{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:25:55Z","timestamp":1773926755392,"version":"3.50.1"},"reference-count":78,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Committee","doi-asserted-by":"publisher","award":["RCYX20210609103056042"],"award-info":[{"award-number":["RCYX20210609103056042"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["G030230001"],"award-info":[{"award-number":["G030230001"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["G03034K003"],"award-info":[{"award-number":["G03034K003"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024B1515020088"],"award-info":[{"award-number":["2024B1515020088"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515220131"],"award-info":[{"award-number":["2021A1515220131"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2023YFC2415400"],"award-info":[{"award-number":["2023YFC2415400"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2422012"],"award-info":[{"award-number":["T2422012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071210"],"award-info":[{"award-number":["62071210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007162","name":"Guangdong Provincial Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008100","name":"Southern University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008100","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.media.2025.103912","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:13:05Z","timestamp":1765354385000},"page":"103912","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MIRAGE: Medical image-text pre-training for robustness against noisy environments"],"prefix":"10.1016","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4844-5146","authenticated-orcid":false,"given":"Pujin","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0988-0134","authenticated-orcid":false,"given":"Yijin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9789-0825","authenticated-orcid":false,"given":"Li","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5744-5201","authenticated-orcid":false,"given":"Junyan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3668-3539","authenticated-orcid":false,"given":"Kenneth Kin-Yip","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7549-6560","authenticated-orcid":false,"given":"Xiaoying","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2025.103912_bib0001","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0002","series-title":"Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization","first-page":"65","article-title":"Meteor: an automatic metric for mt evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.media.2025.103912_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14172","article-title":"Fff: fixing flawed foundations in contrastive pre-training results in very strong vision-language models","author":"Bulat","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0004","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27314","article-title":"Mafa: managing false negatives for vision-language pre-training","author":"Byun","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0005","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6299","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.media.2025.103912_bib0006","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"7346","article-title":"Towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0007","unstructured":"Chen, T.-S., Hung, W.-C., Tseng, H.-Y., Chien, S.-Y., Yang, M.-H., 2021. Incremental false negative detection for contrastive learning. arXiv preprint arXiv:2106.03719."},{"key":"10.1016\/j.media.2025.103912_bib0008","unstructured":"Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C. L., 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325."},{"key":"10.1016\/j.media.2025.103912_bib0009","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z., Gu, L., Wang, X., Li, Q., Ren, Y., Chen, Z., Luo, J., Wang, J., Jiang, T., Wang, B.,... Wang, W., 2024b. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271."},{"key":"10.1016\/j.media.2025.103912_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24185","article-title":"InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0011","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21361","article-title":"Prior: prototype representation joint learning from medical images and reports","author":"Cheng","year":"2023"},{"key":"10.1016\/j.media.2025.103912_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16670","article-title":"Robust contrastive learning against noisy views","author":"Chuang","year":"2022"},{"issue":"2","key":"10.1016\/j.media.2025.103912_bib0013","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Demner-Fushman","year":"2016","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"10.1016\/j.media.2025.103912_bib0015","unstructured":"Dernoncourt, F., Lee, J. Y., 2017. Pubmed 200k rct: a dataset for sequential sentence classification in medical abstracts. arXiv preprint arXiv:1710.06071."},{"key":"10.1016\/j.media.2025.103912_bib0016","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N., 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy."},{"key":"10.1016\/j.media.2025.103912_bib0017","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9588","article-title":"With a little help from my friends: nearest-neighbor contrastive learning of visual representations","author":"Dwibedi","year":"2021"},{"key":"10.1016\/j.media.2025.103912_bib0018","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Data filtering networks","author":"Fang","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0019","unstructured":"Gutman, D., Codella, N. C. F., Celebi, E., Helba, B., Marchetti, M., Mishra, N., Halpern, A., 2016. Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1605.01397."