{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:33:43Z","timestamp":1776375223998,"version":"3.51.2"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conventional white light (WL) endoscopy video stream without virtual chromoendoscopy (blue light, BL). In this work, we evaluated the standalone performance of this computer-aided diagnosis device (CADx) on a prospectively acquired dataset of unaltered colonoscopy videos. An international group of endoscopists performed optical characterization of each polyp acquired in a prospective study, blinded to both histology and CADx result, by means of an online platform enabling careful video assessment. Colorectal polyps were categorized by reviewers, subdivided into 10 experts and 11 non-experts endoscopists, and by the CADx as either \u201cadenoma\u201d or \u201cnon-adenoma\u201d. A total of 513 polyps from 165 patients were assessed. CADx accuracy in WL was found comparable to the accuracy of expert endoscopists (CADx<jats:sub>WL<\/jats:sub>\/Exp; OR 1.211 [0.766\u20131.915]) using histopathology as the reference standard. Moreover, CADx accuracy in WL was found superior to the accuracy of non-expert endoscopists (CADx<jats:sub>WL<\/jats:sub>\/NonExp; OR 1.875 [1.191\u20132.953]), and CADx accuracy in BL was found comparable to it (CADx<jats:sub>BL<\/jats:sub>\/CADx<jats:sub>WL<\/jats:sub>; OR 0.886 [0.612\u20131.282]). The proposed intelligent device shows the potential to support non-expert endoscopists in systematically reaching the performances of expert endoscopists in optical characterization.<\/jats:p>","DOI":"10.1038\/s41746-022-00633-6","type":"journal-article","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T10:02:56Z","timestamp":1656583376000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["A novel AI device for real-time optical characterization of colorectal polyps"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4913-7441","authenticated-orcid":false,"given":"Carlo","family":"Biffi","sequence":"first","affiliation":[]},{"given":"Pietro","family":"Salvagnini","sequence":"additional","affiliation":[]},{"given":"Nhan Ngo","family":"Dinh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7167-1459","authenticated-orcid":false,"given":"Cesare","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Prateek","family":"Sharma","sequence":"additional","affiliation":[]},{"name":"GI Genius CADx Study Group","sequence":"additional","affiliation":[]},{"given":"Giulio","family":"Antonelli","sequence":"additional","affiliation":[]},{"given":"Halim","family":"Awadie","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Bernhofer","sequence":"additional","affiliation":[]},{"given":"Sabela","family":"Carballal","sequence":"additional","affiliation":[]},{"given":"M\u00e1rio","family":"Dinis-Ribeiro","sequence":"additional","affiliation":[]},{"given":"Agn\u00e8s","family":"Fern\u00e1ndez-Clotet","sequence":"additional","affiliation":[]},{"given":"Gl\u00f2ria Fern\u00e1ndez","family":"Esparrach","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Gralnek","sequence":"additional","affiliation":[]},{"given":"Yuta","family":"Higasa","sequence":"additional","affiliation":[]},{"given":"Taku","family":"Hirabayashi","sequence":"additional","affiliation":[]},{"given":"Tatsuki","family":"Hirai","sequence":"additional","affiliation":[]},{"given":"Mineo","family":"Iwatate","sequence":"additional","affiliation":[]},{"given":"Miki","family":"Kawano","sequence":"additional","affiliation":[]},{"given":"Markus","family":"Mader","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Maieron","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Mattes","sequence":"additional","affiliation":[]},{"given":"Tastuya","family":"Nakai","sequence":"additional","affiliation":[]},{"given":"Ingrid","family":"Ordas","sequence":"additional","affiliation":[]},{"given":"Raquel","family":"Ortig\u00e3o","sequence":"additional","affiliation":[]},{"given":"Oswaldo Ortiz","family":"Z\u00fa\u00f1iga","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Pellis\u00e9","sequence":"additional","affiliation":[]},{"given":"Cl\u00e1udia","family":"Pinto","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Riedl","sequence":"additional","affiliation":[]},{"given":"Ariadna","family":"S\u00e1nchez","sequence":"additional","affiliation":[]},{"given":"Emanuel","family":"Steiner","sequence":"additional","affiliation":[]},{"given":"Yukari","family":"Tanaka","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5946-4390","authenticated-orcid":false,"given":"Andrea","family":"Cherubini","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,30]]},"reference":[{"key":"633_CR1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung, H. et al. Global Cancer Statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 71, 209\u2013249 (2021).","journal-title":"CA Cancer J. Clin."},{"key":"633_CR2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1053\/j.gastro.2017.04.006","volume":"153","author":"MF Kaminski","year":"2017","unstructured":"Kaminski, M. F. et al. Increased rate of adenoma detection associates with reduced risk of colorectal cancer and death. Gastroenterology 153, 98\u2013105 (2017).","journal-title":"Gastroenterology"},{"key":"633_CR3","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1038\/ajg.2017.174","volume":"112","author":"DK Rex","year":"2017","unstructured":"Rex, D. K. et al. Colorectal cancer screening: recommendations for physicians and patients from the U.S. multi-society task force on colorectal cancer. Am. J. Gastroenterol. 