{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:02Z","timestamp":1787702402189,"version":"build-2784847793"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"JSPS KAKENHI","award":["21K07885"],"award-info":[{"award-number":["21K07885"]}]},{"DOI":"10.13039\/100018254","name":"Japanese Foundation for Research and Promotion of Endoscopy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018254","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Surg Endosc"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Computer-aided diagnosis (CAD) systems for predicting deeply invasive colorectal cancer (CRC) have been developed, but their clinical utility remains uncertain. This study aimed to compare the diagnostic accuracy of a CAD system with that of endoscopists using magnifying narrow-band imaging (M-NBI) and magnifying chromoendoscopy (MCE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 303 lesions obtained from a prospective multicenter study were analyzed. CAD diagnoses were classified as high- or low-confidence. The diagnostic accuracy of CAD was compared with that of M-NBI and MCE.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The diagnostic accuracy of the CAD system was 61.3%; sensitivity: 92.3%; specificity: 47.5%; positive predictive value (PPV): 95.4%; negative predictive value (NPV), and 89.1% overall accuracy. Among the 303 lesions, 193 (63.7%) were diagnosed with high confidence, with accuracy rates of 95.3% for high-confidence cases and 78.2% for low-confidence cases. For M-NBI, the sensitivity, specificity, PPV, NPV, and accuracy were 74.2%, 96.3%, 69.7%, 97.0%, and 94.1%, respectively. For MCE, the values were 83.9%, 95.2%, 66.7%, 98.1%, and 94.1%, respectively. The overall accuracy of the CAD system was lesser than that of M-NBI (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.011) and MCE (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.014). However, in high-confidence cases, the diagnostic performance of the CAD system was comparable to that of M-NBI and MCE.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In high-confidence cases, the diagnostic accuracy rates of the CAD system were comparable to those of M-NBI and MCE. However, in low-confidence cases, the accuracy of the CAD system was insufficient, and further evaluations using M-NBI and MCE are necessary.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00464-025-12289-w","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:51:47Z","timestamp":1759938707000},"page":"230-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Computer-aided diagnosis system for predicting deeply invasive colorectal cancer: a comparison with a prospective study using magnifying chromoendoscopy"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5314-9325","authenticated-orcid":false,"given":"Tomoaki","family":"Matsumura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mai","family":"Fujie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukihiro","family":"Nomura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenichiro","family":"Okimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mamoru","family":"Tokunaga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsubasa","family":"Ishikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoki","family":"Akizue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Matsusaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuto","family":"Suzuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiyasu","family":"Kitagawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kengo","family":"Nagashima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshiya","family":"Nakaguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Kato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"issue":"2","key":"12289_CR1","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3322\/caac.21262","volume":"65","author":"LA Torre","year":"2015","unstructured":"Torre LA, Bray F, Siegel RL et al (2015) Global cancer statistics, (2012). CA Cancer J Clin 65(2):87. https:\/\/doi.org\/10.3322\/caac.21262","journal-title":"CA Cancer J Clin"},{"key":"12289_CR2","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1056\/NEJMoa1100370","volume":"366","author":"AG