{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:39:02Z","timestamp":1767677942041,"version":"3.48.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203303"],"award-info":[{"award-number":["62203303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFC2511100\/2024YFC2511105"],"award-info":[{"award-number":["2024YFC2511100\/2024YFC2511105"]}]},{"DOI":"10.13039\/501100010256","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tmi.2025.3594364","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:33:42Z","timestamp":1753986822000},"page":"206-219","source":"Crossref","is-referenced-by-count":1,"title":["HoloDx: Knowledge- and Data-Driven Multimodal Diagnosis of Alzheimer\u2019s Disease"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1210-1306","authenticated-orcid":false,"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-5863","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9065-3691","authenticated-orcid":false,"given":"Yi","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2212948"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.13239"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(24)01883-X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-024-05248-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10821851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01045-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108979"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271701"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110285"},{"key":"ref13","article-title":"HuatuoGPT-vision, towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024","journal-title":"arXiv:2406.19280"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385864"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385770"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107207"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00056"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102069"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385819"},{"key":"ref25","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref28","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref29","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":"ref30","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref31","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref36","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181cb3e25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1017\/S1041610209009405"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.9.1498"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.12.044"},{"volume-title":"Multimodal Imaging Evaluation in Degenerative Dementia","year":"2023","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2011.03.005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(07)70178-3"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2018.02.018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24750"},{"key":"ref46","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lundberg"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2016.12.011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.780174"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2020.05.012"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2021.08.093"},{"key":"ref51","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref52","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref53","first-page":"1","article-title":"Me-LLaMA: Foundation large language models for medical applications","volume":"2024","author":"Xie","year":"2024","journal-title":"Res. Square"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp-2024-333467"},{"key":"ref55","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11328978\/11105511.pdf?arnumber=11105511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:35:38Z","timestamp":1767677738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11105511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3594364","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"type":"print","value":"0278-0062"},{"type":"electronic","value":"1558-254X"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}