Development and validation of a deep learning-based pathomics signature for prognosis and chemotherapy benefits in colorectal cancer: a retrospective multicenter cohort study

作者：Shenghan Lou, Yanming Huang, Fenqi Du, Jingmin Xue, Gary Mo, Hao Li, Hao Li, Zhanjiang Yu, Yuanchun Li, Hang Wang, Yuze Huang, Haonan Xie, Wenjie Song, Xinyue Zhang, Huiying Li, Huiying Li, Chun Lou, Peng Han · 发表于：Frontiers in Immunology · 年份：2025 · DOI：10.3389/fimmu.2025.1602909 · 被引用次数：6 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Colorectal Cancer Screening and Detection、AI in cancer detection

Introduction The conventional tumor-node-metastasis (TNM) classification system remains limited in accurately forecasting prognosis and guiding adjuvant chemotherapy decisions for patients with colorectal cancer (CRC). To address this gap, we introduced and validated a novel pathomics signature (PS CRC ) derived from hematoxylin and eosin-stained whole slide images, leveraging a deep learning framework. Methods This retrospective study analyzed 883 slides from two independent cohorts. An interpretable multi-instance learning model was developed to construct PS CRC , with SHapley Additive exPlanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) for the improvement of model interpretability and the identification of critical histopathological features, respectively. The transcriptomic data was provided by The Cancer Genome Atlas (TCGA) and integrated to investigate the biological mechanisms underpinning PS CRC . Results The results demonstrated that PS CRC was proven to be an independent prognostic indicator for both overall and disease-free survival. It significantly enhanced the prognostic performance alongside TNM staging, as shown by improvements in net reclassification and integrated discrimination indices. Furthermore, patients in stages II and III with low PS CRC levels were more likely to benefit from chemotherapy. Morphologically, PS CRC reflected features such as tumor infiltration, adipocyte presence, fibrotic stroma, and immune cell engagement. ...