{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:05:02Z","timestamp":1784243102638,"version":"3.55.0"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.media.2026.104193","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T23:05:32Z","timestamp":1782601532000},"page":"104193","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MedP-CLIP: Medical CLIP with region-aware prompt integration"],"prefix":"10.1016","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1012-2414","authenticated-orcid":false,"given":"Jiahui","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4212-5023","authenticated-orcid":false,"given":"He","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3377-469X","authenticated-orcid":false,"given":"Yanzhou","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6131-8449","authenticated-orcid":false,"given":"Sibo","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongchun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lincheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6849-9093","authenticated-orcid":false,"given":"Junlong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.media.2026.104193_b1","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241613","article-title":"Totalsegmentator mri: Robust sequence-independent segmentation of multiple anatomic structures in mri","volume":"314","author":"Akinci D\u2019Antonoli","year":"2025","journal-title":"Radiology"},{"issue":"11","key":"10.1016\/j.media.2026.104193_b2","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002699","article-title":"Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet","volume":"15","author":"Bien","year":"2018","journal-title":"PLoS Med."},{"key":"10.1016\/j.media.2026.104193_b3","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.media.2026.104193_b4","series-title":"Monai: An open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022"},{"key":"10.1016\/j.media.2026.104193_b5","doi-asserted-by":"crossref","unstructured":"Chen, X., Lai, Z., Ruan, K., Chen, S., Liu, J., Liu, Z., 2025. R-llava: Improving med-vqa understanding through visual region of interest. In: ICLR 2025 Workshop on Human-AI Coevolution.","DOI":"10.1109\/IJCNN64981.2025.11227685"},{"key":"10.1016\/j.media.2026.104193_b6","doi-asserted-by":"crossref","unstructured":"Cheng, J., Fu, B., Ye, J., Wang, G., Li, T., Wang, H., Li, R., Yao, H., Cheng, J., Li, J., et al., 2025. Interactive medical image segmentation: A benchmark dataset and baseline. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 20841\u201320851.","DOI":"10.1109\/CVPR52734.2025.01941"},{"key":"10.1016\/j.media.2026.104193_b7","series-title":"Sam-med2d","author":"Cheng","year":"2023"},{"key":"10.1016\/j.media.2026.104193_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113538","article-title":"Abnormal-region-aware multi-modal feature fusion for medical report generation","volume":"318","author":"Gao","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.media.2026.104193_b9","series-title":"International Conference on Learning Representations","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"issue":"1","key":"10.1016\/j.media.2026.104193_b10","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1038\/s41597-022-01875-5","article-title":"ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset","volume":"9","author":"Hernandez Petzsche","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104193_b11","article-title":"Multi-view masked contrastive representation learning for endoscopic video analysis","author":"Hu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104193_b12","first-page":"3779","article-title":"Towards a multimodal large language model with pixel-level insight for biomedicine","volume":"vol. 39, no. 4","author":"Huang","year":"2025"},{"key":"10.1016\/j.media.2026.104193_b13","series-title":"Medicalnarratives: Connecting medical vision and language with localized narratives","author":"Ikezogwo","year":"2025"},{"key":"10.1016\/j.media.2026.104193_b14","doi-asserted-by":"crossref","first-page":"36722","DOI":"10.52202\/068431-2661","article-title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104193_b15","series-title":"Unimed-clip: Towards a unified image-text pretraining paradigm for diverse medical imaging modalities","author":"Khattak","year":"2024"},{"key":"10.1016\/j.media.2026.104193_b16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al., 2023. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.media.2026.104193_b17","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., Jia, J., 2024. Lisa: Reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9579\u20139589.","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"10.1016\/j.media.2026.104193_b18","doi-asserted-by":"crossref","unstructured":"Lai, H., Yao, Q., Jiang, Z., Wang, R., He, Z., Tao, X., Zhou, S.K., 2024. Carzero: Cross-attention alignment for radiology zero-shot classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11137\u201311146.","DOI":"10.1109\/CVPR52733.2024.01059"},{"key":"10.1016\/j.media.2026.104193_b19","series-title":"2020 Tenth International Conference on Image Processing Theory, Tools and Applications","first-page":"1","article-title":"Segthor: Segmentation of thoracic organs at risk in ct images","author":"Lambert","year":"2020"},{"key":"10.1016\/j.media.2026.104193_b20","series-title":"Understanding pure clip guidance for voxel grid nerf models","author":"Lee","year":"2022"},{"key":"10.1016\/j.media.2026.104193_b21","doi-asserted-by":"crossref","first-page":"30146","DOI":"10.52202\/075280-1312","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104193_b22","series-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"vol. 202","author":"Li","year":"2023"},{"key":"10.1016\/j.media.2026.104193_b23","doi-asserted-by":"crossref","first-page":"28541","DOI":"10.52202\/075280-1240","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104193_b24","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"80","article-title":"Anatomical structure-guided medical vision-language pre-training","author":"Li","year":"2024"},{"key":"10.1016\/j.media.2026.104193_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2026.109585","article-title":"CDCLIP: An interpretable zero-shot medical image classification framework based on concept decomposition","volume":"116","author":"Li","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.media.2026.104193_b26","doi-asserted-by":"crossref","unstructured":"Liang, F., Wu, B., Dai, X., Li, K., Zhao, Y., Zhang, H., Zhang, P., Vajda, P., Marculescu, D., 2023. Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7061\u20137070.","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"10.1016\/j.media.2026.104193_b27","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.media.2026.104193_b28","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104193_b29","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.media.2026.104193_b30","doi-asserted-by":"crossref","unstructured":"Lozano, A., Sun, M.W., Burgess, J., Chen, L., Nirschl, J.J., Gu, J., Lopez, I., Aklilu, J., Rau, A., Katzer, A.W., et al., 2025. Biomedica: An open biomedical image-caption archive, dataset, and vision-language models derived from scientific literature. