{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:03:41Z","timestamp":1789625021734,"version":"build-2803163510"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This paper introduces a new hybrid deep learning architecture, which is named GINet, to accurately and efficiently classify gastrointestinal (GI) diseases using endoscopic images. Automated diagnosis is not an easy task due to the visual similarity among GI conditions and the class imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>To overcome these challenges, the proposed model is based on EfficientNetV2 for powerful feature extraction, supported by a window-based attention mechanism to capture fine-grained local spatial dependencies. Moreover, a state-space module based on Mamba is added to model long-range global contextual relationships with linear computational complexity. It presents a complete data preprocessing pipeline, including class filtering, imbalance management via augmentation, and a leakage-free train-test split. The dataset consists of nine clinically relevant GI classes, with equal distribution for training. The extracted features are further refined by a channel projection layer, and the combined Window Attention and Mamba modules enable the model to learn local and global representations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Extensive experiments show that the proposed GINet achieves 99.41% validation accuracy after classifier fine-tuning and 93% accuracy on the held-out test set, and high precision, recall, and F1 scores across all classes. Statistical analysis shows that the gains in performance are significant compared to the baseline models. Also, explainable artificial intelligence, as demonstrated by Grad-CAM, shows that the model attends to clinically meaningful regions, promoting transparency and trust.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The suggested solution offers a computationally efficient, accurate and interpretable solution to computer-aided diagnosis of gastrointestinal diseases, and represents a step toward computer-aided diagnosis of gastrointestinal diseases, subject to further validation on external, multi-center data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1952159","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:31:41Z","timestamp":1789623101000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mamba-based state-space modeling with window attention for explainable multi-class gastrointestinal disease diagnosis in endoscopic images"],"prefix":"10.3389","volume":"9","author":[{"given":"Vishesh","family":"Tanwar","sequence":"first","affiliation":[{"name":"Chitkara University Institute of Engineering and Technology, Chitkara University","place":["Rajpura, Punjab, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhisham","family":"Sharma","sequence":"additional","affiliation":[{"name":"Chitkara University Institute of Engineering and Technology, Chitkara University","place":["Rajpura, Punjab, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian L.","family":"Webber","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Kuwait College of Science and Technology","place":["Doha Area, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abolfazl","family":"Mehbodniya","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Kuwait College of Science and Technology","place":["Doha Area, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.3390\/bioengineering12121329","article-title":"Gastrointestinal lesion detection using ensemble deep learning through global contextual information","volume":"12","author":"Aadiwal","year":"2025","journal-title":"Bioengineering"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1007\/s10462-019-09743-2","article-title":"A survey of feature extraction and fusion of deep learning for detection of abnormalities in video endoscopy of gastrointestinal-tract","volume":"53","author":"Ali","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1719145","DOI":"10.3389\/fmed.2025.1719145","article-title":"Artificial intelligence in advanced endoscopic imaging: transforming optical diagnosis in gastroenterology","volume":"12","author":"Bencardino","year":"2026","journal-title":"Front. Med."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1349373","DOI":"10.3389\/fmed.2024.1349373","article-title":"Explainable AI-driven model for gastrointestinal cancer classification","volume":"11","author":"Binzagr","year":"2024","journal-title":"Front. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2701","DOI":"10.3390\/jcm15072701","article-title":"GastroMalign: vision transformer-based framework for early detection and malignancy-risk stratification for high-risk gastrointestinal lesions","volume":"15","author":"Boppana","year":"2026","journal-title":"J. Clin. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"S280","DOI":"10.14309\/01.ajg.0001132660.39069.53","article-title":"Automated classification of gastrointestinal endoscopic findings using a fine-tuned vision transformer","volume":"120","author":"Boppana","year":"2025","journal-title":"Am. J. Gastroenterol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"752","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","volume":"2023","author":"Gu","year":"2023","journal-title":"arXiv"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1007\/s11548-025-03441-x","article-title":"DivGI: Delve into digestive endoscopy image classification","volume":"20","author":"He","year":"2025","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref9","author":"Hosny","year":"2026"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"128852","DOI":"10.1016\/j.eswa.2025.128852","article-title":"Beyond transfer learning: attention-enhanced deep learning framework for multiclass gastrointestinal disease classification","volume":"295","author":"Hosny","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref11","author":"Kakarla","year":"2026"},{"key":"ref12","first-page":"276","volume-title":"Medical Image Understanding and Analysis (MIUA 2025); Lecture Notes in Computer Science","author":"Krenzer","year":"2026"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.ejca.2021.07.012","article-title":"Gastrointestinal cancer classification and prognostication from histology using deep learning: a systematic review","volume":"155","author":"Kuntz","year":"2021","journal-title":"Eur. J. Cancer"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"10166","DOI":"10.48550\/arXiv.2401.10166","article-title":"VMamba: visual state space model","volume":"2024","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"388","DOI":"10.5009\/gnl18384","article-title":"Overview of deep learning in gastrointestinal endoscopy","volume":"13","author":"Min","year":"2019","journal-title":"Gut Liver"},{"key":"ref16","author":"Nath","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"479","DOI":"10.2174\/1573405616666200928144626","article-title":"Detection and classification of gastrointestinal diseases using machine learning","volume":"17","author":"Naz","year":"2021","journal-title":"Curr. Med. Imaging Rev."},{"key":"ref18","author":"Pan","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"854677","DOI":"10.3389\/fmed.2022.854677","article-title":"Development and validation of a deep neural network for accurate identification of endoscopic images from patients with ulcerative colitis and Crohn\u2019s disease","volume":"9","author":"Ruan","year":"2022","journal-title":"Front. Med."},{"key":"ref20","author":"Subedi","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"26502","DOI":"10.48550\/arXiv.2509.26502","article-title":"GastroViT: a vision transformer-based ensemble learning approach for gastrointestinal disease classification with grad-CAM and SHAP visualization","volume":"2025","author":"Tabassum","year":"2025","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"26982","DOI":"10.1038\/s41598-025-12128-x","article-title":"Hybrid deep learning framework based on EfficientViT for classification of gastrointestinal diseases","volume":"15","author":"Tanwar","year":"2025","journal-title":"Sci. Rep."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"66544","DOI":"10.1109\/ACCESS.2023.3290997","article-title":"Recent advances in applying machine learning and deep learning to detect upper gastrointestinal tract lesions","volume":"11","author":"Vania","year":"2023","journal-title":"IEEE Access"},{"key":"ref24","author":"Zhu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1007\/s00371-021-02322-z","article-title":"A systematic review on application of deep learning in digestive system image processing","volume":"39","author":"Zhuang","year":"2023","journal-title":"Vis. Comput."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1952159\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:31:42Z","timestamp":1789623102000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1952159\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":25,"alternative-id":["10.3389\/frai.2026.1952159"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1952159","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]},"article-number":"1952159"}}