{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:00:46Z","timestamp":1775041246508,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723896","type":"print"},{"value":"9783031723902","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72390-2_66","type":"book-chapter","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T10:03:14Z","timestamp":1729591394000},"page":"709-719","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["RET-CLIP: A Retinal Image Foundation Model Pre-trained with\u00a0Clinical Diagnostic Reports"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"Du","sequence":"first","affiliation":[]},{"given":"Jia","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Weihang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shengzhu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hanruo","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Huiqi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ningli","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"issue":"11","key":"66_CR1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207982","volume":"13","author":"JM Ahn","year":"2018","unstructured":"Ahn, J.M., Kim, S., Ahn, K.S., Cho, S.H., Lee, K.B., Kim, U.S.: A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PloS one 13(11), e0207982 (2018)","journal-title":"PloS one"},{"key":"66_CR2","doi-asserted-by":"crossref","unstructured":"Baliah, S., Maani, F.A., Sanjeev, S., Khan, M.H.: Exploring the transfer learning capabilities of clip in domain generalization for diabetic retinopathy. In: International Workshop on Machine Learning in Medical Imaging. pp. 444\u2013453. Springer (2023)","DOI":"10.1007\/978-3-031-45673-2_44"},{"issue":"1","key":"66_CR3","doi-asserted-by":"publisher","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","volume":"12","author":"LP Cen","year":"2021","unstructured":"Cen, L.P., Ji, J., Lin, J.W., Ju, S.T., Lin, H.J., Li, T.P., Wang, Y., Yang, J.F., Liu, Y.F., Tan, S., et\u00a0al.: Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks. Nature communications 12(1), \u00a04828 (2021)","journal-title":"Nature communications"},{"key":"66_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"66_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"66_CR6","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: How much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023. pp. 1151\u20131163 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"66_CR7","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"issue":"1","key":"66_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1038\/s41597-022-01388-1","volume":"9","author":"O Kovalyk","year":"2022","unstructured":"Kovalyk, O., Morales-S\u00e1nchez, J., Verd\u00fa-Monedero, R., Sell\u00e9s-Navarro, I., Palaz\u00f3n-Cabanes, A., Sancho-G\u00f3mez, J.L.: Papila: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment. Scientific Data 9(1), \u00a0291 (2022)","journal-title":"Scientific Data"},{"key":"66_CR9","doi-asserted-by":"crossref","unstructured":"Lin, W., Zhao, Z., Zhang, X., Wu, C., Zhang, Y., Wang, Y., Xie, W.: Pmc-clip: Contrastive language-image pre-training using biomedical documents. arXiv preprint arXiv:2303.07240 (2023)","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"66_CR10","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"issue":"7956","key":"66_CR11","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M., Banerjee, O., Abad, Z.S.H., Krumholz, H.M., Leskovec, J., Topol, E.J., Rajpurkar, P.: Foundation models for generalist medical artificial intelligence. Nature 616(7956), 259\u2013265 (2023)","journal-title":"Nature"},{"key":"66_CR12","unstructured":"Moor, M., Huang, Q., Wu, S., Yasunaga, M., Dalmia, Y., Leskovec, J., Zakka, C., Reis, E.P., Rajpurkar, P.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H). pp. 353\u2013367. PMLR (2023)"},{"key":"66_CR13","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"66_CR14","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et\u00a0al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"2","key":"66_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/data6020014","volume":"6","author":"S Pachade","year":"2021","unstructured":"Pachade, S., Porwal, P., Thulkar, D., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., Giancardo, L., Quellec, G., M\u00e9riaudeau, F.: Retinal fundus multi-disease image dataset (rfmid): A dataset for multi-disease detection research. Data 6(2), \u00a014 (2021)","journal-title":"Data"},{"key":"66_CR16","unstructured":"Porwal, P., Pachade, S., Kokare, M., Deshmukh, G., Son, J., Bae, W., Liu, L., Wang, J., Liu, X., Gao, L., et\u00a0al.: Idrid: Diabetic retinopathy\u2013segmentation and grading challenge. Medical image analysis 59, 101561 (2020)"},{"key":"66_CR17","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"66_CR18","unstructured":"Silva-Rodriguez, J., Chakor, H., Kobbi, R., Dolz, J., Ayed, I.B.: A foundation language-image model of the retina (flair): Encoding expert knowledge in text supervision. arXiv preprint arXiv:2308.07898 (2023)"},{"key":"66_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"66_CR20","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: Medical knowledge enhanced language-image pre-training. medRxiv pp. 2023\u201301 (2023)","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"66_CR21","unstructured":"Yang, A., Pan, J., Lin, J., Men, R., Zhang, Y., Zhou, J., Zhou, C.: Chinese clip: Contrastive vision-language pretraining in chinese. arXiv preprint arXiv:2211.01335 (2022)"},{"key":"66_CR22","unstructured":"Zhang, X., Wu, C., Zhao, Z., Lin, W., Zhang, Y., Wang, Y., Xie, W.: Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"66_CR23","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive Learning of Medical Visual Representations from Paired Images and Text (Sep 2022)"},{"key":"66_CR24","unstructured":"Zhong, T., Zhao, W., Zhang, Y., Pan, Y., Dong, P., Jiang, Z., Kui, X., Shang, Y., Yang, L., Wei, Y., et\u00a0al.: Chatradio-valuer: A chat large language model for generalizable radiology report generation based on multi-institution and multi-system data. arXiv preprint arXiv:2310.05242 (2023)"},{"issue":"7981","key":"66_CR25","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","volume":"622","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Chia, M.A., Wagner, S.K., Ayhan, M.S., Williamson, D.J., Struyven, R.R., Liu, T., Xu, M., Lozano, M.G., Woodward-Court, P., et\u00a0al.: A foundation model for generalizable disease detection from retinal images. Nature 622(7981), 156\u2013163 (2023)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72390-2_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T10:15:25Z","timestamp":1729592125000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72390-2_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723896","9783031723902"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72390-2_66","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"23 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}