{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:37:12Z","timestamp":1763203032077,"version":"3.44.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032051844"},{"type":"electronic","value":"9783032051851"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-05185-1_20","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:47:07Z","timestamp":1758325627000},"page":"198-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Tuning Vision Language Models with\u00a0Graph-Based Knowledge for\u00a0Explainable Medical Image Analysis"],"prefix":"10.1007","author":[{"given":"Chenjun","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurin","family":"Lux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander H.","family":"Berger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin J.","family":"Menten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mert R.","family":"Sabuncu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes C.","family":"Paetzold","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"issue":"2","key":"20_CR1","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1097\/IAE.0000000000002373","volume":"40","author":"M Alam","year":"2020","unstructured":"Alam, M., Zhang, Y., Lim, J.I., Chan, R.V., Yang, M., Yao, X.: Quantitative optical coherence tomography angiography features for objective classification and staging of diabetic retinopathy. Retina 40(2), 322\u2013332 (2020)","journal-title":"Retina"},{"issue":"1","key":"20_CR2","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1038\/s41467-021-23458-5","volume":"12","author":"L Dai","year":"2021","unstructured":"Dai, L., et al.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12(1), 3242 (2021)","journal-title":"Nat. Commun."},{"key":"20_CR3","doi-asserted-by":"publisher","unstructured":"Du, J., et al.: RET-CLIP: a retinal image foundation model pre-trained with clinical diagnostic reports. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15012, pp. 709\u2013719. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72390-2_66","DOI":"10.1007\/978-3-031-72390-2_66"},{"key":"20_CR4","unstructured":"Fan, Z., et al.: Ai hospital: benchmarking large language models in a multi-agent medical interaction simulator. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 10183\u201310213 (2025)"},{"key":"20_CR5","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"20_CR6","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Johnson, A., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports, 2019. 6. https:\/\/doi.org\/10.1038\/s41597-019-0322-0. PMID: https:\/\/wwwncbi.nlm.nih.gov\/pubmed\/31831740 p.\u00a0317","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"6","key":"20_CR8","doi-asserted-by":"publisher","first-page":"2061","DOI":"10.1109\/TMI.2024.3354408","volume":"43","author":"L Kreitner","year":"2024","unstructured":"Kreitner, L., et al.: Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations. IEEE Trans. Med. Imaging 43(6), 2061\u20132073 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Lan, W., Hao, J., Zhou, S., Zhang, J., Ma, S., Zhao, Y.: Hybrid graph representation learning for carotid artery stenosis detection based on multimodal retinal octa images. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3412961"},{"key":"20_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40662-015-0026-2","volume":"2","author":"R Lee","year":"2015","unstructured":"Lee, R., Wong, T.Y., Sabanayagam, C.: Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss. Eye Vis. 2, 1\u201325 (2015)","journal-title":"Eye Vis."},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"20_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103092","volume":"93","author":"M Li","year":"2024","unstructured":"Li, M., et al.: Octa-500: a retinal dataset for optical coherence tomography angiography study. Med. Image Anal. 93, 103092 (2024)","journal-title":"Med. Image Anal."},{"key":"20_CR13","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"20_CR14","unstructured":"Lux, L., et al.: Interpretable retinal disease prediction using biology-informed heterogeneous graph representations (2025). https:\/\/arxiv.org\/abs\/2502.16697"},{"issue":"8","key":"20_CR15","first-page":"5450","volume":"64","author":"MJ Menten","year":"2023","unstructured":"Menten, M.J., et al.: Synthetic data facilitates deep-learning-based segmentation of oct angiography images without human annotations. Investig. Ophthalmol. Vis. Sci. 64(8), 5450\u20135450 (2023)","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"20_CR16","unstructured":"OpenAI: OpenAI o1 (2024). https:\/\/openai.com\/o1\/. Accessed 10 Jan 2025"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Salminen, J., et al.: Using cipherbot: an exploratory analysis of student interaction with an llm-based educational chatbot. In: Proceedings of the Eleventh ACM Conference on Learning@ Scale, pp. 279\u2013283 (2024)","DOI":"10.1145\/3657604.3664690"},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.ajo.2020.01.016","volume":"216","author":"HS Sandhu","year":"2020","unstructured":"Sandhu, H.S., et al.: Automated diagnosis of diabetic retinopathy using clinical biomarkers, optical coherence tomography, and optical coherence tomography angiography. Am. J. Ophthalmol. 216, 201\u2013206 (2020)","journal-title":"Am. J. Ophthalmol."},{"key":"20_CR19","doi-asserted-by":"publisher","unstructured":"Shakeri, F., et al.: Few-shot adaptation of medical vision-language models. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15012, pp. 553\u2013563. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72390-2_52","DOI":"10.1007\/978-3-031-72390-2_52"},{"issue":"1","key":"20_CR20","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1038\/s41433-020-01233-y","volume":"35","author":"Z Sun","year":"2021","unstructured":"Sun, Z., Yang, D., Tang, Z., Ng, D.S., Cheung, C.Y.: Optical coherence tomography angiography in diabetic retinopathy: an updated review. Eye 35(1), 149\u2013161 (2021)","journal-title":"Eye"},{"key":"20_CR21","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017)"},{"issue":"6","key":"20_CR22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0179790","volume":"12","author":"H Takahashi","year":"2017","unstructured":"Takahashi, H., Tampo, H., Arai, Y., Inoue, Y., Kawashima, H.: Applying artificial intelligence to disease staging: deep learning for improved staging of diabetic retinopathy. PLoS ONE 12(6), e0179790 (2017)","journal-title":"PLoS ONE"},{"key":"20_CR23","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Xia, P., et al.: Rule: reliable multimodal rag for factuality in medical vision language models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1081\u20131093 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"20_CR25","unstructured":"Yang, A., et\u00a0al.: Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"20_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, J., Wang, G., Kalra, M.K., Yan, P.: Disease-informed adaptation of vision-language models. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15011, pp. 232\u2013242. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72120-5_22","DOI":"10.1007\/978-3-031-72120-5_22"},{"key":"20_CR27","unstructured":"Zhang, K., et\u00a0al.: A generalist vision\u2013language foundation model for diverse biomedical tasks. Nat. Med. 1\u201313 (2024)"},{"key":"20_CR28","unstructured":"Zhang, S., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv: 2303.00915$$\\textbf{2}(3)$$, 6 (2023)"}],"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\/978-3-032-05185-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:47:16Z","timestamp":1758325636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05185-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051844","9783032051851"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05185-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","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","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}