Download PDF
Endoscopy
DOI: 10.1055/a-2451-3071
Original article

A novel endoscopic artificial intelligence system to assist in the diagnosis of autoimmune gastritis: a multicenter study

Shurong Chen
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Louzhe Xu
2   Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China (Ringgold ID: RIN12501)
,
Lingling Yan
3   Department of Gastroenterology, Taizhou Hospital of Zhejiang Province, Linhai, China (Ringgold ID: RIN56709)
,
Jie Zhang
4   Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Xuefeng Zhou
5   Department of Gastroenterology, The Second Hospital of Jiaxing, Jiaxing, China (Ringgold ID: RIN569220)
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Jiayi Wang
6   Department of Gastroenterology, CHC international hospital, Ningbo, China
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Tianlian Yan
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Jinghua Wang
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Xinjue He
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Han Ma
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Xuequn Zhang
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Shenghua Zhu
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Yi-zhen Zhang
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Chengfu Xu
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Jianguo Gao
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Xia Ji
5   Department of Gastroenterology, The Second Hospital of Jiaxing, Jiaxing, China (Ringgold ID: RIN569220)
,
Dezhi Bai
7   Department of Gastroenterology, The First People’s hospital of Yuhang, Hangzhou, China
,
Yuan Chen
8   Department of Gastroenterology, The Third People’s hospital of Zhoushan, Zhoushan, China
,
Hongda Chen
9   Department of Gastroenterology, Zhejiang Chinese Medical University Affiliated Third Hospital, Hangzhou, China (Ringgold ID: RIN232834)
,
Yini Ke
10   Department of Rheumatology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Lan Li
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Chaohui Yu 
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
,
Xinli Mao
3   Department of Gastroenterology, Taizhou Hospital of Zhejiang Province, Linhai, China (Ringgold ID: RIN56709)
,
Ting Li
2   Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China (Ringgold ID: RIN12501)
,
Yi Chen
1   Department of Gastroenterology, Zhejiang University School of Medicine First Affiliated Hospital, Hangzhou, China (Ringgold ID: RIN71069)
› Author AffiliationsSupported by: Key Research and Development Program of Zhejiang Province 2024C03202 to Yi Chen
Supported by: National Natural Science Foundation of China 82170582 to Yi Chen,82204229 to Yini Ke
Supported by: Chinese Academy of Medical Science health innovation project 2021-I2M-1-042 to Ting Li,2022-I2M-C&T-A-005 to Ting Li,2022-I2M-C&T-B-012 to Ting Li
Supported by: Tianjin Outstanding Youth Fund Project 20JCJQIC00230 to Ting Li
› Further Information
Also available at
  PDF Download

Background & Aims: Autoimmune gastritis (AIG), distinct from Helicobacter pylori-associated atrophic gastritis (HpAG), is underdiagnosed due to limited awareness. This multicenter study aims to develop a novel endoscopic artificial intelligence (AI) system assisting in AIG diagnosis. Methods: Patients diagnosed with AIG, as well as HpAG and non-atrophic gastritis (NAG), were retrospectively enrolled from six centers. Endoscopic images with relevant demographic and medical data, were collected for the development of AI-assisted system, SEER-SCOPE AI, based on multi-site feature fusion model. The diagnostic performance of SEER-SCOPE AI was evaluated in the internal and external datasets. Endoscopists’ performance with and without AI support was tested and compared using Mann-Whitney U test. Heatmap analysis was performed to interpret SEER-SCOPE AI. Results: 1 070 patients (294 AIG, 386 HpAG, 390 NAG) with 18 828 endoscopy images were collected. SEER-SCOPE AI achieved strong performance for identifying AIG, with 96.9% sensitivity, 92.2% specificity and an AUROC of 0.990 internally, and 90.3% sensitivity, 93.1% specificity and an AUROC of 0.973 externally. The performance of SEER-SCOPE AI (sensitivity 91.3%) was comparable to experts (87.3%) and significantly outperformed non-experts (70.0%). With AI support, the overall performance of endoscopists was improved (sensitivity: 90.3% [95% CI 86.0%-93.2%] vs. 78.7% [95% CI 73.6%-83.2%], p=0.008). Heatmap analysis revealed consistent focus of SEER-SCOPE AI on regions corresponding to atrophic areas. Conclusions: SEER-SCOPE AI demonstrated expert-level performance in identifying AIG, and enhanced the diagnostic ability of endoscopists. Its application holds promise as a potent endoscopy-assisted tool for guiding biopsy sampling and early detection of AIG.



Publication History

Received: 14 May 2024

Accepted after revision: 24 October 2024

Accepted Manuscript online:
24 October 2024

© . Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany