{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:06:57Z","timestamp":1789492017117,"version":"build-2803163510"},"reference-count":56,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T00:00:00Z","timestamp":1779494400000},"content-version":"vor","delay-in-days":22,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82572378"],"award-info":[{"award-number":["82572378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Human body composition is a key indicator of metabolic health, cardiovascular risk, and other health conditions. Segmentation of different adipose tissues and skeletal muscle based on CT images is a commonly used way to assess body composition\u00a0accurately.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Most current body composition analysis methods focus on single cross\u2010section\u00a0CT images, which may have a bias of selecting single\u2010slice images to represent whole body composition. Existing 3D deep\u2010learning\u2010based segmentation methods usually require densely annotated training volumetric data and face challenges of intra\u2010 and inter\u2010variability among subjects. This article aims to realize accurate volumetric abdominal wall segmentation and body tissue extraction from CT scans with sparse\u2010labeled training\u00a0data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study collected 70 CT scans from one public dataset and one private dataset, which were divided into the training (public, ), internal test (public, ) and external test (private, ). About 10% of the slices in training scans are labeled to develop the model and all test scans are delineated slice\u2010by\u2010slice by radiologists. A novel semi\u2010supervised segmentation method based on a 2D\u20133D hybrid mean\u2010teacher network (2D\u20103D HMT) and an automated body composition assessment pipeline is proposed. Specifically, a 2D teacher model trained with fully\u2010labeled slices guides the fine\u2010tuning of two 2D and 3D student models, taking advantage of the volumetric model while avoiding intensive slice\u2010by\u2010slice labeling work. In addition, an active contour regularization is incorporated into 3D model to improve boundary smoothness. Then, different adipose and muscle tissues are extracted based on the predicted abdominal wall and other ROIs using specific tissue HU ranges.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments were conducted on the internal and external datasets to evaluate the semi\u2010supervised segmentation model and body tissue assessment pipeline. Additionally, the public large\u2010scale AATCT\u2010IDS dataset with adipose tissue annotation was also used to evaluate the proposed method. The proposed method achieved high mean Dice similarity coefficients (DSC) on the internal dataset (0.989, 0.979 and 0.973) and external dataset (0.986, 0.982 and 0.973) for subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT) and skeletal muscle (SM), respectively. The Pearson's correlation analysis was conducted and showed the volumes of SAT, VAT and SM by automated segmentation are strongly correlated with those of manual segmentation (, , , , , , respectively). Compared to related body component assessment methods, the proposed method reached comparable performance while only using 10% labeled\u00a0data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed semi\u2010supervised segmentation method and pipeline can effectively perform body composition assessment with very sparse\u2010labeled CT\u00a0images.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70485","type":"journal-article","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T18:15:56Z","timestamp":1779560156000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Abdominal body composition assessment with 2D\u20133D Hybrid Mean\u2010Teacher Network"],"prefix":"10.1002","volume":"53","author":[{"given":"Peijun","family":"Hu","sequence":"first","affiliation":[{"name":"Research Center for Scientific Data Hub Zhejiang Laboratory Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Research Center for Scientific Data Hub Zhejiang Laboratory Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinnan","family":"Hu","sequence":"additional","affiliation":[{"name":"Research Center for Scientific Data Hub Zhejiang Laboratory Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary and Pancreatic Surgery, the First Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Yu","sequence":"additional","affiliation":[{"name":"Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianshu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Research Center for Scientific Data Hub Zhejiang Laboratory Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingbo","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary and Pancreatic Surgery, the First Affiliated Hospital Zhejiang University School of Medicine Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingsong","family":"Li","sequence":"additional","affiliation":[{"name":"Research Center for Scientific Data Hub Zhejiang Laboratory Hangzhou China"},{"name":"Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,23]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30025-X"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/2162402X.2019.1580128"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2019.09.016"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcct.2018.03.007"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1159\/000499320"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2024.0628"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020201640"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/oby.2003.3"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1136\/jim-2018-000722"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2016.04.019"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-08-2242"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1097\/MCO.0b013e32830b5f23"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims-22-330"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018181432"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2019.0470"},{"key":"e_1_2_11_17_1","unstructured":"PuL AshrafSF GezerNS OcakI DhuparR.Automated segmentation of 3\u2010d body composition on computed tomography.arXiv preprint arXiv:2112.08968 2021."