{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T07:22:55Z","timestamp":1777879375478,"version":"3.51.4"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.bspc.2026.110337","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:10:26Z","timestamp":1776669026000},"page":"110337","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Attribute-driven prompt learning with vision\u2013language models for few-shot gastrointestinal disease classification"],"prefix":"10.1016","volume":"121","author":[{"given":"Weiheng","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4602-8450","authenticated-orcid":false,"given":"Suigu","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Huazhu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chak Fong","family":"Cheang","sequence":"additional","affiliation":[]},{"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Xiaofang","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Nong","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.bspc.2026.110337_b1","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: Cancer J. Clin."},{"issue":"2","key":"10.1016\/j.bspc.2026.110337_b2","first-page":"133","article-title":"Artificial intelligence in gastrointestinal endoscopy: a comprehensive review","volume":"37","author":"Ali","year":"2024","journal-title":"Ann. Gastroenterol."},{"key":"10.1016\/j.bspc.2026.110337_b3","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3483432","article-title":"AI in endoscopic gastrointestinal diagnosis: A systematic review of deep learning and machine learning techniques","author":"Lewis","year":"2024","journal-title":"IEEE Access"},{"issue":"12","key":"10.1016\/j.bspc.2026.110337_b4","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.3390\/diagnostics11122183","article-title":"Impact of image resolution on deep learning performance in endoscopy image classification: An experimental study using a large dataset of endoscopic images","volume":"11","author":"Thambawita","year":"2021","journal-title":"Diagnostics"},{"issue":"6","key":"10.1016\/j.bspc.2026.110337_b5","doi-asserted-by":"crossref","first-page":"3176","DOI":"10.3390\/s23063176","article-title":"Endoscopic image classification based on explainable deep learning","volume":"23","author":"Mukhtorov","year":"2023","journal-title":"Sensors"},{"issue":"7","key":"10.1016\/j.bspc.2026.110337_b6","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.3390\/electronics12071557","article-title":"Efficient gastrointestinal disease classification using pretrained deep convolutional neural network","volume":"12","author":"Nouman Noor","year":"2023","journal-title":"Electronics"},{"key":"10.1016\/j.bspc.2026.110337_b7","doi-asserted-by":"crossref","DOI":"10.1049\/cit2.12231","article-title":"GastroNet: A robust attention-based deep learning and cosine similarity feature selection framework for gastrointestinal disease classification from endoscopic images","author":"Noor","year":"2023","journal-title":"CAAI Trans. Intell. Technol."},{"issue":"9","key":"10.1016\/j.bspc.2026.110337_b8","doi-asserted-by":"crossref","first-page":"4452","DOI":"10.1109\/TCSVT.2023.3277462","article-title":"Vision transformer with hybrid shifted windows for gastrointestinal endoscopy image classification","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.bspc.2026.110337_b9","series-title":"Endoscopy classification model using swin transformer and saliency map","author":"Sobhaninia","year":"2023"},{"key":"10.1016\/j.bspc.2026.110337_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105534","article-title":"HiFuse: Hierarchical multi-scale feature fusion network for medical image classification","volume":"87","author":"Huo","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"issue":"12","key":"10.1016\/j.bspc.2026.110337_b11","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.3390\/bioengineering10121416","article-title":"High-speed and accurate diagnosis of gastrointestinal disease: learning on endoscopy images using lightweight transformer with local feature attention","volume":"10","author":"Wu","year":"2023","journal-title":"Bioengineering"},{"key":"10.1016\/j.bspc.2026.110337_b12","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.bspc.2026.110337_b13","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"},{"key":"10.1016\/j.bspc.2026.110337_b14","series-title":"Medical image understanding with pretrained vision language models: A comprehensive study","author":"Qin","year":"2022"},{"issue":"9","key":"10.1016\/j.bspc.2026.110337_b15","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.bspc.2026.110337_b16","series-title":"Machine Learning for Healthcare Conference","first-page":"532","article-title":"Few-shot learning for dermatological disease diagnosis","author":"Prabhu","year":"2019"},{"key":"10.1016\/j.bspc.2026.110337_b17","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s11517-021-02321-1","article-title":"Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification","volume":"59","author":"Yoo","year":"2021","journal-title":"Med. Biol. Eng. Comput."},{"issue":"18","key":"10.1016\/j.bspc.2026.110337_b18","doi-asserted-by":"crossref","first-page":"55731","DOI":"10.1007\/s11042-023-17691-x","article-title":"Enhancing rare retinal disease classification: a few-shot meta-learning framework utilizing fundus images","volume":"83","author":"Rajpoot","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.bspc.2026.110337_b19","series-title":"2023 International Conference on Machine Learning and Applications","first-page":"2141","article-title":"Few-shot image classification for rare ocular disease with an ensemble of pretrained feature extractors and a statistical classifier","author":"Zorek","year":"2023"},{"key":"10.1016\/j.bspc.2026.110337_b20","article-title":"Enhancing early Alzheimer\u2019s disease detection through big data and ensemble few-shot learning","author":"Atitallah","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.bspc.2026.110337_b21","doi-asserted-by":"crossref","DOI":"10.1109\/JBHI.2024.3386197","article-title":"Dual-channel prototype network for few-shot pathology image classification","author":"Quan","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"4","key":"10.1016\/j.bspc.2026.110337_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e26559","article-title":"Few-shot learning for the classification of intestinal tuberculosis and Crohn\u2019s disease on endoscopic images: A novel learn-to-learn framework","volume":"10","author":"Lin","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.bspc.2026.110337_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106387","article-title":"Few-shot learning with task adaptation for multi-category gastrointestinal endoscopy