{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:38:36Z","timestamp":1762508316519,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T00:00:00Z","timestamp":1604534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T00:00:00Z","timestamp":1604534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA212382"],"award-info":[{"award-number":["R01CA212382"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB023942"],"award-info":[{"award-number":["R01EB023942"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>Deep learning can be used for improving the performance of computer-aided detection (CADe) in various medical imaging tasks. However, in computed tomographic (CT) colonography, the performance is limited by the relatively small size and the variety of the available training datasets. Our purpose in this study was to develop and evaluate a flow-based generative model for performing 3D\u00a0data augmentation of colorectal polyps for effective training of deep learning in CADe for CT colonography.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We developed a 3D-convolutional neural network (3D\u00a0CNN) based on a flow-based generative model (3D\u00a0Glow) for generating synthetic volumes of interest (VOIs) that has characteristics similar to those of the VOIs of its training dataset. The 3D\u00a0Glow was trained to generate synthetic VOIs of polyps by use of our clinical CT colonography case collection. The evaluation was performed by use of a human observer study with three observers and by use of a CADe-based polyp classification study with a 3D\u00a0DenseNet.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The area-under-the-curve values of the receiver operating characteristic analysis of the three observers were not statistically significantly different in distinguishing between real polyps and synthetic polyps. When trained with data augmentation by 3D\u00a0Glow, the 3D\u00a0DenseNet yielded a statistically significantly higher polyp classification performance than when it was trained with alternative augmentation methods.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The 3D\u00a0Glow-generated synthetic polyps are visually indistinguishable from real colorectal polyps. Their application to data augmentation can substantially improve the performance of 3D CNNs in CADe for CT colonography. Thus, 3D Glow is a promising method for improving the performance of deep learning in CADe for CT colonography.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-020-02275-z","type":"journal-article","created":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T02:02:48Z","timestamp":1604541768000},"page":"81-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["A generative flow-based model for volumetric data augmentation in 3D deep learning for computed tomographic colonography"],"prefix":"10.1007","volume":"16","author":[{"given":"Tomoki","family":"Uemura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janne J.","family":"N\u00e4ppi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuji","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chinatsu","family":"Watari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tohru","family":"Kamiya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroyuki","family":"Yoshida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,5]]},"reference":[{"key":"2275_CR1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","volume":"68","author":"F Bray","year":"2018","unstructured":"Bray F, Ferlay J, Soerjomataram I, Siegel R, Torre L, Jemal A (2018) Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68:394\u2013424","journal-title":"CA Cancer J Clin"},{"key":"2275_CR2","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1053\/gast.1997.v112.agast970594","volume":"112","author":"S Winawer","year":"1997","unstructured":"Winawer S, Fletcher R, Miller L, Godlee F, Stolar M, Mulrow C, Woolf S, Glick S, Ganiats T, Bond J, Rosen L, Zapka J, Olsen S, Giardiello F, Sisk J, Van Antwerp R, Brown-Davis C, Marciniak D, Mayer R (1997) Colorectal cancer screening: clinical guidelines and rationale. Gastroenterology 112:594\u2013642","journal-title":"Gastroenterology"},{"key":"2275_CR3","doi-asserted-by":"crossref","unstructured":"U.S. Preventive Services Task Force: Screening for colorectal cancer: U.S. Preventive Services Task Force Recommendation Statement. JAMA 315:2564\u20132575 (2016)","DOI":"10.1001\/jama.2016.5989"},{"key":"2275_CR4","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M, van der Laark J, van Ginneken B, S\u00e1nchez C (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388","journal-title":"Med Image Anal"},{"key":"2275_CR5","doi-asserted-by":"crossref","unstructured":"Shorten C, Khoshgoftaar T (2019) A survey on image data augmentation for deep learning. J Big Data 6:60","DOI":"10.1186\/s40537-019-0197-0"},{"key":"2275_CR6","unstructured":"N\u00e4ppi J, Hironaka T, Regge D, Yoshida H (2016) Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography. In: Proceedings of SPIE medical imaging: computer-aided diagnosis. SPIE Press, vol 97852B, pp V1\u20138"},{"key":"2275_CR7","unstructured":"N\u00e4ppi J, Pickhardt P, Kim D, Hironaka T, Yoshida H (2017) Computer-aided detection of serrated polyps with a deep convolutional neural network in CT