher signal to noise ratio value than the other fractional differential mask operators. Based on the corresponding quantitative analysis we conclude that the new method offers a superior texture enhancement over existing methods.

Feature Recognition of Froth Images Based on Energy Distribution Characteristics

Directory of Open Access Journals (Sweden)

WU Yanpeng

2014-09-01

Full Text Available This paper proposes a determining algorithm for froth image features based on the amplitude spectrum energy statistics by applying Fast Fourier Transformation to analyze the energy distribution of various-sized froth. The proposed algorithm has been used to do a froth feature analysis of the froth images from the alumina flotation processing site, and the results show that the consistency rate reaches 98.1 % and the usability rate 94.2 %; with its good robustness and high efficiency, the algorithm is quite suitable for flotation processing state recognition.

Morphologic Features of Magnetic Resonance Imaging as a Surrogate of Capsular Contracture in Breast Cancer Patients With Implant-based Reconstructions.

Science.gov (United States)

Tyagi, Neelam; Sutton, Elizabeth; Hunt, Margie; Zhang, Jing; Oh, Jung Hun; Apte, Aditya; Mechalakos, James; Wilgucki, Molly; Gelb, Emily; Mehrara, Babak; Matros, Evan; Ho, Alice

2017-02-01

Capsular contracture (CC) is a serious complication in patients receiving implant-based reconstruction for breast cancer. Currently, no objective methods are available for assessing CC. The goal of the present study was to identify image-based surrogates of CC using magnetic resonance imaging (MRI). We analyzed a retrospective data set of 50 patients who had undergone both a diagnostic MRI scan and a plastic surgeon's evaluation of the CC score (Baker's score) within a 6-month period after mastectomy and reconstructive surgery. The MRI scans were assessed for morphologic shape features of the implant and histogram features of the pectoralis muscle. The shape features, such as roundness, eccentricity, solidity, extent, and ratio length for the implant, were compared with the Baker score. For the pectoralis muscle, the muscle width and median, skewness, and kurtosis of the intensity were compared with the Baker score. Univariate analysis (UVA) using a Wilcoxon rank-sum test and multivariate analysis with the least absolute shrinkage and selection operator logistic regression was performed to determine significant differences in these features between the patient groups categorized according to their Baker's scores. UVA showed statistically significant differences between grade 1 and grade ≥2 for morphologic shape features and histogram features, except for volume and skewness. Only eccentricity, ratio length, and volume were borderline significant in differentiating grade ≤2 and grade ≥3. Features with Pbreast cancer patients who undergo implant reconstruction. Copyright © 2016 Elsevier Inc. All rights reserved.

Ultrasound speckle reduction based on fractional order differentiation.

Science.gov (United States)

Shao, Dangguo; Zhou, Ting; Liu, Fan; Yi, Sanli; Xiang, Yan; Ma, Lei; Xiong, Xin; He, Jianfeng

2017-07-01

Ultrasound images show a granular pattern of noise known as speckle that diminishes their quality and results in difficulties in diagnosis. To preserve edges and features, this paper proposes a fractional differentiation-based image operator to reduce speckle in ultrasound. An image de-noising model based on fractional partial differential equations with balance relation between k (gradient modulus threshold that controls the conduction) and v (the order of fractional differentiation) was constructed by the effective combination of fractional calculus theory and a partial differential equation, and the numerical algorithm of it was achieved using a fractional differential mask operator. The proposed algorithm has better speckle reduction and structure preservation than the three existing methods [P-M model, the speckle reducing anisotropic diffusion (SRAD) technique, and the detail preserving anisotropic diffusion (DPAD) technique]. And it is significantly faster than bilateral filtering (BF) in producing virtually the same experimental results. Ultrasound phantom testing and in vivo imaging show that the proposed method can improve the quality of an ultrasound image in terms of tissue SNR, CNR, and FOM values.

Tie Points Extraction for SAR Images Based on Differential Constraints

Science.gov (United States)

Xiong, X.; Jin, G.; Xu, Q.; Zhang, H.

2018-04-01

Automatically extracting tie points (TPs) on large-size synthetic aperture radar (SAR) images is still challenging because the efficiency and correct ratio of the image matching need to be improved. This paper proposes an automatic TPs extraction method based on differential constraints for large-size SAR images obtained from approximately parallel tracks, between which the relative geometric distortions are small in azimuth direction and large in range direction. Image pyramids are built firstly, and then corresponding layers of pyramids are matched from the top to the bottom. In the process, the similarity is measured by the normalized cross correlation (NCC) algorithm, which is calculated from a rectangular window with the long side parallel to the azimuth direction. False matches are removed by the differential constrained random sample consensus (DC-RANSAC) algorithm, which appends strong constraints in azimuth direction and weak constraints in range direction. Matching points in the lower pyramid images are predicted with the local bilinear transformation model in range direction. Experiments performed on ENVISAT ASAR and Chinese airborne SAR images validated the efficiency, correct ratio and accuracy of the proposed method.

Differential diagnosis of benign and malignant vertebral compression fractures with MR imaging

International Nuclear Information System (INIS)

Staebler, A.; Krimmel, K.; Seiderer, M.; Gaertner, C.; Fritsch, S.; Raum, W.

1992-01-01

42 patients with known malignancy and vertebral compressions underwent MRI. Sagittal T 1 -weighted spin-echo images pre and post Gd-DTPA, out of phase long TR gradient-echo images (GE) and short T 1 inversion recovery images (STIR) were obtained at 1.0 T. In 39 of 42 cases a correct differentiation between osteoporotic and tumorous vertebral compression fractures was possible by quantification and correlation of SE and GE signal intensities. Gd-DTPA did not improve differential diagnosis, since both tumour infiltration and bone marrow oedema in acute compression fracture showed comparable enhancement. STIR-sequences were most sensitive for pathology but unspecific due to a comparable amount of water in tumour tissue and bone marrow oedema. Susceptibility-induced signal reduction in GE images and morphologic criteria proved to be most reliable for differentiation of benign and tumour-related fractures. (orig./GDG) [de

Edge enhancement and noise suppression for infrared image based on feature analysis

Science.gov (United States)

Jiang, Meng

2018-06-01

Infrared images are often suffering from background noise, blurred edges, few details and low signal-to-noise ratios. To improve infrared image quality, it is essential to suppress noise and enhance edges simultaneously. To realize it in this paper, we propose a novel algorithm based on feature analysis in shearlet domain. Firstly, as one of multi-scale geometric analysis (MGA), we introduce the theory and superiority of shearlet transform. Secondly, after analyzing the defects of traditional thresholding technique to suppress noise, we propose a novel feature extraction distinguishing image structures from noise well and use it to improve the traditional thresholding technique. Thirdly, with computing the correlations between neighboring shearlet coefficients, the feature attribute maps identifying the weak detail and strong edges are completed to improve the generalized unsharped masking (GUM). At last, experiment results with infrared images captured in different scenes demonstrate that the proposed algorithm suppresses noise efficiently and enhances image edges adaptively.

Feature selection from a facial image for distinction of sasang constitution.

Science.gov (United States)

Koo, Imhoi; Kim, Jong Yeol; Kim, Myoung Geun; Kim, Keun Ho

2009-09-01

Recently, oriental medicine has received attention for providing personalized medicine through consideration of the unique nature and constitution of individual patients. With the eventual goal of globalization, the current trend in oriental medicine research is the standardization by adopting western scientific methods, which could represent a scientific revolution. The purpose of this study is to establish methods for finding statistically significant features in a facial image with respect to distinguishing constitution and to show the meaning of those features. From facial photo images, facial elements are analyzed in terms of the distance, angle and the distance ratios, for which there are 1225, 61 250 and 749 700 features, respectively. Due to the very large number of facial features, it is quite difficult to determine truly meaningful features. We suggest a process for the efficient analysis of facial features including the removal of outliers, control for missing data to guarantee data confidence and calculation of statistical significance by applying ANOVA. We show the statistical properties of selected features according to different constitutions using the nine distances, 10 angles and 10 rates of distance features that are finally established. Additionally, the Sasang constitutional meaning of the selected features is shown here.

Image feature extraction based on the camouflage effectiveness evaluation

Science.gov (United States)

Yuan, Xin; Lv, Xuliang; Li, Ling; Wang, Xinzhu; Zhang, Zhi

2018-04-01

The key step of camouflage effectiveness evaluation is how to combine the human visual physiological features, psychological features to select effectively evaluation indexes. Based on the predecessors' camo comprehensive evaluation method, this paper chooses the suitable indexes combining with the image quality awareness, and optimizes those indexes combining with human subjective perception. Thus, it perfects the theory of index extraction.

