{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:09:00Z","timestamp":1789081740984,"version":"build-2803163510"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":98,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["IS24053"],"award-info":[{"award-number":["IS24053"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFE0205700"],"award-info":[{"award-number":["2022YFE0205700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82441023"],"award-info":[{"award-number":["82441023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Municipal Central Guided Local Science and Technology Development Fund","award":["YDZX20233100001001"],"award-info":[{"award-number":["YDZX20233100001001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02713-3","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:43:43Z","timestamp":1780688623000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning like a radiologist: a medical vision-language model for radiological image analysis via curriculum learning"],"prefix":"10.1038","volume":"9","author":[{"given":"Minhui","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingxia","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genqiang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiang","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinggang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"2713_CR1","unstructured":"Codella, N. C. F. et al. MedImageInsight: an open-source embedding model for general domain medical imaging. Preprint at arXiv https:\/\/arxiv.org\/abs\/2410.06542 (2024)."},{"key":"2713_CR2","unstructured":"Rajpurkar, P. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. Preprint at arXiv https:\/\/arxiv.org\/abs\/1711 (2017)."},{"key":"2713_CR3","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E. et al. Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning. Nat. Biomed. Eng. 6, 1399\u20131406 (2022).","journal-title":"Nat. Biomed. Eng."},{"key":"2713_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7","volume":"14","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Wu, C., Zhang, Y., Xie, W. & Wang, Y. Knowledge-enhanced visual-language pre-training on chest radiology images. Nat. Commun. 14, 4542 (2023).","journal-title":"Nat. Commun."},{"key":"2713_CR5","unstructured":"Yang, Hao, et al. A multimodal vision\u2013language model for generalizable annotation-free pathology localization. Nat. Biomed Eng. 1\u201315 (2026)."},{"key":"2713_CR6","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 Proc. of the IEEE\/CVF International Conference on Computer Vision 3942\u20133951 (2021).","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"2713_CR7","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, C., Zhang, S. & Dou, Q. Foundation model for endoscopy video analysis via large-scale self-supervised pre-train. in International Conference on Medical Image Computing and Computer-Assisted Intervention 101\u2013111 (2023).","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"2713_CR8","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41591-024-02959-y","volume":"30","author":"MVM Christensen","year":"2024","unstructured":"Christensen, M. V. M. & Ouyang, D. Vision\u2013language foundation model for echocardiogram interpretation. Nat. Med. 30, 1481\u20131488 (2024).","journal-title":"Nat. Med."},{"key":"2713_CR9","doi-asserted-by":"crossref","unstructured":"Lu, M. Y. et al. Visual language pretrained multiple instance zero-shot transfer for histopathology images. In Proc. of the IEEE\/CVF conference on computer vision and pattern recognition 19764\u201319775 (2023).","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"2713_CR10","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J. & Zou, J. A visual-language foundation model for pathology image analysis using medical twitter. Nat. Med. 29, 2307\u20132316 (2023).","journal-title":"Nat. Med."},{"key":"2713_CR11","doi-asserted-by":"crossref","unstructured":"Ikezogwo, W. et al. Quilt-1m: one million image-text pairs for histopathology. Adv. Neural Inf. Process Syst. 36, 37995\u201338017 (2024).","DOI":"10.52202\/075280-1654"},{"key":"2713_CR12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863\u2013874 (2024).","journal-title":"Nat. Med."},{"key":"2713_CR13","doi-asserted-by":"crossref","unstructured":"Lin, W. et al. Pmc-clip: Contrastive language-image pre-training using biomedical documents. In International Conference on Medical Image Computing and Computer-Assisted Intervention 525\u2013536 (2023).","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"2713_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, S. et al. A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs. Nejm Ai 2.1 (2025).","DOI":"10.1056\/AIoa2400640"},{"key":"2713_CR15","first-page":"6","volume":"2","author":"S Zhang","year":"2023","unstructured":"Zhang, S. et al. Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv 2, 6 (2023).","journal-title":"arXiv"},{"key":"2713_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, K. et al. A generalist vision-language foundation model for diverse biomedical tasks. Nat. Med. 30, 3129\u20133141 (2024).","DOI":"10.1038\/s41591-024-03185-2"},{"key":"2713_CR17","unstructured":"Khattak, M. U., Kunhimon, S., Naseer, M., Khan, S. & Khan, F. S. UniMed-CLIP: towards a unified image-text pretraining paradigm for diverse medical imaging modalities. arXiv https:\/\/arxiv.org\/abs\/2412.10372 (2024)."