Breast Cancer Classification using Global Discriminate Features in Mammographic Images

Abstract

Breast cancer has become a rapidly prevailing disease among women all over the world. In term of mortality, it is considered to be the second leading cause of death. Death risk can be reduced by early stage detection, followed by a suitable treatment procedure. Contemporary literature shows that mammographic imaging is widely used for premature discovery of breast cancer. In this paper, we propose an efficient Computer Aided Diagnostic (CAD) system for the detection of breast cancer using mammography images. The CAD system extracts largely discriminating features on the global level for representation of target categories in two sets: all 20 extracted features and top 7 ranked features among them. Texture characteristics using cooccurrence matrices are calculated via the single offset vector. Multilayer perceptron neural network with optimized architecture is fed with individual feature sets and results are produced. Data division corresponds as 60%, 20%, and 20% is used for training, cross-validation, and test purposes, respectively. Robust results are achieved and presented after rotating the data up to five times, which shows higher than 99% accuracy for both target categories, and hence outperform the existing solutions.

A Wrapper based feature extraction framework based on AlexNet deep convolutional neural network parameters optimized using gradient‐based optimizer for mammogram images

“…There are numerous breast cancer classification processes that are mentioned on literature review, 13,[26][27][28][29][30][31][32][33][34][35][36] which methods have some limitations, like low detection rate of benign samples likened with high fraction, the accuracy of Benign is obviously categorize and diminish that accuracy of malignant, some processes do not obviously categorize malignant and benign display the accuracy of normal region, certain approaches display the accuracy of image. In this process it overcomes all these problems and provides more precision.…”

“…• Then the efficiency of proposed method is likened with existing methods such as Digital mammogram images utilizing 2D-BDWT and GLCM features through FOA-based feature selection method (FE-2-D-BDWT-GLCM-FOA-SVM), 39 classification of mammograms depend features removal processes with support vector machine (FE-LBP-GLCM-SVM), 33 breast cancer classification with global discriminate on mammographic images (FE-GLCM-ANN), 34 pectoral muscle removal in mammographic images (FE-SMOTE-RF), 35 application of artificial intelligence depend deep learning on breast cancer and imaging diagnosis (FE-CNN-CDCNN) 36 respectively.…”

“…Tariq et al, 34 have suggested a classification of breast cancer through global discrimination features on mammographic images. An efficient computer aided diagnostic (CAD) system for breast cancer detection with mammography images is presented in this paper.…”

“…The key contributions of this manuscript are abridged beneath: In this manuscript, a Wrapper based feature extraction framework depend ADCNN with GBO is proposed for early detection of breast cancer. The input images are occupied as mini‐MIAS database. Then the images are pre‐processed to eliminate that noises using MRF method. Image features are extracted by the process of Wrapper based feature extraction framework with ADCNN. Then, the weight parameters of ADCNN are optimizing with the aid of GBO 37,38 Then the mammogram images are characterized as normal or abnormal (malignant and benign) with SVM classifier. The aim of this work is to detect abnormal tissue present in breast cancer mammogram images through process of screening programs and increase the accuracy. The simulation process is implemented on MATLAB platform. The competence of proposed FE‐ADCNN‐GBO‐SVM approach is evaluated using number of programs that evaluate metrics such as accuracy, sensitivity, specificity and f‐score. Then the efficiency of proposed method is likened with existing methods such as Digital mammogram images utilizing 2D‐BDWT and GLCM features through FOA‐based feature selection method (FE‐2‐D‐BDWT‐GLCM‐FOA‐SVM), 39 classification of mammograms depend features removal processes with support vector machine (FE‐LBP‐GLCM‐SVM), 33 breast cancer classification with global discriminate on mammographic images (FE‐GLCM‐ANN), 34 pectoral muscle removal in mammographic images (FE‐SMOTE‐RF), 35 application of artificial intelligence depend deep learning on breast cancer and imaging diagnosis (FE‐CNN‐CDCNN) 36 respectively. Remaining manuscript is stated beneath. Section 2 outlines literature survey.…”

Presentation of Novel Hybrid Algorithm for Detection and Classification of Breast Cancer Using Growth Region Method and Probabilistic Neural Network

“…Tariq et al [ 25 ] conducted a study to classify mammographic images of breast cancer. GLCM algorithm was used to extract texture-type features from images.…”