colonography. Int J CARS 12S1: 144\u2013146"},{"key":"2275_CR8","doi-asserted-by":"publisher","first-page":"2034","DOI":"10.1148\/rg.2018170173","volume":"38","author":"R Tachibana","year":"2018","unstructured":"Tachibana R, N\u00e4ppi J, Ota J, Kohlhase N, Hironaka T, Kim S, Regge D, Yoshida H (2018) Deep learning electronic cleansing for single- and dual-energy CT colonography. Radiographics 38:2034\u20132050","journal-title":"Radiographics"},{"key":"2275_CR9","doi-asserted-by":"crossref","unstructured":"Chen Y, Ren Y, Fu L, Xiong J, Larsson R, Xu X, Sun J, Zhao J (2018) A 3D convolutional neural network framework for polyp candidates detection on the limited dataset of CT colonography. In: Conf Proc IEEE Eng Med Biol Soc. Honolulu, HI, USA, pp 678\u2013681","DOI":"10.1109\/EMBC.2018.8512305"},{"key":"2275_CR10","unstructured":"N\u00e4ppi J, Hironaka T, Yoshida H (2017) Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy. In: SPIE medical imaging: computer-aided diagnosis. Houston, Texas, United States, vol 10575, p 1057518"},{"key":"2275_CR11","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1109\/TMI.2015.2482920","volume":"35","author":"H Roth","year":"2016","unstructured":"Roth H, Lu L, Liu J, Yao J, Seff A, Cherry K, Kim L, Summers R (2016) Improving computer-aided detection using convolutional neural networks and random view aggregation. IEEE Trans Med Imaging 35:1170\u20131181","journal-title":"IEEE Trans Med Imaging"},{"key":"2275_CR12","unstructured":"Uemura T, Lu H, Kim H, Tachibana R, Hironaka T, N\u00e4ppi J, Yoshida H (2018) 3D deep residual convolutional networks for computer-aided detection of polyps in CT colonography. Int J CARS 13S1:94\u201395"},{"key":"2275_CR13","doi-asserted-by":"publisher","first-page":"101552","DOI":"10.1016\/j.media.2019.101552","volume":"58","author":"X Yi","year":"2019","unstructured":"Yi X, Walia E, Babyn P (2019) Generative adversarial network in medical imaging: a review. Med Image Anal 58:101552","journal-title":"Med Image Anal"},{"key":"2275_CR14","first-page":"1","volume-title":"Simulation and synthesis in medical imaging","author":"HC Shin","year":"2018","unstructured":"Shin HC, Tenenholtz NA, Rogers JK, Schwarz CG, Senjem ML, Gunter JL, Andriole KP, Michalski M (2018) Medical image synthesis for data augmentation and anonymization using generative adversarial networks. In: Gooya A, Goksel O, Oguz I, Burgos N (eds) Simulation and synthesis in medical imaging. Springer, Cham, pp 1\u201311"},{"key":"2275_CR15","doi-asserted-by":"crossref","unstructured":"Uemura T, N\u00e4ppi J, Lu H, Tachibana R, Hironaka T, Yoshida H (2019) Ensemble 3D residual network (E3D-ResNet) for reduction of false-positive polyp detections in CT colonography. In: Proc SPIE medical imaging 2019: computer-aided diagnosis, p 1095038","DOI":"10.1117\/12.2512173"},{"key":"2275_CR16","unstructured":"Kingma D, Prafulla D (2018) Glow: generative flow with invertible $$1\\times 1$$ convolutions. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Blanchl N, Garnett R (eds) 32nd conference on neural information processing systems (NIPS), Montreal, Canada, pp 10235\u201310244"},{"key":"2275_CR17","unstructured":"Dinh L, Sohl-Dickstein J, Bengio Y (2017) Density estimation using real NVP. In: 5th International conference on learning representations (ICLR)"},{"key":"2275_CR18","unstructured":"Dinh L, Krueger D, Bengio Y (2014) NICE: Non-linear independent components estimation. Technical report"},{"key":"2275_CR19","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1056\/NEJMoa031618","volume":"349","author":"P Pickhardt","year":"2003","unstructured":"Pickhardt P, Choi J, Hwang I, Butler J, Puckett M, Hildebrandt H, Wong R, Nugent P, Mysliwiec P, Schindler W (2003) Computed tomographic virtual colonoscopy to screen for colorectal neoplasia in asymptomatic adults. N Engl J Med 349:2191\u20132200","journal-title":"N Engl J Med"},{"issue":"9456","key":"2275_CR20","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/S0140-6736(05)17784-8","volume":"365","author":"DC Rockey","year":"2005","unstructured":"Rockey DC, Paulson E, Niedzwiecki D, Davis W, Bosworth HB, Sanders L, Yee J, Henderson J, Hatten P, Burdick S, Sanyal A, Rubin DT, Sterling M, Akerkar G, Bhutani MS, Binmoeller K, Garvie J, Bini EJ, McQuaid K, Foster WL, Thompson WM, Dachman A, Halvorsen R (2005) Analysis of air contrast barium enema, computed tomographic colonography, and colonoscopy: prospective comparison. Lancet 365(9456):305\u2013311","journal-title":"Lancet"},{"issue":"12","key":"2275_CR21","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1056\/NEJMoa0800996","volume":"359","author":"CD Johnson","year":"2008","unstructured":"Johnson CD, Chen MH, Toledano AY, Heiken JP, Dachman A, Kuo MD, Menias CO, Siewert B, Cheema JI, Obregon RG, Fidler JL, Zimmerman P, Horton KM, Coakley K, Iyer RB, Hara AK, Halvorsen RA, Casola G, Yee J, Herman BA, Burgart LJ, Limburg PJ (2008) Accuracy of CT colonography for detection of large adenomas and cancers. N Engl J Med 359(12):1207\u20131217","journal-title":"N Engl J Med"},{"issue":"23","key":"2275_CR22","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1001\/jama.2009.832","volume":"301","author":"D Regge","year":"2009","unstructured":"Regge D, Laudi C, Galatola G, Della Monica P, Bonelli L, Angelelli