{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:00:16Z","timestamp":1783656016286,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001839","name":"University Grants Committee","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001839","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114114","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:44:50Z","timestamp":1780037090000},"page":"114114","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PB","title":["Clinically-informed prompt learning for explainable diagnosis with biomedical vision\u2013language models"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5787-8725","authenticated-orcid":false,"given":"Hao","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1271-4512","authenticated-orcid":false,"given":"Yucheng","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N.F.","family":"Law","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Ping","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai Ho","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakun","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114114_b1","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114114_b2","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.114114_b3","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"issue":"9","key":"10.1016\/j.patcog.2026.114114_b4","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114114_b5","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional prompt learning for vision-language models, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.patcog.2026.114114_b6","doi-asserted-by":"crossref","unstructured":"M.U. Khattak, S.T. Wasim, M. Naseer, S. Khan, M.-H. Yang, F.S. Khan, Self-regulating prompts: Foundational model adaptation without forgetting, in: IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15190\u201315200.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"10.1016\/j.patcog.2026.114114_b7","first-page":"4230","article-title":"Learning to prompt with text only supervision for vision-language models","volume":"vol. 39","author":"Khattak","year":"2025"},{"key":"10.1016\/j.patcog.2026.114114_b8","series-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114114_b9","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"525","article-title":"Pmc-clip: Contrastive language-image pre-training using biomedical documents","author":"Lin","year":"2023"},{"key":"10.1016\/j.patcog.2026.114114_b10","series-title":"Does clip benefit visual question answering in the medical domain as much as it does in the general domain?","author":"Eslami","year":"2021"},{"key":"10.1016\/j.patcog.2026.114114_b11","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"773","article-title":"Xcoop: Explainable prompt learning for computer-aided diagnosis via concept-guided context optimization","author":"Bie","year":"2024"},{"key":"10.1016\/j.patcog.2026.114114_b12","doi-asserted-by":"crossref","unstructured":"T. Koleilat, H. Asgariandehkordi, H. Rivaz, Y. Xiao, Biomedcoop: Learning to prompt for biomedical vision-language models, in: Computer Vision and Pattern Recognition Conference, 2025, pp. 14766\u201314776.","DOI":"10.1109\/CVPR52734.2025.01376"},{"key":"10.1016\/j.patcog.2026.114114_b13","unstructured":"S. Menon, C. Vondrick, Visual Classification via Description from Large Language Models, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.114114_b14","doi-asserted-by":"crossref","unstructured":"S. Pratt, I. Covert, R. Liu, A. Farhadi, What does a platypus look like? generating customized prompts for zero-shot image classification, in: IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15691\u201315701.","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"10.1016\/j.patcog.2026.114114_b15","article-title":"Image-free multi-label image recognition via LLM-powered hierarchical prompt tuning","author":"Yang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114114_b16","doi-asserted-by":"crossref","unstructured":"X. Tian, S. Zou, Z. Yang, J. Zhang, Argue: Attribute-guided prompt tuning for vision-language models, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28578\u201328587.","DOI":"10.1109\/CVPR52733.2024.02700"},{"key":"10.1016\/j.patcog.2026.114114_b17","doi-asserted-by":"crossref","unstructured":"Z. Li, Y. Song, M.-M. Cheng, X. Li, J. Yang, Advancing textual prompt learning with anchored attributes, in: IEEE\/CVF International Conference on Computer Vision, 2025, pp. 3618\u20133627.","DOI":"10.1109\/ICCV51701.2025.00345"},{"key":"10.1016\/j.patcog.2026.114114_b18","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114114_b19","series-title":"Clip in medical imaging: A comprehensive survey","author":"Zhao","year":"2023"},{"key":"10.1016\/j.patcog.2026.114114_b20","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Wu, D. Agarwal, J. Sun, Medclip: Contrastive learning from unpaired medical images and text, in: Conference on Empirical Methods in Natural Language Processing, 2022, p. 3876.","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"10.1016\/j.patcog.2026.114114_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110250","article-title":"Exploring low-resource medical image classification with weakly supervised prompt learning","volume":"149","author":"Zheng","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114114_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111768","article-title":"GraphMamba: Whole slide image classification meets graph-driven selective state space model","volume":"167","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114114_b23","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2025.3557245","article-title":"Revisiting one-stage deep uncalibrated photometric stereo via fourier embedding","author":"Ju","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114114_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102649","article-title":"SA2net: