{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:04:16Z","timestamp":1789664656306,"version":"4.0.1"},"reference-count":28,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Current artificial intelligence (AI) systems in gastrointestinal (GI) endoscopy primarily emphasize binary detection or static classification, providing limited support for the graded assessment of malignant potential that underpins clinical decision-making. We developed GastroMalign, a transformer-based framework designed to stratify GI lesions according to ordinal disease severity while maintaining clinical interpretability, addressing this unmet need in endoscopic risk assessment. Methods: This retrospective development and validation study used the publicly available GastroVision dataset, comprising 8000 de-identified endoscopic still images from the upper and lower gastrointestinal tract, including the esophagus, stomach, duodenum, colon, rectum, and terminal ileum. GastroMalign integrates a Vision Transformer (ViT) encoder with a Sequential Feature Learner that explicitly models ordinal disease severity along a benign-to-malignant spectrum. The framework produces both categorical risk classification and a continuous malignancy risk score. Images were stratified into training (80%), validation (10%), and test (10%) sets. Performance was compared with convolutional neural network (CNN) baselines and a Swin Transformer. Interpretability was assessed using Score-CAM visualizations reviewed by blinded expert endoscopists. Results: On the held-out test set (n = 800 images), GastroMalign achieved an overall accuracy of 80.06%, precision of 79.65%, recall of 80.06%, and F1-score of 79.17%, with a micro-averaged AUC of 0.98. In comparison, ResNet-50 and DenseNet-121 achieved accuracies of 32.42% and 36.77%, respectively, while the Swin Transformer achieved 60.56% accuracy (AUC = 0.93). Ablation analyses demonstrated a 17% absolute reduction in High-Risk lesion recall when the progression-aware module was removed. Continuous malignancy risk scores increased monotonically across ordinal classes, with mean values &lt; 0.18 for Benign and &gt;0.72 for High-Risk\/Malignant lesions. Score-CAM visualizations demonstrated 92% overlap with clinician-annotated lesion regions. Conclusions: GastroMalign delivers an interpretable, progression-aware AI framework for GI lesion risk stratification that outperforms existing CNN- and transformer-based models. Clinically, GastroMalign is intended as an adjunct decision-support tool during endoscopic review to standardize lesion risk stratification (benign to malignant spectrum), support management decisions (biopsy vs. resection vs. surveillance), and reduce operator-dependent variability by pairing ordinal risk outputs with interpretable visual explanations.<\/jats:p>","DOI":"10.3390\/jcm15072701","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T14:09:54Z","timestamp":1775138994000},"page":"2701","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GastroMalign: Vision Transformer-Based Framework for Early Detection and Malignancy-Risk Stratification for High-Risk Gastrointestinal Lesions"],"prefix":"10.3390","volume":"15","author":[{"given":"Sri Harsha","family":"Boppana","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, Nassau University Medical Center, East Meadow, NY 11554, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7431-1040","authenticated-orcid":false,"given":"Sachin Sravan Kumar","family":"Komati","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Florida International University, Miami, FL 33199, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Medha","family":"Sharath","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Bangalore Medical College and Research Institute, Bangalore 560002, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6914-2187","authenticated-orcid":false,"given":"Aditya","family":"Chandrashekar","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Bangalore Medical College and Research Institute, Bangalore 560002, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9492-2733","authenticated-orcid":false,"given":"Gautam","family":"Maddineni","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology & Hepatology, Creighton University School of Medicine, Omaha, NE 68124, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raja Chandra","family":"Chakinala","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Guthrie Robert Packer Hospital, Sayre, PA 18840, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4239-5808","authenticated-orcid":false,"given":"Pradeep","family":"Yarra","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, The University of Texas Health Science Center at San Antonio, San Antonio, TX 78229, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. David","family":"Mintz","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology & Critical Care Medicine, Johns Hopkins School of Medicine, Baltimore, MD 21205, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"ref_1","first-page":"10","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, Y., Lin, Z., and Wei, M. (2025). Global burden of colorectal cancer in 2022 and projections to 2050: Incidence and mortality estimates from GLOBOCAN. BMC Cancer, 25.","DOI":"10.1186\/s12885-025-15138-0"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.1056\/NEJMoa2208375","article-title":"Effect of Colonoscopy Screening on Risks of Colorectal Cancer and Related Death","volume":"387","author":"Bretthauer","year":"2022","journal-title":"N. Engl. J. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"l5383","DOI":"10.1136\/bmj.l5383","article-title":"Colorectal cancer screening with faecal immunochemical testing, sigmoidoscopy or colonoscopy: A microsimulation modelling study","volume":"367","author":"Buskermolen","year":"2019","journal-title":"BMJ"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1056\/NEJMoa1301969","article-title":"Long-term colorectal-cancer incidence and mortality after lower endoscopy","volume":"369","author":"Nishihara","year":"2013","journal-title":"N. Engl. J. Med."