classification","volume":"95","author":"Jin","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110337_b24","series-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"issue":"2","key":"10.1016\/j.bspc.2026.110337_b25","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.bspc.2026.110337_b26","series-title":"International Conference on Machine Learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.bspc.2026.110337_b27","series-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.bspc.2026.110337_b28","series-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","author":"Lialin","year":"2023"},{"key":"10.1016\/j.bspc.2026.110337_b29","series-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021"},{"issue":"2","key":"10.1016\/j.bspc.2026.110337_b30","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"Clip-adapter: Better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.bspc.2026.110337_b31","series-title":"European Conference on Computer Vision","first-page":"493","article-title":"Tip-adapter: Training-free adaption of clip for few-shot classification","author":"Zhang","year":"2022"},{"key":"10.1016\/j.bspc.2026.110337_b32","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional prompt learning for vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.bspc.2026.110337_b33","doi-asserted-by":"crossref","unstructured":"M.U. Khattak, H. Rasheed, M. Maaz, S. Khan, F.S. Khan, Maple: Multi-modal prompt learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19113\u201319122.","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"10.1016\/j.bspc.2026.110337_b34","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15190\u201315200.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"10.1016\/j.bspc.2026.110337_b35","series-title":"Prompt learning with optimal transport for vision-language models","author":"Chen","year":"2022"},{"key":"10.1016\/j.bspc.2026.110337_b36","doi-asserted-by":"crossref","unstructured":"M. Zanella, I. Ben Ayed, Low-rank few-shot adaptation of vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1593\u20131603.","DOI":"10.1109\/CVPRW63382.2024.00166"},{"issue":"1","key":"10.1016\/j.bspc.2026.110337_b37","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2400640","article-title":"A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs","volume":"2","author":"Zhang","year":"2025","journal-title":"NEJM AI"},{"key":"10.1016\/j.bspc.2026.110337_b38","series-title":"ConceptCLIP: Towards trustworthy medical AI via concept-enhanced contrastive langauge-image pre-training","author":"Nie","year":"2025"},{"key":"10.1016\/j.bspc.2026.110337_b39","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"306","article-title":"Hecvl: Hierarchical video-language pretraining for zero-shot surgical phase recognition","author":"Yuan","year":"2024"},{"key":"10.1016\/j.bspc.2026.110337_b40","first-page":"122952","article-title":"Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation","volume":"37","author":"Yuan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110337_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103644","article-title":"Learning multi-modal representations by watching hundreds of surgical video lectures","author":"Yuan","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110337_b42","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"issue":"140","key":"10.1016\/j.bspc.2026.110337_b43","first-page":"1","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":"10.1016\/j.bspc.2026.110337_b44","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110337_b45","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110337_b46","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.bspc.2026.110337_b47","article-title":"Neural prompt search","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.bspc.2026.110337_b48","series-title":"European Conference on Computer Vision","first-page":"264","article-title":"Gallop: Learning global and local prompts for vision-language models","author":"Lafon","year":"2024"},{"key":"10.1016\/j.bspc.2026.110337_b49","doi-asserted-by":"crossref","unstructured":"H. Yao, R. Zhang, C. Xu, Tcp: Textual-based class-aware prompt tuning for visual-language model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23438\u201323448.","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"10.1016\/j.bspc.2026.110337_b50","series-title":"Visual classification via description from large language models","author":"Menon","year":"2022"},{"key":"10.1016\/j.bspc.2026.110337_b51","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"225","article-title":"Concept bottleneck with visual concept filtering for explainable medical image classification","author":"Kim","year":"2023"},{"key":"10.1016\/j.bspc.2026.110337_b52","series-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","author":"Yang","year":"2023"},{"key":"10.1016\/j.bspc.2026.110337_b53","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: Proceedings of the 8th ACM on Multimedia Systems Conference, 2017, pp. 164\u2013169.","DOI":"10.1145\/3083187.3083212"},{"issue":"1","key":"10.1016\/j.bspc.2026.110337_b54","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1038\/s41597-020-00622-y","article-title":"HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy","volume":"7","author":"Borgli","year":"2020","journal-title":"Sci. Data"},{"key":"10.1016\/j.bspc.2026.110337_b55","doi-asserted-by":"crossref","unstructured":"K. Pogorelov, K.R. Randel, T. de Lange, S.L. Eskeland, C. Griwodz, D. Johansen, C. Spampinato, M. Taschwer, M. Lux, P.T. Schmidt, et al., Nerthus: A bowel preparation quality video dataset, in: Proceedings of the 8th ACM on Multimedia Systems Conference, 2017, pp. 170\u2013174.","DOI":"10.1145\/3083187.3083216"},{"key":"10.1016\/j.bspc.2026.110337_b56","series-title":"Labeled images for ulcerative colitis (limuc) dataset","author":"Polat","year":"2022"},{"key":"10.1016\/j.bspc.2026.110337_b57","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.bspc.2026.110337_b58","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.bspc.2026.110337_b59","series-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"10.1016\/j.bspc.2026.110337_b60","series-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"issue":"11","key":"10.1016\/j.bspc.2026.110337_b61","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426008918?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426008918?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:41:56Z","timestamp":1777592516000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426008918"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":61,"alternative-id":["S1746809426008918"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110337","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Attribute-driven prompt learning with vision\u2013language models for few-shot gastrointestinal disease classification","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110337","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":"110337"}}