{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:42:46Z","timestamp":1784169766345,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["ITS\/028\/21FP"],"award-info":[{"award-number":["ITS\/028\/21FP"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["ITCPD\/17-9"],"award-info":[{"award-number":["ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["MHP\/002\/22"],"award-info":[{"award-number":["MHP\/002\/22"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Committee Fund","doi-asserted-by":"publisher","award":["SGDX20210823103201011"],"award-info":[{"award-number":["SGDX20210823103201011"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone","award":["HZQB-KCZYB-2020083"],"award-info":[{"award-number":["HZQB-KCZYB-2020083"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tmi.2025.3564382","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T13:40:30Z","timestamp":1745588430000},"page":"3727-3740","source":"Crossref","is-referenced-by-count":21,"title":["MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-4263","authenticated-orcid":false,"given":"Jiaxin","family":"Zhuang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linshan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0835-3770","authenticated-orcid":false,"given":"Qiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Fei","sequence":"additional","affiliation":[{"name":"School of Optical and Electronic Information, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6677-3194","authenticated-orcid":false,"given":"Varut","family":"Vardhanabhuti","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, The University of Hong Kong, SAR, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8400-3780","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, the Department of Chemical and Biological Engineering, State Key Laboratory of Molecular Neuroscience, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101693"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/rbme.2024.3496744"},{"key":"ref3","article-title":"Touchstone benchmark: Are we on the right way for evaluating AI algorithms for medical segmentation?","author":"Bassi","year":"2024","journal-title":"arXiv:2411.03670"},{"key":"ref4","article-title":"Label-efficient deep learning in medical image analysis: Challenges and future directions","author":"Jin","year":"2023","journal-title":"arXiv:2303.12484"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385966"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126577"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01453"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"ref10","article-title":"Large-scale 3D medical image pre-training with geometric context priors","author":"Wu","year":"2024","journal-title":"arXiv:2410.09890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02158"},{"key":"ref12","article-title":"MG-3D: Multi-grained knowledge-enhanced 3D medical vision-language pre-training","author":"Ni","year":"2024","journal-title":"arXiv:2412.05876"},{"key":"ref13","article-title":"FreeTumor: Advance tumor segmentation via large-scale tumor synthesis","author":"Wu","year":"2024","journal-title":"arXiv:2406.01264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10822757"},{"key":"ref15","article-title":"Automatic organ and pan-cancer segmentation in abdomen CT: The FLARE 2023 challenge","author":"Ma","year":"2024","journal-title":"arXiv:2408.12534"},{"key":"ref16","article-title":"A multimodal knowledge-enhanced whole-slide pathology foundation model","author":"Xu","year":"2024","journal-title":"arXiv:2407.15362"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"ref20","article-title":"Advancing volumetric medical image segmentation via global-local masked autoencoder","author":"Zhuang","year":"2023","journal-title":"arXiv:2306.08913"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_47"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3169003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref25","first-page":"35632","article-title":"MCMAE: Masked convolution meets masked autoencoders","volume-title":"Proc. NeurIPS","volume":"35","author":"Gao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref30","first-page":"9729","article-title":"Improved baselines with momentum contrastive learning","volume-title":"Proc. CVPR","author":"Chen"},{"key":"ref31","article-title":"An empirical study of training self-supervised visual transformers","author":"Chen","year":"2021","journal-title":"arXiv:2104.02057"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16440-8_52"},{"key":"ref34","first-page":"18158","article-title":"3D self-supervised methods for medical imaging","volume-title":"Proc. NeurIPS","author":"Taleb"},{"key":"ref35","article-title":"PGL: Prior-guided local self-supervised learning for 3D medical image segmentation","author":"Xie","year":"2020","journal-title":"arXiv:2011.12640"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101746"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101840"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref40","first-page":"666","article-title":"ViT-AE++: Improving vision transformer autoencoder for self-supervised medical image representations","volume-title":"Proc. MIDL","author":"Prabhakar"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102879"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00768"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00358"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45857-6_10"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref50","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":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_33"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234002"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.7303\/SYN3193805"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17971-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021210384"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-018-0002-5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024.podcast"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2869576"},{"key":"ref61","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","author":"Simpson","year":"2019","journal-title":"arXiv:1902.09063"},{"key":"ref62","article-title":"Unleashing the strengths of unlabeled data in pan-cancer abdominal organ quantification: The FLARE22 challenge","author":"Ma","year":"2023","journal-title":"arXiv:2308.05862"},{"key":"ref63","first-page":"36722","article-title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume-title":"Proc. NeurIPS","author":"Ji"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.04.045"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3204090"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref71","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref72","article-title":"Conversion between CT and MRI images using diffusion and score-matching models","author":"Lyu","year":"2022","journal-title":"arXiv:2209.12104"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref74","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref75","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. NeurIPS","author":"Sung"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11165775\/10977020.pdf?arnumber=10977020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T17:31:11Z","timestamp":1758130271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10977020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":75,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3564382","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}