{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:59:29Z","timestamp":1790276369197,"version":"4.1.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384690","type":"print"},{"value":"9783032384706","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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\/978-3-032-38470-6_16","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:06:18Z","timestamp":1790273178000},"page":"162-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lost in\u00a0Volume: The CT-SpatialVQA Benchmark for\u00a0Evaluating Semantic-Spatial Understanding of\u00a03D Medical Vision\u2013Language Models"],"prefix":"10.1007","author":[{"given":"Mashrafi","family":"Monon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umaima","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asif","family":"Hanif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Numan","family":"Saeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Yaqub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"16_CR1","unstructured":"Alibaba Cloud Model Studio: Qwen-plus (qwen3 series) model listing. https:\/\/www.alibabacloud.com\/help\/en\/model-studio\/models. Accessed 24 Feb 2026"},{"key":"16_CR2","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":"16_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"16_CR4","unstructured":"Blankemeier, L., et al.: Merlin: a vision language foundation model for 3d computed tomography. Research Square pp. rs\u20133 (2024)"},{"key":"16_CR5","unstructured":"Chen, Y., et al.: Are vision language models ready for clinical diagnosis? a 3d medical benchmark for tumor-centric visual question answering. arXiv preprint arXiv:2505.18915 (2025)"},{"key":"16_CR6","unstructured":"Google AI for Developers: Gemini 2.5 flash (model code: gemini-2.5-flash). https:\/\/ai.google.dev\/gemini-api\/docs\/models\/gemini-2.5-flash. Accessed 24 Feb 2026"},{"key":"16_CR7","unstructured":"Google Research: Medgemma 1.5 model card (2026). https:\/\/huggingface.co\/google\/medgemma-1.5-4b-it. Accessed 22 Feb 2026"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Hamamci, I.E., et al.: Generalist foundation models from a multimodal dataset for 3d computed tomography. Nat. Biomed. Engi., 1\u201319 (2026)","DOI":"10.1038\/s41551-025-01599-y"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Imam, R., Marew, R., Yaqub, M.: On the robustness of medical vision-language models: are they truly generalizable? In: Annual Conference on Medical Image Understanding and Analysis, pp. 233\u2013256. Springer (2025)","DOI":"10.1007\/978-3-031-98688-8_17"},{"key":"16_CR10","unstructured":"Imam, R., Wang, H., Mahapatra, D., Yaqub, M.: T3: test-time model merging in VLMS for zero-shot medical imaging analysis. arXiv preprint arXiv:2510.27265 (2025)"},{"key":"16_CR11","unstructured":"Lai, H., et al.: E3d-gpt: enhanced 3d visual foundation for medical vision-language model. arXiv preprint arXiv:2410.14200 (2024)"},{"key":"16_CR12","unstructured":"Lee, C., et al.: Read like a radiologist: efficient vision-language model for 3d medical imaging interpretation. arXiv preprint arXiv:2412.13558 (2024)"},{"key":"16_CR13","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Nath, V., et\u00a0al.: Vila-m3: enhancing vision-language models with medical expert knowledge. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14788\u201314798 (2025)","DOI":"10.1109\/CVPR52734.2025.01378"},{"key":"16_CR15","unstructured":"OpenAI: Gpt-4o model documentation. https:\/\/platform.openai.com\/docs\/models\/gpt-4o. Accessed 24 Feb 2026"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, U., Imam, R., Yaqub, M., Amor, B.B., Mahapatra, D.: Can language-guided unsupervised adaptation improve medical image classification using unpaired images and texts? In: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), pp. 1\u20135. IEEE (2025)","DOI":"10.1109\/ISBI60581.2025.10981057"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Rahman, U., Imam, R., Yaqub, M., Mahapatra, D.: Decoupling clinical and class-agnostic features for reliable few-shot adaptation under shift. In: International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, pp. 123\u2013133. Springer (2025)","DOI":"10.1007\/978-3-032-06593-3_12"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-Bert: sentence embeddings using siamese Bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"16_CR20","unstructured":"Shui, Z., et\u00a0al.: Large-scale and fine-grained vision-language pre-training for enhanced CT image understanding. arXiv preprint arXiv:2501.14548 (2025)"},{"key":"16_CR21","doi-asserted-by":"publisher","first-page":"99947","DOI":"10.52202\/079017-3171","volume":"37","author":"Y Wang","year":"2024","unstructured":"Wang, Y., et al.: Enhancing vision-language models for medical imaging: bridging the 3d gap with innovative slice selection. Adv. Neural. Inf. Process. Syst. 37, 99947\u201399964 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR22","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 (2025). https:\/\/arxiv.org\/abs\/2508.00549","DOI":"10.1007\/978-3-032-04971-1_65"},{"issue":"1","key":"16_CR23","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)","journal-title":"Nat. Commun."},{"key":"16_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"},{"key":"16_CR25","unstructured":"Xu, W., et\u00a0al.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv:2506.07044 (2025)"}],"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\/978-3-032-38470-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:06:35Z","timestamp":1790273195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38470-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032384690","9783032384706"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38470-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 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"}}]}}