{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:33:46Z","timestamp":1781148826004,"version":"3.54.1"},"reference-count":38,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T00:00:00Z","timestamp":1665705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background and Aims: The aim of our study was to create an accurate patient-level combined algorithm for the identification of ulcers on CE images from two different capsules. Methods: We retrospectively collected CE images from PillCam-SB3\u2032s capsule and PillCam-Crohn\u2019s capsule. ML algorithms were trained to classify small bowel CE images into either normal or ulcerated mucosa: a separate model for each capsule type, a cross-domain model (training the model on one capsule type and testing on the other), and a combined model. Results: The dataset included 33,100 CE images: 20,621 PillCam-SB3 images and 12,479 PillCam-Crohn\u2019s images, of which 3582 were colonic images. There were 15,684 normal mucosa images and 17,416 ulcerated mucosa images. While the separate model for each capsule type achieved excellent accuracy (average AUC 0.95 and 0.98, respectively), the cross-domain model achieved a wide range of accuracies (0.569\u20130.88) with an AUC of 0.93. The combined model achieved the best results with an average AUC of 0.99 and average mean patient accuracy of 0.974. Conclusions: A combined model for two different capsules provided high and consistent diagnostic accuracy. Creating a holistic AI model for automated capsule reading is an essential part of the refinement required in ML models on the way to adapting them to clinical practice.<\/jats:p>","DOI":"10.3390\/diagnostics12102490","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:04:55Z","timestamp":1665965095000},"page":"2490","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Deep Learning Multi-Domain Model Provides Accurate Detection and Grading of Mucosal Ulcers in Different Capsule Endoscopy Types"],"prefix":"10.3390","volume":"12","author":[{"given":"Tom","family":"Kratter","sequence":"first","affiliation":[{"name":"Penta-AI, Tel Aviv 6701101, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noam","family":"Shapira","sequence":"additional","affiliation":[{"name":"Penta-AI, Tel Aviv 6701101, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yarden","family":"Lev","sequence":"additional","affiliation":[{"name":"Penta-AI, Tel Aviv 6701101, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8230-2528","authenticated-orcid":false,"given":"Or","family":"Mauda","sequence":"additional","affiliation":[{"name":"Penta-AI, Tel Aviv 6701101, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehonatan","family":"Moshkovitz","sequence":"additional","affiliation":[{"name":"Penta-AI, Tel Aviv 6701101, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roni","family":"Shitrit","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Ben-Gurion University of the Negev, Be\u2019er Sheva 8410501, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shani","family":"Konyo","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine E, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"},{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8601-6550","authenticated-orcid":false,"given":"Offir","family":"Ukashi","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lior","family":"Dar","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oranit","family":"Shlomi","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Internal Medicine F, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Albshesh","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7853-2029","authenticated-orcid":false,"given":"Shelly","family":"Soffer","sequence":"additional","affiliation":[{"name":"Internal Medicine B, Assuta Medical Center, Ashdod, Israel, Ben-Gurion University of the Negev, Be\u2019er Sheva 8410501, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyal","family":"Klang","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Sami Sagol AI Hub, ARC, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shomron","family":"Ben Horin","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rami","family":"Eliakim","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uri","family":"Kopylov","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reuma","family":"Margalit Yehuda","sequence":"additional","affiliation":[{"name":"Sackler School of Medicine, Tel Aviv University, P.O.B 39040, Tel Aviv 6997801, Israel"},{"name":"Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Ramat Gan 5262100, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1097\/MOG.0000000000000159","article-title":"Diagnostic modalities for the evaluation of small bowel disorders","volume":"31","author":"Kopylov","year":"2015","journal-title":"Curr. Opin. Gastroenterol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"129","DOI":"10.2147\/CEG.S48005","article-title":"Clinical applications