{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T09:35:52Z","timestamp":1773394552683,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2024"],"award-info":[{"award-number":["U21B2024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272337"],"award-info":[{"award-number":["62272337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tmi.2025.3564320","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T13:31:51Z","timestamp":1745933511000},"page":"3476-3489","source":"Crossref","is-referenced-by-count":4,"title":["Structure Causal Models and LLMs Integration in Medical Visual Question Answering"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0160-2545","authenticated-orcid":false,"given":"Zibo","family":"Xu","sequence":"first","affiliation":[{"name":"School of Microelectronics, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7129-1456","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0578-8138","authenticated-orcid":false,"given":"Weizhi","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1168-3527","authenticated-orcid":false,"given":"Weijie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"Anan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s44196-023-00233-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"key":"ref4","first-page":"1","article-title":"NLM at ImageCLEF 2018 visual question answering in the medical domain","volume-title":"Proc. CLEF","author":"Abacha"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10394601"},{"key":"ref7","first-page":"28541","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref9","article-title":"PMC-VQA: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023","journal-title":"arXiv:2305.10415"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref14","article-title":"GCastle: A Python toolbox for causal discovery","author":"Zhang","year":"2021","journal-title":"arXiv:2111.15155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3494568"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1101\/2020.05.04.20090803"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3587251"},{"key":"ref21","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.8056"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01193"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref27","first-page":"2734","article-title":"Interventional few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yue"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref31","first-page":"1","article-title":"UMASS at ImageCLEF medical visual question answering (Med-VQA) 2018 task","volume-title":"Proc. CLEF","author":"Peng"},{"key":"ref32","first-page":"1","article-title":"Employing inception-ResNet-v2 and Bi-LSTM for medical domain visual question answering","volume-title":"Proc. CLEF","author":"Zhou"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"ref36","first-page":"1","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Vuorio"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3322868"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_36"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3689096.3689459"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3425533"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref47","article-title":"PathVQA: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv:2003.10286"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.981"},{"key":"ref51","first-page":"353","article-title":"Med-flamingo: A multimodal medical few-shot learner","volume-title":"Proc. Mach. Learn. Health (MLH)","author":"Moor"},{"key":"ref52","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data","author":"Wu","year":"2023","journal-title":"arXiv:2308.02463"},{"key":"ref53","article-title":"Uni-med: A unified medical generalist foundation model for multi-task learning via connector-MoE","author":"Zhu","year":"2024","journal-title":"arXiv:2409.17508"},{"key":"ref54","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11112567\/10979774.pdf?arnumber=10979774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T04:36:55Z","timestamp":1754368615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":54,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3564320","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}