Breast Cancer Image Classification Using Convolutional Neural Networks

This study aimed to develop and evaluate a deep learning-based classification model for breast ultrasound images. The primary objectives were to classify ultrasound images into three categories: benign, malignant, and normal. Breast cancer detection using ultrasound imaging is challenging due to class imbalance and insufficient annotations in datasets. This research focuses on enhancing classification accuracy by leveraging a pre-trained ResNet-50 model. Methods included data augmentation to address class imbalance and the integration of masks overlayed on ultrasound images to emphasize regions of interest. These enhancements significantly improved the model's ability to distinguish between benign, malignant, and normal breast tissue. The model achieved an accuracy of 98%, up from an initial 86% on unseen data, demonstrating the impact of detailed annotations and fine-tuning. The results underscore the potential of AI-driven models in improving diagnostic accuracy. Future work involves incorporating additional data sources and validating the model across diverse clinical settings, with the goal of advancing early detection and personalized treatment strategies in breast cancer care.