of small bowel capsule endoscopy","volume":"6","author":"Kopylov","year":"2013","journal-title":"Clin. Exp. Gastroenterol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1097\/MOG.0b013e3282f3d946","article-title":"Video capsule endoscopy of the small bowel","volume":"24","author":"Eliakim","year":"2008","journal-title":"Curr. Opin. Gastroenterol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1055\/s-0034-1391855","article-title":"Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) clinical guideline","volume":"47","author":"Pennazio","year":"2015","journal-title":"Endoscopy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.gie.2006.01.014","article-title":"ASGE technology status evaluation report: Wireless capsule endoscopy","volume":"63","author":"Mishkin","year":"2006","journal-title":"Gastrointest. Endosc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1080\/17474124.2017.1359541","article-title":"Monitoring of small bowel Crohn\u2019s disease","volume":"11","author":"Kopylov","year":"2017","journal-title":"Exp. Rev. Gastroenterol. Hepatol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1016\/j.gie.2018.07.035","article-title":"Utility of video capsule endoscopy for longitudinal monitoring of Crohn\u2019s disease activity in the small bowel: A prospective study","volume":"88","author":"Melmed","year":"2018","journal-title":"Gastrointest. Endosc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1097\/MOG.0b013e328334df17","article-title":"Video capsule endoscopy of the small bowel","volume":"26","author":"Eliakim","year":"2010","journal-title":"Curr. Opin. Gastroenterol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1007\/s00261-008-9431-5","article-title":"Capsule enteroscopy of the small intestine","volume":"34","author":"Waterman","year":"2009","journal-title":"Abdom. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1097\/MIB.0000000000000255","article-title":"Small bowel capsule endoscopy in the management of established Crohn\u2019s disease: Clinical impact, safety, and correlation with inflammatory biomarkers","volume":"21","author":"Kopylov","year":"2015","journal-title":"Inflamm. Bowel Dis."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/S2468-1253(19)30088-3","article-title":"Assessment of small bowel mucosal healing by video capsule endoscopy for the prediction of short-term and long-term risk of Crohn\u2019s disease flare: A prospective cohort study","volume":"4","author":"Lahat","year":"2019","journal-title":"Lancet Gastroenterol. Hepatol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1093\/ecco-jcc\/jjy113","article-title":"ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications","volume":"13","author":"Maaser","year":"2019","journal-title":"J. Crohn\u2019s Colitis"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1093\/ecco-jcc\/jjy114","article-title":"ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 2: IBD scores and general principles and technical aspects","volume":"13","author":"Sturm","year":"2019","journal-title":"J. Crohn\u2019s Colitis"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1148\/radiol.2018180547","article-title":"Convolutional Neural Networks for Radiologic Images: A Radiologist\u2019s Guide","volume":"290","author":"Soffer","year":"2019","journal-title":"Radiology"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jia, X., and Meng, M.Q.-H. (2016, January 16\u201320). A deep convolutional neural network for bleeding detection in wireless capsule endoscopy images. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7590783"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1111\/jgh.14941","article-title":"Automatic detection of blood content in capsule endoscopy images based on a deep convolutional neural network","volume":"35","author":"Aoki","year":"2020","journal-title":"J. Gastroenterol. Hepatol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jia, X., and Meng, M.Q.-.H. (2017, January 11\u201315). Gastrointestinal bleeding detection in wireless capsule endoscopy images using handcrafted and CNN features. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju Island, Korea.","DOI":"10.1109\/EMBC.2017.8037526"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.gie.2018.06.036","article-title":"A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy","volume":"89","author":"Leenhardt","year":"2019","journal-title":"Gastrointest. Endosc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1111\/den.13507","article-title":"Artificial intelligence using a convolutional neural network for automatic detection of small-bowel angioectasia in capsule endoscopy images","volume":"32","author":"Tsuboi","year":"2020","journal-title":"Dig. Endosc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mascarenhas Saraiva, M., Ribeiro, T., Afonso, J., Andrade, P., Cardoso, P., Ferreira, J., Cardoso, H., and Macedo, G. (2021). Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia. Medicina, 57.","DOI":"10.3390\/medicina57121378"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1093\/ecco-jcc\/jjaa234","article-title":"Automated Detection of Crohn\u2019s Disease Intestinal Strictures on Capsule Endoscopy Images Using Deep Neural Networks","volume":"15","author":"Klang","year":"2021","journal-title":"J. Crohn\u2019s Colitis"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105236","DOI":"10.1016\/j.cmpb.2019.105236","article-title":"Celiac disease diagnosis from video capsule endoscopy images with residual learning and deep feature extraction","volume":"187","author":"Wang","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4071","DOI":"10.1038\/s41598-022-07199-z","article-title":"Automated detection of celiac disease using Machine Learning Algorithms","volume":"12","author":"Stoleru","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1109\/TIP.2018.2801119","article-title":"Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning","volume":"27","author":"He","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.gie.2019.11.012","article-title":"Deep learning algorithms for automated detection of Crohn\u2019s disease ulcers by video capsule endoscopy","volume":"91","author":"Klang","year":"2020","journal-title":"Gastrointest. Endosc."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.gie.2020.05.066","article-title":"Ulcer severity grading in video capsule images of patients with Crohn\u2019s disease: An ordinal neural network solution","volume":"93","author":"Barash","year":"2021","journal-title":"Gastrointest. Endosc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"165001","DOI":"10.1088\/1361-6560\/aad51c","article-title":"Computer-aided detection of small intestinal ulcer and erosion in wireless capsule endoscopy images","volume":"63","author":"Fan","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Alaskar, H., Hussain, A., Al-Aseem, N., Liatsis, P., and Al-Jumeily, D. (2019). Application of convolutional neural networks for automated ulcer detection in wireless capsule endoscopy images. Sensors, 19.","DOI":"10.3390\/s19061265"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.gie.2018.10.027","article-title":"Automatic detection of erosions and ulcerations in wireless capsule endoscopy images based on a deep convolutional neural network","volume":"89","author":"Aoki","year":"2019","journal-title":"Gastrointest. Endosc."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"235014","DOI":"10.1088\/1361-6560\/ab5086","article-title":"A systematic evaluation and optimization of automatic detection of ulcers in wireless capsule endoscopy on a large dataset using deep convolutional neural networks","volume":"64","author":"Wang","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"656493","DOI":"10.3389\/fmed.2021.656493","article-title":"A Convolutional Neural Network Deep Learning Model Trained on CD Ulcers Images Accurately Identifies NSAID Ulcers","volume":"8","author":"Klang","year":"2021","journal-title":"Front. Med."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/s11517-021-02486-9","article-title":"Automated detection of ulcers and erosions in capsule endoscopy images using a convolutional neural network","volume":"60","author":"Afonso","year":"2022","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1093\/ecco-jcc\/jjab117","article-title":"Identification of Ulcers and Erosions by the Novel Pillcam\u2122 Crohn\u2019s Capsule Using a Convolutional Neural Network: A Multicentre Pilot Study","volume":"16","author":"Ferreira","year":"2022","journal-title":"J. Crohn\u2019s Colitis"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.21037\/jtd.2018.02.76","article-title":"Deep learning and medical imaging","volume":"10","author":"Klang","year":"2018","journal-title":"J. Thorac. Dis."},{"key":"ref_35","unstructured":"Mingxing, T., and Quoc, V.L. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. arXiv.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e33267","DOI":"10.2196\/33267","article-title":"Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis","volume":"23","author":"Bang","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1016\/j.dld.2021.08.026","article-title":"A multisystem-compatible deep learning-based algorithm for detection and characterization of angiectasias in small-bowel capsule endoscopy. A proof-of-concept study","volume":"53","author":"Houdeville","year":"2021","journal-title":"Dig. Liver Dis."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/10\/2490\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:54:29Z","timestamp":1760144069000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/10\/2490"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,14]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["diagnostics12102490"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics12102490","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,14]]}}}