{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:06:13Z","timestamp":1783987573199,"version":"3.55.0"},"reference-count":42,"publisher":"Georg Thieme Verlag KG","issue":"CP","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Romanian Ministry of Research, Innovation and Digitization, CNCS-UEFISCDI","award":["PN-IV-P2-2.2-MC-2024-0624"],"award-info":[{"award-number":["PN-IV-P2-2.2-MC-2024-0624"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Endosc Int Open"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Introduction Colorectal cancer is a major global health concern, with colonoscopy as the gold standard for detection and prevention. Accurate localization of findings remains challenging, limiting reporting objectivity and completeness, which can be supported by artificial intelligence (AI). We present an AI system that identifies the appendiceal orifice, ileocecal valve, and flexures, enabling automated colon segment localization.<\/jats:p>\n                  <jats:p>Methods The AI was trained on 7264 manually annotated images from 991 patients and internally evaluated on 1238 images from 215 patients. Performance was assessed using accuracy, sensitivity, specificity, and F1-score. External validation was conducted on 78 public videos. The impact on standardized reporting was evaluated on 14 videos recorded in a different external clinic that did not contribute training data. These were independently evaluated by two expert endoscopists who reached a consensus that was used as the gold standard for flexure detection.<\/jats:p>\n                  <jats:p>Results On the internal image test set, the AI achieved 94.5% accuracy, 76.7% sensitivity, 97.0% specificity, and 0.79 F1-score. In external validation on videos from a public dataset, the AI identified 91.7% of cecum segments and 66% of flexures, with 81.4% detected within 30 s of annotation. AI integration improved flexure identification in the external video dataset from the second clinic, increasing detected flexures by 53.8% and videos with both flexures identified by 133.3%.<\/jats:p>\n                  <jats:p>Conclusions The AI reliably detects key anatomical landmarks, supporting colon segment localization. Its integration into reporting pipelines could enhance lesion localization, improve report completeness, and reduce documentation workload.<\/jats:p>","DOI":"10.1055\/a-2900-1202","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T23:22:56Z","timestamp":1783984976000},"source":"Crossref","is-referenced-by-count":0,"special_numbering":"S","title":["Artificial Intelligence\u2013Assisted Flexure and Landmark Identification Improves Reporting Completeness in Colonoscopy"],"prefix":"10.1055","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5108-4740","authenticated-orcid":false,"given":"Radu-Alexandru","family":"Vulpoi","sequence":"first","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, IS, Romania","place":["Ia\u0219i"],"department":["Institute of Gastroenterology and Hepatology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3533-2246","authenticated-orcid":false,"given":"Ioannis","family":"Kafetzis","sequence":"first","affiliation":[{"name":"University Hospital W\u00fcrzburg, Germany","place":["W\u00fcrzburg"],"department":["Department of Internal Medicine 2, Interventional and Experimental Endoscopy (InExEn)"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihaela","family":"Luca","sequence":"additional","affiliation":[{"name":"Romanian Academy, Romania","place":["Ia\u015fi"],"department":["Institute of Computer Science, Iasi Branch"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4473-6645","authenticated-orcid":false,"given":"Adrian","family":"Ciobanu","sequence":"additional","affiliation":[{"name":"Romanian Academy, Romania","place":["Ia\u015fi"],"department":["Institute of Computer Science, Iasi Branch"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oana Bogdana","family":"Barboi","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, IS, Romania","place":["Ia\u0219i"],"department":["Institute of Gastroenterology and Hepatology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian","family":"Gheorghe","sequence":"additional","affiliation":[{"name":"University of Medicine and Pharmacy Carol Davila Bucharest, Bucharest, Romania","place":["Bucharest"],"department":["Center of Gastroenterology and Hepatology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugen","family":"Dumitru","sequence":"additional","affiliation":[{"name":"Ovidius University of Constanta, Romania","place":["Constanta"],"department":["Faculty