{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T03:38:53Z","timestamp":1793417933118,"version":"4.5.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"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>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Gastric subepithelial lesions (SELs) are typically covered by intact mucosa, which challenges the determination of their layer of origin under conventional endoscopy. Endoscopic ultrasonography (EUS) is indispensable for diagnosing SELs. However, EUS operation and interpretation are more challenging than standard endoscopy and are subject to inter-observer variability. This study aimed to develop a novel AI system based on the MedMamba architecture to assist clinicians in identifying the layer of origin of gastric SELs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively collected data from patients who underwent EUS at the First Affiliated Hospital of Nanjing Medical University between May 1, 2016 and May 1, 2023. The dataset comprised 1,855 images from 320 patients. Images were split into training, validation, and test sets at an 8:1:1 ratio at the patient level to prevent data leakage. A structured State space sequence model (MedMamba) was trained and the performance was compared against endoscopists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed MedMamba model achieved an overall accuracy of 92.04% (95%CI: 90.33\u201393.75%), with 94.83% (95%CI: 93.22\u201396.44%) specificity and 81.11% (95%CI: 75.19\u201387.03%) sensitivity in the five-category classification. It achieved high sensitivity and accuracy, outperforming other AI models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The MedMamba-based AI system demonstrated superior performance in discriminating the layer of origin of SELs compared with other AI models, indicating its potential utility in reducing diagnostic variability and enhancing clinical diagnostic workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1802113","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:29:32Z","timestamp":1773293372000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial intelligence-based endoscopic ultrasonography model for detecting the origin layer of gastric subepithelial lesions"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Geriatric Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangpeng","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Geriatric Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Geriatric Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaishuai","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Department of Geriatric Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Hua","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopu","family":"He","sequence":"additional","affiliation":[{"name":"Department of Geriatric Gastroenterology, The First Affiliated Hospital of Nanjing Medical University","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"46","DOI":"10.14309\/ajg.0000000000002100","article-title":"ACG clinical guideline: diagnosis and management of gastrointestinal subepithelial lesions","volume":"118","author":"Jacobson","year":"2023","journal-title":"Am J Gastroenterol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1055\/s-2005-861422","article-title":"Endoscopic ultrasound and endoscopic ultrasound-guided fine-needle biopsy for the diagnosis of malignant submucosal tumors","volume":"37","author":"Polkowski","year":"2005","journal-title":"Endoscopy"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"224","DOI":"10.7704\/kjhugr.2025.0039","article-title":"Natural course of gastric subepithelial tumors","volume":"25","author":"Kim","year":"2025","journal-title":"Korean J Helicobacter Up Gastrointest Res"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"209","DOI":"10.7704\/kjhugr.2025.0038","article-title":"Approach to gastric subepithelial lesions: from differential diagnosis to histologic confirmation","volume":"25","author":"Kim","year":"2025","journal-title":"Korean J Helicobacter Up Gastrointest Res."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2435","DOI":"10.1016\/j.cgh.2022.05.054","article-title":"AGA clinical practice update on management of subepithelial lesions encountered during routine endoscopy: expert review","volume":"20","author":"Sharzehi","year":"2022","journal-title":"Clin Gastroenterol Hepatol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1080\/17474124.2025.2519161","article-title":"Approach to upper gastrointestinal subepithelial lesions","volume":"19","author":"Anikhindi","year":"2025","journal-title":"Expert Rev Gastroenterol Hepatol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"308","DOI":"10.4103\/2303-9027.155772","article-title":"The role of EUS and EUS-guided FNA in the management of subepithelial lesions of the esophagus: a large, single-center experience","volume":"6","author":"Baysal","year":"2017","journal-title":"Endosc Ultrasound"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s12029-020-00456-2","article-title":"What about gastric schwannoma? A review article","volume":"52","author":"Lauricella","year":"2021","journal-title":"J Gastrointest Cancer"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1016\/j.gie.2009.10.019","article-title":"Accuracy of EUS in the evaluation of small gastric subepithelial lesions","volume":"71","author":"Karaca","year":"2010","journal-title":"Gastrointest Endosc"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e5246","DOI":"10.1097\/MD.0000000000005246","article-title":"Endoscopic ultrasound without tissue acquisition has poor accuracy for diagnosing gastric subepithelial tumors","volume":"95","author":"Lim","year":"2016","journal-title":"Medicine"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1016\/j.gie.2020.04.044","article-title":"Proceedings from the first global artificial intelligence in gastroenterology and endoscopy summit","volume":"92","author":"Parasa","year":"2020","journal-title":"Gastrointest Endosc"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1055\/a-1751-5742","article-title":"Endoscopic management of subepithelial lesions including