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 19724\u201319735.","DOI":"10.1109\/CVPR52734.2025.01837"},{"issue":"9","key":"10.1016\/j.media.2026.104193_b31","doi-asserted-by":"crossref","first-page":"157","DOI":"10.4236\/jbise.2024.179012","article-title":"Performance comparison of vision transformer-and CNN-based image classification using cross entropy: A preliminary application to lung cancer discrimination from CT images","volume":"17","author":"Matsuyama","year":"2024","journal-title":"J. Biomed. Sci. Eng."},{"key":"10.1016\/j.media.2026.104193_b32","series-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022"},{"key":"10.1016\/j.media.2026.104193_b33","series-title":"2021 13th International Conference on Electronics, Computers and Artificial Intelligence","first-page":"1","article-title":"Deep learning & digital fundus images: Glaucoma detection using DenseNet","author":"Ovreiu","year":"2021"},{"key":"10.1016\/j.media.2026.104193_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2026.103982","article-title":"Surglavi: Large-scale hierarchical dataset for surgical vision\u2013language representation learning","author":"Perez","year":"2026","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104193_b35","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.media.2026.104193_b36","series-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.media.2026.104193_b37","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A., 2023. What does clip know about a red circle? visual prompt engineering for vlms. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 11987\u201311997.","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"10.1016\/j.media.2026.104193_b38","series-title":"3D image reconstruction for comparison of algorithm database","author":"Soler","year":"2010"},{"key":"10.1016\/j.media.2026.104193_b39","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Merrill, W., Darrell, T., Gardner, M., Singh, S., Rohrbach, A., 2022. ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 5198\u20135215.","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"10.1016\/j.media.2026.104193_b40","doi-asserted-by":"crossref","unstructured":"Sun, Z., Fang, Y., Wu, T., Zhang, P., Zang, Y., Kong, S., Xiong, Y., Lin, D., Wang, J., 2024. Alpha-clip: A clip model focusing on wherever you want. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13019\u201313029.","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"10.1016\/j.media.2026.104193_b41","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3446190","article-title":"Brain tumor detection based on deep features concatenation and machine learning classifiers with genetic selection","author":"Wageh","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.media.2026.104193_b42","series-title":"Unifying biomedical vision-language expertise: Towards a generalist foundation model via multi-clip knowledge distillation","author":"Wang","year":"2025"},{"key":"10.1016\/j.media.2026.104193_b43","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Interpretable bilingual multimodal large language model for diverse biomedical tasks","author":"Wang","year":"2025"},{"key":"10.1016\/j.media.2026.104193_b44","first-page":"3876","article-title":"Medclip: Contrastive learning from unpaired medical images and text","volume":"vol. 2022","author":"Wang","year":"2022"},{"issue":"5","key":"10.1016\/j.media.2026.104193_b45","article-title":"TotalSegmentator: robust segmentation of 104 anatomic structures in CT images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol.: Artif. Intell."},{"key":"10.1016\/j.media.2026.104193_b46","first-page":"26992","article-title":"Federated CLIP for resource-efficient heterogeneous medical image classification","volume":"vol. 40, no. 32","author":"Wu","year":"2026"},{"key":"10.1016\/j.media.2026.104193_b47","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"763","article-title":"Vertfound: synergizing semantic and spatial understanding for fine-grained vertebrae classification via foundation models","author":"Wu","year":"2024"},{"key":"10.1016\/j.media.2026.104193_b48","series-title":"Describe anything in medical images","author":"Xiao","year":"2025"},{"key":"10.1016\/j.media.2026.104193_b49","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De Mello, S., 2023. Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2955\u20132966.","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"10.1016\/j.media.2026.104193_b50","series-title":"Covid-ct-dataset: a ct scan dataset about covid-19","author":"Yang","year":"2020"},{"key":"10.1016\/j.media.2026.104193_b51","article-title":"CLIP-guided generative network for pathology nuclei image augmentation","author":"Zhang","year":"2025","journal-title":"Med. Image Anal."},{"issue":"1","key":"10.1016\/j.media.2026.104193_b52","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.media.2026.104193_b53","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L.H., Zhou, L., Dai, X., Yuan, L., Li, Y., et al., 2022. Regionclip: Region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16793\u201316803.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"10.1016\/j.media.2026.104193_b54","series-title":"European Conference on Computer Vision","first-page":"696","article-title":"Extract free dense labels from clip","author":"Zhou","year":"2022"},{"key":"10.1016\/j.media.2026.104193_b55","article-title":"Medsam-u: uncertainty-guided auto multi-prompt adaptation for reliable medsam","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.media.2026.104193_b56","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2025.3596878","article-title":"Uncertainty-aware medical diagnostic phrase identification and grounding","author":"Zou","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.media.2026.104193_b57","article-title":"Agentic artificial intelligence in eye care: is clinical autonomy finally within reach?","volume":"8","author":"Zou","year":"2026","journal-title":"Lancet Digit. Health"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002628?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002628?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:08:36Z","timestamp":1784239716000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526002628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":57,"alternative-id":["S1361841526002628"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104193","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MedP-CLIP: Medical CLIP with region-aware prompt integration","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104193","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104193"}}