},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2479252"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/apha.12224"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2022.110559"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2020.04.011"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa342"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.23.29570"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200130"},{"key":"e_1_2_11_25_1","unstructured":"MaD ChowV PopuriK BegMF.Comprehensive validation of automated whole body skeletal muscle adipose tissue and bone segmentation from 3D CT images for body composition analysis: towards extended body composition.arXiv preprint arXiv:2106.00652 2021."},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14465"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clnu.2021.06.025"},{"issue":"2","key":"e_1_2_11_28_1","first-page":"1","article-title":"CAFT: a deep learning\u2010based comprehensive abdominal fat analysis tool for large cohort studies","volume":"35","author":"Bhanu PK","year":"2021","journal-title":"Magn Reson Mater Phys Biol Med"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-023-01146-3"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07147-3"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02976-1"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-024-03167-2"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"HuP HuoY KongD et\u00a0al.Automated characterization of body composition and frailty with clinically acquired CT. In:Computational Methods and Clinical Applications in Musculoskeletal Imaging: 5th International Workshop MSKI 2017 Held in Conjunction with MICCAI 2017 September 10 2017 Revised Selected Papers Springer International Publishing2018:25\u201035.","DOI":"10.1007\/978-3-319-74113-0_3"},{"key":"e_1_2_11_34_1","unstructured":"ChenJ LuY YuQ et\u00a0al.TransUnet: Transformers make strong encoders for medical image segmentation.arXiv preprint arXiv:2102.04306 2021."},{"key":"e_1_2_11_35_1","doi-asserted-by":"crossref","unstructured":"GrahamB El\u2010NoubyA TouvronH et\u00a0al.LeViT: a vision transformer in ConvNet's clothing for faster inference. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision2021:12259\u201012269.","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"ZhangY LiuH HuQ.Transfuse: fusing transformers and CNNs for medical image segmentation. In:Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th international conference September 27\u2013October 1 2021 proceedings Part I 24 Springer2021:14\u201024.","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"e_1_2_11_38_1","unstructured":"ZhuJ HamdiA QiY JinY WuJ.Medical SAM 2: segment medical images as video via segment anything model 2.arXiv preprint arXiv:2408.00874 2024."},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103061"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abc04e"},{"key":"e_1_2_11_42_1","article-title":"Mean teachers are better role models: Weight\u2010averaged consistency targets improve semi\u2010supervised deep learning results","volume":"30","author":"Tarvainen A","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_11_43_1","doi-asserted-by":"crossref","unstructured":"YuL WangS LiX FuCW andHengPA.Uncertainty\u2010aware self\u2010ensembling model for semi\u2010supervised 3D left atrium segmentation. In:Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference October 13\u201317 2019 proceedings part II 22 Springer 2019:605\u2010613.","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102383"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108628"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(08)70153-0"},{"key":"e_1_2_11_47_1","doi-asserted-by":"crossref","unstructured":"YangM YuK ZhangC LiZ YangK.Denseaspp for semantic segmentation in street scenes. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2018:3684\u20103692.","DOI":"10.1109\/CVPR.2018.00388"},{"key":"e_1_2_11_48_1","doi-asserted-by":"crossref","unstructured":"ChristPF ElshaerMEA EttlingerF et\u00a0al.Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In:Medical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2016: 19th International Conference October 17\u201021 2016 Proceedings Part II vol.19 Springer International Publishing 2016:415\u2010423.","DOI":"10.1007\/978-3-319-46723-8_48"},{"key":"e_1_2_11_49_1","unstructured":"RupprechtC HuarocE BaustM NavabN.Deep active contours.arXiv preprint arXiv:1607.05074 2016."},{"key":"e_1_2_11_50_1","doi-asserted-by":"crossref","unstructured":"MarcosD TuiaD KellenbergerB et\u00a0al.Learning deep structured active contours end\u2010to\u2010end. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8877\u20108885.","DOI":"10.1109\/CVPR.2018.00925"},{"key":"e_1_2_11_51_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA SenguptaD TerzopoulosD.End\u2010to\u2010end trainable deep active contour models for automated image segmentation: Delineating buildings in aerial imagery. In:Computer Vision\u2013ECCV 2020: 16th European Conference August 23\u201328 2020 Proceedings Part XII 16 Springer2020:730\u2010746.","DOI":"10.1007\/978-3-030-58610-2_43"},{"key":"e_1_2_11_52_1","unstructured":"KendallA GalY.What uncertainties do we need in bayesian deep learning for computer vision?In:Advances in Neural Information Processing Systems.30;2017."},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2019.249"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.211561"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3233402"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nut.2025.112882"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70485","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70485","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T16:43:16Z","timestamp":1789490596000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":56,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1002\/mp.70485"],"URL":"https:\/\/doi.org\/10.1002\/mp.70485","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2025-06-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70485"}}