{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T07:23:17Z","timestamp":1783322597908,"version":"3.54.6"},"reference-count":45,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>In radiotherapy planning, manual contouring is labor\u2010intensive and time\u2010consuming. Accurate and robust automated segmentation models improve the efficiency and treatment outcome. We aim to develop a novel hybrid deep learning approach, combining convolutional neural networks (CNNs) and the self\u2010attention mechanism, for rapid and accurate multi\u2010organ segmentation on head and neck computed tomography (CT) images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Head and neck CT images with manual contours of 115 patients were retrospectively collected and used. We set the training\/validation\/testing ratio to 81\/9\/25 and used the 10\u2010fold cross\u2010validation strategy to select the best model parameters. The proposed hybrid model segmented 10 organs\u2010at\u2010risk (OARs) altogether for each case. The performance of the model was evaluated by three metrics, that is, the Dice Similarity Coefficient (DSC), Hausdorff distance 95% (HD95), and mean surface distance (MSD). We also tested the performance of the model on the head and neck 2015 challenge dataset and compared it against several state\u2010of\u2010the\u2010art automated segmentation algorithms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed method generated contours that closely resemble the ground truth for 10 OARs. On the head and neck 2015 challenge dataset, the DSC scores of these OARs were 0.910.02, 0.730.10, 0.950.03, 0.760.08, 0.790.05, 0.870.05, 0.860.08, 0.870.03, and 0.870.07 for brain stem, chiasm, mandible, left\/right optic nerve, left\/right submandibular, and left\/right parotid, respectively. Our results of the new weaving attention U\u2010net (WAU\u2010net) demonstrate superior or similar performance on the segmentation of head and neck CT images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>We developed a deep learning approach that integrates the merits of CNNs and the self\u2010attention mechanism. The proposed WAU\u2010net can efficiently capture local and global dependencies and achieves state\u2010of\u2010the\u2010art performance on the head and neck multi\u2010organ segmentation task.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15287","type":"journal-article","created":{"date-parts":[[2021,10,16]],"date-time":"2021-10-16T13:39:15Z","timestamp":1634391555000},"page":"7052-7062","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Weaving attention U\u2010net: A novel hybrid CNN and attention\u2010based method for organs\u2010at\u2010risk segmentation in head and neck CT images"],"prefix":"10.1002","volume":"48","author":[{"given":"Zhuangzhuang","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering Washington University  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Washington University School of Medicine  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiram","family":"Gay","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Washington University School of Medicine  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weixiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering Washington University  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baozhou","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Washington University School of Medicine  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,10,26]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14378"},{"key":"e_1_2_9_3_1","unstructured":"TA Ratko G Douglas JA De Souza SE Belinson N Aronson 2015"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/0360-3016(94)00421-G"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14580"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.06.090"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ac26e8"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.09.062"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12197"},{"key":"e_1_2_9_10_1","article-title":"Fully automatic segmentation of head and neck organs using active appearance models","author":"Mannion\u2010Haworth R","year":"2015","journal-title":"MIDAS J"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2013.12.006"},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"HanX HoogemanMS LevendagPC et\u00a0al.Atlas\u2010based auto\u2010segmentation of head and neck CT images.Paper presented at: International Conference on Medical Image Computing and Computer\u2010assisted Intervention; September 6\u201010 2008;New York NY USA.","DOI":"10.1007\/978-3-540-85990-1_52"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748-717X-8-154"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"MaL GuoR ZhangG et\u00a0al.Automatic segmentation of the prostate on CT images using deep learning and multi\u2010atlas fusion.Paper presented at: Medical Imaging 2017: Image Processing; February 24 2017;Orlando FL.","DOI":"10.1117\/12.2255755"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8498-1_24"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4871623"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4810971"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737535"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.650883"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"TamC YangX TianS JiangX BeitlerJ LiS.Automated delineation of organs\u2010at\u2010risk in head and neck CT images using multi\u2010output support vector regression. Paper presented at:Medical Imaging 2018: Biomedical Applications in Molecular Structural and Functional Imaging; March 12 2018;Houston TX.","DOI":"10.1117\/12.2292556"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2768621"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"YangQ ZhangS SunX SunJ YuanK.Automatic segmentation of head\u2010neck organs by multi\u2010mode CNNs for radiation therapy. Paper presented at:2019 International Conference on Medical Imaging Physics and Engineering (ICMIPE); November 22\u201024 2019;Shenzhen China.","DOI":"10.1109\/ICMIPE47306.2019.9098166"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944958"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12837"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13147"},{"key":"e_1_2_9_26_1","volume-title":"Deep Learning","author":"Goodfellow I","year":"2016"},{"key":"e_1_2_9_27_1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation. Paper presented at:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; June 7\u201012 2015;Boston MA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: fully convolutional neural networks for volumetric medical image segmentation. Paper presented at:2016 Fourth International Conference on 3D Vision (3DV); October 25\u201028 2016; Stanford CA.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_9_32_1","unstructured":"OktayO SchlemperJ FolgocLL et al.Attention u\u2010net: learning where to look for the pancreas April 11 2018. arXiv preprint arXiv:180403999. 2018."},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12045"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13300"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0099-z"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf83c"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"GuoD JinD ZhuZ et al.Organ at risk segmentation for head and neck cancer using stratified learning and neural architecture search. Paper presented at: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2020 2020 Volume: 1 Pages: 4222\u20104231; Seattle WA.https:\/\/doi.org\/10.1109\/CVPR42600.2020.00428","DOI":"10.1109\/CVPR42600.2020.00428"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_2_9_39_1","doi-asserted-by":"crossref","unstructured":"ValanarasuJMJ OzaP HacihalilogluI PatelVM.Medical transformer: gated axial\u2010attention for medical image segmentation July 6 2021. arXiv preprint arXiv:210210662. 2021.","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"e_1_2_9_40_1","unstructured":"VaswaniA ShazeerN ParmarN et al.Attention is all you need Dec 6 2017 arXiv preprint arXiv:170603762. 2017."},{"key":"e_1_2_9_41_1","unstructured":"TouvronH CordM DouzeM MassaF SablayrollesA J\u00e9gouH.Training data\u2010efficient image transformers & distillation through attention Jan.15 202. arXiv preprint arXiv:201212877. 2020."},{"key":"e_1_2_9_42_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et al.An image is worth 16\u00d716 words: transformers for image recognition at scale June 3 2021 arXiv preprint arXiv:201011929. 2020."},{"key":"e_1_2_9_43_1","unstructured":"ZhangZ SunB ZhangW.Pyramid medical transformer for medical image segmentation April 29 2021. arXiv preprint arXiv:210414702. 2021."},{"key":"e_1_2_9_44_1","unstructured":"HoJ KalchbrennerN WeissenbornD SalimansT.Axial attention in multidimensional transformers Dec.20 2019. arXiv preprint arXiv:191212180. 2019."},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"e_1_2_9_46_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization Jan.30 2017. arXiv preprint arXiv:14126980. 2014."}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15287","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15287","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T13:13:25Z","timestamp":1736860405000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":45,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10.1002\/mp.15287"],"URL":"https:\/\/doi.org\/10.1002\/mp.15287","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-06-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}