DEVELOPMENT OF A CNN-BASED DEEP LEARNING MODEL FOR BREAST CANCER SCREENING AND DIAGNOSIS
Satish L Yedage, Indrabhan S. Borse, Balveer Singh · 2025
Breast cancer remains one of the leading causes of mortality among women worldwide, where early detection and accurate classification are pivotal for effective treatment and improved survival rates.This research presents a novel Convolutional Neural Network (CNN)-based deep learning framework for the automated detection and multi-class classification of breast cancer using mammogram images.The proposed architecture is designed to extract hierarchical features from the input mammograms and classify them into normal, benign, and malignant categories with high precision.The system is trained and evaluated on the publicly available Digital Database for Screening Mammography (DDSM), which provides high-quality grayscale mammogram images.A comprehensive preprocessing pipeline including image resizing, normalization, and augmentation was implemented to enhance model generalization.The CNN architecture comprises three convolutional blocks followed by Satish L Yedage, Indrabhan S. Borse, Balveer Singh https://iaeme.com/Home/journal/IJAIMED22 [email protected], fully connected layers, and a softmax output layer.Experimental results demonstrate that the proposed model achieves superior performance with an accuracy of 94.2%, F1-score of 93.7%, and an AUC of 0.961, outperforming several existing deep learning models including VGG16, ResNet50, DenseNet121, and InceptionV3.A comparative analysis and ablation study validate the robustness and effectiveness of the proposed method.These results suggest that the proposed CNN framework holds significant promise as a clinical decision support tool for radiologists, reducing diagnostic errors and aiding in early breast cancer diagnosis.