{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T03:28:10Z","timestamp":1788492490279,"version":"build-2803163510"},"reference-count":29,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T00:00:00Z","timestamp":1777766400000},"content-version":"am","delay-in-days":365,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#am"},{"start":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:00:00Z","timestamp":1746230400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["P41EB022544"],"award-info":[{"award-number":["P41EB022544"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB033582"],"award-info":[{"award-number":["R01EB033582"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB035093"],"award-info":[{"award-number":["R01EB035093"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R21EB034911"],"award-info":[{"award-number":["R21EB034911"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA165221"],"award-info":[{"award-number":["R01CA165221"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA290745"],"award-info":[{"award-number":["R01CA290745"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE\u2010AC05\u201000OR22725"],"award-info":[{"award-number":["DE\u2010AC05\u201000OR22725"]}],"id":[{"id":"10.13039\/100000015","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":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate delineation of the clinical target volume (CTV) is essential in the radiotherapy treatment of soft tissue sarcomas. However, this process is subject to inter\u2010reader variability due to the need for clinical assessment of risk and extent of potential microscopic spread. This can lead to inconsistencies in treatment planning, potentially impacting treatment outcomes. Most existing automatic CTV delineation methods do not account for this variability and can only generate a single CTV for each case.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aims to develop a deep learning\u2010based technique to generate multiple CTV contours for each case, simulating the inter\u2010reader variability in the clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We employed a publicly available dataset consisting of fluorodeoxyglucose positron emission tomography (FDG\u2010PET), x\u2010ray computed tomography (CT), and pre\u2010contrast T1\u2010weighted magnetic resonance imaging (MRI) scans from 51 patients with soft tissue sarcoma, along with an independent validation set containing five additional patients. An experienced reader drew a contour of the gross tumor volume (GTV) for each patient based on multi\u2010modality images. Subsequently, two additional readers, together with the first one, were responsible for contouring three CTVs in total based on the GTV. We developed a diffusion model\u2010based deep learning method that is capable of generating arbitrary number of different and plausible CTVs to mimic the inter\u2010reader variability in CTV delineation. The proposed model incorporates a separate encoder to extract features from the GTV masks, leveraging the critical role of GTV information in accurate CTV\u00a0delineation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed diffusion model demonstrated superior performance with the highest Dice Index (0.902 compared to values below 0.881 for state\u2010of\u2010the\u2010art models) and the best generalized energy distance (GED) (0.209 compared to values exceeding 0.221 for state\u2010of\u2010the\u2010art models). It also achieved the second\u2010highest recall and precision metrics among the compared ambiguous image segmentation models. Results from both datasets exhibited consistent trends, reinforcing the reliability of our findings. Additionally, ablation studies exploring different model structures and input configurations highlighted the significance of incorporating prior GTV information for accurate CTV\u00a0delineation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed diffusion model successfully generates multiple plausible CTV contours for soft tissue sarcomas, effectively capturing inter\u2010reader variability in CTV\u00a0delineation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17865","type":"journal-article","created":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T11:21:20Z","timestamp":1746271280000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling inter\u2010reader variability in clinical target volume delineation for soft tissue sarcomas using diffusion model"],"prefix":"10.1002","volume":"52","author":[{"given":"Yafei","family":"Dong","sequence":"first","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thibault","family":"Marin","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Biomedical Informatics and Data Science Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elie","family":"Najem","sequence":"additional","affiliation":[{"name":"Department of Imaging Dana\u2010Farber Cancer Institute Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnaud","family":"Beddok","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Rozenblum","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryam","family":"Moteabbed","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Massachusetts General Hospital Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kira","family":"Grogg","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiation Oncology Massachusetts General Hospital Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangxu","family":"Xing","sequence":"additional","affiliation":[{"name":"Gordon Center for Medical Imaging, Department of Radiology Massachusetts General Hospital Boston Massachusetts USA"},{"name":"Department of Radiology Harvard Medical School Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonghye","family":"Woo","sequence":"additional","affiliation":[{"name":"Gordon Center for Medical Imaging, Department of Radiology Massachusetts General Hospital Boston Massachusetts USA"},{"name":"Department of Radiology Harvard Medical School Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen\u2010Lin E.","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Massachusetts General Hospital Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth","family":"Lim","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Biomedical Informatics and Data Science Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georges El","family":"Fakhri","sequence":"additional","affiliation":[{"name":"Yale Biomedical Imaging Institute Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Radiology and Biomedical Imaging Yale University School of Medicine New Haven Connecticut USA"},{"name":"Department of Biomedical Informatics and Data Science Yale University School of Medicine New Haven Connecticut USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,5,3]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-020-0288-4"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.15252\/emmm.201911131"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.12548"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.21037\/jtd.2017.10.147"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1102\/1470-7330.2004.0054"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.11.021"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101909"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14898"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3012186"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.10.005"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2023.03.078"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12602"},{"key":"e_1_2_8_14_1","unstructured":"GalY GhahramaniZ.Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In:BalcanMF WeinbergerKQ eds.Proceedings of the 33rd International Conference on Machine Learning. Vol.48.Proceedings of Machine Learning Research;2016:1050\u20101059."},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.109794"},{"key":"e_1_2_8_16_1","unstructured":"KohlS Romera\u2010ParedesB MeyerC et\u00a0al.A probabilistic U\u2010Net for segmentation of ambiguous images. In:BengioS WallachH LarochelleH GraumanK Cesa\u2010BianchiN GarnettR eds.Advances in Neural Information Processing Systems. Vol.31.Curran Associates Inc.;2018."},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102403"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"BaumgartnerCF TezcanKC ChaitanyaK et\u00a0al.PHiSeg: capturing uncertainty in medical image segmentation. In:ShenD LiuT PetersTM StaibLH EssertC ZhouS YapP\u2010T KhanA eds.Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2019.Springer International Publishing;2019:119\u2010127.","DOI":"10.1007\/978-3-030-32245-8_14"},{"key":"e_1_2_8_19_1","unstructured":"HoJ JainA AbbeelP.Denoising diffusion probabilistic models. In:LarochelleH RanzatoM HadsellR BalcanM LinH eds.Advances in Neural Information Processing Systems. Vol.33.Curran Associates Inc.;2020:6840\u20106851."},{"key":"e_1_2_8_20_1","unstructured":"DhariwalP NicholA.Diffusion models beat GANs on image synthesis. In:RanzatoM BeygelzimerA DauphinY LiangP VaughanJW eds.Advances in Neural Information Processing Systems. Vol.34.Curran Associates Inc.;2021:8780\u20108794."},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"RahmanA ValanarasuJMJ HacihalilogluI PatelVM.Ambiguous medical image segmentation using diffusion models. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2023:11536\u201011546.","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"ZbindenL DoorenbosL PissasT HuberAT SznitmanR M\u00e1rquez\u2010NeilaP.Stochastic segmentation with conditional categorical diffusion models. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).IEEE;2023:1119\u20101129.","DOI":"10.1109\/ICCV51070.2023.00109"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/14\/5471"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2021.04.005"},{"key":"e_1_2_8_25_1","unstructured":"BrockA DonahueJ SimonyanK.Large scale GAN training for high fidelity natural image synthesis. In:International Conference on Learning Representations.2019.https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"WuY HeK.Group normalization. In:FerrariV HebertM SminchisescuC WeissY Cham eds.Computer Vision\u2014ECCV 2018.Springer International Publishing;2018:3\u201019.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0068-x"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acb9cf"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/am-pdf\/10.1002\/mp.17865","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:34:38Z","timestamp":1765190078000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,3]]},"references-count":29,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1002\/mp.17865"],"URL":"https:\/\/doi.org\/10.1002\/mp.17865","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,3]]},"assertion":[{"value":"2024-11-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e17865"}}