Apparent diffusion coefficient value of gastric cancer by diffusion-weighted imaging: Correlations with the histological differentiation and Lauren classification

International Nuclear Information System (INIS)

Liu, Song; Guan, Wenxian; Wang, Hao; Pan, Liang; Zhou, Zhuping; Yu, Haiping; Liu, Tian; Yang, Xiaofeng; He, Jian; Zhou, Zhengyang

2014-01-01

Highlights: • Gastric cancers’ ADC values were significantly lower than normal gastric wall. • Gastric adenocarcinomas with different differentiation had different ADC values. • Gastric adenocarcinomas’ ADC values correlated with histologic differentiations. • Gastric cancers’ ADC values correlated with Lauren classifications. • Mean ADC value was better than min ADC value in characterizing gastric cancers. - Abstract: Objective: The purpose of this study was to evaluate the correlations between histological differentiation and Lauren classification of gastric cancer and the apparent diffusion coefficient (ADC) value of diffusion weighted imaging (DWI). Materials and methods: Sixty-nine patients with gastric cancer lesions underwent preoperative magnetic resonance imaging (MRI) (3.0T) and surgical resection. DWI was obtained with a single-shot, echo-planar imaging sequence in the axial plane (b values: 0 and 1000 s/mm 2 ). Mean and minimum ADC values were obtained for each gastric cancer and normal gastric walls by two radiologists, who were blinded to the histological findings. Histological type, degree of differentiation and Lauren classification of each resected specimen were determined by one pathologist. Mean and minimum ADC values of gastric cancers with different histological types, degrees of differentiation and Lauren classifications were compared. Correlations between ADC values and histological differentiation and Lauren classification were analyzed. Results: The mean and minimum ADC values of gastric cancers, as a whole and separately, were significantly lower than those of normal gastric walls (all p values <0.001). There were significant differences in the mean and minimum ADC values among gastric cancers with different histological types, degrees of differentiation and Lauren classifications (p < 0.05). Mean and minimum ADC values correlated significantly (all p < 0.001) with histological differentiation (r = 0.564, 0.578) and Lauren

Thin plate spline feature point matching for organ surfaces in minimally invasive surgery imaging

Science.gov (United States)

Lin, Bingxiong; Sun, Yu; Qian, Xiaoning

2013-03-01

Robust feature point matching for images with large view angle changes in Minimally Invasive Surgery (MIS) is a challenging task due to low texture and specular reflections in these images. This paper presents a new approach that can improve feature matching performance by exploiting the inherent geometric property of the organ surfaces. Recently, intensity based template image tracking using a Thin Plate Spline (TPS) model has been extended for 3D surface tracking with stereo cameras. The intensity based tracking is also used here for 3D reconstruction of internal organ surfaces. To overcome the small displacement requirement of intensity based tracking, feature point correspondences are used for proper initialization of the nonlinear optimization in the intensity based method. Second, we generate simulated images from the reconstructed 3D surfaces under all potential view positions and orientations, and then extract feature points from these simulated images. The obtained feature points are then filtered and re-projected to the common reference image. The descriptors of the feature points under different view angles are stored to ensure that the proposed method can tolerate a large range of view angles. We evaluate the proposed method with silicon phantoms and in vivo images. The experimental results show that our method is much more robust with respect to the view angle changes than other state-of-the-art methods.

Skull base chordoid meningioma: Imaging features and pathology

International Nuclear Information System (INIS)

Soo, Mark Y.S.; Gomes, Lavier; Ng, Thomas; Cruz, Malville Da; Dexter, Mark

2004-01-01

The clinical, imaging and pathological features of a skull base chordoid meningioma (CM) are described. The huge tumour resulted in obstructive hydrocephalus and partial erosion of the clivus such that a chordoma was suspected. The lesion's MRI findings were similar to those of a meningioma. Light microscopic, immunohistochemistry and ultrastructural features were diagnostic of CM. Chordoid meningioma is a rare subtype of meningioma and has a great tendency to recur should surgical resection be incomplete Copyright (2004) Blackwell Publishing Asia Pty Ltd

Estimating perception of scene layout properties from global image features.

Science.gov (United States)

Ross, Michael G; Oliva, Aude

2010-01-08

The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.

Clinical features and differential diagnosis of type 2 diabetes mellitus in children

Directory of Open Access Journals (Sweden)

Tamara Leonidovna Kuraeva

2009-09-01

Full Text Available This review was designed to evaluate prevalence, specific clinical features, and differential diagnosis of type 2 diabetes mellitus (DM2 in childrenand adolescents. Special emphasis is laid on the importance of immunological and molecular-genetic studies for the verification of diagnosis and activecase detection in h groups.

Profiles of US and CT imaging features with a high probability of appendicitis

International Nuclear Information System (INIS)

Randen, A. van; Lameris, W.; Es, H.W. van; Hove, W. ten; Bouma, W.H.; Leeuwen, M.S. van; Keulen, E.M. van; Hulst, V.P.M. van der; Henneman, O.D.; Bossuyt, P.M.; Boermeester, M.A.; Stoker, J.

2010-01-01

To identify and evaluate profiles of US and CT features associated with acute appendicitis. Consecutive patients presenting with acute abdominal pain at the emergency department were invited to participate in this study. All patients underwent US and CT. Imaging features known to be associated with appendicitis, and an imaging diagnosis were prospectively recorded by two independent radiologists. A final diagnosis was assigned after 6 months. Associations between appendiceal imaging features and a final diagnosis of appendicitis were evaluated with logistic regression analysis. Appendicitis was assigned to 284 of 942 evaluated patients (30%). All evaluated features were associated with appendicitis. Imaging profiles were created after multivariable logistic regression analysis. Of 147 patients with a thickened appendix, local transducer tenderness and peri-appendiceal fat infiltration on US, 139 (95%) had appendicitis. On CT, 119 patients in whom the appendix was completely visualised, thickened, with peri-appendiceal fat infiltration and appendiceal enhancement, 114 had a final diagnosis of appendicitis (96%). When at least two of these essential features were present on US or CT, sensitivity was 92% (95% CI 89-96%) and 96% (95% CI 93-98%), respectively. Most patients with appendicitis can be categorised within a few imaging profiles on US and CT. When two of the essential features are present the diagnosis of appendicitis can be made accurately. (orig.)

Profiles of US and CT imaging features with a high probability of appendicitis

Energy Technology Data Exchange (ETDEWEB)

Randen, A. van; Lameris, W. [University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands); University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); Es, H.W. van [St Antonius Hospital, Department of Radiology, Nieuwegein (Netherlands); Hove, W. ten; Bouma, W.H. [Gelre Hospitals, Department of Surgery, Apeldoorn (Netherlands); Leeuwen, M.S. van [University Medical Centre, Department of Radiology, Utrecht (Netherlands); Keulen, E.M. van [Tergooi Hospitals, Department of Radiology, Hilversum (Netherlands); Hulst, V.P.M. van der [Onze Lieve Vrouwe Gasthuis, Department of Radiology, Amsterdam (Netherlands); Henneman, O.D. [Bronovo Hospital, Department of Radiology, The Hague (Netherlands); Bossuyt, P.M. [University of Amsterdam, Department of Clinical Epidemiology, Biostatistics, and Bioinformatics, Academic Medical Center, Amsterdam (Netherlands); Boermeester, M.A. [University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); Stoker, J. [University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands)

2010-07-15

To identify and evaluate profiles of US and CT features associated with acute appendicitis. Consecutive patients presenting with acute abdominal pain at the emergency department were invited to participate in this study. All patients underwent US and CT. Imaging features known to be associated with appendicitis, and an imaging diagnosis were prospectively recorded by two independent radiologists. A final diagnosis was assigned after 6 months. Associations between appendiceal imaging features and a final diagnosis of appendicitis were evaluated with logistic regression analysis. Appendicitis was assigned to 284 of 942 evaluated patients (30%). All evaluated features were associated with appendicitis. Imaging profiles were created after multivariable logistic regression analysis. Of 147 patients with a thickened appendix, local transducer tenderness and peri-appendiceal fat infiltration on US, 139 (95%) had appendicitis. On CT, 119 patients in whom the appendix was completely visualised, thickened, with peri-appendiceal fat infiltration and appendiceal enhancement, 114 had a final diagnosis of appendicitis (96%). When at least two of these essential features were present on US or CT, sensitivity was 92% (95% CI 89-96%) and 96% (95% CI 93-98%), respectively. Most patients with appendicitis can be categorised within a few imaging profiles on US and CT. When two of the essential features are present the diagnosis of appendicitis can be made accurately. (orig.)

