A Pareto-based Ensemble with Feature and Instance Selection for Learning from Multi-Class Imbalanced Datasets.

Science.gov (United States)

Fernández, Alberto; Carmona, Cristobal José; José Del Jesus, María; Herrera, Francisco

2017-09-01

Imbalanced classification is related to those problems that have an uneven distribution among classes. In addition to the former, when instances are located into the overlapped areas, the correct modeling of the problem becomes harder. Current solutions for both issues are often focused on the binary case study, as multi-class datasets require an additional effort to be addressed. In this research, we overcome these problems by carrying out a combination between feature and instance selections. Feature selection will allow simplifying the overlapping areas easing the generation of rules to distinguish among the classes. Selection of instances from all classes will address the imbalance itself by finding the most appropriate class distribution for the learning task, as well as possibly removing noise and difficult borderline examples. For the sake of obtaining an optimal joint set of features and instances, we embedded the searching for both parameters in a Multi-Objective Evolutionary Algorithm, using the C4.5 decision tree as baseline classifier in this wrapper approach. The multi-objective scheme allows taking a double advantage: the search space becomes broader, and we may provide a set of different solutions in order to build an ensemble of classifiers. This proposal has been contrasted versus several state-of-the-art solutions on imbalanced classification showing excellent results in both binary and multi-class problems.

Mapping US Urban Extents from MODIS Data Using One-Class Classification Method

Directory of Open Access Journals (Sweden)

Bo Wan

2015-08-01

Full Text Available Urban areas are one of the most important components of human society. Their extents have been continuously growing during the last few decades. Accurate and timely measurements of the extents of urban areas can help in analyzing population densities and urban sprawls and in studying environmental issues related to urbanization. Urban extents detected from remotely sensed data are usually a by-product of land use classification results, and their interpretation requires a full understanding of land cover types. In this study, for the first time, we mapped urban extents in the continental United States using a novel one-class classification method, i.e., positive and unlabeled learning (PUL, with multi-temporal Moderate Resolution Imaging Spectroradiometer (MODIS data for the year 2010. The Defense Meteorological Satellite Program Operational Linescan System (DMSP-OLS night stable light data were used to calibrate the urban extents obtained from the one-class classification scheme. Our results demonstrated the effectiveness of the use of the PUL algorithm in mapping large-scale urban areas from coarse remote-sensing images, for the first time. The total accuracy of mapped urban areas was 92.9% and the kappa coefficient was 0.85. The use of DMSP-OLS night stable light data can significantly reduce false detection rates from bare land and cropland far from cities. Compared with traditional supervised classification methods, the one-class classification scheme can greatly reduce the effort involved in collecting training datasets, without losing predictive accuracy.

Binary Stochastic Representations for Large Multi-class Classification

KAUST Repository

Gerald, Thomas

2017-10-23

Classification with a large number of classes is a key problem in machine learning and corresponds to many real-world applications like tagging of images or textual documents in social networks. If one-vs-all methods usually reach top performance in this context, these approaches suffer of a high inference complexity, linear w.r.t. the number of categories. Different models based on the notion of binary codes have been proposed to overcome this limitation, achieving in a sublinear inference complexity. But they a priori need to decide which binary code to associate to which category before learning using more or less complex heuristics. We propose a new end-to-end model which aims at simultaneously learning to associate binary codes with categories, but also learning to map inputs to binary codes. This approach called Deep Stochastic Neural Codes (DSNC) keeps the sublinear inference complexity but do not need any a priori tuning. Experimental results on different datasets show the effectiveness of the approach w.r.t. baseline methods.

Deep learning architectures for multi-label classification of intelligent health risk prediction.

Science.gov (United States)

Maxwell, Andrew; Li, Runzhi; Yang, Bei; Weng, Heng; Ou, Aihua; Hong, Huixiao; Zhou, Zhaoxian; Gong, Ping; Zhang, Chaoyang

2017-12-28

Multi-label classification of data remains to be a challenging problem. Because of the complexity of the data, it is sometimes difficult to infer information about classes that are not mutually exclusive. For medical data, patients could have symptoms of multiple different diseases at the same time and it is important to develop tools that help to identify problems early. Intelligent health risk prediction models built with deep learning architectures offer a powerful tool for physicians to identify patterns in patient data that indicate risks associated with certain types of chronic diseases. Physical examination records of 110,300 anonymous patients were used to predict diabetes, hypertension, fatty liver, a combination of these three chronic diseases, and the absence of disease (8 classes in total). The dataset was split into training (90%) and testing (10%) sub-datasets. Ten-fold cross validation was used to evaluate prediction accuracy with metrics such as precision, recall, and F-score. Deep Learning (DL) architectures were compared with standard and state-of-the-art multi-label classification methods. Preliminary results suggest that Deep Neural Networks (DNN), a DL architecture, when applied to multi-label classification of chronic diseases, produced accuracy that was comparable to that of common methods such as Support Vector Machines. We have implemented DNNs to handle both problem transformation and algorithm adaption type multi-label methods and compare both to see which is preferable. Deep Learning architectures have the potential of inferring more information about the patterns of physical examination data than common classification methods. The advanced techniques of Deep Learning can be used to identify the significance of different features from physical examination data as well as to learn the contributions of each feature that impact a patient's risk for chronic diseases. However, accurate prediction of chronic disease risks remains a challenging

Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma

International Nuclear Information System (INIS)

Liberman, Gilad; Louzoun, Yoram; Aizenstein, Orna; Blumenthal, Deborah T.; Bokstein, Felix; Palmon, Mika; Corn, Benjamin W.; Ben Bashat, Dafna

2013-01-01

Background: Current methods for evaluation of treatment response in glioblastoma are inaccurate, limited and time-consuming. This study aimed to develop a multi-modal MRI automatic classification method to improve accuracy and efficiency of treatment response assessment in patients with recurrent glioblastoma (GB). Materials and methods: A modification of the k-Nearest-Neighbors (kNN) classification method was developed and applied to 59 longitudinal MR data sets of 13 patients with recurrent GB undergoing bevacizumab (anti-angiogenic) therapy. Changes in the enhancing tumor volume were assessed using the proposed method and compared with Macdonald's criteria and with manual volumetric measurements. The edema-like area was further subclassified into peri- and non-peri-tumoral edema, using both the kNN method and an unsupervised method, to monitor longitudinal changes. Results: Automatic classification using the modified kNN method was applicable in all scans, even when the tumors were infiltrative with unclear borders. The enhancing tumor volume obtained using the automatic method was highly correlated with manual measurements (N = 33, r = 0.96, p < 0.0001), while standard radiographic assessment based on Macdonald's criteria matched manual delineation and automatic results in only 68% of cases. A graded pattern of tumor infiltration within the edema-like area was revealed by both automatic methods, showing high agreement. All classification results were confirmed by a senior neuro-radiologist and validated using MR spectroscopy. Conclusion: This study emphasizes the important role of automatic tools based on a multi-modal view of the tissue in monitoring therapy response in patients with high grade gliomas specifically under anti-angiogenic therapy

A method of neighbor classes based SVM classification for optical printed Chinese character recognition.

Science.gov (United States)

Zhang, Jie; Wu, Xiaohong; Yu, Yanmei; Luo, Daisheng

2013-01-01

In optical printed Chinese character recognition (OPCCR), many classifiers have been proposed for the recognition. Among the classifiers, support vector machine (SVM) might be the best classifier. However, SVM is a classifier for two classes. When it is used for multi-classes in OPCCR, its computation is time-consuming. Thus, we propose a neighbor classes based SVM (NC-SVM) to reduce the computation consumption of SVM. Experiments of NC-SVM classification for OPCCR have been done. The results of the experiments have shown that the NC-SVM we proposed can effectively reduce the computation time in OPCCR.

Stellar Spectral Classification with Minimum Within-Class and ...

Indian Academy of Sciences (India)

Support Vector Machine (SVM) is one of the important stellar spectral classification methods, and it is widely used in practice. But its classification efficiencies cannot be greatly improved because it does not take the class distribution into consideration. In view of this, a modified SVM-named Minimum within-class and ...

Retinal Microaneurysms Detection Using Gradient Vector Analysis and Class Imbalance Classification.

Science.gov (United States)

Dai, Baisheng; Wu, Xiangqian; Bu, Wei

2016-01-01

Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification, which is composed of two stages, i.e. candidate MAs extraction and classification. In the first stage, a candidate MAs extraction algorithm is devised by analyzing the gradient field of the image, in which a multi-scale log condition number map is computed based on the gradient vectors for vessel removal, and then the candidate MAs are localized according to the second order directional derivatives computed in different directions. Due to the complexity of fundus image, besides a small number of true MAs, there are also a large amount of non-MAs in the extracted candidates. Classifying the true MAs and the non-MAs is an extremely class imbalanced classification problem. Therefore, in the second stage, several types of features including geometry, contrast, intensity, edge, texture, region descriptors and other features are extracted from the candidate MAs and a class imbalance classifier, i.e., RUSBoost, is trained for the MAs classification. With the Retinopathy Online Challenge (ROC) criterion, the proposed method achieves an average sensitivity of 0.433 at 1/8, 1/4, 1/2, 1, 2, 4 and 8 false positives per image on the ROC database, which is comparable with the state-of-the-art approaches, and 0.321 on the DiaRetDB1 V2.1 database, which outperforms the state-of-the-art approaches.

Describing three-class task performance: three-class linear discriminant analysis and three-class ROC analysis

Science.gov (United States)

He, Xin; Frey, Eric C.

2007-03-01

Binary ROC analysis has solid decision-theoretic foundations and a close relationship to linear discriminant analysis (LDA). In particular, for the case of Gaussian equal covariance input data, the area under the ROC curve (AUC) value has a direct relationship to the Hotelling trace. Many attempts have been made to extend binary classification methods to multi-class. For example, Fukunaga extended binary LDA to obtain multi-class LDA, which uses the multi-class Hotelling trace as a figure-of-merit, and we have previously developed a three-class ROC analysis method. This work explores the relationship between conventional multi-class LDA and three-class ROC analysis. First, we developed a linear observer, the three-class Hotelling observer (3-HO). For Gaussian equal covariance data, the 3- HO provides equivalent performance to the three-class ideal observer and, under less strict conditions, maximizes the signal to noise ratio for classification of all pairs of the three classes simultaneously. The 3-HO templates are not the eigenvectors obtained from multi-class LDA. Second, we show that the three-class Hotelling trace, which is the figureof- merit in the conventional three-class extension of LDA, has significant limitations. Third, we demonstrate that, under certain conditions, there is a linear relationship between the eigenvectors obtained from multi-class LDA and 3-HO templates. We conclude that the 3-HO based on decision theory has advantages both in its decision theoretic background and in the usefulness of its figure-of-merit. Additionally, there exists the possibility of interpreting the two linear features extracted by the conventional extension of LDA from a decision theoretic point of view.

Deteksi Penyakit Dengue Hemorrhagic Fever dengan Pendekatan One Class Classification

Directory of Open Access Journals (Sweden)

Zida Ziyan Azkiya

2017-10-01

Full Text Available Two class classification problem maps input into two target classes. In certain cases, training data is available only in the form of a single class, as in the case of Dengue Hemorrhagic Fever (DHF patients, where only data of positive patients is available. In this paper, we report our experiment in building a classification model for detecting DHF infection using One Class Classification (OCC approach. Data from this study is sourced from laboratory tests of patients with dengue fever. The OCC methods compared are One-Class Support Vector Machine and One-Class K-Means. The result shows SVM method obtained precision value = 1.0, recall = 0.993, f-1 score = 0.997, and accuracy of 99.7% while the K-Means method obtained precision value = 0.901, recall = 0.973, f- 1 score = 0.936, and accuracy of 93.3%. This indicates that the SVM method is slightly superior to K-Means for One-Class Classification of DHF patients.

Development and validation of a microRNA based diagnostic assay for primary tumor site classification of liver core biopsies

DEFF Research Database (Denmark)

Perell, Katharina; Vincent, Martin; Vainer, Ben

2015-01-01

for normal liver tissue contamination. Performance was estimated by cross-validation, followed by independent validation on 55 liver core biopsies with a tumor content as low as 10%. A microRNA classifier developed, using the statistical contamination model, showed an overall classification accuracy of 74...... on classification. MicroRNA profiling was performed using quantitative Real-Time PCR on formalin-fixed paraffin-embedded samples. 278 primary tumors and liver metastases, representing nine primary tumor classes, as well as normal liver samples were used as a training set. A statistical model was applied to adjust.......5% upon independent validation. Two-thirds of the samples were classified with high-confidence, with an accuracy of 92% on high-confidence predictions. A classifier trained without adjusting for liver tissue contamination, showed a classification accuracy of 38.2%. Our results indicate that surrounding...

Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification.

Science.gov (United States)

Taghanaki, Saeid Asgari; Kawahara, Jeremy; Miles, Brandon; Hamarneh, Ghassan

2017-07-01

Feature reduction is an essential stage in computer aided breast cancer diagnosis systems. Multilayer neural networks can be trained to extract relevant features by encoding high-dimensional data into low-dimensional codes. Optimizing traditional auto-encoders works well only if the initial weights are close to a proper solution. They are also trained to only reduce the mean squared reconstruction error (MRE) between the encoder inputs and the decoder outputs, but do not address the classification error. The goal of the current work is to test the hypothesis that extending traditional auto-encoders (which only minimize reconstruction error) to multi-objective optimization for finding Pareto-optimal solutions provides more discriminative features that will improve classification performance when compared to single-objective and other multi-objective approaches (i.e. scalarized and sequential). In this paper, we introduce a novel multi-objective optimization of deep auto-encoder networks, in which the auto-encoder optimizes two objectives: MRE and mean classification error (MCE) for Pareto-optimal solutions, rather than just MRE. These two objectives are optimized simultaneously by a non-dominated sorting genetic algorithm. We tested our method on 949 X-ray mammograms categorized into 12 classes. The results show that the features identified by the proposed algorithm allow a classification accuracy of up to 98.45%, demonstrating favourable accuracy over the results of state-of-the-art methods reported in the literature. We conclude that adding the classification objective to the traditional auto-encoder objective and optimizing for finding Pareto-optimal solutions, using evolutionary multi-objective optimization, results in producing more discriminative features. Copyright © 2017 Elsevier B.V. All rights reserved.

Welcoming the new WHO classification of pituitary tumors 2017: revolution in TTF-1-positive posterior pituitary tumors.

Science.gov (United States)

Shibuya, Makoto

2018-04-01

The fourth edition of the World Health Organization classification of endocrine tumors (EN-WHO2017) was released in 2017. In this new edition, changes in the classification of non-neuroendocrine tumors are proposed particularly in tumors arising in the posterior pituitary. These tumors are a distinct group of low-grade neoplasms of the sellar region that express thyroid transcription factor-1, and include pituicytoma, granular cell tumor of the sellar region, spindle cell oncocytoma, and sellar ependymoma. This short review focuses on the classification of posterior pituitary tumors newly proposed in EN-WHO2017, and controversies in their pathological differential diagnosis are discussed based on recent cases.

Clinical and molecular sub-classification of hepatocellular carcinoma relative to alpha-fetoprotein level in an Asia-Pacific island cohort.

Science.gov (United States)

Nishioka, Scott T; Sato, Miles M; Wong, Linda L; Tiirikainen, Maarit; Kwee, Sandi A

2018-01-01

Increased serum alpha-fetoprotein (AFP) levels are associated with specific molecular sub-classes of hepatocellular carcinoma (HCC), supporting AFP as a predictive or therapeutic biomarker for precision treatment of this disease. Considering recent efforts to validate HCC molecular classification systems across different populations, we applied existing signature-based classification templates to Hawaii cohorts and examined whether associations between HCC molecular sub-class, AFP levels, and clinical features found elsewhere can also be found in Hawaii, a region with a unique demographic and risk factor profile for HCC. Whole-genome expression profiling was performed on HCC tumors collected from 40 patients following partial hepatectomy. Tumors underwent transcriptome-based categorization into 3 molecular sub-classes (S1, S2, and S3). Patient groups based on molecular sub-class and AFP level were then compared with regards to clinical features and survival. Differences associated with AFP level and other clinical parameters were also examined at the gene signature level by gene set enrichment analysis. Statistically confident (false discovery rate 400 ng/mL predicted significant tumor enrichment for genes corresponding to MYC target activation, high cell proliferation, poor clinical prognosis, and the S2 sub-class. AFP > 400 ng/mL and non-S3 tumor classification were found to be significant predictors of overall survival. Distinct sub-classes of HCC associated with different molecular features and survival outcomes can be detected with statistical confidence in a Pacific Island cohort. Molecular classification signatures and other predictive markers for HCC that are valid for all patient populations are needed to support multi-center efforts to develop targeted therapies for HCC.

WHO/ISUP classification of the urothelial tumors of the urinary bladder

Directory of Open Access Journals (Sweden)

Zdenka Ovčak

2005-09-01

Full Text Available Background: The authors present the current classification of urothelial neoplasms of the urinary bladder. The classification of urothelial tumors of the urinary bladder of 1973 was despite some imperfection relatively successfuly used for more than thirty years. The three grade classification of papillary urothelial tumors without invasion has been based on evaluation of variations in architecture of covering epithelium and tumor cell anaplasia. As reccomended by the International Society of Urological Pathologists (ISUP, the World Health Organisation (WHO accepted the new WHO/ ISUP classification in 1998 that was revised in 2002 and finally published in 2004. With intention to avoid unnecessary diagnosis of cancer in patients having papillary urothelial tumors with rare invasive or metastastatic growth, this classification introduced a new entity, the papillary urothelial neoplasia of low malignant potential (PUNLMP. The additional change in classification was the division of invasive urothelial neoplasms only to low and high grade urothelial carcinomas.Conclusions: The authors’ opinion is that although the old classification is not recommended for use anymore the new one is not solving the elementary reproaches to previous classification such as terminological unsuitability and insufficient scientific reasoning. Our proposed solution in classification of papillary urothelial neoplasms would be the application of criteria analogous to that used in diagnostics of papillary noninvasive tumors of the head and neck or alimentary tract.

MULTI-TEMPORAL REMOTE SENSING IMAGE CLASSIFICATION - A MULTI-VIEW APPROACH

Data.gov (United States)

National Aeronautics and Space Administration — MULTI-TEMPORAL REMOTE SENSING IMAGE CLASSIFICATION - A MULTI-VIEW APPROACH VARUN CHANDOLA AND RANGA RAJU VATSAVAI Abstract. Multispectral remote sensing images have...

Deep Multi-Task Learning for Tree Genera Classification

Science.gov (United States)

Ko, C.; Kang, J.; Sohn, G.

2018-05-01

The goal for our paper is to classify tree genera using airborne Light Detection and Ranging (LiDAR) data with Convolution Neural Network (CNN) - Multi-task Network (MTN) implementation. Unlike Single-task Network (STN) where only one task is assigned to the learning outcome, MTN is a deep learning architect for learning a main task (classification of tree genera) with other tasks (in our study, classification of coniferous and deciduous) simultaneously, with shared classification features. The main contribution of this paper is to improve classification accuracy from CNN-STN to CNN-MTN. This is achieved by introducing a concurrence loss (Lcd) to the designed MTN. This term regulates the overall network performance by minimizing the inconsistencies between the two tasks. Results show that we can increase the classification accuracy from 88.7 % to 91.0 % (from STN to MTN). The second goal of this paper is to solve the problem of small training sample size by multiple-view data generation. The motivation of this goal is to address one of the most common problems in implementing deep learning architecture, the insufficient number of training data. We address this problem by simulating training dataset with multiple-view approach. The promising results from this paper are providing a basis for classifying a larger number of dataset and number of classes in the future.

A novel Multi-Agent Ada-Boost algorithm for predicting protein structural class with the information of protein secondary structure.

Science.gov (United States)

Fan, Ming; Zheng, Bin; Li, Lihua

2015-10-01

Knowledge of the structural class of a given protein is important for understanding its folding patterns. Although a lot of efforts have been made, it still remains a challenging problem for prediction of protein structural class solely from protein sequences. The feature extraction and classification of proteins are the main problems in prediction. In this research, we extended our earlier work regarding these two aspects. In protein feature extraction, we proposed a scheme by calculating the word frequency and word position from sequences of amino acid, reduced amino acid, and secondary structure. For an accurate classification of the structural class of protein, we developed a novel Multi-Agent Ada-Boost (MA-Ada) method by integrating the features of Multi-Agent system into Ada-Boost algorithm. Extensive experiments were taken to test and compare the proposed method using four benchmark datasets in low homology. The results showed classification accuracies of 88.5%, 96.0%, 88.4%, and 85.5%, respectively, which are much better compared with the existing methods. The source code and dataset are available on request.

Learning to recognise : A study on one-class classification and active learning

NARCIS (Netherlands)

Juszczak, P.

2006-01-01

The thesis treats classification problems which are undersampled or where there exist an unbalance between classes in the sampling. The thesis is divided into three parts. The first two parts treat the problem of one-class classification. In the one-class classification problem, it is assumed that

Using multi-beam echo sounder backscatter data for sediment classification in very shallow water environments

NARCIS (Netherlands)

Amiri-Simkooei, A.R.; Snellen, M.; Simons, D.G.

2009-01-01

In a recent work described in Ref. [1], an angle-independent methodology was developed to use the multi-beam echo sounder backscatter (MBES) data for the seabed sediment classification. The method employs the backscatter data at a certain angle to obtain the number of sediment classes and to

Multi-label literature classification based on the Gene Ontology graph

Directory of Open Access Journals (Sweden)

Lu Xinghua

2008-12-01

Full Text Available Abstract Background The Gene Ontology is a controlled vocabulary for representing knowledge related to genes and proteins in a computable form. The current effort of manually annotating proteins with the Gene Ontology is outpaced by the rate of accumulation of biomedical knowledge in literature, which urges the development of text mining approaches to facilitate the process by automatically extracting the Gene Ontology annotation from literature. The task is usually cast as a text classification problem, and contemporary methods are confronted with unbalanced training data and the difficulties associated with multi-label classification. Results In this research, we investigated the methods of enhancing automatic multi-label classification of biomedical literature by utilizing the structure of the Gene Ontology graph. We have studied three graph-based multi-label classification algorithms, including a novel stochastic algorithm and two top-down hierarchical classification methods for multi-label literature classification. We systematically evaluated and compared these graph-based classification algorithms to a conventional flat multi-label algorithm. The results indicate that, through utilizing the information from the structure of the Gene Ontology graph, the graph-based multi-label classification methods can significantly improve predictions of the Gene Ontology terms implied by the analyzed text. Furthermore, the graph-based multi-label classifiers are capable of suggesting Gene Ontology annotations (to curators that are closely related to the true annotations even if they fail to predict the true ones directly. A software package implementing the studied algorithms is available for the research community. Conclusion Through utilizing the information from the structure of the Gene Ontology graph, the graph-based multi-label classification methods have better potential than the conventional flat multi-label classification approach to facilitate

Multi-class geospatial object detection based on a position-sensitive balancing framework for high spatial resolution remote sensing imagery

Science.gov (United States)

Zhong, Yanfei; Han, Xiaobing; Zhang, Liangpei

2018-04-01

Multi-class geospatial object detection from high spatial resolution (HSR) remote sensing imagery is attracting increasing attention in a wide range of object-related civil and engineering applications. However, the distribution of objects in HSR remote sensing imagery is location-variable and complicated, and how to accurately detect the objects in HSR remote sensing imagery is a critical problem. Due to the powerful feature extraction and representation capability of deep learning, the deep learning based region proposal generation and object detection integrated framework has greatly promoted the performance of multi-class geospatial object detection for HSR remote sensing imagery. However, due to the translation caused by the convolution operation in the convolutional neural network (CNN), although the performance of the classification stage is seldom influenced, the localization accuracies of the predicted bounding boxes in the detection stage are easily influenced. The dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage has not been addressed for HSR remote sensing imagery, and causes position accuracy problems for multi-class geospatial object detection with region proposal generation and object detection. In order to further improve the performance of the region proposal generation and object detection integrated framework for HSR remote sensing imagery object detection, a position-sensitive balancing (PSB) framework is proposed in this paper for multi-class geospatial object detection from HSR remote sensing imagery. The proposed PSB framework takes full advantage of the fully convolutional network (FCN), on the basis of a residual network, and adopts the PSB framework to solve the dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage. In addition, a pre-training mechanism is utilized to accelerate the training procedure

Multi-angle backscatter classification and sub-bottom profiling for improved seafloor characterization

Science.gov (United States)

Alevizos, Evangelos; Snellen, Mirjam; Simons, Dick; Siemes, Kerstin; Greinert, Jens

2018-06-01

This study applies three classification methods exploiting the angular dependence of acoustic seafloor backscatter along with high resolution sub-bottom profiling for seafloor sediment characterization in the Eckernförde Bay, Baltic Sea Germany. This area is well suited for acoustic backscatter studies due to its shallowness, its smooth bathymetry and the presence of a wide range of sediment types. Backscatter data were acquired using a Seabeam1180 (180 kHz) multibeam echosounder and sub-bottom profiler data were recorded using a SES-2000 parametric sonar transmitting 6 and 12 kHz. The high density of seafloor soundings allowed extracting backscatter layers for five beam angles over a large part of the surveyed area. A Bayesian probability method was employed for sediment classification based on the backscatter variability at a single incidence angle, whereas Maximum Likelihood Classification (MLC) and Principal Components Analysis (PCA) were applied to the multi-angle layers. The Bayesian approach was used for identifying the optimum number of acoustic classes because cluster validation is carried out prior to class assignment and class outputs are ordinal categorical values. The method is based on the principle that backscatter values from a single incidence angle express a normal distribution for a particular sediment type. The resulting Bayesian classes were well correlated to median grain sizes and the percentage of coarse material. The MLC method uses angular response information from five layers of training areas extracted from the Bayesian classification map. The subsequent PCA analysis is based on the transformation of these five layers into two principal components that comprise most of the data variability. These principal components were clustered in five classes after running an external cluster validation test. In general both methods MLC and PCA, separated the various sediment types effectively, showing good agreement (kappa >0.7) with the Bayesian

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.; Bensmail, H.; Yao, N.; Gao, Xin

2013-01-01

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.

2013-09-26

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

CLASS-PAIR-GUIDED MULTIPLE KERNEL LEARNING OF INTEGRATING HETEROGENEOUS FEATURES FOR CLASSIFICATION

Directory of Open Access Journals (Sweden)

Q. Wang

2017-10-01

Full Text Available In recent years, many studies on remote sensing image classification have shown that using multiple features from different data sources can effectively improve the classification accuracy. As a very powerful means of learning, multiple kernel learning (MKL can conveniently be embedded in a variety of characteristics. The conventional combined kernel learned by MKL can be regarded as the compromise of all basic kernels for all classes in classification. It is the best of the whole, but not optimal for each specific class. For this problem, this paper proposes a class-pair-guided MKL method to integrate the heterogeneous features (HFs from multispectral image (MSI and light detection and ranging (LiDAR data. In particular, the one-against-one strategy is adopted, which converts multiclass classification problem to a plurality of two-class classification problem. Then, we select the best kernel from pre-constructed basic kernels set for each class-pair by kernel alignment (KA in the process of classification. The advantage of the proposed method is that only the best kernel for the classification of any two classes can be retained, which leads to greatly enhanced discriminability. Experiments are conducted on two real data sets, and the experimental results show that the proposed method achieves the best performance in terms of classification accuracies in integrating the HFs for classification when compared with several state-of-the-art algorithms.

Fuzzy Continuous Review Inventory Model using ABC Multi-Criteria Classification Approach: A Single Case Study

Directory of Open Access Journals (Sweden)

Meriastuti - Ginting

2015-07-01

Full Text Available Abstract. Inventory is considered as the most expensive, yet important,to any companies. It representsapproximately 50% of the total investment. Inventory cost has become one of the majorcontributorsto inefficiency, therefore it should be managed effectively. This study aims to propose an alternative inventory model,  by using ABC multi-criteria classification approach to minimize total cost. By combining FANP (Fuzzy Analytical Network Process and TOPSIS (Technique of Order Preferences by Similarity to the Ideal Solution, the ABC multi-criteria classification approach identified 12 items of 69 inventory items as “outstanding important class” that contributed to 80% total inventory cost. This finding  is then used as the basis to determine the proposed continuous review inventory model.This study found that by using fuzzy trapezoidal cost, the inventory  turnover ratio can be increased, and inventory cost can be decreased by 78% for each item in “class A” inventory.Keywords:ABC multi-criteria classification, FANP-TOPSIS, continuous review inventory model lead-time demand distribution, trapezoidal fuzzy number 

Deep learning for tumor classification in imaging mass spectrometry.

Science.gov (United States)

Behrmann, Jens; Etmann, Christian; Boskamp, Tobias; Casadonte, Rita; Kriegsmann, Jörg; Maaß, Peter

2018-04-01

Tumor classification using imaging mass spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Since mass spectra exhibit certain structural similarities to image data, deep learning may offer a promising strategy for classification of IMS data as it has been successfully applied to image classification. Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two algorithmically challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods is shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered tasks. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks. https://gitlab.informatik.uni-bremen.de/digipath/Deep_Learning_for_Tumor_Classification_in_IMS. jbehrmann@uni-bremen.de or christianetmann@uni-bremen.de. Supplementary data are available at Bioinformatics online.

The 2017 World Health Organization classification of tumors of the pituitary gland: a summary.

Science.gov (United States)

Lopes, M Beatriz S

2017-10-01

The 4th edition of the World Health Organization (WHO) classification of endocrine tumors has been recently released. In this new edition, major changes are recommended in several areas of the classification of tumors of the anterior pituitary gland (adenophypophysis). The scope of the present manuscript is to summarize these recommended changes, emphasizing a few significant topics. These changes include the following: (1) a novel approach for classifying pituitary neuroendocrine tumors according to pituitary adenohypophyseal cell lineages; (2) changes to the histological grading of pituitary neuroendocrine tumors with the elimination of the term "atypical adenoma;" and (3) introduction of new entities like the pituitary blastoma and re-definition of old entities like the null-cell adenoma. This new classification is very practical and mostly based on immunohistochemistry for pituitary hormones, pituitary-specific transcription factors, and other immunohistochemical markers commonly used in pathology practice, not requiring routine ultrastructural analysis of the tumors. Evaluation of tumor proliferation potential, by mitotic count and Ki-67 labeling index, and tumor invasion is strongly recommended on individual case basis to identify clinically aggressive adenomas. In addition, the classification offers the treating clinical team information on tumor prognosis by identifying specific variants of adenomas associated with an elevated risk for recurrence. Changes in the classification of non-neuroendocrine tumors are also proposed, in particular those tumors arising in the posterior pituitary including pituicytoma, granular cell tumor of the posterior pituitary, and spindle cell oncocytoma. These changes endorse those previously published in the 2016 WHO classification of CNS tumors. Other tumors arising in the sellar region are also reviewed in detail including craniopharyngiomas, mesenchymal and stromal tumors, germ cell tumors, and hematopoietic tumors. It is

A scalable pairwise class interaction framework for multidimensional classification

DEFF Research Database (Denmark)

Arias, Jacinto; Gámez, Jose A.; Nielsen, Thomas Dyhre

2016-01-01

We present a general framework for multidimensional classification that cap- tures the pairwise interactions between class variables. The pairwise class inter- actions are encoded using a collection of base classifiers (Phase 1), for which the class predictions are combined in a Markov random fie...

Quantitative ultrasound assessment of breast tumor response to chemotherapy using a multi-parameter approach.

Science.gov (United States)

Tadayyon, Hadi; Sannachi, Lakshmanan; Gangeh, Mehrdad; Sadeghi-Naini, Ali; Tran, William; Trudeau, Maureen E; Pritchard, Kathleen; Ghandi, Sonal; Verma, Sunil; Czarnota, Gregory J

2016-07-19

This study demonstrated the ability of quantitative ultrasound (QUS) parameters in providing an early prediction of tumor response to neoadjuvant chemotherapy (NAC) in patients with locally advanced breast cancer (LABC). Using a 6-MHz array transducer, ultrasound radiofrequency (RF) data were collected from 58 LABC patients prior to NAC treatment and at weeks 1, 4, and 8 of their treatment, and prior to surgery. QUS parameters including midband fit (MBF), spectral slope (SS), spectral intercept (SI), spacing among scatterers (SAS), attenuation coefficient estimate (ACE), average scatterer diameter (ASD), and average acoustic concentration (AAC) were determined from the tumor region of interest. Ultrasound data were compared with the ultimate clinical and pathological response of the patient's tumor to treatment and patient recurrence-free survival. Multi-parameter discriminant analysis using the κ-nearest-neighbor classifier demonstrated that the best response classification could be achieved using the combination of MBF, SS, and SAS, with an accuracy of 60 ± 10% at week 1, 77 ± 8% at week 4 and 75 ± 6% at week 8. Furthermore, when the QUS measurements at each time (week) were combined with pre-treatment (week 0) QUS values, the classification accuracies improved (70 ± 9% at week 1, 80 ± 5% at week 4, and 81 ± 6% at week 8). Finally, the multi-parameter QUS model demonstrated a significant difference in survival rates of responding and non-responding patients at weeks 1 and 4 (p=0.035, and 0.027, respectively). This study demonstrated for the first time, using new parameters tested on relatively large patient cohort and leave-one-out classifier evaluation, that a hybrid QUS biomarker including MBF, SS, and SAS could, with relatively high sensitivity and specificity, detect the response of LABC tumors to NAC as early as after 4 weeks of therapy. The findings of this study also suggested that incorporating pre-treatment QUS parameters of a tumor improved the

Classification and Compression of Multi-Resolution Vectors: A Tree Structured Vector Quantizer Approach

Science.gov (United States)

2002-01-01

their expression profile and for classification of cells into tumerous and non- tumerous classes. Then we will present a parallel tree method for... cancerous cells. We will use the same dataset and use tree structured classifiers with multi-resolution analysis for classifying cancerous from non- cancerous ...cells. We have the expressions of 4096 genes from 98 different cell types. Of these 98, 72 are cancerous while 26 are non- cancerous . We are interested

The new WHO 2016 classification of brain tumors-what neurosurgeons need to know.

Science.gov (United States)

Banan, Rouzbeh; Hartmann, Christian

2017-03-01

The understanding of molecular alterations of tumors has severely changed the concept of classification in all fields of pathology. The availability of high-throughput technologies such as next-generation sequencing allows for a much more precise definition of tumor entities. Also in the field of brain tumors a dramatic increase of knowledge has occurred over the last years partially calling into question the purely morphologically based concepts that were used as exclusive defining criteria in the WHO 2007 classification. Review of the WHO 2016 classification of brain tumors as well as a search and review of publications in the literature relevant for brain tumor classification from 2007 up to now. The idea of incorporating the molecular features in classifying tumors of the central nervous system led the authors of the new WHO 2016 classification to encounter inevitable conceptual problems, particularly with respect to linking morphology to molecular alterations. As a solution they introduced the concept of a "layered diagnosis" to the classification of brain tumors that still allows at a lower level a purely morphologically based diagnosis while partially forcing the incorporation of molecular characteristics for an "integrated diagnosis" at the highest diagnostic level. In this context the broad availability of molecular assays was debated. On the one hand molecular antibodies specifically targeting mutated proteins should be available in nearly all neuropathological laboratories. On the other hand, different high-throughput assays are accessible only in few first-world neuropathological institutions. As examples oligodendrogliomas are now primarily defined by molecular characteristics since the required assays are generally established, whereas molecular grouping of ependymomas, found to clearly outperform morphologically based tumor interpretation, was rejected from inclusion in the WHO 2016 classification because the required assays are currently only

Texture-based classification of different gastric tumors at contrast-enhanced CT

Energy Technology Data Exchange (ETDEWEB)

Ba-Ssalamah, Ahmed, E-mail: ahmed.ba-ssalamah@meduniwien.ac.at [Department of Radiology, Medical University of Vienna (Austria); Muin, Dina; Schernthaner, Ruediger; Kulinna-Cosentini, Christiana; Bastati, Nina [Department of Radiology, Medical University of Vienna (Austria); Stift, Judith [Department of Pathology, Medical University of Vienna (Austria); Gore, Richard [Department of Radiology, University of Chicago Pritzker School of Medicine, Chicago, IL (United States); Mayerhoefer, Marius E. [Department of Radiology, Medical University of Vienna (Austria)

2013-10-01

Purpose: To determine the feasibility of texture analysis for the classification of gastric adenocarcinoma, lymphoma, and gastrointestinal stromal tumors on contrast-enhanced hydrodynamic-MDCT images. Materials and methods: The arterial phase scans of 47 patients with adenocarcinoma (AC) and a histologic tumor grade of [AC-G1, n = 4, G1, n = 4; AC-G2, n = 7; AC-G3, n = 16]; GIST, n = 15; and lymphoma, n = 5, and the venous phase scans of 48 patients with AC-G1, n = 3; AC-G2, n = 6; AC-G3, n = 14; GIST, n = 17; lymphoma, n = 8, were retrospectively reviewed. Based on regions of interest, texture analysis was performed, and features derived from the gray-level histogram, run-length and co-occurrence matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher coefficients, probability of classification error, average correlation coefficients, and mutual information coefficients were used to create combinations of texture features that were optimized for tumor differentiation. Linear discriminant analysis in combination with a k-nearest neighbor classifier was used for tumor classification. Results: On arterial-phase scans, texture-based lesion classification was highly successful in differentiating between AC and lymphoma, and GIST and lymphoma, with misclassification rates of 3.1% and 0%, respectively. On venous-phase scans, texture-based classification was slightly less successful for AC vs. lymphoma (9.7% misclassification) and GIST vs. lymphoma (8% misclassification), but enabled the differentiation between AC and GIST (10% misclassification), and between the different grades of AC (4.4% misclassification). No texture feature combination was able to adequately distinguish between all three tumor types. Conclusion: Classification of different gastric tumors based on textural information may aid radiologists in establishing the correct diagnosis, at least in cases where the differential diagnosis can be narrowed down to two

Texture-based classification of different gastric tumors at contrast-enhanced CT

International Nuclear Information System (INIS)

Ba-Ssalamah, Ahmed; Muin, Dina; Schernthaner, Ruediger; Kulinna-Cosentini, Christiana; Bastati, Nina; Stift, Judith; Gore, Richard; Mayerhoefer, Marius E.

2013-01-01

Purpose: To determine the feasibility of texture analysis for the classification of gastric adenocarcinoma, lymphoma, and gastrointestinal stromal tumors on contrast-enhanced hydrodynamic-MDCT images. Materials and methods: The arterial phase scans of 47 patients with adenocarcinoma (AC) and a histologic tumor grade of [AC-G1, n = 4, G1, n = 4; AC-G2, n = 7; AC-G3, n = 16]; GIST, n = 15; and lymphoma, n = 5, and the venous phase scans of 48 patients with AC-G1, n = 3; AC-G2, n = 6; AC-G3, n = 14; GIST, n = 17; lymphoma, n = 8, were retrospectively reviewed. Based on regions of interest, texture analysis was performed, and features derived from the gray-level histogram, run-length and co-occurrence matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher coefficients, probability of classification error, average correlation coefficients, and mutual information coefficients were used to create combinations of texture features that were optimized for tumor differentiation. Linear discriminant analysis in combination with a k-nearest neighbor classifier was used for tumor classification. Results: On arterial-phase scans, texture-based lesion classification was highly successful in differentiating between AC and lymphoma, and GIST and lymphoma, with misclassification rates of 3.1% and 0%, respectively. On venous-phase scans, texture-based classification was slightly less successful for AC vs. lymphoma (9.7% misclassification) and GIST vs. lymphoma (8% misclassification), but enabled the differentiation between AC and GIST (10% misclassification), and between the different grades of AC (4.4% misclassification). No texture feature combination was able to adequately distinguish between all three tumor types. Conclusion: Classification of different gastric tumors based on textural information may aid radiologists in establishing the correct diagnosis, at least in cases where the differential diagnosis can be narrowed down to two

A uniform residual tumor (R) classification: integration of the R classification and the circumferential margin status.

NARCIS (Netherlands)

Wittekind, C.; Compton, C.; Quirke, P.; Nagtegaal, I.D.; Merkel, S.; Hermanek, P.; Sobin, L.H.

2009-01-01

BACKGROUND: Since the introduction of the TNM residual tumor (R) classification, the involvement of resection margins has been defined either as a microscopic (R1) or a macroscopic (R2) demonstration of tumor directly at the resection margin ("tumor transected"). METHODS: The recognition of the

The 2015 World Health Organization Classification of Lung Tumors: Impact of Genetic, Clinical and Radiologic Advances Since the 2004 Classification.

Science.gov (United States)

Travis, William D; Brambilla, Elisabeth; Nicholson, Andrew G; Yatabe, Yasushi; Austin, John H M; Beasley, Mary Beth; Chirieac, Lucian R; Dacic, Sanja; Duhig, Edwina; Flieder, Douglas B; Geisinger, Kim; Hirsch, Fred R; Ishikawa, Yuichi; Kerr, Keith M; Noguchi, Masayuki; Pelosi, Giuseppe; Powell, Charles A; Tsao, Ming Sound; Wistuba, Ignacio

2015-09-01

The 2015 World Health Organization (WHO) Classification of Tumors of the Lung, Pleura, Thymus and Heart has just been published with numerous important changes from the 2004 WHO classification. The most significant changes in this edition involve (1) use of immunohistochemistry throughout the classification, (2) a new emphasis on genetic studies, in particular, integration of molecular testing to help personalize treatment strategies for advanced lung cancer patients, (3) a new classification for small biopsies and cytology similar to that proposed in the 2011 Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society classification, (4) a completely different approach to lung adenocarcinoma as proposed by the 2011 Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society classification, (5) restricting the diagnosis of large cell carcinoma only to resected tumors that lack any clear morphologic or immunohistochemical differentiation with reclassification of the remaining former large cell carcinoma subtypes into different categories, (6) reclassifying squamous cell carcinomas into keratinizing, nonkeratinizing, and basaloid subtypes with the nonkeratinizing tumors requiring immunohistochemistry proof of squamous differentiation, (7) grouping of neuroendocrine tumors together in one category, (8) adding NUT carcinoma, (9) changing the term sclerosing hemangioma to sclerosing pneumocytoma, (10) changing the name hamartoma to "pulmonary hamartoma," (11) creating a group of PEComatous tumors that include (a) lymphangioleiomyomatosis, (b) PEComa, benign (with clear cell tumor as a variant) and (c) PEComa, malignant, (12) introducing the entity pulmonary myxoid sarcoma with an EWSR1-CREB1 translocation, (13) adding the entities myoepithelioma and myoepithelial carcinomas, which can show EWSR1 gene rearrangements, (14) recognition of usefulness of WWTR1-CAMTA1 fusions in diagnosis of epithelioid

A Multi-layer Hybrid Framework for Dimensional Emotion Classification

NARCIS (Netherlands)

Nicolaou, Mihalis A.; Gunes, Hatice; Pantic, Maja

2011-01-01

This paper investigates dimensional emotion prediction and classification from naturalistic facial expressions. Similarly to many pattern recognition problems, dimensional emotion classification requires generating multi-dimensional outputs. To date, classification for valence and arousal dimensions

Angular difference feature extraction for urban scene classification using ZY-3 multi-angle high-resolution satellite imagery

Science.gov (United States)

Huang, Xin; Chen, Huijun; Gong, Jianya

2018-01-01

Spaceborne multi-angle images with a high-resolution are capable of simultaneously providing spatial details and three-dimensional (3D) information to support detailed and accurate classification of complex urban scenes. In recent years, satellite-derived digital surface models (DSMs) have been increasingly utilized to provide height information to complement spectral properties for urban classification. However, in such a way, the multi-angle information is not effectively exploited, which is mainly due to the errors and difficulties of the multi-view image matching and the inaccuracy of the generated DSM over complex and dense urban scenes. Therefore, it is still a challenging task to effectively exploit the available angular information from high-resolution multi-angle images. In this paper, we investigate the potential for classifying urban scenes based on local angular properties characterized from high-resolution ZY-3 multi-view images. Specifically, three categories of angular difference features (ADFs) are proposed to describe the angular information at three levels (i.e., pixel, feature, and label levels): (1) ADF-pixel: the angular information is directly extrapolated by pixel comparison between the multi-angle images; (2) ADF-feature: the angular differences are described in the feature domains by comparing the differences between the multi-angle spatial features (e.g., morphological attribute profiles (APs)). (3) ADF-label: label-level angular features are proposed based on a group of urban primitives (e.g., buildings and shadows), in order to describe the specific angular information related to the types of primitive classes. In addition, we utilize spatial-contextual information to refine the multi-level ADF features using superpixel segmentation, for the purpose of alleviating the effects of salt-and-pepper noise and representing the main angular characteristics within a local area. The experiments on ZY-3 multi-angle images confirm that the proposed

Modern classification of neoplasms: reconciling differences between morphologic and molecular approaches

International Nuclear Information System (INIS)

Berman, Jules

2005-01-01

classification of neoplasms should guide the rational design and selection of a new generation of cancer medications targeted to metabolic pathways. Without a scientifically sound neoplasm classification, biological measurements on individual tumor samples cannot be generalized to class-related tumors, and constitutive properties common to a class of tumors cannot be distinguished from uninformative data in complex and chaotic biological systems. This paper discusses the importance of biological classification and examines several different approaches to the specific problem of tumor classification

A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images.

Science.gov (United States)

Guo, Le-Hang; Wang, Dan; Qian, Yi-Yi; Zheng, Xiao; Zhao, Chong-Ke; Li, Xiao-Long; Bo, Xiao-Wan; Yue, Wen-Wen; Zhang, Qi; Shi, Jun; Xu, Hui-Xiong

2018-04-04

With the fast development of artificial intelligence techniques, we proposed a novel two-stage multi-view learning framework for the contrast-enhanced ultrasound (CEUS) based computer-aided diagnosis for liver tumors, which adopted only three typical CEUS images selected from the arterial phase, portal venous phase and late phase. In the first stage, the deep canonical correlation analysis (DCCA) was performed on three image pairs between the arterial and portal venous phases, arterial and delayed phases, and portal venous and delayed phases respectively, which then generated total six-view features. While in the second stage, these multi-view features were then fed to a multiple kernel learning (MKL) based classifier to further promote the diagnosis result. Two MKL classification algorithms were evaluated in this MKL-based classification framework. We evaluated proposed DCCA-MKL framework on 93 lesions (47 malignant cancers vs. 46 benign tumors). The proposed DCCA-MKL framework achieved the mean classification accuracy, sensitivity, specificity, Youden index, false positive rate, and false negative rate of 90.41 ± 5.80%, 93.56 ± 5.90%, 86.89 ± 9.38%, 79.44 ± 11.83%, 13.11 ± 9.38% and 6.44 ± 5.90%, respectively, by soft margin MKL classifier. The experimental results indicate that the proposed DCCA-MKL framework achieves best performance for discriminating benign liver tumors from malignant liver cancers. Moreover, it is also proved that the three-phase CEUS image based CAD is feasible for liver tumors with the proposed DCCA-MKL framework.

Multi-Agent Information Classification Using Dynamic Acquaintance Lists.

Science.gov (United States)

Mukhopadhyay, Snehasis; Peng, Shengquan; Raje, Rajeev; Palakal, Mathew; Mostafa, Javed

2003-01-01

Discussion of automated information services focuses on information classification and collaborative agents, i.e. intelligent computer programs. Highlights include multi-agent systems; distributed artificial intelligence; thesauri; document representation and classification; agent modeling; acquaintances, or remote agents discovered through…

3D terrestrial lidar data classification of complex natural scenes using a multi-scale dimensionality criterion: Applications in geomorphology

Science.gov (United States)

Brodu, N.; Lague, D.

2012-03-01

3D point clouds of natural environments relevant to problems in geomorphology (rivers, coastal environments, cliffs, …) often require classification of the data into elementary relevant classes. A typical example is the separation of riparian vegetation from ground in fluvial environments, the distinction between fresh surfaces and rockfall in cliff environments, or more generally the classification of surfaces according to their morphology (e.g. the presence of bedforms or by grain size). Natural surfaces are heterogeneous and their distinctive properties are seldom defined at a unique scale, prompting the use of multi-scale criteria to achieve a high degree of classification success. We have thus defined a multi-scale measure of the point cloud dimensionality around each point. The dimensionality characterizes the local 3D organization of the point cloud within spheres centered on the measured points and varies from being 1D (points set along a line), 2D (points forming a plane) to the full 3D volume. By varying the diameter of the sphere, we can thus monitor how the local cloud geometry behaves across scales. We present the technique and illustrate its efficiency in separating riparian vegetation from ground and classifying a mountain stream as vegetation, rock, gravel or water surface. In these two cases, separating the vegetation from ground or other classes achieve accuracy larger than 98%. Comparison with a single scale approach shows the superiority of the multi-scale analysis in enhancing class separability and spatial resolution of the classification. Scenes between 10 and one hundred million points can be classified on a common laptop in a reasonable time. The technique is robust to missing data, shadow zones and changes in point density within the scene. The classification is fast and accurate and can account for some degree of intra-class morphological variability such as different vegetation types. A probabilistic confidence in the classification

Tumor Classification Using High-Order Gene Expression Profiles Based on Multilinear ICA

Directory of Open Access Journals (Sweden)

Ming-gang Du

2009-01-01

Full Text Available Motivation. Independent Components Analysis (ICA maximizes the statistical independence of the representational components of a training gene expression profiles (GEP ensemble, but it cannot distinguish relations between the different factors, or different modes, and it is not available to high-order GEP Data Mining. In order to generalize ICA, we introduce Multilinear-ICA and apply it to tumor classification using high order GEP. Firstly, we introduce the basis conceptions and operations of tensor and recommend Support Vector Machine (SVM classifier and Multilinear-ICA. Secondly, the higher score genes of original high order GEP are selected by using t-statistics and tabulate tensors. Thirdly, the tensors are performed by Multilinear-ICA. Finally, the SVM is used to classify the tumor subtypes. Results. To show the validity of the proposed method, we apply it to tumor classification using high order GEP. Though we only use three datasets, the experimental results show that the method is effective and feasible. Through this survey, we hope to gain some insight into the problem of high order GEP tumor classification, in aid of further developing more effective tumor classification algorithms.

Sound classification schemes in Europe - Quality classes intended for renovated housing

DEFF Research Database (Denmark)

Rasmussen, Birgit

2010-01-01

exposure in the home included in the proposed main objectives for a housing policy. In most countries in Europe, building regulations specify minimum requirements concerning acoustical conditions for new dwellings. In addition, several countries have introduced sound classification schemes with classes...... intended to reflect different levels of acoustical comfort. Consequently, acoustic requirements for a dwelling can be specified as the legal minimum requirements or as a specific class in a classification scheme. Most schemes have both higher classes than corresponding to the regulatory requirements...

Border Lakes land-cover classification

Science.gov (United States)

Marvin Bauer; Brian Loeffelholz; Doug. Shinneman

2009-01-01

This document contains metadata and description of land-cover classification of approximately 5.1 million acres of land bordering Minnesota, U.S.A. and Ontario, Canada. The classification focused on the separation and identification of specific forest-cover types. Some separation of the nonforest classes also was performed. The classification was derived from multi-...

Project Based Learning in Multi-Grade Class

Science.gov (United States)

Ciftci, Sabahattin; Baykan, Ayse Aysun

2013-01-01

The purpose of this study is to evaluate project based learning in multi-grade classes. This study, based on a student-centered learning approach, aims to analyze students' and parents' interpretations. The study was done in a primary village school belonging to the Centre of Batman, already adapting multi-grade classes in their education system,…

Multi-Class Motor Imagery EEG Decoding for Brain-Computer Interfaces

Science.gov (United States)

Wang, Deng; Miao, Duoqian; Blohm, Gunnar

2012-01-01

Recent studies show that scalp electroencephalography (EEG) as a non-invasive interface has great potential for brain-computer interfaces (BCIs). However, one factor that has limited practical applications for EEG-based BCI so far is the difficulty to decode brain signals in a reliable and efficient way. This paper proposes a new robust processing framework for decoding of multi-class motor imagery (MI) that is based on five main processing steps. (i) Raw EEG segmentation without the need of visual artifact inspection. (ii) Considering that EEG recordings are often contaminated not just by electrooculography (EOG) but also other types of artifacts, we propose to first implement an automatic artifact correction method that combines regression analysis with independent component analysis for recovering the original source signals. (iii) The significant difference between frequency components based on event-related (de-) synchronization and sample entropy is then used to find non-contiguous discriminating rhythms. After spectral filtering using the discriminating rhythms, a channel selection algorithm is used to select only relevant channels. (iv) Feature vectors are extracted based on the inter-class diversity and time-varying dynamic characteristics of the signals. (v) Finally, a support vector machine is employed for four-class classification. We tested our proposed algorithm on experimental data that was obtained from dataset 2a of BCI competition IV (2008). The overall four-class kappa values (between 0.41 and 0.80) were comparable to other models but without requiring any artifact-contaminated trial removal. The performance showed that multi-class MI tasks can be reliably discriminated using artifact-contaminated EEG recordings from a few channels. This may be a promising avenue for online robust EEG-based BCI applications. PMID:23087607

Computationally efficient SVM multi-class image recognition with confidence measures

International Nuclear Information System (INIS)

Makili, Lazaro; Vega, Jesus; Dormido-Canto, Sebastian; Pastor, Ignacio; Murari, Andrea

2011-01-01

Typically, machine learning methods produce non-qualified estimates, i.e. the accuracy and reliability of the predictions are not provided. Transductive predictors are very recent classifiers able to provide, simultaneously with the prediction, a couple of values (confidence and credibility) to reflect the quality of the prediction. Usually, a drawback of the transductive techniques for huge datasets and large dimensionality is the high computational time. To overcome this issue, a more efficient classifier has been used in a multi-class image classification problem in the TJ-II stellarator database. It is based on the creation of a hash function to generate several 'one versus the rest' classifiers for every class. By using Support Vector Machines as the underlying classifier, a comparison between the pure transductive approach and the new method has been performed. In both cases, the success rates are high and the computation time with the new method is up to 0.4 times the old one.

