{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T11:26:30Z","timestamp":1790335590379,"version":"4.1.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2020,12,7]],"date-time":"2020-12-07T00:00:00Z","timestamp":1607299200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,24]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>A colonoscopy can detect colorectal diseases, including cancers, polyps, and inflammatory bowel diseases. A computer-aided diagnosis (CAD) system using deep convolutional neural networks (CNNs) that can recognize anatomical locations during a colonoscopy could efficiently assist practitioners. We aimed to construct a CAD system using a CNN to distinguish colorectal images from parts of the cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Method<\/jats:title>\n                  <jats:p>We constructed a CNN by training of 9,995 colonoscopy images and tested its performance by 5,121 independent colonoscopy images that were categorized according to seven anatomical locations: the terminal ileum, the cecum, ascending colon to transverse colon, descending colon to sigmoid colon, the rectum, the anus, and indistinguishable parts. We examined images taken during total colonoscopy performed between January 2017 and November 2017 at a single center. We evaluated the concordance between the diagnosis by endoscopists and those by the CNN. The main outcomes of the study were the sensitivity and specificity of the CNN for the anatomical categorization of colonoscopy images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The constructed CNN recognized anatomical locations of colonoscopy images with the following areas under the curves: 0.979 for the terminal ileum; 0.940 for the cecum; 0.875 for ascending colon to transverse colon; 0.846 for descending colon to sigmoid colon; 0.835 for the rectum; and 0.992 for the anus. During the test process, the CNN system correctly recognized 66.6% of images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>We constructed the new CNN system with clinically relevant performance for recognizing anatomical locations of colonoscopy images, which is the first step in constructing a CAD system that will support us during colonoscopy and provide an assurance of the quality of the colonoscopy procedure.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/gastro\/goaa078","type":"journal-article","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T19:13:40Z","timestamp":1600888420000},"page":"226-233","source":"Crossref","is-referenced-by-count":23,"title":["Automatic anatomical classification of colonoscopic images using deep convolutional neural networks"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0824-454X","authenticated-orcid":false,"given":"Hiroaki","family":"Saito","sequence":"first","affiliation":[{"name":"Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuya","family":"Tanimoto","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Navitas Clinic, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsuyoshi","family":"Ozawa","sequence":"additional","affiliation":[{"name":"Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan"},{"name":"Department of Surgery, Teikyo University School of Medicine, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soichiro","family":"Ishihara","sequence":"additional","affiliation":[{"name":"Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan"},{"name":"Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitsuhiro","family":"Fujishiro","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoki","family":"Shichijo","sequence":"additional","affiliation":[{"name":"Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dai","family":"Hirasawa","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Matsuda","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuma","family":"Endo","sequence":"additional","affiliation":[{"name":"AI Medical Service, Inc., Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiro","family":"Tada","sequence":"additional","affiliation":[{"name":"Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan"},{"name":"Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan"},{"name":"AI Medical Service, Inc., Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,12,7]]},"reference":[{"key":"2021072415293034100_goaa078-B1","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1007\/s11605-015-3026-6","article-title":"The worse prognosis of right-sided compared with left-sided colon cancers: a systematic review and meta-analysis","volume":"20","author":"Yahagi","year":"2016","journal-title":"J Gastrointest Surg"},{"key":"2021072415293034100_goaa078-B2","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1186\/s12885-017-3255-z","article-title":"Sidedness is prognostic in locoregional colon cancer: an analysis of 9509 Australian patients","volume":"17","author":"Brungs","year":"2017","journal-title":"BMC Cancer"},{"key":"2021072415293034100_goaa078-B3","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1001\/jamaoncol.2016.4227","article-title":"Prognostic survival associated with left-sided vs right-sided colon cancer: a systematic review and meta-analysis","volume":"3","author":"Petrelli","year":"2017","journal-title":"JAMA Oncol"},{"key":"2021072415293034100_goaa078-B4","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1186\/s12876-017-0694-6","article-title":"Primary tumor location predicts poor clinical outcome with cetuximab in RAS wild-type metastatic colorectal cancer","volume":"17","author":"Kim","year":"2017","journal-title":"BMC Gastroenterol"},{"key":"2021072415293034100_goaa078-B5","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1056\/NEJM199312303292701","article-title":"Prevention of colorectal cancer by colonoscopic polypectomy: the National Polyp Study Workgroup","volume":"329","author":"Winawer","year":"1993","journal-title":"N Engl J Med"},{"key":"2021072415293034100_goaa078-B6","doi-asserted-by":"crossref","first-page":"31","DOI":"10.5009\/gnl.2010.4.1.31","article-title":"Learning curves for colonoscopy: a prospective evaluation of gastroenterology fellows at a single center","volume":"4","author":"Chung","year":"2010","journal-title":"Gut Liver"},{"key":"2021072415293034100_goaa078-B7","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1159\/000481227","article-title":"Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification: preliminary experience","volume":"93","author":"Komeda","year":"2017","journal-title":"Oncology"},{"key":"2021072415293034100_goaa078-B8","doi-asserted-by":"crossref","first-page":"8894","DOI":"10.1088\/1361-6560\/aa93d4","article-title":"Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms","volume":"62","author":"Samala","year":"2017","journal-title":"Phys Med Biol"},{"key":"2021072415293034100_goaa078-B9","doi-asserted-by":"crossref","first-page":"4165","DOI":"10.1038\/s41598-018-22437-z","article-title":"Detecting