{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:05:48Z","timestamp":1784091948547,"version":"3.55.0"},"reference-count":20,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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. Gastroenterol."],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>\n                      <jats:italic>Helicobacter pylori<\/jats:italic>\n                      infection is a major risk factor for gastric cancer, but evidence for predicting\n                      <jats:italic>H. pylori<\/jats:italic>\n                      status from endoscopic images in patients with established gastric cancer remains limited. We evaluated the performance of endoscopic image-based classification models for\n                      <jats:italic>H. pylori<\/jats:italic>\n                      status in a retrospective gastric cancer cohort.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively collected 602 endoscopic images from 337 patients with gastric cancer treated at a tertiary cancer center. After preprocessing and quality control, 576 images from 329 patients were retained for model development and evaluation.\n                      <jats:italic>Helicobacter pylori<\/jats:italic>\n                      status was defined using routine clinical testing, including serum anti-\n                      <jats:italic>H. pylori<\/jats:italic>\n                      IgG and\/or the\n                      <jats:sup>13<\/jats:sup>\n                      C urea breath test. Endoscopic image classification models were evaluated across repeated stratified train, validation, and test splits. The primary performance metric was the area under the receiver operating characteristic curve (AUC).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Model discrimination was limited. The best-performing approach achieved a median test AUC of 0.6255, with sensitivity of 0.7308, specificity of 0.3714, accuracy of 0.6092, and F1 score of 0.6800. Fine-tuning showed a higher median AUC than retraining, but discrimination remained limited in both strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      In this retrospective gastric cancer cohort, endoscopic image-based classification showed limited ability to discriminate\n                      <jats:italic>H. pylori<\/jats:italic>\n                      status. These findings suggest that image-based assessment of\n                      <jats:italic>H. pylori<\/jats:italic>\n                      status in patients with gastric cancer remains challenging and may require more rigorous phenotyping, larger datasets, and validation across clinically diverse populations.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fgstr.2026.1878650","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:22:03Z","timestamp":1784089323000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Limited discriminative performance of endoscopic deep learning for Helicobacter pylori status assessment in gastric cancer patients: a retrospective study"],"prefix":"10.3389","volume":"5","author":[{"given":"Wenyi","family":"Zhou","sequence":"first","affiliation":[{"name":"Radiology Department, Changsha Stomatological Hospital","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Endoscopy, Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongluo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wencan","family":"He","sequence":"additional","affiliation":[{"name":"Precision Medicine Institute, The First Affiliated Hospital, Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Xu","sequence":"additional","affiliation":[{"name":"EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales","place":["Ales, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1086\/516077","article-title":"Helicobacter pylori gastritis, peptic ulcer, and gastric cancer: Clinical and molecular aspects","volume":"25","author":"Stewart Goodwin","year":"1997","journal-title":"Clin Infect Dis"},{"key":"B2","first-page":"17","article-title":"Epidemiology, diagnosis and risk factors of helicobacter pylori infection","volume-title":"Epidemiology, Diagnosis and Risk Factors of Helicobacter Pylori Infection","author":"Kotilea","year":"2019"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v20.i38.13842","article-title":"Gastric cancer: Prevention, screening and early diagnosis","volume":"20","author":"Pasechnikov","year":"2014","journal-title":"World J Gastroenterol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2022-327745","article-title":"Management of helicobacter pylori infection: The maastricht vi\/florence consensus report","volume":"71","author":"Malfertheiner","year":"2022","journal-title":"Gut"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.03058","article-title":"Chestnet: A deep neural network for classification of thoracic diseases on chest radiography","author":"Wang","year":"2018","journal-title":"arXiv preprint arXiv:180703058"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.4253\/wjge.v10.i10.239","article-title":"Artificial intelligence in gastrointestinal endoscopy: The future is almost here","volume":"10","author":"Alagappan","year":"2018","journal-title":"World J Gastrointestinal Endoscopy"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2196\/21983","article-title":"Artificial intelligence for the prediction of helicobacter pylori infection in endoscopic images: Systematic review and meta-analysis of diagnostic test accuracy","volume":"22","author":"Bang","year":"2020","journal-title":"J Med Internet Res"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s10120-018-0793-2","article-title":"Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images","volume":"21","author":"Hirasawa","year":"2018","journal-title":"Gastric Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13215253","article-title":"Artificial intelligence in gastric cancer: Identifying gastric cancer using endoscopic images with convolutional neural network","volume":"13","author":"Islam","year":"2021","journal-title":"Cancers"},{"key":"B10","first-page":"1","article-title":"Detection of gastric cancer in endoscopic images using deep convolutional neural networks","author":"Pauranik","year":"2024"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11081384","article-title":"Transmed: Transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2026.100355","article-title":"Advancing glaucoma diagnosis: Multi-modal deep learning with vision transformer architectures","volume":"13","author":"Gandhi","year":"2026","journal-title":"Intelligence-Based Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2017.10.014","article-title":"Application of convolutional neural networks in the diagnosis of helicobacter pylori infection based on endoscopic images","volume":"25","author":"Shichijo","year":"2017","journal-title":"EBioMedicine"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1055\/s-0043-120830","article-title":"Deep learning analyzes helicobacter pylori infection by upper gastrointestinal endoscopy images","volume":"6","author":"Itoh","year":"2018","journal-title":"Endoscopy Int Open"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-4-431-55705-0_10","article-title":"Endoscopic findings of H. pylori infection","volume-title":"Endoscopic Findings of H. Pylori Infection","author":"Kato","year":"2016"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v28.i43.6078","article-title":"Kyoto classification of gastritis: Advances and future perspectives in endoscopic diagnosis of gastritis","volume":"28","author":"Toyoshima","year":"2022","journal-title":"World J Gastroenterol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.02643","article-title":"Segment anything","author":"Kirillov","year":"2023","journal-title":"arXiv preprint arXiv:230402643"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fbrio.2024.1333641","article-title":"Active trachoma: Enhancing image classification using pretrained sota models and explainable ai","volume":"3","author":"Pan","year":"2024","journal-title":"Front Bacteriology"},{"key":"B19","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of Machine Learning Research","author":"Tan","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2019-320466","article-title":"Machine learning in gi endoscopy: Practical guidance in how to interpret a novel field","volume":"69","author":"van der Sommen","year":"2020","journal-title":"Gut"}],"container-title":["Frontiers in Gastroenterology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgstr.2026.1878650\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:22:04Z","timestamp":1784089324000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgstr.2026.1878650\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":20,"alternative-id":["10.3389\/fgstr.2026.1878650"],"URL":"https:\/\/doi.org\/10.3389\/fgstr.2026.1878650","relation":{},"ISSN":["2813-1169"],"issn-type":[{"value":"2813-1169","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1878650"}}