},{"key":"2713_CR18","doi-asserted-by":"crossref","unstructured":"He, X. et al. Unified medical image pre-training in language-guided common semantic space. In European Conference on Computer Vision 123\u2013139.","DOI":"10.1007\/978-3-031-73004-7_8"},{"key":"2713_CR19","doi-asserted-by":"crossref","unstructured":"Eslami, S., de Melo, G. & Meinel, C. PubMedCLIP: how much does CLIP benefit visual question answering in the medical domain? In Findings of the Association for Computational Linguistics: EACL, 1181\u20131193 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"2713_CR20","unstructured":"Lin, J. et al. Ct-glip: 3d grounded language-image pretraining with ct scans and radiology reports for full-body scenarios. arXiv https:\/\/arxiv.org\/abs\/2404.15272 (2024)."},{"key":"2713_CR21","doi-asserted-by":"crossref","unstructured":"Chauhan, G. et al. Joint modeling of chest radiographs and radiology reports for pulmonary edema assessment. In Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020 (eds. Martel, A. L. et al.) 529\u2013539 (Springer International Publishing, 2020).","DOI":"10.1007\/978-3-030-59713-9_51"},{"key":"2713_CR22","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y. & Xie, W. Medklip: medical knowledge enhanced language-image pre-training for x-ray diagnosis. In Proc. of the IEEE\/CVF International Conference on Computer Vision 21372\u201321383 (2023).","DOI":"10.1101\/2023.01.10.23284412"},{"key":"2713_CR23","doi-asserted-by":"crossref","unstructured":"You, K. et al. Cxr-clip: toward large scale chest x-ray language-image pre-training. In International Conference on Medical Image Computing and Computer-Assisted Intervention 101\u2013111 (2023).","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"2713_CR24","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1038\/s41746-025-01893-8","volume":"8","author":"R Holland","year":"2025","unstructured":"Holland, R. et al. Specialized curricula for training vision language models in retinal image analysis. npj Digit. Med. 8, 532 (2025).","journal-title":"npj Digit. Med."},{"key":"2713_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z. et al. Medclip: Contrastive learning from unpaired medical images and text. In Proc. of the 2022 Conference on Empirical Methods in Natural Language Processing (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"2713_CR26","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1073\/pnas.98.2.381","volume":"98","author":"RJ Roberts","year":"2001","unstructured":"Roberts, R. J. PubMed central: the GenBank of the published literature. Proc. Natl. Acad. Sci. 98, 381\u2013382 (2001).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2713_CR27","unstructured":"Team, L. et al. Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv https:\/\/arxiv.org\/abs\/2506.07044 (2025)."},{"key":"2713_CR28","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R. & Weston, J. Curriculum learning. in Proc. 26th Annu. Int. Conf. Mach. Learn. 41\u201348 (2009).","DOI":"10.1145\/1553374.1553380"},{"key":"2713_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, X. et al. Sigmoid loss for language image pre-training. In Proc. of the IEEE\/CVF international conference on computer vision (2023).","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"2713_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101950","volume":"69","author":"AE Kavur","year":"2021","unstructured":"Kavur, A. E. et al. CHAOS challenge-combined (CT-MR) healthy abdominal organ segmentation. Med. Image Anal. 69, 101950 (2021).","journal-title":"Med. Image Anal."},{"key":"2713_CR31","doi-asserted-by":"publisher","first-page":"36722","DOI":"10.52202\/068431-2661","volume":"35","author":"Y Ji","year":"2022","unstructured":"Ji, Y. et al. Amos: a large-scale abdominal multi-organ benchmark for versatile medical image segmentation. Adv. Neural Inf. Process. Syst. 35, 36722\u201336732 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2713_CR32","doi-asserted-by":"crossref","unstructured":"Akinci D\u2019Antonoli, Tugba, et al. TotalSegmentator MRI: robust sequence-independent segmentation of multiple anatomic structures in MRI. Radiology 314.2 (2025).","DOI":"10.1148\/radiol.241613"},{"key":"2713_CR33","doi-asserted-by":"crossref","unstructured":"Luo, X., Li, Z., Zhang, S., Liao, W. & Wang, G. RetHINKING ABDOMINAL ORGAN SEGMENTATIOn (RAOS) in the clinical scenario: a robustness evaluation benchmark with challenging cases. In International Conference on Medical Image Computing and Computer-Assisted Intervention 531\u2013541 (2024).","DOI":"10.1007\/978-3-031-72114-4_51"},{"key":"2713_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00715-8","volume":"7","author":"B Rister","year":"2020","unstructured":"Rister, B., Yi, D., Shivakumar, K., Nobashi, T. & Rubin, D. L. CT-ORG, a new dataset for multiple organ segmentation in computed tomography. Sci. Data 7, 381 (2020).","journal-title":"Sci. Data"},{"key":"2713_CR35","doi-asserted-by":"publisher","first-page":"e230024","DOI":"10.1148\/ryai.230024","volume":"5","author":"J Wasserthal","year":"2023","unstructured":"Wasserthal, J. et al. TotalSegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol. Artif. Intell. 5, e230024 (2023).","journal-title":"Radiol. Artif. Intell."},{"key":"2713_CR36","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. in International conference on machine learning 8748\u20138763 (2021)."},{"key":"2713_CR37","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A. & Beyer, L. Sigmoid loss for language image pre-training. In Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) 11975\u201311986 (2023).","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"2713_CR38","unstructured":"Sellergren, A. et al. MedGemma technical report. arXiv https:\/\/arxiv.org\/abs\/2507.05201 (2025)."