Interpretable deep learning for multicenter gastric cancer T staging from CT images

Preoperative T staging of gastric cancer is critical for therapeutic stratification, yet conventional contrast-enhanced CT interpretation shows subjectivity and inconsistent reliability. We developed GTRNet, an interpretable end-to-end deep-learning framework that classifies T1-T4 from routine CT without manual segmentation or annotation. In a retrospective multicenter study of 1792 patients, CT images underwent standardized preprocessing and the largest axial tumor slice was used for training; performance was then tested in two independent external cohorts. GTRNet achieved high discrimination (AUC 0.86-0.95) and accuracy (81-85%) in internal and external tests, surpassing radiologists. Grad-CAM heatmaps localized attention to the gastric wall and serosa. Combining a deep-learning rad-score with tumor size, differentiation and Lauren subtype, we constructed a nomogram with good calibration and higher net clinical benefit than conventional approaches. This automated and interpretable pipeline may standardize CT-based staging and support preoperative decision-making and neoadjuvant-therapy selection.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-12-20
DOI
https://doi.org/10.1038/s41746-025-02002-5
Primary Topic
Gastric Cancer Management and Outcomes
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Interpretable deep learning for multicenter gastric cancer T staging from CT images

Xinhui Qi, Zhixue Jiang, Jinshi Wang, Zhendong Zheng et al.
npj Digital Medicine
Gastric Cancer Management and Outcomes
article

Interpretable deep learning for multicenter gastric cancer T staging from CT images

Xinhui Qi, Zhixue Jiang, Jinshi Wang, Zhendong Zheng, Xiaoyun Chai, Guoliang Zheng, Fuze Li, Xin Zhang, Xin Xin, Yingjie Li, Hongfei Li, Jing Zhang, Yan Zhao, Huan Wang, Fengcheng Guo, Dantong Zhu, Zishuo Yan, Yanqiang Zhang, Y. Ban
article en

Abstract

Preoperative T staging of gastric cancer is critical for therapeutic stratification, yet conventional contrast-enhanced CT interpretation shows subjectivity and inconsistent reliability. We developed GTRNet, an interpretable end-to-end deep-learning framework that classifies T1-T4 from routine CT without manual segmentation or annotation. In a retrospective multicenter study of 1792 patients, CT images underwent standardized preprocessing and the largest axial tumor slice was used for training; performance was then tested in two independent external cohorts. GTRNet achieved high discrimination (AUC 0.86-0.95) and accuracy (81-85%) in internal and external tests, surpassing radiologists. Grad-CAM heatmaps localized attention to the gastric wall and serosa. Combining a deep-learning rad-score with tumor size, differentiation and Lauren subtype, we constructed a nomogram with good calibration and higher net clinical benefit than conventional approaches. This automated and interpretable pipeline may standardize CT-based staging and support preoperative decision-making and neoadjuvant-therapy selection.

npj Digital MedicineVol. 9(1)
Liaoning University (CN), Dalian University of Technology (CN), Central Hospital Affiliated to Shenyang Medical College (CN), Zhejiang Cancer Hospital (CN), General Hospital of Shenyang Military Region (CN), Liaoning Cancer Hospital & Institute (CN), China Medical University (CN)
China Medical University, Shengjing Hospital
Openalex Percentile: Top 40%
Gastric Cancer Management and Outcomes
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.