Deep multi-scale convolutional neural network for hyperspectral image classification

Science.gov (United States)

Zhang, Feng-zhe; Yang, Xia

2018-04-01

In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

The Classification of Romanian High-Schools

Science.gov (United States)

Ivan, Ion; Milodin, Daniel; Naie, Lucian

2006-01-01

The article tries to tackle the issue of high-schools classification from one city, district or from Romania. The classification criteria are presented. The National Database of Education is also presented and the application of criteria is illustrated. An algorithm for high-school multi-rang classification is proposed in order to build classes of…

Neuropsychological assessment of individuals with brain tumor: Comparison of approaches used in the classification of impairment

Directory of Open Access Journals (Sweden)

Toni Maree Dwan

2015-03-01

Full Text Available Approaches to classifying neuropsychological impairment after brain tumor vary according to testing level (individual tests, domains or global index and source of reference (i.e., norms, controls and premorbid functioning. This study aimed to compare rates of impairment according to different classification approaches. Participants were 44 individuals (57% female with a primary brain tumor diagnosis (mean age = 45.6 years and 44 matched control participants (59% female, mean age = 44.5 years. All participants completed a test battery that assesses premorbid IQ (Wechsler Adult Reading Test, attention/processing speed (Digit Span, Trail Making Test A, memory (Hopkins Verbal Learning Test – Revised, Rey-Osterrieth Complex Figure-recall and executive function (Trail Making Test B, Rey-Osterrieth Complex Figure copy, Controlled Oral Word Association Test. Results indicated that across the different sources of reference, 86-93% of participants were classified as impaired at a test-specific level, 61-73% were classified as impaired at a domain-specific level, and 32-50% were classified as impaired at a global level. Rates of impairment did not significantly differ according to source of reference (p>.05; however, at the individual participant level, classification based on estimated premorbid IQ was often inconsistent with classification based on the norms or controls. Participants with brain tumor performed significantly poorer than matched controls on tests of neuropsychological functioning, including executive function (p=.001 and memory (p.05. These results highlight the need to examine individuals’ performance across a multi-faceted neuropsychological test battery to avoid over- or under-estimation of impairment.

Manifold regularized multi-task feature selection for multi-modality classification in Alzheimer's disease.

Science.gov (United States)

Jie, Biao; Zhang, Daoqiang; Cheng, Bo; Shen, Dinggang

2013-01-01

Accurate diagnosis of Alzheimer's disease (AD), as well as its prodromal stage (i.e., mild cognitive impairment, MCI), is very important for possible delay and early treatment of the disease. Recently, multi-modality methods have been used for fusing information from multiple different and complementary imaging and non-imaging modalities. Although there are a number of existing multi-modality methods, few of them have addressed the problem of joint identification of disease-related brain regions from multi-modality data for classification. In this paper, we proposed a manifold regularized multi-task learning framework to jointly select features from multi-modality data. Specifically, we formulate the multi-modality classification as a multi-task learning framework, where each task focuses on the classification based on each modality. In order to capture the intrinsic relatedness among multiple tasks (i.e., modalities), we adopted a group sparsity regularizer, which ensures only a small number of features to be selected jointly. In addition, we introduced a new manifold based Laplacian regularization term to preserve the geometric distribution of original data from each task, which can lead to the selection of more discriminative features. Furthermore, we extend our method to the semi-supervised setting, which is very important since the acquisition of a large set of labeled data (i.e., diagnosis of disease) is usually expensive and time-consuming, while the collection of unlabeled data is relatively much easier. To validate our method, we have performed extensive evaluations on the baseline Magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET) data of Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our experimental results demonstrate the effectiveness of the proposed method.

Classification between normal and tumor tissues based on the pair-wise gene expression ratio

International Nuclear Information System (INIS)

Yap, YeeLeng; Zhang, XueWu; Ling, MT; Wang, XiangHong; Wong, YC; Danchin, Antoine

2004-01-01

Precise classification of cancer types is critically important for early cancer diagnosis and treatment. Numerous efforts have been made to use gene expression profiles to improve precision of tumor classification. However, reliable cancer-related signals are generally lacking. Using recent datasets on colon and prostate cancer, a data transformation procedure from single gene expression to pair-wise gene expression ratio is proposed. Making use of the internal consistency of each expression profiling dataset this transformation improves the signal to noise ratio of the dataset and uncovers new relevant cancer-related signals (features). The efficiency in using the transformed dataset to perform normal/tumor classification was investigated using feature partitioning with informative features (gene annotation) as discriminating axes (single gene expression or pair-wise gene expression ratio). Classification results were compared to the original datasets for up to 10-feature model classifiers. 82 and 262 genes that have high correlation to tissue phenotype were selected from the colon and prostate datasets respectively. Remarkably, data transformation of the highly noisy expression data successfully led to lower the coefficient of variation (CV) for the within-class samples as well as improved the correlation with tissue phenotypes. The transformed dataset exhibited lower CV when compared to that of single gene expression. In the colon cancer set, the minimum CV decreased from 45.3% to 16.5%. In prostate cancer, comparable CV was achieved with and without transformation. This improvement in CV, coupled with the improved correlation between the pair-wise gene expression ratio and tissue phenotypes, yielded higher classification efficiency, especially with the colon dataset – from 87.1% to 93.5%. Over 90% of the top ten discriminating axes in both datasets showed significant improvement after data transformation. The high classification efficiency achieved suggested

Three-class classification in computer-aided diagnosis of breast cancer by support vector machine

Science.gov (United States)

Sun, Xuejun; Qian, Wei; Song, Dansheng

2004-05-01

Design of classifier in computer-aided diagnosis (CAD) scheme of breast cancer plays important role to its overall performance in sensitivity and specificity. Classification of a detected object as malignant lesion, benign lesion, or normal tissue on mammogram is a typical three-class pattern recognition problem. This paper presents a three-class classification approach by using two-stage classifier combined with support vector machine (SVM) learning algorithm for classification of breast cancer on mammograms. The first classification stage is used to detect abnormal areas and normal breast tissues, and the second stage is for classification of malignant or benign in detected abnormal objects. A series of spatial, morphology and texture features have been extracted on detected objects areas. By using genetic algorithm (GA), different feature groups for different stage classification have been investigated. Computerized free-response receiver operating characteristic (FROC) and receiver operating characteristic (ROC) analyses have been employed in different classification stages. Results have shown that obvious performance improvement in both sensitivity and specificity was observed through proposed classification approach compared with conventional two-class classification approaches, indicating its effectiveness in classification of breast cancer on mammograms.

Preoperative classification of ovarial tumors by means of computed tomography

International Nuclear Information System (INIS)

Steinbrich, W.; Rohde, U.

1982-01-01

127 histologically demonstrated ovarial tumors were studied in a blindfold test in order to find out to what extent a preoperative determination of dignity or diagnosis of the tumor kind is possible by computed tomography. The overall rate of correct determinations of dignity is 82%. In case of functional cysts and cystomas with thin cyst walls, cystadenocarcinomas and dermoid cysts, this rate is about 95%, whereas the classification results are less exact in case of cystic tumors with broadened cyst walls, preponderantly solid tumors and tumor-like lesions. (orig.) [de

Multi-temporal and Dual-polarization Interferometric SAR for Land Cover Type Classification

Directory of Open Access Journals (Sweden)

WANG Xinshuang

2015-05-01

Full Text Available In order to study SAR land cover classification method, this paper uses the multi-dimensional combination of temporal,polarization and InSAR data. The area covered by space borne data of ALOS PALSAR in Xunke County,Heilongjiang Province was chosen as test site. A land cover classification technique of SVM based on multi-temporal, multi-polarization and InSAR data had been proposed, using the sensitivity to land cover type of multi-temporal, multi-polarization SAR data and InSAR measurements, and combing time series characteristic of backscatter coefficient and correlation coefficient to identify ground objects. The results showed the problem of confusion between forest land and urban construction land can be nicely solved, using the correlation coefficient between HH and HV, and also combing the selected temporal, polarization and InSAR characteristics. The land cover classification result with higher accuracy is gotten using the classification algorithm proposed in this paper.

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

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.

Automatic classification and detection of clinically relevant images for diabetic retinopathy

Science.gov (United States)

Xu, Xinyu; Li, Baoxin

2008-03-01

We proposed a novel approach to automatic classification of Diabetic Retinopathy (DR) images and retrieval of clinically-relevant DR images from a database. Given a query image, our approach first classifies the image into one of the three categories: microaneurysm (MA), neovascularization (NV) and normal, and then it retrieves DR images that are clinically-relevant to the query image from an archival image database. In the classification stage, the query DR images are classified by the Multi-class Multiple-Instance Learning (McMIL) approach, where images are viewed as bags, each of which contains a number of instances corresponding to non-overlapping blocks, and each block is characterized by low-level features including color, texture, histogram of edge directions, and shape. McMIL first learns a collection of instance prototypes for each class that maximizes the Diverse Density function using Expectation- Maximization algorithm. A nonlinear mapping is then defined using the instance prototypes and maps every bag to a point in a new multi-class bag feature space. Finally a multi-class Support Vector Machine is trained in the multi-class bag feature space. In the retrieval stage, we retrieve images from the archival database who bear the same label with the query image, and who are the top K nearest neighbors of the query image in terms of similarity in the multi-class bag feature space. The classification approach achieves high classification accuracy, and the retrieval of clinically-relevant images not only facilitates utilization of the vast amount of hidden diagnostic knowledge in the database, but also improves the efficiency and accuracy of DR lesion diagnosis and assessment.

Distributed optimization of multi-class SVMs.

Directory of Open Access Journals (Sweden)

Maximilian Alber

Full Text Available Training of one-vs.-rest SVMs can be parallelized over the number of classes in a straight forward way. Given enough computational resources, one-vs.-rest SVMs can thus be trained on data involving a large number of classes. The same cannot be stated, however, for the so-called all-in-one SVMs, which require solving a quadratic program of size quadratically in the number of classes. We develop distributed algorithms for two all-in-one SVM formulations (Lee et al. and Weston and Watkins that parallelize the computation evenly over the number of classes. This allows us to compare these models to one-vs.-rest SVMs on unprecedented scale. The results indicate superior accuracy on text classification data.

On the Evaluation of Outlier Detection and One-Class Classification Methods

DEFF Research Database (Denmark)

Swersky, Lorne; Marques, Henrique O.; Sander, Jörg

2016-01-01

It has been shown that unsupervised outlier detection methods can be adapted to the one-class classification problem. In this paper, we focus on the comparison of oneclass classification algorithms with such adapted unsupervised outlier detection methods, improving on previous comparison studies ...

Evaluation of data discretization methods to derive platform independent isoform expression signatures for multi-class tumor subtyping.

Science.gov (United States)

Jung, Segun; Bi, Yingtao; Davuluri, Ramana V

2015-01-01

Many supervised learning algorithms have been applied in deriving gene signatures for patient stratification from gene expression data. However, transferring the multi-gene signatures from one analytical platform to another without loss of classification accuracy is a major challenge. Here, we compared three unsupervised data discretization methods--Equal-width binning, Equal-frequency binning, and k-means clustering--in accurately classifying the four known subtypes of glioblastoma multiforme (GBM) when the classification algorithms were trained on the isoform-level gene expression profiles from exon-array platform and tested on the corresponding profiles from RNA-seq data. We applied an integrated machine learning framework that involves three sequential steps; feature selection, data discretization, and classification. For models trained and tested on exon-array data, the addition of data discretization step led to robust and accurate predictive models with fewer number of variables in the final models. For models trained on exon-array data and tested on RNA-seq data, the addition of data discretization step dramatically improved the classification accuracies with Equal-frequency binning showing the highest improvement with more than 90% accuracies for all the models with features chosen by Random Forest based feature selection. Overall, SVM classifier coupled with Equal-frequency binning achieved the best accuracy (> 95%). Without data discretization, however, only 73.6% accuracy was achieved at most. The classification algorithms, trained and tested on data from the same platform, yielded similar accuracies in predicting the four GBM subgroups. However, when dealing with cross-platform data, from exon-array to RNA-seq, the classifiers yielded stable models with highest classification accuracies on data transformed by Equal frequency binning. The approach presented here is generally applicable to other cancer types for classification and identification of

Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier.

Science.gov (United States)

Zhang, Baochang; Yang, Yun; Chen, Chen; Yang, Linlin; Han, Jungong; Shao, Ling

2017-10-01

Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side, and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared with the existing boosting frameworks, we add a new multi-class constraint into the objective function, which helps to maintain a better margin distribution by maximizing the mean of margin, whereas still minimizing the variance of margin. Experiments on the MSRAction3D, MSRGesture3D, MSRActivity3D, and UTD-MHAD data sets demonstrate that the proposed system combining 3DHoTs and MBC is superior to the state of the art.

EFFECTIVE MULTI-RESOLUTION TRANSFORM IDENTIFICATION FOR CHARACTERIZATION AND CLASSIFICATION OF TEXTURE GROUPS

Directory of Open Access Journals (Sweden)

S. Arivazhagan

2011-11-01

Full Text Available Texture classification is important in applications of computer image analysis for characterization or classification of images based on local spatial variations of intensity or color. Texture can be defined as consisting of mutually related elements. This paper proposes an experimental approach for identification of suitable multi-resolution transform for characterization and classification of different texture groups based on statistical and co-occurrence features derived from multi-resolution transformed sub bands. The statistical and co-occurrence feature sets are extracted for various multi-resolution transforms such as Discrete Wavelet Transform (DWT, Stationary Wavelet Transform (SWT, Double Density Wavelet Transform (DDWT and Dual Tree Complex Wavelet Transform (DTCWT and then, the transform that maximizes the texture classification performance for the particular texture group is identified.

3D multi-view convolutional neural networks for lung nodule classification

Science.gov (United States)

Kang, Guixia; Hou, Beibei; Zhang, Ningbo

2017-01-01

The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All networks employ the multi-view-one-network strategy. We conduct a binary classification (benign and malignant) and a ternary classification (benign, primary malignant and metastatic malignant) on Computed Tomography (CT) images from Lung Image Database Consortium and Image Database Resource Initiative database (LIDC-IDRI). All results are obtained via 10-fold cross validation. As regards the MV-CNN with chain architecture, results show that the performance of 3D MV-CNN surpasses that of 2D MV-CNN by a significant margin. Finally, a 3D Inception network achieved an error rate of 4.59% for the binary classification and 7.70% for the ternary classification, both of which represent superior results for the corresponding task. We compare the multi-view-one-network strategy with the one-view-one-network strategy. The results reveal that the multi-view-one-network strategy can achieve a lower error rate than the one-view-one-network strategy. PMID:29145492

Classification of Hyperspectral or Trichromatic Measurements of Ocean Color Data into Spectral Classes

Directory of Open Access Journals (Sweden)

Dilip K. Prasad

2016-03-01

Full Text Available We propose a method for classifying radiometric oceanic color data measured by hyperspectral satellite sensors into known spectral classes, irrespective of the downwelling irradiance of the particular day, i.e., the illumination conditions. The focus is not on retrieving the inherent optical properties but to classify the pixels according to the known spectral classes of the reflectances from the ocean. The method compensates for the unknown downwelling irradiance by white balancing the radiometric data at the ocean pixels using the radiometric data of bright pixels (typically from clouds. The white-balanced data is compared with the entries in a pre-calibrated lookup table in which each entry represents the spectral properties of one class. The proposed approach is tested on two datasets of in situ measurements and 26 different daylight illumination spectra for medium resolution imaging spectrometer (MERIS, moderate-resolution imaging spectroradiometer (MODIS, sea-viewing wide field-of-view sensor (SeaWiFS, coastal zone color scanner (CZCS, ocean and land colour instrument (OLCI, and visible infrared imaging radiometer suite (VIIRS sensors. Results are also shown for CIMEL’s SeaPRISM sun photometer sensor used on-board field trips. Accuracy of more than 92% is observed on the validation dataset and more than 86% is observed on the other dataset for all satellite sensors. The potential of applying the algorithms to non-satellite and non-multi-spectral sensors mountable on airborne systems is demonstrated by showing classification results for two consumer cameras. Classification on actual MERIS data is also shown. Additional results comparing the spectra of remote sensing reflectance with level 2 MERIS data and chlorophyll concentration estimates of the data are included.

Representation Learning for Class C G Protein-Coupled Receptors Classification

Directory of Open Access Journals (Sweden)

Raúl Cruz-Barbosa

2018-03-01

Full Text Available G protein-coupled receptors (GPCRs are integral cell membrane proteins of relevance for pharmacology. The complete tertiary structure including both extracellular and transmembrane domains has not been determined for any member of class C GPCRs. An alternative way to work on GPCR structural models is the investigation of their functionality through the analysis of their primary structure. For this, sequence representation is a key factor for the GPCRs’ classification context, where usually, feature engineering is carried out. In this paper, we propose the use of representation learning to acquire the features that best represent the class C GPCR sequences and at the same time to obtain a model for classification automatically. Deep learning methods in conjunction with amino acid physicochemical property indices are then used for this purpose. Experimental results assessed by the classification accuracy, Matthews’ correlation coefficient and the balanced error rate show that using a hydrophobicity index and a restricted Boltzmann machine (RBM can achieve performance results (accuracy of 92.9% similar to those reported in the literature. As a second proposal, we combine two or more physicochemical property indices instead of only one as the input for a deep architecture in order to add information from the sequences. Experimental results show that using three hydrophobicity-related index combinations helps to improve the classification performance (accuracy of 94.1% of an RBM better than those reported in the literature for class C GPCRs without using feature selection methods.

Manifold Regularized Multi-Task Feature Selection for Multi-Modality Classification in Alzheimer’s Disease

Science.gov (United States)

Jie, Biao; Cheng, Bo

2014-01-01

Accurate diagnosis of Alzheimer’s disease (AD), as well as its pro-dromal stage (i.e., mild cognitive impairment, MCI), is very important for possible delay and early treatment of the disease. Recently, multi-modality methods have been used for fusing information from multiple different and complementary imaging and non-imaging modalities. Although there are a number of existing multi-modality methods, few of them have addressed the problem of joint identification of disease-related brain regions from multi-modality data for classification. In this paper, we proposed a manifold regularized multi-task learning framework to jointly select features from multi-modality data. Specifically, we formulate the multi-modality classification as a multi-task learning framework, where each task focuses on the classification based on each modality. In order to capture the intrinsic relatedness among multiple tasks (i.e., modalities), we adopted a group sparsity regularizer, which ensures only a small number of features to be selected jointly. In addition, we introduced a new manifold based Laplacian regularization term to preserve the geometric distribution of original data from each task, which can lead to the selection of more discriminative features. Furthermore, we extend our method to the semi-supervised setting, which is very important since the acquisition of a large set of labeled data (i.e., diagnosis of disease) is usually expensive and time-consuming, while the collection of unlabeled data is relatively much easier. To validate our method, we have performed extensive evaluations on the baseline Magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET) data of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our experimental results demonstrate the effectiveness of the proposed method. PMID:24505676

GLOBAL LAND COVER CLASSIFICATION USING MODIS SURFACE REFLECTANCE PROSUCTS

Directory of Open Access Journals (Sweden)

K. Fukue

2016-06-01

Full Text Available The objective of this study is to develop high accuracy land cover classification algorithm for Global scale by using multi-temporal MODIS land reflectance products. In this study, time-domain co-occurrence matrix was introduced as a classification feature which provides time-series signature of land covers. Further, the non-parametric minimum distance classifier was introduced for timedomain co-occurrence matrix, which performs multi-dimensional pattern matching for time-domain co-occurrence matrices of a classification target pixel and each classification classes. The global land cover classification experiments have been conducted by applying the proposed classification method using 46 multi-temporal(in one year SR(Surface Reflectance and NBAR(Nadir BRDF-Adjusted Reflectance products, respectively. IGBP 17 land cover categories were used in our classification experiments. As the results, SR and NBAR products showed similar classification accuracy of 99%.

Classification of Urban Feature from Unmanned Aerial Vehicle Images Using Gasvm Integration and Multi-Scale Segmentation

Science.gov (United States)

Modiri, M.; Salehabadi, A.; Mohebbi, M.; Hashemi, A. M.; Masumi, M.

2015-12-01

The use of UAV in the application of photogrammetry to obtain cover images and achieve the main objectives of the photogrammetric mapping has been a boom in the region. The images taken from REGGIOLO region in the province of, Italy Reggio -Emilia by UAV with non-metric camera Canon Ixus and with an average height of 139.42 meters were used to classify urban feature. Using the software provided SURE and cover images of the study area, to produce dense point cloud, DSM and Artvqvtv spatial resolution of 10 cm was prepared. DTM area using Adaptive TIN filtering algorithm was developed. NDSM area was prepared with using the difference between DSM and DTM and a separate features in the image stack. In order to extract features, using simultaneous occurrence matrix features mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation for each of the RGB band image was used Orthophoto area. Classes used to classify urban problems, including buildings, trees and tall vegetation, grass and vegetation short, paved road and is impervious surfaces. Class consists of impervious surfaces such as pavement conditions, the cement, the car, the roof is stored. In order to pixel-based classification and selection of optimal features of classification was GASVM pixel basis. In order to achieve the classification results with higher accuracy and spectral composition informations, texture, and shape conceptual image featureOrthophoto area was fencing. The segmentation of multi-scale segmentation method was used.it belonged class. Search results using the proposed classification of urban feature, suggests the suitability of this method of classification complications UAV is a city using images. The overall accuracy and kappa coefficient method proposed in this study, respectively, 47/93% and 84/91% was.

Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants.

Science.gov (United States)

Yousef, Malik; Saçar Demirci, Müşerref Duygu; Khalifa, Waleed; Allmer, Jens

2016-01-01

MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection.

Classification of high-resolution remote sensing images based on multi-scale superposition

Science.gov (United States)

Wang, Jinliang; Gao, Wenjie; Liu, Guangjie

2017-07-01

Landscape structures and process on different scale show different characteristics. In the study of specific target landmarks, the most appropriate scale for images can be attained by scale conversion, which improves the accuracy and efficiency of feature identification and classification. In this paper, the authors carried out experiments on multi-scale classification by taking the Shangri-la area in the north-western Yunnan province as the research area and the images from SPOT5 HRG and GF-1 Satellite as date sources. Firstly, the authors upscaled the two images by cubic convolution, and calculated the optimal scale for different objects on the earth shown in images by variation functions. Then the authors conducted multi-scale superposition classification on it by Maximum Likelyhood, and evaluated the classification accuracy. The results indicates that: (1) for most of the object on the earth, the optimal scale appears in the bigger scale instead of the original one. To be specific, water has the biggest optimal scale, i.e. around 25-30m; farmland, grassland, brushwood, roads, settlement places and woodland follows with 20-24m. The optimal scale for shades and flood land is basically as the same as the original one, i.e. 8m and 10m respectively. (2) Regarding the classification of the multi-scale superposed images, the overall accuracy of the ones from SPOT5 HRG and GF-1 Satellite is 12.84% and 14.76% higher than that of the original multi-spectral images, respectively, and Kappa coefficient is 0.1306 and 0.1419 higher, respectively. Hence, the multi-scale superposition classification which was applied in the research area can enhance the classification accuracy of remote sensing images .

Drug-related webpages classification based on multi-modal local decision fusion

Science.gov (United States)

Hu, Ruiguang; Su, Xiaojing; Liu, Yanxin

2018-03-01

In this paper, multi-modal local decision fusion is used for drug-related webpages classification. First, meaningful text are extracted through HTML parsing, and effective images are chosen by the FOCARSS algorithm. Second, six SVM classifiers are trained for six kinds of drug-taking instruments, which are represented by PHOG. One SVM classifier is trained for the cannabis, which is represented by the mid-feature of BOW model. For each instance in a webpage, seven SVMs give seven labels for its image, and other seven labels are given by searching the names of drug-taking instruments and cannabis in its related text. Concatenating seven labels of image and seven labels of text, the representation of those instances in webpages are generated. Last, Multi-Instance Learning is used to classify those drugrelated webpages. Experimental results demonstrate that the classification accuracy of multi-instance learning with multi-modal local decision fusion is much higher than those of single-modal classification.

An assessment of the cultivated cropland class of NLCD 2006 using a multi-source and multi-criteria approach

Science.gov (United States)

Danielson, Patrick; Yang, Limin; Jin, Suming; Homer, Collin G.; Napton, Darrell

2016-01-01

We developed a method that analyzes the quality of the cultivated cropland class mapped in the USA National Land Cover Database (NLCD) 2006. The method integrates multiple geospatial datasets and a Multi Index Integrated Change Analysis (MIICA) change detection method that captures spectral changes to identify the spatial distribution and magnitude of potential commission and omission errors for the cultivated cropland class in NLCD 2006. The majority of the commission and omission errors in NLCD 2006 are in areas where cultivated cropland is not the most dominant land cover type. The errors are primarily attributed to the less accurate training dataset derived from the National Agricultural Statistics Service Cropland Data Layer dataset. In contrast, error rates are low in areas where cultivated cropland is the dominant land cover. Agreement between model-identified commission errors and independently interpreted reference data was high (79%). Agreement was low (40%) for omission error comparison. The majority of the commission errors in the NLCD 2006 cultivated crops were confused with low-intensity developed classes, while the majority of omission errors were from herbaceous and shrub classes. Some errors were caused by inaccurate land cover change from misclassification in NLCD 2001 and the subsequent land cover post-classification process.

Multi-class oscillating systems of interacting neurons

DEFF Research Database (Denmark)

Ditlevsen, Susanne; Löcherbach, Eva

2017-01-01

We consider multi-class systems of interacting nonlinear Hawkes processes modeling several large families of neurons and study their mean field limits. As the total number of neurons goes to infinity we prove that the evolution within each class can be described by a nonlinear limit differential...

Multi-stage classification method oriented to aerial image based on low-rank recovery and multi-feature fusion sparse representation.

Science.gov (United States)

Ma, Xu; Cheng, Yongmei; Hao, Shuai

2016-12-10

Automatic classification of terrain surfaces from an aerial image is essential for an autonomous unmanned aerial vehicle (UAV) landing at an unprepared site by using vision. Diverse terrain surfaces may show similar spectral properties due to the illumination and noise that easily cause poor classification performance. To address this issue, a multi-stage classification algorithm based on low-rank recovery and multi-feature fusion sparse representation is proposed. First, color moments and Gabor texture feature are extracted from training data and stacked as column vectors of a dictionary. Then we perform low-rank matrix recovery for the dictionary by using augmented Lagrange multipliers and construct a multi-stage terrain classifier. Experimental results on an aerial map database that we prepared verify the classification accuracy and robustness of the proposed method.

Intrusion detection model using fusion of chi-square feature selection and multi class SVM

Directory of Open Access Journals (Sweden)

Ikram Sumaiya Thaseen

2017-10-01

Full Text Available Intrusion detection is a promising area of research in the domain of security with the rapid development of internet in everyday life. Many intrusion detection systems (IDS employ a sole classifier algorithm for classifying network traffic as normal or abnormal. Due to the large amount of data, these sole classifier models fail to achieve a high attack detection rate with reduced false alarm rate. However by applying dimensionality reduction, data can be efficiently reduced to an optimal set of attributes without loss of information and then classified accurately using a multi class modeling technique for identifying the different network attacks. In this paper, we propose an intrusion detection model using chi-square feature selection and multi class support vector machine (SVM. A parameter tuning technique is adopted for optimization of Radial Basis Function kernel parameter namely gamma represented by ‘ϒ’ and over fitting constant ‘C’. These are the two important parameters required for the SVM model. The main idea behind this model is to construct a multi class SVM which has not been adopted for IDS so far to decrease the training and testing time and increase the individual classification accuracy of the network attacks. The investigational results on NSL-KDD dataset which is an enhanced version of KDDCup 1999 dataset shows that our proposed approach results in a better detection rate and reduced false alarm rate. An experimentation on the computational time required for training and testing is also carried out for usage in time critical applications.

Class Association Rule Pada Metode Associative Classification

Directory of Open Access Journals (Sweden)

Eka Karyawati

2011-11-01

Full Text Available Frequent patterns (itemsets discovery is an important problem in associative classification rule mining.  Differents approaches have been proposed such as the Apriori-like, Frequent Pattern (FP-growth, and Transaction Data Location (Tid-list Intersection algorithm. This paper focuses on surveying and comparing the state of the art associative classification techniques with regards to the rule generation phase of associative classification algorithms.  This phase includes frequent itemsets discovery and rules mining/extracting methods to generate the set of class association rules (CARs.  There are some techniques proposed to improve the rule generation method.  A technique by utilizing the concepts of discriminative power of itemsets can reduce the size of frequent itemset.  It can prune the useless frequent itemsets. The closed frequent itemset concept can be utilized to compress the rules to be compact rules.  This technique may reduce the size of generated rules.  Other technique is in determining the support threshold value of the itemset. Specifying not single but multiple support threshold values with regard to the class label frequencies can give more appropriate support threshold value.  This technique may generate more accurate rules. Alternative technique to generate rule is utilizing the vertical layout to represent dataset.  This method is very effective because it only needs one scan over dataset, compare with other techniques that need multiple scan over dataset.   However, one problem with these approaches is that the initial set of tid-lists may be too large to fit into main memory. It requires more sophisticated techniques to compress the tid-lists.

An NRG Oncology/GOG study of molecular classification for risk prediction in endometrioid endometrial cancer.

Science.gov (United States)

Cosgrove, Casey M; Tritchler, David L; Cohn, David E; Mutch, David G; Rush, Craig M; Lankes, Heather A; Creasman, William T; Miller, David S; Ramirez, Nilsa C; Geller, Melissa A; Powell, Matthew A; Backes, Floor J; Landrum, Lisa M; Timmers, Cynthia; Suarez, Adrian A; Zaino, Richard J; Pearl, Michael L; DiSilvestro, Paul A; Lele, Shashikant B; Goodfellow, Paul J

2018-01-01

The purpose of this study was to assess the prognostic significance of a simplified, clinically accessible classification system for endometrioid endometrial cancers combining Lynch syndrome screening and molecular risk stratification. Tumors from NRG/GOG GOG210 were evaluated for mismatch repair defects (MSI, MMR IHC, and MLH1 methylation), POLE mutations, and loss of heterozygosity. TP53 was evaluated in a subset of cases. Tumors were assigned to four molecular classes. Relationships between molecular classes and clinicopathologic variables were assessed using contingency tests and Cox proportional methods. Molecular classification was successful for 982 tumors. Based on the NCI consensus MSI panel assessing MSI and loss of heterozygosity combined with POLE testing, 49% of tumors were classified copy number stable (CNS), 39% MMR deficient, 8% copy number altered (CNA) and 4% POLE mutant. Cancer-specific mortality occurred in 5% of patients with CNS tumors; 2.6% with POLE tumors; 7.6% with MMR deficient tumors and 19% with CNA tumors. The CNA group had worse progression-free (HR 2.31, 95%CI 1.53-3.49) and cancer-specific survival (HR 3.95; 95%CI 2.10-7.44). The POLE group had improved outcomes, but the differences were not statistically significant. CNA class remained significant for cancer-specific survival (HR 2.11; 95%CI 1.04-4.26) in multivariable analysis. The CNA molecular class was associated with TP53 mutation and expression status. A simple molecular classification for endometrioid endometrial cancers that can be easily combined with Lynch syndrome screening provides important prognostic information. These findings support prospective clinical validation and further studies on the predictive value of a simplified molecular classification system. Copyright © 2017 Elsevier Inc. All rights reserved.

Guided Classification System for Conceptual Overlapping Classes in OpenStreetMap

Directory of Open Access Journals (Sweden)

Ahmed Loai Ali

2016-06-01

Full Text Available The increased development of Volunteered Geographic Information (VGI and its potential role in GIScience studies raises questions about the resulting data quality. Several studies address VGI quality from various perspectives like completeness, positional accuracy, consistency, etc. They mostly have consensus on the heterogeneity of data quality. The problem may be due to the lack of standard procedures for data collection and absence of quality control feedback for voluntary participants. In our research, we are concerned with data quality from the classification perspective. Particularly in VGI-mapping projects, the limited expertise of participants and the non-strict definition of geographic features lead to conceptual overlapping classes, where an entity could plausibly belong to multiple classes, e.g., lake or pond, park or garden, marsh or swamp, etc. Usually, quantitative and/or qualitative characteristics exist that distinguish between classes. Nevertheless, these characteristics might not be recognizable for non-expert participants. In previous work, we developed the rule-guided classification approach that guides participants to the most appropriate classes. As exemplification, we tackle the conceptual overlapping of some grass-related classes. For a given data set, our approach presents the most highly recommended classes for each entity. In this paper, we present the validation of our approach. We implement a web-based application called Grass&Green that presents recommendations for crowdsourcing validation. The findings show the applicability of the proposed approach. In four months, the application attracted 212 participants from more than 35 countries who checked 2,865 entities. The results indicate that 89% of the contributions fully/partially agree with our recommendations. We then carried out a detailed analysis that demonstrates the potential of this enhanced data classification. This research encourages the development of

An Analysis of Social Class Classification Based on Linguistic Variables

Institute of Scientific and Technical Information of China (English)

QU Xia-sha

2016-01-01

Since language is an influential tool in social interaction, the relationship of speech and social factors, such as social class, gender, even age is worth studying. People employ different linguistic variables to imply their social class, status and iden-tity in the social interaction. Thus the linguistic variation involves vocabulary, sounds, grammatical constructions, dialects and so on. As a result, a classification of social class draws people’s attention. Linguistic variable in speech interactions indicate the social relationship between people. This paper attempts to illustrate three main linguistic variables which influence the social class, and further sociolinguistic studies need to be more concerned about.

Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro-Fuzzy Class Method

Directory of Open Access Journals (Sweden)

Laercio B. Gonçalves

2010-01-01

Full Text Available We used a Hierarchical Neuro-Fuzzy Class Method based on binary space partitioning (NFHB-Class Method for macroscopic rock texture classification. The relevance of this study is in helping Geologists in the diagnosis and planning of oil reservoir exploration. The proposed method is capable of generating its own decision structure, with automatic extraction of fuzzy rules. These rules are linguistically interpretable, thus explaining the obtained data structure. The presented image classification for macroscopic rocks is based on texture descriptors, such as spatial variation coefficient, Hurst coefficient, entropy, and cooccurrence matrix. Four rock classes have been evaluated by the NFHB-Class Method: gneiss (two subclasses, basalt (four subclasses, diabase (five subclasses, and rhyolite (five subclasses. These four rock classes are of great interest in the evaluation of oil boreholes, which is considered a complex task by geologists. We present a computer method to solve this problem. In order to evaluate system performance, we used 50 RGB images for each rock classes and subclasses, thus producing a total of 800 images. For all rock classes, the NFHB-Class Method achieved a percentage of correct hits over 73%. The proposed method converged for all tests presented in the case study.

An Improved Rotation Forest for Multi-Feature Remote-Sensing Imagery Classification

Directory of Open Access Journals (Sweden)

Yingchang Xiu

2017-11-01

Full Text Available Multi-feature, especially multi-temporal, remote-sensing data have the potential to improve land cover classification accuracy. However, sometimes it is difficult to utilize all the features efficiently. To enhance classification performance based on multi-feature imagery, an improved rotation forest, combining Principal Component Analysis (PCA and a boosting naïve Bayesian tree (NBTree, is proposed. First, feature extraction was carried out with PCA. The feature set was randomly split into several disjoint subsets; then, PCA was applied to each subset, and new training data for linear extracted features based on original training data were obtained. These steps were repeated several times. Second, based on the new training data, a boosting naïve Bayesian tree was constructed as the base classifier, which aims to achieve lower prediction error than a decision tree in the original rotation forest. At the classification phase, the improved rotation forest has two-layer voting. It first obtains several predictions through weighted voting in a boosting naïve Bayesian tree; then, the first-layer vote predicts by majority to obtain the final result. To examine the classification performance, the improved rotation forest was applied to multi-feature remote-sensing images, including MODIS Enhanced Vegetation Index (EVI imagery time series, MODIS Surface Reflectance products and ancillary data in Shandong Province for 2013. The EVI imagery time series was preprocessed using harmonic analysis of time series (HANTS to reduce the noise effects. The overall accuracy of the final classification result was 89.17%, and the Kappa coefficient was 0.71, which outperforms the original rotation forest and other classifier ensemble results, as well as the NASA land cover product. However, this new algorithm requires more computational time, meaning the efficiency needs to be further improved. Generally, the improved rotation forest has a potential advantage in

Classification of the lymphatic drainage status of a primary tumor: a proposal

International Nuclear Information System (INIS)

Munz, D.L.; Maza, S.; Ivancevic, V.; Geworski, L.

2000-01-01

Aim: Creation of a classification of the lymphatic drainage status of a primary tumour. It shall enable comparison of different approaches, standardisation and quality control. Methods: Identification and topographic localisation of the sentinel node(s) using lymphatic radionuclide gamma camera imaging and/or gamma probe detection and/or vital dye mapping. Results: A classification comprising four classes (D-Class I-IV) and distinct subclasses (A-E) proved to be simply to be learned and applicable as well as reliably reproducible. It is based on the number of sentinel lymph nodes and their locations and can be combined with the pathological and molecular biological lymph node status. D-classes/subclasses obtained in 420 patients with malignant melanoma of the skin are presented. Conclusions: The classification is applicable to different approaches. Its diagnostic, therapeutic and prognostic value should be studied prospectively in those primary tumours which preferably metastasise via their draining lymphatic vessels. (orig.) [de

Approximations for Markovian multi-class queues with preemptive priorities

NARCIS (Netherlands)

van der Heijden, Matthijs C.; van Harten, Aart; Sleptchenko, Andrei

2004-01-01

We discuss the approximation of performance measures in multi-class M/M/k queues with preemptive priorities for large problem instances (many classes and servers) using class aggregation and server reduction. We compared our approximations to exact and simulation results and found that our approach

Classification of brain tumor extracts by high resolution ¹H MRS using partial least squares discriminant analysis

Directory of Open Access Journals (Sweden)

A.V. Faria

2011-02-01

Full Text Available High resolution proton nuclear magnetic resonance spectroscopy (¹H MRS can be used to detect biochemical changes in vitro caused by distinct pathologies. It can reveal distinct metabolic profiles of brain tumors although the accurate analysis and classification of different spectra remains a challenge. In this study, the pattern recognition method partial least squares discriminant analysis (PLS-DA was used to classify 11.7 T ¹H MRS spectra of brain tissue extracts from patients with brain tumors into four classes (high-grade neuroglial, low-grade neuroglial, non-neuroglial, and metastasis and a group of control brain tissue. PLS-DA revealed 9 metabolites as the most important in group differentiation: γ-aminobutyric acid, acetoacetate, alanine, creatine, glutamate/glutamine, glycine, myo-inositol, N-acetylaspartate, and choline compounds. Leave-one-out cross-validation showed that PLS-DA was efficient in group characterization. The metabolic patterns detected can be explained on the basis of previous multimodal studies of tumor metabolism and are consistent with neoplastic cell abnormalities possibly related to high turnover, resistance to apoptosis, osmotic stress and tumor tendency to use alternative energetic pathways such as glycolysis and ketogenesis.

Distance-Based Image Classification: Generalizing to New Classes at Near Zero Cost

NARCIS (Netherlands)

Mensink, T.; Verbeek, J.; Perronnin, F.; Csurka, G.

2013-01-01

We study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end, we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers, and introduce a new

Multi-q pattern classification of polarization curves

Science.gov (United States)

Fabbri, Ricardo; Bastos, Ivan N.; Neto, Francisco D. Moura; Lopes, Francisco J. P.; Gonçalves, Wesley N.; Bruno, Odemir M.

2014-02-01

Several experimental measurements are expressed in the form of one-dimensional profiles, for which there is a scarcity of methodologies able to classify the pertinence of a given result to a specific group. The polarization curves that evaluate the corrosion kinetics of electrodes in corrosive media are applications where the behavior is chiefly analyzed from profiles. Polarization curves are indeed a classic method to determine the global kinetics of metallic electrodes, but the strong nonlinearity from different metals and alloys can overlap and the discrimination becomes a challenging problem. Moreover, even finding a typical curve from replicated tests requires subjective judgment. In this paper, we used the so-called multi-q approach based on the Tsallis statistics in a classification engine to separate the multiple polarization curve profiles of two stainless steels. We collected 48 experimental polarization curves in an aqueous chloride medium of two stainless steel types, with different resistance against localized corrosion. Multi-q pattern analysis was then carried out on a wide potential range, from cathodic up to anodic regions. An excellent classification rate was obtained, at a success rate of 90%, 80%, and 83% for low (cathodic), high (anodic), and both potential ranges, respectively, using only 2% of the original profile data. These results show the potential of the proposed approach towards efficient, robust, systematic and automatic classification of highly nonlinear profile curves.

Classification of hydrocephalus: critical analysis of classification categories and advantages of "Multi-categorical Hydrocephalus Classification" (Mc HC).

Science.gov (United States)

Oi, Shizuo

2011-10-01

Hydrocephalus is a complex pathophysiology with disturbed cerebrospinal fluid (CSF) circulation. There are numerous numbers of classification trials published focusing on various criteria, such as associated anomalies/underlying lesions, CSF circulation/intracranial pressure patterns, clinical features, and other categories. However, no definitive classification exists comprehensively to cover the variety of these aspects. The new classification of hydrocephalus, "Multi-categorical Hydrocephalus Classification" (Mc HC), was invented and developed to cover the entire aspects of hydrocephalus with all considerable classification items and categories. Ten categories include "Mc HC" category I: onset (age, phase), II: cause, III: underlying lesion, IV: symptomatology, V: pathophysiology 1-CSF circulation, VI: pathophysiology 2-ICP dynamics, VII: chronology, VII: post-shunt, VIII: post-endoscopic third ventriculostomy, and X: others. From a 100-year search of publication related to the classification of hydrocephalus, 14 representative publications were reviewed and divided into the 10 categories. The Baumkuchen classification graph made from the round o'clock classification demonstrated the historical tendency of deviation to the categories in pathophysiology, either CSF or ICP dynamics. In the preliminary clinical application, it was concluded that "Mc HC" is extremely effective in expressing the individual state with various categories in the past and present condition or among the compatible cases of hydrocephalus along with the possible chronological change in the future.

A Multi-Class, Interdisciplinary Project Using Elementary Statistics

Science.gov (United States)

Reese, Margaret

2012-01-01

This article describes a multi-class project that employs statistical computing and writing in a statistics class. Three courses, General Ecology, Meteorology, and Introductory Statistics, cooperated on a project for the EPA's Student Design Competition. The continuing investigation has also spawned several undergraduate research projects in…

An exact solution for the state probabilities of the multi-class, multi-server queue with preemptive priorities

NARCIS (Netherlands)

Sleptchenko, Andrei; van Harten, Aart; van der Heijden, Matthijs C.

2005-01-01

We consider a multi-class, multi-server queueing system with preemptive priorities. We distinguish two groups of priority classes that consist of multiple customer types, each having their own arrival and service rate. We assume Poisson arrival processes and exponentially distributed service times.

Automatic SLEEP staging: From young aduslts to elderly patients using multi-class support vector machine

DEFF Research Database (Denmark)

Kempfner, Jacob; Jennum, Poul; Sorensen, Helge B. D.

2013-01-01

an automatic sleep stage detector, which can separate wakefulness, rapid-eye-movement (REM) sleep and non-REM (NREM) sleep using only EEG and EOG. Most sleep events, which define the sleep stages, are reduced with age. This is addressed by focusing on the amplitude of the clinical EEG bands......Aging is a process that is inevitable, and makes our body vulnerable to age-related diseases. Age is the most consistent factor affecting the sleep structure. Therefore, new automatic sleep staging methods, to be used in both of young and elderly patients, are needed. This study proposes......, and not the affected sleep events. The age-related influences are then reduced by robust subject-specific scaling. The classification of the three sleep stages are achieved by a multi-class support vector machine using the one-versus-rest scheme. It was possible to obtain a high classification accuracy of 0...

The Pattern Recognition in Cattle Brand using Bag of Visual Words and Support Vector Machines Multi-Class

Directory of Open Access Journals (Sweden)

Carlos Silva, Mr

2018-03-01

Full Text Available The recognition images of cattle brand in an automatic way is a necessity to governmental organs responsible for this activity. To help this process, this work presents a method that consists in using Bag of Visual Words for extracting of characteristics from images of cattle brand and Support Vector Machines Multi-Class for classification. This method consists of six stages: a select database of images; b extract points of interest (SURF; c create vocabulary (K-means; d create vector of image characteristics (visual words; e train and sort images (SVM; f evaluate the classification results. The accuracy of the method was tested on database of municipal city hall, where it achieved satisfactory results, reporting 86.02% of accuracy and 56.705 seconds of processing time, respectively.

Multi-level discriminative dictionary learning with application to large scale image classification.

Science.gov (United States)

Shen, Li; Sun, Gang; Huang, Qingming; Wang, Shuhui; Lin, Zhouchen; Wu, Enhua

2015-10-01

The sparse coding technique has shown flexibility and capability in image representation and analysis. It is a powerful tool in many visual applications. Some recent work has shown that incorporating the properties of task (such as discrimination for classification task) into dictionary learning is effective for improving the accuracy. However, the traditional supervised dictionary learning methods suffer from high computation complexity when dealing with large number of categories, making them less satisfactory in large scale applications. In this paper, we propose a novel multi-level discriminative dictionary learning method and apply it to large scale image classification. Our method takes advantage of hierarchical category correlation to encode multi-level discriminative information. Each internal node of the category hierarchy is associated with a discriminative dictionary and a classification model. The dictionaries at different layers are learnt to capture the information of different scales. Moreover, each node at lower layers also inherits the dictionary of its parent, so that the categories at lower layers can be described with multi-scale information. The learning of dictionaries and associated classification models is jointly conducted by minimizing an overall tree loss. The experimental results on challenging data sets demonstrate that our approach achieves excellent accuracy and competitive computation cost compared with other sparse coding methods for large scale image classification.

Learning object-to-class kernels for scene classification.

Science.gov (United States)

Zhang, Lei; Zhen, Xiantong; Shao, Ling

2014-08-01

High-level image representations have drawn increasing attention in visual recognition, e.g., scene classification, since the invention of the object bank. The object bank represents an image as a response map of a large number of pretrained object detectors and has achieved superior performance for visual recognition. In this paper, based on the object bank representation, we propose the object-to-class (O2C) distances to model scene images. In particular, four variants of O2C distances are presented, and with the O2C distances, we can represent the images using the object bank by lower-dimensional but more discriminative spaces, called distance spaces, which are spanned by the O2C distances. Due to the explicit computation of O2C distances based on the object bank, the obtained representations can possess more semantic meanings. To combine the discriminant ability of the O2C distances to all scene classes, we further propose to kernalize the distance representation for the final classification. We have conducted extensive experiments on four benchmark data sets, UIUC-Sports, Scene-15, MIT Indoor, and Caltech-101, which demonstrate that the proposed approaches can significantly improve the original object bank approach and achieve the state-of-the-art performance.

Land cover's refined classification based on multi source of remote sensing information fusion: a case study of national geographic conditions census in China

Science.gov (United States)

Cheng, Tao; Zhang, Jialong; Zheng, Xinyan; Yuan, Rujin

2018-03-01

The project of The First National Geographic Conditions Census developed by Chinese government has designed the data acquisition content and indexes, and has built corresponding classification system mainly based on the natural property of material. However, the unified standard for land cover classification system has not been formed; the production always needs converting to meet the actual needs. Therefore, it proposed a refined classification method based on multi source of remote sensing information fusion. It takes the third-level classes of forest land and grassland for example, and has collected the thematic data of Vegetation Map of China (1:1,000,000), attempts to develop refined classification utilizing raster spatial analysis model. Study area is selected, and refined classification is achieved by using the proposed method. The results show that land cover within study area is divided principally among 20 classes, from subtropical broad-leaved forest (31131) to grass-forb community type of low coverage grassland (41192); what's more, after 30 years in the study area, climatic factors, developmental rhythm characteristics and vegetation ecological geographical characteristics have not changed fundamentally, only part of the original vegetation types have changed in spatial distribution range or land cover types. Research shows that refined classification for the third-level classes of forest land and grassland could make the results take on both the natural attributes of the original and plant community ecology characteristics, which could meet the needs of some industry application, and has certain practical significance for promoting the product of The First National Geographic Conditions Census.

β class II tubulin predominates in normal and tumor breast tissues

International Nuclear Information System (INIS)

Dozier, James H; Hiser, Laree; Davis, Jennifer A; Thomas, Nancy Stubbs; Tucci, Michelle A; Benghuzzi, Hamed A; Frankfurter, Anthony; Correia, John J; Lobert, Sharon

2003-01-01

Antimitotic chemotherapeutic agents target tubulin, the major protein in mitotic spindles. Tubulin isotype composition is thought to be both diagnostic of tumor progression and a determinant of the cellular response to chemotherapy. This implies that there is a difference in isotype composition between normal and tumor tissues. To determine whether such a difference occurs in breast tissues, total tubulin was fractionated from lysates of paired normal and tumor breast tissues, and the amounts of β-tubulin classes I + IV, II, and III were measured by competitive enzyme-linked immunosorbent assay (ELISA). Only primary tumor tissues, before chemotherapy, were examined. Her2/neu protein amplification occurs in about 30% of breast tumors and is considered a marker for poor prognosis. To gain insight into whether tubulin isotype levels might be correlated with prognosis, ELISAs were used to quantify Her2/neu protein levels in these tissues. β-Tubulin isotype distributions in normal and tumor breast tissues were similar. The most abundant β-tubulin isotypes in these tissues were β-tubulin classes II and I + IV. Her2/neu levels in tumor tissues were 5–30-fold those in normal tissues, although there was no correlation between the Her2/neu biomarker and tubulin isotype levels. These results suggest that tubulin isotype levels, alone or in combination with Her2/neu protein levels, might not be diagnostic of tumorigenesis in breast cancer. However, the presence of a broad distribution of these tubulin isotypes (for example, 40–75% β-tubulin class II) in breast tissue, in conjunction with other factors, might still be relevant to disease progression and cellular response to antimitotic drugs

Adaptive swarm cluster-based dynamic multi-objective synthetic minority oversampling technique algorithm for tackling binary imbalanced datasets in biomedical data classification.

Science.gov (United States)

Li, Jinyan; Fong, Simon; Sung, Yunsick; Cho, Kyungeun; Wong, Raymond; Wong, Kelvin K L

2016-01-01

An imbalanced dataset is defined as a training dataset that has imbalanced proportions of data in both interesting and uninteresting classes. Often in biomedical applications, samples from the stimulating class are rare in a population, such as medical anomalies, positive clinical tests, and particular diseases. Although the target samples in the primitive dataset are small in number, the induction of a classification model over such training data leads to poor prediction performance due to insufficient training from the minority class. In this paper, we use a novel class-balancing method named adaptive swarm cluster-based dynamic multi-objective synthetic minority oversampling technique (ASCB_DmSMOTE) to solve this imbalanced dataset problem, which is common in biomedical applications. The proposed method combines under-sampling and over-sampling into a swarm optimisation algorithm. It adaptively selects suitable parameters for the rebalancing algorithm to find the best solution. Compared with the other versions of the SMOTE algorithm, significant improvements, which include higher accuracy and credibility, are observed with ASCB_DmSMOTE. Our proposed method tactfully combines two rebalancing techniques together. It reasonably re-allocates the majority class in the details and dynamically optimises the two parameters of SMOTE to synthesise a reasonable scale of minority class for each clustered sub-imbalanced dataset. The proposed methods ultimately overcome other conventional methods and attains higher credibility with even greater accuracy of the classification model.