},{"key":"10.1016\/j.media.2025.103912_bib0020","series-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","first-page":"547","article-title":"Identifying implicit social biases in vision-language models","volume":"Vol. 7","author":"Hamidieh","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.media.2025.103912_bib0022","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.media.2025.103912_bib0023","series-title":"European Conference on Computer Vision","first-page":"289","article-title":"Rotary position embedding for vision transformer","author":"Heo","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0024","series-title":"SIGIR\u201994: Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, Organised by Dublin City University","first-page":"192","article-title":"Ohsumed: an interactive retrieval evaluation and new large test collection for research","author":"Hersh","year":"1994"},{"key":"10.1016\/j.media.2025.103912_bib0025","article-title":"Noise-robust vision-language pre-training with positive-negative learning","author":"Huang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2025.103912_bib0026","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"590","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"Vol. 33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.media.2025.103912_bib0027","unstructured":"Jang, E., Gu, S., Poole, B., 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144."},{"key":"10.1016\/j.media.2025.103912_bib0028","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":"1","key":"10.1016\/j.media.2025.103912_bib0029","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/s41597-022-01564-3","article-title":"Fives: a fundus image dataset for artificial intelligence based vessel segmentation","volume":"9","author":"Jin","year":"2022","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.media.2025.103912_bib0030","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2025.103912_bib0031","series-title":"Proceedings of the 13Th International Workshop on Health Text Mining and Information Analysis (LOUHI)","first-page":"81","article-title":"BiosimCSE: biomedical sentence embeddings using contrastive learning","author":"Kanakarajan","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0032","unstructured":"Kitamura, F., 2018. Head CT hemorrhage [dataset]. https:\/\/www.kaggle.com\/datasets\/felipekitamura\/head-ct-hemorrhage."},{"key":"10.1016\/j.media.2025.103912_bib0033","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0034","article-title":"Llava-med: training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0035","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.media.2025.103912_bib0036","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.media.2025.103912_bib0037","first-page":"9694","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103092","article-title":"Octa-500: a retinal dataset for optical coherence tomography angiography study","volume":"93","author":"Li","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103912_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23390","article-title":"Scaling language-image pre-training via masking","author":"Li","year":"2023"},{"key":"10.1016\/j.media.2025.103912_bib0040","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.media.2025.103912_bib0041","article-title":"FedLPPA: learning personalized prompt and aggregation for federated weakly-supervised medical image segmentation","author":"Lin","year":"2024","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2025.103912_bib0042","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.2025.103912_bib0043","series-title":"2021IEEE 18Th International Symposium on Biomedical Imaging (ISBI)","first-page":"1650","article-title":"Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering","author":"Liu","year":"2021"},{"key":"10.1016\/j.media.2025.103912_bib0044","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.media.2025.103912_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"issue":"3","key":"10.1016\/j.media.2025.103912_bib0046","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat. Med."},{"issue":"12","key":"10.1016\/j.media.2025.103912_bib0047","doi-asserted-by":"crossref","first-page":"3699","DOI":"10.1109\/TMI.2022.3193146","article-title":"Aadg: automatic augmentation for domain generalization on retinal image segmentation","volume":"41","author":"Lyu","year":"2022","journal-title":"IEEE Trans. Med. Imag."},{"issue":"12","key":"10.1016\/j.media.2025.103912_bib0048","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1162\/jocn.2009.21407","article-title":"Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults","volume":"22","author":"Marcus","year":"2010","journal-title":"J. Cogn. Neurosci."},{"issue":"3","key":"10.1016\/j.media.2025.103912_bib0049","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem. Med. (Zagreb)"},{"key":"10.1016\/j.media.2025.103912_bib0050","article-title":"Qu-brats: miccai brats 2020 challenge on quantifying uncertainty in brain tumor segmentation-analysis of ranking scores and benchmarking results","volume":"2022","author":"Mehta","year":"2022","journal-title":"J. Mach. Learn. Biomed. Imag."},{"key":"10.1016\/j.media.2025.103912_bib0051","series-title":"European Conference on Computer Vision","first-page":"529","article-title":"Slip: self-supervision meets language-image pre-training","author":"Mu","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0052","unstructured":"Naren, O. S., 2021. Retinal OCT image classification - c8 [dataset]. https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/2736749."},{"key":"10.1016\/j.media.2025.103912_bib0053","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19275","article-title":"Fine-grained image-text matching by cross-modal hard aligning network","author":"Pan","year":"2023"},{"key":"10.1016\/j.media.2025.103912_bib0054","series-title":"Proceedings of the 40Th Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.media.2025.103912_bib0055","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.2025.103912_bib0056","unstructured":"Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., Yang, B., Zhu, K., Laird, D., Ball, R. L., Langlotz, C., Shpanskaya, K., Lungren, M. P., Ng, A. Y., 2017. Mura: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957."