neuroendocrine neoplasms: European Society of Gastrointestinal Endoscopy (ESGE) guideline","volume":"54","author":"Deprez","year":"2022","journal-title":"Endoscopy"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1016\/j.gie.2017.02.022","article-title":"The role of endoscopy in subepithelial lesions of the GI tract","volume":"85","author":"Faulx","year":"2017","journal-title":"Gastrointest Endosc"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"103792","DOI":"10.1016\/j.media.2025.103792","article-title":"Switch-UMamba: dynamic scanning vision mamba UNet for medical image segmentation","volume":"107","author":"Zhang","year":"2026","journal-title":"Med Image Anal"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"107916","DOI":"10.1016\/j.neunet.2025.107916","article-title":"MHDBN: mamba-based hybrid dual-branch network for multi-focus image fusion","volume":"192","author":"Wu","year":"2025","journal-title":"Neural Netw"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"4819","DOI":"10.1038\/s41598-025-34909-0","article-title":"A multi-scale dual-stream fusion network for high-accuracy sEMG-based gesture classification","volume":"16","author":"He","year":"2026","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"13258","DOI":"10.1038\/s41598-025-97397-2","article-title":"VMKLA-UNet: vision mamba with KAN linear attention U-net","volume":"15","author":"Su","year":"2025","journal-title":"Sci Rep"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e0330740","DOI":"10.1371\/journal.pone.0330740","article-title":"VM-Unet enhanced with multi-scale pyramid feature extraction for segmentation of tibiofemoral joint tissues from knee MRI","volume":"20","author":"Wang","year":"2025","journal-title":"PLoS One"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e0312136","DOI":"10.1371\/journal.pone.0312136","article-title":"Enhancing bridge damage detection with mamba-enhanced HRNet for semantic segmentation","volume":"19","author":"Liu","year":"2024","journal-title":"PLoS One"},{"key":"ref20","author":"Qin","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"7684","DOI":"10.1109\/TIP.2025.3632221","article-title":"Spatial-frequency enhanced mamba for multi-modal image fusion","volume":"34","author":"Sun","year":"2025","journal-title":"IEEE Trans Image Process"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"107919","DOI":"10.1016\/j.neunet.2025.107919","article-title":"SCFMUNet: a fusion architecture based on multi-scale state space model and channel attention for medical image segmentation","volume":"192","author":"Huang","year":"2025","journal-title":"Neural Netw"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"7473","DOI":"10.1109\/TIP.2025.3626935","article-title":"Salient object detection in traffic scene through the TSOD10K dataset","volume":"34","author":"Qiu","year":"2025","journal-title":"IEEE Trans Image Process"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/BF00591381","article-title":"Endoscopic diagnosis of submucosal gastric lesions. The results after routine endoscopy","volume":"5","author":"Hedenbro","year":"1991","journal-title":"Surg Endosc"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"86","DOI":"10.4253\/wjge.v3.i5.86","article-title":"Endoscopic ultrasonography for gastric submucosal lesions","volume":"3","author":"Papanikolaou","year":"2011","journal-title":"World J Gastrointest Endosc"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1055\/a-1811-7025","article-title":"Endoscopic submucosal dissection for superficial gastrointestinal lesions: European Society of Gastrointestinal Endoscopy (ESGE) guideline\u2014update 2022","volume":"54","author":"Pimentel-Nunes","year":"2022","journal-title":"Endoscopy"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/s10120-021-01261-x","article-title":"Artificial intelligence-based diagnosis of upper gastrointestinal subepithelial lesions on endoscopic ultrasonography images","volume":"25","author":"Hirai","year":"2022","journal-title":"Gastric Cancer"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.3390\/diagnostics13132176","article-title":"EUS-guided diagnosis of gastric subepithelial lesions, what is new?","volume":"13","author":"Vasilakis","year":"2023","journal-title":"Diagnostics"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.gie.2021.08.022","article-title":"Deep learning model for diagnosing gastric mucosal lesions using endoscopic images: development, validation, and method comparison","volume":"95","author":"Nam","year":"2022","journal-title":"Gastrointest Endosc"},{"key":"ref30","first-page":"292","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"101918","DOI":"10.1016\/j.media.2020.101918","article-title":"Multitask learning for segmentation and classification of tumors in 3D automated breast ultrasound images","volume":"70","author":"Zhou","year":"2021","journal-title":"Med Image Anal"},{"key":"ref32","first-page":"900","author":"Qu","year":"2019"},{"key":"ref33","first-page":"54473","article-title":"Vision mamba: efficient visual representation learning with bidirectional state space model","volume":"235","author":"Zhu","year":"2024","journal-title":"Proc Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"16416","DOI":"10.1609\/aaai.v38i15.29577","article-title":"Drfuse: learning disentangled representation for clinical multi-modal fusion with missing modality and modal inconsistency","volume":"38","author":"Yao","year":"2024","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"2598","DOI":"10.1109\/TMI.2022.3167808","article-title":"ResViT: residual vision transformers for multimodal medical image synthesis","volume":"41","author":"Dalmaz","year":"2022","journal-title":"IEEE Trans Med Imaging"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1802113\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:29:33Z","timestamp":1773293373000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1802113\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":35,"alternative-id":["10.3389\/fmed.2026.1802113"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1802113","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]},"article-number":"1802113"}}