MULTI-LABEL ASRS DATASET CLASSIFICATION USING SEMI-SUPERVISED SUBSPACE CLUSTERING

Data.gov (United States)

National Aeronautics and Space Administration — MULTI-LABEL ASRS DATASET CLASSIFICATION USING SEMI-SUPERVISED SUBSPACE CLUSTERING MOHAMMAD SALIM AHMED, LATIFUR KHAN, NIKUNJ OZA, AND MANDAVA RAJESWARI Abstract....

Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs

Science.gov (United States)

Wang, Limin; Guo, Sheng; Huang, Weilin; Xiong, Yuanjun; Qiao, Yu

2017-04-01

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations. In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification. This paper focuses on large-scale scene recognition and makes two major contributions to tackle these issues. First, we propose a multi-resolution CNN architecture that captures visual content and structure at multiple levels. The multi-resolution CNNs are composed of coarse resolution CNNs and fine resolution CNNs, which are complementary to each other. Second, we design two knowledge guided disambiguation techniques to deal with the problem of label ambiguity. (i) We exploit the knowledge from the confusion matrix computed on validation data to merge ambiguous classes into a super category. (ii) We utilize the knowledge of extra networks to produce a soft label for each image. Then the super categories or soft labels are employed to guide CNN training on the Places2. We conduct extensive experiments on three large-scale image datasets (ImageNet, Places, and Places2), demonstrating the effectiveness of our approach. Furthermore, our method takes part in two major scene recognition challenges, and achieves the second place at the Places2 challenge in ILSVRC 2015, and the first place at the LSUN challenge in CVPR 2016. Finally, we directly test the learned representations on other scene benchmarks, and obtain the new state-of-the-art results on the MIT Indoor67 (86.7\\%) and SUN397 (72.0\\%). We release the code and models at~\\url{https://github.com/wanglimin/MRCNN-Scene-Recognition}.

Classification of multiple sclerosis patients by latent class analysis of magnetic resonance imaging characteristics.

Science.gov (United States)

Zwemmer, J N P; Berkhof, J; Castelijns, J A; Barkhof, F; Polman, C H; Uitdehaag, B M J

2006-10-01

Disease heterogeneity is a major issue in multiple sclerosis (MS). Classification of MS patients is usually based on clinical characteristics. More recently, a pathological classification has been presented. While clinical subtypes differ by magnetic resonance imaging (MRI) signature on a group level, a classification of individual MS patients based purely on MRI characteristics has not been presented so far. To investigate whether a restricted classification of MS patients can be made based on a combination of quantitative and qualitative MRI characteristics and to test whether the resulting subgroups are associated with clinical and laboratory characteristics. MRI examinations of the brain and spinal cord of 50 patients were scored for 21 quantitative and qualitative characteristics. Using latent class analysis, subgroups were identified, for whom disease characteristics and laboratory measures were compared. Latent class analysis revealed two subgroups that mainly differed in the extent of lesion confluency and MRI correlates of neuronal loss in the brain. Demographics and disease characteristics were comparable except for cognitive deficits. No correlations with laboratory measures were found. Latent class analysis offers a feasible approach for classifying subgroups of MS patients based on the presence of MRI characteristics. The reproducibility, longitudinal evolution and further clinical or prognostic relevance of the observed classification will have to be explored in a larger and independent sample of patients.

CT and MR imaging findings of endocrine tumor of the pancreas according to WHO classification

International Nuclear Information System (INIS)

Rha, Sung Eun; Jung, Seung Eun; Lee, Kang Hoon; Ku, Young Mi; Byun, Jae Young; Lee, Jae Mun

2007-01-01

The pancreatic endocrine tumors are rare neuroendocrine tumors of the pancreas originating from totipotential stem cells or differentiated mature endocrine cells within the exocrine gland. Endocrine tumors are usually classified into functioning and non-functioning tumors and presents with a range of benignity or malignancy. In this article, we present the various CT and MR imaging findings of endocrine tumors of pancreas according to recent WHO classification

A novel fruit shape classification method based on multi-scale analysis

Science.gov (United States)

Gui, Jiangsheng; Ying, Yibin; Rao, Xiuqin

2005-11-01

Shape is one of the major concerns and which is still a difficult problem in automated inspection and sorting of fruits. In this research, we proposed the multi-scale energy distribution (MSED) for object shape description, the relationship between objects shape and its boundary energy distribution at multi-scale was explored for shape extraction. MSED offers not only the mainly energy which represent primary shape information at the lower scales, but also subordinate energy which represent local shape information at higher differential scales. Thus, it provides a natural tool for multi resolution representation and can be used as a feature for shape classification. We addressed the three main processing steps in the MSED-based shape classification. They are namely, 1) image preprocessing and citrus shape extraction, 2) shape resample and shape feature normalization, 3) energy decomposition by wavelet and classification by BP neural network. Hereinto, shape resample is resample 256 boundary pixel from a curve which is approximated original boundary by using cubic spline in order to get uniform raw data. A probability function was defined and an effective method to select a start point was given through maximal expectation, which overcame the inconvenience of traditional methods in order to have a property of rotation invariants. The experiment result is relatively well normal citrus and serious abnormality, with a classification rate superior to 91.2%. The global correct classification rate is 89.77%, and our method is more effective than traditional method. The global result can meet the request of fruit grading.

A Multi-Classification Method of Improved SVM-based Information Fusion for Traffic Parameters Forecasting

Directory of Open Access Journals (Sweden)

Hongzhuan Zhao

2016-04-01

Full Text Available With the enrichment of perception methods, modern transportation system has many physical objects whose states are influenced by many information factors so that it is a typical Cyber-Physical System (CPS. Thus, the traffic information is generally multi-sourced, heterogeneous and hierarchical. Existing research results show that the multisourced traffic information through accurate classification in the process of information fusion can achieve better parameters forecasting performance. For solving the problem of traffic information accurate classification, via analysing the characteristics of the multi-sourced traffic information and using redefined binary tree to overcome the shortcomings of the original Support Vector Machine (SVM classification in information fusion, a multi-classification method using improved SVM in information fusion for traffic parameters forecasting is proposed. The experiment was conducted to examine the performance of the proposed scheme, and the results reveal that the method can get more accurate and practical outcomes.

On the role of cost-sensitive learning in multi-class brain-computer interfaces.

Science.gov (United States)

Devlaminck, Dieter; Waegeman, Willem; Wyns, Bart; Otte, Georges; Santens, Patrick

2010-06-01

Brain-computer interfaces (BCIs) present an alternative way of communication for people with severe disabilities. One of the shortcomings in current BCI systems, recently put forward in the fourth BCI competition, is the asynchronous detection of motor imagery versus resting state. We investigated this extension to the three-class case, in which the resting state is considered virtually lying between two motor classes, resulting in a large penalty when one motor task is misclassified into the other motor class. We particularly focus on the behavior of different machine-learning techniques and on the role of multi-class cost-sensitive learning in such a context. To this end, four different kernel methods are empirically compared, namely pairwise multi-class support vector machines (SVMs), two cost-sensitive multi-class SVMs and kernel-based ordinal regression. The experimental results illustrate that ordinal regression performs better than the other three approaches when a cost-sensitive performance measure such as the mean-squared error is considered. By contrast, multi-class cost-sensitive learning enables us to control the number of large errors made between two motor tasks.

Analysis of classification and surgical treatment of cervical dumbbell-shaped tumors

Directory of Open Access Journals (Sweden)

LIU Jia-gang

2013-11-01

Full Text Available Objective To investigate the clinical characteristics, classification, surgical approach, complication and prognosis of cervical dumbbell-shaped tumors. Methods Twenty-six consecutive cases with cervical dumbbell-shaped tumors were retrospectively studied. According to tumor location by imaging examination, all tumors were divided into 3 types. Type Ⅰ (17 cases was mostly intravertebral and foraminal. Surgery through posterior approach was performed and internal fixation was operated in 8 cases. Type Ⅱ (4 cases was mostly paravertebral and foraminal. Surgery through the anterolateral approach was performed without internal fixation. Type Ⅲ (5 cases was equalization of intravertebral and paravertebral, and underwent surgery through combined posterior-anterolateral approach and internal fixation was performed in all of those cases. If the unilateral facet joint was destroyed, internal fixation was necessary. Lateral mass screw internal fixation and transpedicular screw fixation supplemented by fusion with autologous iliac bone graft were used to maintain cervical spinal stability. Results Among 26 patients there were 19 schwannomas, 4 neurofibromas, 2 gangliocytoma and 1 spinal meningioma. Total and subtotal tumor resection was achieved in 23 and 3 patients respectively. Among them 50% (13/26 of the cases were used internal fixation including 8 TypeⅠand 5 Type Ⅲ patients. The follow-up period was from 7 to 62 months, and mean time was 30 months. Four cases (15.38% were found local tumor recurrence. Two cases suffered with surgical infection and cerebrospinal fluid leakage. There was no spinal cord injury and spinal deformity. Conclusion In order to increase the total resection rate and decrease recurrence rate, surgical approach should be selected according to the imaging classification of tumors. Stability reconstruction is absolutely necessary for the patients with facet joint destroyed.

Benign fatty tumors: classification, clinical course, imaging appearance, and treatment

International Nuclear Information System (INIS)

Bancroft, Laura W.; Kransdorf, Mark J.; Peterson, Jeffrey J.; O'Connor, Mary I.

2006-01-01

Lipoma is the most common soft-tissue tumor, with a wide spectrum of clinical presentations and imaging appearances. Several subtypes are described, ranging from lesions entirely composed of mature adipose tissue to tumors intimately associated with nonadipose tissue, to those composed of brown fat. The imaging appearance of these fatty masses is frequently sufficiently characteristic to allow a specific diagnosis. However, in other cases, although a specific diagnosis is not achievable, a meaningful limited differential diagnosis can be established. The purpose of this manuscript is to review the spectrum of benign fatty tumors highlighting the current classification system, clinical presentation and behavior, spectrum of imaging appearances, and treatment. The imaging review emphasizes computed tomography (CT) scanning and magnetic resonance (MR) imaging, differentiating radiologic features. (orig.)

Association between traditional clinical high-risk features and gene expression profile classification in uveal melanoma.

Science.gov (United States)

Nguyen, Brandon T; Kim, Ryan S; Bretana, Maria E; Kegley, Eric; Schefler, Amy C

2018-02-01

To evaluate the association between traditional clinical high-risk features of uveal melanoma patients and gene expression profile (GEP). This was a retrospective, single-center, case series of patients with uveal melanoma. Eighty-three patients met inclusion criteria for the study. Patients were examined for the following clinical risk factors: drusen/retinal pigment epithelium (RPE) changes, vascularity on B-scan, internal reflectivity on A-scan, subretinal fluid (SRF), orange pigment, apical tumor height/thickness, and largest basal dimensions (LBD). A novel point system was created to grade the high-risk clinical features of each tumor. Further analyses were performed to assess the degree of association between GEP and each individual risk factor, total clinical risk score, vascularity, internal reflectivity, American Joint Committee on Cancer (AJCC) tumor stage classification, apical tumor height/thickness, and LBD. Of the 83 total patients, 41 were classified as GEP class 1A, 17 as class 1B, and 25 as class 2. The presence of orange pigment, SRF, low internal reflectivity and vascularity on ultrasound, and apical tumor height/thickness ≥ 2 mm were not statistically significantly associated with GEP class. Lack of drusen/RPE changes demonstrated a trend toward statistical association with GEP class 2 compared to class 1A/1B. LBD and advancing AJCC stage was statistically associated with higher GEP class. In this cohort, AJCC stage classification and LBD were the only clinical features statistically associated with GEP class. Clinicians should use caution when inferring the growth potential of melanocytic lesions solely from traditional funduscopic and ultrasonographic risk factors without GEP data.

International society of neuropathology-haarlem consensus guidelines for nervous system tumor classification and grading

NARCIS (Netherlands)

Louis, D.N.; Perry, A.; Burger, P.; Ellison, D.W.; Reifenberger, G.; Deimling, A. Von; Aldape, K.; Brat, D.; Collins, V.P.; Eberhart, C.; Figarella-Branger, D.; Fuller, G.N.; Giangaspero, F.; Giannini, C.; Hawkins, C.; Kleihues, P.; Korshunov, A.; Kros, J.M.; Lopes, M. Beatriz; Ng, H.K.; Ohgaki, H.; Paulus, W.; Pietsch, T.; Rosenblum, M.; Rushing, E.; Soylemezoglu, F.; Wiestler, O.; Wesseling, P.

2014-01-01

Major discoveries in the biology of nervous system tumors have raised the question of how non-histological data such as molecular information can be incorporated into the next World Health Organization (WHO) classification of central nervous system tumors. To address this question, a meeting of

Classification of brain tumors by means of proton nuclear magnetic resonance (NMR) spectroscopy

International Nuclear Information System (INIS)

Sottile, V.S.; Zanchi, D.E.

2017-01-01

In the present work, at the request of health professionals, a computer application named “ViDa” was developed. The aim of this study is to differentiate brain lesions according to whether or not they are tumors, and their subsequent classification into different tumor types using magnetic resonance spectroscopy (SVS) with an echo time of 30 milliseconds. For this development, different areas of knowledge were integrated, among which are Artificial intelligence, physics, programming, physiopathology, images in medicine, among others. Biomedical imaging can be divided into two stages: the pre-processing, performed by the resonator, and post-processing software, performed by ViDa, for the interpretation of the data. This application is included within the Medical Informatics area, as it provides assistance for clinical decision making. The role of the biomedical engineer is fulfilled by developing a health technology in response to a manifested real-life problem. The tool developed shows promising results achieving a 100% Sensitivity, 73% Specificity, 77% Positive Predictive Value and 100% Negative Predictive Value reported in 21 cases tested. The correct classifications of the tumor’s origin reach 70%, the classification of non-astrocytic lesions achieves 67% of correct classifications in that the gradation of astrocytomas achieves a 57% of gradations that agree with biopsies and 43% of slight errors. It was possible to develop an application of assistance to the diagnosis, which together with others medical tests, will make it possible to sharpen the diagnoses of brain tumors. (authors) [es

An enhanced data visualization method for diesel engine malfunction classification using multi-sensor signals.

Science.gov (United States)

Li, Yiqing; Wang, Yu; Zi, Yanyang; Zhang, Mingquan

2015-10-21

The various multi-sensor signal features from a diesel engine constitute a complex high-dimensional dataset. The non-linear dimensionality reduction method, t-distributed stochastic neighbor embedding (t-SNE), provides an effective way to implement data visualization for complex high-dimensional data. However, irrelevant features can deteriorate the performance of data visualization, and thus, should be eliminated a priori. This paper proposes a feature subset score based t-SNE (FSS-t-SNE) data visualization method to deal with the high-dimensional data that are collected from multi-sensor signals. In this method, the optimal feature subset is constructed by a feature subset score criterion. Then the high-dimensional data are visualized in 2-dimension space. According to the UCI dataset test, FSS-t-SNE can effectively improve the classification accuracy. An experiment was performed with a large power marine diesel engine to validate the proposed method for diesel engine malfunction classification. Multi-sensor signals were collected by a cylinder vibration sensor and a cylinder pressure sensor. Compared with other conventional data visualization methods, the proposed method shows good visualization performance and high classification accuracy in multi-malfunction classification of a diesel engine.

EnzML: multi-label prediction of enzyme classes using InterPro signatures

Directory of Open Access Journals (Sweden)

De Ferrari Luna

2012-04-01

Full Text Available Abstract Background Manual annotation of enzymatic functions cannot keep up with automatic genome sequencing. In this work we explore the capacity of InterPro sequence signatures to automatically predict enzymatic function. Results We present EnzML, a multi-label classification method that can efficiently account also for proteins with multiple enzymatic functions: 50,000 in UniProt. EnzML was evaluated using a standard set of 300,747 proteins for which the manually curated Swiss-Prot and KEGG databases have agreeing Enzyme Commission (EC annotations. EnzML achieved more than 98% subset accuracy (exact match of all correct Enzyme Commission classes of a protein for the entire dataset and between 87 and 97% subset accuracy in reannotating eight entire proteomes: human, mouse, rat, mouse-ear cress, fruit fly, the S. pombe yeast, the E. coli bacterium and the M. jannaschii archaebacterium. To understand the role played by the dataset size, we compared the cross-evaluation results of smaller datasets, either constructed at random or from specific taxonomic domains such as archaea, bacteria, fungi, invertebrates, plants and vertebrates. The results were confirmed even when the redundancy in the dataset was reduced using UniRef100, UniRef90 or UniRef50 clusters. Conclusions InterPro signatures are a compact and powerful attribute space for the prediction of enzymatic function. This representation makes multi-label machine learning feasible in reasonable time (30 minutes to train on 300,747 instances with 10,852 attributes and 2,201 class values using the Mulan Binary Relevance Nearest Neighbours algorithm implementation (BR-kNN.

Random forest wetland classification using ALOS-2 L-band, RADARSAT-2 C-band, and TerraSAR-X imagery

Science.gov (United States)

Mahdianpari, Masoud; Salehi, Bahram; Mohammadimanesh, Fariba; Motagh, Mahdi

2017-08-01

Wetlands are important ecosystems around the world, although they are degraded due both to anthropogenic and natural process. Newfoundland is among the richest Canadian province in terms of different wetland classes. Herbaceous wetlands cover extensive areas of the Avalon Peninsula, which are the habitat of a number of animal and plant species. In this study, a novel hierarchical object-based Random Forest (RF) classification approach is proposed for discriminating between different wetland classes in a sub-region located in the north eastern portion of the Avalon Peninsula. Particularly, multi-polarization and multi-frequency SAR data, including X-band TerraSAR-X single polarized (HH), L-band ALOS-2 dual polarized (HH/HV), and C-band RADARSAT-2 fully polarized images, were applied in different classification levels. First, a SAR backscatter analysis of different land cover types was performed by training data and used in Level-I classification to separate water from non-water classes. This was followed by Level-II classification, wherein the water class was further divided into shallow- and deep-water classes, and the non-water class was partitioned into herbaceous and non-herbaceous classes. In Level-III classification, the herbaceous class was further divided into bog, fen, and marsh classes, while the non-herbaceous class was subsequently partitioned into urban, upland, and swamp classes. In Level-II and -III classifications, different polarimetric decomposition approaches, including Cloude-Pottier, Freeman-Durden, Yamaguchi decompositions, and Kennaugh matrix elements were extracted to aid the RF classifier. The overall accuracy and kappa coefficient were determined in each classification level for evaluating the classification results. The importance of input features was also determined using the variable importance obtained by RF. It was found that the Kennaugh matrix elements, Yamaguchi, and Freeman-Durden decompositions were the most important parameters

Changing Histopathological Diagnostics by Genome-Based Tumor Classification

Directory of Open Access Journals (Sweden)

Michael Kloth

2014-05-01

Full Text Available Traditionally, tumors are classified by histopathological criteria, i.e., based on their specific morphological appearances. Consequently, current therapeutic decisions in oncology are strongly influenced by histology rather than underlying molecular or genomic aberrations. The increase of information on molecular changes however, enabled by the Human Genome Project and the International Cancer Genome Consortium as well as the manifold advances in molecular biology and high-throughput sequencing techniques, inaugurated the integration of genomic information into disease classification. Furthermore, in some cases it became evident that former classifications needed major revision and adaption. Such adaptations are often required by understanding the pathogenesis of a disease from a specific molecular alteration, using this molecular driver for targeted and highly effective therapies. Altogether, reclassifications should lead to higher information content of the underlying diagnoses, reflecting their molecular pathogenesis and resulting in optimized and individual therapeutic decisions. The objective of this article is to summarize some particularly important examples of genome-based classification approaches and associated therapeutic concepts. In addition to reviewing disease specific markers, we focus on potentially therapeutic or predictive markers and the relevance of molecular diagnostics in disease monitoring.

Assessment of multi class kinematic wave models

NARCIS (Netherlands)

Van Wageningen-Kessels, F.L.M.; Van Lint, J.W.C.; Vuik, C.; Hoogendoorn, S.P.

2012-01-01

In the last decade many multi class kinematic wave (MCKW) traffic ow models have been proposed. MCKW models introduce heterogeneity among vehicles and drivers. For example, they take into account differences in (maximum) velocities and driving style. Nevertheless, the models are macroscopic and the

EEG source space analysis of the supervised factor analytic approach for the classification of multi-directional arm movement

Science.gov (United States)

Shenoy Handiru, Vikram; Vinod, A. P.; Guan, Cuntai

2017-08-01

Objective. In electroencephalography (EEG)-based brain-computer interface (BCI) systems for motor control tasks the conventional practice is to decode motor intentions by using scalp EEG. However, scalp EEG only reveals certain limited information about the complex tasks of movement with a higher degree of freedom. Therefore, our objective is to investigate the effectiveness of source-space EEG in extracting relevant features that discriminate arm movement in multiple directions. Approach. We have proposed a novel feature extraction algorithm based on supervised factor analysis that models the data from source-space EEG. To this end, we computed the features from the source dipoles confined to Brodmann areas of interest (BA4a, BA4p and BA6). Further, we embedded class-wise labels of multi-direction (multi-class) source-space EEG to an unsupervised factor analysis to make it into a supervised learning method. Main Results. Our approach provided an average decoding accuracy of 71% for the classification of hand movement in four orthogonal directions, that is significantly higher (>10%) than the classification accuracy obtained using state-of-the-art spatial pattern features in sensor space. Also, the group analysis on the spectral characteristics of source-space EEG indicates that the slow cortical potentials from a set of cortical source dipoles reveal discriminative information regarding the movement parameter, direction. Significance. This study presents evidence that low-frequency components in the source space play an important role in movement kinematics, and thus it may lead to new strategies for BCI-based neurorehabilitation.

Multi-agent Negotiation Mechanisms for Statistical Target Classification in Wireless Multimedia Sensor Networks

Science.gov (United States)

Wang, Xue; Bi, Dao-wei; Ding, Liang; Wang, Sheng

2007-01-01

The recent availability of low cost and miniaturized hardware has allowed wireless sensor networks (WSNs) to retrieve audio and video data in real world applications, which has fostered the development of wireless multimedia sensor networks (WMSNs). Resource constraints and challenging multimedia data volume make development of efficient algorithms to perform in-network processing of multimedia contents imperative. This paper proposes solving problems in the domain of WMSNs from the perspective of multi-agent systems. The multi-agent framework enables flexible network configuration and efficient collaborative in-network processing. The focus is placed on target classification in WMSNs where audio information is retrieved by microphones. To deal with the uncertainties related to audio information retrieval, the statistical approaches of power spectral density estimates, principal component analysis and Gaussian process classification are employed. A multi-agent negotiation mechanism is specially developed to efficiently utilize limited resources and simultaneously enhance classification accuracy and reliability. The negotiation is composed of two phases, where an auction based approach is first exploited to allocate the classification task among the agents and then individual agent decisions are combined by the committee decision mechanism. Simulation experiments with real world data are conducted and the results show that the proposed statistical approaches and negotiation mechanism not only reduce memory and computation requirements in WMSNs but also significantly enhance classification accuracy and reliability. PMID:28903223

Multi-objective evolutionary algorithms for fuzzy classification in survival prediction.

Science.gov (United States)

Jiménez, Fernando; Sánchez, Gracia; Juárez, José M

2014-03-01

This paper presents a novel rule-based fuzzy classification methodology for survival/mortality prediction in severe burnt patients. Due to the ethical aspects involved in this medical scenario, physicians tend not to accept a computer-based evaluation unless they understand why and how such a recommendation is given. Therefore, any fuzzy classifier model must be both accurate and interpretable. The proposed methodology is a three-step process: (1) multi-objective constrained optimization of a patient's data set, using Pareto-based elitist multi-objective evolutionary algorithms to maximize accuracy and minimize the complexity (number of rules) of classifiers, subject to interpretability constraints; this step produces a set of alternative (Pareto) classifiers; (2) linguistic labeling, which assigns a linguistic label to each fuzzy set of the classifiers; this step is essential to the interpretability of the classifiers; (3) decision making, whereby a classifier is chosen, if it is satisfactory, according to the preferences of the decision maker. If no classifier is satisfactory for the decision maker, the process starts again in step (1) with a different input parameter set. The performance of three multi-objective evolutionary algorithms, niched pre-selection multi-objective algorithm, elitist Pareto-based multi-objective evolutionary algorithm for diversity reinforcement (ENORA) and the non-dominated sorting genetic algorithm (NSGA-II), was tested using a patient's data set from an intensive care burn unit and a standard machine learning data set from an standard machine learning repository. The results are compared using the hypervolume multi-objective metric. Besides, the results have been compared with other non-evolutionary techniques and validated with a multi-objective cross-validation technique. Our proposal improves the classification rate obtained by other non-evolutionary techniques (decision trees, artificial neural networks, Naive Bayes, and case

Integrating molecular markers into the World Health Organization classification of CNS tumors: a survey of the neuro-oncology community.

Science.gov (United States)

Aldape, Kenneth; Nejad, Romina; Louis, David N; Zadeh, Gelareh

2017-03-01

Molecular markers provide important biological and clinical information related to the classification of brain tumors, and the integration of relevant molecular parameters into brain tumor classification systems has been a widely discussed topic in neuro-oncology over the past decade. With recent advances in the development of clinically relevant molecular signatures and the 2016 World Health Organization (WHO) update, the views of the neuro-oncology community on such changes would be informative for implementing this process. A survey with 8 questions regarding molecular markers in tumor classification was sent to an email list of Society for Neuro-Oncology members and attendees of prior meetings (n=5065). There were 403 respondents. Analysis was performed using whole group response, based on self-reported subspecialty. The survey results show overall strong support for incorporating molecular knowledge into the classification and clinical management of brain tumors. Across all 7 subspecialty groups, ≥70% of respondents agreed to this integration. Interestingly, some variability is seen among subspecialties, notably with lowest support from neuropathologists, which may reflect their roles in implementing such diagnostic technologies. Based on a survey provided to the neuro-oncology community, we report strong support for the integration of molecular markers into the WHO classification of brain tumors, as well as for using an integrated "layered" diagnostic format. While membership from each specialty showed support, there was variation by specialty in enthusiasm regarding proposed changes. The initial results of this survey influenced the deliberations underlying the 2016 WHO classification of tumors of the central nervous system. © The Author(s) 2017. Published by Oxford University Press on behalf of the Society for Neuro-Oncology.

Data Processing And Machine Learning Methods For Multi-Modal Operator State Classification Systems

Science.gov (United States)

Hearn, Tristan A.

2015-01-01

This document is intended as an introduction to a set of common signal processing learning methods that may be used in the software portion of a functional crew state monitoring system. This includes overviews of both the theory of the methods involved, as well as examples of implementation. Practical considerations are discussed for implementing modular, flexible, and scalable processing and classification software for a multi-modal, multi-channel monitoring system. Example source code is also given for all of the discussed processing and classification methods.

Multichannel imaging to quantify four classes of pharmacokinetic distribution in tumors.

Science.gov (United States)

Bhatnagar, Sumit; Deschenes, Emily; Liao, Jianshan; Cilliers, Cornelius; Thurber, Greg M

2014-10-01

Low and heterogeneous delivery of drugs and imaging agents to tumors results in decreased efficacy and poor imaging results. Systemic delivery involves a complex interplay of drug properties and physiological factors, and heterogeneity in the tumor microenvironment makes predicting and overcoming these limitations exceptionally difficult. Theoretical models have indicated that there are four different classes of pharmacokinetic behavior in tissue, depending on the fundamental steps in distribution. In order to study these limiting behaviors, we used multichannel fluorescence microscopy and stitching of high-resolution images to examine the distribution of four agents in the same tumor microenvironment. A validated generic partial differential equation model with a graphical user interface was used to select fluorescent agents exhibiting these four classes of behavior, and the imaging results agreed with predictions. BODIPY-FL exhibited higher concentrations in tissue with high blood flow, cetuximab gave perivascular distribution limited by permeability, high plasma protein and target binding resulted in diffusion-limited distribution for Hoechst 33342, and Integrisense 680 was limited by the number of binding sites in the tissue. Together, the probes and simulations can be used to investigate distribution in other tumor models, predict tumor drug distribution profiles, and design and interpret in vivo experiments. © 2014 Wiley Periodicals, Inc. and the American Pharmacists Association.

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

Science.gov (United States)

Bowman, Tyler; Chavez, Tanny; Khan, Kamrul; Wu, Jingxian; Chakraborty, Avishek; Rajaram, Narasimhan; Bailey, Keith; El-Shenawee, Magda

2018-02-01

This paper investigates terahertz (THz) imaging and classification of freshly excised murine xenograft breast cancer tumors. These tumors are grown via injection of E0771 breast adenocarcinoma cells into the flank of mice maintained on high-fat diet. Within 1 h of excision, the tumor and adjacent tissues are imaged using a pulsed THz system in the reflection mode. The THz images are classified using a statistical Bayesian mixture model with unsupervised and supervised approaches. Correlation with digitized pathology images is conducted using classification images assigned by a modal class decision rule. The corresponding receiver operating characteristic curves are obtained based on the classification results. A total of 13 tumor samples obtained from 9 tumors are investigated. The results show good correlation of THz images with pathology results in all samples of cancer and fat tissues. For tumor samples of cancer, fat, and muscle tissues, THz images show reasonable correlation with pathology where the primary challenge lies in the overlapping dielectric properties of cancer and muscle tissues. The use of a supervised regression approach shows improvement in the classification images although not consistently in all tissue regions. Advancing THz imaging of breast tumors from mice and the development of accurate statistical models will ultimately progress the technique for the assessment of human breast tumor margins.

Neuroendocrine tumors of colon and rectum: validation of clinical and prognostic values of the World Health Organization 2010 grading classifications and European Neuroendocrine Tumor Society staging systems.

Science.gov (United States)

Shen, Chaoyong; Yin, Yuan; Chen, Huijiao; Tang, Sumin; Yin, Xiaonan; Zhou, Zongguang; Zhang, Bo; Chen, Zhixin

2017-03-28

This study evaluated and compared the clinical and prognostic values of the grading criteria used by the World Health Organization (WHO) and the European Neuroendocrine Tumors Society (ENETS). Moreover, this work assessed the current best prognostic model for colorectal neuroendocrine tumors (CRNETs). The 2010 WHO classifications and the ENETS systems can both stratify the patients into prognostic groups, although the 2010 WHO criteria is more applicable to CRNET patients. Along with tumor location, the 2010 WHO criteria are important independent prognostic parameters for CRNETs in both univariate and multivariate analyses through Cox regression (P<0.05). Data from 192 consecutive patients histopathologically diagnosed with CRNETs and had undergone surgical resection from January 2009 to May 2016 in a single center were retrospectively analyzed. Findings suggest that the WHO classifications are superior over the ENETS classification system in predicting the prognosis of CRNETs. Additionally, the WHO classifications can be widely used in clinical practice.

Immunotherapy of MHC class I-deficient tumors

Czech Academy of Sciences Publication Activity Database

Reiniš, Milan

2010-01-01

Roč. 6, č. 10 (2010), s. 1577-1589 ISSN 1479-6694 R&D Projects: GA ČR GA301/07/1410; GA ČR GAP301/10/2174; GA AV ČR IAA500520807; GA AV ČR IAA500520605 EU Projects: European Commission(XE) 18933 - CLINIGENE Institutional research plan: CEZ:AV0Z50520514 Keywords : tumor vaccine * MHC class I expression * antigen presenting machinery Subject RIV: EB - Genetics ; Molecular Biology Impact factor: 2.455, year: 2010

Joint Multi-scale Convolution Neural Network for Scene Classification of High Resolution Remote Sensing Imagery

Directory of Open Access Journals (Sweden)

ZHENG Zhuo

2018-05-01

Full Text Available High resolution remote sensing imagery scene classification is important for automatic complex scene recognition, which is the key technology for military and disaster relief, etc. In this paper, we propose a novel joint multi-scale convolution neural network (JMCNN method using a limited amount of image data for high resolution remote sensing imagery scene classification. Different from traditional convolutional neural network, the proposed JMCNN is an end-to-end training model with joint enhanced high-level feature representation, which includes multi-channel feature extractor, joint multi-scale feature fusion and Softmax classifier. Multi-channel and scale convolutional extractors are used to extract scene middle features, firstly. Then, in order to achieve enhanced high-level feature representation in a limit dataset, joint multi-scale feature fusion is proposed to combine multi-channel and scale features using two feature fusions. Finally, enhanced high-level feature representation can be used for classification by Softmax. Experiments were conducted using two limit public UCM and SIRI datasets. Compared to state-of-the-art methods, the JMCNN achieved improved performance and great robustness with average accuracies of 89.3% and 88.3% on the two datasets.

SUPPORT VECTOR MACHINE CLASSIFICATION OF OBJECT-BASED DATA FOR CROP MAPPING, USING MULTI-TEMPORAL LANDSAT IMAGERY

Directory of Open Access Journals (Sweden)

R. Devadas

2012-07-01

Full Text Available Crop mapping and time series analysis of agronomic cycles are critical for monitoring land use and land management practices, and analysing the issues of agro-environmental impacts and climate change. Multi-temporal Landsat data can be used to analyse decadal changes in cropping patterns at field level, owing to its medium spatial resolution and historical availability. This study attempts to develop robust remote sensing techniques, applicable across a large geographic extent, for state-wide mapping of cropping history in Queensland, Australia. In this context, traditional pixel-based classification was analysed in comparison with image object-based classification using advanced supervised machine-learning algorithms such as Support Vector Machine (SVM. For the Darling Downs region of southern Queensland we gathered a set of Landsat TM images from the 2010–2011 cropping season. Landsat data, along with the vegetation index images, were subjected to multiresolution segmentation to obtain polygon objects. Object-based methods enabled the analysis of aggregated sets of pixels, and exploited shape-related and textural variation, as well as spectral characteristics. SVM models were chosen after examining three shape-based parameters, twenty-three textural parameters and ten spectral parameters of the objects. We found that the object-based methods were superior to the pixel-based methods for classifying 4 major landuse/land cover classes, considering the complexities of within field spectral heterogeneity and spectral mixing. Comparative analysis clearly revealed that higher overall classification accuracy (95% was observed in the object-based SVM compared with that of traditional pixel-based classification (89% using maximum likelihood classifier (MLC. Object-based classification also resulted speckle-free images. Further, object-based SVM models were used to classify different broadacre crop types for summer and winter seasons. The influence of

Tumor vaccine composed of C-class CpG oligodeoxynucleotides and irradiated tumor cells induces long-term antitumor immunity

Directory of Open Access Journals (Sweden)

Cerkovnik Petra

2010-09-01

Full Text Available Abstract Background An ideal tumor vaccine should activate both effector and memory immune response against tumor-specific antigens. Beside the CD8+ T cells that play a central role in the generation of a protective immune response and of long-term memory, dendritic cells (DCs are important for the induction, coordination and regulation of the adaptive immune response. The DCs can conduct all of the elements of the immune orchestra and are therefore a fundamental target and tool for vaccination. The present study was aimed at assessing the ability of tumor vaccine composed of C-class CpG ODNs and irradiated melanoma tumor cells B16F1 followed by two additional injections of CpG ODNs to induce the generation of a functional long-term memory response in experimental tumor model in mice (i.p. B16F1. Results It has been shown that the functional memory response in vaccinated mice persists for at least 60 days after the last vaccination. Repeated vaccination also improves the survival of experimental animals compared to single vaccination, whereas the proportion of animals totally protected from the development of aggressive i.p. B16F1 tumors after vaccination repeated three times varies between 88.9%-100.0%. Additionally, the long-term immune memory and tumor protection is maintained over a prolonged period of time of at least 8 months. Finally, it has been demonstrated that following the vaccination the tumor-specific memory cells predominantly reside in bone marrow and peritoneal tissue and are in a more active state than their splenic counterparts. Conclusions In this study we demonstrated that tumor vaccine composed of C-class CpG ODNs and irradiated tumor cells followed by two additional injections of CpG ODNs induces a long-term immunity against aggressive B16F1 tumors.

CrossLink: a novel method for cross-condition classification of cancer subtypes.

Science.gov (United States)

Ma, Chifeng; Sastry, Konduru S; Flore, Mario; Gehani, Salah; Al-Bozom, Issam; Feng, Yusheng; Serpedin, Erchin; Chouchane, Lotfi; Chen, Yidong; Huang, Yufei

2016-08-22

We considered the prediction of cancer classes (e.g. subtypes) using patient gene expression profiles that contain both systematic and condition-specific biases when compared with the training reference dataset. The conventional normalization-based approaches cannot guarantee that the gene signatures in the reference and prediction datasets always have the same distribution for all different conditions as the class-specific gene signatures change with the condition. Therefore, the trained classifier would work well under one condition but not under another. To address the problem of current normalization approaches, we propose a novel algorithm called CrossLink (CL). CL recognizes that there is no universal, condition-independent normalization mapping of signatures. In contrast, it exploits the fact that the signature is unique to its associated class under any condition and thus employs an unsupervised clustering algorithm to discover this unique signature. We assessed the performance of CL for cross-condition predictions of PAM50 subtypes of breast cancer by using a simulated dataset modeled after TCGA BRCA tumor samples with a cross-validation scheme, and datasets with known and unknown PAM50 classification. CL achieved prediction accuracy >73 %, highest among other methods we evaluated. We also applied the algorithm to a set of breast cancer tumors derived from Arabic population to assign a PAM50 classification to each tumor based on their gene expression profiles. A novel algorithm CrossLink for cross-condition prediction of cancer classes was proposed. In all test datasets, CL showed robust and consistent improvement in prediction performance over other state-of-the-art normalization and classification algorithms.

CT features of the subtypes of thymic epithelial tumors on the basis of the world health organization classification

International Nuclear Information System (INIS)

Guo Xiaoyu; Yu Hong; Xiao Xiangsheng

2013-01-01

Thymic epithelial tumors including thymomas and thymic carcinomas have well-known heterogeneous oncologic behaviors and variable histologic features. They show variable and unpredictable evolutions ranging from an indolent non-invasive feature to a highly infiltrative and metastasising one. Currently, CT is a common and efficient imaging method for assessing thymic epithelial tumors. CT evaluation is the main reference for preoperative clinic staging and histological classification. CT features of subtypes of thymic epithelial tumors on the basis of the World Health Organization classification provide the foundation for the diagnosis and predicting prognosis. (authors)

Multi-Modal Curriculum Learning for Semi-Supervised Image Classification.

Science.gov (United States)

Gong, Chen; Tao, Dacheng; Maybank, Stephen J; Liu, Wei; Kang, Guoliang; Yang, Jie

2016-07-01

Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets.

Classification of tumor based on magnetic resonance (MR) brain images using wavelet energy feature and neuro-fuzzy model

Science.gov (United States)

Damayanti, A.; Werdiningsih, I.

2018-03-01

The brain is the organ that coordinates all the activities that occur in our bodies. Small abnormalities in the brain will affect body activity. Tumor of the brain is a mass formed a result of cell growth not normal and unbridled in the brain. MRI is a non-invasive medical test that is useful for doctors in diagnosing and treating medical conditions. The process of classification of brain tumor can provide the right decision and correct treatment and right on the process of treatment of brain tumor. In this study, the classification process performed to determine the type of brain tumor disease, namely Alzheimer’s, Glioma, Carcinoma and normal, using energy coefficient and ANFIS. Process stages in the classification of images of MR brain are the extraction of a feature, reduction of a feature, and process of classification. The result of feature extraction is a vector approximation of each wavelet decomposition level. The feature reduction is a process of reducing the feature by using the energy coefficients of the vector approximation. The feature reduction result for energy coefficient of 100 per feature is 1 x 52 pixels. This vector will be the input on the classification using ANFIS with Fuzzy C-Means and FLVQ clustering process and LM back-propagation. Percentage of success rate of MR brain images recognition using ANFIS-FLVQ, ANFIS, and LM back-propagation was obtained at 100%.

Image Denoising And Segmentation Approchto Detect Tumor From BRAINMRI Images

Directory of Open Access Journals (Sweden)

Shanta Rangaswamy

2018-04-01

Full Text Available The detection of the Brain Tumor is a challenging problem, due to the structure of the Tumor cells in the brain. This project presents a systematic method that enhances the detection of brain tumor cells and to analyze functional structures by training and classification of the samples in SVM and tumor cell segmentation of the sample using DWT algorithm. From the input MRI Images collected, first noise is removed from MRI images by applying wiener filtering technique. In image enhancement phase, all the color components of MRI Images will be converted into gray scale image and make the edges clear in the image to get better identification and improvised quality of the image. In the segmentation phase, DWT on MRI Image to segment the grey-scale image is performed. During the post-processing, classification of tumor is performed by using SVM classifier. Wiener Filter, DWT, SVM Segmentation strategies were used to find and group the tumor position in the MRI filtered picture respectively. An essential perception in this work is that multi arrange approach utilizes various leveled classification strategy which supports execution altogether. This technique diminishes the computational complexity quality in time and memory. This classification strategy works accurately on all images and have achieved the accuracy of 93%.

PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications

OpenAIRE

Pasquier, Claude; Promponas, Vasilis; Hamodrakas, Stavros

2009-01-01

International audience; A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the av...

Morphologic classification of ductal breast tumors on ultrasound : differential diagnosis of benign and malignant tumors

International Nuclear Information System (INIS)

Won, Mi Sook; Chung, Soo Young; Yang, Ik; Lee, Yul; Park, Hai Jung; Lee, Myoung Hwan; Yoon, In Sook; Koh, Mi Gyoung

1997-01-01

To evaluate the morphologic differential diagnosis of benign and malignant ductal breast tumors, as seen on US US findings in 29 pathologically proven cases of ductal breast tumor were retrospectively reviewed. All patients were female and their mean age was 42 years. Nineteen tumors were benign and ten were malignant, and all ductal or cystic lesions showed solid masses. According to the location of the mural nodule, we classified the sonographic appearance of these tumors into three types:intraductal, intracystic and amorphic. The intraductal type was divided into three subtypes:incompletely obstructive, completely obstructive and multiple mural nodules. For the intracystic type, too, three subtypes were designated:the intracystic mural nodule (mural cyst), intracystic mural nodule with the duct (mural cyst+duct) and intracystic multiple mural nodules. The amorphic type is defined as an atypical ductal tumor with the mural nodule extending into adjacent parenchyma. The margin of the duct or cyst was smooth in 68.4% of benign, and irregular in 90% of malignant ductal tumors. Internal echogeneity of the duct or cyst usually showed homogeneity in both benign and malignant tumors. 73.7% of tumors connecting the duct were benign and 50% were malignant. In benign tumors, 52.6% of mural nodule had an irregular margin, while in malignant tumors, the corresponding proportion was 100%;both types usually showed heterogeneous hypoechogeneity. Among benign tumors, the most common morphologic type was the intraductal incompletely obstructive subtype (36.8%);among those that were malignant, the amorphic type was most common, accounting for 40% of tumors. No amorphic type was benign and no incompletely obstructive subtype was malignant. When ductal breast tumors are morphologically classified on the basis of sonographic findings, the intraductal incompletely obstructive subtype suggests benignancy, and the amorphic type, malignancy. The morphologic classification of ductal

Enhanced risk management by an emerging multi-agent architecture

Science.gov (United States)

Lin, Sin-Jin; Hsu, Ming-Fu

2014-07-01

Classification in imbalanced datasets has attracted much attention from researchers in the field of machine learning. Most existing techniques tend not to perform well on minority class instances when the dataset is highly skewed because they focus on minimising the forecasting error without considering the relative distribution of each class. This investigation proposes an emerging multi-agent architecture, grounded on cooperative learning, to solve the class-imbalanced classification problem. Additionally, this study deals further with the obscure nature of the multi-agent architecture and expresses comprehensive rules for auditors. The results from this study indicate that the presented model performs satisfactorily in risk management and is able to tackle a highly class-imbalanced dataset comparatively well. Furthermore, the knowledge visualised process, supported by real examples, can assist both internal and external auditors who must allocate limited detecting resources; they can take the rules as roadmaps to modify the auditing programme.

Naïve and Robust: Class-Conditional Independence in Human Classification Learning

Science.gov (United States)

Jarecki, Jana B.; Meder, Björn; Nelson, Jonathan D.

2018-01-01

Humans excel in categorization. Yet from a computational standpoint, learning a novel probabilistic classification task involves severe computational challenges. The present paper investigates one way to address these challenges: assuming class-conditional independence of features. This feature independence assumption simplifies the inference…

Automatic detection and classification of breast tumors in ultrasonic images using texture and morphological features.

Science.gov (United States)

Su, Yanni; Wang, Yuanyuan; Jiao, Jing; Guo, Yi

2011-01-01

Due to severe presence of speckle noise, poor image contrast and irregular lesion shape, it is challenging to build a fully automatic detection and classification system for breast ultrasonic images. In this paper, a novel and effective computer-aided method including generation of a region of interest (ROI), segmentation and classification of breast tumor is proposed without any manual intervention. By incorporating local features of texture and position, a ROI is firstly detected using a self-organizing map neural network. Then a modified Normalized Cut approach considering the weighted neighborhood gray values is proposed to partition the ROI into clusters and get the initial boundary. In addition, a regional-fitting active contour model is used to adjust the few inaccurate initial boundaries for the final segmentation. Finally, three textures and five morphologic features are extracted from each breast tumor; whereby a highly efficient Affinity Propagation clustering is used to fulfill the malignancy and benign classification for an existing database without any training process. The proposed system is validated by 132 cases (67 benignancies and 65 malignancies) with its performance compared to traditional methods such as level set segmentation, artificial neural network classifiers, and so forth. Experiment results show that the proposed system, which needs no training procedure or manual interference, performs best in detection and classification of ultrasonic breast tumors, while having the lowest computation complexity.

Identification of Different Classes of Luminal Progenitor Cells within Prostate Tumors

Directory of Open Access Journals (Sweden)

Supreet Agarwal

2015-12-01

Full Text Available Primary prostate cancer almost always has a luminal phenotype. However, little is known about the stem/progenitor properties of transformed cells within tumors. Using the aggressive Pten/Tp53-null mouse model of prostate cancer, we show that two classes of luminal progenitors exist within a tumor. Not only did tumors contain previously described multipotent progenitors, but also a major population of committed luminal progenitors. Luminal cells, sorted directly from tumors or grown as organoids, initiated tumors of adenocarcinoma or multilineage histological phenotypes, which is consistent with luminal and multipotent differentiation potentials, respectively. Moreover, using organoids we show that the ability of luminal-committed progenitors to self-renew is a tumor-specific property, absent in benign luminal cells. Finally, a significant fraction of luminal progenitors survived in vivo castration. In all, these data reveal two luminal tumor populations with different stem/progenitor cell capacities, providing insight into prostate cancer cells that initiate tumors and can influence treatment response.

Multi-Frequency Polarimetric SAR Classification Based on Riemannian Manifold and Simultaneous Sparse Representation

Directory of Open Access Journals (Sweden)

Fan Yang

2015-07-01

Full Text Available Normally, polarimetric SAR classification is a high-dimensional nonlinear mapping problem. In the realm of pattern recognition, sparse representation is a very efficacious and powerful approach. As classical descriptors of polarimetric SAR, covariance and coherency matrices are Hermitian semidefinite and form a Riemannian manifold. Conventional Euclidean metrics are not suitable for a Riemannian manifold, and hence, normal sparse representation classification cannot be applied to polarimetric SAR directly. This paper proposes a new land cover classification approach for polarimetric SAR. There are two principal novelties in this paper. First, a Stein kernel on a Riemannian manifold instead of Euclidean metrics, combined with sparse representation, is employed for polarimetric SAR land cover classification. This approach is named Stein-sparse representation-based classification (SRC. Second, using simultaneous sparse representation and reasonable assumptions of the correlation of representation among different frequency bands, Stein-SRC is generalized to simultaneous Stein-SRC for multi-frequency polarimetric SAR classification. These classifiers are assessed using polarimetric SAR images from the Airborne Synthetic Aperture Radar (AIRSAR sensor of the Jet Propulsion Laboratory (JPL and the Electromagnetics Institute Synthetic Aperture Radar (EMISAR sensor of the Technical University of Denmark (DTU. Experiments on single-band and multi-band data both show that these approaches acquire more accurate classification results in comparison to many conventional and advanced classifiers.

Selective changes in expression of HLA class I polymorphic determinants in human solid tumors

International Nuclear Information System (INIS)

Natali, P.G.; Nicotra, M.R.; Bigotti, A.; Venturo, I.; Giacomini, P.; Marcenaro, L.; Russo, C.

1989-01-01

Analysis of surgical biopsies with monoclonal antibodies (mAbs) to framework determinants of major histocompatibility complex class I antigens has shown that malignant transformation is frequently associated with a marked loss of these cell surface molecules. The present study sought to determine whether more selective losses of major histocompatibility complex class I expression occur. Multiple specimens from 13 different types of primary and metastatic tumors were tested utilizing mAb BB7.2, which recognizes a polymorphic HLA-A2 epitope. In each case, expression of HLA-A,B,C molecules was determined by testing with mAb W6/32 directed to a framework HLA class I determinant. The authors have found that in HLA-A2-positive patients, HLA-A2 products are not detectable or are reduced in their expression in 70-80% of endometrial, colorectal, mammary, and renal tumors; in 40-60% of soft-tissue, skin, ovary, urinary bladder, prostate, and stomach tumors; and in 25-30% of melanomas and lung carcinomas tested. All tumors expressed the framework HLA-A,B.C determinant. The HLA-A2 epitope recognized by mAb BB7.2 is located in a portion of the HLA-A2 molecule postulated to react with the T-cell receptor. The selective loss of an HLA class I polymorphic epitope shown in this study may explain the mechanism by which tumor cells escape both T-cell recognition and natural killer cell surveillance

Robust multi-site MR data processing: iterative optimization of bias correction, tissue classification, and registration.

Science.gov (United States)

Young Kim, Eun; Johnson, Hans J

2013-01-01

A robust multi-modal tool, for automated registration, bias correction, and tissue classification, has been implemented for large-scale heterogeneous multi-site longitudinal MR data analysis. This work focused on improving the an iterative optimization framework between bias-correction, registration, and tissue classification inspired from previous work. The primary contributions are robustness improvements from incorporation of following four elements: (1) utilize multi-modal and repeated scans, (2) incorporate high-deformable registration, (3) use extended set of tissue definitions, and (4) use of multi-modal aware intensity-context priors. The benefits of these enhancements were investigated by a series of experiments with both simulated brain data set (BrainWeb) and by applying to highly-heterogeneous data from a 32 site imaging study with quality assessments through the expert visual inspection. The implementation of this tool is tailored for, but not limited to, large-scale data processing with great data variation with a flexible interface. In this paper, we describe enhancements to a joint registration, bias correction, and the tissue classification, that improve the generalizability and robustness for processing multi-modal longitudinal MR scans collected at multi-sites. The tool was evaluated by using both simulated and simulated and human subject MRI images. With these enhancements, the results showed improved robustness for large-scale heterogeneous MRI processing.

PAI-1 and EGFR expression in adult glioma tumors: toward a molecular prognostic classification

International Nuclear Information System (INIS)

Muracciole, Xavier; Romain, Sylvie; Dufour, Henri; Palmari, Jacqueline; Chinot, Olivier; Ouafik, L'Houcine; Grisoli, Francois; Figarella-Branger, Dominique; Martin, Pierre-Marie

2002-01-01

Purpose: Molecular classification of gliomas is a major challenge in the effort to improve therapeutic decisions. The plasminogen activator system, including plasminogen activator inhibitor type 1 (PAI-1), plays a key role in tumor invasion and neoangiogenesis. Epidermal growth factor receptor (EGFR) is involved in the control of proliferation. The contribution of PAI-1 and EGFR to the survival of gliomas was retrospectively investigated. Methods and Materials: Fifty-nine adult gliomas treated by neurosurgery and conventional irradiation were analyzed, including 9 low-grade (2) and 50 high-grade (3-4) tumors (WHO classification). PAI-1 was measured on cytosols and EGFR on solubilized membranes using ELISA methods. Results: High PAI-1 levels were strongly associated with high histologic grade (p<0.001) and histologic necrosis (p<0.001). PAI-1 also correlated positively with patient age (p=0.05) and negatively with Karnofsky index (p=0.01). By univariate analysis of the high-grade population, higher PAI-1 (p<0.0001) and EGFR values (p=0.02) were associated with shorter overall survival. Only PAI-1 was an independent factor in multivariate analysis. Grade 3 tumors with low PAI-1 (100% 3-year overall survival rate) presented the same clinical outcome as the low-grade tumors. Conclusions: In this prognostic study, PAI-1 and EGFR expression revealed similarities and differences between high-grade gliomas that were not apparent by traditional clinical criteria. These data strongly support that biologic factors should be included in glioma classification and the design of clinical trials to treat more homogeneous populations

Surgical options in benign parotid tumors: a proposal for classification.

