{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T15:15:33Z","timestamp":1760800533366,"version":"3.28.0"},"reference-count":20,"publisher":"SPIE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,4]]},"DOI":"10.1117\/12.2611540","type":"proceedings-article","created":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T15:11:40Z","timestamp":1648825900000},"page":"72","source":"Crossref","is-referenced-by-count":8,"title":["CVT-Vnet:  convolutional-transformer model for head and neck multi-organ segmentation"],"prefix":"10.1117","author":[{"given":"Shaoyan","family":"Pan","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Tonghe","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Mark","family":"McDonald","sequence":"additional","affiliation":[]},{"given":"Jeffrey D.","family":"Bradley","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiaofeng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"189","reference":[{"key":"c1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v48.10"},{"key":"c2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abd953"},{"key":"c3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2014.08.350"},{"key":"c4","unstructured":"F. Milletari, N. Navab, and S.-A. Ahmadi, \u201cV-net: Fully convolutional neural networks for volumetric medical image segmentation.\u201d 565\u2013571."},{"key":"c5","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, \u201cU-net: Convolutional networks for biomedical image segmentation.\u201d 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"c6","doi-asserted-by":"publisher","DOI":"10.2196\/26151"},{"key":"c7","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-10"},{"key":"c8","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v47.9"},{"key":"c9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.05.003"},{"key":"c10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"c11","unstructured":"S. d\u2019Ascoli, H. Touvron, M. L. Leavitt et al., \u201cConvit: Improving vision transformers with soft convolutional inductive biases.\u201d 2286\u20132296."},{"key":"c12","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv preprint arXiv:1607.08022"},{"key":"c13","unstructured":"K. He, X. Zhang, S. Ren et al., \u201cDeep residual learning for image recognition.\u201d 770\u2013778."},{"key":"c14","article-title":"On the relationship between self-attention and convolutional layers","author":"Cordonnier","year":"2019","journal-title":"arXiv preprint arXiv:1911.03584"},{"key":"c15","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"Ramachandran","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"c16","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume":"29","author":"Luo","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"c17","article-title":"Cmt: Convolutional neural networks meet vision transformers","author":"Guo","year":"2021","journal-title":"arXiv preprint arXiv:2107.06263"},{"key":"c18","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12197"},{"key":"c19","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017","journal-title":"arXiv preprint arXiv:1710.09412"},{"key":"c20","article-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv preprint arXiv:1804.03999"}],"event":{"name":"Computer-Aided Diagnosis","start":{"date-parts":[[2022,2,20]]},"location":"San Diego, United States","end":{"date-parts":[[2022,3,28]]}},"container-title":["Medical Imaging 2022: Computer-Aided Diagnosis"],"original-title":[],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T21:31:28Z","timestamp":1656797488000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/conference-proceedings-of-spie\/12033\/2611540\/CVT-Vnet---convolutional-transformer-model-for-head-and\/10.1117\/12.2611540.full"}},"subtitle":[],"editor":[{"given":"Khan M.","family":"Iftekharuddin","sequence":"additional","affiliation":[]},{"given":"Karen","family":"Drukker","sequence":"additional","affiliation":[]},{"given":"Maciej A.","family":"Mazurowski","sequence":"additional","affiliation":[]},{"given":"Hongbing","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Chisako","family":"Muramatsu","sequence":"additional","affiliation":[]},{"given":"Ravi K.","family":"Samala","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,4,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1117\/12.2611540","relation":{},"subject":[],"published":{"date-parts":[[2022,4,4]]}}}