{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T03:44:12Z","timestamp":1784691852157,"version":"3.55.0"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p><jats:italic>Helicobacter pylori (H. pylori)<\/jats:italic> infection is considered to be a primary causative factor for gastric cancer and a common cause of chronic gastritis worldwide. Identifying <jats:italic>H. pylori<\/jats:italic> infection through hematoxylin and eosin (H&amp;amp;E) staining is demanding and tedious for pathologists. We aimed to use artificial intelligence (AI) models to improve the accuracy and efficiency of <jats:italic>H. pylori<\/jats:italic> diagnosis and to reduce the workload of pathologists.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Here, we developed three multi-instance learning (MIL) models: AB-MIL, DS-MIL, and Trans-MIL, to automatically detect <jats:italic>H. pylori<\/jats:italic> infection. A total of 1,020 digitized histological whole-slide images (WSI) from 817 patients were used for training, validating and testing sets at a ratio of 3:1:1. Additionally, 100 cases (218 WSIs) were randomly selected from the test set for pathologists to identify <jats:italic>H. pylori<\/jats:italic> under the microscope. The accuracy, specificity, sensitivity, false negative rate, false positive rate, and other metrics were calculated separately for the MIL models and the pathologists.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All three models demonstrated good diagnostic performance in predicting <jats:italic>H. pylori<\/jats:italic> 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%. Furthermore, the model demonstrates superior performance in terms of sensitivity and specificity. The reliability of DS-MIL is confirmed through the Visual model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Our research presents an AI - based predictive model for <jats:italic>H. pylori<\/jats:italic> infection, which significantly enhances clinical efficiency and diagnostic accuracy. Currently, we are conducting multi-center validation to enhance the model\u2019s generalization capability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1594614","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:15:24Z","timestamp":1749618924000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Artificial intelligence-based model for diagnosing Helicobacter pylori in whole-slide images"],"prefix":"10.3389","volume":"12","author":[{"given":"Kehan","family":"Teng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawei","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hansheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/S2468-1253(23)00070-5","article-title":"Global prevalence of Helicobacter pylori infection between 1980 and 2022: a systematic review and meta-analysis","volume":"8","author":"Li","year":"2023","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1002\/ijc.21731","article-title":"The global health burden of infection-associated cancers in the year 2002","volume":"118","author":"Parkin","year":"2006","journal-title":"Int J Cancer"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"12781","DOI":"10.3748\/wjg.v20.i36.12781","article-title":"Beyond the stomach: an updated view of Helicobacter pylori pathogenesis, diagnosis, and treatment","volume":"20","author":"Testerman","year":"2014","journal-title":"World J Gastroenterol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"280","DOI":"10.23736\/S1121-421X.18.02481-9","article-title":"Benign and malignant gastroduodenal diseases associated with Helicobacter pylori: a narrative review and personal remarks in 2018","volume":"64","author":"Buz\u00e1s","year":"2018","journal-title":"Minerva Gastroenterol Dietol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1476-0711-4-1","article-title":"Helicobacter pylori and gastroduodenal pathology: new threats of the old friend","volume":"4","author":"Ahmed","year":"2005","journal-title":"Ann Clin Microbiol Antimicrob"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"589","DOI":"10.3760\/cma.j.cn321463-20230425-00654","article-title":"Expert consensus on pathological histology of Helicobacter pylori infection of gastric mucosa","volume":"40","year":"2023","journal-title":"Chin J Dig Endosc"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1136\/gutjnl-2016-312288","article-title":"Management of Helicobacter pylori infection-the Maastricht V\/Florence consensus report","volume":"66","author":"Malfertheiner","year":"2017","journal-title":"Gut"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"12767","DOI":"10.3748\/wjg.v20.i36.12767","article-title":"Effect of Helicobacter pylori on gastric epithelial cells","volume":"20","author":"Alzahrani","year":"2014","journal-title":"World J Gastroenterol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1111\/j.1572-0241.2001.03447.x","article-title":"Apoptosis in gastric epithelium induced by Helicobacter pylori infection: implications in gastric carcinogenesis","volume":"96","author":"Xia","year":"2001","journal-title":"Am J Gastroenterol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1053\/j.gastro.2010.08.018","article-title":"A national study of Helicobacter pylori infection in gastric biopsy specimens","volume":"139","author":"Sonnenberg","year":"2010","journal-title":"Gastroenterology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","article-title":"Deep learning-based classification of hyperspectral data","volume":"7","author":"Chen","year":"2014","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.04712","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018","journal-title":"PMLR"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01409","article-title":"Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning","author":"Li","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.48550\/arXiv.2106.00908","article-title":"TransMIL: transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1109\/TMI.2023.3241204","article-title":"Bayesian collaborative learning for whole-slide image classification","volume":"42","author":"Yu","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.2741\/3320","article-title":"Helicobacter pylori associated global gastric cancer burden","volume":"14","author":"Mbulaiteye","year":"2009","journal-title":"Front Biosci Landmark Ed"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"295","DOI":"10.32074\/1591-951X-751","article-title":"Use of digital pathology and artificial intelligence for the diagnosis of helicobacter pylori in gastric biopsies","volume":"114","author":"Liscia","year":"2022","journal-title":"Pathologica"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1186\/s12876-020-01494-7","article-title":"Deep learning for sensitive detection of helicobacter pylori in gastric biopsies","volume":"20","author":"Klein","year":"2020","journal-title":"BMC Gastroenterol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1111\/his.15018","article-title":"Two-tiered deep-learning-based model for histologic diagnosis of helicobacter gastritis","volume":"83","author":"Lin","year":"2023","journal-title":"Histopathology"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"117","DOI":"10.5858\/arpa.2020-0520-OA","article-title":"A deep learning convolutional neural network can differentiate between helicobacter pylori gastritis and autoimmune gastritis with results comparable to gastrointestinal pathologists","volume":"146","author":"Franklin","year":"2022","journal-title":"Arch Pathol Lab Med"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"370","DOI":"10.5858\/arpa.2019-0004-OA","article-title":"A deep learning convolutional neural network can recognize common patterns of injury in gastric pathology","volume":"144","author":"Martin","year":"2020","journal-title":"Arch Pathol Lab Med"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"893","DOI":"10.3760\/cma.j.cn112151-20240112-00028","article-title":"Expert consensus on data acquisition and annotation of artificial intelligence assisted gastric histopathological diagnosis","volume":"53","year":"2024","journal-title":"Zhonghua Bing Li Xue Za Zhi"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1594614\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:15:27Z","timestamp":1749618927000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1594614\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":24,"alternative-id":["10.3389\/fmed.2025.1594614"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1594614","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,11]]},"article-number":"1594614"}}