Science.gov (United States)

Quer, Miquel; Vander Poorten, Vincent; Takes, Robert P; Silver, Carl E; Boedeker, Carsten C; de Bree, Remco; Rinaldo, Alessandra; Sanabria, Alvaro; Shaha, Ashok R; Pujol, Albert; Zbären, Peter; Ferlito, Alfio

2017-11-01

Different surgical options are currently available for treating benign tumors of the parotid gland, and the discussion on optimal treatment continues despite several meta-analyses. These options include more limited resections (extracapsular dissection, partial lateral parotidectomy) versus more extensive and traditional options (lateral parotid lobectomy, total parotidectomy). Different schools favor one option or another based on their experience, skills and tradition. This review provides a critical analysis of the literature regarding these options. The main limitation of all the studies is the bias of selection for different surgical approaches. For this reason, we propose a staging system that could facilitate clinical decision making and the comparison of results. We propose four categories based on the size of the tumor and its location within the parotid gland. Category I includes tumors up to 3 cm, which are mobile, close to the outer surface and close to the parotid borders. Category II includes deeper tumors up to 3 cm. Category III comprises tumors greater than 3 cm involving two levels of the parotid gland, and category IV tumors are greater than 3 cm and involve more than 2 levels. For each category and for the various pathologic types, a guideline of surgical extent is proposed. The objective of this classification is to facilitate prospective multicentric studies on surgical techniques in the treatment of benign parotid tumors and to enable the comparison of results of different clinical studies.

Single-Pol Synthetic Aperture Radar Terrain Classification using Multiclass Confidence for One-Class Classifiers

Energy Technology Data Exchange (ETDEWEB)

Koch, Mark William [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Steinbach, Ryan Matthew [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Moya, Mary M [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

2015-10-01

Except in the most extreme conditions, Synthetic aperture radar (SAR) is a remote sensing technology that can operate day or night. A SAR can provide surveillance over a long time period by making multiple passes over a wide area. For object-based intelligence it is convenient to segment and classify the SAR images into objects that identify various terrains and man-made structures that we call “static features.” In this paper we introduce a novel SAR image product that captures how different regions decorrelate at different rates. Using superpixels and their first two moments we develop a series of one-class classification algorithms using a goodness-of-fit metric. P-value fusion is used to combine the results from different classes. We also show how to combine multiple one-class classifiers to get a confidence about a classification. This can be used by downstream algorithms such as a conditional random field to enforce spatial constraints.

Classification of irreps and invariants of the N-extended Supersymmetric Quantum Mechanics

International Nuclear Information System (INIS)

Kuznetsova, Zhanna; Rojas, Moises; Toppan, Francesco

2006-01-01

We present an algorithmic classification of the irreps of the N-extended one-dimensional supersymmetry algebra linearly realized on a finite number of fields. Our work is based on the 1-to-1 correspondence between Weyl-type Clifford algebras (whose irreps are fully classified) and classes of irreps of the N-extended 1D supersymmetry. The complete classification of irreps is presented up to N ≤ 10. The fields of an irrep are accommodated in l different spin states. N = 10 is the minimal value admitting length l>4 irreps. The classification of length-4 irreps of the N = 12 and real N = 11 extended supersymmetries is also explicitly presented. Tensoring irreps allows us to systematically construct manifestly (N-extended) supersymmetric multi-linear invariants without introducing a superspace formalism. Multi-linear invariants can be constructed both for unconstrained and multi-linearly constrained fields. A whole class of off-shell invariant actions are produced in association with each irreducible representation. The explicit example of the N = 8 off-shell action of the (1,8,7) multiplet is presented. Tensoring zero-energy irreps leads us to the notion of the fusion algebra of the 1D N-extended supersymmetric vacua

Malignant fatty tumors: classification, clinical course, imaging appearance and treatment

International Nuclear Information System (INIS)

Peterson, J.J.; Kransdorf, M.J.; Bancroft, L.W.; O'Connor, M.I.

2003-01-01

Liposarcoma is a relatively common soft tissue malignancy with a wide spectrum of clinical presentations and imaging appearances. Several subtypes are described, ranging from lesions nearly entirely composed of mature adipose tissue, to tumors with very sparse adipose elements. The imaging appearance of these fatty masses is frequently sufficiently characteristic to allow a specific diagnosis, while in other cases, although a specific diagnosis is not achievable, a meaningful limited differential diagnosis can be established. The purpose of this paper is to review the spectrum of malignant fatty tumors, highlighting the current classification system, clinical presentation and behavior, treatment and spectrum of imaging appearances. The imaging review will emphasize CT scanning and MR imaging, and will stress differentiating radiologic features. (orig.)

A Multi-Dimensional Classification Model for Scientific Workflow Characteristics

Energy Technology Data Exchange (ETDEWEB)

Ramakrishnan, Lavanya; Plale, Beth

2010-04-05

Workflows have been used to model repeatable tasks or operations in manufacturing, business process, and software. In recent years, workflows are increasingly used for orchestration of science discovery tasks that use distributed resources and web services environments through resource models such as grid and cloud computing. Workflows have disparate re uirements and constraints that affects how they might be managed in distributed environments. In this paper, we present a multi-dimensional classification model illustrated by workflow examples obtained through a survey of scientists from different domains including bioinformatics and biomedical, weather and ocean modeling, astronomy detailing their data and computational requirements. The survey results and classification model contribute to the high level understandingof scientific workflows.

Classification and handling of non-conformance item of nuclear class equipment during manufacture phase

International Nuclear Information System (INIS)

Wang Ruiping

2001-01-01

Based on inspection experiences in years on nuclear class equipment manufacturing, the author discusses the classification and handling of non-conformance items occurred during equipment manufacturing, and certain technical considerations are presented

Cascaded discrimination of normal, abnormal, and confounder classes in histopathology: Gleason grading of prostate cancer

Directory of Open Access Journals (Sweden)

Doyle Scott

2012-10-01

Full Text Available Abstract Background Automated classification of histopathology involves identification of multiple classes, including benign, cancerous, and confounder categories. The confounder tissue classes can often mimic and share attributes with both the diseased and normal tissue classes, and can be particularly difficult to identify, both manually and by automated classifiers. In the case of prostate cancer, they may be several confounding tissue types present in a biopsy sample, posing as major sources of diagnostic error for pathologists. Two common multi-class approaches are one-shot classification (OSC, where all classes are identified simultaneously, and one-versus-all (OVA, where a “target” class is distinguished from all “non-target” classes. OSC is typically unable to handle discrimination of classes of varying similarity (e.g. with images of prostate atrophy and high grade cancer, while OVA forces several heterogeneous classes into a single “non-target” class. In this work, we present a cascaded (CAS approach to classifying prostate biopsy tissue samples, where images from different classes are grouped to maximize intra-group homogeneity while maximizing inter-group heterogeneity. Results We apply the CAS approach to categorize 2000 tissue samples taken from 214 patient studies into seven classes: epithelium, stroma, atrophy, prostatic intraepithelial neoplasia (PIN, and prostate cancer Gleason grades 3, 4, and 5. A series of increasingly granular binary classifiers are used to split the different tissue classes until the images have been categorized into a single unique class. Our automatically-extracted image feature set includes architectural features based on location of the nuclei within the tissue sample as well as texture features extracted on a per-pixel level. The CAS strategy yields a positive predictive value (PPV of 0.86 in classifying the 2000 tissue images into one of 7 classes, compared with the OVA (0.77 PPV and OSC

Comparison of Single and Multi-Scale Method for Leaf and Wood Points Classification from Terrestrial Laser Scanning Data

Science.gov (United States)

Wei, Hongqiang; Zhou, Guiyun; Zhou, Junjie

2018-04-01

The classification of leaf and wood points is an essential preprocessing step for extracting inventory measurements and canopy characterization of trees from the terrestrial laser scanning (TLS) data. The geometry-based approach is one of the widely used classification method. In the geometry-based method, it is common practice to extract salient features at one single scale before the features are used for classification. It remains unclear how different scale(s) used affect the classification accuracy and efficiency. To assess the scale effect on the classification accuracy and efficiency, we extracted the single-scale and multi-scale salient features from the point clouds of two oak trees of different sizes and conducted the classification on leaf and wood. Our experimental results show that the balanced accuracy of the multi-scale method is higher than the average balanced accuracy of the single-scale method by about 10 % for both trees. The average speed-up ratio of single scale classifiers over multi-scale classifier for each tree is higher than 30.

A class of multi-period semi-variance portfolio for petroleum exploration and development

Science.gov (United States)

Guo, Qiulin; Li, Jianzhong; Zou, Caineng; Guo, Yujuan; Yan, Wei

2012-10-01

Variance is substituted by semi-variance in Markowitz's portfolio selection model. For dynamic valuation on exploration and development projects, one period portfolio selection is extended to multi-period. In this article, a class of multi-period semi-variance exploration and development portfolio model is formulated originally. Besides, a hybrid genetic algorithm, which makes use of the position displacement strategy of the particle swarm optimiser as a mutation operation, is applied to solve the multi-period semi-variance model. For this class of portfolio model, numerical results show that the mode is effective and feasible.

Reverberation time in class rooms – Comparison of regulations and classification criteria in the Nordic countries

DEFF Research Database (Denmark)

Rasmussen, Birgit; Brunskog, Jonas; Hoffmeyer, Dan

2012-01-01

Regulatory requirements or guidelines for classroom reverberation time exist in all five Nordic countries and in most of Europe – as well as other acoustic criteria for schools, e.g. concerning airborne and impact sound insulation, facade sound insulation and installation noise. There are several...... reasons for having such requirements: Improving learning efficiency for pupils and work conditions for teachers and reducing noise levels, thus increasing comfort for everyone. Instead of including acoustic regulatory requirements for schools directly in the building regulations, Iceland, Norway...... and Sweden have introduced acoustic quality classes A, B, C and D in national standards with class C referred to as regulatory requirements. These national classification standards are dealing with acoustic classes for several types of buildings. A classification scheme also exists in Finland...

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

Science.gov (United States)

Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

2015-10-30

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.

A classification plan of design class for systems of an advanced research reactor

International Nuclear Information System (INIS)

Yoon, Doo Byung; Ryu, Jeong Soo

2005-01-01

Advanced Research Reactor(ARR) is being designed by KAERI since 2002. The final goal of the project is to develop a new and unique research reactor model which is superior in safety and economical aspects. The conceptual design for systems, structures, and components of the ARR will be completed by 2005. The basic design for the systems, structures, and components of the ARR will be performed from 2006. Based on the technical experiences on the design and operation of the HANARO, the ARR will be designed. It is necessary to classify the safety class, quality class, and seismic category for the systems, structures, and components. The objective of this work is to propose a classification plan of design class for systems, structures, and components of the ARR. To achieve this purpose, the revision status of the regulations that used as criteria for determining the design class of the systems, structures, and components of the HANARO were investigated. In addition, the present revision status of the codes and the standards that utilized for the design of the HANARO were investigated. Based on these investigations, the codes and the standards for the design of the systems, structures, and components of the ARR were proposed. The feasibility of the proposed classification plan will be verified by performing the conceptual and basic design of the systems, structures, and components of the ARR

Linear Subpixel Learning Algorithm for Land Cover Classification from WELD using High Performance Computing

Science.gov (United States)

Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.

2017-12-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

One input-class and two input-class classifications for differentiating olive oil from other edible vegetable oils by use of the normal-phase liquid chromatography fingerprint of the methyl-transesterified fraction.

Science.gov (United States)

Jiménez-Carvelo, Ana M; Pérez-Castaño, Estefanía; González-Casado, Antonio; Cuadros-Rodríguez, Luis

2017-04-15

A new method for differentiation of olive oil (independently of the quality category) from other vegetable oils (canola, safflower, corn, peanut, seeds, grapeseed, palm, linseed, sesame and soybean) has been developed. The analytical procedure for chromatographic fingerprinting of the methyl-transesterified fraction of each vegetable oil, using normal-phase liquid chromatography, is described and the chemometric strategies applied and discussed. Some chemometric methods, such as k-nearest neighbours (kNN), partial least squared-discriminant analysis (PLS-DA), support vector machine classification analysis (SVM-C), and soft independent modelling of class analogies (SIMCA), were applied to build classification models. Performance of the classification was evaluated and ranked using several classification quality metrics. The discriminant analysis, based on the use of one input-class, (plus a dummy class) was applied for the first time in this study. Copyright © 2016 Elsevier Ltd. All rights reserved.

Upregulation of HLA Class I Expression on Tumor Cells by the Anti-EGFR Antibody Nimotuzumab

Directory of Open Access Journals (Sweden)

Greta Garrido

2017-10-01

Full Text Available Defining how epidermal growth factor receptor (EGFR-targeting therapies influence the immune response is essential to increase their clinical efficacy. A growing emphasis is being placed on immune regulator genes that govern tumor – T cell interactions. Previous studies showed an increase in HLA class I cell surface expression in tumor cell lines treated with anti-EGFR agents. In particular, earlier studies of the anti-EGFR blocking antibody cetuximab, have suggested that increased tumor expression of HLA class I is associated with positive clinical response. We investigated the effect of another commercially available anti-EGFR antibody nimotuzumab on HLA class I expression in tumor cell lines. We observed, for the first time, that nimotuzumab increases HLA class I expression and its effect is associated with a coordinated increase in mRNA levels of the principal antigen processing and presentation components. Moreover, using 7A7 (a specific surrogate antibody against murine EGFR, we obtained results suggesting the importance of the increased MHC-I expression induced by EGFR-targeted therapies display higher in antitumor immune response. 7A7 therapy induced upregulation of tumor MHC-I expression in vivo and tumors treated with this antibody display higher susceptibility to CD8+ T cells-mediated lysis. Our results represent the first evidence suggesting the importance of the adaptive immunity in nimotuzumab-mediated antitumor activity. More experiments should be conducted in order to elucidate the relevance of this mechanism in cancer patients. This novel immune-related antitumor mechanism mediated by nimotuzumab opens new perspectives for its combination with various immunotherapeutic agents and cancer vaccines.

CT and MRI of germ-cell tumors with metastasis or multi-located tumors

International Nuclear Information System (INIS)

Miyagami, Mitsusuke; Tazoe, Makoto; Tsubokawa, Takashi

1989-01-01

Twenty-seven cases of germ-cell tumors were examined with a CT scan in our clinic. In the 11 cases of metastasis or multi-localized tumors, the CT findings were studied in connection with the MRI findings. There were 6 cases of germ-cell tumors which had broad infiltrating tumors with multiple lesions on first admission. Their tumor sites were different from that in cases of malignant glioma, being frequently localized in the pineal and/or the suprasellar region, on the wall of the third and/or lateral ventricle, and in the region of the basal ganglia. Five of the cases of germ-cell tumors had metastasis with various patterns connected to a remote area - that is, to spinal cords, to the ventricular wall and basal cistern of the brain stem by CSF dissemination, to a lung by hematogeneous metastasis, and to the peritoneal wall or organs by a V-P shunt. The CT findings of germ-cell tumors were correlated mainly with the results of the histological diagnosis; they were found not to differ with the tumor site. The germinoma in the suprasellar region had less calcification than in the pineal region. Cysts, calcification, and an enlargement of the lateral ventricle on the tumor side were frequently seen in the germinoma of the basal ganglia. On the MRI of 5 cases of germinoma, the T 1 -weighted image revealed a slightly low or iso signal intensity, while the T 2 -weighted image showed a high signal intensity. In the case of multiple tumor lesions, some cases demonstrated different CT findings and radiosensitivities for each tumor. The possibility of a multicentric origin for the tumors is thus suggested in some cases of germ-cell tumors. (author)

Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

Energy Technology Data Exchange (ETDEWEB)

Jing, Yaqi; Meng, Qinghao, E-mail: qh-meng@tju.edu.cn; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen [Tianjin Key Laboratory of Process Measurement and Control, Institute of Robotics and Autonomous Systems, School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072 (China)

2014-05-15

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.

Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

International Nuclear Information System (INIS)

Jing, Yaqi; Meng, Qinghao; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen

2014-01-01

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively

Multi-sparse dictionary colorization algorithm based on the feature classification and detail enhancement

Science.gov (United States)

Yan, Dan; Bai, Lianfa; Zhang, Yi; Han, Jing

2018-02-01

For the problems of missing details and performance of the colorization based on sparse representation, we propose a conceptual model framework for colorizing gray-scale images, and then a multi-sparse dictionary colorization algorithm based on the feature classification and detail enhancement (CEMDC) is proposed based on this framework. The algorithm can achieve a natural colorized effect for a gray-scale image, and it is consistent with the human vision. First, the algorithm establishes a multi-sparse dictionary classification colorization model. Then, to improve the accuracy rate of the classification, the corresponding local constraint algorithm is proposed. Finally, we propose a detail enhancement based on Laplacian Pyramid, which is effective in solving the problem of missing details and improving the speed of image colorization. In addition, the algorithm not only realizes the colorization of the visual gray-scale image, but also can be applied to the other areas, such as color transfer between color images, colorizing gray fusion images, and infrared images.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Directory of Open Access Journals (Sweden)

Hongqiang Li

2016-10-01

Full Text Available Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.

Incremental Learning of Medical Data for Multi-Step Patient Health Classification

DEFF Research Database (Denmark)

Kranen, Philipp; Müller, Emmanuel; Assent, Ira

2010-01-01

of textile sensors, body sensors and preprocessing techniques as well as the integration and merging of sensor data in electronic health record systems. Emergency detection on multiple levels will show the benefits of multi-step classification and further enhance the scalability of emergency detection...

The Escape of Cancer from T Cell-Mediated Immune Surveillance: HLA Class I Loss and Tumor Tissue Architecture

Directory of Open Access Journals (Sweden)

Federico Garrido

2017-02-01

Full Text Available Tumor immune escape is associated with the loss of tumor HLA class I (HLA-I expression commonly found in malignant cells. Accumulating evidence suggests that the efficacy of immunotherapy depends on the expression levels of HLA class I molecules on tumors cells. It also depends on the molecular mechanism underlying the loss of HLA expression, which could be reversible/“soft” or irreversible/“hard” due to genetic alterations in HLA, β2-microglobulin or IFN genes. Immune selection of HLA-I negative tumor cells harboring structural/irreversible alterations has been demonstrated after immunotherapy in cancer patients and in experimental cancer models. Here, we summarize recent findings indicating that tumor HLA-I loss also correlates with a reduced intra-tumor T cell infiltration and with a specific reorganization of tumor tissue. T cell immune selection of HLA-I negative tumors results in a clear separation between the stroma and the tumor parenchyma with leucocytes, macrophages and other mononuclear cells restrained outside the tumor mass. Better understanding of the structural and functional changes taking place in the tumor microenvironment may help to overcome cancer immune escape and improve the efficacy of different immunotherapeutic strategies. We also underline the urgent need for designing strategies to enhance tumor HLA class I expression that could improve tumor rejection by cytotoxic T-lymphocytes (CTL.

Multi-agent Negotiation Mechanisms for Statistical Target Classification in Wireless Multimedia Sensor Networks

Directory of Open Access Journals (Sweden)

Sheng Wang

2007-10-01

Full Text Available The recent availability of low cost and miniaturized hardware has allowedwireless sensor networks (WSNs to retrieve audio and video data in real worldapplications, which has fostered the development of wireless multimedia sensor networks(WMSNs. Resource constraints and challenging multimedia data volume makedevelopment of efficient algorithms to perform in-network processing of multimediacontents imperative. This paper proposes solving problems in the domain of WMSNs fromthe perspective of multi-agent systems. The multi-agent framework enables flexible networkconfiguration and efficient collaborative in-network processing. The focus is placed ontarget classification in WMSNs where audio information is retrieved by microphones. Todeal with the uncertainties related to audio information retrieval, the statistical approachesof power spectral density estimates, principal component analysis and Gaussian processclassification are employed. A multi-agent negotiation mechanism is specially developed toefficiently utilize limited resources and simultaneously enhance classification accuracy andreliability. The negotiation is composed of two phases, where an auction based approach isfirst exploited to allocate the classification task among the agents and then individual agentdecisions are combined by the committee decision mechanism. Simulation experiments withreal world data are conducted and the results show that the proposed statistical approachesand negotiation mechanism not only reduce memory and computation requi

Detection and classification of interstitial lung diseases and emphysema using a joint morphological-fuzzy approach

Science.gov (United States)

Chang Chien, Kuang-Che; Fetita, Catalin; Brillet, Pierre-Yves; Prêteux, Françoise; Chang, Ruey-Feng

2009-02-01

Multi-detector computed tomography (MDCT) has high accuracy and specificity on volumetrically capturing serial images of the lung. It increases the capability of computerized classification for lung tissue in medical research. This paper proposes a three-dimensional (3D) automated approach based on mathematical morphology and fuzzy logic for quantifying and classifying interstitial lung diseases (ILDs) and emphysema. The proposed methodology is composed of several stages: (1) an image multi-resolution decomposition scheme based on a 3D morphological filter is used to detect and analyze the different density patterns of the lung texture. Then, (2) for each pattern in the multi-resolution decomposition, six features are computed, for which fuzzy membership functions define a probability of association with a pathology class. Finally, (3) for each pathology class, the probabilities are combined up according to the weight assigned to each membership function and two threshold values are used to decide the final class of the pattern. The proposed approach was tested on 10 MDCT cases and the classification accuracy was: emphysema: 95%, fibrosis/honeycombing: 84% and ground glass: 97%.

A Hidden Markov Models Approach for Crop Classification: Linking Crop Phenology to Time Series of Multi-Sensor Remote Sensing Data

Directory of Open Access Journals (Sweden)

Sofia Siachalou

2015-03-01

Full Text Available Vegetation monitoring and mapping based on multi-temporal imagery has recently received much attention due to the plethora of medium-high spatial resolution satellites and the improved classification accuracies attained compared to uni-temporal approaches. Efficient image processing strategies are needed to exploit the phenological information present in temporal image sequences and to limit data redundancy and computational complexity. Within this framework, we implement the theory of Hidden Markov Models in crop classification, based on the time-series analysis of phenological states, inferred by a sequence of remote sensing observations. More specifically, we model the dynamics of vegetation over an agricultural area of Greece, characterized by spatio-temporal heterogeneity and small-sized fields, using RapidEye and Landsat ETM+ imagery. In addition, the classification performance of image sequences with variable spatial and temporal characteristics is evaluated and compared. The classification model considering one RapidEye and four pan-sharpened Landsat ETM+ images was found superior, resulting in a conditional kappa from 0.77 to 0.94 per class and an overall accuracy of 89.7%. The results highlight the potential of the method for operational crop mapping in Euro-Mediterranean areas and provide some hints for optimal image acquisition windows regarding major crop types in Greece.

Deep convolutional neural network training enrichment using multi-view object-based analysis of Unmanned Aerial systems imagery for wetlands classification

Science.gov (United States)

Liu, Tao; Abd-Elrahman, Amr

2018-05-01

Deep convolutional neural network (DCNN) requires massive training datasets to trigger its image classification power, while collecting training samples for remote sensing application is usually an expensive process. When DCNN is simply implemented with traditional object-based image analysis (OBIA) for classification of Unmanned Aerial systems (UAS) orthoimage, its power may be undermined if the number training samples is relatively small. This research aims to develop a novel OBIA classification approach that can take advantage of DCNN by enriching the training dataset automatically using multi-view data. Specifically, this study introduces a Multi-View Object-based classification using Deep convolutional neural network (MODe) method to process UAS images for land cover classification. MODe conducts the classification on multi-view UAS images instead of directly on the orthoimage, and gets the final results via a voting procedure. 10-fold cross validation results show the mean overall classification accuracy increasing substantially from 65.32%, when DCNN was applied on the orthoimage to 82.08% achieved when MODe was implemented. This study also compared the performances of the support vector machine (SVM) and random forest (RF) classifiers with DCNN under traditional OBIA and the proposed multi-view OBIA frameworks. The results indicate that the advantage of DCNN over traditional classifiers in terms of accuracy is more obvious when these classifiers were applied with the proposed multi-view OBIA framework than when these classifiers were applied within the traditional OBIA framework.

Classification of frequency response areas in the inferior colliculus reveals continua not discrete classes.

Science.gov (United States)

Palmer, Alan R; Shackleton, Trevor M; Sumner, Christian J; Zobay, Oliver; Rees, Adrian

2013-08-15

A differential response to sound frequency is a fundamental property of auditory neurons. Frequency analysis in the cochlea gives rise to V-shaped tuning functions in auditory nerve fibres, but by the level of the inferior colliculus (IC), the midbrain nucleus of the auditory pathway, neuronal receptive fields display diverse shapes that reflect the interplay of excitation and inhibition. The origin and nature of these frequency receptive field types is still open to question. One proposed hypothesis is that the frequency response class of any given neuron in the IC is predominantly inherited from one of three major afferent pathways projecting to the IC, giving rise to three distinct receptive field classes. Here, we applied subjective classification, principal component analysis, cluster analysis, and other objective statistical measures, to a large population (2826) of frequency response areas from single neurons recorded in the IC of the anaesthetised guinea pig. Subjectively, we recognised seven frequency response classes (V-shaped, non-monotonic Vs, narrow, closed, tilt down, tilt up and double-peaked), that were represented at all frequencies. We could identify similar classes using our objective classification tools. Importantly, however, many neurons exhibited properties intermediate between these classes, and none of the objective methods used here showed evidence of discrete response classes. Thus receptive field shapes in the IC form continua rather than discrete classes, a finding consistent with the integration of afferent inputs in the generation of frequency response areas. The frequency disposition of inhibition in the response areas of some neurons suggests that across-frequency inputs originating at or below the level of the IC are involved in their generation.

Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

Science.gov (United States)

Lavreniuk, M. S.

2016-12-01

Land cover and crop type maps are one of the most essential inputs when dealing with environmental and agriculture monitoring tasks [1]. During long time neural network (NN) approach was one of the most efficient and popular approach for most applications, including crop classification using remote sensing data, with high an overall accuracy (OA) [2]. In the last years the most popular and efficient method for multi-sensor and multi-temporal land cover classification is convolution neural networks (CNNs). Taking into account presence clouds in optical data, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of optical imagery from Landsat-8 satellite. After missing data restoration, optical data from Landsat-8 was merged with Sentinel-1A radar data for better crop types discrimination [3]. An ensemble of CNNs is proposed for multi-temporal satellite images supervised classification. Each CNN in the corresponding ensemble is a 1-d CNN with 4 layers implemented using the Google's library TensorFlow. The efficiency of the proposed approach was tested on a time-series of Landsat-8 and Sentinel-1A images over the JECAM test site (Kyiv region) in Ukraine in 2015. Overall classification accuracy for ensemble of CNNs was 93.5% that outperformed an ensemble of multi-layer perceptrons (MLPs) by +0.8% and allowed us to better discriminate summer crops, in particular maize and soybeans. For 2016 we would like to validate this method using Sentinel-1 and Sentinel-2 data for Ukraine territory within ESA project on country level demonstration Sen2Agri. 1. A. Kolotii et al., "Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine," The Int. Arch. of Photogram., Rem. Sens. and Spatial Inform. Scie., vol. 40, no. 7, pp. 39-44, 2015. 2. F. Waldner et al., "Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity," Int. Journal of Rem. Sens. vol. 37, no. 14, pp

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

Science.gov (United States)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECTORIENTED CLASSIFICATION

Directory of Open Access Journals (Sweden)

L. Ding

2018-04-01

Full Text Available In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Efficient Identification of miRNAs for Classification of Tumor Origin

DEFF Research Database (Denmark)

Søkilde, Rolf; Vincent, Martin; Møller, Anne K

2014-01-01

Carcinomas of unknown primary origin constitute 3% to 5% of all newly diagnosed metastatic cancers, with the primary source difficult to classify with current histological methods. Effective cancer treatment depends on early and accurate identification of the tumor; patients with metastases...... of unknown origin have poor prognosis and short survival. Because miRNA expression is highly tissue specific, the miRNA profile of a metastasis may be used to identify its origin. We therefore evaluated the potential of miRNA profiling to identify the primary tumor of known metastases. Two hundred eight...... formalin-fixed, paraffin-embedded samples, representing 15 different histologies, were profiled on a locked nucleic acid-enhanced microarray platform, which allows for highly sensitive and specific detection of miRNA. On the basis of these data, we developed and cross-validated a novel classification...

Case based reasoning applied to medical diagnosis using multi-class classifier: A preliminary study

Directory of Open Access Journals (Sweden)

D. Viveros-Melo

2017-02-01

Full Text Available Case-based reasoning (CBR is a process used for computer processing that tries to mimic the behavior of a human expert in making decisions regarding a subject and learn from the experience of past cases. CBR has demonstrated to be appropriate for working with unstructured domains data or difficult knowledge acquisition situations, such as medical diagnosis, where it is possible to identify diseases such as: cancer diagnosis, epilepsy prediction and appendicitis diagnosis. Some of the trends that may be developed for CBR in the health science are oriented to reduce the number of features in highly dimensional data. An important contribution may be the estimation of probabilities of belonging to each class for new cases. In this paper, in order to adequately represent the database and to avoid the inconveniences caused by the high dimensionality, noise and redundancy, a number of algorithms are used in the preprocessing stage for performing both variable selection and dimension reduction procedures. Also, a comparison of the performance of some representative multi-class classifiers is carried out to identify the most effective one to include within a CBR scheme. Particularly, four classification techniques and two reduction techniques are employed to make a comparative study of multiclass classifiers on CBR

Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification

Directory of Open Access Journals (Sweden)

Lu Bing

2017-01-01

Full Text Available We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL. After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM. Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification.

Science.gov (United States)

Bing, Lu; Wang, Wei

2017-01-01

We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM). Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

Optimizing Ship Classification in the Arctic Ocean: A Case Study of Multi-Disciplinary Problem Solving

Directory of Open Access Journals (Sweden)

Mark Rahmes

2014-08-01

Full Text Available We describe a multi-disciplinary system model for determining decision making strategies based upon the ability to perform data mining and pattern discovery utilizing open source actionable information to prepare for specific events or situations from multiple information sources. We focus on combining detection theory with game theory for classifying ships in Arctic Ocean to verify ship reporting. More specifically, detection theory is used to determine probability of deciding if a ship or certain ship class is present or not. We use game theory to fuse information for optimal decision making on ship classification. Hierarchy game theory framework enables complex modeling of data in probabilistic modeling. However, applicability to big data is complicated by the difficulties of inference in complex probabilistic models, and by computational constraints. We provide a framework for fusing sensor inputs to help compare if the information of a ship matches its AIS reporting requirements using mixed probabilities from game theory. Our method can be further applied to optimizing other choke point scenarios where a decision is needed for classification of ground assets or signals. We model impact on decision making on accuracy by adding more parameters or sensors to the decision making process as sensitivity analysis.

Multi-small molecule conjugations as new targeted delivery carriers for tumor therapy

Directory of Open Access Journals (Sweden)

Shan L

2015-09-01

Full Text Available Lingling Shan,1 Ming Liu,2 Chao Wu,1 Liang Zhao,1 Siwen Li,3 Lisheng Xu,1 Wengen Cao,1 Guizhen Gao,1 Yueqing Gu3 1Institute of Pharmaceutical Biotechnology, School of Biology and Food Engineering, Suzhou University, Suzhou, People’s Republic of China; 2Department of Biology, University of South Dakota, Vermillion, SD, USA; 3Department of Biomedical Engineering, School of Life Science and Technology, China Pharmaceutical University, Nanjing, People’s Republic of China Abstract: In response to the challenges of cancer chemotherapeutics, including poor physicochemical properties, low tumor targeting ability, and harmful side effects, we developed a new tumor-targeted multi-small molecule drug delivery platform. Using paclitaxel (PTX as a model therapeutic, we prepared two prodrugs, ie, folic acid-fluorescein-5(6-isothiocyanate-arginine-paclitaxel (FA-FITC-Arg-PTX and folic acid-5-aminofluorescein-glutamic-paclitaxel (FA-5AF-Glu-PTX, composed of folic acid (FA, target, amino acids (Arg or Glu, linker, and fluorescent dye (fluorescein in vitro or near-infrared fluorescent dye in vivo in order to better understand the mechanism of PTX prodrug targeting. In vitro and acute toxicity studies demonstrated the low toxicity of the prodrug formulations compared with the free drug. In vitro and in vivo studies indicated that folate receptor-mediated uptake of PTX-conjugated multi-small molecule carriers induced high antitumor activity. Notably, compared with free PTX and with PTX-loaded macromolecular carriers from our previous study, this multi-small molecule-conjugated strategy improved the water solubility, loading rate, targeting ability, antitumor activity, and toxicity profile of PTX. These results support the use of multi-small molecules as tumor-targeting drug delivery systems. Keywords: multi-small molecules, paclitaxel, prodrugs, targeting, tumor therapy

APPLICATION OF FUSION WITH SAR AND OPTICAL IMAGES IN LAND USE CLASSIFICATION BASED ON SVM

Directory of Open Access Journals (Sweden)

C. Bao

2012-07-01

Full Text Available As the increment of remote sensing data with multi-space resolution, multi-spectral resolution and multi-source, data fusion technologies have been widely used in geological fields. Synthetic Aperture Radar (SAR and optical camera are two most common sensors presently. The multi-spectral optical images express spectral features of ground objects, while SAR images express backscatter information. Accuracy of the image classification could be effectively improved fusing the two kinds of images. In this paper, Terra SAR-X images and ALOS multi-spectral images were fused for land use classification. After preprocess such as geometric rectification, radiometric rectification noise suppression and so on, the two kind images were fused, and then SVM model identification method was used for land use classification. Two different fusion methods were used, one is joining SAR image into multi-spectral images as one band, and the other is direct fusing the two kind images. The former one can raise the resolution and reserve the texture information, and the latter can reserve spectral feature information and improve capability of identifying different features. The experiment results showed that accuracy of classification using fused images is better than only using multi-spectral images. Accuracy of classification about roads, habitation and water bodies was significantly improved. Compared to traditional classification method, the method of this paper for fused images with SVM classifier could achieve better results in identifying complicated land use classes, especially for small pieces ground features.

Tumor location and patient characteristics of colon and rectal adenocarcinomas in relation to survival and TNM classes

International Nuclear Information System (INIS)

Hemminki, Kari; Santi, Irene; Weires, Marianne; Thomsen, Hauke; Sundquist, Jan; Bermejo, Justo Lorenzo

2010-01-01

Old age at diagnosis is associated with poor survival in colorectal cancer (CRC) for unknown reasons. Recent data show that colonoscopy is efficient in preventing left-sided cancers only. We examine the association of Tumor Node Metastasis (TNM) classes with diagnostic age and patient characteristics. The Swedish Family-Cancer Database has data on TNM classes on 6,105 CRC adenocarcinoma patients. Ordinal logistic regression analysis was performed to model tumor characteristics according to age at diagnosis, tumor localization, gender, socioeconomic status, medical region and family history. The results were compared to results from survival analysis. The only parameters systematically associated with TNM classes were age and tumor localization. Young age at diagnosis was a risk factor for aggressive CRC, according to stage, N and M with odds ratios (ORs) ranging from 1.80 to 1.93 for diagnosis before age 50 years compared to diagnosis at 80+ years. All tumor characteristics, particularly T, were worse for colon compared to rectal tumors. Right-sided tumors showed worse characteristics for all classifiers but M. The survival analysis on patients diagnosed since 2000 showed a hazard ratio of 0.55 for diagnosis before age 50 years compared to diagnosis at over 80 years and a modestly better prognosis for left-sided compared to right-sided tumors. The results showed systematically more aggressive tumors in young compared to old patients. The poorer survival of old patients in colon cancer was not related to the available tumor characteristics. However, these partially agreed with the limited colonoscopic success with right-sided tumors

Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders

Science.gov (United States)

Rußwurm, Marc; Körner, Marco

2018-03-01

Earth observation (EO) sensors deliver data with daily or weekly temporal resolution. Most land use and land cover (LULC) approaches, however, expect cloud-free and mono-temporal observations. The increasing temporal capabilities of today's sensors enables the use of temporal, along with spectral and spatial features. Domains, such as speech recognition or neural machine translation, work with inherently temporal data and, today, achieve impressive results using sequential encoder-decoder structures. Inspired by these sequence-to-sequence models, we adapt an encoder structure with convolutional recurrent layers in order to approximate a phenological model for vegetation classes based on a temporal sequence of Sentinel 2 (S2) images. In our experiments, we visualize internal activations over a sequence of cloudy and non-cloudy images and find several recurrent cells, which reduce the input activity for cloudy observations. Hence, we assume that our network has learned cloud-filtering schemes solely from input data, which could alleviate the need for tedious cloud-filtering as a preprocessing step for many EO approaches. Moreover, using unfiltered temporal series of top-of-atmosphere (TOA) reflectance data, we achieved in our experiments state-of-the-art classification accuracies on a large number of crop classes with minimal preprocessing compared to other classification approaches.

Intra-axial brain tumors in adults. On the basis of the 2016 WHO classification

International Nuclear Information System (INIS)

Peitgen, N.; Papanagiotou, P.

2017-01-01

The influence of the World Health Organization (WHO) classification from 2016 on the radiological diagnosis for tumors of the central nervous system (CNS) in adults. Computed tomography (CT), magnetic resonance imaging (MRI) and MR spectroscopy. In order to come as close as possible to the correct diagnosis of CNS tumors, MRI is the long-standing accepted method of choice that can in some cases be supported by the use of CT to demonstrate calcification or bone destruction. In individual cases MRI spectroscopy can be helpful for the differentiation between neoplasms and inflammatory lesions or surveillance of tumor therapy, just as perfusion, which is not discussed in this article. (orig.) [de

Diagnostic value of multi-tumor markers protein biochip detection for primary pulmonary cancer

International Nuclear Information System (INIS)

Xu Fengpo; Wu Yiwei; Li Qingru; Fa Yihua

2005-01-01

To evaluate the diagnostic value of multi-tumor markers protein biochip detection for primary pulmonary cancer, 12 tumor markers including AFP, CEA, NSE, CA125, CA15-3, CA242, CA19-9, PSA, f-PSA, FER, β-HCG and HGH were measured by the protein biochip in the serum of 45 primary pulmonary cancer patients. Positive rate of tumor markers was FER (42.2%), CEA (35.6%), CA125 (24.4%), CA15-3 (17.8%), CA242 (13.3%), CA19-9 (11.1%), β-HCG(8.9%), HGH(6.7%), NSE(4.4%), AFP (0), f-PSA (0) and PSA (0), respectively. The rate of patients with one abnorma indicator was 57.8% except FER. The positive rate using multi-tumor markers protein biochip detection was significantly higher than that of single tumor marker detective method, and this detection can be used for the diagnosis of patients with primary pulmonary cancer. (authors)

From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

Science.gov (United States)

2010-01-01

Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for

From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

Directory of Open Access Journals (Sweden)

Dawyndt Peter

2010-01-01

Full Text Available Abstract Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the

From learning taxonomies to phylogenetic learning: integration of 16S rRNA gene data into FAME-based bacterial classification.

Science.gov (United States)

Slabbinck, Bram; Waegeman, Willem; Dawyndt, Peter; De Vos, Paul; De Baets, Bernard

2010-01-30

Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial

Radiological diagnostics of skeletal tumors

International Nuclear Information System (INIS)

Uhl, M.; Herget, G.W.

2008-01-01

The book contains contributions concerning the following topics: 1. introduction and fundamentals: WHO classification of bone tumors, imaging diagnostics and their function; localization, typical clinical and radiological criteria, TNM classification and status classification, invasive tumor diagnostics; 2. specific tumor diagnostics: chondrogenic bone tumors, osseous tumors, connective tissue bony tumors, osteoclastoma, osteomyelogenic bone tumors, vascular bone tumors, neurogenic bone tumors, chordoma; adamantinoma of the long tubular bone; tumor-like lesions, bony metastases, bone granulomas, differential diagnostics: tumor-like lesions

An Empirical Study on User-oriented Association Analysis of Library Classification Schemes

Directory of Open Access Journals (Sweden)

Hsiao-Tieh Pu

2002-12-01

Full Text Available Library classification schemes are mostly organized based on disciplines with a hierarchical structure. From the user point of view, some highly related yet non-hierarchical classes may not be easy to perceive in these schemes. This paper is to discover hidden associations between classes by analyzing users’ usage of library collections. The proposed approach employs collaborative filtering techniques to discover associated classes based on the circulation patterns of similar users. Many associated classes scattered across different subject hierarchies could be discovered from the circulation patterns of similar users. The obtained association norms between classes were found to be useful in understanding users' subject preferences for a given class. Classification schemes can, therefore, be made more adaptable to changes of users and the uses of different library collections. There are implications for applications in information organization and retrieval as well. For example, catalogers could refer to the ranked associated classes when they perform multi-classification, and users could also browse the associated classes for related subjects in an enhanced OPAC system. In future research, more empirical studies will be needed to validate the findings, and methods for obtaining user-oriented associations can still be improved.[Article content in Chinese

CS2164, a novel multi-target inhibitor against tumor angiogenesis, mitosis and chronic inflammation with anti-tumor potency.

Science.gov (United States)

Zhou, You; Shan, Song; Li, Zhi-Bin; Xin, Li-Jun; Pan, De-Si; Yang, Qian-Jiao; Liu, Ying-Ping; Yue, Xu-Peng; Liu, Xiao-Rong; Gao, Ji-Zhou; Zhang, Jin-Wen; Ning, Zhi-Qiang; Lu, Xian-Ping

2017-03-01

Although inhibitors targeting tumor angiogenic pathway have provided improvement for clinical treatment in patients with various solid tumors, the still very limited anti-cancer efficacy and acquired drug resistance demand new agents that may offer better clinical benefits. In the effort to find a small molecule potentially targeting several key pathways for tumor development, we designed, discovered and evaluated a novel multi-kinase inhibitor, CS2164. CS2164 inhibited the angiogenesis-related kinases (VEGFR2, VEGFR1, VEGFR3, PDGFRα and c-Kit), mitosis-related kinase Aurora B and chronic inflammation-related kinase CSF-1R in a high potency manner with the IC 50 at a single-digit nanomolar range. Consequently, CS2164 displayed anti-angiogenic activities through suppression of VEGFR/PDGFR phosphorylation, inhibition of ligand-dependent cell proliferation and capillary tube formation, and prevention of vasculature formation in tumor tissues. CS2164 also showed induction of G2/M cell cycle arrest and suppression of cell proliferation in tumor tissues through the inhibition of Aurora B-mediated H3 phosphorylation. Furthermore, CS2164 demonstrated the inhibitory effect on CSF-1R phosphorylation that led to the suppression of ligand-stimulated monocyte-to-macrophage differentiation and reduced CSF-1R + cells in tumor tissues. The in vivo animal efficacy studies revealed that CS2164 induced remarkable regression or complete inhibition of tumor growth at well-tolerated oral doses in several human tumor xenograft models. Collectively, these results indicate that CS2164 is a highly selective multi-kinase inhibitor with potent anti-tumor activities against tumor angiogenesis, mitosis and chronic inflammation, which may provide the rationale for further clinical assessment of CS2164 as a therapeutic agent in the treatment of cancer. © 2016 The Authors. Cancer Science published by John Wiley & Sons Australia, Ltd on behalf of Japanese Cancer Association.

Coupling biomechanics to a cellular level model: an approach to patient-specific image driven multi-scale and multi-physics tumor simulation.

Science.gov (United States)

May, Christian P; Kolokotroni, Eleni; Stamatakos, Georgios S; Büchler, Philippe

2011-10-01

Modeling of tumor growth has been performed according to various approaches addressing different biocomplexity levels and spatiotemporal scales. Mathematical treatments range from partial differential equation based diffusion models to rule-based cellular level simulators, aiming at both improving our quantitative understanding of the underlying biological processes and, in the mid- and long term, constructing reliable multi-scale predictive platforms to support patient-individualized treatment planning and optimization. The aim of this paper is to establish a multi-scale and multi-physics approach to tumor modeling taking into account both the cellular and the macroscopic mechanical level. Therefore, an already developed biomodel of clinical tumor growth and response to treatment is self-consistently coupled with a biomechanical model. Results are presented for the free growth case of the imageable component of an initially point-like glioblastoma multiforme tumor. The composite model leads to significant tumor shape corrections that are achieved through the utilization of environmental pressure information and the application of biomechanical principles. Using the ratio of smallest to largest moment of inertia of the tumor material to quantify the effect of our coupled approach, we have found a tumor shape correction of 20% by coupling biomechanics to the cellular simulator as compared to a cellular simulation without preferred growth directions. We conclude that the integration of the two models provides additional morphological insight into realistic tumor growth behavior. Therefore, it might be used for the development of an advanced oncosimulator focusing on tumor types for which morphology plays an important role in surgical and/or radio-therapeutic treatment planning. Copyright © 2011 Elsevier Ltd. All rights reserved.

hemaClass.org: Online One-By-One Microarray Normalization and Classification of Hematological Cancers for Precision Medicine.

Science.gov (United States)

Falgreen, Steffen; Ellern Bilgrau, Anders; Brøndum, Rasmus Froberg; Hjort Jakobsen, Lasse; Have, Jonas; Lindblad Nielsen, Kasper; El-Galaly, Tarec Christoffer; Bødker, Julie Støve; Schmitz, Alexander; H Young, Ken; Johnsen, Hans Erik; Dybkær, Karen; Bøgsted, Martin

2016-01-01

Dozens of omics based cancer classification systems have been introduced with prognostic, diagnostic, and predictive capabilities. However, they often employ complex algorithms and are only applicable on whole cohorts of patients, making them difficult to apply in a personalized clinical setting. This prompted us to create hemaClass.org, an online web application providing an easy interface to one-by-one RMA normalization of microarrays and subsequent risk classifications of diffuse large B-cell lymphoma (DLBCL) into cell-of-origin and chemotherapeutic sensitivity classes. Classification results for one-by-one array pre-processing with and without a laboratory specific RMA reference dataset were compared to cohort based classifiers in 4 publicly available datasets. Classifications showed high agreement between one-by-one and whole cohort pre-processsed data when a laboratory specific reference set was supplied. The website is essentially the R-package hemaClass accompanied by a Shiny web application. The well-documented package can be used to run the website locally or to use the developed methods programmatically. The website and R-package is relevant for biological and clinical lymphoma researchers using affymetrix U-133 Plus 2 arrays, as it provides reliable and swift methods for calculation of disease subclasses. The proposed one-by-one pre-processing method is relevant for all researchers using microarrays.

Metrics and textural features of MRI diffusion to improve classification of pediatric posterior fossa tumors.

Science.gov (United States)

Rodriguez Gutierrez, D; Awwad, A; Meijer, L; Manita, M; Jaspan, T; Dineen, R A; Grundy, R G; Auer, D P

2014-05-01

Qualitative radiologic MR imaging review affords limited differentiation among types of pediatric posterior fossa brain tumors and cannot detect histologic or molecular subtypes, which could help to stratify treatment. This study aimed to improve current posterior fossa discrimination of histologic tumor type by using support vector machine classifiers on quantitative MR imaging features. This retrospective study included preoperative MRI in 40 children with posterior fossa tumors (17 medulloblastomas, 16 pilocytic astrocytomas, and 7 ependymomas). Shape, histogram, and textural features were computed from contrast-enhanced T2WI and T1WI and diffusivity (ADC) maps. Combinations of features were used to train tumor-type-specific classifiers for medulloblastoma, pilocytic astrocytoma, and ependymoma types in separation and as a joint posterior fossa classifier. A tumor-subtype classifier was also produced for classic medulloblastoma. The performance of different classifiers was assessed and compared by using randomly selected subsets of training and test data. ADC histogram features (25th and 75th percentiles and skewness) yielded the best classification of tumor type (on average >95.8% of medulloblastomas, >96.9% of pilocytic astrocytomas, and >94.3% of ependymomas by using 8 training samples). The resulting joint posterior fossa classifier correctly assigned >91.4% of the posterior fossa tumors. For subtype classification, 89.4% of classic medulloblastomas were correctly classified on the basis of ADC texture features extracted from the Gray-Level Co-Occurence Matrix. Support vector machine-based classifiers using ADC histogram features yielded very good discrimination among pediatric posterior fossa tumor types, and ADC textural features show promise for further subtype discrimination. These findings suggest an added diagnostic value of quantitative feature analysis of diffusion MR imaging in pediatric neuro-oncology. © 2014 by American Journal of Neuroradiology.

Five-class differential diagnostics of neurodegenerative diseases using random undersampling boosting

DEFF Research Database (Denmark)

Tong, Tong; Ledig, Christian; Guerrero, Ricardo

2017-01-01

Differentiating between different types of neurodegenerative diseases is not only crucial in clinical practice when treatment decisions have to be made, but also has a significant potential for the enrichment of clinical trials. The purpose of this study is to develop a classification framework......-wise grading features) and non-imaging features (CSF measures) were extracted for each subject. In clinical practice, the prevalence of different dementia types is imbalanced, posing challenges for learning an effective classification model. Therefore, we propose the use of the RUSBoost algorithm in order...... to train classifiers and to handle the class imbalance training problem. Furthermore, a multi-class feature selection method based on sparsity is integrated into the proposed framework to improve the classification performance. It also provides a way for investigating the importance of different features...

Quantitative diffusion weighted imaging parameters in tumor and peritumoral stroma for prediction of molecular subtypes in breast cancer

Science.gov (United States)

He, Ting; Fan, Ming; Zhang, Peng; Li, Hui; Zhang, Juan; Shao, Guoliang; Li, Lihua

2018-03-01

Breast cancer can be classified into four molecular subtypes of Luminal A, Luminal B, HER2 and Basal-like, which have significant differences in treatment and survival outcomes. We in this study aim to predict immunohistochemistry (IHC) determined molecular subtypes of breast cancer using image features derived from tumor and peritumoral stroma region based on diffusion weighted imaging (DWI). A dataset of 126 breast cancer patients were collected who underwent preoperative breast MRI with a 3T scanner. The apparent diffusion coefficients (ADCs) were recorded from DWI, and breast image was segmented into regions comprising the tumor and the surrounding stromal. Statistical characteristics in various breast tumor and peritumoral regions were computed, including mean, minimum, maximum, variance, interquartile range, range, skewness, and kurtosis of ADC values. Additionally, the difference of features between each two regions were also calculated. The univariate logistic based classifier was performed for evaluating the performance of the individual features for discriminating subtypes. For multi-class classification, multivariate logistic regression model was trained and validated. The results showed that the tumor boundary and proximal peritumoral stroma region derived features have a higher performance in classification compared to that of the other regions. Furthermore, the prediction model using statistical features, difference features and all the features combined from these regions generated AUC values of 0.774, 0.796 and 0.811, respectively. The results in this study indicate that ADC feature in tumor and peritumoral stromal region would be valuable for estimating the molecular subtype in breast cancer.

Three-Class Mammogram Classification Based on Descriptive CNN Features

Directory of Open Access Journals (Sweden)

M. Mohsin Jadoon

2017-01-01

Full Text Available In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases. In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW and convolutional neural network-curvelet transform (CNN-CT. An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE. In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT, while in the second method discrete curvelet transform (DCT is used. In both methods, dense scale invariant feature (DSIFT for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN. Softmax layer and support vector machine (SVM layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

Bio-stimuli-responsive multi-scale hyaluronic acid nanoparticles for deepened tumor penetration and enhanced therapy.

Science.gov (United States)

Huo, Mengmeng; Li, Wenyan; Chaudhuri, Arka Sen; Fan, Yuchao; Han, Xiu; Yang, Chen; Wu, Zhenghong; Qi, Xiaole

2017-09-01

In this study, we developed bio-stimuli-responsive multi-scale hyaluronic acid (HA) nanoparticles encapsulated with polyamidoamine (PAMAM) dendrimers as the subunits. These HA/PAMAM nanoparticles of large scale (197.10±3.00nm) were stable during systematic circulation then enriched at the tumor sites; however, they were prone to be degraded by the high expressed hyaluronidase (HAase) to release inner PAMAM dendrimers and regained a small scale (5.77±0.25nm) with positive charge. After employing tumor spheroids penetration assay on A549 3D tumor spheroids for 8h, the fluorescein isothiocyanate (FITC) labeled multi-scale HA/PAMAM-FITC nanoparticles could penetrate deeply into these tumor spheroids with the degradation of HAase. Moreover, small animal imaging technology in male nude mice bearing H22 tumor showed HA/PAMAM-FITC nanoparticles possess higher prolonged systematic circulation compared with both PAMAM-FITC nanoparticles and free FITC. In addition, after intravenous administration in mice bearing H22 tumors, methotrexate (MTX) loaded multi-scale HA/PAMAM-MTX nanoparticles exhibited a 2.68-fold greater antitumor activity. Copyright © 2017 Elsevier Ltd. All rights reserved.

A novel multi-drug metronomic chemotherapy significantly delays tumor growth in mice.

