{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:02:44Z","timestamp":1790352164234,"version":"4.1.0"},"reference-count":38,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background and purpose<\/jats:title><jats:p>In radiotherapy, magnetic resonance (MR) imaging has higher contrast for soft tissues compared to computed tomography (CT) scanning and does not emit radiation. However, manual annotation of the deep learning\u2010based automatic organ\u2010at\u2010risk (OAR) delineation algorithms is expensive, making the collection of large\u2010high\u2010quality annotated datasets a challenge. Therefore, we proposed the low\u2010cost semi\u2010supervised OAR segmentation method using small pelvic MR image annotations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We trained a deep learning\u2010based segmentation model using 116 sets of MR images from 116 patients. The bladder, femoral heads, rectum, and small intestine were selected as OAR regions. To generate the training set, we utilized a semi\u2010supervised method and ensemble learning techniques. Additionally, we employed a post\u2010processing algorithm to correct the self\u2010annotation data. Both 2D and 3D auto\u2010segmentation networks were evaluated for their performance. Furthermore, we evaluated the performance of semi\u2010supervised method for 50 labeled data and only 10 labeled data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The Dice similarity coefficient (DSC) of the bladder, femoral heads, rectum and small intestine between segmentation results and reference masks is 0.954, 0.984, 0.908, 0.852 only using self\u2010annotation and post\u2010processing methods of 2D segmentation model. The DSC of corresponding OARs is 0.871, 0.975, 0.975, 0.783, 0.724 using 3D segmentation network, 0.896, 0.984, 0.890, 0.828 using 2D segmentation network and common supervised method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The outcomes of our study demonstrate that it is possible to train a multi\u2010OAR segmentation model using small annotation samples and additional unlabeled data. To effectively annotate the dataset, ensemble learning and post\u2010processing methods were employed. Additionally, when dealing with anisotropy and limited sample sizes, the 2D model outperformed the 3D model in terms of performance.<\/jats:p><\/jats:sec>","DOI":"10.1002\/acm2.14296","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T21:00:45Z","timestamp":1708635645000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Semi\u2010supervised auto\u2010segmentation method for pelvic organ\u2010at\u2010risk in magnetic resonance images based on deep\u2010learning"],"prefix":"10.1002","volume":"25","author":[{"given":"Xianan","family":"Li","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Peking University People's Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lecheng","family":"Jia","sequence":"additional","affiliation":[{"name":"Radiotherapy laboratory Shenzhen United Imaging Research Institute of Innovative Medical Equipment  Shenzhen China"},{"name":"Zhejiang Engineering Research Center for Innovation and Application of Intelligent Radiotherapy Technology  Wenzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Radiotherapy laboratory Shenzhen United Imaging Research Institute of Innovative Medical Equipment  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Radiology Peking University People's Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology Peking University People's Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Radiotherapy Business Unit Shanghai United Imaging Healthcare Co., Ltd.  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziquan","family":"Wei","sequence":"additional","affiliation":[{"name":"Radiotherapy laboratory Shenzhen United Imaging Research Institute of Innovative Medical Equipment  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiqi","family":"Xiong","sequence":"additional","affiliation":[{"name":"Radiotherapy Business Unit Shanghai United Imaging Healthcare Co., Ltd.  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Li","sequence":"additional","affiliation":[{"name":"Radiotherapy laboratory Shenzhen United Imaging Research Institute of Innovative Medical Equipment  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Peking University People's Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology Peking University People's Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab79c3"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103027"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.918330"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104815"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101821"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2019.10.006"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.6.1.014001"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.2174\/1574893615999200425232601"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2377694"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2013.12.002"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010319\u201024574\u20104_28"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"BallestarL VilaplanaV.MRI brain tumor segmentation and uncertainty estimation using 3D\u2010UNet architectures. Brainlesion: Glioma Multiple Sclerosis Stroke and Traumatic Brain Injuries.2021;12658:376\u2010390. doi:10.1007\/978\u20103\u2010030\u201072084\u20101_34","DOI":"10.1007\/978-3-030-72084-1_34"},{"key":"e_1_2_8_15_1","doi-asserted-by":"crossref","unstructured":"YuH ChenW.Research on 3D medical image segmentation based on improved 3D\u2010Unet. 2021 IEEE 4th Advanced Information Management Communicates Electronic and Automation Control Conference (IMCEC) Chongqing China 2021;923\u2010928. doi:10.1109\/IMCEC51613.2021.9482365","DOI":"10.1109\/IMCEC51613.2021.9482365"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac529"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims\u201020\u20101076"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742\u20106596\/1924\/1\/012018"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880\u2010022\u201000851\u20100"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"FuZ LuoF Efio\u2010AkollyK et\u00a0al.HAUNet\u20103D: a novel hierarchical attention 3D UNet for lung nodule segmentation. 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Houston TX USA 2021;1213\u20101220. doi:10.1109\/BIBM52615.2021.9669883","DOI":"10.1109\/BIBM52615.2021.9669883"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"PapandreouG ChenL\u2010C MurphyK YuilleA.Weakly\u2010and semi\u2010supervised learning of a deep convolutional network for semantic image segmentation. 2015 IEEE International Conference on Computer Vision (ICCV) Santiago Chile 2015;1742\u20101750. doi:10.1109\/ICCV.2015.203","DOI":"10.1109\/ICCV.2015.203"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2020.1775290"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104269"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20114"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics1030007"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.12.057"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2011.2122306"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.856346"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101851"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182012"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14196"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2022.11.004"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22093440"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.37936\/ecti\u2010cit.2021152.240112"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102459"},{"key":"e_1_2_8_38_1","doi-asserted-by":"crossref","unstructured":"RenzhenW WuY HuaiC WangL MengD.Neighbor matching for semi\u2010supervised learning. Medical Image Computing and Computer Assisted Intervention MICCAI.2021;12902:439\u2010449. doi:10.1007\/978\u20103\u2010030\u201087196\u20103_41","DOI":"10.1007\/978-3-030-87196-3_41"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1088\/2057\u20101976\/aad100"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.14296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:20:55Z","timestamp":1710260455000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.14296"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10.1002\/acm2.14296"],"URL":"https:\/\/doi.org\/10.1002\/acm2.14296","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"assertion":[{"value":"2023-05-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-23","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14296"}}