Deep Learning in Breast Cancer Molecular Subtyping: Recent Advances and Clinical Translation

Breast cancer, as the second most prevalent malignancy among women in China, necessitates molecular subtyping for precision treatment decisions. While traditional biopsies face limitations due to invasiveness and spatial heterogeneity, deep learning demonstrates significant potential in enhancing non-invasive subtype prediction through automated feature extraction and multimodal data fusion. This review comprehensively summarizes recent advances in radiomics research and DL applications across mammography, MRI, and ultrasound imaging for predicting breast cancer molecular subtypes. It critically evaluates the strengths and limitations of existing methodologies, providing a reference framework for future DL-based research and clinical implementation of non-invasive subtyping approaches.