BREAST CANCER CLASSIFICATION ON ENHANCED SEGMENTED MAMMOGRAMS USING OPTIMIZED CONVOLUTIONAL NEURAL NETWORKS

Breast cancer ranks as the second most common malignancy among women and second-most reason for deaths worldwide. Digital Mammogram screening can offer low-cost early diagnosis reduce breast fatality rate victims. This research aims to build a model that automatically assists in classifying malignant benign lesions depicted on digital mammograms without any human interventions. The Mammographic Image Analysis Society (mini-MIAS) image dataset, which contains 322 mammograms, is employed present study. focuses Background Preserved Feature-Oriented Contrast Improvement (BPFO-CI) method contrast enhancement uses Weighted Cumulative Distribution Function. Region of Interest (RoI) then extracted from improved using Thresholding Segmentation method. Then RoIs are used input classification optimal Convolutional Neural Networks (CNN). Data augmentation applied pre-processed dataset. suggested CNN model's performance compared various algorithms pertaining accuracy confusion matrix. simulation results confirm importance effectiveness comparison other well-known conventional approaches. As result, this predicted aid cancer.