{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:44:13Z","timestamp":1775119453789,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100013915","name":"Sarnoff Cardiovascular Research Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100013915","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Institutes of Health National Center for Advancing Translational Studies","award":["UL1TR001878"],"award-info":[{"award-number":["UL1TR001878"]}]},{"name":"National Institutes of Health\/National Heart, Lung, and Blood Institute","award":["R01 HL137984"],"award-info":[{"award-number":["R01 HL137984"]}]},{"name":"National Institutes of Health\/National Heart, Lung, and Blood Institute","award":["R01 AA026302-02"],"award-info":[{"award-number":["R01 AA026302-02"]}]},{"name":"National Institutes of Health\/National Heart, Lung, and Blood Institute","award":["P30 DK0503060 (to RC)"],"award-info":[{"award-number":["P30 DK0503060 (to RC)"]}]},{"name":"Penn Center for Precision Medicine"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The objective was to develop a fully automated algorithm for abdominal fat segmentation and to deploy this method at scale in an academic biobank.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We built a fully automated image curation and labeling technique using deep learning and distributive computing to identify subcutaneous and visceral abdominal fat compartments from 52,844 computed tomography scans in 13,502 patients in the Penn Medicine Biobank (PMBB). A classification network identified the inferior and superior borders of the abdomen, and a segmentation network differentiated visceral and subcutaneous fat. Following technical evaluation of our method, we conducted studies to validate known relationships with visceral and subcutaneous fat.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>When compared with 100 manually annotated cases, the classification network was on average within one 5-mm slice for both the superior (0.4\u2009\u00b1\u20091.1 slice) and inferior (0.4\u2009\u00b1\u20090.6 slice) borders. The segmentation network also demonstrated excellent performance with intraclass correlation coefficients of 1.00 (P\u2009&amp;lt;\u20092 \u00d7 10-16) for subcutaneous and 1.00 (P &amp;lt; 2 \u00d7 10-16) for visceral fat on 100 testing cases. We performed integrative analyses of abdominal fat with the phenome extracted from the electronic health record and found highly significant associations with diabetes mellitus, hypertension, and renal failure, among other phenotypes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This work presents a fully automated and highly accurate method for the quantification of abdominal fat that can be applied to routine clinical imaging studies to fuel translational scientific discovery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaa342","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T17:16:27Z","timestamp":1609953387000},"page":"1178-1187","source":"Crossref","is-referenced-by-count":26,"title":["Quantification of abdominal fat from computed tomography using deep learning and its association with electronic health records in an academic biobank"],"prefix":"10.1093","volume":"28","author":[{"given":"Matthew T","family":"MacLean","sequence":"first","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"},{"name":"Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Qasim","family":"Jehangir","sequence":"additional","affiliation":[{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Marijana","family":"Vujkovic","sequence":"additional","affiliation":[{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Yi-An","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Harold","family":"Litt","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Arijitt","family":"Borthakur","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Hersh","family":"Sagreiya","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Mark","family":"Rosen","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"David A","family":"Mankoff","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Mitchell D","family":"Schnall","sequence":"additional","affiliation":[{"name":"Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Haochang","family":"Shou","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Julio","family":"Chirinos","sequence":"additional","affiliation":[{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Scott M","family":"Damrauer","sequence":"additional","affiliation":[{"name":"Department of Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Drew