{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T05:10:44Z","timestamp":1790745044956,"version":"4.1.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000050","name":"U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["1R01HL180504"],"award-info":[{"award-number":["1R01HL180504"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-026-73022-2","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T09:02:29Z","timestamp":1779354149000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Contrastive language image pretraining for a cardiac magnetic resonance image embedding with zero-shot capabilities"],"prefix":"10.1038","volume":"17","author":[{"given":"Makiya","family":"Nakashima","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jielin","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peide","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihye","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Grimm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1475-2329","authenticated-orcid":false,"given":"Christopher","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung-Hak","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5531-9180","authenticated-orcid":false,"given":"David","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"73022_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968-020-00607-1","volume":"22","author":"CM Kramer","year":"2020","unstructured":"Kramer, C. M. et al. Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J. Cardiovasc. Magn. Reson. 22, 17 (2020).","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"73022_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s12968-016-0225-6","volume":"18","author":"F von Knobelsdorff-Brenkenhoff","year":"2016","unstructured":"von Knobelsdorff-Brenkenhoff, F. & Schulz-Menger, J. Role of cardiovascular magnetic resonance in the guidelines of the European Society of Cardiology. J. Cardiovasc. Magn. Reson. 18, 6 (2016).","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"73022_CR3","unstructured":"Rizkallah, D. et al. Impact of automated transfer of semi-automated segmentation and structured report rule requirements on cardiac MRI report quality, standardization, and efficiency. In Proceedings of AMIA Annual Symposium (American Medical Informatics Association, 2024)."},{"key":"73022_CR4","doi-asserted-by":"publisher","unstructured":"Cockrum, J. et al. Leveraging a vision transformer model to improve diagnostic accuracy of cardiac amyloidosis with cardiac magnetic resonance. JACC Cardiovasc. Imaging https:\/\/doi.org\/10.1016\/j.jcmg.2024.09.010 (2024).","DOI":"10.1016\/j.jcmg.2024.09.010"},{"key":"73022_CR5","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-020-00511-1","volume":"20","author":"G-P Diller","year":"2020","unstructured":"Diller, G.-P. et al. Utility of deep learning networks for the generation of artificial cardiac magnetic resonance images in congenital heart disease. BMC Med. Imaging 20, 113 (2020).","journal-title":"BMC Med. Imaging"},{"key":"73022_CR6","doi-asserted-by":"crossref","unstructured":"Lee, C. et al. Big healthcare data analytics: challenges and applications. In Handbook of Large-scale Distributed Computing in Smart Healthcare 11\u201341 (2017).","DOI":"10.1007\/978-3-319-58280-1_2"},{"key":"73022_CR7","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1161\/CIRCRESAHA.117.310782","volume":"122","author":"JA Leopold","year":"2018","unstructured":"Leopold, J. A. & Loscalzo, J. Emerging role of precision medicine in cardiovascular disease. Circ. Res. 122, 1302\u20131315 (2018).","journal-title":"Circ. Res."},{"key":"73022_CR8","doi-asserted-by":"crossref","unstructured":"Azizi, S. et al. Big self-supervised models advance medical image classification. In Proc. IEEE\/CVF International Conference on Computer Vision, 3478\u20133488 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"73022_CR9","doi-asserted-by":"crossref","unstructured":"Bai, W. et al. Self-supervised learning for cardiac MR image segmentation by anatomical position prediction. In Medical Image Computing and Computer Assisted Intervention (eds Shen, D. et al.) 541\u2013549 (Springer International Publishing, 2019).","DOI":"10.1007\/978-3-030-32245-8_60"},{"key":"73022_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539","volume":"58","author":"L Chen","year":"2019","unstructured":"Chen, L. et al. Self-supervised learning for medical image analysis using image context restoration. Med. Image Anal. 58, 101539 (2019).","journal-title":"Med. Image Anal."},{"key":"73022_CR11","doi-asserted-by":"crossref","unstructured":"He, K. et al. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16000\u201316009 (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"73022_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y. C. et al. Uniter: universal image-text representation learning. In European Conference on Computer Vision 104\u2013120 (Springer International Publishing, 2020).","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"73022_CR13","first-page":"6616","volume":"33","author":"Z Gan","year":"2020","unstructured":"Gan, Z. et al. Large-scale adversarial training for vision-and-language representation learning. Adv. Neural Inf. Process. Syst. 33, 6616\u20136628 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"73022_CR14","doi-asserted-by":"crossref","unstructured":"Li, X. et al. Oscar: Object-semantics Aligned Pre-training for Vision-language Tasks, 121\u2013137 (Springer, 2020).","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"73022_CR15","unstructured":"Li, J., Li, D., Xiong, C. & Hoi, S. Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning 12888\u201312900 (PMLR, 2022)."},{"key":"73022_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D. & Sun, J. Medclip: contrastive learning from unpaired medical images and text. In Proc. 2022 Conference on Empirical Methods in Natural Language Processing 3876\u20133887 (ACM, 2022).","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"73022_CR17","doi-asserted-by":"publisher","unstructured":"Christensen, M., Vukadinovic, M., Yuan, N. & Ouyang, D. Vision\u2013language foundation model for echocardiogram interpretation. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-024-02959-y (2024).","DOI":"10.1038\/s41591-024-02959-y"},{"key":"73022_CR18","doi-asserted-by":"publisher","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-024-02856-4 (2024).","DOI":"10.1038\/s41591-024-02856-4"},{"key":"73022_CR19","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G. & Zisserman, A. Frozen in time: A joint video and image encoder for end-to-end retrieval. In Proceedings of the IEEE\/CVF International Conference on Computer Vision 1728\u20131738 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"73022_CR20","unstructured":"Endo, M., Krishnan, R., Krishna, V., Ng, A. Y. & Rajpurkar, P. Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model. In Machine Learning for Health, 209\u2013219 (PMLR, 2021)."},{"key":"73022_CR21","unstructured":"Nakashima, M. et al. Indication driven autoregressive report generation for cardiac magnetic resonance imaging. In Proceedings of Machine Learning Research vol. 259, 775\u2013786 (PMLR, Vancouver, 2025)."},{"key":"73022_CR22","doi-asserted-by":"crossref","unstructured":"Miech, A. et al. End-to-end learning of visual representations from uncurated instructional videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 9879\u20139889 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"73022_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12968-021-00740-5","volume":"23","author":"SJ Backhaus","year":"2021","unstructured":"Backhaus, S. J. et al. Defining the optimal temporal and spatial resolution for cardiovascular magnetic resonance imaging feature tracking. J. Cardiovasc. Magn. Reson. 23, 1\u201312 (2021).","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"73022_CR24","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1016\/j.jcmg.2013.09.013","volume":"6","author":"Cullen","year":"2013","unstructured":"Cullen, Michael, W., Howard, J. ulien, Weissman & Neil, J. CV imaging for fellows in training: challenges and opportunities. JACC Cardiovasc. Imaging 6, 1225\u20131226 (2013).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"73022_CR25","unstructured":"Kandpal, N., Deng, H., Roberts, A., Wallace, E. & Raffel, C. Large language models struggle to learn long-tail knowledge. In International Conference on Machine Learning 15696\u201315707 (PMLR, 2023)."},{"key":"73022_CR26","doi-asserted-by":"publisher","DOI":"10.1148\/ryct.2021200112","volume":"3","author":"JW Goldfarb","year":"2021","unstructured":"Goldfarb, J. W. & Weber, J. Trends in cardiovascular MRI and CT in the U.S. medicare population from 2012 to 2017. Radio. Cardiothorac. Imaging 3, e200112 (2021).","journal-title":"Radio. Cardiothorac. Imaging"},{"key":"73022_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocmr.2024.101061","volume":"26","author":"JM Li","year":"2024","unstructured":"Li, J. M. et al. Regional variability of cardiovascular magnetic resonance access and utilization in the United States. J. Cardiovasc. Magn. Reson. 26, 101061 (2024).","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"73022_CR28","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C. D. & Langlotz, C. P. Contrastive learning of medical visual representations from paired images and text. In Machine Learning for Healthcare Conference, 2\u201325 (PMLR, 2022)."},{"key":"73022_CR29","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning, 1597\u20131607 (PMLR, 2020)."},{"key":"73022_CR30","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R. & LeCun, Y. Learning a similarity metric discriminatively, with application to face verification. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), Vol. 1, 539\u2013546 (IEEE, 2005).","DOI":"10.1109\/CVPR.2005.202"},{"key":"73022_CR31","first-page":"3951","volume":"3942","author":"S-C Huang","year":"2021","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.  Int. Conf. Comput. Vis. 3942, 3951 (2021).","journal-title":"Int. Conf. Comput. Vis."},{"key":"73022_CR32","doi-asserted-by":"crossref","unstructured":"Miech, A. et al. Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In Proceedings of the IEEE\/CVF International Conference on Computer Vision 2630\u20132640 (IEEE, 2019).","DOI":"10.1109\/ICCV.2019.00272"},{"key":"73022_CR33","doi-asserted-by":"crossref","unstructured":"Xu, H. et al. Videoclip: contrastive pre-training for zero-shot video-text understanding. In Proc. 2021 Conference on Empirical Methods in Natural Language Processing 6787\u20136800 (ACM, 2021).","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"73022_CR34","doi-asserted-by":"crossref","unstructured":"Buch, S. et al. Revisiting the\u201d video\u201d in video-language understanding. