{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:25:51Z","timestamp":1781367951722,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018530","name":"Major Science and Technology Projects in Jiangsu Province","doi-asserted-by":"publisher","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}],"id":[{"id":"10.13039\/501100018530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tmi.2025.3525673","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T19:26:30Z","timestamp":1735932390000},"page":"2131-2142","source":"Crossref","is-referenced-by-count":50,"title":["Merging Context Clustering With Visual State Space Models for Medical Image Segmentation"],"prefix":"10.1109","volume":"44","author":[{"given":"Yun","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4543-2179","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7635-2518","authenticated-orcid":false,"given":"Yi","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of General Surgery, First Affiliated Hospital, First School of Clinical Medicine, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26216-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102395"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3224459"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-1009-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0931-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0099-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.10.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3233400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2806309"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3385098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref19","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3590-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref23","first-page":"1","article-title":"Attention U-Net: Learning where to look for the pancreas","volume-title":"Proc. MIDL","author":"Oktay"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref25","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref26","article-title":"LocalMamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024","journal-title":"arXiv:2403.09338"},{"key":"ref27","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref28","article-title":"VM-UNet: Vision mamba UNet for medical image segmentation","author":"Ruan","year":"2024","journal-title":"arXiv:2402.02491"},{"key":"ref29","article-title":"HC-mamba: Vision MAMBA with hybrid convolutional techniques for medical image segmentation","author":"Xu","year":"2024","journal-title":"arXiv:2405.05007"},{"key":"ref30","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2677499"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2019.00053"},{"key":"ref33","article-title":"ISIC 2017-skin lesion analysis towards melanoma detection","author":"Berseth","year":"2017","journal-title":"arXiv:1703.00523"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.03368"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.7303\/SYN3193805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108594"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","article-title":"Understanding the tricks of deep learning in medical image segmentation: Challenges and future directions","author":"Zhang","year":"2022","journal-title":"arXiv:2209.10307"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-61136-w"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/83.552100"},{"key":"ref45","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3230943"},{"key":"ref48","first-page":"1","article-title":"Image as set of points","volume-title":"Proc. ICLR","author":"Ma"},{"key":"ref49","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. ICML","author":"Zhu"},{"key":"ref50","first-page":"1","article-title":"Can mamba learn how to learn? A comparative study on in-context learning tasks","volume-title":"Proc. ICML","author":"Park"},{"key":"ref51","article-title":"Zamba: A compact 7B SSM hybrid model","author":"Glorioso","year":"2024","journal-title":"arXiv:2405.16712"},{"key":"ref52","article-title":"Jamba: A hybrid transformer-mamba language model","author":"Lieber","year":"2024","journal-title":"arXiv:2403.19887"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995040"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3472296"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref58","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2865709"},{"key":"ref62","article-title":"A multi-scale transformer for medical image segmentation: Architectures, model efficiency, and benchmarks","author":"Gao","year":"2022","journal-title":"arXiv:2203.00131"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.6.1.014006"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3211501"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16919-9_9"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"ref70","article-title":"MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation","author":"Ruan","year":"2022","journal-title":"arXiv:2210.14007"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10982228\/10824894.pdf?arnumber=10824894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:56:17Z","timestamp":1746467777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10824894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":70,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3525673","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}