Scholarlink

<p>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&amp;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 (<i>n</i> = 2876) and validated internally (<i>n</i> = 288) and on TCGA-STAD (<i>n</i> = 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.</p><p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An interpretable deep learning biomarker for prognostication and prediction of adjuvant chemotherapy benefit in gastric cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月7日

查看全文
  • Jianxin Ji,
  • Xuan Zhang,
  • Menglei Hua,
  • Meng Wang,
  • Huiying Li,
  • Xiaohan Zheng,
  • Liuying Wang,
  • Hesong Wang,
  • Yongzhen Song,
  • Jia He,
  • Ruihao Qin,
  • Yong Cao,
  • Qi Zhang,
  • Kaiyuan Ge,
  • Yaru Wang,
  • Huimin Zhang,
  • Shenghan Lou,
  • Peng Han,
  • Lei Cao

摘要

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.