{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:01:59Z","timestamp":1789984919182,"version":"4.0.1"},"publisher-location":"Cham","reference-count":30,"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_33","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:11:15Z","timestamp":1789981875000},"page":"345-355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Chemical structure of a molecule featuring a central ring with alternating single and double bonds, connected to various side groups including a nitrogen atom bonded to a methyl group, a hydroxyl group, and a carboxyl group. The image highlights the arrangement of atoms and bonds to show the molecule\u2019s shape and functional parts important for its chemical behavior. MedObvious: Exposing the\u00a0Medical Moravec\u2019s Paradox in\u00a0VLMs via\u00a0Clinical Triage"],"prefix":"10.1007","author":[{"given":"Ufaq","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umair","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lekkala","family":"Sai Teja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Numan","family":"Saeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Bilal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Yaqub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Haris","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"33_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"33_CR2","unstructured":"Agrawal, K.: To study the phenomenon of the Moravec\u2019s paradox. arXiv preprint arXiv:1012.3148 (2010)"},{"key":"33_CR3","unstructured":"Agrawal, P., et al.: Pixtral 12b. arXiv preprint arXiv:2410.07073 (2024)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"33_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"33_CR6","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes. 9-12 September 2019 (2019)"},{"key":"33_CR7","unstructured":"Chen, J., et al.: Detecting and evaluating medical hallucinations in large vision language models. arXiv preprint arXiv:2406.10185 (2024)"},{"key":"33_CR8","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Dahou, Y., Huynh, N.D., Le-Khac, P.H., Para, W.R., Singh, A., Narayan, S.: Vision-language models can\u2019t see the obvious. arXiv preprint arXiv:2507.04741 (2025)","DOI":"10.1109\/ICCV51701.2025.02239"},{"key":"33_CR10","unstructured":"Fallahpour, A., Ma, J., Munim, A., Lyu, H., Wang, B.: Medrax: medical reasoning agent for chest x-ray. arXiv preprint arXiv:2502.02673 (2025)"},{"issue":"9","key":"33_CR11","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","volume":"30","author":"A Fedorov","year":"2012","unstructured":"Fedorov, A., et al.: 3d slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323\u20131341 (2012)","journal-title":"Magn. Reson. Imaging"},{"key":"33_CR12","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":"33_CR13","unstructured":"Jiang, S., et al.: Omniv-med: scaling medical vision-language model for universal visual understanding. arXiv preprint arXiv:2504.14692 (2025)"},{"issue":"1","key":"33_CR14","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":"33_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, vol. 36, pp. 28541\u201328564 (2023)","DOI":"10.52202\/075280-1240"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: Showui: one vision-language-action model for GUI visual agent. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19498\u201319508 (2025)","DOI":"10.1109\/CVPR52734.2025.01816"},{"key":"33_CR17","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":"33_CR18","unstructured":"Liu, C., Li, D., Shu, Y., Chen, R., Duan, D., Fang, T., Dai, B.: Fleming-r1: toward expert-level medical reasoning via reinforcement learning. arXiv preprint arXiv:2509.15279 (2025)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern RecognitionD pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"33_CR21","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":"33_CR22","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Medvlm-r1: incentivizing medical reasoning capability of vision-language models (VLMs) via reinforcement learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 337\u2013347. Springer (2025)","DOI":"10.1007\/978-3-032-04981-0_32"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., Friedrich, C.M.: Radiology objects in context (ROCO): a multimodal image dataset. In: Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, pp. 180\u2013189. Springer, Cham (2018)","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Pogorelov, K., et\u00a0al.: Kvasir: a multi-class image dataset for computer aided gastrointestinal disease detection. In: Proceedings of the 8th ACM on Multimedia Systems Conference, pp. 164\u2013169 (2017)","DOI":"10.1145\/3083187.3083212"},{"key":"33_CR25","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)"},{"issue":"1","key":"33_CR26","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","volume":"16","author":"C Wu","year":"2025","unstructured":"Wu, C., et al.: 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":"33_CR27","doi-asserted-by":"crossref","unstructured":"Xu, W., et\u00a0al.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv:2506.07044 (2025)","DOI":"10.1109\/TPAMI.2026.3730310"},{"issue":"3","key":"33_CR28","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","volume":"31","author":"PA Yushkevich","year":"2006","unstructured":"Yushkevich, P.A., et al.: User-guided 3d active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116\u20131128 (2006)","journal-title":"Neuroimage"},{"key":"33_CR29","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"33_CR30","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (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\/978-3-032-38059-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:11:33Z","timestamp":1789981893000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38059-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"ISBN":["9783032380586","9783032380593"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38059-3_33","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"}}]}}