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"US Preventive Services Task Force (2021). Screening for Colorectal Cancer: US Preventive Services Task Force Recommendation Statement. JAMA, 325, 1965\u20131977.","DOI":"10.1001\/jama.2021.6238"},{"key":"ref_7","first-page":"28","article-title":"Factors affecting successful colonoscopy procedures: Single-center experience","volume":"34","author":"Kozan","year":"2018","journal-title":"Turk. J. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1053\/j.gastro.2019.01.260","article-title":"Magnitude, Risk Factors, and Factors Associated with Adenoma Miss Rate of Tandem Colonoscopy: A Systematic Review and Meta-analysis","volume":"156","author":"Zhao","year":"2019","journal-title":"Gastroenterology"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nie, Z., Xu, M., Wang, Z., Lu, X., and Song, W. (2024). A Review of Application of Deep Learning in Endoscopic Image Processing. J. Imaging, 10.","DOI":"10.3390\/jimaging10110275"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1053\/j.gastro.2018.06.037","article-title":"Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy","volume":"155","author":"Urban","year":"2018","journal-title":"Gastroenterology"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, G., Zhou, J., Zhang, Z., Ding, Y., Xia, K., and Xu, X. (2024). AI support for colonoscopy quality control using CNN and transformer architectures. BMC Gastroenterol., 24.","DOI":"10.1186\/s12876-024-03354-0"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"117","DOI":"10.5946\/ce.2020.054","article-title":"Convolutional Neural Network Technology in Endoscopic Imaging: Artificial Intelligence for Endoscopy","volume":"53","author":"Choi","year":"2020","journal-title":"Clin. Endosc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102625","DOI":"10.1016\/j.media.2022.102625","article-title":"Polyp detection on video colonoscopy using a hybrid 2D\/3D CNN","volume":"82","author":"Brandao","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Selvaraj, J., Sadaf, K., Aslam, S.M., and Umapathy, S. (2025). Multiclassification of Colorectal Polyps from Colonoscopy Images Using AI for Early Diagnosis. Diagnostics, 15.","DOI":"10.3390\/diagnostics15101285"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2410","DOI":"10.1007\/s10489-022-03689-9","article-title":"A deep ensemble learning method for colorectal polyp classification with optimized network parameters","volume":"53","author":"Younas","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"10375","DOI":"10.1007\/s00521-021-06496-4","article-title":"Real-time polyp detection model using convolutional neural networks","volume":"34","author":"Herrero","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_17","first-page":"616","article-title":"SwinE-Net: Hybrid deep learning approach to novel polyp segmentation using convolutional neural network and Swin Transformer","volume":"9","author":"Park","year":"2022","journal-title":"J. Comput. Des. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Guo, Y., Bernal, J., and JMatuszewski, B. (2020). Polyp Segmentation with Fully Convolutional Deep Neural Networks-Extended Evaluation Study. J. Imaging, 6.","DOI":"10.3390\/jimaging6070069"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3928","DOI":"10.1007\/s10278-025-01481-y","article-title":"Vision Transformers in Medical Imaging: A Comprehensive Review of Advancements and Applications Across Multiple Diseases","volume":"38","author":"Aburass","year":"2025","journal-title":"J. Imaging Inform. Med."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ayana, G., Barki, H., and Choe, S.W. (2024). Pathological Insights: Enhanced Vision Transformers for the Early Detection of Colorectal Cancer. Cancers, 16.","DOI":"10.3390\/cancers16071441"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106723","DOI":"10.1016\/j.compbiomed.2023.106723","article-title":"Transformer-based multi-task learning for classification and segmentation of gastrointestinal tract endoscopic images","volume":"157","author":"Tang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Jha, D., Sharma, V., Dasu, N., Tomar, N.K., Hicks, S., Bhuyan, M.K., Das, P.K., Riegler, M.A., Halvorsen, P., and Bagci, U. (2023). GastroVision: A multi-class endoscopy image dataset for computer aided gastrointestinal disease detection. Lecture Notes in Computer Science, Springer Nature.","DOI":"10.1007\/978-3-031-47679-2_10"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"102762","DOI":"10.1016\/j.media.2023.102762","article-title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","volume":"85","author":"Li","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_24","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1016\/0092-8674(90)90186-I","article-title":"A genetic model for colorectal tumorigenesis","volume":"61","author":"Fearon","year":"1990","journal-title":"Cell"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"15334","DOI":"10.1038\/s41598-024-63659-8","article-title":"Colon cancer diagnosis by means of explainable deep learning","volume":"14","author":"Martinelli","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"106115","DOI":"10.1016\/j.ijmedinf.2025.106115","article-title":"AI for colon cancer: A focus on classification, detection, and predictive modeling","volume":"206","author":"Merabet","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1136\/gutjnl-2017-314547","article-title":"Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model","volume":"68","author":"Byrne","year":"2019","journal-title":"Gut"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/7\/2701\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T14:26:55Z","timestamp":1775140015000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/7\/2701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":28,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["jcm15072701"],"URL":"https:\/\/doi.org\/10.3390\/jcm15072701","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}