and classifying lesions in mammograms with deep learning","volume":"8","author":"Ribli","year":"2018","journal-title":"Sci Rep"},{"key":"2021072415293034100_goaa078-B10","doi-asserted-by":"crossref","first-page":"8533","DOI":"10.1038\/s41598-017-08040-8","article-title":"Automatic categorization and scoring of solid, part-solid and non-solid pulmonary nodules in CT images with convolutional neural network","volume":"7","author":"Tu","year":"2017","journal-title":"Sci Rep"},{"key":"2021072415293034100_goaa078-B11","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/s12938-017-0420-1","article-title":"Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network","volume":"16","author":"Jiang","year":"2017","journal-title":"Biomed Eng Online"},{"key":"2021072415293034100_goaa078-B12","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.neucom.2016.01.034","article-title":"A deep convolutional neural network for segmenting and classifying epithelial and stromal regions in histopathological images","volume":"191","author":"Xu","year":"2016","journal-title":"Neurocomputing"},{"key":"2021072415293034100_goaa078-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2017\/9545920","article-title":"An automatic gastrointestinal polyp detection system in video endoscopy using fusion of color wavelet and convolutional neural network features","volume":"2017","author":"Billah","year":"2017","journal-title":"Int J Biomed Imaging"},{"key":"2021072415293034100_goaa078-B14","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s10120-018-0793-2","article-title":"Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images","volume":"21","author":"Hirasawa","year":"2018","journal-title":"Gastric Cancer"},{"key":"2021072415293034100_goaa078-B15","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.ebiom.2017.10.014","article-title":"Application of convolutional neural networks in the diagnosis of Helicobacter pylori infection based on endoscopic images","volume":"25","author":"Shichijo","year":"2017","journal-title":"EBioMedicine"},{"key":"2021072415293034100_goaa078-B16","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1053\/j.gastro.2017.10.010","article-title":"Accurate classification of diminutive colorectal polyps using computer-aided analysis","volume":"154","author":"Chen","year":"2018","journal-title":"Gastroenterology"},{"key":"2021072415293034100_goaa078-B17"},{"key":"2021072415293034100_goaa078-B18","first-page":"248","author":"Deng","year":"2009"},{"key":"2021072415293034100_goaa078-B19","article-title":"AdaDelta: an adaptive learning rate method","volume":"22","author":"Zeiler","year":"2012","journal-title":"arXiv Preprint arXiv: 1212.5701"},{"key":"2021072415293034100_goaa078-B20","doi-asserted-by":"crossref","first-page":"7497","DOI":"10.1038\/s41598-018-25842-6","article-title":"Automatic anatomical classification of esophagogastroduodenoscopy images using deep convolutional neural networks","volume":"8","author":"Takiyama","year":"2018","journal-title":"Sci Rep"},{"key":"2021072415293034100_goaa078-B21","doi-asserted-by":"crossref","first-page":"2349","DOI":"10.1109\/IEMBS.2006.260686","article-title":"Automatic classification of images with appendiceal orifice in colonoscopy videos","volume":"2006","author":"Cao","year":"2006","journal-title":"Conf Proc IEEE Eng Med Biol Soc"},{"key":"2021072415293034100_goaa078-B22","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1109\/TBME.2009.2034466","article-title":"Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection","volume":"57","author":"Wang","year":"2010","journal-title":"IEEE Trans Biomed Eng"},{"key":"2021072415293034100_goaa078-B23","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/S2468-1253(19)30413-3","article-title":"Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study","volume":"5","author":"Gong","year":"2020","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"2021072415293034100_goaa078-B24","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/JBHI.2016.2637004","article-title":"Integrating online and offline three-dimensional deep learning for automated polyp detection in colonoscopy videos","volume":"21","author":"Yu","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"key":"2021072415293034100_goaa078-B25","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s13534-017-0048-x","article-title":"Gastrointestinal polyp detection in endoscopic images using an improved feature extraction method","volume":"8","author":"Billah","year":"2018","journal-title":"Biomed Eng Lett"},{"key":"2021072415293034100_goaa078-B26","doi-asserted-by":"crossref","article-title":"Going deeper with convolutions","author":"Szegedy","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2021072415293034100_goaa078-B27","first-page":"770","author":"He","year":"2016"},{"key":"2021072415293034100_goaa078-B28","doi-asserted-by":"crossref","first-page":"2045","DOI":"10.1136\/gutjnl-2016-312043","article-title":"Expert opinions and scientific evidence for colonoscopy key performance indicators","volume":"65","author":"Rees","year":"2016","journal-title":"Gut"},{"key":"2021072415293034100_goaa078-B29","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.1056\/NEJMoa055498","article-title":"Colonoscopic withdrawal times and adenoma detection during screening colonoscopy","volume":"355","author":"Barclay","year":"2006","journal-title":"N Engl J Med"},{"key":"2021072415293034100_goaa078-B30","doi-asserted-by":"crossref","first-page":"e0174155","DOI":"10.1371\/journal.pone.0174155","article-title":"Polyp detection rate in transverse and sigmoid colon significantly increases with longer withdrawal time during screening colonoscopy","volume":"12","author":"Kashiwagi","year":"2017","journal-title":"PLoS One"},{"key":"2021072415293034100_goaa078-B31","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.1136\/gutjnl-2013-305973","article-title":"An analysis of the learning curve to achieve competency at colonoscopy using the JETS database","volume":"63","author":"Ward","year":"2014","journal-title":"Gut"}],"container-title":["Gastroenterology Report"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/gastro\/article-pdf\/9\/3\/226\/39308386\/goaa078.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/gastro\/article-pdf\/9\/3\/226\/39308386\/goaa078.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T15:30:16Z","timestamp":1627140616000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/gastro\/article\/9\/3\/226\/6025428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,7]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,12,7]]},"published-print":{"date-parts":[[2021,7,24]]}},"URL":"https:\/\/doi.org\/10.1093\/gastro\/goaa078","relation":{},"ISSN":["2052-0034"],"issn-type":[{"value":"2052-0034","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,6,1]]},"published":{"date-parts":[[2020,12,7]]}}}