G, Asnaghi R, Barbaro B, Bartolozzi C, Bielen D, Boni L, Borghi C, Bruzzi P, Cassinis MC, Galia M, Gallo TM, Grasso A, Hassan C, Laghi A, Martina MC, Neri E, Senore C, Simonetti G, Venturini S, Gandini G (2009) Diagnostic accuracy of computed tomographic colonography for the detection of advanced neoplasia in individuals at increased risk of colorectal cancer. JAMA 301(23):2453\u20132461","journal-title":"JAMA"},{"issue":"7","key":"2275_CR23","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1016\/j.acra.2008.12.027","volume":"16","author":"K Nagata","year":"2009","unstructured":"Nagata K, Okawa T, Honma A, Endo S, Kudo SE, Yoshida H (2009) Full-laxative versus minimum-laxative fecal-tagging CT colonography using 64-detector row CT: prospective blinded comparison of diagnostic performance, tagging quality, and patient acceptance. Acad Radiol 16(7):780\u2013789","journal-title":"Acad Radiol"},{"key":"2275_CR24","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.acra.2006.11.007","volume":"25","author":"J N\u00e4ppi","year":"2007","unstructured":"N\u00e4ppi J, Yoshida H (2007) Fully automated three-dimensional detection of polyps in fecal-tagging CT colonography. Acad Radiol 25:287\u2013300","journal-title":"Acad Radiol"},{"key":"2275_CR25","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/42.974921","volume":"20","author":"H Yoshida","year":"2001","unstructured":"Yoshida H, N\u00e4ppi J (2001) Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Trans Med Imaging 20:1261\u20131274","journal-title":"IEEE Trans Med Imaging"},{"key":"2275_CR26","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1016\/j.media.2008.01.001","volume":"12","author":"J N\u00e4ppi","year":"2008","unstructured":"N\u00e4ppi J, Yoshida H (2008) Adaptive correction of the pseudo-enhancement of CT attenuation for fecal-tagging CT colonography. Med Image Anal 12:413\u2013426","journal-title":"Med Image Anal"},{"key":"2275_CR27","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/S1076-6332(03)80184-8","volume":"9","author":"J N\u00e4ppi","year":"2002","unstructured":"N\u00e4ppi J, Yoshida H (2002) Automated detection of polyps in CT colonography: evaluation of volumetric features for reduction of false positives. Acad Radiol 9:386\u2013397","journal-title":"Acad Radiol"},{"key":"2275_CR28","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/1471-2105-12-77","volume":"12","author":"X Robin","year":"2011","unstructured":"Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, Mller M (2011) pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform 12:77","journal-title":"BMC Bioinform"},{"key":"2275_CR29","unstructured":"R Core Team: R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2020) https:\/\/www.R-project.org\/"},{"key":"2275_CR30","doi-asserted-by":"publisher","unstructured":"Uemura T, N\u00e4ppi J, Hironaka T, Hyougseop K, Yoshida H (2020) Comparative performance of 3D-DenseNet, 3D-ResNet, and 3D-VGG models in polyp detection for CT colonography. In: Proceedings of SPIE medical imaging 2020: computer-aided diagnosis, p 1131435. https:\/\/doi.org\/10.1117\/12.2549103","DOI":"10.1117\/12.2549103"},{"key":"2275_CR31","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1016\/j.ejrad.2012.04.022","volume":"82","author":"D Regge","year":"2013","unstructured":"Regge D, Halligan S (2013) CAD: How it works, how to use it, performance. Eur J Radiol 82:1171\u20131176","journal-title":"Eur J Radiol"},{"key":"2275_CR32","doi-asserted-by":"publisher","unstructured":"N\u00e4ppi J, Uemura T, Kim S, Kim H, Yoshida H (2020) Comparative performance of 3D machine-learning and deep-learning models in the detection of small polyps in dual-energy CT colonography. In: Proceedings of SPIE medical imaging 2020: computer-aided diagnosis, p 113143C. https:\/\/doi.org\/10.1117\/12.2549793","DOI":"10.1117\/12.2549793"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-020-02275-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11548-020-02275-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-020-02275-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,23]],"date-time":"2021-01-23T03:17:33Z","timestamp":1611371853000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11548-020-02275-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,5]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["2275"],"URL":"https:\/\/doi.org\/10.1007\/s11548-020-02275-z","relation":{},"ISSN":["1861-6410","1861-6429"],"issn-type":[{"type":"print","value":"1861-6410"},{"type":"electronic","value":"1861-6429"}],"subject":[],"published":{"date-parts":[[2020,11,5]]},"assertion":[{"value":"30 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The other authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This retrospective single-center study was approved by the Mass General Brigham (MGB) institutional review board (IRB).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical standards"}},{"value":"All procedures involving human participants were performed in accordance with the ethical standards of the IRB and with the 1964 Declaration of Helsinki and its later amendments.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights statement"}},{"value":"Informed consent was waived for this study by the MGB IRB.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}