Zauber","year":"2012","unstructured":"Zauber AG, Winawer SJ, O\u2019Brien MJ et al (2012) Colonoscopic polypectomy and long-term prevention of colorectal cancer deaths. N Engl J Med 366:687\u2013696. https:\/\/doi.org\/10.1056\/NEJMoa1100370","journal-title":"N Engl J Med"},{"key":"12289_CR3","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1111\/den.12456","volume":"27","author":"S Tanaka","year":"2015","unstructured":"Tanaka S, Kashida H, Saito Y et al (2015) JGES guidelines for colorectal endoscopic submucosal dissection\/endoscopic mucosal resection. Dig Endosc 27:417\u2013434. https:\/\/doi.org\/10.1111\/den.12456","journal-title":"Dig Endosc"},{"key":"12289_CR4","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1055\/s-0043-102569","volume":"49","author":"M Ferlitsch","year":"2017","unstructured":"Ferlitsch M, Moss A, Hassan C et al (2017) Colorectal polypectomy and endoscopic mucosal resection (EMR): European society of gastrointestinal endoscopy (ESGE) clinical guideline. Endoscopy 49:270\u2013297. https:\/\/doi.org\/10.1055\/s-0043-102569","journal-title":"Endoscopy"},{"key":"12289_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/s0016-5107(04)02391-0","volume":"61","author":"RE Davila","year":"2005","unstructured":"Davila RE, Rajan E, Adler D et al (2005) ASGE guideline: the role of endoscopy in the diagnosis, staging, and management of colorectal cancer. Gastrointest Endosc 61:1\u20137. https:\/\/doi.org\/10.1016\/s0016-5107(04)02391-0","journal-title":"Gastrointest Endosc"},{"issue":"12","key":"12289_CR6","doi-asserted-by":"publisher","first-page":"C6","DOI":"10.1055\/a-1074-5788","volume":"51","author":"R Bisschops","year":"2019","unstructured":"Bisschops R, East JE, Hassan C et al (2019) Advanced imaging for detection and differentiation of colorectal neoplasia: European society of gastrointestinal endoscopy (ESGE) guideline\u2014update 2019. Endoscopy 51(12):C6. https:\/\/doi.org\/10.1055\/a-1074-5788","journal-title":"Endoscopy"},{"key":"12289_CR7","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1136\/gutjnl-2018-316882","volume":"69","author":"JLA Vleugels","year":"2020","unstructured":"Vleugels JLA, Koens L, Dijkgraaf MGW et al (2020) Suboptimal endoscopic cancer recognition in colorectal lesions in a national bowel screening programme. Gut 69:977\u2013980. https:\/\/doi.org\/10.1136\/gutjnl-2018-316882","journal-title":"Gut"},{"key":"12289_CR8","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1055\/s-0042-118449","volume":"49","author":"A Probst","year":"2017","unstructured":"Probst A, Ebigbo A, M\u00e4rkl B et al (2017) Endoscopic submucosal dissection for early rectal neoplasia: experience from a European center. Endoscopy 49:222\u2013232. https:\/\/doi.org\/10.1055\/s-0042-118449","journal-title":"Endoscopy"},{"key":"12289_CR9","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1016\/j.cgh.2013.06.022","volume":"12","author":"T Shimura","year":"2014","unstructured":"Shimura T, Ebi M, Yamada T et al (2014) Magnifying chromoendoscopy and endoscopic ultrasonography measure invasion depth of early stage colorectal cancer with equal accuracy on the basis of a prospective trial. Clin Gastroenterol Hepatol 12:662\u2013668. https:\/\/doi.org\/10.1016\/j.cgh.2013.06.022","journal-title":"Clin Gastroenterol Hepatol"},{"key":"12289_CR10","doi-asserted-by":"publisher","first-page":"357","DOI":"10.7326\/M18-0249","volume":"18","author":"Y Mori","year":"2018","unstructured":"Mori Y, Kudo SE, Misawa M et al (2018) Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann Intern Med 18:357\u2013366. https:\/\/doi.org\/10.7326\/M18-0249","journal-title":"Ann Intern Med"},{"key":"12289_CR11","doi-asserted-by":"publisher","first-page":"911","DOI":"10.7326\/M24-0086","volume":"177","author":"DK Rex","year":"2024","unstructured":"Rex DK, Bhavsar-Burke I, Buckles D et al (2024) Artificial intelligence for real-time prediction of the histology of colorectal polyps by general endoscopists. Ann Intern Med 177:911\u2013918. https:\/\/doi.org\/10.7326\/M24-0086","journal-title":"Ann Intern Med"},{"key":"12289_CR12","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.14309\/ajg.0000000000002282","volume":"118","author":"JW Li","year":"2023","unstructured":"Li JW, Wu