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2917\u20132927 (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"73022_CR35","doi-asserted-by":"crossref","unstructured":"Vukadinovic, M. et al. Comprehensive echocardiogram evaluation with view primed vision language AI. Nature 650, 970\u2013977 (2026).","DOI":"10.1038\/s41586-025-09850-x"},{"key":"73022_CR36","doi-asserted-by":"publisher","unstructured":"Zhang, K. et al. A generalist vision\u2013language foundation model for diverse biomedical tasks. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-024-03185-2 (2024).","DOI":"10.1038\/s41591-024-03185-2"},{"key":"73022_CR37","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03469-9","volume":"11","author":"DF Pace","year":"2024","unstructured":"Pace, D. F. et al. HVSMR-2.0: a 3D cardiovascular MR dataset for whole-heart segmentation in congenital heart disease. Sci. Data 11, 721 (2024).","journal-title":"Sci. Data"},{"key":"73022_CR38","doi-asserted-by":"crossref","unstructured":"Meier, C., Eisenbl\u00e4tter, M. & Gielen, S. Myocardial late gadolinium enhancement (LGE) in cardiac magnetic resonance imaging (CMR)\u2014an important risk marker for cardiac disease. J. Cardiovasc. Dev. Dis. 11, 40 (2024).","DOI":"10.3390\/jcdd11020040"},{"key":"73022_CR39","unstructured":"Touvron, H. et al. Llama 2: open foundation and fine-tuned chat models. Preprint at https:\/\/arxiv.org\/abs\/2307.09288 (2023)."},{"key":"73022_CR40","first-page":"e783","volume":"124","author":"BJ Gersh","year":"2011","unstructured":"Gersh, B. J. et al. ACCF\/AHA guideline for the diagnosis and treatment of hypertrophic cardiomyopathy: a report of the American College of Cardiology Foundation\/American Heart Association Task Force on Practice Guidelines. Circulation 124, e783\u2013e831 (2011).","journal-title":"Circulation"},{"key":"73022_CR41","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1161\/CIRCRESAHA.117.309711","volume":"121","author":"WJ McKenna","year":"2017","unstructured":"McKenna, W. J., Maron, B. J. & Thiene, G. Classification, epidemiology, and global burden of cardiomyopathies. Circ. Res. 121, 722\u2013730 (2017).","journal-title":"Circ. Res."},{"key":"73022_CR42","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.ihj.2020.04.004","volume":"72","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z. et al. Clinical characteristics and long-term prognosis of ischemic and non-ischemic cardiomyopathy. Indian Heart J. 72, 93\u2013100 (2020).","journal-title":"Indian Heart J."},{"key":"73022_CR43","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O. et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37, 2514\u20132525 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"73022_CR44","doi-asserted-by":"publisher","unstructured":"Zhai, A. & Wu, H.-Y. Classification is a strong baseline for deep metric learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1811.12649 (2019).","DOI":"10.48550\/arXiv.1811.12649"},{"key":"73022_CR45","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M. W., Lee, K. & Toutanova, K. Bert: pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) 4171\u20134186 (ACL, 2019).","DOI":"10.18653\/v1\/N19-1423"},{"key":"73022_CR46","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, 8748\u20138763 (PMLR, 2021)."},{"key":"73022_CR47","doi-asserted-by":"crossref","unstructured":"Alsentzer, E. et al. Publicly available clinical BERT embeddings. In Proc. 2nd Clinical Natural Language Processing Workshop 72\u201378 (ACL, 2019).","DOI":"10.18653\/v1\/W19-1909"},{"key":"73022_CR48","first-page":"4","volume":"2","author":"G Bertasius","year":"2021","unstructured":"Bertasius, G., Wang, H. & Torresani, L. Is space-time attention all you need for video understanding? ICML 2, 4 (2021).","journal-title":"ICML"},{"key":"73022_CR49","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J. & Wang, L. Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural Inf. Process. Syst. 35, 10078\u201310093 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"73022_CR50","doi-asserted-by":"crossref","unstructured":"Wang, L. et al. Videomae v2: Scaling video masked autoencoders with dual masking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 14549\u201314560 (2023).","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"73022_CR51","doi-asserted-by":"publisher","unstructured":"Wang, Y. et al. InternVideo: general video foundation models via generative and discriminative learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2212.03191 (2022).","DOI":"10.48550\/arXiv.2212.03191"},{"key":"73022_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. Towards cardiac MRI foundation models: comprehensive visual-tabular representations for whole-heart assessment and beyond. Med. Image Anal. 106, 103756 (2025).","DOI":"10.1016\/j.media.2025.103756"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73022-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73022-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73022-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T09:02:55Z","timestamp":1779354175000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-73022-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["73022"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-73022-2","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]},"assertion":[{"value":"6 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"4416"}}