{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:44:58Z","timestamp":1785822298604,"version":"3.56.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"crossref","award":["DP250100462"],"award-info":[{"award-number":["DP250100462"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tmi.2026.3705770","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:55:49Z","timestamp":1782158149000},"page":"4579-4590","source":"Crossref","is-referenced-by-count":0,"title":["Medical Referring Image Segmentation via Next-Token Mask Prediction"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1020-7913","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6335-4634","authenticated-orcid":false,"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0948-4641","authenticated-orcid":false,"given":"Gaoyang","family":"Pang","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafu","family":"Hao","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5877-2319","authenticated-orcid":false,"given":"Chentao","family":"Yue","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-2424","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7702-1123","authenticated-orcid":false,"given":"Yonghui","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2538465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2903562"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996645"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3035253"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_69"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_23"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_52"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3395349"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635823"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72384-1_8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_60"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref16","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv:2409.18869"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01575"},{"key":"ref18","article-title":"The pitfalls of next-token prediction","author":"Bachmann","year":"2024","journal-title":"arXiv:2403.06963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"ref20","article-title":"A simple contrastive learning objective for alleviating neural text degeneration","author":"Jiang","year":"2022","journal-title":"arXiv:2205.02517"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3523333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref23","article-title":"Language-guided scale-aware MedSegmentor for lesion segmentation in medical imaging","author":"Ouyang","year":"2024","journal-title":"arXiv:2408.17347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_57"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755166"},{"key":"ref31","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3601359"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04978-0_22"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref36","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"ref43","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"ref51","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020","journal-title":"arXiv:2005.06465"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-020-00173-2"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11640890\/11574023.pdf?arnumber=11574023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:57:10Z","timestamp":1785819430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11574023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":52,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2026.3705770","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}