CCH, Lee JWJ et al (2023) Real-world validation of a computer-aided diagnosis system for prediction of polyp histology in colonoscopy: a prospective multicenter study. Am J Gastroenterol 118:1353\u20131364. https:\/\/doi.org\/10.14309\/ajg.0000000000002282","journal-title":"Am J Gastroenterol"},{"key":"12289_CR13","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1053\/j.gastro.2022.03.053","volume":"163","author":"Y Minegishi","year":"2022","unstructured":"Minegishi Y, Kudo SE, Miyata Y et al (2022) Comprehensive diagnostic performance of real-time characterization of colorectal lesions using an Artificial intelligence-assisted system: a prospective study. Gastroenterology. 163:323\u2013325. https:\/\/doi.org\/10.1053\/j.gastro.2022.03.053","journal-title":"Gastroenterology."},{"key":"12289_CR14","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1055\/s-0043-105486","volume":"49","author":"K Takeda","year":"2017","unstructured":"Takeda K, Kudo SE, Mori Y et al (2017) Accuracy of diagnosing invasive colorectal cancer using computer-aided endocytoscopy. Endoscopy 49:798\u2013802. https:\/\/doi.org\/10.1055\/s-0043-105486","journal-title":"Endoscopy"},{"key":"12289_CR15","doi-asserted-by":"publisher","first-page":"E690","DOI":"10.1055\/s-0043-105490","volume":"5","author":"N Tamai","year":"2017","unstructured":"Tamai N, Saito Y, Sakamoto T et al (2017) Effectiveness of computer-aided diagnosis of colorectal lesions using novel software for magnifying narrow-band imaging: a pilot study. Endosc Int Open 5:E690\u2013E694. https:\/\/doi.org\/10.1055\/s-0043-105490","journal-title":"Endosc Int Open"},{"key":"12289_CR16","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1016\/j.gie.2020.07.053","volume":"93","author":"M Tokunaga","year":"2021","unstructured":"Tokunaga M, Matsumura T, Nankinzan R et al (2021) Computer-aided diagnosis system using only white-light endoscopy for the prediction of invasion depth in colorectal cancer. Gastrointest Endosc 93:647\u2013653. https:\/\/doi.org\/10.1016\/j.gie.2020.07.053","journal-title":"Gastrointest Endosc"},{"key":"12289_CR17","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1016\/j.gie.2021.03.936","volume":"94","author":"X Luo","year":"2021","unstructured":"Luo X, Wang J, Han Z et al (2021) Artificial intelligence-enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth. Gastrointest Endosc 94:627\u2013638. https:\/\/doi.org\/10.1016\/j.gie.2021.03.936","journal-title":"Gastrointest Endosc"},{"key":"12289_CR18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.gie.2023.01.050","volume":"98","author":"D Nemoto","year":"2023","unstructured":"Nemoto D, Guo Z, Katsuki S et al (2023) Computer-aided diagnosis of early-stage colorectal cancer using nonmagnified endoscopic white-light images (with videos). Gastrointest Endosc 98:90\u201399. https:\/\/doi.org\/10.1016\/j.gie.2023.01.050","journal-title":"Gastrointest Endosc"},{"key":"12289_CR19","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1016\/j.cgh.2023.01.028","volume":"21","author":"T Matsumura","year":"2023","unstructured":"Matsumura T, Ebigbo A, R\u00f6mmele C et al (2023) Diagnostic value of adding magnifying chromoendoscopy to magnifying narrow-band imaging endoscopy for colorectal polyps. Clin Gastroenterol Hepatol 21:2551\u20132559. https:\/\/doi.org\/10.1016\/j.cgh.2023.01.028","journal-title":"Clin Gastroenterol Hepatol"},{"key":"12289_CR20","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1111\/den.12644","volume":"28","author":"Y Sano","year":"2016","unstructured":"Sano Y, Tanaka S, Kudo SE et al (2016) Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team. Dig Endosc 28:526\u2013533. https:\/\/doi.org\/10.1111\/den.12644","journal-title":"Dig Endosc"},{"key":"12289_CR21","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1111\/j.1443-1661.2010.00983.x","volume":"22","author":"Y Wada","year":"2010","unstructured":"Wada Y, Kashida H, Kudo SE et al (2010) Diagnostic accuracy of pit pattern and vascular pattern analyses in colorectal lesions. Dig Endosc 22:192\u2013199. https:\/\/doi.org\/10.1111\/j.1443-1661.2010.00983.x","journal-title":"Dig Endosc"},{"key":"12289_CR22","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1136\/gut.51.1.130","volume":"52","author":"MF