112, 1016\u20131030 (2017).","journal-title":"Am. J. Gastroenterol."},{"key":"633_CR4","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1055\/a-1031-7657","volume":"51","author":"R Bisschops","year":"2019","unstructured":"Bisschops, R. et al. Advanced imaging for detection and differentiation of colorectal neoplasia: European society of Gastrointestinal Endoscopy (ESGE) guideline\u2013update 2019. Endoscopy 51, 1155\u20131179 (2019).","journal-title":"Endoscopy"},{"key":"633_CR5","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1111\/den.12644","volume":"28","author":"Y Sano","year":"2016","unstructured":"Sano, Y. et al. Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team. Dig. Endoscopy 28, 526\u2013533 (2016).","journal-title":"Dig. Endoscopy"},{"key":"633_CR6","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1055\/s-0043-121570","volume":"50","author":"R Bisschops","year":"2018","unstructured":"Bisschops, R. et al. BASIC (BLI Adenoma Serrated International Classification) classification for colorectal polyp characterization with blue light imaging. Endoscopy 50, 211\u2013220 (2018).","journal-title":"Endoscopy"},{"key":"633_CR7","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1055\/s-0044-100791","volume":"50","author":"M Iacucci","year":"2018","unstructured":"Iacucci, M. et al. Development and validation of the simple endoscopic classification of diminutive and small colorectal polyps. Endoscopy 50, 779\u2013789 (2018).","journal-title":"Endoscopy"},{"key":"633_CR8","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.gie.2014.06.020","volume":"81","author":"MA Manfredi","year":"2015","unstructured":"Manfredi, M. A. et al. Electronic chromoendoscopy. Gastrointest. Endoscopy 81, 249\u2013261 (2015).","journal-title":"Gastrointest. Endoscopy"},{"key":"633_CR9","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1053\/j.gastro.2012.09.054","volume":"144","author":"U Ladabaum","year":"2013","unstructured":"Ladabaum, U. et al. Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions. Gastroenterology 144, 81\u201391 (2013).","journal-title":"Gastroenterology"},{"key":"633_CR10","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1136\/gutjnl-2015-310584","volume":"66","author":"CJ Rees","year":"2017","unstructured":"Rees, C. J. et al. Narrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study. Gut 66, 887\u2013895 (2017).","journal-title":"Gut"},{"key":"633_CR11","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S2468-1253(18)30282-6","volume":"4","author":"OF Ahmad","year":"2019","unstructured":"Ahmad, O. F. et al. Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. Lancet Gastroenterol. Hepatol. 4, 71\u201380 (2019).","journal-title":"Lancet Gastroenterol. Hepatol."},{"key":"633_CR12","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1016\/j.gie.2020.06.035","volume":"92","author":"TM Berzin","year":"2020","unstructured":"Berzin, T. M. et al. Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force. Gastrointest. Endoscopy 92, 951\u2013959 (2020).","journal-title":"Gastrointest. Endoscopy"},{"key":"633_CR13","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/s12599-019-00595-2","volume":"61","author":"D Dellermann","year":"2019","unstructured":"Dellermann, D., Ebel, P., S\u00f6llner, M. & Leimeister, J. Hybrid intelligence. Bus. Inf. Syst. Eng. 61, 637\u2013643 (2019).","journal-title":"Bus. Inf. Syst. Eng."},{"key":"633_CR14","unstructured":"FDA. FDA Authorizes Marketing of First Device that Uses Artificial Intelligence to Help Detect Potential Signs of Colon Cancer. https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-authorizes-marketing-first-device-uses-artificial-intelligence-help-detect-potential-signs-colon (2021)."},{"key":"633_CR15","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/j.gie.2020.05.040","volume":"92","author":"T Walradt","year":"2020","unstructured":"Walradt, T., Glissen Brown, J. R., Alagappan, M., Lerner, H. P. & Berzin, T. M. Regulatory considerations for artificial intelligence technologies in GI endoscopy. Gastrointest. Endoscopy 92, 801\u2013806 (2020).","journal-title":"Gastrointest. Endoscopy"},{"key":"633_CR16","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1053\/j.gastro.2020.04.062","volume":"159","author":"A Repici","year":"2020","unstructured":"Repici, A. et al. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology 159, 512\u2013520 (2020).","journal-title":"Gastroenterology"},{"key":"633_CR17","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/S2468-1253(19)30411-X","volume":"5","author":"P Wang","year":"2020","unstructured":"Wang, P. et al. Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study. Lancet Gastroenterol. Hepatol. 5, 343\u2013351 (2020).","journal-title":"Lancet Gastroenterol. Hepatol."},{"key":"633_CR18","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1136\/gutjnl-2021-324471","volume":"71","author":"A Repici","year":"2021","unstructured":"Repici, A. et al. Artificial intelligence and colonoscopy experience: lessons from two randomised trials. Gut 71, 757\u2013765 (2021).","journal-title":"Gut"},{"key":"633_CR19","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.giec.2021.05.010","volume":"31","author":"JR Glissen Brown","year":"2021","unstructured":"Glissen Brown, J. R. & Berzin, T. M. Adoption of new technologies: artificial intelligence. Gastrointest. Endosc. Clin. N. A. 31, 743\u2013758 (2021).","journal-title":"Gastrointest. Endosc. Clin. N. A."