{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:29:16Z","timestamp":1790879356188,"version":"4.1.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-025-05922-9","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T09:50:58Z","timestamp":1760089858000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Development of a large-scale grounded vision language dataset for chest CT analysis"],"prefix":"10.1038","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-9366","authenticated-orcid":false,"given":"Xiaoman","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5390-9053","authenticated-orcid":false,"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8609-6826","authenticated-orcid":false,"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-2347","authenticated-orcid":false,"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"5922_CR1","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. Nature Medicine 30, 863\u2013874 (2024).","journal-title":"Nature Medicine"},{"key":"5922_CR2","unstructured":"Achiam, J. et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"5922_CR3","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"5922_CR4","unstructured":"Team, G. et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"5922_CR5","first-page":"23716","volume":"35","author":"J-B Alayrac","year":"2022","unstructured":"Alayrac, J.-B. et al. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems 35, 23716\u201323736 (2022).","journal-title":"Advances in neural information processing systems"},{"key":"5922_CR6","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y. & Xie, W. Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data. Nature Communications, 16(1) (2025).","DOI":"10.1038\/s41467-025-62385-7"},{"key":"5922_CR7","doi-asserted-by":"publisher","first-page":"AIoa2300138","DOI":"10.1056\/AIoa2300138","volume":"1","author":"T Tu","year":"2024","unstructured":"Tu, T. et al. Towards generalist biomedical ai. NEJM AI 1, AIoa2300138 (2024).","journal-title":"NEJM AI"},{"key":"5922_CR8","doi-asserted-by":"crossref","unstructured":"Li, C. et al. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems 36 (2024).","DOI":"10.32388\/VLXB6M"},{"key":"5922_CR9","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\u2013language foundation model for pathology image analysis using medical twitter. Nature medicine 29, 2307\u20132316 (2023).","journal-title":"Nature medicine"},{"key":"5922_CR10","unstructured":"Moor, M. et al. Med-flamingo: a multimodal medical few-shot learner. In Machine Learning for Health (ML4H), 353\u2013367 (PMLR, 2023)."},{"key":"5922_CR11","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. Scientific data 6, 317 (2019).","journal-title":"Scientific data"},{"key":"5922_CR12","unstructured":"Hamamci, I. E. et al. A foundation model utilizing chest ct volumes and radiology reports for supervised-level zero-shot detection of abnormalities. CoRR (2024)."},{"key":"5922_CR13","unstructured":"Wu, J. et al. Chest imagenome dataset. Physio Net (2021)."},{"key":"5922_CR14","doi-asserted-by":"crossref","unstructured":"Castro, D. C. et al. Padchest-gr: A bilingual chest x-ray dataset for grounded radiology report generation. NEJM AI, 2(7) (2025).","DOI":"10.1056\/AIdbp2401120"},{"key":"5922_CR15","doi-asserted-by":"publisher","unstructured":"Boecking, B. et al. Ms-cxr: Making the most of text semantics to improve biomedical vision-language processing. https:\/\/doi.org\/10.13026\/b90j-vb87 (2022).","DOI":"10.13026\/b90j-vb87"},{"key":"5922_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, X. et al. RadGenome-Chest CT. https:\/\/doi.org\/10.57967\/hf\/5331 Hugging Face (2025).","DOI":"10.57967\/hf\/5331"},{"key":"5922_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, Z. et al. Large-vocabulary segmentation for medical images with text prompts. npj Digital Medicine 8,1 (2025).","DOI":"10.1038\/s41746-025-01964-w"},{"key":"5922_CR18","doi-asserted-by":"crossref","unstructured":"Hamamci, I. E., Er, S. & Menze, B. Ct2rep: Automated radiology report generation for 3d medical imaging. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 476\u2013486 (2024).","DOI":"10.1007\/978-3-031-72390-2_45"},{"key":"5922_CR19","doi-asserted-by":"crossref","unstructured":"Hamamci, I. E. et al. Generatect: Text-conditional generation of 3d chest ct volumes. In European Conference on Computer Vision, 126\u2013143 (2024).","DOI":"10.1007\/978-3-031-72986-7_8"},{"key":"5922_CR20","unstructured":"Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E. Capabilities of gpt-4 on medical challenge problems. arXiv preprint arXiv:2303.13375 (2023)."},{"key":"5922_CR21","unstructured":"Liu, Q. et al. Exploring the boundaries of gpt-4 in radiology. arXiv preprint arXiv:2310.14573 (2023)."},{"key":"5922_CR22","doi-asserted-by":"crossref","unstructured":"Hu, X. et al. Expert knowledge-aware image difference graph representation learning for difference-aware medical visual question answering. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 4156\u20134165 (2023).","DOI":"10.1145\/3580305.3599819"},{"key":"5922_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J. J., Gayen, S., Ben Abacha, A. & Demner-Fushman, D. A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5, 1\u201310 (2018).","journal-title":"Scientific data"},{"key":"5922_CR24","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E. J. et al. Lora: Low-rank adaptation of large language models. ICLR 1, 3 (2022).","journal-title":"ICLR"},{"key":"5922_CR25","unstructured":"AI@Meta. Llama 3 model card. huggingface (2024)."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05922-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05922-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05922-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T09:51:03Z","timestamp":1760089863000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05922-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["5922"],"URL":"https:\/\/doi.org\/10.1038\/s41597-025-05922-9","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"assertion":[{"value":"7 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","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":"1636"}}