of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Meining","sequence":"additional","affiliation":[{"name":"University Hospital W\u00fcrzburg, Germany","place":["W\u00fcrzburg"],"department":["Department of Internal Medicine 2, Interventional and Experimental Endoscopy (InExEn)"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8035-3559","authenticated-orcid":false,"given":"Alexander","family":"Hann","sequence":"additional","affiliation":[{"name":"University Hospital W\u00fcrzburg, Germany","place":["W\u00fcrzburg"],"department":["Department of Internal Medicine 2, Interventional and Experimental Endoscopy (InExEn)"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasile Liviu","family":"Drug","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, IS, Romania","place":["Ia\u0219i"],"department":["Institute of Gastroenterology and Hepatology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"issue":"03","key":"ref1","doi-asserted-by":"publisher","first-page":"463.e5","DOI":"10.1016\/j.gie.2020.01.014","article-title":"Recommendations for follow-up after colonoscopy and Polypectomy: a consensus update by the US multi-society task force on colorectal cancer","volume":"91","author":"S Gupta","year":"2020","journal-title":"Gastrointest Endosc"},{"issue":"03","key":"ref2","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1055\/S-0042-100186","article-title":"Requirements and standards facilitating quality improvement for reporting systems in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) position statement","volume":"48","author":"M Bretthauer","year":"2016","journal-title":"Endoscopy"},{"issue":"03","key":"ref3","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1159\/000538113","article-title":"Closing the gap: a critical examination of adherence, inconsistency, and improvements in colonoscopy reporting practices","volume":"105","author":"T J Lux","year":"2024","journal-title":"Digestion"},{"issue":"06","key":"ref4","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1007\/S00384-022-04178-8","article-title":"Pilot study of a new freely available computer-aided polyp detection system in clinical practice","volume":"37","author":"T J Lux","year":"2022","journal-title":"Int J Color Dis"},{"issue":"06","key":"ref5","doi-asserted-by":"publisher","first-page":"357","DOI":"10.7326\/M18-0249","article-title":"Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study","volume":"169","author":"Y Mori","year":"2018","journal-title":"Ann Intern Med"},{"issue":"05","key":"ref6","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1136\/GUTJNL-2019-319914","article-title":"New artificial intelligence system: first validation study versus experienced endoscopists for colorectal polyp detection","volume":"69","author":"C Hassan","year":"2020","journal-title":"Gut"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1136\/GUTJNL-2025-335091","article-title":"Large language models for detecting colorectal polyps in endoscopic images","author":"L Carlini","year":"2025","journal-title":"Gut"},{"issue":"10","key":"ref8","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/S2468-1253(24)00161-4","article-title":"Polyp detection with colonoscopy assisted by the GI genius artificial intelligence endoscopy module compared with standard colonoscopy in routine colonoscopy practice (COLO-DETECT): a multicentre, open-label, parallel-arm, pragmatic randomised controlled trial","volume":"9","author":"A Seager","year":"2024","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"07","key":"ref9","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1016\/j.cgh.2021.09.009","article-title":"Deep learning computer-aided polyp detection reduces adenoma miss rate: a United States multi-center randomized tandem colonoscopy study (CADeT-CS trial)","volume":"20","author":"J R Glissen Brown","year":"2022","journal-title":"Clin Gastroenterol Hepatol"},{"issue":"01","key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/S41746-022-00633-6","article-title":"A novel AI device for real-time optical characterization of colorectal polyps","volume":"5","author":"C Biffi","year":"2022","journal-title":"npj Digit Med"},{"issue":"02","key":"ref11","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.cgh.2022.07.006","article-title":"Artificial intelligence\u2013assisted colonoscopy for colorectal cancer screening: a Multicenter randomized controlled trial","volume":"21","author":"H Xu","year":"2023","journal-title":"Clin Gastroenterol Hepatol"},{"issue":"03","key":"ref12","doi-asserted-by":"publisher","first-page":"E413","DOI":"10.1055\/A-2261-2711","article-title":"Artificial intelligence for characterization of colorectal polyps: prospective multicenter