Multimodal Image Alignment via Linear Mapping between Feature Modalities.

Science.gov (United States)

Jiang, Yanyun; Zheng, Yuanjie; Hou, Sujuan; Chang, Yuchou; Gee, James

2017-01-01

We propose a novel landmark matching based method for aligning multimodal images, which is accomplished uniquely by resolving a linear mapping between different feature modalities. This linear mapping results in a new measurement on similarity of images captured from different modalities. In addition, our method simultaneously solves this linear mapping and the landmark correspondences by minimizing a convex quadratic function. Our method can estimate complex image relationship between different modalities and nonlinear nonrigid spatial transformations even in the presence of heavy noise, as shown in our experiments carried out by using a variety of image modalities.

Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation

Directory of Open Access Journals (Sweden)

YANG Zhaoxia

2015-07-01

Full Text Available In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification, a novel approach based on the combination of spatial-spectral feature and sparse representation is proposed in this paper. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first d principal components(PCs into a vector representation, followed by a sorting scheme to make the vector invariant to local image rotation. Secondly, we learn the dictionary through a supervised method, and use it to code the features from test samples afterwards. Finally, we embed the resulting sparse feature coding into the support vector machine(SVM for hyperspectral image classification. Experiments using three hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classification methods.

Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models

International Nuclear Information System (INIS)

Khalvati, Farzad; Wong, Alexander; Haider, Masoom A.

2015-01-01

Prostate cancer is the most common form of cancer and the second leading cause of cancer death in North America. Auto-detection of prostate cancer can play a major role in early detection of prostate cancer, which has a significant impact on patient survival rates. While multi-parametric magnetic resonance imaging (MP-MRI) has shown promise in diagnosis of prostate cancer, the existing auto-detection algorithms do not take advantage of abundance of data available in MP-MRI to improve detection accuracy. The goal of this research was to design a radiomics-based auto-detection method for prostate cancer via utilizing MP-MRI data. In this work, we present new MP-MRI texture feature models for radiomics-driven detection of prostate cancer. In addition to commonly used non-invasive imaging sequences in conventional MP-MRI, namely T2-weighted MRI (T2w) and diffusion-weighted imaging (DWI), our proposed MP-MRI texture feature models incorporate computed high-b DWI (CHB-DWI) and a new diffusion imaging modality called correlated diffusion imaging (CDI). Moreover, the proposed texture feature models incorporate features from individual b-value images. A comprehensive set of texture features was calculated for both the conventional MP-MRI and new MP-MRI texture feature models. We performed feature selection analysis for each individual modality and then combined best features from each modality to construct the optimized texture feature models. The performance of the proposed MP-MRI texture feature models was evaluated via leave-one-patient-out cross-validation using a support vector machine (SVM) classifier trained on 40,975 cancerous and healthy tissue samples obtained from real clinical MP-MRI datasets. The proposed MP-MRI texture feature models outperformed the conventional model (i.e., T2w+DWI) with regard to cancer detection accuracy. Comprehensive texture feature models were developed for improved radiomics-driven detection of prostate cancer using MP-MRI. Using a

Feature Tracking for High Speed AFM Imaging of Biopolymers.

Science.gov (United States)

Hartman, Brett; Andersson, Sean B

2018-03-31

The scanning speed of atomic force microscopes continues to advance with some current commercial microscopes achieving on the order of one frame per second and at least one reaching 10 frames per second. Despite the success of these instruments, even higher frame rates are needed with scan ranges larger than are currently achievable. Moreover, there is a significant installed base of slower instruments that would benefit from algorithmic approaches to increasing their frame rate without requiring significant hardware modifications. In this paper, we present an experimental demonstration of high speed scanning on an existing, non-high speed instrument, through the use of a feedback-based, feature-tracking algorithm that reduces imaging time by focusing on features of interest to reduce the total imaging area. Experiments on both circular and square gratings, as well as silicon steps and DNA strands show a reduction in imaging time by a factor of 3-12 over raster scanning, depending on the parameters chosen.

Features and limitations of mobile tablet devices for viewing radiological images.

Science.gov (United States)

Grunert, J H

2015-03-01

Mobile radiological image display systems are becoming increasingly common, necessitating a comparison of the features of these systems, specifically the operating system employed, connection to stationary PACS, data security and rang of image display and image analysis functions. In the fall of 2013, a total of 17 PACS suppliers were surveyed regarding the technical features of 18 mobile radiological image display systems using a standardized questionnaire. The study also examined to what extent the technical specifications of the mobile image display systems satisfy the provisions of the Germany Medical Devices Act as well as the provisions of the German X-ray ordinance (RöV). There are clear differences in terms of how the mobile systems connected to the stationary PACS. Web-based solutions allow the mobile image display systems to function independently of their operating systems. The examined systems differed very little in terms of image display and image analysis functions. Mobile image display systems complement stationary PACS and can be used to view images. The impacts of the new quality assurance guidelines (QS-RL) as well as the upcoming new standard DIN 6868 - 157 on the acceptance testing of mobile image display units for the purpose of image evaluation are discussed. © Georg Thieme Verlag KG Stuttgart · New York.

Image features dependant correlation-weighting function for efficient PRNU based source camera identification.

Science.gov (United States)

Tiwari, Mayank; Gupta, Bhupendra

2018-04-01

For source camera identification (SCI), photo response non-uniformity (PRNU) has been widely used as the fingerprint of the camera. The PRNU is extracted from the image by applying a de-noising filter then taking the difference between the original image and the de-noised image. However, it is observed that intensity-based features and high-frequency details (edges and texture) of the image, effect quality of the extracted PRNU. This effects correlation calculation and creates problems in SCI. For solving this problem, we propose a weighting function based on image features. We have experimentally identified image features (intensity and high-frequency contents) effect on the estimated PRNU, and then develop a weighting function which gives higher weights to image regions which give reliable PRNU and at the same point it gives comparatively less weights to the image regions which do not give reliable PRNU. Experimental results show that the proposed weighting function is able to improve the accuracy of SCI up to a great extent. Copyright © 2018 Elsevier B.V. All rights reserved.

Robust and efficient method for matching features in omnidirectional images

Science.gov (United States)

Zhu, Qinyi; Zhang, Zhijiang; Zeng, Dan

2018-04-01

Binary descriptors have been widely used in many real-time applications due to their efficiency. These descriptors are commonly designed for perspective images but perform poorly on omnidirectional images, which are severely distorted. To address this issue, this paper proposes tangent plane BRIEF (TPBRIEF) and adapted log polar grid-based motion statistics (ALPGMS). TPBRIEF projects keypoints to a unit sphere and applies the fixed test set in BRIEF descriptor on the tangent plane of the unit sphere. The fixed test set is then backprojected onto the original distorted images to construct the distortion invariant descriptor. TPBRIEF directly enables keypoint detecting and feature describing on original distorted images, whereas other approaches correct the distortion through image resampling, which introduces artifacts and adds time cost. With ALPGMS, omnidirectional images are divided into circular arches named adapted log polar grids. Whether a match is true or false is then determined by simply thresholding the match numbers in a grid pair where the two matched points located. Experiments show that TPBRIEF greatly improves the feature matching accuracy and ALPGMS robustly removes wrong matches. Our proposed method outperforms the state-of-the-art methods.

