Journal ArticleDOI
Analysis of Co-Occurrence Texture Statistics as a Function of Gray-Level Quantization for Classifying Breast Ultrasound
Reads0
Chats0
TLDR
It was observed that averaging texture descriptors of a same distance impacts negatively the classification performance, while regarding the single texture features, the quantization level does not impact the discrimination power, since AUC=0.87 was obtained for the six quantization levels.Abstract:
In this paper, we investigated the behavior of 22 co-occurrence statistics combined to six gray-scale quantization levels to classify breast lesions on ultrasound (BUS) images. The database of 436 BUS images used in this investigation was formed by 217 carcinoma and 219 benign lesions images. The region delimited by a minimum bounding rectangle around the lesion was employed to calculate the gray-level co-occurrence matrix (GLCM). Next, 22 co-occurrence statistics were computed regarding six quantization levels (8, 16, 32, 64, 128, and 256), four orientations (0° , 45° , 90° , and 135° ), and ten distances (1, 2,...,10 pixels). Also, to reduce feature space dimensionality, texture descriptors of the same distance were averaged over all orientations, which is a common practice in the literature. Thereafter, the feature space was ranked using mutual information technique with minimal-redundancy-maximal-relevance (mRMR) criterion. Fisher linear discriminant analysis (FLDA) was applied to assess the discrimination power of texture features, by adding the first m-ranked features to the classification procedure iteratively until all of them were considered. The area under ROC curve (AUC) was used as figure of merit to measure the performance of the classifier. It was observed that averaging texture descriptors of a same distance impacts negatively the classification performance, since the best AUC of 0.81 was achieved with 32 gray levels and 109 features. On the other hand, regarding the single texture features (i.e., without averaging procedure), the quantization level does not impact the discrimination power, since AUC=0.87 was obtained for the six quantization levels. Moreover, the number of features was reduced (between 17 and 24 features). The texture descriptors that contributed notably to distinguish breast lesions were contrast and correlation computed from GLCMs with orientation of 90° and distance more than five pixels.read more
Citations
More filters
Journal ArticleDOI
Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans
Jie-Zhi Cheng,Dong Ni,Yi-Hong Chou,Jing Qin,Chui Mei Tiu,Yeun-Chung Chang,Chiun-Sheng Huang,Dinggang Shen,Chung-Ming Chen +8 more
TL;DR: The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.
Journal ArticleDOI
A deep learning framework for supporting the classification of breast lesions in ultrasound images.
Seokmin Han,Ho-kyung Kang,Ja-Yeon Jeong,Moon-Ho Park,Wonsik Kim,Won-Chul Bang,Yeong Kyeong Seong +6 more
TL;DR: The proposed method can work in tandem with human radiologists to improve performance, which is a fundamental purpose of computer-aided diagnosis.
Journal ArticleDOI
Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review
TL;DR: This review provides a review of ultrasound-guided, breast biopsy and the fusion of ultrasound with other imaging modalities, especially magnetic resonance imaging (MRI), and discusses their future directions.
Journal ArticleDOI
Coronavirus disease (COVID-19) detection in Chest X-Ray images using majority voting based classifier ensemble
TL;DR: An automatic COVID screening (ACoS) system that uses radiomic texture descriptors extracted from CXR images to identify the normal, suspected, and nCOVID-19 infected patients is presented.
Journal ArticleDOI
A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling.
Stefan Leger,Stefan Leger,Alex Zwanenburg,K. Pilz,Fabian Lohaus,Annett Linge,Klaus Zöphel,Klaus Zöphel,Jörg Kotzerke,Jörg Kotzerke,Andreas Schreiber,Inge Tinhofer,Inge Tinhofer,Volker Budach,Volker Budach,Ali Sak,Ali Sak,Martin Stuschke,Martin Stuschke,Panagiotis Balermpas,Panagiotis Balermpas,Claus Rödel,Claus Rödel,Ute Ganswindt,Ute Ganswindt,Claus Belka,Steffi Pigorsch,Steffi Pigorsch,Stephanie E. Combs,Stephanie E. Combs,David Mönnich,David Mönnich,Daniel Zips,Daniel Zips,Mechthild Krause,Michael Baumann,Esther G.C. Troost,Steffen Löck,Steffen Löck,Steffen Löck,Christian Richter +40 more
TL;DR: A subset of algorithms are identified which should be considered in future radiomics studies to develop stable and clinically relevant predictive models for time-to-event endpoints.
References
More filters
Journal ArticleDOI
Textural Features for Image Classification
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Journal ArticleDOI
An introduction to ROC analysis
TL;DR: The purpose of this article is to serve as an introduction to ROC graphs and as a guide for using them in research.
Journal ArticleDOI
Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy
TL;DR: In this article, the maximal statistical dependency criterion based on mutual information (mRMR) was proposed to select good features according to the maximal dependency condition. But the problem of feature selection is not solved by directly implementing mRMR.
Feature selection based on mutual information: criteria ofmax-dependency, max-relevance, and min-redundancy
TL;DR: This work derives an equivalent form, called minimal-redundancy-maximal-relevance criterion (mRMR), for first-order incremental feature selection, and presents a two-stage feature selection algorithm by combining mRMR and other more sophisticated feature selectors (e.g., wrappers).
Book ChapterDOI
Supervised and unsupervised discretization of continuous features
TL;DR: Binning, an unsupervised discretization method, is compared to entropy-based and purity-based methods, which are supervised algorithms, and it is found that the performance of the Naive-Bayes algorithm significantly improved when features were discretized using an entropy- based method.
Related Papers (5)
Automated breast cancer detection and classification using ultrasound images: A survey
Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices
Leen-Kiat Soh,Costas Tsatsoulis +1 more