},{"key":"633_CR20","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1136\/gutjnl-2017-314547","volume":"68","author":"MF Byrne","year":"2019","unstructured":"Byrne, M. F. et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 68, 94\u2013100 (2019).","journal-title":"Gut"},{"key":"633_CR21","doi-asserted-by":"publisher","first-page":"357","DOI":"10.7326\/M18-0249","volume":"169","author":"Y Mori","year":"2018","unstructured":"Mori, Y. et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann. Intern. Med. 169, 357\u2013366 (2018).","journal-title":"Ann. Intern. Med."},{"key":"633_CR22","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1016\/j.neucom.2020.02.123","volume":"423","author":"A Nogueira-Rodr\u00edguez","year":"2021","unstructured":"Nogueira-Rodr\u00edguez, A. et al. Deep neural networks approaches for detecting and classifying colorectal polyps. Neurocomputing 423, 721\u2013734 (2021).","journal-title":"Neurocomputing"},{"key":"633_CR23","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1055\/a-0831-2348","volume":"51","author":"P Ponugoti","year":"2019","unstructured":"Ponugoti, P. et al. Disagreement between high confidence endoscopic adenoma prediction and histopathological diagnosis in colonic lesions \u2264 3 mm in size. Endoscopy 51, 221\u2013226 (2019).","journal-title":"Endoscopy"},{"key":"633_CR24","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1053\/j.gastro.2019.10.024","volume":"158","author":"N Shahidi","year":"2020","unstructured":"Shahidi, N. et al. Use of endoscopic impression, artificial intelligence, and pathologist interpretation to resolve discrepancies between endoscopy and pathology analyses of diminutive colorectal polyps. Gastroenterology 158, 783\u2013785 (2020).","journal-title":"Gastroenterology"},{"key":"633_CR25","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1055\/a-0832-8381","volume":"51","author":"M Vieth","year":"2019","unstructured":"Vieth, M. & Neurath, M. F. Challenges for the crosstalk between endoscopists and pathologists. Endoscopy 51, 212\u2013214 (2019).","journal-title":"Endoscopy"},{"key":"633_CR26","doi-asserted-by":"publisher","first-page":"G49","DOI":"10.1046\/j.1440-1746.2000.02266.x","volume":"15","author":"RJ Schlemper","year":"2000","unstructured":"Schlemper, R. J., Kato, Y. & Stolte, M. Diagnostic criteria for gastrointestinal carcinomas in japan and western countries: proposal for a new classification system of gastrointestinal epithelial neoplasia. J. Gastroenterol. Hepatol. 15, G49\u2013G57 (2000).","journal-title":"J. Gastroenterol. Hepatol."},{"key":"633_CR27","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1136\/gutjnl-2014-308411","volume":"65","author":"J IJspeert","year":"2016","unstructured":"IJspeert, J. et al. Development and validation of the WASP classification system for optical diagnosis of adenomas, hyperplastic polyps and sessile serrated adenomas\/polyps. Gut 65, 963\u2013970 (2016).","journal-title":"Gut"},{"key":"633_CR28","doi-asserted-by":"crossref","unstructured":"Wei, J. et al. Learn like a pathologist: curriculum learning by annotator agreement for histopathology image classification. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2473\u20132483 (2021).","DOI":"10.1109\/WACV48630.2021.00252"},{"key":"633_CR29","unstructured":"Thulasidasan, S., Chennupati, G., Bilmes, J. A., Bhattacharya, T. & Michalak, S. On mixup training: Improved calibration and predictive uncertainty for deep neural networks. Adv. Neural. Inf. Process. Syst. 32, (2016)."},{"key":"633_CR30","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F. & Upcroft, B. Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP), 3464\u20133468 (IEEE, 2016).","DOI":"10.1109\/ICIP.2016.7533003"}],"updated-by":[{"DOI":"10.1038\/s41746-022-00669-8","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T00:00:00Z","timestamp":1660608000000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00633-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00633-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00633-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T08:05:06Z","timestamp":1669363506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00633-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["633"],"URL":"https:\/\/doi.org\/10.1038\/s41746-022-00633-6","relation":{"correction":[{"id-type":"doi","id":"10.1038\/s41746-022-00669-8","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"4 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2022","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-022-00669-8","URL":"https:\/\/doi.org\/10.1038\/s41746-022-00669-8","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"C.B., Pi.S., N.N.D., and A.C. are inventors of patents related to the submitted work and are employees of the company manufacturing the device. C.H. is consultant for Medtronic and Fujifilm. Pr.S. is a consultant for Medtronic, Olympus, Boston Scientific, Fujifilm, Lumendi, and receives grant support from Ironwood, Erbe, Docbot, Cosmo Pharmaceuticals, and CDx Labs.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"84"}}