study","volume":"12","author":"G De Lange","year":"2024","journal-title":"Endosc Int Open"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1136\/GUTJNL-2025-335441","article-title":"Implementing discard strategies for diminutive polyps using autonomous CADx in clinical practice","author":"M Taghiakbari","year":"2025","journal-title":"Gut"},{"issue":"01","key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/S41597-025-05251-X","article-title":"Polyp-size: a precise endoscopic dataset for AI-driven polyp sizing","volume":"12","author":"Y Song","year":"2025","journal-title":"Sci Data"},{"issue":"09","key":"ref15","doi-asserted-by":"publisher","DOI":"10.1055\/A-2077-7398","article-title":"Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference","volume":"55","author":"B Sudarevic","year":"2023","journal-title":"Endoscopy"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1055\/A-2556-1836","article-title":"Use of artificial intelligence to measure colorectal polyp size without a reference object","volume":"13","author":"C-Y Yii","year":"2025","journal-title":"Endosc Int Open"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1055\/A-2695-1978","article-title":"Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy","author":"G Antonelli","journal-title":"Endoscopy"},{"issue":"03","key":"ref18","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3390\/JIMAGING11030084\/S1","article-title":"Deep learning-based semantic segmentation for objective colonoscopy quality assessment","volume":"11","author":"R A Vulpoi","year":"2025","journal-title":"J Imaging"},{"issue":"01","key":"ref19","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.gie.2019.03.019","article-title":"Quality assurance of computer-aided detection and diagnosis in colonoscopy","volume":"90","author":"D G Vinsard","year":"2019","journal-title":"Gastrointest Endosc"},{"issue":"01","key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/DEO2.70150","article-title":"Artificial intelligence-assisted endoscopy and examiner confidence: a study on human-artificial intelligence interaction in Barrett\u2019s Esophagus (with video)","volume":"6","author":"D Roser","year":"2025","journal-title":"DEN Open"},{"issue":"10","key":"ref21","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1055\/A-1770-7353","article-title":"The influence of computer-aided polyp detection systems on reaction time for polyp detection and eye gaze","volume":"54","author":"J Troya","year":"2022","journal-title":"Endoscopy"},{"issue":"02","key":"ref22","doi-asserted-by":"publisher","first-page":"184.e16","DOI":"10.1016\/j.gie.2022.08.043","article-title":"Comprehensive review of publicly available colonoscopic imaging databases for artificial intelligence research: availability, accessibility, and usability","volume":"97","author":"B BSL Houwen","year":"2023","journal-title":"Gastrointest Endosc"},{"issue":"02","key":"ref23","doi-asserted-by":"publisher","first-page":"327","DOI":"10.5946\/CE.2024.213","article-title":"Usefulness of an artificial intelligence-based colonoscopy report generation support system","volume":"58","author":"T Naito","year":"2025","journal-title":"Clin Endosc"},{"issue":"12","key":"ref24","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1055\/A-2122-1671","article-title":"Assisted documentation as a new focus for artificial intelligence in endoscopy: the precedent of reliable withdrawal time and image reporting","volume":"55","author":"T J Lux","year":"2022","journal-title":"Endoscopy"},{"issue":"01","key":"ref25","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/S12565-022-00681-8\/FIGURES\/3","article-title":"Acute colonic flexures: the basis for developing an artificial intelligence-based tool for predicting the course of colonoscopy","volume":"98","author":"S Wozniak","year":"2023","journal-title":"Anat Sci Int"},{"issue":"01","key":"ref27","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1038\/s41746-026-02576-8","article-title":"Artificial intelligence assisted colorectal lesion detection in private practices a randomized controlled study","volume":"9","author":"T J Lux","year":"2026","journal-title":"npj Digit Med"},{"issue":"01","key":"ref28","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1038\/S41597-025-05588-3","article-title":"CAS-colon: a comprehensive colonoscopy anatomical segmentation dataset for artificial intelligence development","volume":"12","author":"Y Song","year":"2025","journal-title":"Sci Data"},{"issue":"03","key":"ref29","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/j.gie.2024.04.2905","article-title":"Quality indicators for colonoscopy","volume":"100","author":"D