Dixon","year":"2002","unstructured":"Dixon MF (2002) Gastrointestinal epithelial neoplasia: Vienna revisited. Gut 52:130\u2013131. https:\/\/doi.org\/10.1136\/gut.51.1.130","journal-title":"Gut"},{"key":"12289_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10147-011-0315-2","volume":"17","author":"T Watanabe","year":"2010","unstructured":"Watanabe T, Itabashi M, Shimada Y et al (2010) Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2010 for the treatment of colorectal cancer. Int J Clin Oncol 17:1\u201329. https:\/\/doi.org\/10.1007\/s10147-011-0315-2","journal-title":"Int J Clin Oncol"},{"key":"12289_CR24","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1111\/j.1572-0241.2008.02190.x","volume":"103","author":"T Matsuda","year":"2008","unstructured":"Matsuda T, Fujii T, Saito Y et al (2008) Efficacy of the invasive\/non-invasive pattern by magnifying chromoendoscopy to estimate the depth of invasion of early colorectal neoplasms. Am J Gastroenterol 103:2700\u20132706. https:\/\/doi.org\/10.1111\/j.1572-0241.2008.02190.x","journal-title":"Am J Gastroenterol"},{"key":"12289_CR25","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1136\/gutjnl-2017-314723","volume":"68","author":"Y Backes","year":"2019","unstructured":"Backes Y, Schwartz MP, Ter Borg F et al (2019) Multicentre prospective evaluation of real-time optical diagnosis of T1 colorectal cancer in large non-pedunculated colorectal polyps using narrow band imaging (the OPTICAL study). Gut 68:271\u2013279. https:\/\/doi.org\/10.1136\/gutjnl-2017-314723","journal-title":"Gut"},{"key":"12289_CR26","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1055\/a-2009-3990","volume":"55","author":"BBSL Houwen","year":"2023","unstructured":"Houwen BBSL, Hazewinkel Y, Giotis I et al (2023) Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists. Endoscopy 55:756\u2013765. https:\/\/doi.org\/10.1055\/a-2009-3990","journal-title":"Endoscopy"},{"key":"12289_CR27","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1055\/a-1852-0330","volume":"55","author":"E Rondonotti","year":"2023","unstructured":"Rondonotti E, Hassan C, Tamanini G et al (2023) Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study. Endoscopy 55:14\u201322. https:\/\/doi.org\/10.1055\/a-1852-0330","journal-title":"Endoscopy"},{"key":"12289_CR28","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1016\/j.cgh.2022.04.045","volume":"20","author":"C Hassan","year":"2022","unstructured":"Hassan C, Balsamo G, Lorenzetti R et al (2022) Artificial intelligence allows leaving-in-situ colorectal polyps. Clin Gastroenterol Hepatol 20:2505\u20132513. https:\/\/doi.org\/10.1016\/j.cgh.2022.04.045","journal-title":"Clin Gastroenterol Hepatol"},{"key":"12289_CR29","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, PMLR 97:6105\u20136114"},{"key":"12289_CR30","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1136\/gut.2005.087452","volume":"55","author":"T Uraoka","year":"2006","unstructured":"Uraoka T, Saito Y, Matsuda T et al (2006) Endoscopic indications for endoscopic mucosal resection of laterally spreading tumours in the colorectum. Gut 55:1565\u20131571","journal-title":"Gut"}],"container-title":["Surgical Endoscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00464-025-12289-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00464-025-12289-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00464-025-12289-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T19:33:05Z","timestamp":1769023985000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00464-025-12289-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["12289"],"URL":"https:\/\/doi.org\/10.1007\/s00464-025-12289-w","relation":{},"ISSN":["0930-2794","1432-2218"],"issn-type":[{"value":"0930-2794","type":"print"},{"value":"1432-2218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"1 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Tomoaki Matsumura, Yukihiro Nomura, Kenichiro Okimoto, Mamoru Tokunaga, Tsubasa Ishikawa, Naoki Akizue, Keisuke Matsusaka, Takuto Suzuki, Yoshiyasu Kitagawa, Kengo Nagashima, Toshiya Nakaguchi, and Jun Kato, and Fujie have no conflicts of interest or financial ties to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosures"}}]}}