The abstract is read at the publisher; the summary is JClub's.
BCALN-Net, an MRI-based hierarchical multitask deep learning model, predicts sentinel lymph node metastasis, SLN metastatic burden, and non-SLN metastasis in 6,271 breast cancer patients with robust performance.
- Why it matters: An integrated preoperative method to identify SLN metastasis, metastatic burden, and non-SLN spread is needed to guide axillary surgery de-escalation.
- What they did: The model was trained and evaluated on 6,271 breast cancer patients to predict SLN metastasis, SLN metastatic burden, and NSLN metastasis from MRI, with testing across molecular subtypes, tumor/node stages, ER, HER2, menopausal status, and SLN burden.
- The result: In pooled analysis of 4,081 patients, BCALN-Net shows superior performance for predicting omission of axillary invasive procedures and adds value over clinical criteria, supporting integrated ALN-status guidance for de-escalation.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.