MR imaging features of hemispherical spondylosclerosis

Energy Technology Data Exchange (ETDEWEB)

Vicentini, Joao R.T.; Martinez-Salazar, Edgar L.; Chang, Connie Y.; Bredella, Miriam A.; Rosenthal, Daniel I.; Torriani, Martin [Massachusetts General Hospital and Harvard Medical School, Division of Musculoskeletal Imaging and Intervention, Department of Radiology, Boston, MA (United States)

2017-10-15

Hemispherical spondylosclerosis (HS) is a rare degenerative entity characterized by dome-shaped sclerosis of a single vertebral body that may pose a diagnostic dilemma. The goal of this study was to describe the MR imaging features of HS. We identified spine radiographs and CT examinations of subjects with HS who also had MR imaging for correlation. Two musculoskeletal radiologists independently assessed sclerosis characteristics, presence of endplate erosions, marrow signal intensity, and disk degeneration (Pfirrmann scale). We identified 11 subjects (six males, five females, mean 48 ± 10 years) with radiographic/CT findings of HS. The most commonly affected vertebral body was L4 (6/11; 55%). On MR imaging, variable signal intensity was noted, being most commonly low on T1 (8/11, 73%) and high on fat-suppressed T2-weighted (8/11, 73%) images. In two subjects, diffuse post-contrast enhancement was seen in the lesion. Moderate disk degeneration and endplate bone erosions adjacent to sclerosis were present in all subjects. Erosions of the opposite endplate were present in two subjects (2/11, 18%). CT data from nine subjects showed the mean attenuation value of HS was 472 ± 96 HU. HS appearance on MR imaging is variable and may not correlate with the degree of sclerosis seen on radiographs or CT. Disk degenerative changes and asymmetric endplate erosions are consistent markers of HS. (orig.)

Feature Detection of Curve Traffic Sign Image on The Bandung - Jakarta Highway

Science.gov (United States)

Naseer, M.; Supriadi, I.; Supangkat, S. H.

2018-03-01

Unsealed roadside and problems with the road surface are common causes of road crashes, particularly when those are combined with curves. Curve traffic sign is an important component for giving early warning to driver on traffic, especially on high-speed traffic like on the highway. Traffic sign detection has became a very interesting research now, and in this paper will be discussed about the detection of curve traffic sign. There are two types of curve signs are discussed, namely the curve turn to the left and the curve turn to the right and the all data sample used are the curves taken / recorded from some signs on the Bandung - Jakarta Highway. Feature detection of the curve signs use Speed Up Robust Feature (SURF) method, where the detected scene image is 800x450. From 45 curve turn to the right images, the system can detect the feature well to 35 images, where the success rate is 77,78%, while from the 45 curve turn to the left images, the system can detect the feature well to 34 images and the success rate is 75,56%, so the average accuracy in the detection process is 76,67%. While the average time for the detection process is 0.411 seconds.

The Feature Extraction Based on Texture Image Information for Emotion Sensing in Speech

Directory of Open Access Journals (Sweden)

Kun-Ching Wang

2014-09-01

Full Text Available In this paper, we present a novel texture image feature for Emotion Sensing in Speech (ESS. This idea is based on the fact that the texture images carry emotion-related information. The feature extraction is derived from time-frequency representation of spectrogram images. First, we transform the spectrogram as a recognizable image. Next, we use a cubic curve to enhance the image contrast. Then, the texture image information (TII derived from the spectrogram image can be extracted by using Laws’ masks to characterize emotional state. In order to evaluate the effectiveness of the proposed emotion recognition in different languages, we use two open emotional databases including the Berlin Emotional Speech Database (EMO-DB and eNTERFACE corpus and one self-recorded database (KHUSC-EmoDB, to evaluate the performance cross-corpora. The results of the proposed ESS system are presented using support vector machine (SVM as a classifier. Experimental results show that the proposed TII-based feature extraction inspired by visual perception can provide significant classification for ESS systems. The two-dimensional (2-D TII feature can provide the discrimination between different emotions in visual expressions except for the conveyance pitch and formant tracks. In addition, the de-noising in 2-D images can be more easily completed than de-noising in 1-D speech.

Significance of the impact of motion compensation on the variability of PET image features

Science.gov (United States)

Carles, M.; Bach, T.; Torres-Espallardo, I.; Baltas, D.; Nestle, U.; Martí-Bonmatí, L.

2018-03-01

In lung cancer, quantification by positron emission tomography/computed tomography (PET/CT) imaging presents challenges due to respiratory movement. Our primary aim was to study the impact of motion compensation implied by retrospectively gated (4D)-PET/CT on the variability of PET quantitative parameters. Its significance was evaluated by comparison with the variability due to (i) the voxel size in image reconstruction and (ii) the voxel size in image post-resampling. The method employed for feature extraction was chosen based on the analysis of (i) the effect of discretization of the standardized uptake value (SUV) on complementarity between texture features (TF) and conventional indices, (ii) the impact of the segmentation method on the variability of image features, and (iii) the variability of image features across the time-frame of 4D-PET. Thirty-one PET-features were involved. Three SUV discretization methods were applied: a constant width (SUV resolution) of the resampling bin (method RW), a constant number of bins (method RN) and RN on the image obtained after histogram equalization (method EqRN). The segmentation approaches evaluated were 40% of SUVmax and the contrast oriented algorithm (COA). Parameters derived from 4D-PET images were compared with values derived from the PET image obtained for (i) the static protocol used in our clinical routine (3D) and (ii) the 3D image post-resampled to the voxel size of the 4D image and PET image derived after modifying the reconstruction of the 3D image to comprise the voxel size of the 4D image. Results showed that TF complementarity with conventional indices was sensitive to the SUV discretization method. In the comparison of COA and 40% contours, despite the values not being interchangeable, all image features showed strong linear correlations (r  >  0.91, p\\ll 0.001 ). Across the time-frames of 4D-PET, all image features followed a normal distribution in most patients. For our patient cohort, the

Comparison on imaging features of central serous chorioretinopathy fundus

Directory of Open Access Journals (Sweden)

Ji-Jin Zhang

2014-10-01

Full Text Available AIM: To explore and analyze the image features, diagnosis and treatment of the central serous chorioretinopathy(CSCRfundus. METHODS: From May 2008 to May 2014, 97 cases of 121 eyes with central serous chorioretinopathy were treated in in our hospital. The imaging features were compared and analyzed through different methods. RESULTS: Sixty-one cases(61 eyeswere ≤45 years, including 13 case with disease in both eyes, single stove leak accounted for 48.6%, multifocal leakage(25.7%, atypical leakage accounted for 25.7%. Thirty-six cases(47 eyeswere >45 years, 11 cases with disease in both eyes, single focal leakage(8.5%, multifocal leakage(48.9%, atypical leakage accounted for 42.6%. FFA results showed acute hairstyle at the beginning of 89 eyes, chronic deferment type 32 eyes. OCT examination showed that the main features were neuroepithelial detachment, as well as the change of the retinal pigment epithelium(RPElayer, which was divided into RPE layer detachment 93 eyes, accounting for 76.9%, rough and RPE little ridges in 28 cases, accounting for 23.1%. The average thickness of macular center concave on the cortex of microns was 137.87±19.21μm, and there was no significant difference conpared with normal(137.32±4.98μmmicrons(t=0.30, P>0.05. The closer leakage area to macular fovea, the worse of eyesight.. CONCLUSION: Different imaging examination on central serous chorioretinopathy can show different features. For clinical diagnosis and treatment it had different and complementary roles, but were given significant help for diseases treatment.

Efficacy of dynamic susceptibility contrast MRI using echo-planar imaging in differential diagnosis of breast tumors

International Nuclear Information System (INIS)

Yoshino, Ayako

1998-01-01

It has been shown that T1-weighted dynamic MR imaging is a useful method in differentiating malignant breast tumors from benign lesions. Invasive breast carcinomas enhance more rapidly than benign lesions such as fibroadenomas, papillomas, and proliferative fibrocystic diseases. However, significant overlap in the dynamic profile of benign and malignant lesions may occur, resulting in relatively low specificity, which is an inherent limitation of this technique. The author attempted to improve diagnostic accuracy by utilizing dynamic susceptibility contrast MR imaging (DSC-MRI) with a single-shot echo-planar imaging sequence. Twenty-two patients underwent DSC-MRI using a 1.5-T unit (Magnetom Vision, Siemens). Images were obtained before, during and after the bolus injection of 20 mL of gadopentetate dimeglumine. The signal reduction rate within the first 30 seconds (ΔRT2) was calculated by the following equation: ΔRT2 = (postcontrast signal intensity-precontrast signal intensity) /precontrast signal intensity. A rapid, strong decrease in signal intensity was observed on the first pass of the contrast material in all cases of carcinoma, whereas no or only a minimal decrease in signal intensity was observed in all but one of the benign lesions. This method seems to be more accurate than T1-weighted dynamic MR imaging in the differentiation benign and malignant breast lesions. Since DSC-MRI can be performed quickly, subsequent conventional T1-weighted imaging can provide additional information about the morphologic features of lesions, to further support the diagnosis. In conclusion, DSC-MRI seems to be a promising method for the accurate preoperative assessment of breast lesions. (author)

