Deep Learning Approaches to Detect Breast Cancer: A Comprehensive Review

Detection and diagnosis of breast cancer have greatly benefited from advances in deep learning, addressing the critical challenge of early detection and accurate diagnosis. This paper presents a comprehensive review of 68 high-quality studies from 2022 and 2023 that applied deep learning to various imaging modalities, including mammography, ultrasound, MRI, histopathology, and thermography. The reviewed works are analyzed based on datasets, model architectures, input dimensions, and performance outcomes. Convolutional Neural Networks (CNNs) are found to enhance image accuracy, sensitivity, and specificity, particularly in mammography and MRI. The study also discusses the challenges of limited and imbalanced datasets, exploring transfer learning and data augmentation as solutions to improve model robustness and generalization. Furthermore, it highlights the importance of larger datasets, interpretability, and multi-modal integration for future research directions in breast cancer detection.