An interpretable deep learning biomarker for prognostication and prediction of adjuvant chemotherapy benefit in gastric cancer
Menée à l'aide d'un algorithme d'apprentissage automatique utilisant un transformeur à faible supervision, d'images numériques de lames histologiques ainsi que de données cliniques portant sur 2 876 patients atteints d'un cancer gastrique puis validée sur 288 patients supplémentaires et à l'aide de données du projet "The Cancer Genome Atlas", cette étude évalue la performance d'un score de risque pathologique pour prédire le bénéfice, en termes de survie, d'une chimiothérapie adjuvante
Prognostic stratification in gastric cancer (GC) currently relies on the tumour-node-metastasis (TNM) staging system, which incompletely captures tumour heterogeneity. Routine haematoxylin and eosin (H&E)-stained whole-slide images (WSIs) contain additional prognostic information that is not routinely quantified. We developed an interpretable deep learning framework using a weakly supervised Transformer to derive a pathological risk score (TPRS) from WSIs for overall survival (OS) stratification and adjuvant chemotherapy benefit prediction. TPRS was developed on HMU-GC (n = 2876) and validated internally (n = 288) and on TCGA-STAD (n = 355). It achieved a mean 10-fold cross-validation C-index of 0.765 ± 0.003 internally and 0.621 ± 0.005 externally, and was an independent prognostic factor. Stage III patients with high TPRS showed significant survival benefit from adjuvant chemotherapy. Mediation analysis of differentially expressed genes (DEGs) and cellular features in high-attention patches supported a ‘Gene → Cellular Features → TPRS’ relationship, linking transcriptomics to cellular features and TPRS.
npj Precision Oncology , article en libre accès, 2026