AI-based large-scale screening of gastric cancer from noncontrast CT imaging

Early detection through screening is critical for reducing gastric cancer (GC) mortality. However, in most high-prevalence regions, large-scale screening remains challenging due to limited resources, low compliance and suboptimal detection rate of upper endoscopic screening. Therefore, there is an urgent need for more efficient screening protocols. Noncontrast computed tomography (CT), routinely performed for clinical purposes, presents a promising avenue for large-scale designed or opportunistic screening. Here we developed the Gastric Cancer Risk Assessment Procedure with Artificial Intelligence (GRAPE), leveraging noncontrast CT and deep learning to identify GC. Our study comprised three phases. First, we developed GRAPE using a cohort from 2 centers in China (3,470 GC and 3,250 non-GC cases) and validated its performance on an internal validation set (1,298 cases, area under curve = 0.970) and an independent external cohort from 16 centers (18,160 cases, area under curve = 0.927). Subgroup analysis showed that the detection rate of GRAPE increased with advancing T stage but was independent of tumor location. Next, we compared the interpretations of GRAPE with those of radiologists and assessed its potential in assisting diagnostic interpretation. Reader studies demonstrated that GRAPE significantly outperformed radiologists, improving sensitivity by 21.8% and specificity by 14.0%, particularly in early-stage GC. Finally, we evaluated GRAPE in real-world opportunistic screening using 78,593 consecutive noncontrast CT scans from a comprehensive cancer center and 2 independent regional hospitals. GRAPE identified persons at high risk with GC detection rates of 24.5% and 17.7% in 2 regional hospitals, with 23.2% and 26.8% of detected cases in T1/T2 stage. Additionally, GRAPE detected GC cases that radiologists had initially missed, enabling earlier diagnosis of GC during follow-up for other diseases. In conclusion, GRAPE demonstrates strong potential for large-scale GC screening, offering a feasible and effective approach for early detection. ClinicalTrials.gov registration: NCT06614179 .

Authors

Institutions

Publication Details

Journal
Nature Medicine
Published
2025-06-24
DOI
https://doi.org/10.1038/s41591-025-03785-6
Citations
20
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
27.20
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AI-based large-scale screening of gastric cancer from noncontrast CT imaging

Shengjie Zhang, Jiahui Chen, Xijun Gong, Wenchao Guo et al.
20 citations
Nature Medicine
Radiomics and Machine Learning in Medical Imaging
27.20
article

AI-based large-scale screening of gastric cancer from noncontrast CT imaging

Shengjie Zhang, Jiahui Chen, Xijun Gong, Wenchao Guo, Lei Shi, Shufeng Fan, Jielu Cao, Zhilin Zheng, Xinxin Yang, Shangqi Chen, Guanxia Zhu, Wujie Chen, Mengxuan Cao, Jinfang Qiao, Ling Zhang, Xianghui Kong, Xing‐Gang Yan, Siwei Pan, Yao Wang, Qi Zheng, Jianwei Xu, Weiqun Ao, Zufeng Ge, Zaisheng Ye, Zhiyuan Xu, Miaoguang Su, Yahan Tong, Xiangdong Cheng, Yingda Xia, Yibo Pan, Jiawen Yao, Guoliang Zheng, Zhongwei Qiu, Keda Chen, Ruo‐Lan Zhang, Yan Cheng, Weiwei Zhu, Huan Li, Yan Wang, Jianfeng Zhang, Lei Zhang, Pengfei Yu, Chen Gao, Jiancheng Sun, Kangjie Xie, Tiancheng Lin, Boxiang Yun, Xun Tian, Yingjie Wu, Jingli Xu, Yanqiang Zhang, Zhaoxia Wen, Lin Zheng, Yizhou Wei, Xiaozhong Zheng, Haoming Qiu, Xin Zhang
article en
20 citations

Abstract

Early detection through screening is critical for reducing gastric cancer (GC) mortality. However, in most high-prevalence regions, large-scale screening remains challenging due to limited resources, low compliance and suboptimal detection rate of upper endoscopic screening. Therefore, there is an urgent need for more efficient screening protocols. Noncontrast computed tomography (CT), routinely performed for clinical purposes, presents a promising avenue for large-scale designed or opportunistic screening. Here we developed the Gastric Cancer Risk Assessment Procedure with Artificial Intelligence (GRAPE), leveraging noncontrast CT and deep learning to identify GC. Our study comprised three phases. First, we developed GRAPE using a cohort from 2 centers in China (3,470 GC and 3,250 non-GC cases) and validated its performance on an internal validation set (1,298 cases, area under curve = 0.970) and an independent external cohort from 16 centers (18,160 cases, area under curve = 0.927). Subgroup analysis showed that the detection rate of GRAPE increased with advancing T stage but was independent of tumor location. Next, we compared the interpretations of GRAPE with those of radiologists and assessed its potential in assisting diagnostic interpretation. Reader studies demonstrated that GRAPE significantly outperformed radiologists, improving sensitivity by 21.8% and specificity by 14.0%, particularly in early-stage GC. Finally, we evaluated GRAPE in real-world opportunistic screening using 78,593 consecutive noncontrast CT scans from a comprehensive cancer center and 2 independent regional hospitals. GRAPE identified persons at high risk with GC detection rates of 24.5% and 17.7% in 2 regional hospitals, with 23.2% and 26.8% of detected cases in T1/T2 stage. Additionally, GRAPE detected GC cases that radiologists had initially missed, enabling earlier diagnosis of GC during follow-up for other diseases. In conclusion, GRAPE demonstrates strong potential for large-scale GC screening, offering a feasible and effective approach for early detection. ClinicalTrials.gov registration: NCT06614179 .

Nature MedicineVol. 31(9)
Zhejiang Chinese Medical University (CN), Anhui Medical University (CN), Chinese Academy of Sciences (CN), Wenzhou Medical University (CN), First Affiliated Hospital of Wenzhou Medical University (CN), Alibaba Group (Cayman Islands) (KY), Alibaba Group (United States) (US), Tongde Hospital of Zhejiang Province (CN), Zhejiang Cancer Hospital (CN), Ningbo No. 2 Hospital (CN), Huzhou Central Hospital (CN), Qingzhou City People's Hospital (CN), Zhejiang Lab (CN), Third People's Hospital of Huzhou (CN), Fujian Provincial Cancer Hospital (CN), Affiliated Hangzhou First People's Hospital, Westlake University, School of Medicine (CN), Second Affiliated Hospital of Anhui Medical University (CN), Wenzhou City People's Hospital (CN), Liaoning Cancer Hospital & Institute (CN), Cixian People's Hospital (CN), Ningbo No.6 Hospital (CN), Yuxian People's Hospital (CN), Hangzhou Cancer Hospital (CN), Alibaba Group (China) (CN), East China Normal University (CN), China Medical University (CN)
Good health and well-being
Openalex Percentile: Top 0%
Radiomics and Machine Learning in Medical Imaging
27.20
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.