},{"key":"10.1016\/j.media.2025.103912_bib0057","unstructured":"Ren, S., Wu, Z., Zhu, K. Q., 2023. Emo: Earth mover distance optimization for auto-regressive language modeling. arXiv preprint arXiv:2310.04691."},{"key":"10.1016\/j.media.2025.103912_bib0058","series-title":"Medical Imaging with Deep Learning","article-title":"Multimedeval: a benchmark and a toolkit for evaluating medical vision-language models","author":"Royer","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2025.103912_bib0059","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1038\/s41597-024-03496-6","article-title":"Rocov2: radiology objects in context version 2, an updated multimodal image dataset","volume":"11","author":"R\u00fcckert","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2025.103912_bib0060","series-title":"Proceedings of the 2022 6Th International Conference on Natural Language Processing and Information Retrieval","first-page":"6","article-title":"Evaluating unsupervised text classification: zero-shot and similarity-based approaches","author":"Schopf","year":"2023"},{"key":"10.1016\/j.media.2025.103912_bib0061","first-page":"25278","article-title":"Laion-5b: an open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0062","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., Komatsuzaki, A. L., 2021. 400m: Open dataset of clip-filtered 400 million image-text pairs. arxiv 2021. arXiv preprint arXiv:2111.02114."},{"key":"10.1016\/j.media.2025.103912_bib0063","series-title":"Forty-first International Conference on Machine Learning","article-title":"Ot-clip: understanding and generalizing clip via optimal transport","author":"Shi","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0064","article-title":"MedICat: a dataset of medical images, captions, and textual references","author":"Subramanian","year":"2020","journal-title":"Find. Assoc. Comput. Linguist.: EMNLP"},{"key":"10.1016\/j.media.2025.103912_bib0014","unstructured":"Van den, O. A., Li, Y., Vinyals, O., 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"key":"10.1016\/j.media.2025.103912_bib0065","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103912_bib0066","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J., 2022b. Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163.","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"10.1016\/j.media.2025.103912_bib0067","series-title":"International Conference on Machine Learning","first-page":"23631","article-title":"Mitigating neural network overconfidence with logit normalization","author":"Wei","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0068","series-title":"International Conference on Learning Representations","article-title":"Data efficient language-supervised zero-shot recognition with optimal transport distillation","author":"Wu","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0069","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"1081","article-title":"Rule: reliable multimodal rag for factuality in medical vision language models","author":"Xia","year":"2024"},{"key":"10.1016\/j.media.2025.103912_bib0070","unstructured":"Xu, H., Xie, S., Tan, X. E., Huang, P.-Y., Howes, R., Sharma, V., Li, S.-W., Ghosh, G., Zettlemoyer, L., Feichtenhofer, C., 2023. Demystifying clip data. arXiv preprint arXiv:2309.16671."},{"key":"10.1016\/j.media.2025.103912_bib0071","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"77","article-title":"Imagechd: a 3d computed tomography image dataset for classification of congenital heart disease","author":"Xu","year":"2020"},{"key":"10.1016\/j.media.2025.103912_bib0072","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15671","article-title":"Vision-language pre-training with triple contrastive learning","author":"Yang","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0073","article-title":"Coca: contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.media.2025.103912_bib0074","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10819","article-title":"Metaformer is actually what you need for vision","author":"Yu","year":"2022"},{"key":"10.1016\/j.media.2025.103912_bib0075","series-title":"Proceedings of the 31St ACM International Conference on Multimedia","first-page":"547","article-title":"Ramm: retrieval-augmented biomedical visual question answering with multi-modal pre-training","author":"Yuan","year":"2023"},{"issue":"1","key":"10.1016\/j.media.2025.103912_bib0076","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2400640","article-title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","volume":"2","author":"Zhang","year":"2024","journal-title":"NEJM AI"},{"key":"10.1016\/j.media.2025.103912_bib0077","unstructured":"Zhang, X., Wu, C., Zhao, Z., Lin, W., Zhang, Y., Wang, Y., Xie, W., 2023. Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415."},{"key":"10.1016\/j.media.2025.103912_bib0078","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11028","article-title":"Non-contrastive learning meets language-image pre-training","author":"Zhou","year":"2023"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152500458X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152500458X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T09:56:46Z","timestamp":1773914206000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S136184152500458X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":78,"alternative-id":["S136184152500458X"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2025.103912","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MIRAGE: Medical image-text pre-training for robustness against noisy environments","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2025.103912","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 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":"103912"}}