A","family":"Torigian","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Rotonya","family":"Carr","sequence":"additional","affiliation":[{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"given":"Daniel J","family":"Rader","sequence":"additional","affiliation":[{"name":"Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"},{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1669-2120","authenticated-orcid":false,"given":"Walter R","family":"Witschey","sequence":"additional","affiliation":[{"name":"Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,2,12]]},"reference":[{"issue":"2","key":"2021061318594392700_ocaa342-B1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1136\/gut.2005.073163","article-title":"Influence of obesity on the risk of developing colon cancer","volume":"55","author":"Frezza","year":"2006","journal-title":"Gut"},{"issue":"7121","key":"2021061318594392700_ocaa342-B2","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1038\/nature05487","article-title":"Mechanisms linking obesity with cardiovascular disease","volume":"444","author":"Van Gaal","year":"2006","journal-title":"Nature"},{"issue":"2","key":"2021061318594392700_ocaa342-B3","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.jhealeco.2007.05.005","article-title":"Beyond BMI: the value of more accurate measures of fatness and obesity in social science research","volume":"27","author":"Burkhauser","year":"2008","journal-title":"J Health Econ"},{"issue":"2S","key":"2021061318594392700_ocaa342-B4","doi-asserted-by":"crossref","first-page":"16S","DOI":"10.1038\/oby.2006.277","article-title":"Why visceral fat is bad: mechanisms of the metabolic syndrome","volume":"14","author":"Bergman","year":"2006","journal-title":"Obesity (Silver Spring)"},{"issue":"2","key":"2021061318594392700_ocaa342-B5","doi-asserted-by":"crossref","first-page":"202","DOI":"10.2169\/internalmedicine.38.202","article-title":"Role of adipocytokines on the pathogenesis of atherosclerosis in visceral obesity","volume":"38","author":"Funahashi","year":"1999","journal-title":"Intern Med"},{"issue":"8","key":"2021061318594392700_ocaa342-B6","doi-asserted-by":"crossref","first-page":"629","DOI":"10.5551\/jat.7922","article-title":"The concept of metabolic syndrome: contribution of visceral fat accumulation and its molecular mechanism","volume":"18","author":"Matsuzawa","year":"2011","journal-title":"J Atheroscler Thromb"},{"issue":"4","key":"2021061318594392700_ocaa342-B7","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1093\/ajcn\/75.4.683","article-title":"Body mass index and waist circumference independently contribute to the prediction of nonabdominal, abdominal subcutaneous, and visceral fat","volume":"75","author":"Janssen","year":"2002","journal-title":"Am J Clin Nutr"},{"issue":"18","key":"2021061318594392700_ocaa342-B8","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1001\/archinte.162.18.2074","article-title":"Body mass index, waist circumference, and health risk: evidence in support of current National Institutes of Health guidelines","volume":"162","author":"Janssen","year":"2002","journal-title":"Arch Intern Med"},{"issue":"7","key":"2021061318594392700_ocaa342-B9","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/0002-9149(94)90676-9","article-title":"Waist circumference and abdominal sagittal diameter: best simple anthropometric indexes of abdominal visceral adipose tissue accumulation and related cardiovascular risk in men and women","volume":"73","author":"Pouliot","year":"1994","journal-title":"Am J Cardiol"},{"issue":"5","key":"2021061318594392700_ocaa342-B10","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1093\/jn\/134.5.1071","article-title":"Waist circumference is a better predictor than body mass index of coronary heart disease risk in overweight premenopausal women","volume":"134","author":"Lofgren","year":"2004","journal-title":"J Nutr"},{"issue":"11","key":"2021061318594392700_ocaa342-B11","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1038\/ijo.2011.268","article-title":"Body mass index versus waist circumference as predictors of mortality in Canadian adults","volume":"36","author":"Staiano","year":"2012","journal-title":"Int J Obes"},{"issue":"5","key":"2021061318594392700_ocaa342-B12","doi-asserted-by":"crossref","first-page":"954","DOI":"10.3945\/jn.109.118737","article-title":"Measurement site for waist circumference affects its accuracy as an index of visceral and abdominal subcutaneous fat in a Caucasian population","volume":"140","author":"Bosy-Westphal","year":"2010","journal-title":"J