{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:14:50Z","timestamp":1765808090808,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tmi.2022.3191974","type":"journal-article","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T20:35:15Z","timestamp":1658176515000},"page":"1241-1253","source":"Crossref","is-referenced-by-count":10,"title":["3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0009-2817","authenticated-orcid":false,"given":"Jianye","family":"Pang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6135-3991","authenticated-orcid":false,"given":"Cheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent AI Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Peking Union Medical College Hospital, Dongcheng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0192-3881","authenticated-orcid":false,"given":"Jianbo","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Peking Union Medical College Hospital, Dongcheng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Peking Union Medical College Hospital, Dongcheng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Peking Union Medical College Hospital, Dongcheng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent AI Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"chen","year":"2021","journal-title":"arXiv 2102 04306"},{"key":"ref12","article-title":"MLP-mixer: An all-MLP architecture for vision","author":"tolstikhin","year":"2021","journal-title":"arXiv 2105 01601"},{"key":"ref56","article-title":"Vision transformers are robust learners","author":"paul","year":"2021","journal-title":"arXiv 2105 07581"},{"key":"ref15","article-title":"ViT-V-Net: Vision transformer for unsupervised volumetric medical image registration","author":"chen","year":"2021","journal-title":"arXiv 2104 06468"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"ref53","first-page":"131","article-title":"3D U-Net based brain tumor segmentation and survival days prediction","author":"wang","year":"2019","journal-title":"Proc Int MICCAI Brainlesion Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref11","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"arXiv 2103 10697"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59719-1_36"},{"key":"ref10","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref54","first-page":"210","article-title":"Bag of tricks for 3D MRI brain tumor segmentation","author":"zhao","year":"2019","journal-title":"Proc Int MICCAI Brainlesion Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_43"},{"key":"ref19","article-title":"Refiner: Refining self-attention for vision transformers","author":"zhou","year":"2021","journal-title":"arXiv 2106 03714"},{"key":"ref18","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021","journal-title":"arXiv 2103 11886"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref50","first-page":"311","article-title":"3D MRI brain tumor segmentation using autoencoder regularization","author":"myronenko","year":"2018","journal-title":"Proc Int MICCAI Brainlesion Workshop"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_94"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_71"},{"key":"ref48","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"oktay","year":"2018","journal-title":"arXiv 1804 03999"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2878669"},{"key":"ref42","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","first-page":"1","article-title":"Rethinking positional encoding in language pre-training","author":"ke","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref44","article-title":"Uformer: A general U-shaped transformer for image restoration","author":"wang","year":"2021","journal-title":"arXiv 2106 03106"},{"key":"ref43","first-page":"15316","article-title":"Augmented shortcuts for vision transformers","author":"tang","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01070"},{"key":"ref8","first-page":"424","article-title":"3D U-Net: Learning dense volumetric segmentation from sparse annotation","author":"\u00e7i\u00e7ek","year":"2016","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_36"},{"key":"ref9","first-page":"3","article-title":"UNet++: A nested u-net architecture for medical image segmentation","author":"zhou","year":"2018","journal-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13416"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3088421"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_20"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2897538"},{"key":"ref40","first-page":"30392","article-title":"Early convolutions help transformers see better","author":"xiao","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref35","article-title":"CoTr: Efficiently bridging CNN and transformer for 3D medical image segmentation","author":"xie","year":"2021","journal-title":"arXiv 2103 03024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref36","first-page":"109","article-title":"TransBTS: Multimodal brain tumor segmentation using transformer","author":"wang","year":"2021","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref31","article-title":"CycleMLP: A MLP-like architecture for dense prediction","author":"chen","year":"2021","journal-title":"arXiv 2107 10224"},{"key":"ref30","article-title":"AS-MLP: An axial shifted MLP architecture for vision","author":"lian","year":"2021","journal-title":"arXiv 2107 08391"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/112"},{"key":"ref32","article-title":"Video swin transformer","author":"liu","year":"2021","journal-title":"arXiv 2106 13230"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13121"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840695"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_27"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_9"},{"key":"ref24","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021","journal-title":"arXiv 2104 13840"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref25","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"huang","year":"2021","journal-title":"arXiv 2106 03650"},{"key":"ref20","article-title":"On the connection between local attention and dynamic depth-wise convolution","author":"han","year":"2021","journal-title":"arXiv 2106 04263"},{"key":"ref22","article-title":"Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention","author":"wu","year":"2021","journal-title":"arXiv 2111 03368"},{"key":"ref21","article-title":"Swin-UNet: Unet-like pure transformer for medical image segmentation","author":"cao","year":"2021","journal-title":"arXiv 2105 05537"},{"key":"ref28","article-title":"MSG-transformer: Exchanging local spatial information by manipulating messenger tokens","author":"fang","year":"2021","journal-title":"arXiv 2105 15168"},{"key":"ref27","article-title":"PVT V2: Improved baselines with pyramid vision transformer","author":"wang","year":"2021","journal-title":"arXiv 2106 13797"},{"key":"ref29","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped Windows","author":"dong","year":"2021","journal-title":"arXiv 2107 00652"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/42\/10114431\/09832644.pdf?arnumber=9832644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T17:51:08Z","timestamp":1684777868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9832644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2022.3191974","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"type":"print","value":"0278-0062"},{"type":"electronic","value":"1558-254X"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}