K Rex","year":"2024","journal-title":"Gastrointest Endosc"},{"issue":"03","key":"ref30","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1111\/ANS.15775","article-title":"Quality indicators in colonoscopy: an evolving paradigm","volume":"90","author":"R Shine","year":"2020","journal-title":"ANZ J Surg"},{"issue":"07","key":"ref31","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1111\/DEN.14627","article-title":"Optimization of colonoscopy quality: comprehensive review of the literature and future perspectives","volume":"35","author":"W F Hsu","year":"2023","journal-title":"Dig Endosc"},{"issue":"04","key":"ref32","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1093\/JCAG\/GWAD017","article-title":"Automated detection of anatomical landmarks during colonoscopy using a deep learning model","volume":"6","author":"M Taghiakbari","year":"2023","journal-title":"J Can Assoc Gastroenterol"},{"issue":"05","key":"ref33","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1159\/000485567","article-title":"Clinical practice impact of the Boston bowel preparation scale in a European country","volume":"25","author":"P Massinha","year":"2018","journal-title":"GE Port J Gastroenterol"},{"issue":"08","key":"ref34","doi-asserted-by":"publisher","first-page":"625","DOI":"10.17235\/REED.2020.7678\/2020","article-title":"Use of the Boston bowel preparation scale in the real life setting: what affects it?","volume":"113","author":"S Saraiva","year":"2021","journal-title":"Rev Esp Enferm Dig"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1016\/j.gie.2008.05.057","article-title":"The Boston bowel preparation scale: a valid and reliable instrument for colonoscopy-oriented research","volume":"69","author":"E J Lai","year":"2009","journal-title":"Gastrointest Endosc"},{"issue":"12","key":"ref36","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.1007\/S10151-023-02789-Z","article-title":"Interobserver agreement on landmark and flexure identification in colon capsule endoscopy","volume":"27","author":"B Schelde-Olesen","year":"2023","journal-title":"Tech Coloproctol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/ICCV48922.2021.00010","article-title":"Going deeper with image transformers","author":"H Touvron","year":"2021","journal-title":"Proc IEEE Int Conf Comput Vis"},{"issue":"06","key":"ref38","doi-asserted-by":"publisher","first-page":"e0325987","DOI":"10.1371\/JOURNAL.PONE.0325987","article-title":"Advancing artificial intelligence applicability in endoscopy through source-agnostic camera signal extraction from endoscopic images","volume":"20","author":"I Kafetzis","year":"2025","journal-title":"PLoS One"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1055\/A-2721-6798","article-title":"A prospective study evaluating an artificial intelligence-based system for withdrawal time measurement","author":"I Kafetzis","year":"2025","journal-title":"Endoscopy"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/CVPRW50498.2020.00020","volume-title":"Score-CAM: score-weighted visual explanations for convolutional neural networks","author":"H Wang","year":"2020"},{"issue":"05","key":"ref41","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1159\/000525345","article-title":"Frame-by-frame analysis of a commercially available artificial intelligence polyp detection system in full-length colonoscopies","volume":"103","author":"M Brand","year":"2022","journal-title":"Digestion"},{"issue":"01","key":"ref43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/S41598-023-51056-6","article-title":"Density clustering-based automatic anatomical section recognition in colonoscopy video using deep learning","volume":"14","author":"B S Kim","year":"2024","journal-title":"Sci Rep"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-3-031-21083-9_3","volume-title":"Colonoscopy landmark detection using vision transformers","author":"A Tamhane","year":"2022"}],"container-title":["Endoscopy International Open"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-2900-1202.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T23:23:01Z","timestamp":1783984981000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-2900-1202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":42,"journal-issue":{"issue":"CP","published-online":{"date-parts":[[2026,1,13]]},"published-print":{"date-parts":[[2026]]}},"alternative-id":["a29001202"],"URL":"https:\/\/doi.org\/10.1055\/a-2900-1202","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["2364-3722","2196-9736"],"issn-type":[{"value":"2364-3722","type":"print"},{"value":"2196-9736","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]}}}