Nutr"},{"issue":"1","key":"2021061318594392700_ocaa342-B13","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13167-016-0053-7","article-title":"Biobanks in the era of personalized medicine: objectives, challenges, and innovation","volume":"7","author":"Kinkorov\u00e1","year":"2015","journal-title":"EPMA J"},{"key":"2021061318594392700_ocaa342-B14","author":"Jiang","year":"2020"},{"key":"2021061318594392700_ocaa342-B15","author":"Mehrabi","year":"2019"},{"issue":"5","key":"2021061318594392700_ocaa342-B16","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1097\/01.rct.0000228164.08968.e8","article-title":"Automated quantification of body fat distribution on volumetric computed tomography","volume":"30","author":"Zhao","year":"2006","journal-title":"J Comput Assist Tomogr"},{"key":"2021061318594392700_ocaa342-B17","author":"Pednekar","year":"2005"},{"issue":"2","key":"2021061318594392700_ocaa342-B18","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s10278-012-9488-0","article-title":"Body fat assessment method using CT images with separation mask algorithm","volume":"26","author":"Kim","year":"2013","journal-title":"J Digit Imaging"},{"key":"2021061318594392700_ocaa342-B19","doi-asserted-by":"crossref","first-page":"3253096","DOI":"10.1155\/2018\/3253096","article-title":"Using adipose measures from health care provider-based imaging data for discovery","volume":"2018","author":"Cha","year":"2018","journal-title":"J Obes"},{"issue":"4","key":"2021061318594392700_ocaa342-B20","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1002\/jmri.20167","article-title":"An accurate and robust method for unsupervised assessment of abdominal fat by MRI","volume":"20","author":"Positano","year":"2004","journal-title":"J Magn Reson Imaging"},{"key":"2021061318594392700_ocaa342-B21","author":"Chung","year":"2009"},{"issue":"4","key":"2021061318594392700_ocaa342-B22","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1002\/jmri.24655","article-title":"Automated segmentation of visceral and subcutaneous (deep and superficial) adipose tissues in normal and overweight men","volume":"41","author":"Sadananthan","year":"2015","journal-title":"J Magn Reson Imaging"},{"issue":"2","key":"2021061318594392700_ocaa342-B23","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1109\/TMI.2015.2479252","article-title":"Body composition assessment in axial CT images using FEM-based automatic segmentation of skeletal muscle","volume":"35","author":"Popuri","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"2021061318594392700_ocaa342-B24","author":"Agarwal","year":"2017"},{"issue":"4","key":"2021061318594392700_ocaa342-B25","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/BF00133570","article-title":"Snakes: active contour models","volume":"1","author":"Kass","year":"1988","journal-title":"Int J Comput Vision"},{"issue":"2","key":"2021061318594392700_ocaa342-B26","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1109\/TPAMI.2010.83","article-title":"Decoupled active contour (DAC) for boundary detection","volume":"33","author":"Mishra","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2021061318594392700_ocaa342-B27","doi-asserted-by":"crossref","first-page":"3","DOI":"10.4103\/0971-6203.58777","article-title":"Automated medical image segmentation techniques","volume":"35","author":"Sharma","year":"2010","journal-title":"J Med Phys"},{"key":"2021061318594392700_ocaa342-B28","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.neucom.2016.07.059","article-title":"Abdominal adipose tissues extraction using multi-scale deep neural network","volume":"229","author":"Jiang","year":"2017","journal-title":"Neurocomputing"},{"key":"2021061318594392700_ocaa342-B29","first-page":"415","article-title":"Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields","author":"Christ","year":"2016","journal-title":"MICCAI 2016: Medical Image Computing and Computer-Assisted Intervention"},{"issue":"7639","key":"2021061318594392700_ocaa342-B30","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"issue":"22","key":"2021061318594392700_ocaa342-B31","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"22","key":"2021061318594392700_ocaa342-B32","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Ehteshami Bejnordi","year":"2017","journal-title":"JAMA"},{"issue":"3","key":"2021061318594392700_ocaa342-B33","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1148\/radiol.2018181432","article-title":"Automated abdominal segmentation of CT scans for body composition analysis using deep