Science.gov (United States)

Tagliamonte, Maria; Petrizzo, Annacarmen; Napolitano, Maria; Luciano, Antonio; Rea, Domenica; Barbieri, Antonio; Arra, Claudio; Maiolino, Piera; Tornesello, Marialina; Ciliberto, Gennaro; Buonaguro, Franco M; Buonaguro, Luigi

2016-02-24

The tumor immunosuppressive microenvironment represents a major obstacle to an effective tumor-specific cellular immune response. In the present study, the counterbalance effect of a novel metronomic chemotherapy protocol on such an immunosuppressive microenvironment was evaluated in a mouse model upon sub-cutaneous ectopic implantation of B16 melanoma cells. The chemotherapy consisted of a novel multi-drug cocktail including taxanes and alkylating agents, administered in a daily metronomic fashion. The newly designed strategy was shown to be safe, well tolerated and significantly efficacious. Treated animals showed a remarkable delay in tumor growth and prolonged survival as compared to control group. Such an effect was directly correlated with CD4(+) T cell reduction and CD8(+) T cell increase. Furthermore, a significant reduction in the percentage of both CD25(+)FoxP3(+) and CD25(+)CD127(low) regulatory T cell population was found both in the spleens and in the tumor lesions. Finally, the metronomic chemotherapy induced an intrinsic CD8(+) T cell response specific to B16 naturally expressed Trp2 TAA. The novel multi-drug daily metronomic chemotherapy evaluated in the present study was very effective in counterbalancing the immunosuppressive tumor microenvironment. Consequently, the intrinsic anti-tumor T cell immunity could exert its function, targeting specific TAA and significantly containing tumor growth. Overall, the results show that this represents a promising adjuvant approach to significantly enhance efficacy of intrinsic or vaccine-elicited tumor-specific cellular immunity.

Estimating Classification Errors under Edit Restrictions in Composite Survey-Register Data Using Multiple Imputation Latent Class Modelling (MILC)

NARCIS (Netherlands)

Boeschoten, Laura; Oberski, Daniel; De Waal, Ton

2017-01-01

Both registers and surveys can contain classification errors. These errors can be estimated by making use of a composite data set. We propose a new method based on latent class modelling to estimate the number of classification errors across several sources while taking into account impossible

adabag: An R Package for Classification with Boosting and Bagging

Directory of Open Access Journals (Sweden)

Esteban Alfaro

2013-09-01

Full Text Available Boosting and bagging are two widely used ensemble methods for classification. Their common goal is to improve the accuracy of a classifier combining single classifiers which are slightly better than random guessing. Among the family of boosting algorithms, AdaBoost (adaptive boosting is the best known, although it is suitable only for dichotomous tasks. AdaBoost.M1 and SAMME (stagewise additive modeling using a multi-class exponential loss function are two easy and natural extensions to the general case of two or more classes. In this paper, the adabag R package is introduced. This version implements AdaBoost.M1, SAMME and bagging algorithms with classification trees as base classifiers. Once the ensembles have been trained, they can be used to predict the class of new samples. The accuracy of these classifiers can be estimated in a separated data set or through cross validation. Moreover, the evolution of the error as the ensemble grows can be analysed and the ensemble can be pruned. In addition, the margin in the class prediction and the probability of each class for the observations can be calculated. Finally, several classic examples in classification literature are shown to illustrate the use of this package.

Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China

Directory of Open Access Journals (Sweden)

Shaohong Tian

2016-11-01

Full Text Available The wetland classification from remotely sensed data is usually difficult due to the extensive seasonal vegetation dynamics and hydrological fluctuation. This study presents a random forest classification approach for the retrieval of the wetland landcover in the arid regions by fusing the Pléiade-1B data with multi-date Landsat-8 data. The segmentation of the Pléiade-1B multispectral image data was performed based on an object-oriented approach, and the geometric and spectral features were extracted for the segmented image objects. The normalized difference vegetation index (NDVI series data were also calculated from the multi-date Landsat-8 data, reflecting vegetation phenological changes in its growth cycle. The feature set extracted from the two sensors data was optimized and employed to create the random forest model for the classification of the wetland landcovers in the Ertix River in northern Xinjiang, China. Comparison with other classification methods such as support vector machine and artificial neural network classifiers indicates that the random forest classifier can achieve accurate classification with an overall accuracy of 93% and the Kappa coefficient of 0.92. The classification accuracy of the farming lands and water bodies that have distinct boundaries with the surrounding land covers was improved 5%–10% by making use of the property of geometric shapes. To remove the difficulty in the classification that was caused by the similar spectral features of the vegetation covers, the phenological difference and the textural information of co-occurrence gray matrix were incorporated into the classification, and the main wetland vegetation covers in the study area were derived from the two sensors data. The inclusion of phenological information in the classification enables the classification errors being reduced down, and the overall accuracy was improved approximately 10%. The results show that the proposed random forest

Spectral multi-energy CT texture analysis with machine learning for tissue classification: an investigation using classification of benign parotid tumours as a testing paradigm.

Science.gov (United States)

Al Ajmi, Eiman; Forghani, Behzad; Reinhold, Caroline; Bayat, Maryam; Forghani, Reza

2018-06-01

There is a rich amount of quantitative information in spectral datasets generated from dual-energy CT (DECT). In this study, we compare the performance of texture analysis performed on multi-energy datasets to that of virtual monochromatic images (VMIs) at 65 keV only, using classification of the two most common benign parotid neoplasms as a testing paradigm. Forty-two patients with pathologically proven Warthin tumour (n = 25) or pleomorphic adenoma (n = 17) were evaluated. Texture analysis was performed on VMIs ranging from 40 to 140 keV in 5-keV increments (multi-energy analysis) or 65-keV VMIs only, which is typically considered equivalent to single-energy CT. Random forest (RF) models were constructed for outcome prediction using separate randomly selected training and testing sets or the entire patient set. Using multi-energy texture analysis, tumour classification in the independent testing set had accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 92%, 86%, 100%, 100%, and 83%, compared to 75%, 57%, 100%, 100%, and 63%, respectively, for single-energy analysis. Multi-energy texture analysis demonstrates superior performance compared to single-energy texture analysis of VMIs at 65 keV for classification of benign parotid tumours. • We present and validate a paradigm for texture analysis of DECT scans. • Multi-energy dataset texture analysis is superior to single-energy dataset texture analysis. • DECT texture analysis has high accura\\cy for diagnosis of benign parotid tumours. • DECT texture analysis with machine learning can enhance non-invasive diagnostic tumour evaluation.

Systematic bias in genomic classification due to contaminating non-neoplastic tissue in breast tumor samples.

Science.gov (United States)

Elloumi, Fathi; Hu, Zhiyuan; Li, Yan; Parker, Joel S; Gulley, Margaret L; Amos, Keith D; Troester, Melissa A

2011-06-30

Genomic tests are available to predict breast cancer recurrence and to guide clinical decision making. These predictors provide recurrence risk scores along with a measure of uncertainty, usually a confidence interval. The confidence interval conveys random error and not systematic bias. Standard tumor sampling methods make this problematic, as it is common to have a substantial proportion (typically 30-50%) of a tumor sample comprised of histologically benign tissue. This "normal" tissue could represent a source of non-random error or systematic bias in genomic classification. To assess the performance characteristics of genomic classification to systematic error from normal contamination, we collected 55 tumor samples and paired tumor-adjacent normal tissue. Using genomic signatures from the tumor and paired normal, we evaluated how increasing normal contamination altered recurrence risk scores for various genomic predictors. Simulations of normal tissue contamination caused misclassification of tumors in all predictors evaluated, but different breast cancer predictors showed different types of vulnerability to normal tissue bias. While two predictors had unpredictable direction of bias (either higher or lower risk of relapse resulted from normal contamination), one signature showed predictable direction of normal tissue effects. Due to this predictable direction of effect, this signature (the PAM50) was adjusted for normal tissue contamination and these corrections improved sensitivity and negative predictive value. For all three assays quality control standards and/or appropriate bias adjustment strategies can be used to improve assay reliability. Normal tissue sampled concurrently with tumor is an important source of bias in breast genomic predictors. All genomic predictors show some sensitivity to normal tissue contamination and ideal strategies for mitigating this bias vary depending upon the particular genes and computational methods used in the predictor.

DisoMCS: Accurately Predicting Protein Intrinsically Disordered Regions Using a Multi-Class Conservative Score Approach.

Directory of Open Access Journals (Sweden)

Zhiheng Wang

Full Text Available The precise prediction of protein intrinsically disordered regions, which play a crucial role in biological procedures, is a necessary prerequisite to further the understanding of the principles and mechanisms of protein function. Here, we propose a novel predictor, DisoMCS, which is a more accurate predictor of protein intrinsically disordered regions. The DisoMCS bases on an original multi-class conservative score (MCS obtained by sequence-order/disorder alignment. Initially, near-disorder regions are defined on fragments located at both the terminus of an ordered region connecting a disordered region. Then the multi-class conservative score is generated by sequence alignment against a known structure database and represented as order, near-disorder and disorder conservative scores. The MCS of each amino acid has three elements: order, near-disorder and disorder profiles. Finally, the MCS is exploited as features to identify disordered regions in sequences. DisoMCS utilizes a non-redundant data set as the training set, MCS and predicted secondary structure as features, and a conditional random field as the classification algorithm. In predicted near-disorder regions a residue is determined as an order or a disorder according to the optimized decision threshold. DisoMCS was evaluated by cross-validation, large-scale prediction, independent tests and CASP (Critical Assessment of Techniques for Protein Structure Prediction tests. All results confirmed that DisoMCS was very competitive in terms of accuracy of prediction when compared with well-established publicly available disordered region predictors. It also indicated our approach was more accurate when a query has higher homologous with the knowledge database.The DisoMCS is available at http://cal.tongji.edu.cn/disorder/.

Supervised target detection in hyperspectral images using one-class Fukunaga-Koontz Transform

Science.gov (United States)

Binol, Hamidullah; Bal, Abdullah

2016-05-01

A novel hyperspectral target detection technique based on Fukunaga-Koontz transform (FKT) is presented. FKT offers significant properties for feature selection and ordering. However, it can only be used to solve multi-pattern classification problems. Target detection may be considered as a two-class classification problem, i.e., target versus background clutter. Nevertheless, background clutter typically contains different types of materials. That's why; target detection techniques are different than classification methods by way of modeling clutter. To avoid the modeling of the background clutter, we have improved one-class FKT (OC-FKT) for target detection. The statistical properties of target training samples are used to define tunnel-like boundary of the target class. Non-target samples are then created synthetically as to be outside of the boundary. Thus, only limited target samples become adequate for training of FKT. The hyperspectral image experiments confirm that the proposed OC-FKT technique provides an effective means for target detection.

Value of multi-slice CT in the classification diagnosis of hilar cholangiocarcinoma

International Nuclear Information System (INIS)

Qian Yi; Zeng Mengsu; Ling Zhiqing; Rao Shengxiang; Liu Yalan

2008-01-01

Objective: To evaluate the value of multi-slice CT (MSCT) classification in the assessment of the hilar cholangiocarcinoma resectability. Methods: Thirty patients with surgically and histopathologically proved hilar cholangiocarcinomas who underwent preoperative MSCT and were diagnosed correctly were included in present study. Transverse images and reconstructed MPR images were reviewed for Bismuth-Corlette classification and morphological classification of hilar cholangiocarcinoma. Then MSCT classification was compared with findings of surgery and histopathology. Curative resectabilty of different types according to Bismuth-Corlette classification and morphological classification were analyzed with chi-square test. Results: In 30 cases, the numbers of Type I, II, IIIa, IIIb and IV according to Bismuth-Corlette classification were 1, 3, 4, 5 and 17. Seventeen patients underwent curative resections, among which 1, 2, 1, 4 and 9 belonged to Type I, II, IIIa, IIIb and IV respectively. However, there was no significant difference in curative resectability among different types of Bismuth-Corlette classification (χ 2 = 0.9875, P>0.05). In present study, the accuracy of MSCT in Bismuth-Corlette classification reached 86.7% (26/30). The numbers of periductal infiltrating, mass forming and intraductal growing type were 13, 13 and 4, while 6, 8 and 3 cases of each type underwent curative resections. There was no significant difference in curative resectability among different types of morphological classification (χ 2 =1.2583, P>0.05). The accuracy of MSCT in morphological classification was 100% (30/30) in this study group. Conclusion: MSCT can make accurate diagnosis of Bismuth-Corlette classification and morphological classification, which is helpful in preoperative respectability assessment of hilar cholangiocarcinoma. (authors)

PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications.

Science.gov (United States)

Pasquier, C; Promponas, V J; Hamodrakas, S J

2001-08-15

A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the avoidance of data overfitting. Capturing information from as few as 50 protein sequences spread among the four target classes (6 transmembrane, 10 fibrous, 13 globular, and 17 mixed), PRED-CLASS was able to obtain 371 correct predictions out of a set of 387 proteins (success rate approximately 96%) unambiguously assigned into one of the target classes. The application of PRED-CLASS to several test sets and complete proteomes of several organisms demonstrates that such a method could serve as a valuable tool in the annotation of genomic open reading frames with no functional assignment or as a preliminary step in fold recognition and ab initio structure prediction methods. Detailed results obtained for various data sets and completed genomes, along with a web sever running the PRED-CLASS algorithm, can be accessed over the World Wide Web at http://o2.biol.uoa.gr/PRED-CLASS.

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.

New fuzzy support vector machine for the class imbalance problem in medical datasets classification.

Science.gov (United States)

Gu, Xiaoqing; Ni, Tongguang; Wang, Hongyuan

2014-01-01

In medical datasets classification, support vector machine (SVM) is considered to be one of the most successful methods. However, most of the real-world medical datasets usually contain some outliers/noise and data often have class imbalance problems. In this paper, a fuzzy support machine (FSVM) for the class imbalance problem (called FSVM-CIP) is presented, which can be seen as a modified class of FSVM by extending manifold regularization and assigning two misclassification costs for two classes. The proposed FSVM-CIP can be used to handle the class imbalance problem in the presence of outliers/noise, and enhance the locality maximum margin. Five real-world medical datasets, breast, heart, hepatitis, BUPA liver, and pima diabetes, from the UCI medical database are employed to illustrate the method presented in this paper. Experimental results on these datasets show the outperformed or comparable effectiveness of FSVM-CIP.

New Fuzzy Support Vector Machine for the Class Imbalance Problem in Medical Datasets Classification

Directory of Open Access Journals (Sweden)

Xiaoqing Gu

2014-01-01

Full Text Available In medical datasets classification, support vector machine (SVM is considered to be one of the most successful methods. However, most of the real-world medical datasets usually contain some outliers/noise and data often have class imbalance problems. In this paper, a fuzzy support machine (FSVM for the class imbalance problem (called FSVM-CIP is presented, which can be seen as a modified class of FSVM by extending manifold regularization and assigning two misclassification costs for two classes. The proposed FSVM-CIP can be used to handle the class imbalance problem in the presence of outliers/noise, and enhance the locality maximum margin. Five real-world medical datasets, breast, heart, hepatitis, BUPA liver, and pima diabetes, from the UCI medical database are employed to illustrate the method presented in this paper. Experimental results on these datasets show the outperformed or comparable effectiveness of FSVM-CIP.

A clinical perspective on the 2016 WHO brain tumor classification and routine molecular diagnostics.

Science.gov (United States)

van den Bent, Martin J; Weller, Michael; Wen, Patrick Y; Kros, Johan M; Aldape, Ken; Chang, Susan

2017-05-01

The 2007 World Health Organization (WHO) classification of brain tumors did not use molecular abnormalities as diagnostic criteria. Studies have shown that genotyping allows a better prognostic classification of diffuse glioma with improved treatment selection. This has resulted in a major revision of the WHO classification, which is now for adult diffuse glioma centered around isocitrate dehydrogenase (IDH) and 1p/19q diagnostics. This revised classification is reviewed with a focus on adult brain tumors, and includes a recommendation of genes of which routine testing is clinically useful. Apart from assessment of IDH mutational status including sequencing of R132H-immunohistochemistry negative cases and testing for 1p/19q, several other markers can be considered for routine testing, including assessment of copy number alterations of chromosome 7 and 10 and of TERT promoter, BRAF, and H3F3A mutations. For "glioblastoma, IDH mutated" the term "astrocytoma grade IV" could be considered. It should be considered to treat IDH wild-type grades II and III diffuse glioma with polysomy of chromosome 7 and loss of 10q as glioblastoma. New developments must be more quickly translated into further revised diagnostic categories. Quality control and rapid integration of molecular findings into the final diagnosis and the communication of the final diagnosis to clinicians require systematic attention. © The Author(s) 2017. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Estimating Classification Errors Under Edit Restrictions in Composite Survey-Register Data Using Multiple Imputation Latent Class Modelling (MILC

Directory of Open Access Journals (Sweden)

Boeschoten Laura

2017-12-01

Full Text Available Both registers and surveys can contain classification errors. These errors can be estimated by making use of a composite data set. We propose a new method based on latent class modelling to estimate the number of classification errors across several sources while taking into account impossible combinations with scores on other variables. Furthermore, the latent class model, by multiply imputing a new variable, enhances the quality of statistics based on the composite data set. The performance of this method is investigated by a simulation study, which shows that whether or not the method can be applied depends on the entropy R2 of the latent class model and the type of analysis a researcher is planning to do. Finally, the method is applied to public data from Statistics Netherlands.

hMuLab: A Biomedical Hybrid MUlti-LABel Classifier Based on Multiple Linear Regression.

Science.gov (United States)

Wang, Pu; Ge, Ruiquan; Xiao, Xuan; Zhou, Manli; Zhou, Fengfeng

2017-01-01

Many biomedical classification problems are multi-label by nature, e.g., a gene involved in a variety of functions and a patient with multiple diseases. The majority of existing classification algorithms assumes each sample with only one class label, and the multi-label classification problem remains to be a challenge for biomedical researchers. This study proposes a novel multi-label learning algorithm, hMuLab, by integrating both feature-based and neighbor-based similarity scores. The multiple linear regression modeling techniques make hMuLab capable of producing multiple label assignments for a query sample. The comparison results over six commonly-used multi-label performance measurements suggest that hMuLab performs accurately and stably for the biomedical datasets, and may serve as a complement to the existing literature.

Cancer classification in the genomic era: five contemporary problems.

Science.gov (United States)

Song, Qingxuan; Merajver, Sofia D; Li, Jun Z

2015-10-19

Classification is an everyday instinct as well as a full-fledged scientific discipline. Throughout the history of medicine, disease classification is central to how we develop knowledge, make diagnosis, and assign treatment. Here, we discuss the classification of cancer and the process of categorizing cancer subtypes based on their observed clinical and biological features. Traditionally, cancer nomenclature is primarily based on organ location, e.g., "lung cancer" designates a tumor originating in lung structures. Within each organ-specific major type, finer subgroups can be defined based on patient age, cell type, histological grades, and sometimes molecular markers, e.g., hormonal receptor status in breast cancer or microsatellite instability in colorectal cancer. In the past 15+ years, high-throughput technologies have generated rich new data regarding somatic variations in DNA, RNA, protein, or epigenomic features for many cancers. These data, collected for increasingly large tumor cohorts, have provided not only new insights into the biological diversity of human cancers but also exciting opportunities to discover previously unrecognized cancer subtypes. Meanwhile, the unprecedented volume and complexity of these data pose significant challenges for biostatisticians, cancer biologists, and clinicians alike. Here, we review five related issues that represent contemporary problems in cancer taxonomy and interpretation. (1) How many cancer subtypes are there? (2) How can we evaluate the robustness of a new classification system? (3) How are classification systems affected by intratumor heterogeneity and tumor evolution? (4) How should we interpret cancer subtypes? (5) Can multiple classification systems co-exist? While related issues have existed for a long time, we will focus on those aspects that have been magnified by the recent influx of complex multi-omics data. Exploration of these problems is essential for data-driven refinement of cancer classification

Classification of cancerous cells based on the one-class problem approach

Science.gov (United States)

Murshed, Nabeel A.; Bortolozzi, Flavio; Sabourin, Robert

1996-03-01

One of the most important factors in reducing the effect of cancerous diseases is the early diagnosis, which requires a good and a robust method. With the advancement of computer technologies and digital image processing, the development of a computer-based system has become feasible. In this paper, we introduce a new approach for the detection of cancerous cells. This approach is based on the one-class problem approach, through which the classification system need only be trained with patterns of cancerous cells. This reduces the burden of the training task by about 50%. Based on this approach, a computer-based classification system is developed, based on the Fuzzy ARTMAP neural networks. Experimental results were performed using a set of 542 patterns taken from a sample of breast cancer. Results of the experiment show 98% correct identification of cancerous cells and 95% correct identification of non-cancerous cells.

poLCA: An R Package for Polytomous Variable Latent Class Analysis

Directory of Open Access Journals (Sweden)

Drew A. Linzer

2011-08-01

Full Text Available poLCA is a software package for the estimation of latent class and latent class regression models for polytomous outcome variables, implemented in the R statistical computing environment. Both models can be called using a single simple command line. The basic latent class model is a finite mixture model in which the component distributions are assumed to be multi-way cross-classification tables with all variables mutually independent. The latent class regression model further enables the researcher to estimate the effects of covariates on predicting latent class membership. poLCA uses expectation-maximization and Newton-Raphson algorithms to find maximum likelihood estimates of the model parameters.

Multi-course PDT of malignant tumors: the influence on primary tumor, metastatic spreading and homeostasis of cancer patients

Science.gov (United States)

Sokolov, Victor V.; Chissov, Valery I.; Yakubovskaya, Raisa I.; Filonenko, E. V.; Sukhin, Garry M.; Nemtsova, E. R.; Belous, T. A.; Zharkova, Natalia N.

1996-12-01

The first clinical trials of photodynamic therapy (PDT) of cancer with two photosensitizers, PHOTOHEME and PHOTOSENS, were started in P.A. Hertzen Research Oncological Institute (Moscow, Russia) in 1992 and 1994. Up to now, 208 patients with primary, recurrent and metastatic malignant tumors (469) of skin (34 patients/185 tumors), breast cancer (24/101), head and neck (30/31), trachea and bronchus (31/42), esophagus (35/35), stomach (31/32), rectum (4/4), vagina and uterine cervix (7/8) and bladder (12/31) have been treated by PDT. One-hundred-thirty patients were injected with PHOTOHEME, 64 patients were injected with PHOTOSENS, 14 patients were injected with PHOTOHEME and PHOTOSENS. Totally, 302 courses of treatment were performed: 155 patients had one course and 53 patients were subjected to two to nine PDT sources with intervals from 1 to 18 months. A therapeutic effect of a one-course and multi- course PDT of malignant tumors (respiratory, digestive and urogenital systems) was evaluated clinically, histologically, roentgenologically, sonographically and endoscopically. The biochemical, hematological and immunological investigations were performed for all the patients in dynamics. Results of our study showed that a multi-course PDT method seems to be perspective in treatment of malignant tumors of basic localizations.

Multiparametric classification links tumor microenvironments with tumor cell phenotype.

Directory of Open Access Journals (Sweden)

Bojana Gligorijevic

2014-11-01

Full Text Available While it has been established that a number of microenvironment components can affect the likelihood of metastasis, the link between microenvironment and tumor cell phenotypes is poorly understood. Here we have examined microenvironment control over two different tumor cell motility phenotypes required for metastasis. By high-resolution multiphoton microscopy of mammary carcinoma in mice, we detected two phenotypes of motile tumor cells, different in locomotion speed. Only slower tumor cells exhibited protrusions with molecular, morphological, and functional characteristics associated with invadopodia. Each region in the primary tumor exhibited either fast- or slow-locomotion. To understand how the tumor microenvironment controls invadopodium formation and tumor cell locomotion, we systematically analyzed components of the microenvironment previously associated with cell invasion and migration. No single microenvironmental property was able to predict the locations of tumor cell phenotypes in the tumor if used in isolation or combined linearly. To solve this, we utilized the support vector machine (SVM algorithm to classify phenotypes in a nonlinear fashion. This approach identified conditions that promoted either motility phenotype. We then demonstrated that varying one of the conditions may change tumor cell behavior only in a context-dependent manner. In addition, to establish the link between phenotypes and cell fates, we photoconverted and monitored the fate of tumor cells in different microenvironments, finding that only tumor cells in the invadopodium-rich microenvironments degraded extracellular matrix (ECM and disseminated. The number of invadopodia positively correlated with degradation, while the inhibiting metalloproteases eliminated degradation and lung metastasis, consistent with a direct link among invadopodia, ECM degradation, and metastasis. We have detected and characterized two phenotypes of motile tumor cells in vivo, which

A hierarchical anatomical classification schema for prediction of phenotypic side effects.

Science.gov (United States)

Wadhwa, Somin; Gupta, Aishwarya; Dokania, Shubham; Kanji, Rakesh; Bagler, Ganesh

2018-01-01

Prediction of adverse drug reactions is an important problem in drug discovery endeavors which can be addressed with data-driven strategies. SIDER is one of the most reliable and frequently used datasets for identification of key features as well as building machine learning models for side effects prediction. The inherently unbalanced nature of this data presents with a difficult multi-label multi-class problem towards prediction of drug side effects. We highlight the intrinsic issue with SIDER data and methodological flaws in relying on performance measures such as AUC while attempting to predict side effects.We argue for the use of metrics that are robust to class imbalance for evaluation of classifiers. Importantly, we present a 'hierarchical anatomical classification schema' which aggregates side effects into organs, sub-systems, and systems. With the help of a weighted performance measure, using 5-fold cross-validation we show that this strategy facilitates biologically meaningful side effects prediction at different levels of anatomical hierarchy. By implementing various machine learning classifiers we show that Random Forest model yields best classification accuracy at each level of coarse-graining. The manually curated, hierarchical schema for side effects can also serve as the basis of future studies towards prediction of adverse reactions and identification of key features linked to specific organ systems. Our study provides a strategy for hierarchical classification of side effects rooted in the anatomy and can pave the way for calibrated expert systems for multi-level prediction of side effects.

An Ensemble Based Evolutionary Approach to the Class Imbalance Problem with Applications in CBIR

Directory of Open Access Journals (Sweden)

Aun Irtaza

2018-03-01

Full Text Available In order to lower the dependence on textual annotations for image searches, the content based image retrieval (CBIR has become a popular topic in computer vision. A wide range of CBIR applications consider classification techniques, such as artificial neural networks (ANN, support vector machines (SVM, etc. to understand the query image content to retrieve relevant output. However, in multi-class search environments, the retrieval results are far from optimal due to overlapping semantics amongst subjects of various classes. The classification through multiple classifiers generate better results, but as the number of negative examples increases due to highly correlated semantic classes, classification bias occurs towards the negative class, hence, the combination of the classifiers become even more unstable particularly in one-against-all classification scenarios. In order to resolve this issue, a genetic algorithm (GA based classifier comity learning (GCCL method is presented in this paper to generate stable classifiers by combining ANN with SVMs through asymmetric and symmetric bagging. The proposed approach resolves the classification disagreement amongst different classifiers and also resolves the class imbalance problem in CBIR. Once the stable classifiers are generated, the query image is presented to the trained model to understand the underlying semantic content of the query image for association with the precise semantic class. Afterwards, the feature similarity is computed within the obtained class to generate the semantic response of the system. The experiments reveal that the proposed method outperforms various state-of-the-art methods and significantly improves the image retrieval performance.

A generalized parametric response mapping method for analysis of multi-parametric imaging: A feasibility study with application to glioblastoma.

Science.gov (United States)

Lausch, Anthony; Yeung, Timothy Pok-Chi; Chen, Jeff; Law, Elton; Wang, Yong; Urbini, Benedetta; Donelli, Filippo; Manco, Luigi; Fainardi, Enrico; Lee, Ting-Yim; Wong, Eugene

2017-11-01

Parametric response map (PRM) analysis of functional imaging has been shown to be an effective tool for early prediction of cancer treatment outcomes and may also be well-suited toward guiding personalized adaptive radiotherapy (RT) strategies such as sub-volume boosting. However, the PRM method was primarily designed for analysis of longitudinally acquired pairs of single-parameter image data. The purpose of this study was to demonstrate the feasibility of a generalized parametric response map analysis framework, which enables analysis of multi-parametric data while maintaining the key advantages of the original PRM method. MRI-derived apparent diffusion coefficient (ADC) and relative cerebral blood volume (rCBV) maps acquired at 1 and 3-months post-RT for 19 patients with high-grade glioma were used to demonstrate the algorithm. Images were first co-registered and then standardized using normal tissue image intensity values. Tumor voxels were then plotted in a four-dimensional Cartesian space with coordinate values equal to a voxel's image intensity in each of the image volumes and an origin defined as the multi-parametric mean of normal tissue image intensity values. Voxel positions were orthogonally projected onto a line defined by the origin and a pre-determined response vector. The voxels are subsequently classified as positive, negative or nil, according to whether projected positions along the response vector exceeded a threshold distance from the origin. The response vector was selected by identifying the direction in which the standard deviation of tumor image intensity values was maximally different between responding and non-responding patients within a training dataset. Voxel classifications were visualized via familiar three-class response maps and then the fraction of tumor voxels associated with each of the classes was investigated for predictive utility analogous to the original PRM method. Independent PRM and MPRM analyses of the contrast

A Multiagent-based Intrusion Detection System with the Support of Multi-Class Supervised Classification

Science.gov (United States)

Shyu, Mei-Ling; Sainani, Varsha

The increasing number of network security related incidents have made it necessary for the organizations to actively protect their sensitive data with network intrusion detection systems (IDSs). IDSs are expected to analyze a large volume of data while not placing a significantly added load on the monitoring systems and networks. This requires good data mining strategies which take less time and give accurate results. In this study, a novel data mining assisted multiagent-based intrusion detection system (DMAS-IDS) is proposed, particularly with the support of multiclass supervised classification. These agents can detect and take predefined actions against malicious activities, and data mining techniques can help detect them. Our proposed DMAS-IDS shows superior performance compared to central sniffing IDS techniques, and saves network resources compared to other distributed IDS with mobile agents that activate too many sniffers causing bottlenecks in the network. This is one of the major motivations to use a distributed model based on multiagent platform along with a supervised classification technique.

Multi-Temporal Land Cover Classification with Long Short-Term Memory Neural Networks

Science.gov (United States)

Rußwurm, M.; Körner, M.

2017-05-01

Land cover classification (LCC) is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM) neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN), with a classical non-temporal convolutional neural network (CNN) model and an additional support vector machine (SVM) baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

MULTI-TEMPORAL LAND COVER CLASSIFICATION WITH LONG SHORT-TERM MEMORY NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

M. Rußwurm

2017-05-01

Full Text Available Land cover classification (LCC is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN, with a classical non-temporal convolutional neural network (CNN model and an additional support vector machine (SVM baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

3D model-based documentation with the Tumor Therapy Manager (TTM) improves TNM staging of head and neck tumor patients.

Science.gov (United States)

Pankau, Thomas; Wichmann, Gunnar; Neumuth, Thomas; Preim, Bernhard; Dietz, Andreas; Stumpp, Patrick; Boehm, Andreas

2015-10-01

Many treatment approaches are available for head and neck cancer (HNC), leading to challenges for a multidisciplinary medical team in matching each patient with an appropriate regimen. In this effort, primary diagnostics and its reliable documentation are indispensable. A three-dimensional (3D) documentation system was developed and tested to determine its influence on interpretation of these data, especially for TNM classification. A total of 42 HNC patient data sets were available, including primary diagnostics such as panendoscopy, performed and evaluated by an experienced head and neck surgeon. In addition to the conventional panendoscopy form and report, a 3D representation was generated with the "Tumor Therapy Manager" (TTM) software. These cases were randomly re-evaluated by 11 experienced otolaryngologists from five hospitals, half with and half without the TTM data. The accuracy of tumor staging was assessed by pre-post comparison of the TNM classification. TNM staging showed no significant differences in tumor classification (T) with and without 3D from TTM. However, there was a significant decrease in standard deviation from 0.86 to 0.63 via TTM ([Formula: see text]). In nodal staging without TTM, the lymph nodes (N) were significantly underestimated with [Formula: see text] classes compared with [Formula: see text] with TTM ([Formula: see text]). Likewise, the standard deviation was reduced from 0.79 to 0.69 ([Formula: see text]). There was no influence of TTM results on the evaluation of distant metastases (M). TNM staging was more reproducible and nodal staging more accurate when 3D documentation of HNC primary data was available to experienced otolaryngologists. The more precise assessment of the tumor classification with TTM should provide improved decision-making concerning therapy, especially within the interdisciplinary tumor board.

Multi-Cohort Stand Structural Classification: Ground- and LiDAR-based Approaches for Boreal Mixedwood and Black Spruce Forest Types of Northeastern Ontario

Science.gov (United States)

Kuttner, Benjamin George

Natural fire return intervals are relatively long in eastern Canadian boreal forests and often allow for the development of stands with multiple, successive cohorts of trees. Multi-cohort forest management (MCM) provides a strategy to maintain such multi-cohort stands that focuses on three broad phases of increasingly complex, post-fire stand development, termed "cohorts", and recommends different silvicultural approaches be applied to emulate different cohort types. Previous research on structural cohort typing has relied upon primarily subjective classification methods; in this thesis, I develop more comprehensive and objective methods for three common boreal mixedwood and black spruce forest types in northeastern Ontario. Additionally, I examine relationships between cohort types and stand age, productivity, and disturbance history and the utility of airborne LiDAR to retrieve ground-based classifications and to extend structural cohort typing from plot- to stand-levels. In both mixedwood and black spruce forest types, stand age and age-related deadwood features varied systematically with cohort classes in support of an age-based interpretation of increasing cohort complexity. However, correlations of stand age with cohort classes were surprisingly weak. Differences in site productivity had a significant effect on the accrual of increasingly complex multi-cohort stand structure in both forest types, especially in black spruce stands. The effects of past harvesting in predictive models of class membership were only significant when considered in isolation of age. As an age-emulation strategy, the three cohort model appeared to be poorly suited to black spruce forests where the accrual of structural complexity appeared to be more a function of site productivity than age. Airborne LiDAR data appear to be particularly useful in recovering plot-based cohort types and extending them to the stand-level. The main gradients of structural variability detected using Li

[Categorization of uterine cervix tumors : What's new in the 2014 WHO classification].

Science.gov (United States)

Lax, S F; Horn, L-C; Löning, T

2016-11-01

In the 2014 WHO classification, squamous cell precursor lesions are classified as low-grade and high-grade intraepithelial lesions. LSIL corresponds to CIN1, HSIL includes CIN2 and CIN3. Only adenocarcinoma in situ (AIS) is accepted as precursor of adenocarcinoma and includes the stratified mucin-producing intraepithelial lesion (SMILE). Although relatively rare, adenocarcinoma and squamous cell carcinoma can be mixed with a poorly differentiated neuroendocrine carcinoma. Most cervical adenocarcinomas are low grade and of endocervical type. Mucinous carcinomas show marked intra- and extracellular mucin production. Almost all squamous cell carcinomas, the vast majority of adenocarcinomas, and many rare carcinoma types are HPV related. For low grade endocervical adenocarcinomas, the pattern-based classification according to Silva should be reported. Neuroendocrine tumors are rare and are classified into low-grade and high-grade, whereby the term carcinoid is still used.

MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering

Directory of Open Access Journals (Sweden)

Ashlock Daniel

2009-08-01

Full Text Available Abstract Background Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. Results We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. Conclusion The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors.

MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering.

Science.gov (United States)

Kim, Eun-Youn; Kim, Seon-Young; Ashlock, Daniel; Nam, Dougu

2009-08-22

Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors.

Authentication of bee pollen grains in bright-field microscopy by combining one-class classification techniques and image processing.

Science.gov (United States)

Chica, Manuel

2012-11-01

A novel method for authenticating pollen grains in bright-field microscopic images is presented in this work. The usage of this new method is clear in many application fields such as bee-keeping sector, where laboratory experts need to identify fraudulent bee pollen samples against local known pollen types. Our system is based on image processing and one-class classification to reject unknown pollen grain objects. The latter classification technique allows us to tackle the major difficulty of the problem, the existence of many possible fraudulent pollen types, and the impossibility of modeling all of them. Different one-class classification paradigms are compared to study the most suitable technique for solving the problem. In addition, feature selection algorithms are applied to reduce the complexity and increase the accuracy of the models. For each local pollen type, a one-class classifier is trained and aggregated into a multiclassifier model. This multiclassification scheme combines the output of all the one-class classifiers in a unique final response. The proposed method is validated by authenticating pollen grains belonging to different Spanish bee pollen types. The overall accuracy of the system on classifying fraudulent microscopic pollen grain objects is 92.3%. The system is able to rapidly reject pollen grains, which belong to nonlocal pollen types, reducing the laboratory work and effort. The number of possible applications of this authentication method in the microscopy research field is unlimited. Copyright © 2012 Wiley Periodicals, Inc.

SEMIAUTOMATIC DETECTION OF TUMORAL ZONE

Directory of Open Access Journals (Sweden)

Ezzeddine Zagrouba

2011-05-01

Full Text Available This paper describes a robust method based on the cooperation of fuzzy classification and regions segmentation algorithms, in order to detect the tumoral zone in the brain Magnetic Resonance Imaging (MRI. On one hand, the classification in fuzzy sets is done by the Fuzzy C-Means algorithm (FCM, where a study of its different parameters and its complexity has been previously realised, which led us to improve it. On the other hand, the segmentation in regions is obtained by an hierarchical method through adaptive thresholding. Then, an operator expert selects a germ in the tumoral zone, and the class containing the sick zone is localised in return for the FCM algorithm. Finally, the superposition of the two partitions of the image will determine the sick zone. The originality of our approach is the parallel exploitation of different types of information in the image by the cooperation of two complementary approaches. This allows us to carry out a pertinent approach for the detection of sick zone in MRI images.

Slow Learner Prediction Using Multi-Variate Naïve Bayes Classification Algorithm

Directory of Open Access Journals (Sweden)

Shiwani Rana

2017-01-01

Full Text Available Machine Learning is a field of computer science that learns from data by studying algorithms and their constructions. In machine learning, for specific inputs, algorithms help to make predictions. Classification is a supervised learning approach, which maps a data item into predefined classes. For predicting slow learners in an institute, a modified Naïve Bayes algorithm implemented. The implementation is carried sing Python.  It takes into account a combination of likewise multi-valued attributes. A dataset of the 60 students of BE (Information Technology Third Semester for the subject of Digital Electronics of University Institute of Engineering and Technology (UIET, Panjab University (PU, Chandigarh, India is taken to carry out the simulations. The analysis is done by choosing most significant forty-eight attributes. The experimental results have shown that the modified Naïve Bayes model has outperformed the Naïve Bayes Classifier in accuracy but requires significant improvement in the terms of elapsed time. By using Modified Naïve Bayes approach, the accuracy is found out to be 71.66% whereas it is calculated 66.66% using existing Naïve Bayes model. Further, a comparison is drawn by using WEKA tool. Here, an accuracy of Naïve Bayes is obtained as 58.33 %.

Embedding filtering criteria into a wrapper marker selection method for brain tumor classification: an application on metabolic peak area ratios

International Nuclear Information System (INIS)

Kounelakis, M G; Zervakis, M E; Giakos, G C; Postma, G J; Buydens, L M C; Kotsiakis, X

2011-01-01

The purpose of this study is to identify reliable sets of metabolic markers that provide accurate classification of complex brain tumors and facilitate the process of clinical diagnosis. Several ratios of metabolites are tested alone or in combination with imaging markers. A wrapper feature selection and classification methodology is studied, employing Fisher's criterion for ranking the markers. The set of extracted markers that express statistical significance is further studied in terms of biological behavior with respect to the brain tumor type and grade. The outcome of this study indicates that the proposed method by exploiting the intrinsic properties of data can actually reveal reliable and biologically relevant sets of metabolic markers, which form an important adjunct toward a more accurate type and grade discrimination of complex brain tumors

Modeling activity recognition of multi resident using label combination of multi label classification in smart home

Science.gov (United States)

Mohamed, Raihani; Perumal, Thinagaran; Sulaiman, Md Nasir; Mustapha, Norwati; Zainudin, M. N. Shah

2017-10-01

Pertaining to the human centric concern and non-obtrusive way, the ambient sensor type technology has been selected, accepted and embedded in the environment in resilient style. Human activities, everyday are gradually becoming complex and thus complicate the inferences of activities when it involving the multi resident in the same smart environment. Current works solutions focus on separate model between the resident, activities and interactions. Some study use data association and extra auxiliary of graphical nodes to model human tracking information in an environment and some produce separate framework to incorporate the auxiliary for interaction feature model. Thus, recognizing the activities and which resident perform the activity at the same time in the smart home are vital for the smart home development and future applications. This paper will cater the above issue by considering the simplification and efficient method using the multi label classification framework. This effort eliminates time consuming and simplifies a lot of pre-processing tasks comparing with previous approach. Applications to the multi resident multi label learning in smart home problems shows the LC (Label Combination) using Decision Tree (DT) as base classifier can tackle the above problems.

Multi-Class load balancing scheme for QoS and energy ...

African Journals Online (AJOL)

Multi-Class load balancing scheme for QoS and energy conservation in cloud computing. ... If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs. Alternatively, you can download the PDF file directly to your computer, from ...

Bacteria classification using Cyranose 320 electronic nose

Directory of Open Access Journals (Sweden)

Gardner Julian W

2002-10-01

Full Text Available Abstract Background An electronic nose (e-nose, the Cyrano Sciences' Cyranose 320, comprising an array of thirty-two polymer carbon black composite sensors has been used to identify six species of bacteria responsible for eye infections when present at a range of concentrations in saline solutions. Readings were taken from the headspace of the samples by manually introducing the portable e-nose system into a sterile glass containing a fixed volume of bacteria in suspension. Gathered data were a very complex mixture of different chemical compounds. Method Linear Principal Component Analysis (PCA method was able to classify four classes of bacteria out of six classes though in reality other two classes were not better evident from PCA analysis and we got 74% classification accuracy from PCA. An innovative data clustering approach was investigated for these bacteria data by combining the 3-dimensional scatter plot, Fuzzy C Means (FCM and Self Organizing Map (SOM network. Using these three data clustering algorithms simultaneously better 'classification' of six eye bacteria classes were represented. Then three supervised classifiers, namely Multi Layer Perceptron (MLP, Probabilistic Neural network (PNN and Radial basis function network (RBF, were used to classify the six bacteria classes. Results A [6 × 1] SOM network gave 96% accuracy for bacteria classification which was best accuracy. A comparative evaluation of the classifiers was conducted for this application. The best results suggest that we are able to predict six classes of bacteria with up to 98% accuracy with the application of the RBF network. Conclusion This type of bacteria data analysis and feature extraction is very difficult. But we can conclude that this combined use of three nonlinear methods can solve the feature extraction problem with very complex data and enhance the performance of Cyranose 320.

Ingenious Snake: An Adaptive Multi-Class Contours Extraction

Science.gov (United States)

Li, Baolin; Zhou, Shoujun

2018-04-01

Active contour model (ACM) plays an important role in computer vision and medical image application. The traditional ACMs were used to extract single-class of object contours. While, simultaneous extraction of multi-class of interesting contours (i.e., various contours with closed- or open-ended) have not been solved so far. Therefore, a novel ACM model named “Ingenious Snake” is proposed to adaptively extract these interesting contours. In the first place, the ridge-points are extracted based on the local phase measurement of gradient vector flow field; the consequential ridgelines initialization are automated with high speed. Secondly, the contours’ deformation and evolvement are implemented with the ingenious snake. In the experiments, the result from initialization, deformation and evolvement are compared with the existing methods. The quantitative evaluation of the structure extraction is satisfying with respect of effectiveness and accuracy.

Classification of multiple sclerosis lesions using adaptive dictionary learning.

Science.gov (United States)

Deshpande, Hrishikesh; Maurel, Pierre; Barillot, Christian

2015-12-01

This paper presents a sparse representation and an adaptive dictionary learning based method for automated classification of multiple sclerosis (MS) lesions in magnetic resonance (MR) images. Manual delineation of MS lesions is a time-consuming task, requiring neuroradiology experts to analyze huge volume of MR data. This, in addition to the high intra- and inter-observer variability necessitates the requirement of automated MS lesion classification methods. Among many image representation models and classification methods that can be used for such purpose, we investigate the use of sparse modeling. In the recent years, sparse representation has evolved as a tool in modeling data using a few basis elements of an over-complete dictionary and has found applications in many image processing tasks including classification. We propose a supervised classification approach by learning dictionaries specific to the lesions and individual healthy brain tissues, which include white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The size of the dictionaries learned for each class plays a major role in data representation but it is an even more crucial element in the case of competitive classification. Our approach adapts the size of the dictionary for each class, depending on the complexity of the underlying data. The algorithm is validated using 52 multi-sequence MR images acquired from 13 MS patients. The results demonstrate the effectiveness of our approach in MS lesion classification. Copyright © 2015 Elsevier Ltd. All rights reserved.

REAL-TIME INTELLIGENT MULTILAYER ATTACK CLASSIFICATION SYSTEM

Directory of Open Access Journals (Sweden)

T. Subbhulakshmi

2014-01-01

Full Text Available Intrusion Detection Systems (IDS takes the lion’s share of the current security infrastructure. Detection of intrusions is vital for initiating the defensive procedures. Intrusion detection was done by statistical and distance based methods. A threshold value is used in these methods to indicate the level of normalcy. When the network traffic crosses the level of normalcy then above which it is flagged as anomalous. When there are occurrences of new intrusion events which are increasingly a key part of system security, the statistical techniques cannot detect them. To overcome this issue, learning techniques are used which helps in identifying new intrusion activities in a computer system. The objective of the proposed system designed in this paper is to classify the intrusions using an Intelligent Multi Layered Attack Classification System (IMLACS which helps in detecting and classifying the intrusions with improved classification accuracy. The intelligent multi layered approach contains three intelligent layers. The first layer involves Binary Support Vector Machine classification for detecting the normal and attack. The second layer involves neural network classification to classify the attacks into classes of attacks. The third layer involves fuzzy inference system to classify the attacks into various subclasses. The proposed IMLACS can be able to detect an intrusion behavior of the networks since the system contains a three intelligent layer classification and better set of rules. Feature selection is also used to improve the time of detection. The experimental results show that the IMLACS achieves the Classification Rate of 97.31%.

NIM: A Node Influence Based Method for Cancer Classification

Directory of Open Access Journals (Sweden)

Yiwen Wang

2014-01-01

Full Text Available The classification of different cancer types owns great significance in the medical field. However, the great majority of existing cancer classification methods are clinical-based and have relatively weak diagnostic ability. With the rapid development of gene expression technology, it is able to classify different kinds of cancers using DNA microarray. Our main idea is to confront the problem of cancer classification using gene expression data from a graph-based view. Based on a new node influence model we proposed, this paper presents a novel high accuracy method for cancer classification, which is composed of four parts: the first is to calculate the similarity matrix of all samples, the second is to compute the node influence of training samples, the third is to obtain the similarity between every test sample and each class using weighted sum of node influence and similarity matrix, and the last is to classify each test sample based on its similarity between every class. The data sets used in our experiments are breast cancer, central nervous system, colon tumor, prostate cancer, acute lymphoblastic leukemia, and lung cancer. experimental results showed that our node influence based method (NIM is more efficient and robust than the support vector machine, K-nearest neighbor, C4.5, naive Bayes, and CART.

Multi-label classifier based on histogram of gradients for predicting the anatomical therapeutic chemical class/classes of a given compound.

Science.gov (United States)

Nanni, Loris; Brahnam, Sheryl

2017-09-15

Given an unknown compound, is it possible to predict its Anatomical Therapeutic Chemical class/classes? This is a challenging yet important problem since such a prediction could be used to deduce not only a compound's possible active ingredients but also its therapeutic, pharmacological and chemical properties, thereby substantially expediting the pace of drug development. The problem is challenging because some drugs and compounds belong to two or more ATC classes, making machine learning extremely difficult. In this article a multi-label classifier system is proposed that incorporates information about a compound's chemical-chemical interaction and its structural and fingerprint similarities to other compounds belonging to the different ATC classes. The proposed system reshapes a 1D feature vector to obtain a 2D matrix representation of the compound. This matrix is then described by a histogram of gradients that is fed into a Multi-Label Learning with Label-Specific Features classifier. Rigorous cross-validations demonstrate the superior prediction quality of this method compared with other state-of-the-art approaches developed for this problem, a superiority that is reflected particularly in the absolute true rate, the most important and harshest metric for assessing multi-label systems. The MATLAB code for replicating the experiments presented in this article is available at https://www.dropbox.com/s/7v1mey48tl9bfgz/ToolPaperATC.rar?dl=0 . loris.nanni@unipd.it. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Volumetric response classification in metastatic solid tumors on MSCT: Initial results in a whole-body setting

International Nuclear Information System (INIS)

Wulff, A.M.; Fabel, M.; Freitag-Wolf, S.; Tepper, M.; Knabe, H.M.; Schäfer, J.P.; Jansen, O.; Bolte, H.

2013-01-01

Purpose: To examine technical parameters of measurement accuracy and differences in tumor response classification using RECIST 1.1 and volumetric assessment in three common metastasis types (lung nodules, liver lesions, lymph node metastasis) simultaneously. Materials and methods: 56 consecutive patients (32 female) aged 41–82 years with a wide range of metastatic solid tumors were examined with MSCT for baseline and follow up. Images were evaluated by three experienced radiologists using manual measurements and semi-automatic lesion segmentation. Institutional ethics review was obtained and all patients gave written informed consent. Data analysis comprised interobserver variability operationalized as coefficient of variation and categorical response classification according to RECIST 1.1 for both manual and volumetric measures. Continuous data were assessed for statistical significance with Wilcoxon signed-rank test and categorical data with Fleiss kappa. Results: Interobserver variability was 6.3% (IQR 4.6%) for manual and 4.1% (IQR 4.4%) for volumetrically obtained sum of relevant diameters (p < 0.05, corrected). 4–8 patients’ response to therapy was classified differently across observers by using volumetry compared to standard manual measurements. Fleiss kappa revealed no significant difference in categorical agreement of response classification between manual (0.7558) and volumetric (0.7623) measurements. Conclusion: Under standard RECIST thresholds there was no advantage of volumetric compared to manual response evaluation. However volumetric assessment yielded significantly lower interobserver variability. This may allow narrower thresholds for volumetric response classification in the future

Volumetric response classification in metastatic solid tumors on MSCT: Initial results in a whole-body setting

Energy Technology Data Exchange (ETDEWEB)

Wulff, A.M., E-mail: a.wulff@rad.uni-kiel.de [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Fabel, M. [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Freitag-Wolf, S., E-mail: freitag@medinfo.uni-kiel.de [Institut für Medizinische Informatik und Statistik, Brunswiker Str. 10, 24105 Kiel (Germany); Tepper, M., E-mail: m.tepper@rad.uni-kiel.de [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Knabe, H.M., E-mail: h.knabe@rad.uni-kiel.de [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Schäfer, J.P., E-mail: jp.schaefer@rad.uni-kiel.de [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Jansen, O., E-mail: o.jansen@neurorad.uni-kiel.de [Klinik für Diagnostische Radiologie, Arnold-Heller-Straße 3, Haus 23, 24105 Kiel (Germany); Bolte, H., E-mail: hendrik.bolte@ukmuenster.de [Klinik für Nuklearmedizin, Albert-Schweitzer-Campus 1, Gebäude A1, 48149 Münster (Germany)

2013-10-01

Purpose: To examine technical parameters of measurement accuracy and differences in tumor response classification using RECIST 1.1 and volumetric assessment in three common metastasis types (lung nodules, liver lesions, lymph node metastasis) simultaneously. Materials and methods: 56 consecutive patients (32 female) aged 41–82 years with a wide range of metastatic solid tumors were examined with MSCT for baseline and follow up. Images were evaluated by three experienced radiologists using manual measurements and semi-automatic lesion segmentation. Institutional ethics review was obtained and all patients gave written informed consent. Data analysis comprised interobserver variability operationalized as coefficient of variation and categorical response classification according to RECIST 1.1 for both manual and volumetric measures. Continuous data were assessed for statistical significance with Wilcoxon signed-rank test and categorical data with Fleiss kappa. Results: Interobserver variability was 6.3% (IQR 4.6%) for manual and 4.1% (IQR 4.4%) for volumetrically obtained sum of relevant diameters (p < 0.05, corrected). 4–8 patients’ response to therapy was classified differently across observers by using volumetry compared to standard manual measurements. Fleiss kappa revealed no significant difference in categorical agreement of response classification between manual (0.7558) and volumetric (0.7623) measurements. Conclusion: Under standard RECIST thresholds there was no advantage of volumetric compared to manual response evaluation. However volumetric assessment yielded significantly lower interobserver variability. This may allow narrower thresholds for volumetric response classification in the future.