},{"key":"2713_CR39","doi-asserted-by":"publisher","first-page":"102680","DOI":"10.1016\/j.media.2022.102680","volume":"84","author":"P Bilic","year":"2023","unstructured":"Bilic, P. et al. The Liver tumor segmentation benchmark (LiTS). Me\u0301d. Image Anal. 84, 102680 (2023).","journal-title":"Me\u0301d. Image Anal."},{"key":"2713_CR40","unstructured":"Br35H: brain tumor detection 2020. https:\/\/www.kaggle.com\/datasets\/ahmedhamada0\/braintumor-detection (2020)."},{"key":"2713_CR41","doi-asserted-by":"publisher","first-page":"e1002699","DOI":"10.1371\/journal.pmed.1002699","volume":"15","author":"N Bien","year":"2018","unstructured":"Bien, N. et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLoS Med. 15, e1002699 (2018).","journal-title":"PLoS Med."},{"key":"2713_CR42","doi-asserted-by":"crossref","unstructured":"Habib, M. E. H., K\u00fccukmanisa, A. & Urhan, O. A few-shot learning approach for multi-task CT image classification. In 2023 14th International Conference on Electrical and Electronics Engineering (ELECO) 1\u20135 (IEEE, 2023).","DOI":"10.1109\/ELECO60389.2023.10415985"},{"key":"2713_CR43","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/data5010014","volume":"5","author":"M Hssayeni","year":"2020","unstructured":"Hssayeni, M. et al. Computed tomography images for intracranial hemorrhage detection and segmentation. Intracranial hemorrhage segmentation using a deep convolutional model. Data 5, 14 (2020).","journal-title":"Data"},{"key":"2713_CR44","unstructured":"Yang, X. et al. Covid-ct-dataset: a CT scan dataset about covid-19. arXiv https:\/\/arxiv.org\/abs\/2003.13865 (2020)."},{"key":"2713_CR45","doi-asserted-by":"crossref","unstructured":"Roth, H. R. et al. A new 2.5 D representation for lymph node detection using random sets of deep convolutional neural network observations. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2014: 17th International Conference, Boston, MA, USA, September 14\u201318, 2014, Proceedings, Part I 17, 520\u2013527 (2014).","DOI":"10.1007\/978-3-319-10404-1_65"},{"key":"2713_CR46","doi-asserted-by":"crossref","unstructured":"Yang, J., Shi, R. & Ni, B. Medmnist classification decathlon: a lightweight automl benchmark for medical image analysis. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) 191\u2013195 (2021).","DOI":"10.1109\/ISBI48211.2021.9434062"},{"key":"2713_CR47","doi-asserted-by":"publisher","first-page":"e180041","DOI":"10.1148\/ryai.2019180041","volume":"1","author":"G Shih","year":"2019","unstructured":"Shih, G. et al. Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1, e180041 (2019).","journal-title":"Radiol. Artif. Intell."},{"key":"2713_CR48","unstructured":"Brain Tumor Classification MRI Images. https:\/\/www.kaggle.com\/datasets\/jarvisgroot\/brain-tumor-classification-mri-images?resource=download-directory (2021)."},{"key":"2713_CR49","doi-asserted-by":"crossref","unstructured":"Irvin, J. et al. Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on artificial intelligence. 33, 590\u2013597 (2019).","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"2713_CR50","first-page":"109","volume":"42","author":"D Vorwerk","year":"2002","unstructured":"Vorwerk, D. Neue internationale Wege in der radiologischen Fort- und Weiterbildung: www.eurorad.org\u2013ein Projekt der EAR zur Onlinepublikation radiologischer Daten. Radiology 42, 109\u2013112 (2002).","journal-title":"Radiology"},{"key":"2713_CR51","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A. E. et al. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6, 317 (2019).","journal-title":"Sci. Data"},{"key":"2713_CR52","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D. et al. Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23, 304\u2013310 (2016).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2713_CR53","unstructured":"Bai, S. et al. Qwen2.5-VL technical report. arXiv https:\/\/arxiv.org\/abs\/arxiv.2502.13923 (2025)."},{"key":"2713_CR54","unstructured":"Zhang, H. et al. HuatuoGPT, towards taming language model to be a doctor. arXiv https:\/\/arxiv.org\/abs\/2305.15075 (2023)."},{"key":"2713_CR55","doi-asserted-by":"crossref","unstructured":"Chakraborty, S. et al. BioMedBERT: a pre-trained biomedical language model for QA and IR. Proc. 28th Int. Conf. Comput. Linguistics 669\u2013679 (2020).","DOI":"10.18653\/v1\/2020.coling-main.59"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02713-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02713-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02713-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:37:33Z","timestamp":1789079853000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02713-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":55,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2713"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02713-3","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]},"assertion":[{"value":"15 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.T. is an intern at Shanghai United Imaging Intelligence Co., Ltd. B.Z., G.R., J.N., Z.X., Y.Z., S.Z., X.C., and D.S. are employees of Shanghai United Imaging Intelligence Co., Ltd. The companies have no role in designing and performing the surveillance and analyzing and interpreting the data.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"695"}}