{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:16:02Z","timestamp":1770740162600,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"China National Natural Science Foundation for the Key Program","doi-asserted-by":"publisher","award":["62237001"],"award-info":[{"award-number":["62237001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Fund Project","award":["2024A1515011502"],"award-info":[{"award-number":["2024A1515011502"]}]},{"name":"Zhuhai Science and Technology Plan Project","award":["2320004002758"],"award-info":[{"award-number":["2320004002758"]}]},{"name":"Guangdong Provincial Hospital of Chinese Medicine Special Fund for Scientific and Technological Research on Traditional Chinese Medicine","award":["YN2024MS029"],"award-info":[{"award-number":["YN2024MS029"]}]},{"DOI":"10.13039\/501100001321","name":"Hong Kong Research Grants Council (RGC) Research Impact Fund","doi-asserted-by":"publisher","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2025.3649346","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:36Z","timestamp":1768255476000},"page":"402-417","source":"Crossref","is-referenced-by-count":0,"title":["MCFL: Multimodal Collaborative Fusion Learning for Hashimoto\u2019s Thyroiditis Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6300-1962","authenticated-orcid":false,"given":"Wenchao","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3796-7722","authenticated-orcid":false,"given":"Guanjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghua","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Emergency, Guangdong Provincial Corps Hospital of Chinese People’s Armed Police Force, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9811-6500","authenticated-orcid":false,"given":"Ji","family":"He","sequence":"additional","affiliation":[{"name":"The Fourth Affiliated Hospital, Guangzhou Medical University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2244-638X","authenticated-orcid":false,"given":"Chao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0470-8594","authenticated-orcid":false,"given":"Feng","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4211-7034","authenticated-orcid":false,"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2020.102649"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40618-020-01477-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S413230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-78938-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2741\/4437"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app142210384"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3331944"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3414389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-023-00225-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.54393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21037\/qims-23-1357"},{"key":"ref12","article-title":"MegaPairs: Massive data synthesis for universal multimodal retrieval","author":"Zhou","year":"2024","journal-title":"arXiv:2412.14475"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680966"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102344"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106791"},{"key":"ref18","article-title":"Attention-gated networks for improving ultrasound scan plane detection","author":"Schlemper","year":"2018","journal-title":"arXiv:1804.05338"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpbup.2024.100148"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31449-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3653644.3680497"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/ijms25094703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103515"},{"key":"ref26","article-title":"Benchmarking multimodal retrieval augmented generation with dynamic VQA dataset and self-adaptive planning agent","author":"Li","year":"2024","journal-title":"arXiv:2411.02937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3477916"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3391002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.wikinlp-1.17"},{"key":"ref30","article-title":"Multimodal fusion on low-quality data: A comprehensive survey","author":"Zhang","year":"2024","journal-title":"arXiv:2404.18947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2057"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-023-00779-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/acc2fe"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102994"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s24082461"},{"key":"ref36","article-title":"Deep reinforced active learning for multi-class image classification","author":"Slade","year":"2022","journal-title":"arXiv:2206.13391"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13081491"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102193"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2025.05.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s22103911"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref43","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1052"},{"key":"ref50","article-title":"Bag of tricks for efficient text classification","author":"Joulin","year":"2016","journal-title":"arXiv:1607.01759"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128680"},{"key":"ref53","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","article-title":"BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref56","article-title":"UniMed-CLIP: Towards a unified image-text pretraining paradigm for diverse medical imaging modalities","author":"Khattak","year":"2024","journal-title":"arXiv:2412.10372"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11339361.pdf?arnumber=11339361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:31Z","timestamp":1770671431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3649346","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}