Strategies for pathology-based prediction of pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. (IMAGE)
Caption
(A) Immunohistochemical staining is precise and interpretable but time-consuming and labor-intensive. (B) Deep-learning (DL)-based multiple-instance learning enables automated prediction with limited interpretability. (C) Our method integrates DLPSs, spatial graph features, and clinical variables to improve both accuracy and interpretability by modeling whole-slide-level tissue interactions. Check marks indicate methodological advantages, whereas cross marks denote limitations. DLPSs, DL-derived pCR scores.
Credit
Wensheng Cui, Hangzhou Dianzi University.
Usage Restrictions
News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.
License
Licensed content