Scale-adaptive structure-affinity transformation for spine segmentation from ultrasound volume projection imaging","author":"Xie","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.patcog.2026.114114_b25","series-title":"2023 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"1567","article-title":"A structure-affinity dual attention-based network to segment spine for scoliosis assessment","author":"Xie","year":"2023"},{"key":"10.1016\/j.patcog.2026.114114_b26","unstructured":"G. Chen, W. Yao, X. Song, X. Li, Y. Rao, K. Zhang, PLOT: Prompt Learning with Optimal Transport for Vision-Language Models, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.114114_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111359","article-title":"Context-aware prompt learning for test-time vision recognition with frozen vision-language model","volume":"162","author":"Yin","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114114_b28","article-title":"MKGPL: graph prompt learning with multi-view knowledge for few-shot recognition","author":"Xie","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114114_b29","doi-asserted-by":"crossref","unstructured":"H. Yao, R. Zhang, C. Xu, Visual-language prompt tuning with knowledge-guided context optimization, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6757\u20136767.","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"10.1016\/j.patcog.2026.114114_b30","doi-asserted-by":"crossref","unstructured":"B. Zhu, Y. Niu, Y. Han, Y. Wu, H. Zhang, Prompt-aligned gradient for prompt tuning, in: IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15659\u201315669.","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"10.1016\/j.patcog.2026.114114_b31","doi-asserted-by":"crossref","unstructured":"G. Kim, S. Kim, S. Lee, AAPL: Adding Attributes to Prompt Learning for Vision-Language Models, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, 2024, pp. 1572\u20131582.","DOI":"10.1109\/CVPRW63382.2024.00164"},{"key":"10.1016\/j.patcog.2026.114114_b32","unstructured":"T. Ding, W. Li, Z. Miao, H. Pfister, Tree of Attributes Prompt Learning for Vision-Language Models, in: International Conference on Learning Representations, 2025."},{"key":"10.1016\/j.patcog.2026.114114_b33","first-page":"1","article-title":"Deep blind super-resolution for satellite video","volume":"61","author":"Xiao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"11","key":"10.1016\/j.patcog.2026.114114_b34","doi-asserted-by":"crossref","first-page":"2253","DOI":"10.1109\/JAS.2024.124521","article-title":"Image enhancement via associated perturbation removal and texture reconstruction learning","volume":"11","author":"Jiang","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.patcog.2026.114114_b35","series-title":"Openai GPT-5 system card","author":"Singh","year":"2025"},{"key":"10.1016\/j.patcog.2026.114114_b36","series-title":"Brain tumor MRI dataset","author":"Nickparvar","year":"2021"},{"key":"10.1016\/j.patcog.2026.114114_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"issue":"1","key":"10.1016\/j.patcog.2026.114114_b38","doi-asserted-by":"crossref","first-page":"11440","DOI":"10.1038\/s41598-022-15634-4","article-title":"Vision transformer and explainable transfer learning models for auto detection of kidney cyst, stone and tumor from CT-radiography","volume":"12","author":"Islam","year":"2022","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.patcog.2026.114114_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.patcog.2026.114114_b40","doi-asserted-by":"crossref","unstructured":"K. Pogorelov, K.R. Randel, C. Griwodz, S.L. Eskeland, T. de Lange, D. Johansen, C. Spampinato, D.-T. Dang-Nguyen, M. Lux, P.T. Schmidt, et al., Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection, in: ACM on Multimedia Systems Conference, 2017, pp. 164\u2013169.","DOI":"10.1145\/3083187.3083212"},{"issue":"5","key":"10.1016\/j.patcog.2026.114114_b41","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"issue":"3","key":"10.1016\/j.patcog.2026.114114_b42","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3390\/data3030025","article-title":"Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research","volume":"3","author":"Porwal","year":"2018","journal-title":"Data"},{"issue":"1","key":"10.1016\/j.patcog.2026.114114_b43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep27988","article-title":"Multi-class texture analysis in colorectal cancer histology","volume":"6","author":"Kather","year":"2016","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patcog.2026.114114_b44","series-title":"Lung and colon cancer histopathological image dataset (lc25000)","author":"Borkowski","year":"2019"},{"key":"10.1016\/j.patcog.2026.114114_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.105002","article-title":"COVID-19 infection localization and severity grading from chest X-ray images","volume":"139","author":"Tahir","year":"2021","journal-title":"Comput. Biol. Med."},{"issue":"10.17632","key":"10.1016\/j.patcog.2026.114114_b46","article-title":"Knee osteoarthritis severity grading dataset","volume":"1","author":"Chen","year":"2018","journal-title":"Mendeley Data"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010794?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010794?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:24:38Z","timestamp":1783056278000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326010794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":46,"alternative-id":["S0031320326010794"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114114","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Clinically-informed prompt learning for explainable diagnosis with biomedical vision\u2013language models","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114114","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114114"}}