{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T22:50:16Z","timestamp":1791931816416,"version":"4.3.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_33","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:10:43Z","timestamp":1758377443000},"page":"341-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Localization Lens for\u00a0Improving Medical Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3782-8105","authenticated-orcid":false,"given":"Hasan","family":"Farooq","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2353-4462","authenticated-orcid":false,"given":"Murtaza","family":"Taj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0683-9125","authenticated-orcid":false,"given":"Mehwish","family":"Nasim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5986-9876","authenticated-orcid":false,"given":"Arif","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"33_CR1","unstructured":"SmolLM: Everything about the SmolLM2 and SmolVLM family of models (2024), https:\/\/github.com\/huggingface\/smollm"},{"issue":"9","key":"33_CR2","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","volume":"28","author":"JN Acosta","year":"2022","unstructured":"Acosta, J.N., Falcone, G.J., Rajpurkar, P., Topol, E.J.: Multimodal Biomedical AI. Nat. Med. 28(9), 1773\u20131784 (2022)","journal-title":"Nat. Med."},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Christophe, C., Raha, T., Maslenkova, S., Salman, M.U., Kanithi, P., Pimentel, M.A., Khan, S.: Beyond fine-tuning: Unleashing the potential of continuous pretraining for clinical LLMs. In: Findings of the Association for Computational Linguistics: EMNLP 2024. pp. 10549\u201310561 (Nov 2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.618"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: PubMedCLIP: How much does CLIP benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics. pp. 1151\u20131163 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Frontiers in Artificial Intelligence (2024)","DOI":"10.3389\/frai.2024.1430984"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Huix, J.P., Ganeshan, A.R., Haslum, J.F., S\u00f6derberg, M., Matsoukas, C., Smith, K.: Are natural domain foundation models useful for medical image classification? In: Proc. of the Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00746"},{"key":"33_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111068","volume":"158","author":"H Ibrahem","year":"2025","unstructured":"Ibrahem, H., Salem, A., Kang, H.S.: Pixel shuffling is all you need: spatially aware convmixer for dense prediction tasks. Pattern Recogn. 158, 111068 (2025)","journal-title":"Pattern Recogn."},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, S., Zheng, T., Zhang, Y., Jin, Y., Yuan, L., Liu, Z.: Med-MoE: Mixture of domain-specific experts for lightweight medical vision-language models. In: Findings of the Association for Computational Linguistics: EMNLP 2024. pp. 3843\u20133860 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.221"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., Doll\u00e1r, P.: Segment anything. In: In. Proc. of Int. Conf. on Computer Vision. pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"1","key":"33_CR10","doi-asserted-by":"publisher","first-page":"1","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. Scientific Data 5(1), 1 (2018)","journal-title":"Scientific Data"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., Gao, J.: LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems. vol.\u00a036 (2024)","DOI":"10.52202\/075280-1240"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Vision-language models in medical image analysis: From simple fusion to general large models. Information Fusion (2025)","DOI":"10.1016\/j.inffus.2025.102995"},{"key":"33_CR13","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: Int. Symposium on Biomedical Imaging. pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"33_CR14","unstructured":"Liu, D., et\u00a0al.: SPHINX-x: Scaling data and parameters for a family of multi-modal large language models. In: Proc. of the Int. Conf. on Machine Learning. pp. 32400\u201332420. PMLR (2024),"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nature Communications 15 (2024)","DOI":"10.1038\/s41467-024-44824-z"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Magnini, M., Aguzzi, G., Montagna, S.: Open-source small language models for personal medical assistant chatbots. Intelligence-Based Medicine p. 100197 (2025)","DOI":"10.1016\/j.ibmed.2024.100197"},{"key":"33_CR17","unstructured":"Meta AI: Llama 3.2 vision model card (2024), https:\/\/github.com\/meta-llama\/llama-models\/blob\/main\/models\/llama3_2\/MODEL_CARD_VISION.md"},{"key":"33_CR18","unstructured":"Moor, M., Huang, Q., Wu, S., Yasunaga, M., Dalmia, Y., Leskovec, J., Zakka, C., Reis, E.P., Rajpurkar, P.: Med-Flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health. pp. 353\u2013367. PMLR (2023)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Kaissis, G., Rueckert, D.: ChEX: Interactive Localization and Region Description in Chest X-Rays. In: European Conference on Computer Vision. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-72664-4_6"},{"key":"33_CR20","unstructured":"Pellegrini, C., \u00d6zsoy, E., Busam, B., Navab, N., Keicher, M.: Radialog: A large vision-language model for radiology report generation and conversational assistance. arXiv preprint arXiv:2311.18681 (2023)"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Shakeri, F., et\u00a0al.: Few-shot adaptation of medical vision-language models. In: Medical Image Computing and Computer Assisted Intervention. pp. 553\u2013563 (2024)","DOI":"10.1007\/978-3-031-72390-2_52"},{"key":"33_CR22","unstructured":"Shen, Z., Tao, T., Ma, L., Neiswanger, W., Liu, Z., Wang, H., Tan, B., Hestness, J., Vassilieva, N., Soboleva, D., Xing, E.: SlimPajama-DC: Understanding data combinations for LLM training (2024), https:\/\/arxiv.org\/abs\/2309.10818"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Shi, B., Wu, Z., Mao, M., Wang, X., Darrell, T.: When do we not need larger vision models? In: European Conference on Computer Vision. pp. 444\u2013462. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Sun, J., Chen, K., He, Z., Ren, S., He, X., Liu, X., Peng, C.: Medical image analysis using improved SAM-Med2D: Segmentation and classification perspectives. BMC Medical Imaging 24 (2024)","DOI":"10.1186\/s12880-024-01401-6"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. In: In Proc. of Int. Conf. on Computer Vision and Pattern Recognition. pp. 7433\u20137442 (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Thirunavukarasu, A.J., Ting, D.S., Elangovan, K., Gutierrez, L., Tan, T.F., Ting, D.S.: Large language models in medicine. Nature Medicine pp. 1930\u20131940 (2023)","DOI":"10.1038\/s41591-023-02448-8"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Xue, F., Fu, Y., Zhou, W., Zheng, Z., You, Y.: To repeat or not to repeat: Insights from scaling llm under token-crisis. In: Advances in Neural Information Processing Systems. vol.\u00a036, pp. 59304\u201359322 (2023)","DOI":"10.52202\/075280-2590"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Yeh, C.H., Hong, C.Y., Hsu, Y.C., Liu, T.L., Chen, Y., LeCun, Y.: Decoupled contrastive learning. In: European Conf. on Computer Vision. pp. 668\u2013684 (2022)","DOI":"10.1007\/978-3-031-19809-0_38"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, S., et\u00a0al.: A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs. NEJM AI p. AIoa2400640 (2025)","DOI":"10.1056\/AIoa2400640"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, M., Zhu, Y., Liu, X., Liu, N., Xu, Z., Shen, C., Peng, Y., Ou, Z., Feng, F., Tang, J.: A comprehensive overhaul of multimodal assistant with small language models. In: Proc. of the AAAI Conf. on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v39i10.33194"}],"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\/978-3-032-05114-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T10:07:43Z","timestamp":1790849263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests 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":"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"}}]}}