ORIGINAL RESEARCH article
Front. Med.
Sec. Pathology
Volume 12 - 2025 | doi: 10.3389/fmed.2025.1594614
This article is part of the Research TopicEvaluating Foundation Models in Medical ImagingView all 3 articles
Artificial intelligence-based model for Diagnosing Helicobacter Pylori in Whole-Slide Images
Provisionally accepted
- 1Department of Pathology, Zhongda Hospital, Southeast University School of Medicine, Nanjing, China
- 2Department of Gastroenterology, Zhongda Hospital, Southeast University School of Medicine, Nanjing, China
- 3School of Information Science and Technology, Northwest University, Xi’an, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Helicobacter pylori (H. pylori) infection is considered to be a primary causative factor for gastric cancer and a common cause of chronic gastritis worldwide.Identifying H. pylori infection through hematoxylin and eosin (H&E) staining is demanding and tedious for pathologists. Here, we developed three multi-instance learning (MIL) models: AB-MIL, DS-MIL, and Trans-MIL, to automatically detect H. pylori infection. A total of 1020 digitized histological whole-slide images (WSI) from 817 patients were used for training, validating and testing sets at a ratio of 3:1:1. The accuracy, precision, sensitivity, specificity, false positive rate, false negative rate, F1 score, AUC, and other metrics were calculated for the three models respectively. Ultimately, all three models demonstrated good diagnostic performance in predicting H. pylori infection, with the DS-MIL classification model showing the best diagnostic performance, achieving an accuracy of 89.7% and an area under the curve (AUC) of 0.949, which is higher than the accuracy rate of senior pathologists at 81.7%. Our results present an artificial intelligence (AI)-based predictive model for H. pylori infection, which significantly enhances clinical efficiency and diagnostic accuracy.
Keywords: Helicobacter pylori, gastric mucosal biopsy, Pathological diagnosis, artificial intelligence, Chronic gastritis
Received: 16 Mar 2025; Accepted: 28 May 2025.
Copyright: © 2025 Teng, Ren, Yan, Duan, Chen, Li, Zhang and Cui. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Lihua Zhang, Department of Pathology, Zhongda Hospital, Southeast University School of Medicine, Nanjing, China
Lei Cui, School of Information Science and Technology, Northwest University, Xi’an, 710127, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.