{"ID":2826553,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18734","arxiv_id":"2512.18734","title":"Breast Cancer Recurrence Risk Prediction Based on Multiple Instance Learning","abstract":"Predicting breast cancer recurrence risk is a critical clinical challenge. This study investigates the potential of computational pathology to stratify patients using deep learning on routine Hematoxylin and Eosin (H\u0026E) stained whole-slide images (WSIs). We developed and compared three Multiple Instance Learning (MIL) frameworks -- CLAM-SB, ABMIL, and ConvNeXt-MIL-XGBoost -- on an in-house dataset of 210 patient cases. The models were trained to predict 5-year recurrence risk, categorized into three tiers (low, medium, high), with ground truth labels established by the 21-gene Recurrence Score. Features were extracted using the UNI and CONCH pre-trained models. In a 5-fold cross-validation, the modified CLAM-SB model demonstrated the strongest performance, achieving a mean Area Under the Curve (AUC) of 0.836 and a classification accuracy of 76.2%. Our findings demonstrate the feasibility of using deep learning on standard histology slides for automated, genomics-correlated risk stratification, highlighting a promising pathway toward rapid and cost-effective clinical decision support.","short_abstract":"Predicting breast cancer recurrence risk is a critical clinical challenge. This study investigates the potential of computational pathology to stratify patients using deep learning on routine Hematoxylin and Eosin (H\u0026E) stained whole-slide images (WSIs). We developed and compared three Multiple Instance Learning (MIL)...","url_abs":"https://arxiv.org/abs/2512.18734","url_pdf":"https://arxiv.org/pdf/2512.18734v1","authors":"[\"Jinqiu Chen\",\"Huyan Xu\"]","published":"2025-12-21T13:46:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}