Angle′s Molar Classification Revisited

Directory of Open Access Journals (Sweden)

Devanshi Yadav

2014-01-01

Results: Of the 500 pretreatment study casts assessed 52.4% were definitive Class I, 23.6% were Class II, 2.6% were Class III and the ambiguous cases were 21%. These could be easily classified with our method of classification. Conclusion: This improvised classification technique will help orthodontists in making classification of malocclusion accurate and simple.

Multi-Objective Particle Swarm Optimization Approach for Cost-Based Feature Selection in Classification.

Science.gov (United States)

Zhang, Yong; Gong, Dun-Wei; Cheng, Jian

2017-01-01

Feature selection is an important data-preprocessing technique in classification problems such as bioinformatics and signal processing. Generally, there are some situations where a user is interested in not only maximizing the classification performance but also minimizing the cost that may be associated with features. This kind of problem is called cost-based feature selection. However, most existing feature selection approaches treat this task as a single-objective optimization problem. This paper presents the first study of multi-objective particle swarm optimization (PSO) for cost-based feature selection problems. The task of this paper is to generate a Pareto front of nondominated solutions, that is, feature subsets, to meet different requirements of decision-makers in real-world applications. In order to enhance the search capability of the proposed algorithm, a probability-based encoding technology and an effective hybrid operator, together with the ideas of the crowding distance, the external archive, and the Pareto domination relationship, are applied to PSO. The proposed PSO-based multi-objective feature selection algorithm is compared with several multi-objective feature selection algorithms on five benchmark datasets. Experimental results show that the proposed algorithm can automatically evolve a set of nondominated solutions, and it is a highly competitive feature selection method for solving cost-based feature selection problems.

Modeling and optimization of the single-leg multi-fare class ...

African Journals Online (AJOL)

This paper presents a static overbooking model for a single-leg multi-fare class flight. A realistic distribution of no-show data in modeling the cost function was considered using data collected from the Ethiopian airlines. The overbooking model developed considers the interaction (i.e. the transfer of an extra passenger in a ...

Ensemble support vector machine classification of dementia using structural MRI and mini-mental state examination.

Science.gov (United States)

Sørensen, Lauge; Nielsen, Mads

2018-05-15

The International Challenge for Automated Prediction of MCI from MRI data offered independent, standardized comparison of machine learning algorithms for multi-class classification of normal control (NC), mild cognitive impairment (MCI), converting MCI (cMCI), and Alzheimer's disease (AD) using brain imaging and general cognition. We proposed to use an ensemble of support vector machines (SVMs) that combined bagging without replacement and feature selection. SVM is the most commonly used algorithm in multivariate classification of dementia, and it was therefore valuable to evaluate the potential benefit of ensembling this type of classifier. The ensemble SVM, using either a linear or a radial basis function (RBF) kernel, achieved multi-class classification accuracies of 55.6% and 55.0% in the challenge test set (60 NC, 60 MCI, 60 cMCI, 60 AD), resulting in a third place in the challenge. Similar feature subset sizes were obtained for both kernels, and the most frequently selected MRI features were the volumes of the two hippocampal subregions left presubiculum and right subiculum. Post-challenge analysis revealed that enforcing a minimum number of selected features and increasing the number of ensemble classifiers improved classification accuracy up to 59.1%. The ensemble SVM outperformed single SVM classifications consistently in the challenge test set. Ensemble methods using bagging and feature selection can improve the performance of the commonly applied SVM classifier in dementia classification. This resulted in competitive classification accuracies in the International Challenge for Automated Prediction of MCI from MRI data. Copyright © 2018 Elsevier B.V. All rights reserved.

Automatic classification of endogenous seismic sources within a landslide body using random forest algorithm

Science.gov (United States)

Provost, Floriane; Hibert, Clément; Malet, Jean-Philippe; Stumpf, André; Doubre, Cécile

2016-04-01

Different studies have shown the presence of microseismic activity in soft-rock landslides. The seismic signals exhibit significantly different features in the time and frequency domains which allow their classification and interpretation. Most of the classes could be associated with different mechanisms of deformation occurring within and at the surface (e.g. rockfall, slide-quake, fissure opening, fluid circulation). However, some signals remain not fully understood and some classes contain few examples that prevent any interpretation. To move toward a more complete interpretation of the links between the dynamics of soft-rock landslides and the physical processes controlling their behaviour, a complete catalog of the endogeneous seismicity is needed. We propose a multi-class detection method based on the random forests algorithm to automatically classify the source of seismic signals. Random forests is a supervised machine learning technique that is based on the computation of a large number of decision trees. The multiple decision trees are constructed from training sets including each of the target classes. In the case of seismic signals, these attributes may encompass spectral features but also waveform characteristics, multi-stations observations and other relevant information. The Random Forest classifier is used because it provides state-of-the-art performance when compared with other machine learning techniques (e.g. SVM, Neural Networks) and requires no fine tuning. Furthermore it is relatively fast, robust, easy to parallelize, and inherently suitable for multi-class problems. In this work, we present the first results of the classification method applied to the seismicity recorded at the Super-Sauze landslide between 2013 and 2015. We selected a dozen of seismic signal features that characterize precisely its spectral content (e.g. central frequency, spectrum width, energy in several frequency bands, spectrogram shape, spectrum local and global maxima

Multi-element neutron activation analysis and solution of classification problems using multidimensional statistics

International Nuclear Information System (INIS)

Vaganov, P.A.; Kol'tsov, A.A.; Kulikov, V.D.; Mejer, V.A.

1983-01-01

The multi-element instrumental neutron activation analysis of samples of mountain rocks (sandstones, aleurolites and shales of one of gold deposits) is performed. The spectra of irradiated samples are measured by Ge(Li) detector of the volume of 35 mm 3 . The content of 22 chemical elements is determined in each sample. The results of analysis serve as reliable basis for multi-dimensional statistic information processing, they constitute the basis for the generalized characteristics of rocks which brings about the solution of classification problem for rocks of different deposits

Prognostic factors of non-functioning pancreatic neuroendocrine tumor revisited: The value of WHO 2010 classification.

Science.gov (United States)

Bu, Jiyoung; Youn, Sangmin; Kwon, Wooil; Jang, Kee Taek; Han, Sanghyup; Han, Sunjong; You, Younghun; Heo, Jin Seok; Choi, Seong Ho; Choi, Dong Wook

2018-02-01

Various factors have been reported as prognostic factors of non-functional pancreatic neuroendocrine tumors (NF-pNETs). There remains some controversy as to the factors which might actually serve to successfully prognosticate future manifestation and diagnosis of NF-pNETs. As well, consensus regarding management strategy has never been achieved. The aim of this study is to further investigate potential prognostic factors using a large single-center cohort to help determine the management strategy of NF-pNETs. During the time period 1995 through 2013, 166 patients with NF-pNETs who underwent surgery in Samsung Medical Center were entered in a prospective database, and those factors thought to represent predictors of prognosis were tested in uni- and multivariate models. The median follow-up time was 46.5 months; there was a maximum follow-up period of 217 months. The five-year overall survival and disease-free survival rates were 88.5% and 77.0%, respectively. The 2010 WHO classification was found to be the only prognostic factor which affects overall survival and disease-free survival in multivariate analysis. Also, pathologic tumor size and preoperative image tumor size correlated strongly with the WHO grades ( p <0.001, and p <0.001). Our study demonstrates that 2010 WHO classification represents a valuable prognostic factor of NF-pNETs and tumor size on preoperative image correlated with WHO grade. In view of the foregoing, the preoperative image size is thought to represent a reasonable reference with regard to determination and development of treatment strategy of NF-pNETs.

Intelligent feature selection techniques for pattern classification of Lamb wave signals

International Nuclear Information System (INIS)

Hinders, Mark K.; Miller, Corey A.

2014-01-01

Lamb wave interaction with flaws is a complex, three-dimensional phenomenon, which often frustrates signal interpretation schemes based on mode arrival time shifts predicted by dispersion curves. As the flaw severity increases, scattering and mode conversion effects will often dominate the time-domain signals, obscuring available information about flaws because multiple modes may arrive on top of each other. Even for idealized flaw geometries the scattering and mode conversion behavior of Lamb waves is very complex. Here, multi-mode Lamb waves in a metal plate are propagated across a rectangular flat-bottom hole in a sequence of pitch-catch measurements corresponding to the double crosshole tomography geometry. The flaw is sequentially deepened, with the Lamb wave measurements repeated at each flaw depth. Lamb wave tomography reconstructions are used to identify which waveforms have interacted with the flaw and thereby carry information about its depth. Multiple features are extracted from each of the Lamb wave signals using wavelets, which are then fed to statistical pattern classification algorithms that identify flaw severity. In order to achieve the highest classification accuracy, an optimal feature space is required but it’s never known a priori which features are going to be best. For structural health monitoring we make use of the fact that physical flaws, such as corrosion, will only increase over time. This allows us to identify feature vectors which are topologically well-behaved by requiring that sequential classes “line up” in feature vector space. An intelligent feature selection routine is illustrated that identifies favorable class distributions in multi-dimensional feature spaces using computational homology theory. Betti numbers and formal classification accuracies are calculated for each feature space subset to establish a correlation between the topology of the class distribution and the corresponding classification accuracy

CONSTRUCTION OF A CALIBRATED PROBABILISTIC CLASSIFICATION CATALOG: APPLICATION TO 50k VARIABLE SOURCES IN THE ALL-SKY AUTOMATED SURVEY

International Nuclear Information System (INIS)

Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.; Bloom, Joshua S.; Brink, Henrik; Crellin-Quick, Arien; Butler, Nathaniel R.

2012-01-01

With growing data volumes from synoptic surveys, astronomers necessarily must become more abstracted from the discovery and introspection processes. Given the scarcity of follow-up resources, there is a particularly sharp onus on the frameworks that replace these human roles to provide accurate and well-calibrated probabilistic classification catalogs. Such catalogs inform the subsequent follow-up, allowing consumers to optimize the selection of specific sources for further study and permitting rigorous treatment of classification purities and efficiencies for population studies. Here, we describe a process to produce a probabilistic classification catalog of variability with machine learning from a multi-epoch photometric survey. In addition to producing accurate classifications, we show how to estimate calibrated class probabilities and motivate the importance of probability calibration. We also introduce a methodology for feature-based anomaly detection, which allows discovery of objects in the survey that do not fit within the predefined class taxonomy. Finally, we apply these methods to sources observed by the All-Sky Automated Survey (ASAS), and release the Machine-learned ASAS Classification Catalog (MACC), a 28 class probabilistic classification catalog of 50,124 ASAS sources in the ASAS Catalog of Variable Stars. We estimate that MACC achieves a sub-20% classification error rate and demonstrate that the class posterior probabilities are reasonably calibrated. MACC classifications compare favorably to the classifications of several previous domain-specific ASAS papers and to the ASAS Catalog of Variable Stars, which had classified only 24% of those sources into one of 12 science classes.

CONSTRUCTION OF A CALIBRATED PROBABILISTIC CLASSIFICATION CATALOG: APPLICATION TO 50k VARIABLE SOURCES IN THE ALL-SKY AUTOMATED SURVEY

Energy Technology Data Exchange (ETDEWEB)

Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.; Bloom, Joshua S.; Brink, Henrik; Crellin-Quick, Arien [Astronomy Department, University of California, Berkeley, CA 94720-3411 (United States); Butler, Nathaniel R., E-mail: jwrichar@stat.berkeley.edu [School of Earth and Space Exploration, Arizona State University, Tempe, AZ 85287 (United States)

2012-12-15

With growing data volumes from synoptic surveys, astronomers necessarily must become more abstracted from the discovery and introspection processes. Given the scarcity of follow-up resources, there is a particularly sharp onus on the frameworks that replace these human roles to provide accurate and well-calibrated probabilistic classification catalogs. Such catalogs inform the subsequent follow-up, allowing consumers to optimize the selection of specific sources for further study and permitting rigorous treatment of classification purities and efficiencies for population studies. Here, we describe a process to produce a probabilistic classification catalog of variability with machine learning from a multi-epoch photometric survey. In addition to producing accurate classifications, we show how to estimate calibrated class probabilities and motivate the importance of probability calibration. We also introduce a methodology for feature-based anomaly detection, which allows discovery of objects in the survey that do not fit within the predefined class taxonomy. Finally, we apply these methods to sources observed by the All-Sky Automated Survey (ASAS), and release the Machine-learned ASAS Classification Catalog (MACC), a 28 class probabilistic classification catalog of 50,124 ASAS sources in the ASAS Catalog of Variable Stars. We estimate that MACC achieves a sub-20% classification error rate and demonstrate that the class posterior probabilities are reasonably calibrated. MACC classifications compare favorably to the classifications of several previous domain-specific ASAS papers and to the ASAS Catalog of Variable Stars, which had classified only 24% of those sources into one of 12 science classes.

Hierarchical multi-scale classification of nearshore aquatic habitats of the Great Lakes: Western Lake Erie

Science.gov (United States)

McKenna, J.E.; Castiglione, C.

2010-01-01

Classification is a valuable conservation tool for examining natural resource status and problems and is being developed for coastal aquatic habitats. We present an objective, multi-scale hydrospatial framework for nearshore areas of the Great Lakes. The hydrospatial framework consists of spatial units at eight hierarchical scales from the North American Continent to the individual 270-m spatial cell. Characterization of spatial units based on fish abundance and diversity provides a fish-guided classification of aquatic areas at each spatial scale and demonstrates how classifications may be generated from that framework. Those classification units then provide information about habitat, as well as biotic conditions, which can be compared, contrasted, and hierarchically related spatially. Examples within several representative coastal or open water zones of the Western Lake Erie pilot area highlight potential application of this classification system to management problems. This classification system can assist natural resource managers with planning and establishing priorities for aquatic habitat protection, developing rehabilitation strategies, or identifying special management actions.

Buffer Management of Multi-Queue QoS Switches with Class Segregation

OpenAIRE

Itoh, Toshiya; Yoshimoto, Seiji

2013-01-01

In this paper, we focus on buffer management of multi-queue QoS switches in which packets of different values are segregated in different queues. Our model consists of $m$ queues and $m$ packet values $0 < v_{1} < v_{2} < ... < v_{m}$. Recently, Al-Bawani and Souza [IPL 113(4), pp.145-150, 2013] presented an online algorithm GREEDY for buffer management of multi-queue QoS switches with class segregation and showed thatif $m$ queues have the same size, then the competitive ratio of GREEDY is $...

Evaluation of classification method of lung lobe for multi-slice CT images

International Nuclear Information System (INIS)

Sakurai, Kousuke; Matsuhiro, Mikio; Saita, Shinsuke

2010-01-01

Recently, due to the introduction of multi-slice CT, to obtain a high resolution 3D CT image is possible in a short time. The temporal and spatial resolutions are high, so a highly accurate 3D image analysis is possible. To develop a structure analysis of the lung is needed and to be used as a fundamental technology for early detection of the disease. By separating the lung into lung lobes may provide important information for analysis, diagnosis and treatment of lung diseases. Therefore in this report, we adapt to abnormality example with the classification algorithms using the anatomical information of the bronchus, the pulmonary vein and interlobar fissure information, we evaluate the classification. (author)

Deep learning based classification of breast tumors with shear-wave elastography.

Science.gov (United States)

Zhang, Qi; Xiao, Yang; Dai, Wei; Suo, Jingfeng; Wang, Congzhi; Shi, Jun; Zheng, Hairong

2016-12-01

This study aims to build a deep learning (DL) architecture for automated extraction of learned-from-data image features from the shear-wave elastography (SWE), and to evaluate the DL architecture in differentiation between benign and malignant breast tumors. We construct a two-layer DL architecture for SWE feature extraction, comprised of the point-wise gated Boltzmann machine (PGBM) and the restricted Boltzmann machine (RBM). The PGBM contains task-relevant and task-irrelevant hidden units, and the task-relevant units are connected to the RBM. Experimental evaluation was performed with five-fold cross validation on a set of 227 SWE images, 135 of benign tumors and 92 of malignant tumors, from 121 patients. The features learned with our DL architecture were compared with the statistical features quantifying image intensity and texture. Results showed that the DL features achieved better classification performance with an accuracy of 93.4%, a sensitivity of 88.6%, a specificity of 97.1%, and an area under the receiver operating characteristic curve of 0.947. The DL-based method integrates feature learning with feature selection on SWE. It may be potentially used in clinical computer-aided diagnosis of breast cancer. Copyright © 2016 Elsevier B.V. All rights reserved.

Classification of malignant and benign liver tumors using a radiomics approach

Science.gov (United States)

Starmans, Martijn P. A.; Miclea, Razvan L.; van der Voort, Sebastian R.; Niessen, Wiro J.; Thomeer, Maarten G.; Klein, Stefan

2018-03-01

Correct diagnosis of the liver tumor phenotype is crucial for treatment planning, especially the distinction between malignant and benign lesions. Clinical practice includes manual scoring of the tumors on Magnetic Resonance (MR) images by a radiologist. As this is challenging and subjective, it is often followed by a biopsy. In this study, we propose a radiomics approach as an objective and non-invasive alternative for distinguishing between malignant and benign phenotypes. T2-weighted (T2w) MR sequences of 119 patients from multiple centers were collected. We developed an efficient semi-automatic segmentation method, which was used by a radiologist to delineate the tumors. Within these regions, features quantifying tumor shape, intensity, texture, heterogeneity and orientation were extracted. Patient characteristics and semantic features were added for a total of 424 features. Classification was performed using Support Vector Machines (SVMs). The performance was evaluated using internal random-split cross-validation. On the training set within each iteration, feature selection and hyperparameter optimization were performed. To this end, another cross validation was performed by splitting the training sets in training and validation parts. The optimal settings were evaluated on the independent test sets. Manual scoring by a radiologist was also performed. The radiomics approach resulted in 95% confidence intervals of the AUC of [0.75, 0.92], specificity [0.76, 0.96] and sensitivity [0.52, 0.82]. These approach the performance of the radiologist, which were an AUC of 0.93, specificity 0.70 and sensitivity 0.93. Hence, radiomics has the potential to predict the liver tumor benignity in an objective and non-invasive manner.

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI

Directory of Open Access Journals (Sweden)

Ling-Li Zeng

2018-04-01

Full Text Available Background: A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. Methods: A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Findings: Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. Interpretation: The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the “disconnectivity” model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Keywords: Schizophrenia, Deep learning, Connectome, f

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI.

Science.gov (United States)

Zeng, Ling-Li; Wang, Huaning; Hu, Panpan; Yang, Bo; Pu, Weidan; Shen, Hui; Chen, Xingui; Liu, Zhening; Yin, Hong; Tan, Qingrong; Wang, Kai; Hu, Dewen

2018-04-01

A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Copyright © 2018 German Center for Neurodegenerative Diseases (DZNE). Published by Elsevier B.V. All rights reserved.

Maximum mutual information regularized classification

KAUST Repository

Wang, Jim Jing-Yan

2014-09-07

In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned classifier, the uncertainty of the true class label of a data sample should be reduced by knowing its classification response as much as possible. The reduced uncertainty is measured by the mutual information between the classification response and the true class label. To this end, when learning a linear classifier, we propose to maximize the mutual information between classification responses and true class labels of training samples, besides minimizing the classification error and reducing the classifier complexity. An objective function is constructed by modeling mutual information with entropy estimation, and it is optimized by a gradient descend method in an iterative algorithm. Experiments on two real world pattern classification problems show the significant improvements achieved by maximum mutual information regularization.

Maximum mutual information regularized classification

KAUST Repository

Wang, Jim Jing-Yan; Wang, Yi; Zhao, Shiguang; Gao, Xin

2014-01-01

In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned classifier, the uncertainty of the true class label of a data sample should be reduced by knowing its classification response as much as possible. The reduced uncertainty is measured by the mutual information between the classification response and the true class label. To this end, when learning a linear classifier, we propose to maximize the mutual information between classification responses and true class labels of training samples, besides minimizing the classification error and reducing the classifier complexity. An objective function is constructed by modeling mutual information with entropy estimation, and it is optimized by a gradient descend method in an iterative algorithm. Experiments on two real world pattern classification problems show the significant improvements achieved by maximum mutual information regularization.

Gene features selection for three-class disease classification via multiple orthogonal partial least square discriminant analysis and S-plot using microarray data.

Science.gov (United States)

Yang, Mingxing; Li, Xiumin; Li, Zhibin; Ou, Zhimin; Liu, Ming; Liu, Suhuan; Li, Xuejun; Yang, Shuyu

2013-01-01

DNA microarray analysis is characterized by obtaining a large number of gene variables from a small number of observations. Cluster analysis is widely used to analyze DNA microarray data to make classification and diagnosis of disease. Because there are so many irrelevant and insignificant genes in a dataset, a feature selection approach must be employed in data analysis. The performance of cluster analysis of this high-throughput data depends on whether the feature selection approach chooses the most relevant genes associated with disease classes. Here we proposed a new method using multiple Orthogonal Partial Least Squares-Discriminant Analysis (mOPLS-DA) models and S-plots to select the most relevant genes to conduct three-class disease classification and prediction. We tested our method using Golub's leukemia microarray data. For three classes with subtypes, we proposed hierarchical orthogonal partial least squares-discriminant analysis (OPLS-DA) models and S-plots to select features for two main classes and their subtypes. For three classes in parallel, we employed three OPLS-DA models and S-plots to choose marker genes for each class. The power of feature selection to classify and predict three-class disease was evaluated using cluster analysis. Further, the general performance of our method was tested using four public datasets and compared with those of four other feature selection methods. The results revealed that our method effectively selected the most relevant features for disease classification and prediction, and its performance was better than that of the other methods.

Predicting Assignment Submissions in a Multiclass Classification Problem

Directory of Open Access Journals (Sweden)

Bogdan Drăgulescu

2015-08-01

Full Text Available Predicting student failure is an important task that can empower educators to counteract the factors that affect student performance. In this paper, a part of the bigger problem of predicting student failure is addressed: predicting the students that do not complete their assignment tasks. For solving this problem, real data collected by our university’s educational platform was used. Because the problem consisted of predicting one of three possible classes (multi-class classification, the appropriate algorithms and methods were selected. Several experiments were carried out to find the best approach for this prediction problem and the used data set. An approach of time segmentation is proposed in order to facilitate the prediction from early on. Methods that address the problems of high dimensionality and imbalanced data were also evaluated. The outcome of each approach is shown and compared in order to select the best performing classification algorithm for the problem at hand.

MetClass: A software for the visualization and exploitation of Dill's (2010) "chessboard" classification of mineral deposits

Science.gov (United States)

Kaabeche, Hamza; Chabou, Moulley Charaf; Bendaoud, Abderrahmane; Bodinier, Jean-Louis; Lobry, Olivier; Retif, Fabien

2016-06-01

Rising economic value of a large number of metals as a result of their importance for new technologies and industrial development has renewed worldwide interest for mineral exploration and detailed studies of ore deposits. The Dill's (2010) "chessboard" classification of mineral deposits is the most recent attempt to provide an exhaustive overview of all mineral deposits known to date. However, the voluminous Dills review paper is accessible only in print or as PDF file. In this article, we present MetClass, software that provides advanced solutions to perform efficient research and statistics using Dill's classification and the related database. MetClass allows to assemble all results relevant to a given ore deposit on a user-friendly interface. This software is therefore a valuable tool for mineral exploration and research on ore deposits, as well as an educational solution for students in metallogeny.

Checking the Course of Colorectal Carcinoma Follow up Using Mathematical Classification of Tumor Marker Profiles

Czech Academy of Sciences Publication Activity Database

Holubec jr., L.; Botterlich, N.; Topolčan, O.; Finek, J.; Pikner, R.; Pecen, Ladislav; Holubec, L.

2002-01-01

Roč. 23, Suppl.1 (2002), s. 57 ISSN 1010-4283. [Meeting of the International Society for Oncodevelopmental Biology and Medicine /30./. 08.09.2002-12.09.2002, Boston] R&D Projects: GA MŠk ME 438 Institutional research plan: AV0Z1030915 Keywords : tumor markers * colorectal CA * mathematical classification Subject RIV: BA - General Mathematics

BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

Directory of Open Access Journals (Sweden)

F. Pirotti

2016-06-01

Full Text Available Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels for testing and validating subsets. The classes used are the following: (i urban (ii sowable areas (iii water (iv tree plantations (v grasslands. Validation is carried out using three different approaches: (i using pixels from the training dataset (train, (ii using pixels from the training dataset and applying cross-validation with the k-fold method (kfold and (iii using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train, the whole control dataset (full and with k-fold cross-validation (kfold with ten folds. Results from validation of predictions of the whole dataset (full show the

Segmentation and object-oriented classification of wetlands in a karst Florida landscape using multi-season Landsat-7 ETM+ Imagery

Science.gov (United States)

Segmentation and object-oriented processing of single-season and multi-season Landsat-7 ETM+ data was utilized for the classification of wetlands in a 1560 km2 study area of north central Florida. This segmentation and object-oriented classification outperformed the traditional ...

Sub-Volumetric Classification and Visualization of Emphysema Using a Multi-Threshold Method and Neural Network

Science.gov (United States)

Tan, Kok Liang; Tanaka, Toshiyuki; Nakamura, Hidetoshi; Shirahata, Toru; Sugiura, Hiroaki

Chronic Obstructive Pulmonary Disease is a disease in which the airways and tiny air sacs (alveoli) inside the lung are partially obstructed or destroyed. Emphysema is what occurs as more and more of the walls between air sacs get destroyed. The goal of this paper is to produce a more practical emphysema-quantification algorithm that has higher correlation with the parameters of pulmonary function tests compared to classical methods. The use of the threshold range from approximately -900 Hounsfield Unit to -990 Hounsfield Unit for extracting emphysema from CT has been reported in many papers. From our experiments, we realize that a threshold which is optimal for a particular CT data set might not be optimal for other CT data sets due to the subtle radiographic variations in the CT images. Consequently, we propose a multi-threshold method that utilizes ten thresholds between and including -900 Hounsfield Unit and -990 Hounsfield Unit for identifying the different potential emphysematous regions in the lung. Subsequently, we divide the lung into eight sub-volumes. From each sub-volume, we calculate the ratio of the voxels with the intensity below a certain threshold. The respective ratios of the voxels below the ten thresholds are employed as the features for classifying the sub-volumes into four emphysema severity classes. Neural network is used as the classifier. The neural network is trained using 80 training sub-volumes. The performance of the classifier is assessed by classifying 248 test sub-volumes of the lung obtained from 31 subjects. Actual diagnoses of the sub-volumes are hand-annotated and consensus-classified by radiologists. The four-class classification accuracy of the proposed method is 89.82%. The sub-volumetric classification results produced in this study encompass not only the information of emphysema severity but also the distribution of emphysema severity from the top to the bottom of the lung. We hypothesize that besides emphysema severity, the

Multi-slice spiral CT detects spread of small laryngeal tumors

International Nuclear Information System (INIS)

Bruening, R.; Schoepf, U.; Becker, C.; Reiser, M.; Hong, C.; Sturm, C.; Wollenberg, B.

1999-01-01

The purpose of the study was to preoperatively investigate small laryngeal carcinomas using multi-slice spiral CT (MSCT) and subsequent multiplanar reconstructions (MPR) and to compare the results to the detailed spread found a surgery and histology. Nine patients with small (T1, T2) laryngeal cancer were investigated on a MSCT scanner (Siemens plus 4 Volume Zoom, Siemens). A 4x1 mm collimation, 120 kV, 200 mAs and a 0.5 seconds rotation time were used, allowing a coverage of the entire larynx in approximately 10 seconds within a single breathhold. Multiplanar reconstruction's (MPR) in sagittal and coronal plane were reconstructed in all patients and rated in consensus reading. In 8 of nine patients, the glottic spread was detected by MSCT, in one case of a supraglottic tumor a glottic invasion was excluded. The infiltration of the anterior commissure, the infiltration into the subglottic space and the extension into the hypo-pharynx was correctly assessed in all patients. MSCT was not able to predict infiltration of the arythnoids in two patients. The use of multi-slice CT for the preoperative assessment of small laryngeal tumors shows great promise. The detection or exclusion of subtle spread of these tumors into the supra- or subglottic space and along the glottic level was possible with high accuracy. As the examination time is short, artifacts are rare and multiplanar reconstructions gain in clinical importance. (orig.) [de

Lipofection indirectly increases expression of endogenous major histocompatibility complex class I molecules on tumor cells.

Science.gov (United States)

Fox, B A; Drury, M; Hu, H M; Cao, Z; Huntzicker, E G; Qie, W; Urba, W J

1998-01-01

Direct intratumoral injection of a lipid/DNA complex encoding an allogeneic major histocompatibility complex (MHC) class I molecule leads to regression of both an immunogenic murine tumor and also melanoma lesions in some patients. We have sought to understand the mechanism(s) for this augmentation of antitumor activity. While optimizing parameters for in vitro gene transfer into the D5 subclone of B16BL6, it was noted that lipofected tumors not only expressed the new alloantigen but also exhibited increased expression of endogenous MHC class I, both H-2 Kb and H-2 Db. This increase in expression was not restricted to the small percentage of cells that expressed the transfected gene, but appeared to affect the majority of cells in culture. Class I expression was not increased by lipopolysaccharide, DNA alone, lipid, or lipid/lipopolysaccharide mixtures. Enhanced class I expression required a DNA/lipid complex and was greatest when parameters optimized for gene transfer of the alloantigen were used. All DNA plasmids tested had this effect, including one plasmid whose DNA was not transcribed because it lacked an expression cassette. Because of the critical role that MHC class I antigens play in immune recognition, we propose that lipid complex-mediated gene transfer may provide immunological advantages beyond those that are attributable to expression of the specific gene transferred.

Modified Angle's Classification for Primary Dentition.

Science.gov (United States)

Chandranee, Kaushik Narendra; Chandranee, Narendra Jayantilal; Nagpal, Devendra; Lamba, Gagandeep; Choudhari, Purva; Hotwani, Kavita

2017-01-01

This study aims to propose a modification of Angle's classification for primary dentition and to assess its applicability in children from Central India, Nagpur. Modification in Angle's classification has been proposed for application in primary dentition. Small roman numbers i/ii/iii are used for primary dentition notation to represent Angle's Class I/II/III molar relationships as in permanent dentition, respectively. To assess applicability of modified Angle's classification a cross-sectional preschool 2000 children population from central India; 3-6 years of age residing in Nagpur metropolitan city of Maharashtra state were selected randomly as per the inclusion and exclusion criteria. Majority 93.35% children were found to have bilateral Class i followed by 2.5% bilateral Class ii and 0.2% bilateral half cusp Class iii molar relationships as per the modified Angle's classification for primary dentition. About 3.75% children had various combinations of Class ii relationships and 0.2% children were having Class iii subdivision relationship. Modification of Angle's classification for application in primary dentition has been proposed. A cross-sectional investigation using new classification revealed various 6.25% Class ii and 0.4% Class iii molar relationships cases in preschool children population in a metropolitan city of Nagpur. Application of the modified Angle's classification to other population groups is warranted to validate its routine application in clinical pediatric dentistry.

Advances in the Genetic Characterization of Cutaneous Mesenchymal Neoplasms: Implications for Tumor Classification and Novel Diagnostic Markers.

Science.gov (United States)

Compton, Leigh A; Doyle, Leona A

2017-06-01

Cutaneous mesenchymal neoplasms often pose significant diagnostic challenges; many such entities are rare or show clinical and histologic overlap with both other mesenchymal and non-mesenchymal lesions. Recent advances in the genetic classification of many cutaneous mesenchymal neoplasms have not only helped define unique pathologic entities and increase our understanding of their biology, but have also provided new diagnostic markers. This review details these recent discoveries, with a focus on their implications for tumor classification and diagnosis. Copyright © 2017 Elsevier Inc. All rights reserved.

Prediction and classification of respiratory motion

CERN Document Server

Lee, Suk Jin

2014-01-01

This book describes recent radiotherapy technologies including tools for measuring target position during radiotherapy and tracking-based delivery systems. This book presents a customized prediction of respiratory motion with clustering from multiple patient interactions. The proposed method contributes to the improvement of patient treatments by considering breathing pattern for the accurate dose calculation in radiotherapy systems. Real-time tumor-tracking, where the prediction of irregularities becomes relevant, has yet to be clinically established. The statistical quantitative modeling for irregular breathing classification, in which commercial respiration traces are retrospectively categorized into several classes based on breathing pattern are discussed as well. The proposed statistical classification may provide clinical advantages to adjust the dose rate before and during the external beam radiotherapy for minimizing the safety margin. In the first chapter following the Introduction  to this book, we...

Classification of protein fold classes by knot theory and prediction of folds by neural networks: A combined theoretical and experimental approach

DEFF Research Database (Denmark)

Ramnarayan, K.; Bohr, Henrik; Jalkanen, Karl J.

2008-01-01

We present different means of classifying protein structure. One is made rigorous by mathematical knot invariants that coincide reasonably well with ordinary graphical fold classification and another classification is by packing analysis. Furthermore when constructing our mathematical fold...... classifications, we utilize standard neural network methods for predicting protein fold classes from amino acid sequences. We also make an analysis of the redundancy of the structural classifications in relation to function and ligand binding. Finally we advocate the use of combining the measurement of the VA...

Piaget's Geographical Spatial Stages: An Examination of Their Relationship to Elementary Children's Classification-Class Inclusion Abilities.

Science.gov (United States)

Rand, David C.; Towler, John O.

This study examines the relationship between a child's concept of geographic and territorial relationships and his competence on classification and class inclusion measures. Jean Piaget's stages of development and studies conducted by other investigators (Jahoda, 1964; Stoltman, 1971; Rand and Towler, 1973; Flavell, 1963; Asher, et al, 1971;…

Sparse Detector Imaging Sensor with Two-Class Silhouette Classification

Directory of Open Access Journals (Sweden)

David Russomanno

2008-12-01

Full Text Available This paper presents the design and test of a simple active near-infrared sparse detector imaging sensor. The prototype of the sensor is novel in that it can capture remarkable silhouettes or profiles of a wide-variety of moving objects, including humans, animals, and vehicles using a sparse detector array comprised of only sixteen sensing elements deployed in a vertical configuration. The prototype sensor was built to collect silhouettes for a variety of objects and to evaluate several algorithms for classifying the data obtained from the sensor into two classes: human versus non-human. Initial tests show that the classification of individually sensed objects into two classes can be achieved with accuracy greater than ninety-nine percent (99% with a subset of the sixteen detectors using a representative dataset consisting of 512 signatures. The prototype also includes a Webservice interface such that the sensor can be tasked in a network-centric environment. The sensor appears to be a low-cost alternative to traditional, high-resolution focal plane array imaging sensors for some applications. After a power optimization study, appropriate packaging, and testing with more extensive datasets, the sensor may be a good candidate for deployment in vast geographic regions for a myriad of intelligent electronic fence and persistent surveillance applications, including perimeter security scenarios.

Predicting respiratory tumor motion with multi-dimensional adaptive filters and support vector regression

International Nuclear Information System (INIS)

Riaz, Nadeem; Wiersma, Rodney; Mao Weihua; Xing Lei; Shanker, Piyush; Gudmundsson, Olafur; Widrow, Bernard

2009-01-01

Intra-fraction tumor tracking methods can improve radiation delivery during radiotherapy sessions. Image acquisition for tumor tracking and subsequent adjustment of the treatment beam with gating or beam tracking introduces time latency and necessitates predicting the future position of the tumor. This study evaluates the use of multi-dimensional linear adaptive filters and support vector regression to predict the motion of lung tumors tracked at 30 Hz. We expand on the prior work of other groups who have looked at adaptive filters by using a general framework of a multiple-input single-output (MISO) adaptive system that uses multiple correlated signals to predict the motion of a tumor. We compare the performance of these two novel methods to conventional methods like linear regression and single-input, single-output adaptive filters. At 400 ms latency the average root-mean-square-errors (RMSEs) for the 14 treatment sessions studied using no prediction, linear regression, single-output adaptive filter, MISO and support vector regression are 2.58, 1.60, 1.58, 1.71 and 1.26 mm, respectively. At 1 s, the RMSEs are 4.40, 2.61, 3.34, 2.66 and 1.93 mm, respectively. We find that support vector regression most accurately predicts the future tumor position of the methods studied and can provide a RMSE of less than 2 mm at 1 s latency. Also, a multi-dimensional adaptive filter framework provides improved performance over single-dimension adaptive filters. Work is underway to combine these two frameworks to improve performance.

Emergent Stratification in Solid Tumors Selects for Reduced Cohesion of Tumor Cells: A Multi-Cell, Virtual-Tissue Model of Tumor Evolution Using CompuCell3D.

Directory of Open Access Journals (Sweden)

Maciej H Swat

Full Text Available Tumor cells and structure both evolve due to heritable variation of cell behaviors and selection over periods of weeks to years (somatic evolution. Micro-environmental factors exert selection pressures on tumor-cell behaviors, which influence both the rate and direction of evolution of specific behaviors, especially the development of tumor-cell aggression and resistance to chemotherapies. In this paper, we present, step-by-step, the development of a multi-cell, virtual-tissue model of tumor somatic evolution, simulated using the open-source CompuCell3D modeling environment. Our model includes essential cell behaviors, microenvironmental components and their interactions. Our model provides a platform for exploring selection pressures leading to the evolution of tumor-cell aggression, showing that emergent stratification into regions with different cell survival rates drives the evolution of less cohesive cells with lower levels of cadherins and higher levels of integrins. Such reduced cohesivity is a key hallmark in the progression of many types of solid tumors.

The edge-preservation multi-classifier relearning framework for the classification of high-resolution remotely sensed imagery

Science.gov (United States)

Han, Xiaopeng; Huang, Xin; Li, Jiayi; Li, Yansheng; Yang, Michael Ying; Gong, Jianya

2018-04-01

In recent years, the availability of high-resolution imagery has enabled more detailed observation of the Earth. However, it is imperative to simultaneously achieve accurate interpretation and preserve the spatial details for the classification of such high-resolution data. To this aim, we propose the edge-preservation multi-classifier relearning framework (EMRF). This multi-classifier framework is made up of support vector machine (SVM), random forest (RF), and sparse multinomial logistic regression via variable splitting and augmented Lagrangian (LORSAL) classifiers, considering their complementary characteristics. To better characterize complex scenes of remote sensing images, relearning based on landscape metrics is proposed, which iteratively quantizes both the landscape composition and spatial configuration by the use of the initial classification results. In addition, a novel tri-training strategy is proposed to solve the over-smoothing effect of relearning by means of automatic selection of training samples with low classification certainties, which always distribute in or near the edge areas. Finally, EMRF flexibly combines the strengths of relearning and tri-training via the classification certainties calculated by the probabilistic output of the respective classifiers. It should be noted that, in order to achieve an unbiased evaluation, we assessed the classification accuracy of the proposed framework using both edge and non-edge test samples. The experimental results obtained with four multispectral high-resolution images confirm the efficacy of the proposed framework, in terms of both edge and non-edge accuracy.

Classification of Focal and Non Focal Epileptic Seizures Using Multi-Features and SVM Classifier.

Science.gov (United States)

Sriraam, N; Raghu, S

2017-09-02

Identifying epileptogenic zones prior to surgery is an essential and crucial step in treating patients having pharmacoresistant focal epilepsy. Electroencephalogram (EEG) is a significant measurement benchmark to assess patients suffering from epilepsy. This paper investigates the application of multi-features derived from different domains to recognize the focal and non focal epileptic seizures obtained from pharmacoresistant focal epilepsy patients from Bern Barcelona database. From the dataset, five different classification tasks were formed. Total 26 features were extracted from focal and non focal EEG. Significant features were selected using Wilcoxon rank sum test by setting p-value (p z > 1.96) at 95% significance interval. Hypothesis was made that the effect of removing outliers improves the classification accuracy. Turkey's range test was adopted for pruning outliers from feature set. Finally, 21 features were classified using optimized support vector machine (SVM) classifier with 10-fold cross validation. Bayesian optimization technique was adopted to minimize the cross-validation loss. From the simulation results, it was inferred that the highest sensitivity, specificity, and classification accuracy of 94.56%, 89.74%, and 92.15% achieved respectively and found to be better than the state-of-the-art approaches. Further, it was observed that the classification accuracy improved from 80.2% with outliers to 92.15% without outliers. The classifier performance metrics ensures the suitability of the proposed multi-features with optimized SVM classifier. It can be concluded that the proposed approach can be applied for recognition of focal EEG signals to localize epileptogenic zones.

Crop classification based on multi-temporal satellite remote sensing data for agro-advisory services

Science.gov (United States)

Karale, Yogita; Mohite, Jayant; Jagyasi, Bhushan

2014-11-01

In this paper, we envision the use of satellite images coupled with GIS to obtain location specific crop type information in order to disseminate crop specific advises to the farmers. In our ongoing mKRISHI R project, the accurate information about the field level crop type and acreage will help in the agro-advisory services and supply chain planning and management. The key contribution of this paper is the field level crop classification using multi temporal images of Landsat-8 acquired during November 2013 to April 2014. The study area chosen is Vani, Maharashtra, India, from where the field level ground truth information for various crops such as grape, wheat, onion, soybean, tomato, along with fodder and fallow fields has been collected using the mobile application. The ground truth information includes crop type, crop stage and GPS location for 104 farms in the study area with approximate area of 42 hectares. The seven multi-temporal images of the Landsat-8 were used to compute the vegetation indices namely: Normalized Difference Vegetation Index (NDVI), Simple Ratio (SR) and Difference Vegetation Index (DVI) for the study area. The vegetation indices values of the pixels within a field were then averaged to obtain the field level vegetation indices. For each crop, binary classification has been carried out using the feed forward neural network operating on the field level vegetation indices. The classification accuracy for the individual crop was in the range of 74.5% to 97.5% and the overall classification accuracy was found to be 88.49%.

Multi-National Banknote Classification Based on Visible-light Line Sensor and Convolutional Neural Network.

Science.gov (United States)

Pham, Tuyen Danh; Lee, Dong Eun; Park, Kang Ryoung

2017-07-08

Automatic recognition of banknotes is applied in payment facilities, such as automated teller machines (ATMs) and banknote counters. Besides the popular approaches that focus on studying the methods applied to various individual types of currencies, there have been studies conducted on simultaneous classification of banknotes from multiple countries. However, their methods were conducted with limited numbers of banknote images, national currencies, and denominations. To address this issue, we propose a multi-national banknote classification method based on visible-light banknote images captured by a one-dimensional line sensor and classified by a convolutional neural network (CNN) considering the size information of each denomination. Experiments conducted on the combined banknote image database of six countries with 62 denominations gave a classification accuracy of 100%, and results show that our proposed algorithm outperforms previous methods.

Modified angle's classification for primary dentition

Directory of Open Access Journals (Sweden)

Kaushik Narendra Chandranee

2017-01-01

Full Text Available Aim: This study aims to propose a modification of Angle's classification for primary dentition and to assess its applicability in children from Central India, Nagpur. Methods: Modification in Angle's classification has been proposed for application in primary dentition. Small roman numbers i/ii/iii are used for primary dentition notation to represent Angle's Class I/II/III molar relationships as in permanent dentition, respectively. To assess applicability of modified Angle's classification a cross-sectional preschool 2000 children population from central India; 3–6 years of age residing in Nagpur metropolitan city of Maharashtra state were selected randomly as per the inclusion and exclusion criteria. Results: Majority 93.35% children were found to have bilateral Class i followed by 2.5% bilateral Class ii and 0.2% bilateral half cusp Class iii molar relationships as per the modified Angle's classification for primary dentition. About 3.75% children had various combinations of Class ii relationships and 0.2% children were having Class iii subdivision relationship. Conclusions: Modification of Angle's classification for application in primary dentition has been proposed. A cross-sectional investigation using new classification revealed various 6.25% Class ii and 0.4% Class iii molar relationships cases in preschool children population in a metropolitan city of Nagpur. Application of the modified Angle's classification to other population groups is warranted to validate its routine application in clinical pediatric dentistry.

Existence and convergence theorems for a class of multi-valued variational inclusions in Banach spaces

International Nuclear Information System (INIS)

Chidume, C.E.; Zegeye, H.; Kazmi, K.R.

2002-07-01

An existence theorem for a new class of multi-valued variational inclusion problems is established in smooth Banach spaces. Further, it is shown that a sequence of a Mann-type iteration algorithm is strongly convergent to the solutions in this class of variational inclusion problems. (author)

CLAss-Specific Subspace Kernel Representations and Adaptive Margin Slack Minimization for Large Scale Classification.

Science.gov (United States)

Yu, Yinan; Diamantaras, Konstantinos I; McKelvey, Tomas; Kung, Sun-Yuan

2018-02-01

In kernel-based classification models, given limited computational power and storage capacity, operations over the full kernel matrix becomes prohibitive. In this paper, we propose a new supervised learning framework using kernel models for sequential data processing. The framework is based on two components that both aim at enhancing the classification capability with a subset selection scheme. The first part is a subspace projection technique in the reproducing kernel Hilbert space using a CLAss-specific Subspace Kernel representation for kernel approximation. In the second part, we propose a novel structural risk minimization algorithm called the adaptive margin slack minimization to iteratively improve the classification accuracy by an adaptive data selection. We motivate each part separately, and then integrate them into learning frameworks for large scale data. We propose two such frameworks: the memory efficient sequential processing for sequential data processing and the parallelized sequential processing for distributed computing with sequential data acquisition. We test our methods on several benchmark data sets and compared with the state-of-the-art techniques to verify the validity of the proposed techniques.

A NEW SAR CLASSIFICATION SCHEME FOR SEDIMENTS ON INTERTIDAL FLATS BASED ON MULTI-FREQUENCY POLARIMETRIC SAR IMAGERY

Directory of Open Access Journals (Sweden)

W. Wang

2017-11-01

Full Text Available We present a new classification scheme for muddy and sandy sediments on exposed intertidal flats, which is based on synthetic aperture radar (SAR data, and use ALOS-2 (L-band, Radarsat-2 (C-band and TerraSAR-X (X-band fully polarimetric SAR imagery to demonstrate its effectiveness. Four test sites on the German North Sea coast were chosen, which represent typical surface compositions of different sediments, vegetation, and habitats, and of which a large amount of SAR is used for our analyses. Both Freeman-Durden and Cloude-Pottier polarimetric decomposition are utilized, and an additional descriptor called Double-Bounce Eigenvalue Relative Difference (DERD is introduced into the feature sets instead of the original polarimetric intensity channels. The classification is conducted following Random Forest theory, and the results are verified using ground truth data from field campaigns and an existing classification based on optical imagery. In addition, the use of Kennaugh elements for classification purposes is demonstrated using both fully and dual-polarization multi-frequency and multi-temporal SAR data. Our results show that the proposed classification scheme can be applied for the discrimination of muddy and sandy sediments using L-, C-, and X-band SAR images, while SAR imagery acquired at short wavelengths (C- and X-band can also be used to detect more detailed features such as bivalve beds on intertidal flats.

Geospatial Method for Computing Supplemental Multi-Decadal U.S. Coastal Land-Use and Land-Cover Classification Products, Using Landsat Data and C-CAP Products

Science.gov (United States)

Spruce, J. P.; Smoot, James; Ellis, Jean; Hilbert, Kent; Swann, Roberta

2012-01-01

This paper discusses the development and implementation of a geospatial data processing method and multi-decadal Landsat time series for computing general coastal U.S. land-use and land-cover (LULC) classifications and change products consisting of seven classes (water, barren, upland herbaceous, non-woody wetland, woody upland, woody wetland, and urban). Use of this approach extends the observational period of the NOAA-generated Coastal Change and Analysis Program (C-CAP) products by almost two decades, assuming the availability of one cloud free Landsat scene from any season for each targeted year. The Mobile Bay region in Alabama was used as a study area to develop, demonstrate, and validate the method that was applied to derive LULC products for nine dates at approximate five year intervals across a 34-year time span, using single dates of data for each classification in which forests were either leaf-on, leaf-off, or mixed senescent conditions. Classifications were computed and refined using decision rules in conjunction with unsupervised classification of Landsat data and C-CAP value-added products. Each classification's overall accuracy was assessed by comparing stratified random locations to available reference data, including higher spatial resolution satellite and aerial imagery, field survey data, and raw Landsat RGBs. Overall classification accuracies ranged from 83 to 91% with overall Kappa statistics ranging from 0.78 to 0.89. The accuracies are comparable to those from similar, generalized LULC products derived from C-CAP data. The Landsat MSS-based LULC product accuracies are similar to those from Landsat TM or ETM+ data. Accurate classifications were computed for all nine dates, yielding effective results regardless of season. This classification method yielded products that were used to compute LULC change products via additive GIS overlay techniques.

A New Classification Approach Based on Multiple Classification Rules

OpenAIRE

Zhongmei Zhou

2014-01-01

A good classifier can correctly predict new data for which the class label is unknown, so it is important to construct a high accuracy classifier. Hence, classification techniques are much useful in ubiquitous computing. Associative classification achieves higher classification accuracy than some traditional rule-based classification approaches. However, the approach also has two major deficiencies. First, it generates a very large number of association classification rules, especially when t...

Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction.

Science.gov (United States)

Faust, Kevin; Xie, Quin; Han, Dominick; Goyle, Kartikay; Volynskaya, Zoya; Djuric, Ugljesa; Diamandis, Phedias

2018-05-16

There is growing interest in utilizing artificial intelligence, and particularly deep learning, for computer vision in histopathology. While accumulating studies highlight expert-level performance of convolutional neural networks (CNNs) on focused classification tasks, most studies rely on probability distribution scores with empirically defined cutoff values based on post-hoc analysis. More generalizable tools that allow humans to visualize histology-based deep learning inferences and decision making are scarce. Here, we leverage t-distributed Stochastic Neighbor Embedding (t-SNE) to reduce dimensionality and depict how CNNs organize histomorphologic information. Unique to our workflow, we develop a quantitative and transparent approach to visualizing classification decisions prior to softmax compression. By discretizing the relationships between classes on the t-SNE plot, we show we can super-impose randomly sampled regions of test images and use their distribution to render statistically-driven classifications. Therefore, in addition to providing intuitive outputs for human review, this visual approach can carry out automated and objective multi-class classifications similar to more traditional and less-transparent categorical probability distribution scores. Importantly, this novel classification approach is driven by a priori statistically defined cutoffs. It therefore serves as a generalizable classification and anomaly detection tool less reliant on post-hoc tuning. Routine incorporation of this convenient approach for quantitative visualization and error reduction in histopathology aims to accelerate early adoption of CNNs into generalized real-world applications where unanticipated and previously untrained classes are often encountered.

An ensemble classification approach for improved Land use/cover change detection

Science.gov (United States)

Chellasamy, M.; Ferré, T. P. A.; Humlekrog Greve, M.; Larsen, R.; Chinnasamy, U.

2014-11-01

Change Detection (CD) methods based on post-classification comparison approaches are claimed to provide potentially reliable results. They are considered to be most obvious quantitative method in the analysis of Land Use Land Cover (LULC) changes which provides from - to change information. But, the performance of post-classification comparison approaches highly depends on the accuracy of classification of individual images used for comparison. Hence, we present a classification approach that produce accurate classified results which aids to obtain improved change detection results. Machine learning is a part of broader framework in change detection, where neural networks have drawn much attention. Neural network algorithms adaptively estimate continuous functions from input data without mathematical representation of output dependence on input. A common practice for classification is to use Multi-Layer-Perceptron (MLP) neural network with backpropogation learning algorithm for prediction. To increase the ability of learning and prediction, multiple inputs (spectral, texture, topography, and multi-temporal information) are generally stacked to incorporate diversity of information. On the other hand literatures claims backpropagation algorithm to exhibit weak and unstable learning in use of multiple inputs, while dealing with complex datasets characterized by mixed uncertainty levels. To address the problem of learning complex information, we propose an ensemble classification technique that incorporates multiple inputs for classification unlike traditional stacking of multiple input data. In this paper, we present an Endorsement Theory based ensemble classification that integrates multiple information, in terms of prediction probabilities, to produce final classification results. Three different input datasets are used in this study: spectral, texture and indices, from SPOT-4 multispectral imagery captured on 1998 and 2003. Each SPOT image is classified

Fuzzy One-Class Classification Model Using Contamination Neighborhoods

Directory of Open Access Journals (Sweden)

Lev V. Utkin

2012-01-01

Full Text Available A fuzzy classification model is studied in the paper. It is based on the contaminated (robust model which produces fuzzy expected risk measures characterizing classification errors. Optimal classification parameters of the models are derived by minimizing the fuzzy expected risk. It is shown that an algorithm for computing the classification parameters is reduced to a set of standard support vector machine tasks with weighted data points. Experimental results with synthetic data illustrate the proposed fuzzy model.

