AI combining mammography and tomosynthesis improves preoperative differentiation of breast microcalcifications

AI combining mammography and tomosynthesis radiomics+deep learning (DL) improved breast microcalcification differentiation: test AUC 0.835, significantly better than BI-RADS (0.809) or single-modality models (P<0.05).

• Multimodal model (MD) integrated radiomics and DL scores from mammography (MG) and digital breast tomosynthesis (DBT).
• SHAP analysis identified MG craniocaudal DL scores and radiomic textural features as most influential.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.