Efficacy of dynamic susceptibility contrast MRI using echo-planar imaging in differential diagnosis of breast tumors

Energy Technology Data Exchange (ETDEWEB)

Yoshino, Ayako [Kyorin Univ., Mitaka, Tokyo (Japan). School of Medicine

1998-07-01

It has been shown that T1-weighted dynamic MR imaging is a useful method in differentiating malignant breast tumors from benign lesions. Invasive breast carcinomas enhance more rapidly than benign lesions such as fibroadenomas, papillomas, and proliferative fibrocystic diseases. However, significant overlap in the dynamic profile of benign and malignant lesions may occur, resulting in relatively low specificity, which is an inherent limitation of this technique. The author attempted to improve diagnostic accuracy by utilizing dynamic susceptibility contrast MR imaging (DSC-MRI) with a single-shot echo-planar imaging sequence. Twenty-two patients underwent DSC-MRI using a 1.5-T unit (Magnetom Vision, Siemens). Images were obtained before, during and after the bolus injection of 20 mL of gadopentetate dimeglumine. The signal reduction rate within the first 30 seconds ({Delta}RT2) was calculated by the following equation: {Delta}RT2 (postcontrast signal intensity-precontrast signal intensity) /precontrast signal intensity. A rapid, strong decrease in signal intensity was observed on the first pass of the contrast material in all cases of carcinoma, whereas no or only a minimal decrease in signal intensity was observed in all but one of the benign lesions. This method seems to be more accurate than T1-weighted dynamic MR imaging in the differentiation benign and malignant breast lesions. Since DSC-MRI can be performed quickly, subsequent conventional T1-weighted imaging can provide additional information about the morphologic features of lesions, to further support the diagnosis. In conclusion, DSC-MRI seems to be a promising method for the accurate preoperative assessment of breast lesions. (author)

Feature Extraction and Classification on Esophageal X-Ray Images of Xinjiang Kazak Nationality

Directory of Open Access Journals (Sweden)

Fang Yang

2017-01-01

Full Text Available Esophageal cancer is one of the fastest rising types of cancers in China. The Kazak nationality is the highest-risk group in Xinjiang. In this work, an effective computer-aided diagnostic system is developed to assist physicians in interpreting digital X-ray image features and improving the quality of diagnosis. The modules of the proposed system include image preprocessing, feature extraction, feature selection, image classification, and performance evaluation. 300 original esophageal X-ray images were resized to a region of interest and then enhanced by the median filter and histogram equalization method. 37 features from textural, frequency, and complexity domains were extracted. Both sequential forward selection and principal component analysis methods were employed to select the discriminative features for classification. Then, support vector machine and K-nearest neighbors were applied to classify the esophageal cancer images with respect to their specific types. The classification performance was evaluated in terms of the area under the receiver operating characteristic curve, accuracy, precision, and recall, respectively. Experimental results show that the classification performance of the proposed system outperforms the conventional visual inspection approaches in terms of diagnostic quality and processing time. Therefore, the proposed computer-aided diagnostic system is promising for the diagnostics of esophageal cancer.

Medical Image Fusion Algorithm Based on Nonlinear Approximation of Contourlet Transform and Regional Features

Directory of Open Access Journals (Sweden)

Hui Huang

2017-01-01

Full Text Available According to the pros and cons of contourlet transform and multimodality medical imaging, here we propose a novel image fusion algorithm that combines nonlinear approximation of contourlet transform with image regional features. The most important coefficient bands of the contourlet sparse matrix are retained by nonlinear approximation. Low-frequency and high-frequency regional features are also elaborated to fuse medical images. The results strongly suggested that the proposed algorithm could improve the visual effects of medical image fusion and image quality, image denoising, and enhancement.

Feature Selection from a Facial Image for Distinction of Sasang Constitution

Directory of Open Access Journals (Sweden)

Imhoi Koo

2009-01-01

Full Text Available Recently, oriental medicine has received attention for providing personalized medicine through consideration of the unique nature and constitution of individual patients. With the eventual goal of globalization, the current trend in oriental medicine research is the standardization by adopting western scientific methods, which could represent a scientific revolution. The purpose of this study is to establish methods for finding statistically significant features in a facial image with respect to distinguishing constitution and to show the meaning of those features. From facial photo images, facial elements are analyzed in terms of the distance, angle and the distance ratios, for which there are 1225, 61 250 and 749 700 features, respectively. Due to the very large number of facial features, it is quite difficult to determine truly meaningful features. We suggest a process for the efficient analysis of facial features including the removal of outliers, control for missing data to guarantee data confidence and calculation of statistical significance by applying ANOVA. We show the statistical properties of selected features according to different constitutions using the nine distances, 10 angles and 10 rates of distance features that are finally established. Additionally, the Sasang constitutional meaning of the selected features is shown here.

Feature Selection from a Facial Image for Distinction of Sasang Constitution

Science.gov (United States)

Koo, Imhoi; Kim, Jong Yeol; Kim, Myoung Geun

2009-01-01

Recently, oriental medicine has received attention for providing personalized medicine through consideration of the unique nature and constitution of individual patients. With the eventual goal of globalization, the current trend in oriental medicine research is the standardization by adopting western scientific methods, which could represent a scientific revolution. The purpose of this study is to establish methods for finding statistically significant features in a facial image with respect to distinguishing constitution and to show the meaning of those features. From facial photo images, facial elements are analyzed in terms of the distance, angle and the distance ratios, for which there are 1225, 61 250 and 749 700 features, respectively. Due to the very large number of facial features, it is quite difficult to determine truly meaningful features. We suggest a process for the efficient analysis of facial features including the removal of outliers, control for missing data to guarantee data confidence and calculation of statistical significance by applying ANOVA. We show the statistical properties of selected features according to different constitutions using the nine distances, 10 angles and 10 rates of distance features that are finally established. Additionally, the Sasang constitutional meaning of the selected features is shown here. PMID:19745013

Fast hybrid fractal image compression using an image feature and neural network

International Nuclear Information System (INIS)

Zhou Yiming; Zhang Chao; Zhang Zengke

2008-01-01

Since fractal image compression could maintain high-resolution reconstructed images at very high compression ratio, it has great potential to improve the efficiency of image storage and image transmission. On the other hand, fractal image encoding is time consuming for the best matching search between range blocks and domain blocks, which limits the algorithm to practical application greatly. In order to solve this problem, two strategies are adopted to improve the fractal image encoding algorithm in this paper. Firstly, based on the definition of an image feature, a necessary condition of the best matching search and FFC algorithm are proposed, and it could reduce the search space observably and exclude most inappropriate domain blocks according to each range block before the best matching search. Secondly, on the basis of FFC algorithm, in order to reduce the mapping error during the best matching search, a special neural network is constructed to modify the mapping scheme for the subblocks, in which the pixel values fluctuate greatly (FNFC algorithm). Experimental results show that the proposed algorithms could obtain good quality of the reconstructed images and need much less time than the baseline encoding algorithm

Differential privacy-based evaporative cooling feature selection and classification with relief-F and random forests.

