{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:17:46Z","timestamp":1778167066964,"version":"3.51.4"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council (RGC) Collaborative Research Fund","doi-asserted-by":"publisher","award":["C5055-24G"],"award-info":[{"award-number":["C5055-24G"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Start-Up Fund of The Hong Kong Polytechnic University","award":["P0045999"],"award-info":[{"award-number":["P0045999"]}]},{"name":"Seed Fund of the Research Institute for Smart Ageing","award":["P0050946"],"award-info":[{"award-number":["P0050946"]}]},{"name":"Tsinghua-PolyU Joint Research Initiative Fund","award":["P0056509"],"award-info":[{"award-number":["P0056509"]}]},{"name":"PolyU UGC Funding","award":["P0053716"],"award-info":[{"award-number":["P0053716"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tmi.2025.3584841","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T13:39:06Z","timestamp":1751377146000},"page":"4945-4959","source":"Crossref","is-referenced-by-count":3,"title":["Medical Knowledge Intervention Prompt Tuning for Medical Image Classification"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3057-1862","authenticated-orcid":false,"given":"Ye","family":"Du","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5774-1591","authenticated-orcid":false,"given":"Nanxi","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1495-3278","authenticated-orcid":false,"given":"Shujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, the Research Institute for Smart Ageing, and the Research Institute for Artificial Intelligence of Things, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref3","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref4","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref5","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02887-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02959-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref16","first-page":"63908","article-title":"ReFT: Representation finetuning for language models","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref17","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"arXiv:2403.14608"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref19","first-page":"1","article-title":"Parameter-efficient fine-tuning for media: The missed opportunity","volume-title":"Proc. Med. Imag. with Deep Learn.","author":"Dutt"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02688"},{"key":"ref21","first-page":"1","article-title":"Consistency-guided prompt learning for vision-language models","volume-title":"Proc. ICLR","author":"Roy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref23","first-page":"1","article-title":"Cascade-CLIP: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref24","first-page":"1","article-title":"Less could be better: Parameter-efficient fine-tuning advances medical vision foundation models","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Lian"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref28","first-page":"8678","article-title":"HyperPrompt: Prompt-based task-conditioning of transformers","volume-title":"Proc. ICML","author":"He"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00164"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00098"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101985"},{"key":"ref39","first-page":"558","article-title":"DScGANS: Integrate domain knowledge in training dual-path semi-supervised conditional generative adversarial networks and S3 VM for ultrasonography thyroid nodules classification","volume-title":"Proc. MICCAI","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_72"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27853"},{"key":"ref42","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref43","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref44","volume-title":"Llama 3 Model Card","year":"2024"},{"key":"ref45","volume-title":"Chatgpt","year":"2023"},{"key":"ref46","article-title":"PaLM 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref47","volume-title":"Gpt-4 Technical Report","year":"2024"},{"key":"ref48","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref52","article-title":"Medical vision language pretraining: A survey","author":"Shrestha","year":"2023","journal-title":"arXiv:2312.06224"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01398"},{"key":"ref54","first-page":"1","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72117-5_6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_52"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01376"},{"key":"ref59","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023","journal-title":"arXiv:2307.12980"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"ref61","first-page":"9574","article-title":"Causal abstractions of neural networks","volume-title":"Proc. NeurIPS","author":"Geiger"},{"key":"ref62","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. ICML","author":"Kornblith"},{"key":"ref63","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref64","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Language Technol.","author":"Devlin"},{"key":"ref65","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NeurIPS","author":"Khosla"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2018.2824327"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.03368"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3172773"},{"key":"ref70","volume-title":"Aptos 2019 Blindness Detection","author":"Karthik","year":"2019"},{"key":"ref71","volume-title":"Ocular Disease Recognition","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-67076-5"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3083187.3083212"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s12553-021-00630-x"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"issue":"8","key":"ref77","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref79","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"},{"issue":"11","key":"ref80","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref81","volume-title":"Openbiollms: Advancing Open-source Large Language Models for Healthcare and Life Sciences","author":"Pal","year":"2024"},{"key":"ref82","volume-title":"Medllama3-v20","year":"2024"},{"key":"ref83","volume-title":"Open Medical-llm Leaderboard","year":"2025"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01160-9"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20220878"},{"key":"ref87","article-title":"Bias in large language models across clinical applications: A systematic review","author":"Suenghataiphorn","year":"2025","journal-title":"arXiv:2504.02917"},{"key":"ref88","first-page":"1","article-title":"Socio-demographic biases in medical decision-making by large language models: A large-scale multi-model analysis","volume":"2024","author":"Omar","year":"2024","journal-title":"MedRxiv"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3507831"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11279972\/11062464.pdf?arnumber=11062464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:40:33Z","timestamp":1765219233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11062464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":89,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3584841","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}