Breast Cancer Image Classification Using Multi-Modal Datasets: A Comprehensive Review

Breast cancer is one of the most frequently diagnosed malignancies worldwide and remains a leading cause of cancer-related mortality among women. Early and accurate detection significantly improves survival rates and treatment outcomes. Recent advances in artificial intelligence, particularly deep learning, have transformed breast cancer diagnosis through automated image classification. This review presents a comprehensive analysis of breast cancer image classification techniques across multiple dataset modalities, including histopathological images, mammography scans, cytopathology images, and multi-resolution datasets. Traditional machine learning methods and modern deep learning architectures are critically examined with respect to feature extraction, dataset characteristics, and classification performance. Special attention is given to transfer learning, hybrid models, class imbalance handling, and magnification variability. The review also highlights key research findings, limitations, and open challenges hindering clinical adoption. By synthesizing recent state-of-the-art studies, this paper provides valuable insights into current trends and future directions for developing robust, accurate, and clinically deployable breast cancer diagnostic systems.