{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:01:26Z","timestamp":1789984886329,"version":"4.0.1"},"publisher-location":"Cham","reference-count":24,"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_32","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:05:34Z","timestamp":1789981534000},"page":"335-344","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Medical Image Spatial Grounding with\u00a0Semantic Sampling"],"prefix":"10.1007","author":[{"given":"Andrew Seohwan","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Hariri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunio","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingrui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vipin","family":"Chaudhary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"32_CR1","unstructured":"Bai, F., Du, Y., Huang, T., Meng, M.Q.H., Zhao, B.: M3d: advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578 (2024)"},{"key":"32_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"32_CR3","unstructured":"Bai, S., et al.: Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"32_CR4","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"32_CR5","unstructured":"Clark, C., et al.: Molmo2: Open weights and data for vision-language models with video understanding and grounding. arXiv preprint arXiv:2601.10611 (2026)"},{"key":"32_CR6","unstructured":"Gemini Team: Gemini 2.5: Pushing the frontier with advanced reasoning. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"32_CR7","unstructured":"Google DeepMind: Gemini 3 flash (model documentation) (2026). https:\/\/deepmind.google\/models\/gemini\/"},{"key":"32_CR8","unstructured":"Hamamci, I.E., et al.: Developing generalist foundation models from a multimodal dataset for 3d computed tomography. arXiv preprint arXiv:2403.17834 (2024)"},{"key":"32_CR9","unstructured":"Hariri, M., Samandar, A., Hinczewski, M., Chaudhary, V.: Don\u2019t pass@k: a bayesian framework for large language model evaluation. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=PTXi3Ef4sT"},{"key":"32_CR10","unstructured":"Hashmi, A.U.R., Saeed, N., Lippert, C.: Anatomix, an anatomy-aware grounded multimodal large language model for chest x-ray interpretation. arXiv preprint arXiv:2601.03191 (2026)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data, 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"1","key":"32_CR13","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)","journal-title":"Sci. Data"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-llava: learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"32_CR15","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"32_CR16","doi-asserted-by":"publisher","unstructured":"Peterfy, C.G., Schneider, E., Nevitt, M.: The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarthritis Cartilage 16(12), 1433\u20131441 (2008). https:\/\/doi.org\/10.1016\/j.joca.2008.06.016","DOI":"10.1016\/j.joca.2008.06.016"},{"key":"32_CR17","unstructured":"Qwen Team: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"32_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Sambara, S., et al.: 3dreasonknee: advancing grounded reasoning in medical vision language models. In: Biocomputing 2026: Proceedings of the Pacific Symposium, pp. 99\u2013113. World Scientific (2025)","DOI":"10.1142\/9789819824755_0008"},{"key":"32_CR20","unstructured":"Sellergren, A., et al.: Medgemma technical report. arXiv preprint arXiv:2507.05201 (2025)"},{"key":"32_CR21","unstructured":"Wang, P.: Qwen2-vl technical report. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Wasserthal, J., et\u00a0al.: Totalsegmentator: robust segmentation of 104 anatomic structures in CT images. Radiology: Artif. Intell. 5(5), e230024 (2023)","DOI":"10.1148\/ryai.230024"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Wolf, D., Hillenhagen, H., Taskin, B., B\u00e4uerle, A., Beer, M., G\u00f6tz, M., Ropinski, T.: Your other left! vision-language models fail to identify relative positions in medical images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 691\u2013701. Springer, Cham (2025)","DOI":"10.1007\/978-3-032-04971-1_65"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Xin, Y., Ates, G.C., Gong, K., Shao, W.: Med3dvlm: an efficient vision-language model for 3d medical image analysis. IEEE J. Biomed. Health Inform. (2025)","DOI":"10.1109\/JBHI.2025.3604595"}],"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_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:05:51Z","timestamp":1789981551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38059-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"ISBN":["9783032380586","9783032380593"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38059-3_32","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 declare they have no competing interests.","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"}}]}}