Science.gov (United States)

Le, Trang T; Simmons, W Kyle; Misaki, Masaya; Bodurka, Jerzy; White, Bill C; Savitz, Jonathan; McKinney, Brett A

2017-09-15

Classification of individuals into disease or clinical categories from high-dimensional biological data with low prediction error is an important challenge of statistical learning in bioinformatics. Feature selection can improve classification accuracy but must be incorporated carefully into cross-validation to avoid overfitting. Recently, feature selection methods based on differential privacy, such as differentially private random forests and reusable holdout sets, have been proposed. However, for domains such as bioinformatics, where the number of features is much larger than the number of observations p≫n , these differential privacy methods are susceptible to overfitting. We introduce private Evaporative Cooling, a stochastic privacy-preserving machine learning algorithm that uses Relief-F for feature selection and random forest for privacy preserving classification that also prevents overfitting. We relate the privacy-preserving threshold mechanism to a thermodynamic Maxwell-Boltzmann distribution, where the temperature represents the privacy threshold. We use the thermal statistical physics concept of Evaporative Cooling of atomic gases to perform backward stepwise privacy-preserving feature selection. On simulated data with main effects and statistical interactions, we compare accuracies on holdout and validation sets for three privacy-preserving methods: the reusable holdout, reusable holdout with random forest, and private Evaporative Cooling, which uses Relief-F feature selection and random forest classification. In simulations where interactions exist between attributes, private Evaporative Cooling provides higher classification accuracy without overfitting based on an independent validation set. In simulations without interactions, thresholdout with random forest and private Evaporative Cooling give comparable accuracies. We also apply these privacy methods to human brain resting-state fMRI data from a study of major depressive disorder. Code

TIE POINTS EXTRACTION FOR SAR IMAGES BASED ON DIFFERENTIAL CONSTRAINTS

Directory of Open Access Journals (Sweden)

X. Xiong

2018-04-01

Full Text Available Automatically extracting tie points (TPs on large-size synthetic aperture radar (SAR images is still challenging because the efficiency and correct ratio of the image matching need to be improved. This paper proposes an automatic TPs extraction method based on differential constraints for large-size SAR images obtained from approximately parallel tracks, between which the relative geometric distortions are small in azimuth direction and large in range direction. Image pyramids are built firstly, and then corresponding layers of pyramids are matched from the top to the bottom. In the process, the similarity is measured by the normalized cross correlation (NCC algorithm, which is calculated from a rectangular window with the long side parallel to the azimuth direction. False matches are removed by the differential constrained random sample consensus (DC-RANSAC algorithm, which appends strong constraints in azimuth direction and weak constraints in range direction. Matching points in the lower pyramid images are predicted with the local bilinear transformation model in range direction. Experiments performed on ENVISAT ASAR and Chinese airborne SAR images validated the efficiency, correct ratio and accuracy of the proposed method.

Extended feature-fusion guidelines to improve image-based multi-modal biometrics

CSIR Research Space (South Africa)

Brown, Dane

2016-09-01

Full Text Available The feature-level, unlike the match score-level, lacks multi-modal fusion guidelines. This work demonstrates a practical approach for improved image-based biometric feature-fusion. The approach extracts and combines the face, fingerprint...

a Statistical Texture Feature for Building Collapse Information Extraction of SAR Image

Science.gov (United States)

Li, L.; Yang, H.; Chen, Q.; Liu, X.

2018-04-01

Synthetic Aperture Radar (SAR) has become one of the most important ways to extract post-disaster collapsed building information, due to its extreme versatility and almost all-weather, day-and-night working capability, etc. In view of the fact that the inherent statistical distribution of speckle in SAR images is not used to extract collapsed building information, this paper proposed a novel texture feature of statistical models of SAR images to extract the collapsed buildings. In the proposed feature, the texture parameter of G0 distribution from SAR images is used to reflect the uniformity of the target to extract the collapsed building. This feature not only considers the statistical distribution of SAR images, providing more accurate description of the object texture, but also is applied to extract collapsed building information of single-, dual- or full-polarization SAR data. The RADARSAT-2 data of Yushu earthquake which acquired on April 21, 2010 is used to present and analyze the performance of the proposed method. In addition, the applicability of this feature to SAR data with different polarizations is also analysed, which provides decision support for the data selection of collapsed building information extraction.

Optimization of wavelet decomposition for image compression and feature preservation.

Science.gov (United States)

Lo, Shih-Chung B; Li, Huai; Freedman, Matthew T

2003-09-01

A neural-network-based framework has been developed to search for an optimal wavelet kernel that can be used for a specific image processing task. In this paper, a linear convolution neural network was employed to seek a wavelet that minimizes errors and maximizes compression efficiency for an image or a defined image pattern such as microcalcifications in mammograms and bone in computed tomography (CT) head images. We have used this method to evaluate the performance of tap-4 wavelets on mammograms, CTs, magnetic resonance images, and Lena images. We found that the Daubechies wavelet or those wavelets with similar filtering characteristics can produce the highest compression efficiency with the smallest mean-square-error for many image patterns including general image textures as well as microcalcifications in digital mammograms. However, the Haar wavelet produces the best results on sharp edges and low-noise smooth areas. We also found that a special wavelet whose low-pass filter coefficients are 0.32252136, 0.85258927, 1.38458542, and -0.14548269) produces the best preservation outcomes in all tested microcalcification features including the peak signal-to-noise ratio, the contrast and the figure of merit in the wavelet lossy compression scheme. Having analyzed the spectrum of the wavelet filters, we can find the compression outcomes and feature preservation characteristics as a function of wavelets. This newly developed optimization approach can be generalized to other image analysis applications where a wavelet decomposition is employed.

Body imaging in the differential diagnosis of jaundice

International Nuclear Information System (INIS)

Kuno, Nobuyoshi; Endo, Tokiko; Kasugai, Tatsuzo

1981-01-01

Forty-five jaundiced patients with confirmed pancreatico-biliary diseases were studied to determine the value of body imaging in the differential diagnosis of jaundice. In this study, body imaging included five tests, which were US, CT, ERCP, PTC and RI. The results indicate that each to these five tests is useful and highly accurate in differentiating between obstructive and nonobstructive jaundice (about 90%). The site of obstruction was delineated in 91.3%, 90.9%, 82.5%, 66.7% and 50% by PTC, ERCP, CT, US and RI, respectively. ERCP, PTC, CT, US and RI helped determine the etiology of jaundice in 79.5%, 65.2%, 57.5%, 50% and 0%, respectively. ERCP and US were highly accurate in establishing the diagnosis of resectable pancreatico-biliary cancer with obstructive jaundice. On the basis of these results, we propose a diagnostic approach to obstructive jaundice as in Table 5. (author)

Computer-aided breast MR image feature analysis for prediction of tumor response to chemotherapy

International Nuclear Information System (INIS)

Aghaei, Faranak; Tan, Maxine; Liu, Hong; Zheng, Bin; Hollingsworth, Alan B.; Qian, Wei

2015-01-01

Purpose: To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy. Methods: The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from both tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method. Results: In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC = 0.85 ± 0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96 ± 0.03 (p < 0.01). Conclusions: This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy

Computer-aided breast MR image feature analysis for prediction of tumor response to chemotherapy

Energy Technology Data Exchange (ETDEWEB)

Aghaei, Faranak; Tan, Maxine; Liu, Hong; Zheng, Bin, E-mail: Bin.Zheng-1@ou.edu [School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019 (United States); Hollingsworth, Alan B. [Mercy Women’s Center, Mercy Health Center, Oklahoma City, Oklahoma 73120 (United States); Qian, Wei [Department of Electrical and Computer Engineering, University of Texas, El Paso, Texas 79968 (United States)

2015-11-15

Purpose: To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy. Methods: The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from both tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method. Results: In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC = 0.85 ± 0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96 ± 0.03 (p < 0.01). Conclusions: This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy.

Enhancement and feature extraction of RS images from seismic area and seismic disaster recognition technologies

Science.gov (United States)

Zhang, Jingfa; Qin, Qiming

2003-09-01

Many types of feature extracting of RS image are analyzed, and the work procedure of pattern recognizing in RS images of seismic disaster is proposed. The aerial RS image of Tangshan Great Earthquake is processed, and the digital features of various typical seismic disaster on the RS image is calculated.

Change Detection of High-Resolution Remote Sensing Images Based on Adaptive Fusion of Multiple Features

Science.gov (United States)

Wang, G. H.; Wang, H. B.; Fan, W. F.; Liu, Y.; Chen, C.

2018-04-01

In view of the traditional change detection algorithm mainly depends on the spectral information image spot, failed to effectively mining and fusion of multi-image feature detection advantage, the article borrows the ideas of object oriented analysis proposed a multi feature fusion of remote sensing image change detection algorithm. First by the multi-scale segmentation of image objects based; then calculate the various objects of color histogram and linear gradient histogram; utilizes the color distance and edge line feature distance between EMD statistical operator in different periods of the object, using the adaptive weighted method, the color feature distance and edge in a straight line distance of combination is constructed object heterogeneity. Finally, the curvature histogram analysis image spot change detection results. The experimental results show that the method can fully fuse the color and edge line features, thus improving the accuracy of the change detection.

