{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:13:44Z","timestamp":1760195624709,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032078445","type":"print"},{"value":"9783032078452","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07845-2_8","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:28:30Z","timestamp":1760192910000},"page":"76-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RadiSimCLIP: A Radiology Vision-Language Model Pretrained on\u00a0Simulated Radiologist Learning Dataset for Zero-Shot Medical Image Understanding"],"prefix":"10.1007","author":[{"given":"Minhui","family":"Tan","sequence":"first","affiliation":[]},{"given":"Qingxia","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Boyang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Genqiang","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Jianlong","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Zhong","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Xiaohuan","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Dinggang","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"issue":"11","key":"8_CR1","doi-asserted-by":"publisher","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(11), e1002699 (2018)","journal-title":"PLoS Med."},{"key":"8_CR2","unstructured":"Chen, Q., et\u00a0al.: A survey of medical vision-and-language applications and their techniques. arXiv preprint arXiv:2411.12195 (2024)"},{"key":"8_CR3","unstructured":"Codella, N.C., et\u00a0al.: Medimageinsight: an open-source embedding model for general domain medical imaging. arXiv preprint arXiv:2410.06542 (2024)"},{"key":"8_CR4","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. 1181\u20131193 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"8_CR5","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting clip\u2019s image representation via text-based decomposition. arXiv preprint arXiv:2310.05916 (2023)"},{"key":"8_CR6","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, pp. 123\u2013139. Springer (2025)","DOI":"10.1007\/978-3-031-73004-7_8"},{"issue":"9","key":"8_CR7","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(9), 2307\u20132316 (2023)","journal-title":"Nat. Med."},{"key":"8_CR8","unstructured":"Ikezogwo, W., et al.: Quilt-1m: one million image-text pairs for histopathology. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR9","unstructured":"Ji, Y., et al.: Amos: a large-scale abdominal multi-organ benchmark for versatile medical image segmentation (2022). https:\/\/arxiv.org\/abs\/2206.08023"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Kakkar, M., Shanbhag, D., Aladahalli, C., Reddy, G.: Language augmentation in clip for improved anatomy detection on multi-modal medical images. In: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.\u00a01\u20134. IEEE (2024)","DOI":"10.1109\/EMBC53108.2024.10781689"},{"key":"8_CR11","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 preprint arXiv:2412.10372 (2024)"},{"key":"8_CR12","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, pp. 525\u2013536. Springer (2023)","DOI":"10.1007\/978-3-031-43993-3_51"},{"issue":"3","key":"8_CR13","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(3), 863\u2013874 (2024)","journal-title":"Nat. Med."},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., et al.: Visual language pretrained multiple instance zero-shot transfer for histopathology images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19764\u201319775 (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"8_CR15","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1038\/s41591-024-02959-y","volume":"30","author":"Vision-language foundation model for echocardiogram interpretation","year":"2024","unstructured":"Vision-language foundation model for echocardiogram interpretation: Matthew Christensen, Milos Vukadinovic, N.Y., Ouyang, D. Nat. Med. 30, 1481\u20131488 (2024)","journal-title":"Nat. Med."},{"key":"8_CR16","unstructured":"National Library of Medicine: PMC open access subset (2003). https:\/\/pmc.ncbi.nlm.nih.gov\/tools\/openftlist\/"},{"key":"8_CR17","unstructured":"of\u00a0North\u00a0America, R.S.: RSNA pneumonia detection challenge (2018). https:\/\/www.kaggle.com\/c\/rsna-pneumonia-detection-challenge\/. Accessed: [date of access]"},{"key":"8_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"8_CR19","unstructured":"Rajpurkar, P.: Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. ArXiv abs\/1711 5225 (2017)"},{"issue":"12","key":"8_CR20","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E., Talius, E., Patel, P., Langlotz, C.P., Ng, A.Y., Rajpurkar, P.: Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nature Biomed. Eng. 6(12), 1399\u20131406 (2022)","journal-title":"Nature Biomed. Eng."},{"key":"8_CR21","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"8_CR22","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, pp. 101\u2013111. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"8_CR23","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":"8_CR24","doi-asserted-by":"crossref","unstructured":"Woerner, S., Jaques, A., Baumgartner, C.F.: A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset (medimeta) (2024). https:\/\/arxiv.org\/abs\/2404.16000","DOI":"10.1038\/s41597-025-04866-4"},{"key":"8_CR25","unstructured":"Yang, H., et al.: Multi-modal vision-language model for generalizable annotation-free pathological lesions localization and clinical diagnosis. http:\/\/arxiv.org\/abs\/2401.02044"},{"issue":"1","key":"8_CR26","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","volume":"10","author":"J Yang","year":"2023","unstructured":"Yang, J., et al.: Medmnist v2-a large-scale lightweight benchmark for 2D and 3D biomedical image classification. Sci. Data 10(1), 41 (2023)","journal-title":"Sci. Data"},{"key":"8_CR27","unstructured":"Zhang, K., et\u00a0al.: A generalist vision\u2013language foundation model for diverse biomedical tasks. Nature Medi. 1\u201313 (2024)"},{"key":"8_CR28","unstructured":"Zhang, S., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv:2303.009152(3), 6 (2023)"},{"key":"8_CR29","unstructured":"Zhang, S., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"issue":"1","key":"8_CR30","doi-asserted-by":"publisher","first-page":"4542","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(1), 4542 (2023)","journal-title":"Nat. Commun."}],"container-title":["Lecture Notes in Computer Science","Foundation Models for General Medical AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07845-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:28:35Z","timestamp":1760192915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07845-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032078445","9783032078452"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07845-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MedAGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Foundation Models for General Medical AI","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"medagi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/medagi2025.github.io\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}