A Transfer Learning-Based Deep Learning Model for Automated Breast Cancer Identification in Mammograms

Abstract

Breast cancer poses a significant global health threat to women, underscoring the crucial need for reliable and effective screening approaches. The utilization of computer-aided diagnostic (CAD) systems, leveraging mammograms, enables early detection, diagnosis, and treatment of breast cancer, thereby offering vital support in combating this disease. This study introduces a unique deep-learning model that uses transfer learning to identify and categorize breast cancer automatically. Several recent studies have shown that deep convolutional neural networks (DCNNs) can be used to diagnose breast cancer in mammograms with performances comparable to or even superior to those of human experts. The proposed model extracts features from the Mammographic Image Analysis Society (MIAS) dataset using pre-trained convolutional neural network (CNN) architectures such as ResNet50 and VGG-16. This revolutionary deep-learning model has the potential to improve the efficiency and accuracy of breast cancer detection and categorization.