Breast tumor classification in ultrasound images using texture analysis and super-resolution methods
TL;DR: It is shown that the super-resolution-based approach improves the performance of the evaluated texture methods and thus outperforms the state of the art in benign/malignant tumor classification.
About: This article is published in Engineering Applications of Artificial Intelligence.The article was published on 2017-03-01. It has received 89 citations till now. The article focuses on the topics: Local binary patterns & Phase congruency.
Citations
More filters
TL;DR: A general analysis of the current status of CAD systems according to the used image modalities and the machine learning based classifiers is provided.
245 citations
TL;DR: This study aims at presenting a review that shows the new applications of machine learning and deep learning technology for detecting and classifying breast cancer and provides an overview of progress and the future trends and challenges in the classification and detection of breast cancer.
Abstract: Breast cancer is the second leading cause of death for women, so accurate early detection can help decrease breast cancer mortality rates. Computer-aided detection allows radiologists to detect abnormalities efficiently. Medical images are sources of information relevant to the detection and diagnosis of various diseases and abnormalities. Several modalities allow radiologists to study the internal structure, and these modalities have been met with great interest in several types of research. In some medical fields, each of these modalities is of considerable significance. This study aims at presenting a review that shows the new applications of machine learning and deep learning technology for detecting and classifying breast cancer and provides an overview of progress in this area. This review reflects on the classification of breast cancer utilizing multi-modalities medical imaging. Details are also given on techniques developed to facilitate the classification of tumors, non-tumors, and dense masses in various medical imaging modalities. It first provides an overview of the different approaches to machine learning, then an overview of the different deep learning techniques and specific architectures for the detection and classification of breast cancer. We also provide a brief overview of the different image modalities to give a complete overview of the area. In the same context, this review was performed using a broad variety of research databases as a source of information for access to various field publications. Finally, this review summarizes the future trends and challenges in the classification and detection of breast cancer.
164 citations
TL;DR: This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years and introduced the major feature and the classifier employed by the traditional ultrasound CAD and the deep learning ultrasound CAD.
Abstract: The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.
152 citations
Cites methods from "Breast tumor classification in ultr..."
...In this approach, every 3 × 3 neighborhood will be transformed into an 8-bit binary number [34]....
[...]
TL;DR: Comparative analyses validate that the proposed HSI SR method enhances the spatial information better than the state-of-arts methods, with spectral information preserving simultaneously.
112 citations
TL;DR: Various performance measures like classification accuracy, sensitivity, specificity, confusion matrices, a statistical test and the area under the receiver operating characteristic (AUC) are reported to show the superiority of the proposed method as compared to classical models.
Abstract: Breast cancer is a decisive disease worldwide It is one of the most widely spread cancer among women As per the survey, one out of eight women in the world are at risk of breast cancer at some point of time in her life One of the methods to reduce breast cancer mortality rate is timely detection and effective treatment That is why, more accurate classification of a breast cancer tumor has become a challenging problem in the medical field Many classification techniques are proposed in the literature Today, expert systems and machine learning techniques are being extensively used in the breast cancer classification problem They provide high classification accuracy and effective diagnostic capabilities In this paper, we have proposed a novel Gauss-Newton representation based algorithm (GNRBA) for breast cancer classification It uses the sparse representation with training sample selection Until now, sparse representation has been successfully applied in pattern recognition only The proposed method introduces a novel Gauss-Newton based approach to find the optimal weights for the training samples for classification In addition, it evaluates the sparsity in a computationally efficient way as compared to the conventional l1-norm method The effectiveness of the GNRBA is examined on the Wisconsin Breast Cancer Database (WBCD) and the Wisconsin Diagnosis Breast Cancer (WDBC) database from the UCI Machine Learning repository Various performance measures like classification accuracy, sensitivity, specificity, confusion matrices, a statistical test and the area under the receiver operating characteristic (AUC) are reported to show the superiority of the proposed method as compared to classical models The experimental results show that the proposed GNRBA could be a good alternative for breast cancer classification for clinical experts
77 citations
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
"Breast tumor classification in ultr..." refers background or methods in this paper
...Classification stage A random forest (RF) classifier is an ensemble learning method that operates by constructing a multitude of decision trees at the training stage and producing the class that is the mode of the classes output by the individual trees at the test stage (Breiman, 2001)....
[...]
...According to Breiman (2001), each tree is trained using 2/3 of the total training data....
[...]
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
31,952 citations
"Breast tumor classification in ultr..." refers methods in this paper
...HOG is a robust feature extraction method as it produces distinctive features in the case of illumination changes (Dalal and Triggs, 2005)....
[...]
...Histogram of oriented gradients (HOG) HOG is a robust feature extraction method as it produces distinctive features in the case of illumination changes (Dalal and Triggs, 2005)....
[...]
01 Nov 1973
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.
Abstract: Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.
20,442 citations
"Breast tumor classification in ultr..." refers background or methods in this paper
...In the GLCM the distribution of co-occurring grey level values in a given direction and at a given distance is computed (Haralick et al., 1973)....
[...]
...The GLCM features and their mathematical expressions are listed in Table 1 (Haralick et al., 1973; Soh and Tsatsoulis, 1999; Clausi, 2002)....
[...]
...Gray level co-occurrence matrix In the GLCM the distribution of co-occurring grey level values in a given direction and at a given distance is computed (Haralick et al., 1973)....
[...]
...Appendix The mathematical expressions used to calculate the GLCM features are listed in Table 7 (Haralick et al., 1973; Soh and Tsatsoulis, 1999)....
[...]
...The mathematical expressions used to calculate the GLCM features are listed in Table 7 (Haralick et al., 1973; Soh and Tsatsoulis, 1999)....
[...]
TL;DR: A generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis.
Abstract: Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.
14,245 citations
"Breast tumor classification in ultr..." refers methods in this paper
...LBP is a grey scale invariant texture analysis method that labels the pixels of an image by comparing a q q× neighborhood surrounding each pixel with the value of that pixel (Ojala et al., 2002)....
[...]
...Local binary pattern LBP is a grey scale invariant texture analysis method that labels the pixels of an image by comparing a q q × neighborhood surrounding each pixel with the value of that pixel (Ojala et al., 2002)....
[...]
01 Jul 1984
TL;DR: A blend of erudition (fascinating and sometimes obscure historical minutiae abound), popularization (mathematical rigor is relegated to appendices) and exposition (the reader need have little knowledge of the fields involved) is presented in this article.
Abstract: "...a blend of erudition (fascinating and sometimes obscure historical minutiae abound), popularization (mathematical rigor is relegated to appendices) and exposition (the reader need have little knowledge of the fields involved) ...and the illustrations include many superb examples of computer graphics that are works of art in their own right." Nature
7,560 citations