Breast Cancer Detection Using Deep Learning

Breast cancer, a potentially life-threatening disease, highlights the crucial need for early and accurate detection. This study investigates the application of deep learning methods, particularly CNN and the VGG19 architecture, for automated breast cancer detection using the MIAS dataset. The primary aim is to utilize CNNs and VGG19 to improve the accuracy and efficiency of early diagnosis by learning hierarchical representations of mammographic images. The MIAS dataset, a standard in mammography research, offers annotated mammograms for training and evaluation. Preprocessing techniques like image normalization and augmentation are employed to optimize model performance. The results demonstrate the efficacy of the proposed models, showing high sensitivity and specificity in distinguishing between benign and malignant lesions. Specifically, the CNN model achieves an impressive accuracy of 98%, while the VGG19 model attains a notable accuracy of 97%. This research contributes to advancing automated breast cancer detection through deep learning, promising improved outcomes.