{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:53:20Z","timestamp":1788897200545,"version":"build-2803163510"},"reference-count":26,"publisher":"IOP Publishing","issue":"20","license":[{"start":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T00:00:00Z","timestamp":1665705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T00:00:00Z","timestamp":1665705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"crossref","award":["R01EB032680"],"award-info":[{"award-number":["R01EB032680"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Cancer Institute","award":["R01CA215718"],"award-info":[{"award-number":["R01CA215718"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2022,10,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . This work aims to develop an automated segmentation method for the prostate and its surrounding organs-at-risk in pelvic computed tomography to facilitate prostate radiation treatment planning.\n                    <jats:italic>Approach<\/jats:italic>\n                    . In this work, we propose a novel deep learning algorithm combining a U-shaped convolutional neural network (CNN) and vision transformer (VIT) for multi-organ (i.e. bladder, prostate, rectum, left and right femoral heads) segmentation in male pelvic CT images. The U-shaped model consists of three components: a CNN-based encoder for local feature extraction, a token-based VIT for capturing global dependencies from the CNN features, and a CNN-based decoder for predicting the segmentation outcome from the VIT\u2019s output. The novelty of our network is a token-based multi-head self-attention mechanism used in the transformer, which encourages long-range dependencies and forwards informative high-resolution feature maps from the encoder to the decoder. In addition, a knowledge distillation strategy is deployed to further enhance the learning capability of the proposed network.\n                    <jats:italic>Main results<\/jats:italic>\n                    . We evaluated the network using: (1) a dataset collected from 94 patients with prostate cancer; (2) and a public dataset CT-ORG. A quantitative evaluation of the proposed network\u2019s performance was performed on each organ based on (1) volume similarity between the segmented contours and ground truth using Dice score, segmentation sensitivity, and precision, (2) surface similarity evaluated by Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMS), (3) and percentage volume difference (PVD). The performance was then compared against other state-of-art methods. Average volume similarity measures obtained by the network overall organs were Dice score\u00a0=\u00a00.91, sensitivity\u00a0=\u00a00.90, precision = 0.92, average surface similarities were HD\u00a0=\u00a03.78 mm, MSD\u00a0=\u00a01.24 mm, RMS\u00a0=\u00a02.03 mm; average percentage volume difference was PVD\u00a0=\u00a09.9% on the first dataset. The network also obtained Dice score\u00a0=\u00a00.93, sensitivity\u00a0=\u00a00.93, precision = 0.93, average surface similarities were HD\u00a0=\u00a05.82 mm, MSD\u00a0=\u00a01.16 mm, RMS\u00a0=\u00a01.24 mm; average percentage volume difference was PVD\u00a0=\u00a06.6% on the CT-ORG dataset.\n                    <jats:italic>Significance<\/jats:italic>\n                    . In summary, we propose a token-based transformer network with knowledge distillation for multi-organ segmentation using CT images. This method provides accurate and reliable segmentation results for each organ using CT imaging, facilitating the prostate radiation clinical workflow.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ac95f7","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T18:45:17Z","timestamp":1664390717000},"page":"205012","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Male pelvic multi-organ segmentation using token-based transformer Vnet"],"prefix":"10.1088","volume":"67","author":[{"given":"Shaoyan","family":"Pan","sequence":"first","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Lei","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonghe","family":"Wang","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"Wynne","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Roper","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashesh B","family":"Jani","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pretesh","family":"Patel","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey D","family":"Bradley","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Liu","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9023-5855","authenticated-orcid":false,"given":"Xiaofeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Emory University"},{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"pmbac95f7bib1","doi-asserted-by":"publisher","first-page":"245015","DOI":"10.1088\/1361-6560\/aaf11c","type":"journal-article","article-title":"Fully automated organ segmentation in male pelvic CT images","volume":"63","author":"Balagopal","year":"2018","journal-title":"Physics in Medicine & Biology"},{"key":"pmbac95f7bib2","article-title":"Swin-Unet: unet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","type":"preprint"},{"key":"pmbac95f7bib3","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","type":"preprint"},{"key":"pmbac95f7bib4","doi-asserted-by":"publisher","first-page":"192\u20139","DOI":"10.1016\/j.radonc.2019.09.028","type":"journal-article","article-title":"Synthetic MRI-aided multi-organ segmentation on male pelvic CT using cycle consistent deep attention network","volume":"141","author":"Dong","year":"2019","journal-title":"Radiotherapy and Oncology"},{"key":"pmbac95f7bib5","article-title":"An image is worth 16 \u00d7 16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"pmbac95f7bib6","doi-asserted-by":"publisher","first-page":"1189\u2013201","DOI":"10.1109\/TMI.2008.918330","type":"journal-article","article-title":"Automatic model-based segmentation of the heart in CT images","volume":"27","author":"Ecabert","year":"2008","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pmbac95f7bib7","first-page":"1748","author":"Hatamizadeh","year":"2022","type":"conference-proceedings"},{"key":"pmbac95f7bib8","first-page":"770","author":"He","year":"2016","type":"conference-proceedings"},{"key":"pmbac95f7bib9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbac95f7bib11","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1002\/mp.13933","type":"journal-article","article-title":"CT prostate segmentation based on synthetic MRI-aided deep attention fully convolution network","volume":"47","author":"Lei","year":"2020","journal-title":"Medical Physics"},{"key":"pmbac95f7bib12","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab63bb","type":"journal-article","article-title":"Male pelvic multi-organ segmentation aided by CBCT-based synthetic MRI","volume":"65","author":"Lei","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbac95f7bib13","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.promfg.2020.01.386","type":"journal-article","article-title":"A 3D convolutional neural network for volumetric image semantic segmentation","volume":"39","author":"Lu","year":"2019","journal-title":"Procedia Manuf."},{"key":"pmbac95f7bib14","first-page":"-","type":"conference-proceedings","article-title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","author":"Luo","year":"2016"},{"key":"pmbac95f7bib15","doi-asserted-by":"publisher","DOI":"10.1117\/12.2628064","type":"journal-article","volume":"12036","author":"Pan","year":"2022a","journal-title":"Proc SPIE"},{"key":"pmbac95f7bib16","doi-asserted-by":"publisher","DOI":"10.1117\/12.2611540","type":"journal-article","volume":"12033","author":"Pan","year":"2022b","journal-title":"Proc SPIE"},{"key":"pmbac95f7bib17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/s41597-020-00715-8","type":"journal-article","article-title":"CT-ORG, a new dataset for multiple organ segmentation in computed tomography","volume":"7","author":"Rister","year":"2020","journal-title":"Sci. Data"},{"key":"pmbac95f7bib18","first-page":"234","author":"Ronneberger","year":"2015","type":"book"},{"key":"pmbac95f7bib10","first-page":"200","type":"journal-article","article-title":"Transformers in vision: a survey","volume":"24","author":"Salman","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"pmbac95f7bib20","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1109\/TMI.2011.2171357","type":"journal-article","article-title":"Automated 3D segmentation of lungs with lung cancer in CT data using a novel robust active shape model approach","volume":"31","author":"Sun","year":"2012","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pmbac95f7bib19","type":"journal-article","article-title":"CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy","volume":"11315","author":"Sultana","year":"2020","journal-title":"Proc. SPIE"},{"key":"pmbac95f7bib21","first-page":"1","author":"Szegedy","year":"2015","type":"conference-proceedings"},{"key":"pmbac95f7bib22","first-page":"78","author":"Tong","year":"2013","type":"conference-proceedings"},{"key":"pmbac95f7bib23","first-page":"10347","type":"conference-proceedings","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"pmbac95f7bib24","article-title":"Visual transformers: token-based image representation and processing for computer vision","author":"Wu","year":"2020","type":"other"},{"key":"pmbac95f7bib25","article-title":"mixup: Beyond Empirical Risk Minimization","author":"Zhang","year":"2018","type":"other"},{"key":"pmbac95f7bib26","author":"Ulyanov","year":"2016","type":"preprint"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:11:31Z","timestamp":1778778691000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac95f7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,14]]},"references-count":26,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2022,10,14]]},"published-print":{"date-parts":[[2022,10,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ac95f7","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,14]]},"assertion":[{"value":"Male pelvic multi-organ segmentation using token-based transformer Vnet","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2022-06-01","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-09-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-10-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}