learning","volume":"290","author":"Weston","year":"2019","journal-title":"Radiology"},{"issue":"1","key":"2021061318594392700_ocaa342-B34","doi-asserted-by":"crossref","first-page":"88","DOI":"10.3348\/kjr.2019.0470","article-title":"Development and validation of a deep learning system for segmentation of abdominal muscle and fat on computed tomography","volume":"21","author":"Park","year":"2020","journal-title":"Korean J Radiol"},{"key":"2021061318594392700_ocaa342-B35","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.cmpb.2017.03.017","article-title":"A two-step convolutional neural network based computer-aided detection scheme for automatically segmenting adipose tissue volume depicting on CT images","volume":"144","author":"Wang","year":"2017","journal-title":"Comput Methods Programs Biomed"},{"key":"2021061318594392700_ocaa342-B36","author":"Hassan","year":"2019"},{"key":"2021061318594392700_ocaa342-B37","author":"He","year":"2016"},{"key":"2021061318594392700_ocaa342-B38","author":"Szegedy"},{"key":"2021061318594392700_ocaa342-B39","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S1571-0661(04)00313-5","article-title":"Efficient algorithms for the maximum subarray problem by distance matrix multiplication","volume":"61","author":"Takaoka","year":"2002","journal-title":"Electr Notes Theor Compu Sci"},{"key":"2021061318594392700_ocaa342-B40","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"MICCAI 2015: Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger","year":"2015"},{"issue":"4","key":"2021061318594392700_ocaa342-B41","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2021061318594392700_ocaa342-B42","author":"Chollet","year":"2017"},{"key":"2021061318594392700_ocaa342-B43","first-page":"4510","author":"Sandler","year":"2018"},{"issue":"3","key":"2021061318594392700_ocaa342-B44","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"issue":"1","key":"2021061318594392700_ocaa342-B45","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12894-015-0013-x","article-title":"Which anthropometric measurements including visceral fat, subcutaneous fat, body mass index, and waist circumference could predict the urinary stone composition most?","volume":"15","author":"Kim","year":"2015","journal-title":"BMC Urol"},{"issue":"2","key":"2021061318594392700_ocaa342-B46","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1038\/oby.2010.248","article-title":"The relationship of waist circumference and BMI to visceral, subcutaneous, and total body fat: sex and race differences","volume":"19","author":"Camhi","year":"2011","journal-title":"Obesity"},{"issue":"1","key":"2021061318594392700_ocaa342-B47","doi-asserted-by":"crossref","first-page":"165","DOI":"10.3803\/EnM.2020.35.1.165","article-title":"Visceral-to-subcutaneous abdominal fat ratio is associated with nonalcoholic fatty liver disease and liver fibrosis","volume":"35","author":"Jung","year":"2020","journal-title":"Endocrinol Metab"},{"issue":"11","key":"2021061318594392700_ocaa342-B48","doi-asserted-by":"crossref","first-page":"3550","DOI":"10.1093\/ndt\/gfq634","article-title":"Relationship of visceral and subcutaneous adiposity with renal function in people with type 2 diabetes mellitus","volume":"26","author":"Kim","year":"2011","journal-title":"Nephrol Dial Transplant"},{"key":"2021061318594392700_ocaa342-B49","doi-asserted-by":"crossref","first-page":"S141","DOI":"10.1097\/00002030-200304001-00017","article-title":"HIV lipodystrophy: risk factors, pathogenesis, diagnosis and management","volume":"17","author":"Carr","year":"2003","journal-title":"AIDS"},{"issue":"6","key":"2021061318594392700_ocaa342-B50","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1530\/eje.0.1490543","article-title":"Computed tomography assessment of fat distribution in male and female patients with Cushing's syndrome","volume":"149","author":"Rockall","year":"2003","journal-title":"Eur J Endocrinol"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/6\/1178\/38615488\/ocaa342.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/6\/1178\/38615488\/ocaa342.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,13]],"date-time":"2021-06-13T15:01:28Z","timestamp":1623596488000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/6\/1178\/6133906"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,12]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,2,12]]},"published-print":{"date-parts":[[2021,6,12]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaa342","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.09.22.20199844","asserted-by":"object"}]},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,6,1]]},"published":{"date-parts":[[2021,2,12]]}}}