Codon 61 mutations in the c-Harvey-ras gene in mouse skin tumors induced by 7,12-dimethylbenz[a]anthracene plus okadaic acid class tumor promoters.

Science.gov (United States)

Fujiki, H; Suganuma, M; Yoshizawa, S; Kanazawa, H; Sugimura, T; Manam, S; Kahn, S M; Jiang, W; Hoshina, S; Weinstein, I B

1989-01-01

Three okadaic acid class tumor promoters, okadaic acid, dinophysistoxin-1, and calyculin A, have potent tumor-promoting activity in two-stage carcinogenesis experiments on mouse skin. DNA isolated from tumors induced by 7,12-dimethylbenz[a]anthracene (DMBA) and each of these tumor promoters revealed the same mutation at the second nucleotide of codon 61 (CAA----CTA) in the c-Ha-ras gene, determined by the polymerase chain reaction procedure and DNA sequencing. Three potent 12-O-tetradecanoylphorbol-13-acetate (TPA)-type tumor promoters, TPA, teleocidin, and aplysiatoxin, showed the same effects. These results provide strong evidence that this mutation in the c-Ha-ras gene is due to a direct effect of DMBA rather than a selective effect of specific tumor promoters.

HPSLPred: An Ensemble Multi-Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source.

Science.gov (United States)

Wan, Shixiang; Duan, Yucong; Zou, Quan

2017-09-01

Predicting the subcellular localization of proteins is an important and challenging problem. Traditional experimental approaches are often expensive and time-consuming. Consequently, a growing number of research efforts employ a series of machine learning approaches to predict the subcellular location of proteins. There are two main challenges among the state-of-the-art prediction methods. First, most of the existing techniques are designed to deal with multi-class rather than multi-label classification, which ignores connections between multiple labels. In reality, multiple locations of particular proteins imply that there are vital and unique biological significances that deserve special focus and cannot be ignored. Second, techniques for handling imbalanced data in multi-label classification problems are necessary, but never employed. For solving these two issues, we have developed an ensemble multi-label classifier called HPSLPred, which can be applied for multi-label classification with an imbalanced protein source. For convenience, a user-friendly webserver has been established at http://server.malab.cn/HPSLPred. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Dermal and inhalation acute toxic class methods: test procedures and biometric evaluations for the Globally Harmonized Classification System.

Science.gov (United States)

Holzhütter, H G; Genschow, E; Diener, W; Schlede, E

2003-05-01

The acute toxic class (ATC) methods were developed for determining LD(50)/LC(50) estimates of chemical substances with significantly fewer animals than needed when applying conventional LD(50)/LC(50) tests. The ATC methods are sequential stepwise procedures with fixed starting doses/concentrations and a maximum of six animals used per dose/concentration. The numbers of dead/moribund animals determine whether further testing is necessary or whether the test is terminated. In recent years we have developed classification procedures for the oral, dermal and inhalation routes of administration by using biometric methods. The biometric approach assumes a probit model for the mortality probability of a single animal and assigns the chemical to that toxicity class for which the best concordance is achieved between the statistically expected and the observed numbers of dead/moribund animals at the various steps of the test procedure. In previous publications we have demonstrated the validity of the biometric ATC methods on the basis of data obtained for the oral ATC method in two-animal ring studies with 15 participants from six countries. Although the test procedures and biometric evaluations for the dermal and inhalation ATC methods have already been published, there was a need for an adaptation of the classification schemes to the starting doses/concentrations of the Globally Harmonized Classification System (GHS) recently adopted by the Organization for Economic Co-operation and Development (OECD). Here we present the biometric evaluation of the dermal and inhalation ATC methods for the starting doses/concentrations of the GHS and of some other international classification systems still in use. We have developed new test procedures and decision rules for the dermal and inhalation ATC methods, which require significantly fewer animals to provide predictions of toxicity classes, that are equally good or even better than those achieved by using the conventional LD(50)/LC

Multiple-animal MR imaging using a 3T clinical scanner and multi-channel coil for volumetric analysis in a mouse tumor model

International Nuclear Information System (INIS)

Mitsuda, Minoru; Yamaguchi, Masayuki; Furuta, Toshihiro; Fujii, Hirofumi; Nabetani, Akira; Hirayama, Akira; Nozaki, Atsushi; Niitsu, Mamoru

2011-01-01

Multiple small-animal magnetic resonance (MR) imaging to measure tumor volume may increase the throughput of preclinical cancer research assessing tumor response to novel therapies. We used a clinical scanner and multi-channel coil to evaluate the usefulness of this imaging to assess experimental tumor volume in mice. We performed a phantom study to assess 2-dimensional (2D) geometric distortion using 9-cm spherical and 32-cell (8 x 4 one-cm 2 grids) phantoms using a 3-tesla clinical MR scanner and dedicated multi-channel coil composed of 16 5-cm circular coils. Employing the multi-channel coil, we simultaneously scanned 6 or 8 mice bearing sarcoma 180 tumors. We estimated tumor volume from the sum of the product of tumor area and slice thickness on 2D spin-echo images (repetition time/echo time, 3500/16 ms; in-plane resolution, 0.195 x 0.195 x 1 mm 3 ). After MR acquisition, we excised and weighed tumors, calculated reference tumor volumes from actual tumor weight assuming a density of 1.05 g/cm 3 , and assessed the correlation between the estimated and reference volumes using Pearson's test. Two-dimensional geometric distortion was acceptable below 5% in the 9-cm spherical phantom and in every cell in the 32-cell phantom. We scanned up to 8 mice simultaneously using the multi-channel coil and found 11 tumors larger than 0.1 g in 12 mice. Tumor volumes were 1.04±0.73 estimated by MR imaging and 1.04±0.80 cm 3 by reference volume (average±standard deviation) and highly correlated (correlation coefficient, 0.995; P<0.01, Pearson's test). Use of multiple small-animal MR imaging employing a clinical scanner and multi-channel coil enabled accurate assessment of experimental tumor volume in a large number of mice and may facilitate high throughput monitoring of tumor response to therapy in preclinical research. (author)

Identification and optimization of classifier genes from multi-class earthworm microarray dataset.

Directory of Open Access Journals (Sweden)

Ying Li

Full Text Available Monitoring, assessment and prediction of environmental risks that chemicals pose demand rapid and accurate diagnostic assays. A variety of toxicological effects have been associated with explosive compounds TNT and RDX. One important goal of microarray experiments is to discover novel biomarkers for toxicity evaluation. We have developed an earthworm microarray containing 15,208 unique oligo probes and have used it to profile gene expression in 248 earthworms exposed to TNT, RDX or neither. We assembled a new machine learning pipeline consisting of several well-established feature filtering/selection and classification techniques to analyze the 248-array dataset in order to construct classifier models that can separate earthworm samples into three groups: control, TNT-treated, and RDX-treated. First, a total of 869 genes differentially expressed in response to TNT or RDX exposure were identified using a univariate statistical algorithm of class comparison. Then, decision tree-based algorithms were applied to select a subset of 354 classifier genes, which were ranked by their overall weight of significance. A multiclass support vector machine (MC-SVM method and an unsupervised K-mean clustering method were applied to independently refine the classifier, producing a smaller subset of 39 and 30 classifier genes, separately, with 11 common genes being potential biomarkers. The combined 58 genes were considered the refined subset and used to build MC-SVM and clustering models with classification accuracy of 83.5% and 56.9%, respectively. This study demonstrates that the machine learning approach can be used to identify and optimize a small subset of classifier/biomarker genes from high dimensional datasets and generate classification models of acceptable precision for multiple classes.

Class prediction for high-dimensional class-imbalanced data

Directory of Open Access Journals (Sweden)

Lusa Lara

2010-10-01

Full Text Available Abstract Background The goal of class prediction studies is to develop rules to accurately predict the class membership of new samples. The rules are derived using the values of the variables available for each subject: the main characteristic of high-dimensional data is that the number of variables greatly exceeds the number of samples. Frequently the classifiers are developed using class-imbalanced data, i.e., data sets where the number of samples in each class is not equal. Standard classification methods used on class-imbalanced data often produce classifiers that do not accurately predict the minority class; the prediction is biased towards the majority class. In this paper we investigate if the high-dimensionality poses additional challenges when dealing with class-imbalanced prediction. We evaluate the performance of six types of classifiers on class-imbalanced data, using simulated data and a publicly available data set from a breast cancer gene-expression microarray study. We also investigate the effectiveness of some strategies that are available to overcome the effect of class imbalance. Results Our results show that the evaluated classifiers are highly sensitive to class imbalance and that variable selection introduces an additional bias towards classification into the majority class. Most new samples are assigned to the majority class from the training set, unless the difference between the classes is very large. As a consequence, the class-specific predictive accuracies differ considerably. When the class imbalance is not too severe, down-sizing and asymmetric bagging embedding variable selection work well, while over-sampling does not. Variable normalization can further worsen the performance of the classifiers. Conclusions Our results show that matching the prevalence of the classes in training and test set does not guarantee good performance of classifiers and that the problems related to classification with class

Feature extraction based on extended multi-attribute profiles and sparse autoencoder for remote sensing image classification

Science.gov (United States)

Teffahi, Hanane; Yao, Hongxun; Belabid, Nasreddine; Chaib, Souleyman

2018-02-01

The satellite images with very high spatial resolution have been recently widely used in image classification topic as it has become challenging task in remote sensing field. Due to a number of limitations such as the redundancy of features and the high dimensionality of the data, different classification methods have been proposed for remote sensing images classification particularly the methods using feature extraction techniques. This paper propose a simple efficient method exploiting the capability of extended multi-attribute profiles (EMAP) with sparse autoencoder (SAE) for remote sensing image classification. The proposed method is used to classify various remote sensing datasets including hyperspectral and multispectral images by extracting spatial and spectral features based on the combination of EMAP and SAE by linking them to kernel support vector machine (SVM) for classification. Experiments on new hyperspectral image "Huston data" and multispectral image "Washington DC data" shows that this new scheme can achieve better performance of feature learning than the primitive features, traditional classifiers and ordinary autoencoder and has huge potential to achieve higher accuracy for classification in short running time.

Object-based classification of global undersea topography and geomorphological features from the SRTM30_PLUS data

Science.gov (United States)

Dekavalla, Maria; Argialas, Demetre

2017-07-01

The analysis of undersea topography and geomorphological features provides necessary information to related disciplines and many applications. The development of an automated knowledge-based classification approach of undersea topography and geomorphological features is challenging due to their multi-scale nature. The aim of the study is to develop and evaluate an automated knowledge-based OBIA approach to: i) decompose the global undersea topography to multi-scale regions of distinct morphometric properties, and ii) assign the derived regions to characteristic geomorphological features. First, the global undersea topography was decomposed through the SRTM30_PLUS bathymetry data to the so-called morphometric objects of discrete morphometric properties and spatial scales defined by data-driven methods (local variance graphs and nested means) and multi-scale analysis. The derived morphometric objects were combined with additional relative topographic position information computed with a self-adaptive pattern recognition method (geomorphons), and auxiliary data and were assigned to characteristic undersea geomorphological feature classes through a knowledge base, developed from standard definitions. The decomposition of the SRTM30_PLUS data to morphometric objects was considered successful for the requirements of maximizing intra-object and inter-object heterogeneity, based on the near zero values of the Moran's I and the low values of the weighted variance index. The knowledge-based classification approach was tested for its transferability in six case studies of various tectonic settings and achieved the efficient extraction of 11 undersea geomorphological feature classes. The classification results for the six case studies were compared with the digital global seafloor geomorphic features map (GSFM). The 11 undersea feature classes and their producer's accuracies in respect to the GSFM relevant areas were Basin (95%), Continental Shelf (94.9%), Trough (88

Epigenetic silencing of MLH1 in endometrial cancers is associated with larger tumor volume, increased rate of lymph node positivity and reduced recurrence-free survival.

Science.gov (United States)

Cosgrove, Casey M; Cohn, David E; Hampel, Heather; Frankel, Wendy L; Jones, Dan; McElroy, Joseph P; Suarez, Adrian A; Zhao, Weiqiang; Chen, Wei; Salani, Ritu; Copeland, Larry J; O'Malley, David M; Fowler, Jeffrey M; Yilmaz, Ahmet; Chassen, Alexis S; Pearlman, Rachel; Goodfellow, Paul J; Backes, Floor J

2017-09-01

To determine the relationship between mismatch repair (MMR) classification and clinicopathologic features including tumor volume, and explore outcomes by MMR class in a contemporary cohort. Single institution cohort evaluating MMR classification for endometrial cancers (EC). MMR immunohistochemistry (IHC)±microsatellite instability (MSI) testing and reflex MLH1 methylation testing was performed. Tumors with MMR abnormalities by IHC or MSI and MLH1 methylation were classified as epigenetic MMR deficiency while those without MLH1 methylation were classified as probable MMR mutations. Clinicopathologic characteristics were analyzed. 466 endometrial cancers were classified; 75% as MMR proficient, 20% epigenetic MMR defects, and 5% as probable MMR mutations. Epigenetic MMR defects were associated with advanced stage, higher grade, presence of lymphovascular space invasion, and older age. MMR class was significantly associated with tumor volume, an association not previously reported. The epigenetic MMR defect tumors median volume was 10,220mm 3 compared to 3321mm 3 and 2,846mm 3 , for MMR proficient and probable MMR mutations respectively (PMLH1 methylation analysis defines a subset of tumors that have worse prognostic features and reduced RFS. Copyright © 2017 Elsevier Inc. All rights reserved.

Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma.

Directory of Open Access Journals (Sweden)

Leland S Hu

Full Text Available Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM. Contrast-enhanced MRI (CE-MRI targets enhancing core (ENH but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT, despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM.We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set.We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients. The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients.Multi-parametric MRI and texture analysis can help characterize and visualize GBM's spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.

Breast tumor classification using axial shear strain elastography: a feasibility study

International Nuclear Information System (INIS)

Thitaikumar, Arun; Ophir, Jonathan; Mobbs, Louise M; Kraemer-Chant, Christina M; Garra, Brian S

2008-01-01

Recently, the feasibility of visualizing the characteristics of bonding at an inclusion-background boundary using axial-shear strain elastography was demonstrated. In this paper, we report a feasibility study on the utility of the axial-shear strain elastograms in the classification of in vivo breast tumor as being benign or malignant. The study was performed using data sets obtained from 15 benign and 15 malignant cases that were biopsy proven. A total of three independent observers were trained, and their services were utilized for the study. A total of 9 cases were used as training set and the remaining cases were used as testing set. The feature from the axial-shear strain elastogram, namely, the area of the axial-shear region, was extracted by the observers. The observers also outlined the tumor area on the corresponding sonogram, which was used to normalize the area of the axial-shear strain region. There are several observations that can be drawn from the results. First, the result indicates that the observers consistently (∼82% of the cases) noticed the characteristic pattern of the axial-shear strain distribution data as predicted in the previous simulation studies, i.e. alternating regions of positive and negative axial-shear strain values around the tumor-background interface. Second, the analysis of the result suggests that in approximately 57% of the cases in which the observers did not visualize tumor in the sonogram, the elastograms helped them to locate the tumor. Finally, the analysis of the result suggests that for the discriminant feature value of 0.46, the number of unnecessary biopsies could be reduced by 56.3% without compromising on sensitivity and on negative predictive value (NPV). Based on the results in this study, feature values greater than 0.75 appear to be indicative of malignancy, while values less than 0.46 to be indicative of benignity. Feature values between 0.46 and 0.75 may result in an overlap between benign and malignant

Neural network classification of gamma-ray bursts

International Nuclear Information System (INIS)

Balastegui, A.; Canal, R.

2005-01-01

From a cluster analysis it appeared that a three-class classification of GRBs could be preferable to just the classic separation of short/hard and long/soft GRBs (Balastegui A., Ruiz-Lapuente, P. and Canal, R. MNRAS 328 (2001) 283). A new classification of GRBs obtained via a neural network is presented, with a short/hard class, an intermediate-duration/soft class, and a long/soft class, the latter being a brighter and more inhomogeneous class than the intermediate duration one. A possible physical meaning of this new classification is also outlined

[A review of progress of real-time tumor tracking radiotherapy technology based on dynamic multi-leaf collimator].

Science.gov (United States)

Liu, Fubo; Li, Guangjun; Shen, Jiuling; Li, Ligin; Bai, Sen

2017-02-01

While radiation treatment to patients with tumors in thorax and abdomen is being performed, further improvement of radiation accuracy is restricted by the tumor intra-fractional motion due to respiration. Real-time tumor tracking radiation is an optimal solution to tumor intra-fractional motion. A review of the progress of real-time dynamic multi-leaf collimator(DMLC) tracking is provided in the present review, including DMLC tracking method, time lag of DMLC tracking system, and dosimetric verification.

SU-E-I-83: Error Analysis of Multi-Modality Image-Based Volumes of Rodent Solid Tumors Using a Preclinical Multi-Modality QA Phantom

Energy Technology Data Exchange (ETDEWEB)

Lee, Y [University of Kansas Hospital, Kansas City, KS (United States); Fullerton, G; Goins, B [University of Texas Health Science Center at San Antonio, San Antonio, TX (United States)

2015-06-15

Purpose: In our previous study a preclinical multi-modality quality assurance (QA) phantom that contains five tumor-simulating test objects with 2, 4, 7, 10 and 14 mm diameters was developed for accurate tumor size measurement by researchers during cancer drug development and testing. This study analyzed the errors during tumor volume measurement from preclinical magnetic resonance (MR), micro-computed tomography (micro- CT) and ultrasound (US) images acquired in a rodent tumor model using the preclinical multi-modality QA phantom. Methods: Using preclinical 7-Tesla MR, US and micro-CT scanners, images were acquired of subcutaneous SCC4 tumor xenografts in nude rats (3–4 rats per group; 5 groups) along with the QA phantom using the same imaging protocols. After tumors were excised, in-air micro-CT imaging was performed to determine reference tumor volume. Volumes measured for the rat tumors and phantom test objects were calculated using formula V = (π/6)*a*b*c where a, b and c are the maximum diameters in three perpendicular dimensions determined by the three imaging modalities. Then linear regression analysis was performed to compare image-based tumor volumes with the reference tumor volume and known test object volume for the rats and the phantom respectively. Results: The slopes of regression lines for in-vivo tumor volumes measured by three imaging modalities were 1.021, 1.101 and 0.862 for MRI, micro-CT and US respectively. For phantom, the slopes were 0.9485, 0.9971 and 0.9734 for MRI, micro-CT and US respectively. Conclusion: For both animal and phantom studies, random and systematic errors were observed. Random errors were observer-dependent and systematic errors were mainly due to selected imaging protocols and/or measurement method. In the animal study, there were additional systematic errors attributed to ellipsoidal assumption for tumor shape. The systematic errors measured using the QA phantom need to be taken into account to reduce measurement

Anomaly detection for medical images based on a one-class classification

Science.gov (United States)

Wei, Qi; Ren, Yinhao; Hou, Rui; Shi, Bibo; Lo, Joseph Y.; Carin, Lawrence

2018-02-01

Detecting an anomaly such as a malignant tumor or a nodule from medical images including mammogram, CT or PET images is still an ongoing research problem drawing a lot of attention with applications in medical diagnosis. A conventional way to address this is to learn a discriminative model using training datasets of negative and positive samples. The learned model can be used to classify a testing sample into a positive or negative class. However, in medical applications, the high unbalance between negative and positive samples poses a difficulty for learning algorithms, as they will be biased towards the majority group, i.e., the negative one. To address this imbalanced data issue as well as leverage the huge amount of negative samples, i.e., normal medical images, we propose to learn an unsupervised model to characterize the negative class. To make the learned model more flexible and extendable for medical images of different scales, we have designed an autoencoder based on a deep neural network to characterize the negative patches decomposed from large medical images. A testing image is decomposed into patches and then fed into the learned autoencoder to reconstruct these patches themselves. The reconstruction error of one patch is used to classify this patch into a binary class, i.e., a positive or a negative one, leading to a one-class classifier. The positive patches highlight the suspicious areas containing anomalies in a large medical image. The proposed method has been tested on InBreast dataset and achieves an AUC of 0.84. The main contribution of our work can be summarized as follows. 1) The proposed one-class learning requires only data from one class, i.e., the negative data; 2) The patch-based learning makes the proposed method scalable to images of different sizes and helps avoid the large scale problem for medical images; 3) The training of the proposed deep convolutional neural network (DCNN) based auto-encoder is fast and stable.

Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples

Science.gov (United States)

Khan, Faisal; Enzmann, Frieder; Kersten, Michael

2016-03-01

Image processing of X-ray-computed polychromatic cone-beam micro-tomography (μXCT) data of geological samples mainly involves artefact reduction and phase segmentation. For the former, the main beam-hardening (BH) artefact is removed by applying a best-fit quadratic surface algorithm to a given image data set (reconstructed slice), which minimizes the BH offsets of the attenuation data points from that surface. A Matlab code for this approach is provided in the Appendix. The final BH-corrected image is extracted from the residual data or from the difference between the surface elevation values and the original grey-scale values. For the segmentation, we propose a novel least-squares support vector machine (LS-SVM, an algorithm for pixel-based multi-phase classification) approach. A receiver operating characteristic (ROC) analysis was performed on BH-corrected and uncorrected samples to show that BH correction is in fact an important prerequisite for accurate multi-phase classification. The combination of the two approaches was thus used to classify successfully three different more or less complex multi-phase rock core samples.

Accuracy and reproducibility of tumor positioning during prolonged and multi-modality animal imaging studies

International Nuclear Information System (INIS)

Zhang Mutian; Huang Minming; Le, Carl; Zanzonico, Pat B; Ling, C Clifton; Koutcher, Jason A; Humm, John L; Claus, Filip; Kolbert, Katherine S; Martin, Kyle

2008-01-01

Dedicated small-animal imaging devices, e.g. positron emission tomography (PET), computed tomography (CT) and magnetic resonance imaging (MRI) scanners, are being increasingly used for translational molecular imaging studies. The objective of this work was to determine the positional accuracy and precision with which tumors in situ can be reliably and reproducibly imaged on dedicated small-animal imaging equipment. We designed, fabricated and tested a custom rodent cradle with a stereotactic template to facilitate registration among image sets. To quantify tumor motion during our small-animal imaging protocols, 'gold standard' multi-modality point markers were inserted into tumor masses on the hind limbs of rats. Three types of imaging examination were then performed with the animals continuously anesthetized and immobilized: (i) consecutive microPET and MR images of tumor xenografts in which the animals remained in the same scanner for 2 h duration, (ii) multi-modality imaging studies in which the animals were transported between distant imaging devices and (iii) serial microPET scans in which the animals were repositioned in the same scanner for subsequent images. Our results showed that the animal tumor moved by less than 0.2-0.3 mm over a continuous 2 h microPET or MR imaging session. The process of transporting the animal between instruments introduced additional errors of ∼0.2 mm. In serial animal imaging studies, the positioning reproducibility within ∼0.8 mm could be obtained.

The Multi-Purpose Tool of Tumor Immunotherapy: Gene-Engineered T Cells.

Science.gov (United States)

Mo, Zeming; Du, Peixin; Wang, Guoping; Wang, Yongsheng

2017-01-01

A detailed summary of the published clinical trials of chimeric antigen receptor T cells (CAR-T) and TCR-transduced T cells (TCR-T) was constructed to understand the development trend of adoptive T cell therapy (ACT). In contrast to TCR-T, the number of CAR-T clinical trials has increased dramatically in China in the last three years. The ACT seems to be very prosperous. But, the multidimensional interaction of tumor, tumor associated antigen (TAA) and normal tissue exacerbates the uncontrolled outcome of T cells gene therapy. It reminds us the importance that optimizing treatment security to prevent the fatal serious adverse events. How to balance the safety and effectiveness of the ACT? At least six measures can potentially optimize the safety of ACT. At the same time, with the application of gene editing techniques, more endogenous receptors are disrupted while more exogenous receptors are expressed on T cells. As a multi-purpose tool of tumor immunotherapy, gene-engineered T cells (GE-T) have been given different functional weapons. A network which is likely to link radiation therapy, tumor vaccines, CAR-T and TCR-T is being built. Moreover, more and more evidences indicated that the combination of the ACT and other therapies would further enhance the anti-tumor capacity of the GE-T.

Experimental study on multi-sub-classifier for land cover classification: a case study in Shangri-La, China

Science.gov (United States)

Wang, Yan-ying; Wang, Jin-liang; Wang, Ping; Hu, Wen-yin; Su, Shao-hua

2015-12-01

High accuracy remote sensed image classification technology is a long-term and continuous pursuit goal of remote sensing applications. In order to evaluate single classification algorithm accuracy, take Landsat TM image as data source, Northwest Yunnan as study area, seven types of land cover classification like Maximum Likelihood Classification has been tested, the results show that: (1)the overall classification accuracy of Maximum Likelihood Classification(MLC), Artificial Neural Network Classification(ANN), Minimum Distance Classification(MinDC) is higher, which is 82.81% and 82.26% and 66.41% respectively; the overall classification accuracy of Parallel Hexahedron Classification(Para), Spectral Information Divergence Classification(SID), Spectral Angle Classification(SAM) is low, which is 37.29%, 38.37, 53.73%, respectively. (2) from each category classification accuracy: although the overall accuracy of the Para is the lowest, it is much higher on grasslands, wetlands, forests, airport land, which is 89.59%, 94.14%, and 89.04%, respectively; the SAM, SID are good at forests classification with higher overall classification accuracy, which is 89.8% and 87.98%, respectively. Although the overall classification accuracy of ANN is very high, the classification accuracy of road, rural residential land and airport land is very low, which is 10.59%, 11% and 11.59% respectively. Other classification methods have their advantages and disadvantages. These results show that, under the same conditions, the same images with different classification methods to classify, there will be a classifier to some features has higher classification accuracy, a classifier to other objects has high classification accuracy, and therefore, we may select multi sub-classifier integration to improve the classification accuracy.

Object-based Dimensionality Reduction in Land Surface Phenology Classification

Directory of Open Access Journals (Sweden)

Brian E. Bunker

2016-11-01

Full Text Available Unsupervised classification or clustering of multi-decadal land surface phenology provides a spatio-temporal synopsis of natural and agricultural vegetation response to environmental variability and anthropogenic activities. Notwithstanding the detailed temporal information available in calibrated bi-monthly normalized difference vegetation index (NDVI and comparable time series, typical pre-classification workflows average a pixel’s bi-monthly index within the larger multi-decadal time series. While this process is one practical way to reduce the dimensionality of time series with many hundreds of image epochs, it effectively dampens temporal variation from both intra and inter-annual observations related to land surface phenology. Through a novel application of object-based segmentation aimed at spatial (not temporal dimensionality reduction, all 294 image epochs from a Moderate Resolution Imaging Spectroradiometer (MODIS bi-monthly NDVI time series covering the northern Fertile Crescent were retained (in homogenous landscape units as unsupervised classification inputs. Given the inherent challenges of in situ or manual image interpretation of land surface phenology classes, a cluster validation approach based on transformed divergence enabled comparison between traditional and novel techniques. Improved intra-annual contrast was clearly manifest in rain-fed agriculture and inter-annual trajectories showed increased cluster cohesion, reducing the overall number of classes identified in the Fertile Crescent study area from 24 to 10. Given careful segmentation parameters, this spatial dimensionality reduction technique augments the value of unsupervised learning to generate homogeneous land surface phenology units. By combining recent scalable computational approaches to image segmentation, future work can pursue new global land surface phenology products based on the high temporal resolution signatures of vegetation index time series.

Optimization of restricted ROC surfaces in three-class classification tasks.

Science.gov (United States)

Edwards, Darrin C; Metz, Charles E

2007-10-01

We have shown previously that an N-class ideal observer achieves the optimal receiver operating characteristic (ROC) hypersurface in a Neyman-Pearson sense. Due to the inherent complexity of evaluating observer performance even in a three-class classification task, some researchers have suggested a generally incomplete but more tractable evaluation in terms of a surface, plotting only the three "sensitivities." More generally, one can evaluate observer performance with a single sensitivity or misclassification probability as a function of two linear combinations of sensitivities or misclassification probabilities. We analyzed four such formulations including the "sensitivity" surface. In each case, we applied the Neyman-Pearson criterion to find the observer which achieves optimal performance with respect to each given set of "performance description variables" under consideration. In the unrestricted case, optimization with respect to the Neyman-Pearson criterion yields the ideal observer, as does maximization of the observer's expected utility. Moreover, during our consideration of the restricted cases, we found that the two optimization methods do not merely yield the same observer, but are in fact completely equivalent in a mathematical sense. Thus, for a wide variety of observers which maximize performance with respect to a restricted ROC surface in the Neyman-Pearson sense, that ROC surface can also be shown to provide a complete description of the observer's performance in an expected utility sense.

A neural network-based optimal spatial filter design method for motor imagery classification.

Directory of Open Access Journals (Sweden)

Ayhan Yuksel

Full Text Available In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.

Mapping Deforestation in North Korea Using Phenology-Based Multi-Index and Random Forest

Directory of Open Access Journals (Sweden)

Yihua Jin

2016-12-01

Full Text Available Phenology-based multi-index with the random forest (RF algorithm can be used to overcome the shortcomings of traditional deforestation mapping that involves pixel-based classification, such as ISODATA or decision trees, and single images. The purpose of this study was to investigate methods to identify specific types of deforestation in North Korea, and to increase the accuracy of classification, using phenological characteristics extracted with multi-index and random forest algorithms. The mapping of deforestation area based on RF was carried out by merging phenology-based multi-indices (i.e., normalized difference vegetation index (NDVI, normalized difference water index (NDWI, and normalized difference soil index (NDSI derived from MODIS (Moderate Resolution Imaging Spectroradiometer products and topographical variables. Our results showed overall classification accuracy of 89.38%, with corresponding kappa coefficients of 0.87. In particular, for forest and farm land categories with similar phenological characteristic (e.g., paddy, plateau vegetation, unstocked forest, hillside field, this approach improved the classification accuracy in comparison with pixel-based methods and other classes. The deforestation types were identified by incorporating point data from high-resolution imagery, outcomes of image classification, and slope data. Our study demonstrated that the proposed methodology could be used for deciding on the restoration priority and monitoring the expansion of deforestation areas.

Prediction of solubility and permeability class membership: provisional BCS classification of the world's top oral drugs.

Science.gov (United States)

Dahan, Arik; Miller, Jonathan M; Amidon, Gordon L

2009-12-01

The Biopharmaceutics Classification System (BCS) categorizes drugs into one of four biopharmaceutical classes according to their water solubility and membrane permeability characteristics and broadly allows the prediction of the rate-limiting step in the intestinal absorption process following oral administration. Since its introduction in 1995, the BCS has generated remarkable impact on the global pharmaceutical sciences arena, in drug discovery, development, and regulation, and extensive validation/discussion/extension of the BCS is continuously published in the literature. The BCS has been effectively implanted by drug regulatory agencies around the world in setting bioavailability/bioequivalence standards for immediate-release (IR) oral drug product approval. In this review, we describe the BCS scientific framework and impact on regulatory practice of oral drug products and review the provisional BCS classification of the top drugs on the global market. The Biopharmaceutical Drug Disposition Classification System and its association with the BCS are discussed as well. One notable finding of the provisional BCS classification is that the clinical performance of the majority of approved IR oral drug products essential for human health can be assured with an in vitro dissolution test, rather than empirical in vivo human studies.

Depression and suicidal behavior in adolescents: a multi-informant and multi-methods approach to diagnostic classification.

Directory of Open Access Journals (Sweden)

Andrew James Lewis

2014-07-01

Full Text Available Background: Informant discrepancies have been reported between parent and adolescent measures of depressive disorders and suicidality. We aimed to examine the concordance between adolescent and parent ratings of depressive disorder using both clinical interview and questionnaire measures and assess multi-informant and multi-method approaches to classification.Method: Within the context of assessment of eligibility for a randomized clinical trial, 50 parent–adolescent pairs (mean age of adolescents = 15.0 years were interviewed separately with a structured diagnostic interview for depression, the KID-SCID. Adolescent self-report and parent-report versions of the Strengths and Difficulties Questionnaire, the Short Mood and Feelings Questionnaire and the Depressive Experiences Questionnaire were also administered. We examined the diagnostic concordance rates of the parent vs. adolescent structured interview methods and the prediction of adolescent diagnosis via questionnaire methods.Results: Parent proxy reporting of adolescent depression and suicidal thoughts and behavior is not strongly concordant with adolescent report. Adolescent self-reported symptoms on depression scales provide a more accurate report of diagnosable adolescent depression than parent proxy reports of adolescent depressive symptoms. Adolescent self-report measures can be combined to improve the accuracy of classification. Parents tend to over report their adolescent’s depressive symptoms while under reporting their suicidal thoughts and behavior.Conclusion: Parent proxy report is clearly less reliable than the adolescent’s own report of their symptoms and subjective experiences, and could be considered inaccurate for research purposes. While parent report would still be sought clinically where an adolescent refuses to provide information, our findings suggest that parent reporting of adolescent suicidality should be interpreted with caution.

A Quick Negative Selection Algorithm for One-Class Classification in Big Data Era

Directory of Open Access Journals (Sweden)

Fangdong Zhu

2017-01-01

Full Text Available Negative selection algorithm (NSA is an important kind of the one-class classification model, but it is limited in the big data era due to its low efficiency. In this paper, we propose a new NSA based on Voronoi diagrams: VorNSA. The scheme of the detector generation process is changed from the traditional “Random-Discard” model to the “Computing-Designated” model by VorNSA. Furthermore, we present an immune detection process of VorNSA under Map/Reduce framework (VorNSA/MR to further reduce the time consumption on massive data in the testing stage. Theoretical analyses show that the time complexity of VorNSA decreases from the exponential level to the logarithmic level. Experiments are performed to compare the proposed technique with other NSAs and one-class classifiers. The results show that the time cost of the VorNSA is averagely decreased by 87.5% compared with traditional NSAs in UCI skin dataset.

Genetic Bee Colony (GBC) algorithm: A new gene selection method for microarray cancer classification.

Science.gov (United States)

Alshamlan, Hala M; Badr, Ghada H; Alohali, Yousef A

2015-06-01

Naturally inspired evolutionary algorithms prove effectiveness when used for solving feature selection and classification problems. Artificial Bee Colony (ABC) is a relatively new swarm intelligence method. In this paper, we propose a new hybrid gene selection method, namely Genetic Bee Colony (GBC) algorithm. The proposed algorithm combines the used of a Genetic Algorithm (GA) along with Artificial Bee Colony (ABC) algorithm. The goal is to integrate the advantages of both algorithms. The proposed algorithm is applied to a microarray gene expression profile in order to select the most predictive and informative genes for cancer classification. In order to test the accuracy performance of the proposed algorithm, extensive experiments were conducted. Three binary microarray datasets are use, which include: colon, leukemia, and lung. In addition, another three multi-class microarray datasets are used, which are: SRBCT, lymphoma, and leukemia. Results of the GBC algorithm are compared with our recently proposed technique: mRMR when combined with the Artificial Bee Colony algorithm (mRMR-ABC). We also compared the combination of mRMR with GA (mRMR-GA) and Particle Swarm Optimization (mRMR-PSO) algorithms. In addition, we compared the GBC algorithm with other related algorithms that have been recently published in the literature, using all benchmark datasets. The GBC algorithm shows superior performance as it achieved the highest classification accuracy along with the lowest average number of selected genes. This proves that the GBC algorithm is a promising approach for solving the gene selection problem in both binary and multi-class cancer classification. Copyright © 2015 Elsevier Ltd. All rights reserved.

Road and Street Centerlines - FUNCTIONAL_CLASS_INDOTMODEL_IN: Functional Classification of Roadways in Indiana, 2015 (Indiana Department of Transportation, Line Shapefile)

Data.gov (United States)

NSGIC State | GIS Inventory — FUNCTIONAL_CLASS_INDOTMODEL_IN is a line shapefile that shows the Federal Highway Administration functional classification of roadways from the Road Inventory of the...

Variation of stemness markers expression in tumor nodules from synchronous multi-focal hepatocellular carcinoma - an immunohistochemical study.

Science.gov (United States)

Lo, Regina Cheuk-Lam; Leung, Carmen Oi-Ning; Chok, Kenneth Siu-Ho; Ng, Irene Oi-Lin

2017-08-01

Advancing knowledge in molecular pathogenesis of hepatocellular carcinoma (HCC) opens up new horizons in the diagnostic, prognostic and therapeutic perspectives. Assessing the expression of molecular targets prior to definitive treatment is gaining importance in clinical practice. In this study, we investigated the variation in expression pattern of stemness markers in synchronous multi-focal HCC. In the first cohort, 21 liver explants with multi-focal HCC were examined for expression of stemness markers EpCAM, Sox9 and CK19 by immunohistochemistry (IHC). Expression data of 50 tumor nodules were analyzed to determine the concordance of expression among nodules in the same livers. In the second cohort, 14 tumor nodules from 6 multi-focal HCC cases proven as intra-hepatic metastasis were examined for Soc9 immunoexpression. In the first cohort, thirty nodules from 16 cases expressed one or more markers, with Sox9 being most frequently expressed. Complete concordance of expression pattern for all 3 markers was observed in 6 cases. Discrepancy of staining degree was noted in 4 cases for EpCAM, 14 cases for Sox9, and 6 cases for CK19. A two-tier or three-tier difference in staining scores was noted in 5 cases for Sox9 and one case for CK19. With Sox9, identical tumor morphology in terms of Edmondson grading and growth pattern did not infer the same degree of immunoexpression; and the largest tumor nodule was not representative of highest IHC score. In the second cohort of intra-hepatic metastasis, complete concordance of Sox9 expression level was observed in 5 out of 6 cases; while the remaining case showed a 1-tier difference of positive staining. Our findings suggested that clonality of tumor nodules is apparently an important factor to infer immunoexpression pattern. When there is limited information to discern multiple primaries versus intra-hepatic metastasis in multi-focal HCC, discordant degree of stemness markers expression among tumor nodules was commonly

Analysis of Different Classification Techniques for Two-Class Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface

Directory of Open Access Journals (Sweden)

Noman Naseer

2016-01-01

Full Text Available We analyse and compare the classification accuracies of six different classifiers for a two-class mental task (mental arithmetic and rest using functional near-infrared spectroscopy (fNIRS signals. The signals of the mental arithmetic and rest tasks from the prefrontal cortex region of the brain for seven healthy subjects were acquired using a multichannel continuous-wave imaging system. After removal of the physiological noises, six features were extracted from the oxygenated hemoglobin (HbO signals. Two- and three-dimensional combinations of those features were used for classification of mental tasks. In the classification, six different modalities, linear discriminant analysis (LDA, quadratic discriminant analysis (QDA, k-nearest neighbour (kNN, the Naïve Bayes approach, support vector machine (SVM, and artificial neural networks (ANN, were utilized. With these classifiers, the average classification accuracies among the seven subjects for the 2- and 3-dimensional combinations of features were 71.6, 90.0, 69.7, 89.8, 89.5, and 91.4% and 79.6, 95.2, 64.5, 94.8, 95.2, and 96.3%, respectively. ANN showed the maximum classification accuracies: 91.4 and 96.3%. In order to validate the results, a statistical significance test was performed, which confirmed that the p values were statistically significant relative to all of the other classifiers (p < 0.005 using HbO signals.

Classification

DEFF Research Database (Denmark)

Hjørland, Birger

2017-01-01

This article presents and discusses definitions of the term “classification” and the related concepts “Concept/conceptualization,”“categorization,” “ordering,” “taxonomy” and “typology.” It further presents and discusses theories of classification including the influences of Aristotle...... and Wittgenstein. It presents different views on forming classes, including logical division, numerical taxonomy, historical classification, hermeneutical and pragmatic/critical views. Finally, issues related to artificial versus natural classification and taxonomic monism versus taxonomic pluralism are briefly...

How Do CD4+ T Cells Detect and Eliminate Tumor Cells That Either Lack or Express MHC Class II Molecules?

Science.gov (United States)

Haabeth, Ole Audun Werner; Tveita, Anders Aune; Fauskanger, Marte; Schjesvold, Fredrik; Lorvik, Kristina Berg; Hofgaard, Peter O.; Omholt, Hilde; Munthe, Ludvig A.; Dembic, Zlatko; Corthay, Alexandre; Bogen, Bjarne

2014-01-01

CD4+ T cells contribute to tumor eradication, even in the absence of CD8+ T cells. Cytotoxic CD4+ T cells can directly kill MHC class II positive tumor cells. More surprisingly, CD4+ T cells can indirectly eliminate tumor cells that lack MHC class II expression. Here, we review the mechanisms of direct and indirect CD4+ T cell-mediated elimination of tumor cells. An emphasis is put on T cell receptor (TCR) transgenic models, where anti-tumor responses of naïve CD4+ T cells of defined specificity can be tracked. Some generalizations can tentatively be made. For both MHCIIPOS and MHCIINEG tumors, presentation of tumor-specific antigen by host antigen-presenting cells (APCs) appears to be required for CD4+ T cell priming. This has been extensively studied in a myeloma model (MOPC315), where host APCs in tumor-draining lymph nodes are primed with secreted tumor antigen. Upon antigen recognition, naïve CD4+ T cells differentiate into Th1 cells and migrate to the tumor. At the tumor site, the mechanisms for elimination of MHCIIPOS and MHCIINEG tumor cells differ. In a TCR-transgenic B16 melanoma model, MHCIIPOS melanoma cells are directly killed by cytotoxic CD4+ T cells in a perforin/granzyme B-dependent manner. By contrast, MHCIINEG myeloma cells are killed by IFN-γ stimulated M1-like macrophages. In summary, while the priming phase of CD4+ T cells appears similar for MHCIIPOS and MHCIINEG tumors, the killing mechanisms are different. Unresolved issues and directions for future research are addressed. PMID:24782871

How do CD4+ T cells detect and eliminate tumor cells that either lack or express MHC class II molecules?

Directory of Open Access Journals (Sweden)

Ole Audun Werner Haabeth

2014-04-01

Full Text Available CD4+ T cells contribute to tumor eradication, even in the absence of CD8+ T cells. Cytotoxic CD4+ T cells can directly kill MHC class II positive tumor cells. More surprisingly, CD4+ T cells can indirectly eliminate tumor cells that lack MHC class II expression. Here, we review the mechanisms of direct and indirect CD4+ T cell-mediated elimination of tumor cells. An emphasis is put on T cell receptor (TCR transgenic models, where anti-tumor responses of naïve CD4+ T cells of defined specificity can be tracked. Some generalizations can tentatively be made. For both MHCIIPOS and MHCIINEG tumors, presentation of tumor specific antigen by host antigen presenting cells (APCs appears to be required for CD4+ T cell priming. This has been extensively studied in a myeloma model (MOPC315, where host APCs in tumor-draining lymph nodes are primed with secreted tumor antigen. Upon antigen recognition, naïve CD4+ T cells differentiate into Th1 cells and migrate to the tumor. At the tumor site, the mechanisms for elimination of MHCIIPOS and MHCIINEG tumor cells differ. In a TCR transgenic B16 melanoma model, MHCIIPOS melanoma cells are directly killed by cytotoxic CD4+ T cells in a perforin/granzyme B-dependent manner. By contrast, MHCIINEG myeloma cells are killed by IFN-g stimulated M1-like macrophages. In summary, while the priming phase of CD4+ T cells appears similar for MHCIIPOS and MHCIINEG tumors, the killing mechanisms are different. Unresolved issues and directions for future research are addressed.

MODELLING THE RELATIONSHIP BETWEEN LAND SURFACE TEMPERATURE AND LANDSCAPE PATTERNS OF LAND USE LAND COVER CLASSIFICATION USING MULTI LINEAR REGRESSION MODELS

Directory of Open Access Journals (Sweden)

A. M. Bernales

2016-06-01

Full Text Available The threat of the ailments related to urbanization like heat stress is very prevalent. There are a lot of things that can be done to lessen the effect of urbanization to the surface temperature of the area like using green roofs or planting trees in the area. So land use really matters in both increasing and decreasing surface temperature. It is known that there is a relationship between land use land cover (LULC and land surface temperature (LST. Quantifying this relationship in terms of a mathematical model is very important so as to provide a way to predict LST based on the LULC alone. This study aims to examine the relationship between LST and LULC as well as to create a model that can predict LST using class-level spatial metrics from LULC. LST was derived from a Landsat 8 image and LULC classification was derived from LiDAR and Orthophoto datasets. Class-level spatial metrics were created in FRAGSTATS with the LULC and LST as inputs and these metrics were analysed using a statistical framework. Multi linear regression was done to create models that would predict LST for each class and it was found that the spatial metric “Effective mesh size” was a top predictor for LST in 6 out of 7 classes. The model created can still be refined by adding a temporal aspect by analysing the LST of another farming period (for rural areas and looking for common predictors between LSTs of these two different farming periods.

Recursive partitioning analysis (RPA) classification predicts survival in patients with brain metastases from sarcoma.

Science.gov (United States)

Grossman, Rachel; Ram, Zvi

2014-12-01

Sarcoma rarely metastasizes to the brain, and there are no specific treatment guidelines for these tumors. The recursive partitioning analysis (RPA) classification is a well-established prognostic scale used in many malignancies. In this study we assessed the clinical characteristics of metastatic sarcoma to the brain and the validity of the RPA classification system in a subset of 21 patients who underwent surgical resection of metastatic sarcoma to the brain We retrospectively analyzed the medical, radiological, surgical, pathological, and follow-up clinical records of 21 patients who were operated for metastatic sarcoma to the brain between 1996 and 2012. Gliosarcomas, sarcomas of the head and neck with local extension into the brain, and metastatic sarcomas to the spine were excluded from this reported series. The patients' mean age was 49.6 ± 14.2 years (range, 25-75 years) at the time of diagnosis. Sixteen patients had a known history of systemic sarcoma, mostly in the extremities, and had previously received systemic chemotherapy and radiation therapy for their primary tumor. The mean maximal tumor diameter in the brain was 4.9 ± 1.7 cm (range 1.7-7.2 cm). The group's median preoperative Karnofsky Performance Scale was 80, with 14 patients presenting with Karnofsky Performance Scale of 70 or greater. The median overall survival was 7 months (range 0.2-204 months). The median survival time stratified by the Radiation Therapy Oncology Group RPA classes were 31, 7, and 2 months for RPA class I, II, and III, respectively (P = 0.0001). This analysis is the first to support the prognostic utility of the Radiation Therapy Oncology Group RPA classification for sarcoma brain metastases and may be used as a treatment guideline tool in this rare disease. Copyright © 2014 Elsevier Inc. All rights reserved.

Defuzzification Strategies for Fuzzy Classifications of Remote Sensing Data

Directory of Open Access Journals (Sweden)

Peter Hofmann

2016-06-01

Full Text Available The classes in fuzzy classification schemes are defined as fuzzy sets, partitioning the feature space through fuzzy rules, defined by fuzzy membership functions. Applying fuzzy classification schemes in remote sensing allows each pixel or segment to be an incomplete member of more than one class simultaneously, i.e., one that does not fully meet all of the classification criteria for any one of the classes and is member of more than one class simultaneously. This can lead to fuzzy, ambiguous and uncertain class assignation, which is unacceptable for many applications, indicating the need for a reliable defuzzification method. Defuzzification in remote sensing has to date, been performed by “crisp-assigning” each fuzzy-classified pixel or segment to the class for which it best fulfills the fuzzy classification rules, regardless of its classification fuzziness, uncertainty or ambiguity (maximum method. The defuzzification of an uncertain or ambiguous fuzzy classification leads to a more or less reliable crisp classification. In this paper the most common parameters for expressing classification uncertainty, fuzziness and ambiguity are analysed and discussed in terms of their ability to express the reliability of a crisp classification. This is done by means of a typical practical example from Object Based Image Analysis (OBIA.

[Object-oriented stand type classification based on the combination of multi-source remote sen-sing data].

Science.gov (United States)

Mao, Xue Gang; Wei, Jing Yu

2017-11-01

The recognition of forest type is one of the key problems in forest resource monitoring. The Radarsat-2 data and QuickBird remote sensing image were used for object-based classification to study the object-based forest type classification and recognition based on the combination of multi-source remote sensing data. In the process of object-based classification, three segmentation schemes (segmentation with QuickBird remote sensing image only, segmentation with Radarsat-2 data only, segmentation with combination of QuickBird and Radarsat-2) were adopted. For the three segmentation schemes, ten segmentation scale parameters were adopted (25-250, step 25), and modified Euclidean distance 3 index was further used to evaluate the segmented results to determine the optimal segmentation scheme and segmentation scale. Based on the optimal segmented result, three forest types of Chinese fir, Masson pine and broad-leaved forest were classified and recognized using Support Vector Machine (SVM) classifier with Radial Basis Foundation (RBF) kernel according to different feature combinations of topography, height, spectrum and common features. The results showed that the combination of Radarsat-2 data and QuickBird remote sensing image had its advantages of object-based forest type classification over using Radarsat-2 data or QuickBird remote sensing image only. The optimal scale parameter for QuickBirdRadarsat-2 segmentation was 100, and at the optimal scale, the accuracy of object-based forest type classification was the highest (OA=86%, Kappa=0.86), when using all features which were extracted from two kinds of data resources. This study could not only provide a reference for forest type recognition using multi-source remote sensing data, but also had a practical significance for forest resource investigation and monitoring.

Decomposition and classification of electroencephalography data

DEFF Research Database (Denmark)

Frølich, Laura

. To enforce orthonormality of projection matrices, objective functions quantifying class discrimination were optimised on a cross-product of Stiefel (orthonormal matrix) manifolds. Supervised feature extraction outperformed unsupervised methods, but the choice of supervised method mattered less. We suggested......_MARC was also used to inspect effects of artefacts on motor imagery based Brain-Computer Interfaces (BCIs) in two studies, where removing artefactual ICs had little performance impact. Finally, we investigated multi-linear classification on single trials of EEG data, proposing a rigorous optimisation approach...... completions of methods to include both PARAFAC and Tucker structures. The two structures provided similar performances, making the more interpretable PARAFAC models appealing....

TU-AB-202-11: Tumor Segmentation by Fusion of Multi-Tracer PET Images Using Copula Based Statistical Methods

International Nuclear Information System (INIS)

Lapuyade-Lahorgue, J; Ruan, S; Li, H; Vera, P

2016-01-01

Purpose: Multi-tracer PET imaging is getting more attention in radiotherapy by providing additional tumor volume information such as glucose and oxygenation. However, automatic PET-based tumor segmentation is still a very challenging problem. We propose a statistical fusion approach to joint segment the sub-area of tumors from the two tracers FDG and FMISO PET images. Methods: Non-standardized Gamma distributions are convenient to model intensity distributions in PET. As a serious correlation exists in multi-tracer PET images, we proposed a new fusion method based on copula which is capable to represent dependency between different tracers. The Hidden Markov Field (HMF) model is used to represent spatial relationship between PET image voxels and statistical dynamics of intensities for each modality. Real PET images of five patients with FDG and FMISO are used to evaluate quantitatively and qualitatively our method. A comparison between individual and multi-tracer segmentations was conducted to show advantages of the proposed fusion method. Results: The segmentation results show that fusion with Gaussian copula can receive high Dice coefficient of 0.84 compared to that of 0.54 and 0.3 of monomodal segmentation results based on individual segmentation of FDG and FMISO PET images. In addition, high correlation coefficients (0.75 to 0.91) for the Gaussian copula for all five testing patients indicates the dependency between tumor regions in the multi-tracer PET images. Conclusion: This study shows that using multi-tracer PET imaging can efficiently improve the segmentation of tumor region where hypoxia and glucidic consumption are present at the same time. Introduction of copulas for modeling the dependency between two tracers can simultaneously take into account information from both tracers and deal with two pathological phenomena. Future work will be to consider other families of copula such as spherical and archimedian copulas, and to eliminate partial volume

A Novel Approach for Multi Class Fault Diagnosis in Induction Machine Based on Statistical Time Features and Random Forest Classifier

Science.gov (United States)

Sonje, M. Deepak; Kundu, P.; Chowdhury, A.

2017-08-01

Fault diagnosis and detection is the important area in health monitoring of electrical machines. This paper proposes the recently developed machine learning classifier for multi class fault diagnosis in induction machine. The classification is based on random forest (RF) algorithm. Initially, stator currents are acquired from the induction machine under various conditions. After preprocessing the currents, fourteen statistical time features are estimated for each phase of the current. These parameters are considered as inputs to the classifier. The main scope of the paper is to evaluate effectiveness of RF classifier for individual and mixed fault diagnosis in induction machine. The stator, rotor and mixed faults (stator and rotor faults) are classified using the proposed classifier. The obtained performance measures are compared with the multilayer perceptron neural network (MLPNN) classifier. The results show the much better performance measures and more accurate than MLPNN classifier. For demonstration of planned fault diagnosis algorithm, experimentally obtained results are considered to build the classifier more practical.

