{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:03:49Z","timestamp":1785701029271,"version":"3.56.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02264","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24423-24433","source":"Crossref","is-referenced-by-count":7,"title":["MaskSAM: Auto-Prompt SAM with Mask Classification for Volumetric Medical Image Segmentation"],"prefix":"10.1109","author":[{"given":"Bin","family":"Xie","sequence":"first","affiliation":[{"name":"Illinois Institute of Technology,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Duan","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawen","family":"Cai","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Cell and Developmental Biology,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gady","family":"Agam","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-017-9983-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.01.005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/isbi56570.2024.10635844"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635844"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47425-5_33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2352\/ei.2025.37.14.coimg-132"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Desam: Decoupling segment anything model for generalizable medical image segmentation","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"3dsam-adapter: Holistic adaptation of sam from 2d to 3d for promptable medical image segmentation","author":"Gong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","article-title":"Accuracy of segment-anything model (sam) in medical image segmentation tasks","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"In International Conference on Machine Learning","author":"Houlsby"},{"key":"ref24","article-title":"When sam meets medical images: An investigation of segment anything model (sam) on multi-phase liver tumor segmentation","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Automated design of deep learning methods for biomedical image segmentation","author":"Isensee","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3881-x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1385-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2661"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7303\/SYN3193805"},{"key":"ref32","article-title":"Auto-prompting sam for mobile friendly 3d medical image segmentation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1117\/12.3006809"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"issue":"4","key":"ref37","article-title":"Sam vs bet: A comparative study for brain extraction and segmentation of magnetic resonance images using deep learning","volume":"2","author":"Mohapatra","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","year":"2023","journal-title":"OpenAI. GPT-4 technical report"},{"key":"ref39","first-page":"1","article-title":"R OpenAI. Gpt-4 technical report.","volume":"2","year":"2023","journal-title":"View in Article"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref42","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","article-title":"Sam. md: Zero-shot medical image segmentation capabilities of the segment anything model","author":"Roy","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Autosam: Adapting sam to medical images by overloading the prompt encoder","author":"Shaharabany","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Sam. md: Zero-shot medical image segmentation capabilities of the segment anything model","author":"Wald","year":"2023","journal-title":"In Medical Imaging with Deep Learning"},{"key":"ref48","article-title":"Sam meets robotic surgery: An empirical study in robustness perspective","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref51","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Customized segment anything model for medical image segmentation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238"},{"key":"ref54","article-title":"nnformer: Interleaved transformer for volumetric segmentation","author":"Zhou","year":"2021","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Can sam segment polyps?","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444753.pdf?arnumber=11444753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:31Z","timestamp":1777612051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02264","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}