Key points are not available for this paper at this time.
Artificial intelligence (AI), particularly deep learning, is reshaping breast cancer diagnostics in the radiology and pathology fields. This review synthesizes recent advances in mammography, digital breast tomosynthesis (DBT), ultrasound, MRI, and whole-slide imaging, with an emphasis on convolutional neural networks (CNNs), Vision Transformers (ViTs), and generative adversarial networks (GANs). When embedded within established screening and diagnostic workflows, AI systems can enhance lesion detection and triage, as well as reduce interpretive variability. However, performance and generalizability depend on dataset quality, population and vendor heterogeneity, acquisition protocols, and calibrated probability outputs; diminished performance on external datasets and miscalibration remain recurrent risks that require explicit mitigation during development and deployment of these models. Beyond detection and classification, segmentation and risk prediction models increasingly integrate imaging with clinicopathological and, where available, genomic variables to enable individualized risk stratification and follow-up planning. Data generation strategies, including GAN-based augmentation, can partially address data scarcity and class imbalance but require rigorous quality control and bias monitoring. Persistent barriers to clinical adoption include uneven external validation, domain shifts across institutions, variability in reporting standards, limited interpretability, and ethical, privacy, and regulatory constraints. Overall, AI should augment, rather than replace, the role of clinicians. Priorities for responsible integration include multi-site prospective evaluations, transparent and standardized reporting, bias mitigation, robust calibration, and lifecycle monitoring to ensure sustained safety and equity.
Ali et al. (Wed,) studied this question.