Classification of video sequences into chosen generalized use classes of target size and lighting level.

Science.gov (United States)

Leszczuk, Mikołaj; Dudek, Łukasz; Witkowski, Marcin

The VQiPS (Video Quality in Public Safety) Working Group, supported by the U.S. Department of Homeland Security, has been developing a user guide for public safety video applications. According to VQiPS, five parameters have particular importance influencing the ability to achieve a recognition task. They are: usage time-frame, discrimination level, target size, lighting level, and level of motion. These parameters form what are referred to as Generalized Use Classes (GUCs). The aim of our research was to develop algorithms that would automatically assist classification of input sequences into one of the GUCs. Target size and lighting level parameters were approached. The experiment described reveals the experts' ambiguity and hesitation during the manual target size determination process. However, the automatic methods developed for target size classification make it possible to determine GUC parameters with 70 % compliance to the end-users' opinion. Lighting levels of the entire sequence can be classified with an efficiency reaching 93 %. To make the algorithms available for use, a test application has been developed. It is able to process video files and display classification results, the user interface being very simple and requiring only minimal user interaction.

Repeatability of quantitative 18F-FLT uptake measurements in solid tumors: an individual patient data multi-center meta-analysis.

Science.gov (United States)

Kramer, G M; Liu, Y; de Langen, A J; Jansma, E P; Trigonis, I; Asselin, M-C; Jackson, A; Kenny, L; Aboagye, E O; Hoekstra, O S; Boellaard, R

2018-06-01

3'-deoxy-3'-[ 18 F]fluorothymidine ( 18 F-FLT) positron emission tomography (PET) provides a non-invasive method to assess cellular proliferation and response to antitumor therapy. Quantitative 18 F-FLT uptake metrics are being used for evaluation of proliferative response in investigational setting, however multi-center repeatability needs to be established. The aim of this study was to determine the repeatability of 18 F-FLT tumor uptake metrics by re-analyzing individual patient data from previously published reports using the same tumor segmentation method and repeatability metrics across cohorts. A systematic search in PubMed, EMBASE.com and the Cochrane Library from inception-October 2016 yielded five 18 F-FLT repeatability cohorts in solid tumors. 18 F-FLT avid lesions were delineated using a 50% isocontour adapted for local background on test and retest scans. SUV max , SUV mean , SUV peak , proliferative volume and total lesion uptake (TLU) were calculated. Repeatability was assessed using the repeatability coefficient (RC = 1.96 × SD of test-retest differences), linear regression analysis, and the intra-class correlation coefficient (ICC). The impact of different lesion selection criteria was also evaluated. Images from four cohorts containing 30 patients with 52 lesions were obtained and analyzed (ten in breast cancer, nine in head and neck squamous cell carcinoma, and 33 in non-small cell lung cancer patients). A good correlation was found between test-retest data for all 18 F-FLT uptake metrics (R 2  ≥ 0.93; ICC ≥ 0.96). Best repeatability was found for SUV peak (RC: 23.1%), without significant differences in RC between different SUV metrics. Repeatability of proliferative volume (RC: 36.0%) and TLU (RC: 36.4%) was worse than SUV. Lesion selection methods based on SUV max  ≥ 4.0 improved the repeatability of volumetric metrics (RC: 26-28%), but did not affect the repeatability of SUV metrics. In multi-center studies

Risk factors and classifications of hilar cholangiocarcinoma.

Science.gov (United States)

Suarez-Munoz, Miguel Angel; Fernandez-Aguilar, Jose Luis; Sanchez-Perez, Belinda; Perez-Daga, Jose Antonio; Garcia-Albiach, Beatriz; Pulido-Roa, Ysabel; Marin-Camero, Naiara; Santoyo-Santoyo, Julio

2013-07-15

Cholangiocarcinoma is the second most common primary malignant tumor of the liver. Perihilar cholangiocarcinoma or Klatskin tumor represents more than 50% of all biliary tract cholangiocarcinomas. A wide range of risk factors have been identified among patients with Perihilar cholangiocarcinoma including advanced age, male gender, primary sclerosing cholangitis, choledochal cysts, cholelithiasis, cholecystitis, parasitic infection (Opisthorchis viverrini and Clonorchis sinensis), inflammatory bowel disease, alcoholic cirrhosis, nonalcoholic cirrhosis, chronic pancreatitis and metabolic syndrome. Various classifications have been used to describe the pathologic and radiologic appearance of cholangiocarcinoma. The three systems most commonly used to evaluate Perihilar cholangiocarcinoma are the Bismuth-Corlette (BC) system, the Memorial Sloan-Kettering Cancer Center and the TNM classification. The BC classification provides preoperative assessment of local spread. The Memorial Sloan-Kettering cancer center proposes a staging system according to three factors related to local tumor extent: the location and extent of bile duct involvement, the presence or absence of portal venous invasion, and the presence or absence of hepatic lobar atrophy. The TNM classification, besides the usual descriptors, tumor, node and metastases, provides additional information concerning the possibility for the residual tumor (R) and the histological grade (G). Recently, in 2011, a new consensus classification for the Perihilar cholangiocarcinoma had been published. The consensus was organised by the European Hepato-Pancreato-Biliary Association which identified the need for a new staging system for this type of tumors. The classification includes information concerning biliary or vascular (portal or arterial) involvement, lymph node status or metastases, but also other essential aspects related to the surgical risk, such as remnant hepatic volume or the possibility of underlying disease.

A Multi-targeted Approach to Suppress Tumor-Promoting Inflammation

Science.gov (United States)

Samadi, Abbas K.; Georgakilas, Alexandros G.; Amedei, Amedeo; Amin, Amr; Bishayee, Anupam; Lokeshwar, Bal L.; Grue, Brendan; Panis, Carolina; Boosani, Chandra S.; Poudyal, Deepak; Stafforini, Diana M.; Bhakta, Dipita; Niccolai, Elena; Guha, Gunjan; Rupasinghe, H.P. Vasantha; Fujii, Hiromasa; Honoki, Kanya; Mehta, Kapil; Aquilano, Katia; Lowe, Leroy; Hofseth, Lorne J.; Ricciardiello, Luigi; Ciriolo, Maria Rosa; Singh, Neetu; Whelan, Richard L.; Chaturvedi, Rupesh; Ashraf, S. Salman; Kumara, HMC Shantha; Nowsheen, Somaira; Mohammed, Sulma I.; Helferich, William G.; Yang, Xujuan

2015-01-01

Cancers harbor significant genetic heterogeneity and patterns of relapse following many therapies are due to evolved resistance to treatment. While efforts have been made to combine targeted therapies, significant levels of toxicity have stymied efforts to effectively treat cancer with multi-drug combinations using currently approved therapeutics. We discuss the relationship between tumor-promoting inflammation and cancer as part of a larger effort to develop a broad-spectrum therapeutic approach aimed at a wide range of targets to address this heterogeneity. Specifically, macrophage migration inhibitory factor, cyclooxygenase-2, transcription factor nuclear factor-kappaB, tumor necrosis factor alpha, inducible nitric oxide synthase, protein kinase B, and CXC chemokines are reviewed as important antiinflammatory targets while curcumin, resveratrol, epigallocatechin gallate, genistein, lycopene, and anthocyanins are reviewed as low-cost, low toxicity means by which these targets might all be reached simultaneously. Future translational work will need to assess the resulting synergies of rationally designed antiinflammatory mixtures (employing low-toxicity constituents), and then combine this with similar approaches targeting the most important pathways across the range of cancer hallmark phenotypes. PMID:25951989

Land cover classification accuracy from electro-optical, X, C, and L-band Synthetic Aperture Radar data fusion

Science.gov (United States)

Hammann, Mark Gregory

The fusion of electro-optical (EO) multi-spectral satellite imagery with Synthetic Aperture Radar (SAR) data was explored with the working hypothesis that the addition of multi-band SAR will increase the land-cover (LC) classification accuracy compared to EO alone. Three satellite sources for SAR imagery were used: X-band from TerraSAR-X, C-band from RADARSAT-2, and L-band from PALSAR. Images from the RapidEye satellites were the source of the EO imagery. Imagery from the GeoEye-1 and WorldView-2 satellites aided the selection of ground truth. Three study areas were chosen: Wad Medani, Sudan; Campinas, Brazil; and Fresno- Kings Counties, USA. EO imagery were radiometrically calibrated, atmospherically compensated, orthorectifed, co-registered, and clipped to a common area of interest (AOI). SAR imagery were radiometrically calibrated, and geometrically corrected for terrain and incidence angle by converting to ground range and Sigma Naught (?0). The original SAR HH data were included in the fused image stack after despeckling with a 3x3 Enhanced Lee filter. The variance and Gray-Level-Co-occurrence Matrix (GLCM) texture measures of contrast, entropy, and correlation were derived from the non-despeckled SAR HH bands. Data fusion was done with layer stacking and all data were resampled to a common spatial resolution. The Support Vector Machine (SVM) decision rule was used for the supervised classifications. Similar LC classes were identified and tested for each study area. For Wad Medani, nine classes were tested: low and medium intensity urban, sparse forest, water, barren ground, and four agriculture classes (fallow, bare agricultural ground, green crops, and orchards). For Campinas, Brazil, five generic classes were tested: urban, agriculture, forest, water, and barren ground. For the Fresno-Kings Counties location 11 classes were studied: three generic classes (urban, water, barren land), and eight specific crops. In all cases the addition of SAR to EO resulted

Landscape object-based analysis of wetland plant functional types: the effects of spatial scale, vegetation classes and classifier methods

Science.gov (United States)

Dronova, I.; Gong, P.; Wang, L.; Clinton, N.; Fu, W.; Qi, S.

2011-12-01

individual classes differed in scales at which they were best discriminated from others. Main classification challenges included a) presence of C3 grasses in C4-grass areas, particularly following harvesting of C4 reeds and b) mixtures of emergent, floating and submerged aquatic plants at sub-object and sub-pixel scales. We conclude that OBIA with advanced statistical classifiers offers useful instruments for landscape vegetation analyses, and that spatial scale considerations are critical in mapping PFTs, while multi-scale comparisons can be used to guide class selection. Future work will further apply fuzzy classification and field-collected spectral data for PFT analysis and compare results with MODIS PFT products.

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification.

Science.gov (United States)

Wen, Cuihong; Zhang, Jing; Rebelo, Ana; Cheng, Fanyong

2016-01-01

Optical Music Recognition (OMR) has received increasing attention in recent years. In this paper, we propose a classifier based on a new method named Directed Acyclic Graph-Large margin Distribution Machine (DAG-LDM). The DAG-LDM is an improvement of the Large margin Distribution Machine (LDM), which is a binary classifier that optimizes the margin distribution by maximizing the margin mean and minimizing the margin variance simultaneously. We modify the LDM to the DAG-LDM to solve the multi-class music symbol classification problem. Tests are conducted on more than 10000 music symbol images, obtained from handwritten and printed images of music scores. The proposed method provides superior classification capability and achieves much higher classification accuracy than the state-of-the-art algorithms such as Support Vector Machines (SVMs) and Neural Networks (NNs).

Involvement of HLA class I molecules in the immune escape of urologic tumors.

Science.gov (United States)

Carretero, R; Gil-Julio, H; Vázquez-Alonso, F; Garrido, F; Castiñeiras, J; Cózar, J M

2014-04-01

To analyze the influence of different alterations in human leukocyte antigen class I molecules (HLA I) in renal cell carcinoma, as well as in bladder and prostate cancer. We also study the correlation between HLA I expression and the progression of the disease and the response after immunotherapy protocols. It has been shown, experimentally, that the immune system can recognize and kill neoplastic cells. By analyzing the expression of HLA I molecules on the surface of cancer cells, we were able to study the tumor escape mechanisms against the immune system. Alteration or irreversible damage in HLA I molecules is used by the neoplastic cells to escape the immune system. The function of these molecules is to recognize endogenous peptides and present them to T cells of the immune system. There is a clear relationship between HLA I reversible alterations and success of therapy. Irreversible lesions also imply a lack of response to treatment. The immune system activation can reverse HLA I molecules expression in tumors with reversible lesions, whereas tumors with irreversible ones do not respond to such activation. Determine the type of altered HLA I molecules in tumors is of paramount importance when choosing the type of treatment to keep looking for therapeutic success. Those tumors with reversible lesions can be treated with traditional immunotherapy; however, tumour with irreversible alterations should follow alternative protocols, such as the use of viral vectors carrying the HLA genes to achieve damaged re-expression of the protein. From studies in urologic tumors, we can conclude that the HLA I molecules play a key role in these tumors escape to the immune system. Copyright © 2013 AEU. Published by Elsevier Espana. All rights reserved.

Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma.

Science.gov (United States)

Hu, Leland S; Ning, Shuluo; Eschbacher, Jennifer M; Gaw, Nathan; Dueck, Amylou C; Smith, Kris A; Nakaji, Peter; Plasencia, Jonathan; Ranjbar, Sara; Price, Stephen J; Tran, Nhan; Loftus, Joseph; Jenkins, Robert; O'Neill, Brian P; Elmquist, William; Baxter, Leslie C; Gao, Fei; Frakes, David; Karis, John P; Zwart, Christine; Swanson, Kristin R; Sarkaria, Jann; Wu, Teresa; Mitchell, J Ross; Li, Jing

2015-01-01

Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs heterogeneity to identify regional tumor-rich biopsy targets.

Fusing in vivo and ex vivo NMR sources of information for brain tumor classification

International Nuclear Information System (INIS)

Croitor-Sava, A R; Laudadio, T; Sima, D M; Van Huffel, S; Martinez-Bisbal, M C; Celda, B; Piquer, J; Heerschap, A

2011-01-01

In this study we classify short echo-time brain magnetic resonance spectroscopic imaging (MRSI) data by applying a model-based canonical correlation analyses algorithm and by using, as prior knowledge, multimodal sources of information coming from high-resolution magic angle spinning (HR-MAS), MRSI and magnetic resonance imaging. The potential and limitations of fusing in vivo and ex vivo nuclear magnetic resonance sources to detect brain tumors is investigated. We present various modalities for multimodal data fusion, study the effect and the impact of using multimodal information for classifying MRSI brain glial tumors data and analyze which parameters influence the classification results by means of extensive simulation and in vivo studies. Special attention is drawn to the possibility of considering HR-MAS data as a complementary dataset when dealing with a lack of MRSI data needed to build a classifier. Results show that HR-MAS information can have added value in the process of classifying MRSI data

Classifications within molecular subtypes enables identification of BRCA1/BRCA2 mutation carriers by RNA tumor profiling

DEFF Research Database (Denmark)

Larsen, Martin J; Kruse, Torben A; Tan, Qihua

2013-01-01

Pathogenic germline mutations in BRCA1 or BRCA2 are detected in less than one third of families with a strong history of breast cancer. It is therefore expected that mutations still remain undetected by currently used screening methods. In addition, a growing number of BRCA1/2 sequence variants...... of unclear pathogen significance are found in the families, constituting an increasing clinical challenge. New methods are therefore needed to improve the detection rate and aid the interpretation of the clinically uncertain variants. In this study we analyzed a series of 33 BRCA1, 22 BRCA2, and 128 sporadic...... tumors by RNA profiling to investigate the classification potential of RNA profiles to predict BRCA1/2 mutation status. We found that breast tumors from BRCA1 and BRCA2 mutation carriers display characteristic RNA expression patterns, allowing them to be distinguished from sporadic tumors. The majority...

National-Scale Hydrologic Classification & Agricultural Decision Support: A Multi-Scale Approach

Science.gov (United States)

Coopersmith, E. J.; Minsker, B.; Sivapalan, M.

2012-12-01

Classification frameworks can help organize catchments exhibiting similarity in hydrologic and climatic terms. Focusing this assessment of "similarity" upon specific hydrologic signatures, in this case the annual regime curve, can facilitate the prediction of hydrologic responses. Agricultural decision-support over a diverse set of catchments throughout the United States depends upon successful modeling of the wetting/drying process without necessitating separate model calibration at every site where such insights are required. To this end, a holistic classification framework is developed to describe both climatic variability (humid vs. arid, winter rainfall vs. summer rainfall) and the draining, storing, and filtering behavior of any catchment, including ungauged or minimally gauged basins. At the national scale, over 400 catchments from the MOPEX database are analyzed to construct the classification system, with over 77% of these catchments ultimately falling into only six clusters. At individual locations, soil moisture models, receiving only rainfall as input, produce correlation values in excess of 0.9 with respect to observed soil moisture measurements. By deploying physical models for predicting soil moisture exclusively from precipitation that are calibrated at gauged locations, overlaying machine learning techniques to improve these estimates, then generalizing the calibration parameters for catchments in a given class, agronomic decision-support becomes available where it is needed rather than only where sensing data are located.lassifications of 428 U.S. catchments on the basis of hydrologic regime data, Coopersmith et al, 2012.

A Cognitive Computing Approach for Classification of Complaints in the Insurance Industry

Science.gov (United States)

Forster, J.; Entrup, B.

2017-10-01

In this paper we present and evaluate a cognitive computing approach for classification of dissatisfaction and four complaint specific complaint classes in correspondence documents between insurance clients and an insurance company. A cognitive computing approach includes the combination classical natural language processing methods, machine learning algorithms and the evaluation of hypothesis. The approach combines a MaxEnt machine learning algorithm with language modelling, tf-idf and sentiment analytics to create a multi-label text classification model. The result is trained and tested with a set of 2500 original insurance communication documents written in German, which have been manually annotated by the partnering insurance company. With a F1-Score of 0.9, a reliable text classification component has been implemented and evaluated. A final outlook towards a cognitive computing insurance assistant is given in the end.

a Comparison Study of Different Kernel Functions for Svm-Based Classification of Multi-Temporal Polarimetry SAR Data

Science.gov (United States)

Yekkehkhany, B.; Safari, A.; Homayouni, S.; Hasanlou, M.

2014-10-01

In this paper, a framework is developed based on Support Vector Machines (SVM) for crop classification using polarimetric features extracted from multi-temporal Synthetic Aperture Radar (SAR) imageries. The multi-temporal integration of data not only improves the overall retrieval accuracy but also provides more reliable estimates with respect to single-date data. Several kernel functions are employed and compared in this study for mapping the input space to higher Hilbert dimension space. These kernel functions include linear, polynomials and Radial Based Function (RBF). The method is applied to several UAVSAR L-band SAR images acquired over an agricultural area near Winnipeg, Manitoba, Canada. In this research, the temporal alpha features of H/A/α decomposition method are used in classification. The experimental tests show an SVM classifier with RBF kernel for three dates of data increases the Overall Accuracy (OA) to up to 3% in comparison to using linear kernel function, and up to 1% in comparison to a 3rd degree polynomial kernel function.

Quantitative Multi-Parametric Magnetic Resonance Imaging of Tumor Response to Photodynamic Therapy.

Directory of Open Access Journals (Sweden)

Tom J L Schreurs

Full Text Available The aim of this study was to characterize response to photodynamic therapy (PDT in a mouse cancer model using a multi-parametric quantitative MRI protocol and to identify MR parameters as potential biomarkers for early assessment of treatment outcome.CT26.WT colon carcinoma tumors were grown subcutaneously in the hind limb of BALB/c mice. Therapy consisted of intravenous injection of the photosensitizer Bremachlorin, followed by 10 min laser illumination (200 mW/cm2 of the tumor 6 h post injection. MRI at 7 T was performed at baseline, directly after PDT, as well as at 24 h, and 72 h. Tumor relaxation time constants (T1 and T2 and apparent diffusion coefficient (ADC were quantified at each time point. Additionally, Gd-DOTA dynamic contrast-enhanced (DCE MRI was performed to estimate transfer constants (Ktrans and volume fractions of the extravascular extracellular space (ve using standard Tofts-Kermode tracer kinetic modeling. At the end of the experiment, tumor viability was characterized by histology using NADH-diaphorase staining.The therapy induced extensive cell death in the tumor and resulted in significant reduction in tumor growth, as compared to untreated controls. Tumor T1 and T2 relaxation times remained unchanged up to 24 h, but decreased at 72 h after treatment. Tumor ADC values significantly increased at 24 h and 72 h. DCE-MRI derived tracer kinetic parameters displayed an early response to the treatment. Directly after PDT complete vascular shutdown was observed in large parts of the tumors and reduced uptake (decreased Ktrans in remaining tumor tissue. At 24 h, contrast uptake in most tumors was essentially absent. Out of 5 animals that were monitored for 2 weeks after treatment, 3 had tumor recurrence, in locations that showed strong contrast uptake at 72 h.DCE-MRI is an effective tool for visualization of vascular effects directly after PDT. Endogenous contrast parameters T1, T2, and ADC, measured at 24 to 72 h after PDT, are

Breast Cancer Survival Defined by the ER/PR/HER2 Subtypes and a Surrogate Classification according to Tumor Grade and Immunohistochemical Bio markers

International Nuclear Information System (INIS)

Parise, C. A.; Caggiano, V.

2014-01-01

ER, PR, and HER2 are routinely available in breast cancer specimens. The purpose of this study is to contrast breast cancer-specific survival for the eight ER/PR/HER2 subtypes with survival of an immunohistochemical surrogate for the molecular subtype based on the ER/PR/HER2 subtypes and tumor grade. Methods. We identified 123,780 cases of stages 1-3 primary female invasive breast cancer from California Cancer Registry. The surrogate classification was derived using ER/PR/HER2 and tumor grade. Kaplan-Meier survival analysis and Cox proportional hazards modeling were used to assess differences in survival and risk of mortality for the ER/PR/HER2 subtypes and surrogate classification within each stage. Results. The luminal B/HER2− surrogate classification had a higher risk of mortality than the luminal B/HER2+ for all stages of disease. There was no difference in risk of mortality between the ER+/PR+/HER2− and ER+/PR+/HER2+ in stage 3. With one exception in stage 3, the ER-negative subtypes all had an increased risk of mortality when compared with the ER-positive subtypes. Conclusions. Assessment of survival using ER/PR/HER2 illustrates the heterogeneity of HER2+ subtypes. The surrogate classification provides clear separation in survival and adjusted mortality but underestimates the wide variability within the subtypes that make up the classification.

Breast Cancer Survival Defined by the ER/PR/HER2 Subtypes and a Surrogate Classification according to Tumor Grade and Immunohistochemical Biomarkers

Directory of Open Access Journals (Sweden)

Carol A. Parise

2014-01-01

Full Text Available Introduction. ER, PR, and HER2 are routinely available in breast cancer specimens. The purpose of this study is to contrast breast cancer-specific survival for the eight ER/PR/HER2 subtypes with survival of an immunohistochemical surrogate for the molecular subtype based on the ER/PR/HER2 subtypes and tumor grade. Methods. We identified 123,780 cases of stages 1–3 primary female invasive breast cancer from California Cancer Registry. The surrogate classification was derived using ER/PR/HER2 and tumor grade. Kaplan-Meier survival analysis and Cox proportional hazards modeling were used to assess differences in survival and risk of mortality for the ER/PR/HER2 subtypes and surrogate classification within each stage. Results. The luminal B/HER2− surrogate classification had a higher risk of mortality than the luminal B/HER2+ for all stages of disease. There was no difference in risk of mortality between the ER+/PR+/HER2− and ER+/PR+/HER2+ in stage 3. With one exception in stage 3, the ER-negative subtypes all had an increased risk of mortality when compared with the ER-positive subtypes. Conclusions. Assessment of survival using ER/PR/HER2 illustrates the heterogeneity of HER2+ subtypes. The surrogate classification provides clear separation in survival and adjusted mortality but underestimates the wide variability within the subtypes that make up the classification.

Multivariate decision tree designing for the classification of multi-jet topologies in e sup + e sup - collisions

CERN Document Server

Mjahed, M

2002-01-01

The binary decision tree method is used to separate between several multi-jet topologies in e sup + e sup - collisions. Instead of the univariate process usually taken, a new design procedure for constructing multivariate decision trees is proposed. The segmentation is obtained by considering some features functions, where linear and non-linear discriminant functions and a minimal distance method are used. The classification focuses on ALEPH simulated events, with multi-jet topologies. Compared to a standard univariate tree, the multivariate decision trees offer significantly better performance.

Malignant tumors of gastrointestinal tract

International Nuclear Information System (INIS)

Anon.

1989-01-01

International histological classification and classification according to TNM systems, domestic clinical classification according to stages of carcinoma of stomach, large intestine and rectum are presented. Diagnosis of tumoral processes of the given localizations should be based on complex application of diagnostic methods: clinical, ultrasonic, radiological and others. Surgical method and variants of surgical method with preoperative radiotherapy play a leading role in treatment of mentioned tumors. Combined method of treatment-surgical intervention with postoperation intravenous injection of colloid 198 Au - is applied for preventing propagation of stomach cancer metastases. Advisability of combining operations with radiological and antitumoral medicamentous therapy is shown. Reliable results of treatment of malignant tumors of gastrointestinal tract are presented

Human Activity Recognition from Smart-Phone Sensor Data using a Multi-Class Ensemble Learning in Home Monitoring.

Science.gov (United States)

Ghose, Soumya; Mitra, Jhimli; Karunanithi, Mohan; Dowling, Jason

2015-01-01

Home monitoring of chronically ill or elderly patient can reduce frequent hospitalisations and hence provide improved quality of care at a reduced cost to the community, therefore reducing the burden on the healthcare system. Activity recognition of such patients is of high importance in such a design. In this work, a system for automatic human physical activity recognition from smart-phone inertial sensors data is proposed. An ensemble of decision trees framework is adopted to train and predict the multi-class human activity system. A comparison of our proposed method with a multi-class traditional support vector machine shows significant improvement in activity recognition accuracies.

Handling Imbalanced Data Sets in Multistage Classification

Science.gov (United States)

López, M.

Multistage classification is a logical approach, based on a divide-and-conquer solution, for dealing with problems with a high number of classes. The classification problem is divided into several sequential steps, each one associated to a single classifier that works with subgroups of the original classes. In each level, the current set of classes is split into smaller subgroups of classes until they (the subgroups) are composed of only one class. The resulting chain of classifiers can be represented as a tree, which (1) simplifies the classification process by using fewer categories in each classifier and (2) makes it possible to combine several algorithms or use different attributes in each stage. Most of the classification algorithms can be biased in the sense of selecting the most populated class in overlapping areas of the input space. This can degrade a multistage classifier performance if the training set sample frequencies do not reflect the real prevalence in the population. Several techniques such as applying prior probabilities, assigning weights to the classes, or replicating instances have been developed to overcome this handicap. Most of them are designed for two-class (accept-reject) problems. In this article, we evaluate several of these techniques as applied to multistage classification and analyze how they can be useful for astronomy. We compare the results obtained by classifying a data set based on Hipparcos with and without these methods.

Feature Genes Selection Using Supervised Locally Linear Embedding and Correlation Coefficient for Microarray Classification.

Science.gov (United States)

Xu, Jiucheng; Mu, Huiyu; Wang, Yun; Huang, Fangzhou

2018-01-01

The selection of feature genes with high recognition ability from the gene expression profiles has gained great significance in biology. However, most of the existing methods have a high time complexity and poor classification performance. Motivated by this, an effective feature selection method, called supervised locally linear embedding and Spearman's rank correlation coefficient (SLLE-SC 2 ), is proposed which is based on the concept of locally linear embedding and correlation coefficient algorithms. Supervised locally linear embedding takes into account class label information and improves the classification performance. Furthermore, Spearman's rank correlation coefficient is used to remove the coexpression genes. The experiment results obtained on four public tumor microarray datasets illustrate that our method is valid and feasible.

Multi-task linear programming discriminant analysis for the identification of progressive MCI individuals.

Science.gov (United States)

Yu, Guan; Liu, Yufeng; Thung, Kim-Han; Shen, Dinggang

2014-01-01

Accurately identifying mild cognitive impairment (MCI) individuals who will progress to Alzheimer's disease (AD) is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET). However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD) analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification) for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF) learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI) subjects and 226 stable MCI (sMCI) subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images) and also the single-task classification method (using only MRI or only subjects with both MRI and PET images

Multi-task linear programming discriminant analysis for the identification of progressive MCI individuals.

Directory of Open Access Journals (Sweden)

Guan Yu

Full Text Available Accurately identifying mild cognitive impairment (MCI individuals who will progress to Alzheimer's disease (AD is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI and fluorodeoxyglucose positron emission tomography (FDG-PET. However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI subjects and 226 stable MCI (sMCI subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images and also the single-task classification method (using only MRI or only subjects with both MRI and

Probability Density Components Analysis: A New Approach to Treatment and Classification of SAR Images

Directory of Open Access Journals (Sweden)

Osmar Abílio de Carvalho Júnior

2014-04-01

Full Text Available Speckle noise (salt and pepper is inherent to synthetic aperture radar (SAR, which causes a usual noise-like granular aspect and complicates the image classification. In SAR image analysis, the spatial information might be a particular benefit for denoising and mapping classes characterized by a statistical distribution of the pixel intensities from a complex and heterogeneous spectral response. This paper proposes the Probability Density Components Analysis (PDCA, a new alternative that combines filtering and frequency histogram to improve the classification procedure for the single-channel synthetic aperture radar (SAR images. This method was tested on L-band SAR data from the Advanced Land Observation System (ALOS Phased-Array Synthetic-Aperture Radar (PALSAR sensor. The study area is localized in the Brazilian Amazon rainforest, northern Rondônia State (municipality of Candeias do Jamari, containing forest and land use patterns. The proposed algorithm uses a moving window over the image, estimating the probability density curve in different image components. Therefore, a single input image generates an output with multi-components. Initially the multi-components should be treated by noise-reduction methods, such as maximum noise fraction (MNF or noise-adjusted principal components (NAPCs. Both methods enable reducing noise as well as the ordering of multi-component data in terms of the image quality. In this paper, the NAPC applied to multi-components provided large reductions in the noise levels, and the color composites considering the first NAPC enhance the classification of different surface features. In the spectral classification, the Spectral Correlation Mapper and Minimum Distance were used. The results obtained presented as similar to the visual interpretation of optical images from TM-Landsat and Google Maps.

A Hierarchical Feature Extraction Model for Multi-Label Mechanical Patent Classification

Directory of Open Access Journals (Sweden)

Jie Hu

2018-01-01

Full Text Available Various studies have focused on feature extraction methods for automatic patent classification in recent years. However, most of these approaches are based on the knowledge from experts in related domains. Here we propose a hierarchical feature extraction model (HFEM for multi-label mechanical patent classification, which is able to capture both local features of phrases as well as global and temporal semantics. First, a n-gram feature extractor based on convolutional neural networks (CNNs is designed to extract salient local lexical-level features. Next, a long dependency feature extraction model based on the bidirectional long–short-term memory (BiLSTM neural network model is proposed to capture sequential correlations from higher-level sequence representations. Then the HFEM algorithm and its hierarchical feature extraction architecture are detailed. We establish the training, validation and test datasets, containing 72,532, 18,133, and 2679 mechanical patent documents, respectively, and then check the performance of HFEMs. Finally, we compared the results of the proposed HFEM and three other single neural network models, namely CNN, long–short-term memory (LSTM, and BiLSTM. The experimental results indicate that our proposed HFEM outperforms the other compared models in both precision and recall.

Multi-asset class mutual funds: Can they time the market? Evidence from the US, UK and Canada

OpenAIRE

Clare, A.; O'Sullivan, N.; Sherman, M.; Thomas, S.

2016-01-01

The importance of asset allocation decisions in wealth management is well established. However, given its importance it is perhaps surprising that so little attention has been paid to the question of whether professional fund managers are skilful at timing market movement across asset classes over time. The timing literature has tended to concentrate on the timing skill of single asset class funds. Using data on US, UK and Canadian multi-asset class funds, we apply two alternative methodologi...

Use of UAV-Borne Spectrometer for Land Cover Classification

Directory of Open Access Journals (Sweden)

Sowmya Natesan

2018-04-01

Full Text Available Unmanned aerial vehicles (UAV are being used for low altitude remote sensing for thematic land classification using visible light and multi-spectral sensors. The objective of this work was to investigate the use of UAV equipped with a compact spectrometer for land cover classification. The UAV platform used was a DJI Flamewheel F550 hexacopter equipped with GPS and Inertial Measurement Unit (IMU navigation sensors, and a Raspberry Pi processor and camera module. The spectrometer used was the FLAME-NIR, a near-infrared spectrometer for hyperspectral measurements. RGB images and spectrometer data were captured simultaneously. As spectrometer data do not provide continuous terrain coverage, the locations of their ground elliptical footprints were determined from the bundle adjustment solution of the captured images. For each of the spectrometer ground ellipses, the land cover signature at the footprint location was determined to enable the characterization, identification, and classification of land cover elements. To attain a continuous land cover classification map, spatial interpolation was carried out from the irregularly distributed labeled spectrometer points. The accuracy of the classification was assessed using spatial intersection with the object-based image classification performed using the RGB images. Results show that in homogeneous land cover, like water, the accuracy of classification is 78% and in mixed classes, like grass, trees and manmade features, the average accuracy is 50%, thus, indicating the contribution of hyperspectral measurements of low altitude UAV-borne spectrometers to improve land cover classification.

Individual motile CD4+ T cells can participate in efficient multi-killing through conjugation to multiple tumor cells

Science.gov (United States)

Liadi, Ivan; Singh, Harjeet; Romain, Gabrielle; Rey-Villamizar, Nicolas; Merouane, Amine; Adolacion, Jay R T.; Kebriaei, Partow; Huls, Helen; Qiu, Peng; Roysam, Badrinath; Cooper, Laurence J.N.; Varadarajan, Navin

2015-01-01

T cells genetically modified to express a CD19-specific chimeric antigen receptor (CAR) for the investigational treatment of B-cell malignancies comprise a heterogeneous population, and their ability to persist and participate in serial killing of tumor cells is a predictor of therapeutic success. We implemented Timelapse Imaging Microscopy In Nanowell Grids (TIMING) to provide direct evidence that CD4+CAR+ T cells (CAR4 cells) can engage in multi-killing via simultaneous conjugation to multiple tumor cells. Comparisons of the CAR4 cells and CD8+CAR+ T cells (CAR8 cells) demonstrate that while CAR4 cells can participate in killing and multi-killing, they do so at slower rates, likely due to the lower Granzyme B content. Significantly, in both sets of T cells, a minor sub-population of individual T cells identified by their high motility, demonstrated efficient killing of single tumor cells. By comparing both the multi-killer and single killer CAR+ T cells it appears that the propensity and kinetics of T-cell apoptosis was modulated by the number of functional conjugations. T cells underwent rapid apoptosis, and at higher frequencies, when conjugated to single tumor cells in isolation and this effect was more pronounced on CAR8 cells. Our results suggest that the ability of CAR+ T cells to participate in multi-killing should be evaluated in the context of their ability to resist activation induced cell death (AICD). We anticipate that TIMING may be utilized to rapidly determine the potency of T-cell populations and may facilitate the design and manufacture of next-generation CAR+ T cells with improved efficacy. PMID:25711538

Vegetation classification and distribution mapping report Mesa Verde National Park

Science.gov (United States)

Thomas, Kathryn A.; McTeague, Monica L.; Ogden, Lindsay; Floyd, M. Lisa; Schulz, Keith; Friesen, Beverly A.; Fancher, Tammy; Waltermire, Robert G.; Cully, Anne

2009-01-01

The classification and distribution mapping of the vegetation of Mesa Verde National Park (MEVE) and surrounding environment was achieved through a multi-agency effort between 2004 and 2007. The National Park Service’s Southern Colorado Plateau Network facilitated the team that conducted the work, which comprised the U.S. Geological Survey’s Southwest Biological Science Center, Fort Collins Research Center, and Rocky Mountain Geographic Science Center; Northern Arizona University; Prescott College; and NatureServe. The project team described 47 plant communities for MEVE, 34 of which were described from quantitative classification based on f eld-relevé data collected in 1993 and 2004. The team derived 13 additional plant communities from field observations during the photointerpretation phase of the project. The National Vegetation Classification Standard served as a framework for classifying these plant communities to the alliance and association level. Eleven of the 47 plant communities were classified as “park specials;” that is, plant communities with insufficient data to describe them as new alliances or associations. The project team also developed a spatial vegetation map database representing MEVE, with three different map-class schemas: base, group, and management map classes. The base map classes represent the fi nest level of spatial detail. Initial polygons were developed using Definiens Professional (at the time of our use, this software was called eCognition), assisted by interpretation of 1:12,000 true-color digital orthophoto quarter quadrangles (DOQQs). These polygons (base map classes) were labeled using manual photo interpretation of the DOQQs and 1:12,000 true-color aerial photography. Field visits verified interpretation concepts. The vegetation map database includes 46 base map classes, which consist of associations, alliances, and park specials classified with quantitative analysis, additional associations and park specials noted

BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

Science.gov (United States)

Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

2018-04-11

The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes

Radon classification of building ground

International Nuclear Information System (INIS)

Slunga, E.

1988-01-01

The Laboratories of Building Technology and Soil Mechanics and Foundation Engineering at the Helsinki University of Technology in cooperation with The Ministry of the Environment have proposed a radon classification for building ground. The proposed classification is based on the radon concentration in soil pores and on the permeability of the foundation soil. The classification includes four radon classes: negligible, normal, high and very high. Depending on the radon class the radon-technical solution for structures is chosen. It is proposed that the classification be done in general terms in connection with the site investigations for the planning of land use and in more detail in connection with the site investigations for an individual house. (author)

Optimizing solubility and permeability of a biopharmaceutics classification system (BCS) class 4 antibiotic drug using lipophilic fragments disturbing the crystal lattice.

Science.gov (United States)

Tehler, Ulrika; Fagerberg, Jonas H; Svensson, Richard; Larhed, Mats; Artursson, Per; Bergström, Christel A S

2013-03-28

Esterification was used to simultaneously increase solubility and permeability of ciprofloxacin, a biopharmaceutics classification system (BCS) class 4 drug (low solubility/low permeability) with solid-state limited solubility. Molecular flexibility was increased to disturb the crystal lattice, lower the melting point, and thereby improve the solubility, whereas lipophilicity was increased to enhance the intestinal permeability. These structural changes resulted in BCS class 1 analogues (high solubility/high permeability) emphasizing that simple medicinal chemistry may improve both these properties.

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification.

Directory of Open Access Journals (Sweden)

Cuihong Wen

Full Text Available Optical Music Recognition (OMR has received increasing attention in recent years. In this paper, we propose a classifier based on a new method named Directed Acyclic Graph-Large margin Distribution Machine (DAG-LDM. The DAG-LDM is an improvement of the Large margin Distribution Machine (LDM, which is a binary classifier that optimizes the margin distribution by maximizing the margin mean and minimizing the margin variance simultaneously. We modify the LDM to the DAG-LDM to solve the multi-class music symbol classification problem. Tests are conducted on more than 10000 music symbol images, obtained from handwritten and printed images of music scores. The proposed method provides superior classification capability and achieves much higher classification accuracy than the state-of-the-art algorithms such as Support Vector Machines (SVMs and Neural Networks (NNs.

Neuroendocrine Tumors of the Lung

Energy Technology Data Exchange (ETDEWEB)

Fisseler-Eckhoff, Annette, E-mail: Annette.Fisseler-Eckhoff@hsk-wiesbaden.de; Demes, Melanie [Department of Pathology und Cytology, Dr. Horst-Schmidt-Kliniken (HSK), Wiesbaden 65199 (Germany)

2012-07-31

Neuroendocrine tumors may develop throughout the human body with the majority being found in the gastrointestinal tract and bronchopulmonary system. Neuroendocrine tumors are classified according to the grade of biological aggressiveness (G1–G3) and the extent of differentiation (well-differentiated/poorly-differentiated). The well-differentiated neoplasms comprise typical (G1) and atypical (G2) carcinoids. Large cell neuroendocrine carcinomas as well as small cell carcinomas (G3) are poorly-differentiated. The identification and differentiation of atypical from typical carcinoids or large cell neuroendocrine carcinomas and small cell carcinomas is essential for treatment options and prognosis. Pulmonary neuroendocrine tumors are characterized according to the proportion of necrosis, the mitotic activity, palisading, rosette-like structure, trabecular pattern and organoid nesting. The given information about the histopathological assessment, classification, prognosis, genetic aberration as well as treatment options of pulmonary neuroendocrine tumors are based on own experiences and reviewing the current literature available. Most disagreements among the classification of neuroendocrine tumor entities exist in the identification of typical versus atypical carcinoids, atypical versus large cell neuroendocrine carcinomas and large cell neuroendocrine carcinomas versus small cell carcinomas. Additionally, the classification is restricted in terms of limited specificity of immunohistochemical markers and possible artifacts in small biopsies which can be compressed in cytological specimens. Until now, pulmonary neuroendocrine tumors have been increasing in incidence. As compared to NSCLCs, only little research has been done with respect to new molecular targets as well as improving the classification and differential diagnosis of neuroendocrine tumors of the lung.

Training echo state networks for rotation-invariant bone marrow cell classification.

Science.gov (United States)

Kainz, Philipp; Burgsteiner, Harald; Asslaber, Martin; Ahammer, Helmut

2017-01-01

The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.

Developing multi-cellular tumor spheroid model (MCTS) in the chitosan/collagen/alginate (CCA) fibrous scaffold for anticancer drug screening

Energy Technology Data Exchange (ETDEWEB)

Wang, Jian-Zheng, E-mail: wppzheng@126.com [Laboratory of Biomedical Material Engineering, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, 457 Zhongshan Road, Dalian 116023 (China); Affiliated General Hospital, Tianguan Group Co., Ltd, Nanyang 473000 (China); Testing Center of Henan Tianguan Group Co., Ltd, Nanyang 473000 (China); Zhu, Yu-Xia [Laboratory of Biomedical Material Engineering, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, 457 Zhongshan Road, Dalian 116023 (China); Affiliated General Hospital, Tianguan Group Co., Ltd, Nanyang 473000 (China); Testing Center of Henan Tianguan Group Co., Ltd, Nanyang 473000 (China); Ma, Hui-Chao; Chen, Si-Nan; Chao, Ji-Ye; Ruan, Wen-Ding; Wang, Duo; Du, Feng-guang [Affiliated General Hospital, Tianguan Group Co., Ltd, Nanyang 473000 (China); Testing Center of Henan Tianguan Group Co., Ltd, Nanyang 473000 (China); Meng, Yue-Zhong [State Key Laboratory of Optoelectronic Materials and Technologies, Sun Yat-sen University, Guangzhou 510275 (China)

2016-05-01

In this work, a 3D MCTS-CCA system was constructed by culturing multi-cellular tumor spheroid (MCTS) in the chitosan/collagen/alginate (CCA) fibrous scaffold for anticancer drug screening. The CCA scaffolds were fabricated by spray-spinning. The interactions between the components of the spray-spun fibers were evidenced by methods of Coomassie Blue stain, X-ray diffraction (XRD) and Fourier transform-infrared spectroscopy (FTIR). Co-culture indicated that MCF-7 cells showed a spatial growth pattern of multi-cellular tumor spheroid (MCTS) in the CCA fibrous scaffold with increased proliferation rate and drug-resistance to MMC, ADM and 5-Aza comparing with the 2D culture cells. Significant increases of total viable cells were found in 3D MCTS groups after drug administration by method of apoptotic analysis. Glucose–lactate analysis indicated that the metabolism of MCTS in CCA scaffold was closer to the tumor issue in vivo than the monolayer cells. In addition, MCTS showed the characteristic of epithelial mesenchymal transition (EMT) which is subverted by carcinoma cells to facilitate metastatic spread. These results demonstrated that MCTS in CCA scaffold possessed a more conservative phenotype of tumor than monolayer cells, and anticancer drug screening in 3D MCTS-CCA system might be superior to the 2D culture system. - Highlights: • Chitosan/collagen/alginate (CCA) scaffolds were fabricated by spray-spinning. • MCF-7 cells presented a multi-cellular tumor spheroid model (MCTS) in CCA scaffold. • MCTS in CCA possessed a more conservative phenotype of tumor than monolayer cells. • Anticancer drug screening in MCTS-CCA system is superior to 2D culture system.

Developing multi-cellular tumor spheroid model (MCTS) in the chitosan/collagen/alginate (CCA) fibrous scaffold for anticancer drug screening

International Nuclear Information System (INIS)

Wang, Jian-Zheng; Zhu, Yu-Xia; Ma, Hui-Chao; Chen, Si-Nan; Chao, Ji-Ye; Ruan, Wen-Ding; Wang, Duo; Du, Feng-guang; Meng, Yue-Zhong

2016-01-01

In this work, a 3D MCTS-CCA system was constructed by culturing multi-cellular tumor spheroid (MCTS) in the chitosan/collagen/alginate (CCA) fibrous scaffold for anticancer drug screening. The CCA scaffolds were fabricated by spray-spinning. The interactions between the components of the spray-spun fibers were evidenced by methods of Coomassie Blue stain, X-ray diffraction (XRD) and Fourier transform-infrared spectroscopy (FTIR). Co-culture indicated that MCF-7 cells showed a spatial growth pattern of multi-cellular tumor spheroid (MCTS) in the CCA fibrous scaffold with increased proliferation rate and drug-resistance to MMC, ADM and 5-Aza comparing with the 2D culture cells. Significant increases of total viable cells were found in 3D MCTS groups after drug administration by method of apoptotic analysis. Glucose–lactate analysis indicated that the metabolism of MCTS in CCA scaffold was closer to the tumor issue in vivo than the monolayer cells. In addition, MCTS showed the characteristic of epithelial mesenchymal transition (EMT) which is subverted by carcinoma cells to facilitate metastatic spread. These results demonstrated that MCTS in CCA scaffold possessed a more conservative phenotype of tumor than monolayer cells, and anticancer drug screening in 3D MCTS-CCA system might be superior to the 2D culture system. - Highlights: • Chitosan/collagen/alginate (CCA) scaffolds were fabricated by spray-spinning. • MCF-7 cells presented a multi-cellular tumor spheroid model (MCTS) in CCA scaffold. • MCTS in CCA possessed a more conservative phenotype of tumor than monolayer cells. • Anticancer drug screening in MCTS-CCA system is superior to 2D culture system.

7 CFR 28.911 - Review classification.

Science.gov (United States)

2010-01-01

... 7 Agriculture 2 2010-01-01 2010-01-01 false Review classification. 28.911 Section 28.911... REGULATIONS COTTON CLASSING, TESTING, AND STANDARDS Cotton Classification and Market News Service for Producers Classification § 28.911 Review classification. (a) A producer may request one review...

Zone-specific logistic regression models improve classification of prostate cancer on multi-parametric MRI

Energy Technology Data Exchange (ETDEWEB)

Dikaios, Nikolaos; Halligan, Steve; Taylor, Stuart; Atkinson, David; Punwani, Shonit [University College London, Centre for Medical Imaging, London (United Kingdom); University College London Hospital, Departments of Radiology, London (United Kingdom); Alkalbani, Jokha; Sidhu, Harbir Singh [University College London, Centre for Medical Imaging, London (United Kingdom); Abd-Alazeez, Mohamed; Ahmed, Hashim U.; Emberton, Mark [University College London, Research Department of Urology, Division of Surgery and Interventional Science, London (United Kingdom); Kirkham, Alex [University College London Hospital, Departments of Radiology, London (United Kingdom); Freeman, Alex [University College London Hospital, Department of Histopathology, London (United Kingdom)

2015-09-15

To assess the interchangeability of zone-specific (peripheral-zone (PZ) and transition-zone (TZ)) multiparametric-MRI (mp-MRI) logistic-regression (LR) models for classification of prostate cancer. Two hundred and thirty-one patients (70 TZ training-cohort; 76 PZ training-cohort; 85 TZ temporal validation-cohort) underwent mp-MRI and transperineal-template-prostate-mapping biopsy. PZ and TZ uni/multi-variate mp-MRI LR-models for classification of significant cancer (any cancer-core-length (CCL) with Gleason > 3 + 3 or any grade with CCL ≥ 4 mm) were derived from the respective cohorts and validated within the same zone by leave-one-out analysis. Inter-zonal performance was tested by applying TZ models to the PZ training-cohort and vice-versa. Classification performance of TZ models for TZ cancer was further assessed in the TZ validation-cohort. ROC area-under-curve (ROC-AUC) analysis was used to compare models. The univariate parameters with the best classification performance were the normalised T2 signal (T2nSI) within the TZ (ROC-AUC = 0.77) and normalized early contrast-enhanced T1 signal (DCE-nSI) within the PZ (ROC-AUC = 0.79). Performance was not significantly improved by bi-variate/tri-variate modelling. PZ models that contained DCE-nSI performed poorly in classification of TZ cancer. The TZ model based solely on maximum-enhancement poorly classified PZ cancer. LR-models dependent on DCE-MRI parameters alone are not interchangeable between prostatic zones; however, models based exclusively on T2 and/or ADC are more robust for inter-zonal application. (orig.)

Automatic classification of time-variable X-ray sources

Energy Technology Data Exchange (ETDEWEB)

Lo, Kitty K.; Farrell, Sean; Murphy, Tara; Gaensler, B. M. [Sydney Institute for Astronomy, School of Physics, The University of Sydney, Sydney, NSW 2006 (Australia)

2014-05-01

To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of supervised classification is suitable for this problem. Here, we present a supervised learning method to automatically classify variable X-ray sources in the Second XMM-Newton Serendipitous Source Catalog (2XMMi-DR2). Random Forest is our classifier of choice since it is one of the most accurate learning algorithms available. Our training set consists of 873 variable sources and their features are derived from time series, spectra, and other multi-wavelength contextual information. The 10 fold cross validation accuracy of the training data is ∼97% on a 7 class data set. We applied the trained classification model to 411 unknown variable 2XMM sources to produce a probabilistically classified catalog. Using the classification margin and the Random Forest derived outlier measure, we identified 12 anomalous sources, of which 2XMM J180658.7–500250 appears to be the most unusual source in the sample. Its X-ray spectra is suggestive of a ultraluminous X-ray source but its variability makes it highly unusual. Machine-learned classification and anomaly detection will facilitate scientific discoveries in the era of all-sky surveys.

Automatic classification of time-variable X-ray sources

International Nuclear Information System (INIS)

Lo, Kitty K.; Farrell, Sean; Murphy, Tara; Gaensler, B. M.

2014-01-01

To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of supervised classification is suitable for this problem. Here, we present a supervised learning method to automatically classify variable X-ray sources in the Second XMM-Newton Serendipitous Source Catalog (2XMMi-DR2). Random Forest is our classifier of choice since it is one of the most accurate learning algorithms available. Our training set consists of 873 variable sources and their features are derived from time series, spectra, and other multi-wavelength contextual information. The 10 fold cross validation accuracy of the training data is ∼97% on a 7 class data set. We applied the trained classification model to 411 unknown variable 2XMM sources to produce a probabilistically classified catalog. Using the classification margin and the Random Forest derived outlier measure, we identified 12 anomalous sources, of which 2XMM J180658.7–500250 appears to be the most unusual source in the sample. Its X-ray spectra is suggestive of a ultraluminous X-ray source but its variability makes it highly unusual. Machine-learned classification and anomaly detection will facilitate scientific discoveries in the era of all-sky surveys.

Classification in Astronomy: Past and Present

Science.gov (United States)

Feigelson, Eric

2012-03-01

Astronomers have always classified celestial objects. The ancient Greeks distinguished between asteros, the fixed stars, and planetos, the roving stars. The latter were associated with the Gods and, starting with Plato in his dialog Timaeus, provided the first mathematical models of celestial phenomena. Giovanni Hodierna classified nebulous objects, seen with a Galilean refractor telescope in the mid-seventeenth century into three classes: "Luminosae," "Nebulosae," and "Occultae." A century later, Charles Messier compiled a larger list of nebulae, star clusters and galaxies, but did not attempt a classification. Classification of comets was a significant enterprise in the 19th century: Alexander (1850) considered two groups based on orbit sizes, Lardner (1853) proposed three groups of orbits, and Barnard (1891) divided them into two classes based on morphology. Aside from the segmentation of the bright stars into constellations, most stellar classifications were based on colors and spectral properties. During the 1860s, the pioneering spectroscopist Angelo Secchi classified stars into five classes: white, yellow, orange, carbon stars, and emission line stars. After many debates, the stellar spectral sequence was refined by the group at Harvard into the familiar OBAFGKM spectral types, later found to be a sequence on surface temperature (Cannon 1926). The spectral classification is still being extended with recent additions of O2 hot stars (Walborn et al. 2002) and L and T brown dwarfs (Kirkpatrick 2005). Townley (1913) reviews 30 years of variable star classification, emerging with six classes with five subclasses. The modern classification of variable stars has about 80 (sub)classes, and is still under debate (Samus 2009). Shortly after his confirmation that some nebulae are external galaxies, Edwin Hubble (1926) proposed his famous bifurcated classification of galaxy morphologies with three classes: ellipticals, spirals, and irregulars. These classes are still