A Review Comparative Mamography Image Analysis on Modified CNN Deep Learning Method

Abstract

This study aims to review classification of breast abnormality acuracy on deep learing using comparative CNN development of concepts and models in various cases and implementation. The CNN based breast mass detection approach to simultaneously localize and classify the mass into either benign or malignant abnormality by exploring all major types of medical image modalities that collected on dataset and hospital. This CNN method modified to R-CNN and SD-CNN based on modification on feature extraction to improve acuracy level. R-CNN adopt RPN and ROI for Feature extraction. The model designed, trained and evaluated to achieved detection acuracy. The proposed model on R-CNN achieved detection accuracy of up to 91.86%, sensitivity of 94.67% and AUC-ROC of 92.2%. SD-CNN study the two-fold applicability of CNN to improve the breast cancer diagnosis. This method recombined images from CEDM in helping the diagnosis of breast lessons using a Deep-CNN method with virtual feature image. The experiment shows the features from LE images can achieve from accuracy of 0.85 and AUC of 0.84, then when adding the recombined imaging features, model performance improves to accuracy of 0.89 with AUC of 0.91 until 0.92