{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:00:48Z","timestamp":1789984848661,"version":"4.0.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032380586","type":"print"},{"value":"9783032380593","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38059-3_53","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:10:29Z","timestamp":1789981829000},"page":"558-568","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Training of\u00a0Spatially Grounded 2D Vision\u2013Language Models for\u00a0Radiology"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1040-4011","authenticated-orcid":false,"given":"Yusuf","family":"Salcan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5159-9792","authenticated-orcid":false,"given":"Simon","family":"Ging","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5518-7445","authenticated-orcid":false,"given":"Robin Tibor","family":"Schirrmeister","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0686-7361","authenticated-orcid":false,"given":"Philipp","family":"Arnold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9022-6000","authenticated-orcid":false,"given":"Elmar","family":"Kotter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5759-4896","authenticated-orcid":false,"given":"Behzad","family":"Bozorgtabar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6282-8861","authenticated-orcid":false,"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"53_CR1","doi-asserted-by":"publisher","unstructured":"Akinci\u00a0D\u2019Antonoli, T., Berger, L.K., Indrakanti, A.K., Vishwanathan, N., Weiss, J., et\u00a0al.: TotalSegmentator MRI: robust sequence-independent segmentation of multiple anatomic structures in MRI. Radiology 314(2) (2025). https:\/\/doi.org\/10.1148\/radiol.241613","DOI":"10.1148\/radiol.241613"},{"key":"53_CR2","unstructured":"Bannur, S., Bouzid, K., Castro, D.C., Schwaighofer, A., Thieme, A.: MAIRA-2: grounded radiology report generation. arXiv:2406.04449 (2024)"},{"key":"53_CR3","unstructured":"Chen, Z., Varma, M., Delbrouck, J.B., Paschali, M., Blankemeier, L.: CheXagent: towards a foundation model for chest X-ray interpretation. In: AAAI 2024 Spring Symposium Series on Clinical Foundation Models (2024)"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Dubois, Y., Li, X., Taori, R., Zhang, T., Gulrajani, I.: AlpacaFarm: a simulation framework for methods that learn from human feedback. Adv. Neural Inf. Process. Syst. 36 (2023)","DOI":"10.52202\/075280-1308"},{"key":"53_CR5","unstructured":"Team, G.: Gemma: open models based on Gemini research and technology. arXiv:2403.08295 (2024)"},{"key":"53_CR6","unstructured":"Team, G.: Gemma 3 technical report. arXiv:2503.19786 (2025)"},{"key":"53_CR7","unstructured":"Ging, S., Bravo, M.A., Brox, T.: Open-ended VQA benchmarking of vision-language models by exploiting classification datasets and their semantic hierarchy. In: The Twelfth International Conference on Learning Representations (2024)"},{"issue":"1","key":"53_CR8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1080\/19312450709336664","volume":"1","author":"AF Hayes","year":"2007","unstructured":"Hayes, A.F., Krippendorff, K.: Answering the call for a standard reliability measure for coding data. Commun. Methods Meas. 1(1), 77\u201389 (2007). https:\/\/doi.org\/10.1080\/19312450709336664","journal-title":"Commun. Methods Meas."},{"key":"53_CR9","doi-asserted-by":"publisher","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3992\u20134003. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"1","key":"53_CR10","doi-asserted-by":"publisher","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. Sci. Data 5(1), 180251 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251","journal-title":"Sci. Data"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., et\u00a0al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, Datasets and Benchmarks Track, vol.\u00a036 (2023)","DOI":"10.52202\/075280-1240"},{"key":"53_CR12","doi-asserted-by":"publisher","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434010","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"53_CR13","doi-asserted-by":"publisher","unstructured":"Luo, L., Tang, B., Chen, X., Han, R., Chen, T.: VividMed: vision language model with versatile visual grounding for medicine. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1: Long Papers, pp. 1800\u20131821. Association for Computational Linguistics, Albuquerque (2025). https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.89","DOI":"10.18653\/v1\/2025.naacl-long.89"},{"issue":"1","key":"53_CR14","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13326-018-0179-8","volume":"9","author":"A N\u00e9v\u00e9ol","year":"2018","unstructured":"N\u00e9v\u00e9ol, A., Dalianis, H., Velupillai, S., Savova, G., Zweigenbaum, P.: Clinical natural language processing in languages other than English: opportunities and challenges. J. Biomed. Semant. 9(1), 12 (2018). https:\/\/doi.org\/10.1186\/s13326-018-0179-8","journal-title":"J. Biomed. Semant."},{"key":"53_CR15","unstructured":"OpenAI: gpt-oss-120b & gpt-oss-20b model card. arXiv:2508.10925 (2025)"},{"key":"53_CR16","unstructured":"Saab, K., Tu, T., Weng, W.H., Tanno, R., Stutz, D.: Capabilities of Gemini models in medicine. arXiv:2404.18416 (2024)"},{"key":"53_CR17","unstructured":"Sellergren, A., Kazemzadeh, S., Jaroensri, T., Kiraly, A., Traverse, M.: MedGemma technical report. arXiv:2507.05201 (2025)"},{"key":"53_CR18","doi-asserted-by":"publisher","unstructured":"Smith-Bindman, R., Kwan, M.L., Marlow, E.C., Theis, M.K., Bolch, W., et\u00a0al.: Trends in use of medical imaging in US health care systems and in Ontario, Canada, 2000\u20132016. JAMA 322(9), 843\u2013856 (2019). https:\/\/doi.org\/10.1001\/jama.2019.11456","DOI":"10.1001\/jama.2019.11456"},{"key":"53_CR19","unstructured":"Steiner, A., et al.: PaliGemma 2: a family of versatile VLMs for transfer. arXiv:2412.03555 (2024)"},{"issue":"8","key":"53_CR20","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A.J., Ting, D.S.J., Elangovan, K., Gutierrez, L., Tan, T.F., Ting, D.S.W.: Large language models in medicine. Nat. Med. 29(8), 1930\u20131940 (2023). https:\/\/doi.org\/10.1038\/s41591-023-02448-8","journal-title":"Nat. Med."},{"key":"53_CR21","doi-asserted-by":"publisher","unstructured":"Wasserthal, J., Breit, H.C., Meyer, M.T., Pradella, M., Hinck, D., et\u00a0al.: TotalSegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol. Artif. Intell. 5(5), e230024 (2023). https:\/\/doi.org\/10.1148\/ryai.230024","DOI":"10.1148\/ryai.230024"},{"issue":"1","key":"53_CR22","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","volume":"16","author":"C Wu","year":"2025","unstructured":"Wu, C., Zhang, X., Zhang, Y., Hui, H., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. Nat. Commun. 16(1), 7866 (2025). https:\/\/doi.org\/10.1038\/s41467-025-62385-7","journal-title":"Nat. Commun."},{"key":"53_CR23","unstructured":"Xu, S., Yang, L., Kelly, C., Sieniek, M., Kohlberger, T.: ELIXR: towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders. arXiv:2308.01317 (2023)"},{"key":"53_CR24","unstructured":"Yang, L., Xu, S., Sellergren, A., Kohlberger, T., Zhou, Y.: Advancing multimodal medical capabilities of Gemini. arXiv:2405.03162 (2024)"},{"key":"53_CR25","doi-asserted-by":"publisher","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11941\u201311952. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01100","DOI":"10.1109\/ICCV51070.2023.01100"},{"issue":"11","key":"53_CR26","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","volume":"30","author":"K Zhang","year":"2024","unstructured":"Zhang, K., Zhou, R., Adhikarla, E., Yan, Z., Liu, Y., et al.: A generalist vision-language foundation model for diverse biomedical tasks. Nat. Med. 30(11), 3129\u20133141 (2024). https:\/\/doi.org\/10.1038\/s41591-024-03185-2","journal-title":"Nat. Med."},{"key":"53_CR27","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chiang, W.L., Sheng, Y., Zhuang, S., Wu, Z.: Judging LLM-as-a-judge with MT-Bench and chatbot arena. In: Advances in Neural Information Processing Systems, Datasets and Benchmarks Track, vol. 36 (2023)","DOI":"10.52202\/075280-2020"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38059-3_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:10:40Z","timestamp":1789981840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38059-3_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"ISBN":["9783032380586","9783032380593"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38059-3_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"assertion":[{"value":"22 September 2026","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","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}