Human gait recognition by pyramid of HOG feature on silhouette images

Science.gov (United States)

Yang, Guang; Yin, Yafeng; Park, Jeanrok; Man, Hong

2013-03-01

As a uncommon biometric modality, human gait recognition has a great advantage of identify people at a distance without high resolution images. It has attracted much attention in recent years, especially in the fields of computer vision and remote sensing. In this paper, we propose a human gait recognition framework that consists of a reliable background subtraction method followed by the pyramid of Histogram of Gradient (pHOG) feature extraction on the silhouette image, and a Hidden Markov Model (HMM) based classifier. Through background subtraction, the silhouette of human gait in each frame is extracted and normalized from the raw video sequence. After removing the shadow and noise in each region of interest (ROI), pHOG feature is computed on the silhouettes images. Then the pHOG features of each gait class will be used to train a corresponding HMM. In the test stage, pHOG feature will be extracted from each test sequence and used to calculate the posterior probability toward each trained HMM model. Experimental results on the CASIA Gait Dataset B1 demonstrate that with our proposed method can achieve very competitive recognition rate.

Susceptibility weighted imaging: differentiating between calcification and hemosiderin

Energy Technology Data Exchange (ETDEWEB)

Barbosa, Jeam Haroldo Oliveira; Salmon, Carlos Ernesto Garrido, E-mail: jeamharoldo@hotmail.com [Universidade de Sao Paulo (FFCLRP/USP), Ribeirao Preto, SP (Brazil). Faculdade de Filosofia, Ciencias e Letras; Santos, Antonio Carlos [Universidade de Sao Paulo (FMRP/USP), Ribeirao Preto, SP (Brazil). Faculdade de Medicina

2015-03-15

Objective: to present a detailed explanation on the processing of magnetic susceptibility weighted imaging (SWI), demonstrating the effects of echo time and sensitive mask on the differentiation between calcification and hemosiderin. Materials and methods: computed tomography and magnetic resonance (magnitude and phase) images of six patients (age range 41-54 years; four men) were retrospectively selected. The SWI images processing was performed using the Matlab's own routine. Results: four out of the six patients showed calcifications at computed tomography images and their SWI images demonstrated hyperintense signal at the calcification regions. The other patients did not show any calcifications at computed tomography, and SWI revealed the presence of hemosiderin deposits with hypointense signal. Conclusion: the selection of echo time and of the mask may change all the information on SWI images, and compromise the diagnostic reliability. Amongst the possible masks, the authors highlight that the sigmoid mask allows for contrasting calcifications and hemosiderin on a single SWI image. (author)

Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging.

Science.gov (United States)

Larroza, Andrés; Materka, Andrzej; López-Lereu, María P; Monmeneu, José V; Bodí, Vicente; Moratal, David

2017-07-01

The purpose of this study was to differentiate acute from chronic myocardial infarction using machine learning techniques and texture features extracted from cardiac magnetic resonance imaging (MRI). The study group comprised 22 cases with acute myocardial infarction (AMI) and 22 cases with chronic myocardial infarction (CMI). Cine and late gadolinium enhancement (LGE) MRI were analyzed independently to differentiate AMI from CMI. A total of 279 texture features were extracted from predefined regions of interest (ROIs): the infarcted area on LGE MRI, and the entire myocardium on cine MRI. Classification performance was evaluated by a nested cross-validation approach combining a feature selection technique with three predictive models: random forest, support vector machine (SVM) with Gaussian Kernel, and SVM with polynomial kernel. The polynomial SVM yielded the best classification performance. Receiver operating characteristic curves provided area-under-the-curve (AUC) (mean±standard deviation) of 0.86±0.06 on LGE MRI using 72 features; AMI sensitivity=0.81±0.08 and specificity=0.84±0.09. On cine MRI, AUC=0.82±0.06 using 75 features; AMI sensitivity=0.79±0.10 and specificity=0.80±0.10. We concluded that texture analysis can be used for differentiation of AMI from CMI on cardiac LGE MRI, and also on standard cine sequences in which the infarction is visually imperceptible in most cases. Copyright © 2017 Elsevier B.V. All rights reserved.

Computer-aided diagnosis with textural features for breast lesions in sonograms.

Science.gov (United States)

Chen, Dar-Ren; Huang, Yu-Len; Lin, Sheng-Hsiung

2011-04-01

Computer-aided diagnosis (CAD) systems provided second beneficial support reference and enhance the diagnostic accuracy. This paper was aimed to develop and evaluate a CAD with texture analysis in the classification of breast tumors for ultrasound images. The ultrasound (US) dataset evaluated in this study composed of 1020 sonograms of region of interest (ROI) subimages from 255 patients. Two-view sonogram (longitudinal and transverse views) and four different rectangular regions were utilized to analyze each tumor. Six practical textural features from the US images were performed to classify breast tumors as benign or malignant. However, the textural features always perform as a high dimensional vector; high dimensional vector is unfavorable to differentiate breast tumors in practice. The principal component analysis (PCA) was used to reduce the dimension of textural feature vector and then the image retrieval technique was performed to differentiate between benign and malignant tumors. In the experiments, all the cases were sampled with k-fold cross-validation (k=10) to evaluate the performance with receiver operating characteristic (ROC) curve. The area (A(Z)) under the ROC curve for the proposed CAD system with the specific textural features was 0.925±0.019. The classification ability for breast tumor with textural information is satisfactory. This system differentiates benign from malignant breast tumors with a good result and is therefore clinically useful to provide a second opinion. Copyright © 2010 Elsevier Ltd. All rights reserved.

Fake/Bogus Conferences; Their Features and Some Subtle Ways to Differentiate Them from Real Ones

DEFF Research Database (Denmark)

Asadi, Amin; Rahbar, Nader; Rezvani, Mohammad Javad

2018-01-01

The main objective of the present paper is to introduce some features of fake/bogus conferences and some viable approaches to differentiate them from the real ones. These fake/bogus conferences introduce themselves as international conferences, which are multidisciplinary and indexed in major sci...... scientific digital libraries. Furthermore, most of the fake/bogus conference holders offer publishing the accepted papers in ISI journals and use other techniques in their advertisement e-mails.......The main objective of the present paper is to introduce some features of fake/bogus conferences and some viable approaches to differentiate them from the real ones. These fake/bogus conferences introduce themselves as international conferences, which are multidisciplinary and indexed in major...

Differential diagnosis of idiopathic granulomatous mastitis and breast cancer using acoustic radiation force impulse imaging.

Science.gov (United States)

Teke, Memik; Teke, Fatma; Alan, Bircan; Türkoğlu, Ahmet; Hamidi, Cihad; Göya, Cemil; Hattapoğlu, Salih; Gumus, Metehan

2017-01-01

Differentiation of idiopathic granulomatous mastitis (IGM) from carcinoma with routine imaging methods, such as ultrasonography (US) and mammography, is difficult. Therefore, we evaluated the value of a newly developed noninvasive technique called acoustic radiation force impulse imaging in differentiating IGM versus malignant lesions in the breast. Four hundred and eighty-six patients, who were referred to us with a presumptive diagnosis of a mass, underwent Virtual Touch tissue imaging (VTI; Siemens) and Virtual Touch tissue quantification (VTQ; Siemens) after conventional gray-scale US. US-guided percutaneous needle biopsy was then performed on 276 lesions with clinically and radiologically suspicious features. Malignant lesions (n = 122) and IGM (n = 48) were included in the final study group. There was a statistically significant difference in shear wave velocity marginal and internal values between the IGM and malignant lesions. The median marginal velocity for IGM and malignant lesions was 3.19 m/s (minimum-maximum 2.49-5.82) and 5.05 m/s (minimum-maximum 2.09-8.46), respectively (p < 0.001). The median internal velocity for IGM and malignant lesions was 2.76 m/s (minimum-maximum 1.14-4.12) and 4.79 m/s (minimum-maximum 2.12-8.02), respectively (p < 0.001). The combination of VTI and VTQ as a complement to conventional US provides viscoelastic properties of tissues, and thus has the potential to increase the specificity of US.

Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

Science.gov (United States)

Huo, Guanying

2017-01-01

As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases. PMID:28316614

Value of multiparametric magnetic resonance imaging of the breast for the differentiation of fat necrosis and tumor recurrence after breast-conserving surgery. A case report

Energy Technology Data Exchange (ETDEWEB)

Doerner, Jonas; Krug, Kathrin Barbara [University Hospital Cologne (Germany). Dept. of Diagnostic and Interventional Radiology; Malter, Wolfram [University Hospital Cologne (Germany). Dept. of Obstetrics and Gynaecology; Markiefka, Birgid [University Hospital Cologne (Germany). Inst. of Pathology

2018-02-15

In rare cases the differentiation of tumor recurrence and fat necrosis in patients with breast-conserving surgery with or without radiotherapy can be challenging. In such cases magnetic resonance imaging features, in particular strong vs. faint contrast enhancement and diffusion restriction vs. non-restriction can help to characterize such lesions.

