{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:06:38Z","timestamp":1777921598066,"version":"3.51.4"},"reference-count":213,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Joint Funds of the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276199"],"award-info":[{"award-number":["62276199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62431020"],"award-info":[{"award-number":["62431020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276201"],"award-info":[{"award-number":["62276201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"111 Project, the Program for Cheung Kong Scholars and Innovative Research Team in University","award":["15R53"],"award-info":[{"award-number":["15R53"]}]},{"name":"Science and Technology Innovation Project from the Chinese Ministry of Education, the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University","award":["HMHAI-202404"],"award-info":[{"award-number":["HMHAI-202404"]}]},{"name":"Science and Technology Innovation Project from the Chinese Ministry of Education, the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University","award":["HMHAI-202405"],"award-info":[{"award-number":["HMHAI-202405"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tai.2025.3618796","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:42:57Z","timestamp":1760463777000},"page":"2426-2446","source":"Crossref","is-referenced-by-count":0,"title":["Foundation Model for Medical Imaging: A Comprehensive Review"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1577-1484","authenticated-orcid":false,"given":"Jingyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3390-2599","authenticated-orcid":false,"given":"Ruiyang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-8830","authenticated-orcid":false,"given":"Yuwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9124-696X","authenticated-orcid":false,"given":"Ronghua","family":"Shang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8872-2195","authenticated-orcid":false,"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Dehghani","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102996"},{"key":"ref5","article-title":"Foundational models in medical imaging: A comprehensive survey and future vision","author":"Azad","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3506283"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"240","key":"ref12","first-page":"1","article-title":"PALM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Radford","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7326\/M23-2772"},{"key":"ref21","article-title":"The (r) evolution of multimodal large language models: A survey","author":"Caffagni","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00914-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00516-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.59717\/j.xinn-med.2023.100030"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06638-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06812-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06823-w"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1063\/5.0186054"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adg3289"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00376-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1089\/omi.2019.0038"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/science.1209236"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06013-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3170001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3247455"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-021-01671-z"},{"key":"ref40","first-page":"248","article-title":"MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering","volume-title":"Proc. Conf. Health, Inference, Learn. (PMLR)","author":"Pal","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024.podcast"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2661"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref45","article-title":"SA-Med2D-20M dataset: Segment anything in 2D medical imaging with 20 million masks","author":"Ye","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11845-021-02730-z"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102134"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-03302-0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101988"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10300-7"},{"key":"ref53","first-page":"55565","article-title":"Are emergent abilities of large language models a mirage?","volume":"36","author":"Schaeffer","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.63317\/3dhqzf3tvt2z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3611651"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref57","article-title":"Modeling the language of life\u2013deep learning protein sequences","author":"Heinzinger","year":"2019","journal-title":"bioRxiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref59","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref60","article-title":"RobertA: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref61","article-title":"Albert: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref63","article-title":"ClinicalBERT: Modeling clinical notes and predicting hospital readmission","author":"Huang","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1023281"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref67","article-title":"Pretrained pooled contextualized embeddings for biomedical sequence labeling tasks","author":"Sharma","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.59"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"ref70","article-title":"Transfer learning for biomedical question answering","volume-title":"Proc. CLEF (Work. Notes)","author":"Akdemir","year":"2020"},{"key":"ref71","first-page":"2022","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Workshop"},{"issue":"1","key":"ref72","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref74","article-title":"MedGPT: Medical concept prediction from clinical narratives","author":"Kraljevic","year":"2021"},{"key":"ref75","article-title":"SciFive: A text-to-text transformer model for biomedical literature","author":"Phan","year":"2021"},{"key":"ref76","article-title":"PubMedGPT 2.7 b","author":"Bolton","year":"2022"},{"key":"ref77","article-title":"DoctorGLM: Fine-tuning your chinese doctor is not a herculean task","author":"Xiong","year":"2023"},{"key":"ref78","article-title":"MedAlpaca\u2014An open-source collection of medical conversational AI models and training data","author":"Han","year":"2023"},{"key":"ref79","article-title":"BianQue: Balancing the questioning and suggestion ability of health LLMS with multi-turn health conversations polished by ChatGPT","author":"Chen","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00958-w"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.83"},{"key":"ref84","article-title":"STU-Net: Scalable and transferable medical image segmentation models empowered by large-scale supervised pre-training","author":"Huang","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-01998-6"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01064"},{"key":"ref88","article-title":"MedUniSeg: 2D and 3D medical image segmentation via a prompt-driven universal model","author":"Ye","year":"2024"},{"key":"ref89","article-title":"MIS-FM: 3D medical image segmentation using foundation models pretrained on a large-scale unannotated dataset","author":"Wang","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref91","article-title":"Expertise-informed generative AI enables ultra-high data efficiency for building generalist medical foundation model","author":"Yan","year":"2024","journal-title":"PREPRINT (Version 1) Available at Res. Square"},{"key":"ref92","article-title":"Sam-Med2D","author":"Cheng","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3586694"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103370"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024"},{"key":"ref97","article-title":"NNFormer: Interleaved transformer for volumetric segmentation","author":"Zhou","year":"2021"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref101","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref103","article-title":"Foundation models for biomedical image segmentation: A survey","author":"Lee","year":"2024"},{"key":"ref104","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-0600-3"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01614-0"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40687-y"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"},{"key":"ref110","article-title":"Can SAM segment anything? when SAM meets camouflaged object detection","author":"Tang","year":"2023"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3881-x"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1385-0"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103061"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13111947"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00699"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref118","article-title":"One model to rule them all: Towards universal segmentation for medical images with text prompts","author":"Zhao","year":"2023"},{"key":"ref119","article-title":"OphGLM: Training an ophthalmology large language-and-vision assistant based on instructions and dialogue","author":"Gao","year":"2023"},{"key":"ref120","article-title":"Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement","author":"Li","year":"2024"},{"key":"ref121","first-page":"110","article-title":"SegVol: Universal and interactive volumetric medical image segmentation","volume":"37","author":"Du","year":"2025","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref122","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume":"225","author":"Moor","year":"2023","journal-title":"Mach. Learn. Health (ML4H)"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref125","article-title":"Large-scale domain-specific pretraining for biomedical vision-language processing","author":"Zhang","year":"2023"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref128","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref131","first-page":"2022","article-title":"GLM-130B: An open bilingual pre-trained model","author":"Zeng"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-020-0540-1"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2022-0282-ed"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2015-0493-ED"},{"key":"ref137","article-title":"Entity embeddings of categorical variables","author":"Guo","year":"2016"},{"key":"ref138","article-title":"Openclip","author":"Gabriel","year":"2021"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref143","first-page":"2022","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu"},{"key":"ref144","first-page":"2023","article-title":"Leveraging medical Twitter to build a visual\u2013language foundation model for pathology AI","author":"Huang","year":"2023","journal-title":"bioRxiv"},{"key":"ref145","volume-title":"The AI Revolution in Medicine: GPT-4 and Beyond","author":"Lee","year":"2023"},{"key":"ref146","article-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsr2214184"},{"key":"ref148","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref149","first-page":"2022","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","author":"Lu"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref151","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023"},{"key":"ref152","article-title":"BioMedGPT: A unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks","author":"Zhang","year":"2023"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2582"},{"issue":"1","key":"ref154","article-title":"PubMed: the bibliographic database","volume":"2","author":"Canese","year":"2013","journal-title":"The NCBI Handbook"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"ref157","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.6028\/nist.sp.500-324.qa-overview"},{"key":"ref159","article-title":"CORD-19: The COVID-19 open research dataset","author":"Wang","year":"2020","journal-title":"ArXiv"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.40895"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx238"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baw068"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.743"},{"key":"ref164","article-title":"Huatuo-26M, a large-scale Chinese medical QA dataset","author":"Li","year":"2023"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01718-3"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00715-8"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.107801"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16197"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12197"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98253-9"},{"issue":"5","key":"ref171","first-page":"2252","article-title":"Thyroid nodule segmentation and classification in ultrasound images","volume":"3","author":"Gireesha","year":"2014","journal-title":"Int. J. Eng. Res. Technol."},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1117\/12.2073532"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434087"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00946-3"},{"key":"ref175","article-title":"The RSNA-ASNR-Miccai Brats 2021 benchmark on brain tumor segmentation and radiogenomic classification","author":"Baid","year":"2021"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01401-7"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010287"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref180","article-title":"LAION-400M: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref181","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref182","article-title":"PMC-VQA: Visual instruction tuning for medical visual question answering","year":"2023"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref184","article-title":"LLAVA-Med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37477-x"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599819"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.11.004"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.gltp.2022.04.020"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102158"},{"key":"ref190","article-title":"Capabilities of Gemini models in medicine","author":"Saab","year":"2024"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-024-00271-8"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/ICDS50568.2020.9268742"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abi8017"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m1211"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07894-z"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1016\/j.apsb.2022.02.002"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/s11427-022-2239-y"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.2196\/46885"},{"key":"ref201","article-title":"Ai Hospital: Benchmarking large language models in a multi-agent medical interaction simulator","author":"Zhihao","year":"2024"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20771"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-021-00218-1"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1186\/s40779-021-00338-z"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.3390\/bios12080562"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-020-09477-5"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900119"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100005"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3077529"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05519-w"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00873-0"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11503071\/11202641.pdf?arnumber=11202641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:57:24Z","timestamp":1777665444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":213,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3618796","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}