{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:38:14Z","timestamp":1767418694253,"version":"3.48.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032049803"},{"type":"electronic","value":"9783032049810"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-04981-0_33","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:10:54Z","timestamp":1758258654000},"page":"348-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["More Performant and\u00a0Scalable: Rethinking Contrastive Vision-Language Pre-training of\u00a0Radiology in\u00a0the\u00a0LLM Era"],"prefix":"10.1007","author":[{"given":"Yingtai","family":"Li","sequence":"first","affiliation":[]},{"given":"Haoran","family":"Lai","sequence":"additional","affiliation":[]},{"given":"Xiaoqian","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Ming","sequence":"additional","affiliation":[]},{"given":"Wenxin","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Shaohua Kevin","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"33_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"6","key":"33_CR2","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1038\/s41591-019-0447-x","volume":"25","author":"D Ardila","year":"2019","unstructured":"Ardila, D., et al.: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat. Med. 25(6), 954\u2013961 (2019)","journal-title":"Nat. Med."},{"key":"33_CR3","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Blankemeier, L., et\u00a0al.: Merlin: a vision language foundation model for 3D computed tomography. Res. Square, rs\u20133 (2024)","DOI":"10.21203\/rs.3.rs-4546309\/v1"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Boecking, B., et\u00a0al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: European Conference on Computer Vision, pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"33_CR6","unstructured":"ByteDance: Doubao: a large language model by bytedance. https:\/\/www.doubao.com (2023). Accessed Jun 2024"},{"issue":"12","key":"33_CR7","doi-asserted-by":"publisher","first-page":"3033","DOI":"10.1038\/s41591-023-02640-w","volume":"29","author":"K Cao","year":"2023","unstructured":"Cao, K., et al.: Large-scale pancreatic cancer detection via non-contrast CT and deep learning. Nat. Med. 29(12), 3033\u20133043 (2023)","journal-title":"Nat. Med."},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Cao, W., et al.: Bootstrapping chest CT image understanding by distilling knowledge from X-Ray expert models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11238\u201311247 (2024)","DOI":"10.1109\/CVPR52733.2024.01068"},{"issue":"1","key":"33_CR9","doi-asserted-by":"publisher","first-page":"e44","DOI":"10.1016\/S2589-7500(23)00218-2","volume":"6","author":"YD Cid","year":"2024","unstructured":"Cid, Y.D., et al.: Development and validation of open-source deep neural networks for comprehensive chest X-Ray reading: a retrospective, multicentre study. Lancet Digit. Health 6(1), e44\u2013e57 (2024)","journal-title":"Lancet Digit. Health"},{"key":"33_CR10","unstructured":"Dai, D., et\u00a0al.: DeepSeekMoE: towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066 (2024)"},{"key":"33_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101857","volume":"67","author":"RL Draelos","year":"2021","unstructured":"Draelos, R.L., et al.: Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes. Med. Image Anal. 67, 101857 (2021)","journal-title":"Med. Image Anal."},{"key":"33_CR12","unstructured":"Hamamci, I.E., et\u00a0al.: A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities. CoRR (2024)"},{"key":"33_CR13","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Lai, H., et al.: Bridged semantic alignment for zero-shot 3D medical image diagnosis. arXiv preprint arXiv:2501.03565 (2025)","DOI":"10.1109\/JBHI.2025.3629096"},{"key":"33_CR15","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"33_CR16","unstructured":"Li, Y., Ming, S., Lai, H., Tang, F., Wei, W., Zhou, S.K.: Scaling supervision for free: leveraging universal segmentation models for enhanced medical image diagnosis. In: Submitted to Medical Imaging with Deep Learning (2025). https:\/\/openreview.net\/forum?id=SpHsR20XjU, under review"},{"key":"33_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Park, R.Y., Windsor, R., Jamaludin, A., Zisserman, A.: Automated spinal MRI labelling from reports using a large language model. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 101\u2013111. Springer (2024)","DOI":"10.1007\/978-3-031-72086-4_10"},{"key":"33_CR19","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":"33_CR20","unstructured":"Shui, Z., et al.: Large-scale and fine-grained vision-language pre-training for enhanced CT image understanding. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=nYpPAT4L3D"},{"issue":"22","key":"33_CR21","doi-asserted-by":"publisher","first-page":"2400","DOI":"10.1001\/jama.2012.5960","volume":"307","author":"R Smith-Bindman","year":"2012","unstructured":"Smith-Bindman, R., et al.: Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996\u20132010. JAMA 307(22), 2400\u20132409 (2012)","journal-title":"JAMA"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"issue":"12","key":"33_CR23","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. Nat. Biomed. Eng. 6(12), 1399\u20131406 (2022)","journal-title":"Nat. Biomed. Eng."},{"issue":"1","key":"33_CR24","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1038\/s41746-022-00648-z","volume":"5","author":"C Wang","year":"2022","unstructured":"Wang, C., et al.: Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases. NPJ Digit. Med. 5(1), 124 (2022)","journal-title":"NPJ Digit. Med."},{"key":"33_CR25","unstructured":"Wang, Y.R., et\u00a0al.: Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging. Nat. Med., 1\u201310 (2024)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"issue":"1","key":"33_CR27","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","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04981-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:33:36Z","timestamp":1767418416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04981-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049803","9783032049810"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04981-0_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are 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":"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":"23 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":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}