The mental representation of living and nonliving things: differential weighting and interactivity of sensorial and non-sensorial features.

Science.gov (United States)

Ventura, Paulo; Morais, José; Brito-Mendes, Carlos; Kolinsky, Régine

2005-02-01

Warrington and colleagues (Warrington & McCarthy, 1983, 1987; Warrington & Shallice, 1984) claimed that sensorial and functional-associative (FA) features are differentially important in determining the meaning of living things (LT) and nonliving things (NLT). The first aim of the present study was to evaluate this hypothesis through two different access tasks: feature generation (Experiment 1) and cued recall (Experiment 2). The results of both experiments provided consistent empirical support for Warrington and colleagues' assumption. The second aim of the present study was to test a new differential interactivity hypothesis that combines Warrington and colleagueS' assumption with the notion of a higher number of intercorrelations and hence of a stronger connectivity between sensorial and non-sensorial features for LTs than for NLTs. This hypothesis was motivated by previoUs reports of an uncrossed interaction between domain (LTs vs NLTs) and attribute type (sensorial vs FA) in, for example, a feature verification task (Laws, Humber, Ramsey, & McCarthy, 1995): while FA attributes are verified faster than sensorial attributes for NLTs, no difference is observed for LTs. We replicated and generalised this finding using several feature verification tasks on both written words and pictures (Experiment 3), including in conditions aimed at minimising the intervention of priming biases and strategic or mnemonic processes (Experiment 4). The whole set of results suggests that both privileged relations between features and categories, and the differential importance of intercorrelations between features as a function of category, modulate access to semantic features.

MR imaging of transient synovitis: differentiation from septic arthritis

International Nuclear Information System (INIS)

Yang, W.J.; Im, S.A.; Lim, G.Y.; Chun, H.J.; Jung, N.Y.; Sung, M.S.; Choi, B.G.

2006-01-01

Transient synovitis is the most common cause of acute hip pain in children. However, MR imaging findings in transient synovitis and the role of MR imaging in differentiating transient synovitis from septic arthritis have not been fully reported. To describe the MR findings of transient synovitis and to determine whether the MR characteristics can differentiate this disease entity from septic arthritis. Clinical findings and MR images of 49 patients with transient synovitis (male/female 36/13, mean age 6.1 years) and 18 patients with septic arthritis (male/female 10/8, mean age 4.9 years) were retrospectively reviewed. MR findings of transient synovitis were symptomatic joint effusion, synovial enhancement, contralateral joint effusion, synovial thickening, and signal intensity (SI) alterations and enhancement in surrounding soft tissue. Among these, SI alterations and enhancement in bone marrow and soft tissue, contralateral joint effusion, and synovial thickening were statistically significant MR findings in differentiating transient synovitis from septic arthritis. The statistically significant MR findings in transient synovitis are contralateral (asymptomatic) joint effusions and the absence of SI abnormalities of the bone marrow. It is less common to have SI alterations and contrast enhancement of the soft tissues. The statistically significant MR findings in septic arthritis are SI alterations of the bone marrow, and SI alterations and contrast enhancement of the soft tissue. Ipsilateral effusion and synovial thickening and enhancement are present in both diseases

CT appearance and features of tubal pregnancy

Energy Technology Data Exchange (ETDEWEB)

Xiaohong, Wang; Hong, Shan; Zaibo, Jiang; Xinghe, Deng; Xiaochun, Meng; Bingbing, Ye; Mingyue, Luo; Yunya, Lin [Sun Yat-sen Univ., Guangzhou (China). The Third Univ. Hospital, Dept. of Radiology

2004-06-01

Objective: To investigate the CT appearance and features of tubal pregnancy. Methods: Precontrast and postcontrast CT scans were employed in 38 patients who were clinically and ultrasonographically suspected of tubal pregnancy. 34 of them were verified as tubal pregnancy through operative pathology. Results: 1. The direct CT imaging feature was the whole pregnancies sac (4/34, 11.8%) or half-baked pregnancies sac (14/34, 41.2%); 2. The indirect CT imaging features were: (1) abnormal density image, which could be enhanced, in a cystic mass around adnexal area (8/34, 23.5%); (2) mix density mass around adnexal area, which was mainly solid and had mild to moderate inhomogeneous enhancement (19/34, 55.9%); (3) large area irregular shadow with high density were found beside the uterus, with no enhancement (3/34, 8.8%). (4) bloody density in uterus-rectum-fossa (23/34, 67.6%). 3. The CT imaging features of tubal pregnancy was classified as: (1) Pregnant sac type (4/34, 11.8%); (2) Cystic (8/34, 23.5%); (3) Massive type (17/34, 50%); (4) Chronic mass type (2/34, 5.9%); (5) Bleeding type (3/34, 8.8%). 4. The CT imaging appearance of tubal pregnancy related with the pregnancy location; 5. The CT imaging appearance of tubal pregnancy related with the clinical significant. Conclusion: The CT imaging appearance of tubal pregnancy has some features, which can help in the diagnosis or differential diagnosis of the pelvis masses. CT scan is an effective supplementary attempt to the clinically and ultrasonographically suspected tubal pregnancy patients.

CT appearance and features of tubal pregnancy

International Nuclear Information System (INIS)

Wang Xiaohong; Shan Hong; Jiang Zaibo; Deng Xinghe; Meng Xiaochun; Ye Bingbing; Luo Mingyue; Lin Yunya

2004-01-01

Objective: To investigate the CT appearance and features of tubal pregnancy. Methods: Precontrast and postcontrast CT scans were employed in 38 patients who were clinically and ultrasonographically suspected of tubal pregnancy. 34 of them were verified as tubal pregnancy through operative pathology. Results: 1. The direct CT imaging feature was the whole pregnancies sac (4/34, 11.8%) or half-baked pregnancies sac (14/34, 41.2%); 2. The indirect CT imaging features were: (1) abnormal density image, which could be enhanced, in a cystic mass around adnexal area (8/34, 23.5%); (2) mix density mass around adnexal area, which was mainly solid and had mild to moderate inhomogeneous enhancement (19/34, 55.9%); (3) large area irregular shadow with high density were found beside the uterus, with no enhancement (3/34, 8.8%). (4) bloody density in uterus-rectum-fossa (23/34, 67.6%). 3. The CT imaging features of tubal pregnancy was classified as: (1) Pregnant sac type (4/34, 11.8%); (2) Cystic (8/34, 23.5%); (3) Massive type (17/34, 50%); (4) Chronic mass type (2/34, 5.9%); (5) Bleeding type (3/34, 8.8%). 4. The CT imaging appearance of tubal pregnancy related with the pregnancy location; 5. The CT imaging appearance of tubal pregnancy related with the clinical significant. Conclusion: The CT imaging appearance of tubal pregnancy has some features, which can help in the diagnosis or differential diagnosis of the pelvis masses. CT scan is an effective supplementary attempt to the clinically and ultrasonographically suspected tubal pregnancy patients

Feature Extraction and Simplification from colour images based on Colour Image Segmentation and Skeletonization using the Quad-Edge data structure

DEFF Research Database (Denmark)

Sharma, Ojaswa; Mioc, Darka; Anton, François

2007-01-01

Region features in colour images are of interest in applications such as mapping, GIS, climatology, change detection, medicine, etc. This research work is an attempt to automate the process of extracting feature boundaries from colour images. This process is an attempt to eventually replace manua...

Identification of natural images and computer-generated graphics based on statistical and textural features.

Science.gov (United States)

Peng, Fei; Li, Jiao-ting; Long, Min

2015-03-01

To discriminate the acquisition pipelines of digital images, a novel scheme for the identification of natural images and computer-generated graphics is proposed based on statistical and textural features. First, the differences between them are investigated from the view of statistics and texture, and 31 dimensions of feature are acquired for identification. Then, LIBSVM is used for the classification. Finally, the experimental results are presented. The results show that it can achieve an identification accuracy of 97.89% for computer-generated graphics, and an identification accuracy of 97.75% for natural images. The analyses also demonstrate the proposed method has excellent performance, compared with some existing methods based only on statistical features or other features. The method has a great potential to be implemented for the identification of natural images and computer-generated graphics. © 2014 American Academy of Forensic Sciences.