Performance of MRI-based deep learning models in differentiation of triple negative breast cancer from other breast cancer subtypes: A systematic review and meta-analysis.

Deep learning models applied to breast MRI showed potential for noninvasive TNBC identification with high diagnostic accuracy, but more standardized studies are needed before clinical implementation.

A systematic review and meta-analysis synthesized current evidence on MRI-based deep learning models for identifying triple negative breast cancer (TNBC).

The review included nine studies with 2985 patients, which demonstrated high diagnostic accuracy with an AUC of 0.85 and sensitivity of 0.83.

However, the evidence certainty was rated as low due to limited external validation and variability in methodological quality.