{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:02:12Z","timestamp":1781881332252,"version":"3.54.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049773","type":"print"},{"value":"9783032049780","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"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\/978-3-032-04978-0_27","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T16:16:45Z","timestamp":1758212205000},"page":"278-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FunBench: Benchmarking Fundus Reading Skills of\u00a0MLLMs"],"prefix":"10.1007","author":[{"given":"Qijie","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiheng","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"issue":"8","key":"27_CR1","first-page":"1858","volume":"38","author":"H Bogunovi\u0107","year":"2019","unstructured":"Bogunovi\u0107, H., Venhuizen, F., et al.: RETOUCH: the retinal OCT fluid detection and segmentation benchmark and challenge. TMI 38(8), 1858\u20131874 (2019)","journal-title":"TMI"},{"issue":"1","key":"27_CR2","doi-asserted-by":"publisher","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","volume":"12","author":"LP Cen","year":"2021","unstructured":"Cen, L.P., et al.: Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks. Nat. Commun. 12(1), 4828 (2021)","journal-title":"Nat. Commun."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Gui, C., et al.: HuatuoGPT-Vision, towards injecting medical visual knowledge into multimodal LLMs at scale. arXiv (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.418"},{"key":"27_CR4","unstructured":"Chen, X., Wu, Z., et\u00a0al.: Janus-Pro: unified multimodal understanding and generation with data and model scaling. arXiv (2025)"},{"key":"27_CR5","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv (2024)"},{"key":"27_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103001","volume":"157","author":"Z Deng","year":"2024","unstructured":"Deng, Z., et al.: OphGLM: an ophthalmology large language-and-vision assistant. Artif. Intell. Med. 157, 103001 (2024)","journal-title":"Artif. Intell. Med."},{"key":"27_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.106532","volume":"81","author":"P Gholami","year":"2020","unstructured":"Gholami, P., Roy, P., Parthasarathy, M.K., Lakshminarayanan, V.: OCTID: Optical coherence tomography image database. Comput. Electr. Eng. 81, 106532 (2020)","journal-title":"Comput. Electr. Eng."},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"He, R., et al.: PitVQA: image-grounded text embedding LLM for visual question answering in pituitary surgery. In: MICCAI (2024)","DOI":"10.1007\/978-3-031-72089-5_46"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Y., Li, T., et al.: OmniMedVQA: a new large-scale comprehensive evaluation benchmark for medical LVLM. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"27_CR10","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv (2024)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Kermany, D.S., Goldbaum, M., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122\u20131131 (2018)","DOI":"10.1016\/j.cell.2018.02.010"},{"issue":"1","key":"27_CR12","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1038\/s41597-024-03182-7","volume":"11","author":"M Kulyabin","year":"2024","unstructured":"Kulyabin, M., Zhdanov, A., et al.: OCTDL: optical coherence tomography dataset for image-based deep learning methods. Sci. Data 11(1), 365 (2024)","journal-title":"Sci. Data"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Lai, X., Li, X., Qian, R., Ding, D., Wu, J., Xu, J.: Four models for automatic recognition of left and right eye in fundus images. In: MMM (2019)","DOI":"10.1007\/978-3-030-05710-7_42"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Li, C., Wong, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. In: NeurIPS (2024)","DOI":"10.32388\/VLXB6M"},{"issue":"10","key":"27_CR15","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1038\/s41591-024-03139-8","volume":"30","author":"J Li","year":"2024","unstructured":"Li, J., Guan, Z., et al.: Integrated image-based deep learning and language models for primary diabetes care. Nat. Med. 30(10), 2886\u20132896 (2024)","journal-title":"Nat. Med."},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Hu, C., Wang, K., Kang, H.: A benchmark of ocular disease intelligent recognition: one shot for multi-disease detection. In: BMO (2021)","DOI":"10.1007\/978-3-030-71058-3_11"},{"key":"27_CR17","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.ins.2019.06.011","volume":"501","author":"T Li","year":"2019","unstructured":"Li, T., Gao, Y., Wang, K., Guo, S., Liu, H., Kang, H.: Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf. Sci. 501, 511\u2013522 (2019)","journal-title":"Inf. Sci."},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"27_CR19","unstructured":"Liu, H., et al.: LLaVA-NeXT: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"27_CR20","unstructured":"Liu, J., Wang, Z., Ye, Q., Chong, D., Zhou, P., Hua, Y.: Qilin-Med-VL: towards Chinese large vision-language model for general healthcare. arXiv (2023)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: DeepDRiD: diabetic retinopathy\u2014grading and image quality estimation challenge. Patterns 3(6) (2022)","DOI":"10.1016\/j.patter.2022.100512"},{"key":"27_CR22","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. J. 1\u201331 (2024)"},{"issue":"2","key":"27_CR23","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/data6020014","volume":"6","author":"S Pachade","year":"2021","unstructured":"Pachade, S., et al.: Retinal fundus multi-disease image dataset (RFMiD): a dataset for multi-disease detection research. Data 6(2), 14 (2021)","journal-title":"Data"},{"issue":"3","key":"27_CR24","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/data3030025","volume":"3","author":"P Porwal","year":"2018","unstructured":"Porwal, P., et al.: Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research. Data 3(3), 25 (2018)","journal-title":"Data"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Qin, Z., et al.: LMOD: a large multimodal ophthalmology dataset and benchmark for large vision-language models. In: NAACL (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.135"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"27_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105368","volume":"144","author":"S Sotoudeh-Paima","year":"2022","unstructured":"Sotoudeh-Paima, S., Jodeiri, A., Hajizadeh, F., Soltanian-Zadeh, H.: Multi-scale convolutional neural network for automated AMD classification using retinal OCT images. Comput. Biol. Med. 144, 105368 (2022)","journal-title":"Comput. Biol. Med."},{"key":"27_CR28","unstructured":"Qwen Team: Qwen2.5-VL (2025). https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Tu, C.H., Mai, Z., Chao, W.L.: Visual query tuning: towards effective usage of intermediate representations for parameter and memory efficient transfer learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"27_CR30","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv (2024)"},{"issue":"8","key":"27_CR31","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1109\/JBHI.2022.3171523","volume":"26","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: Learning two-stream CNN for multi-modal age-related macular degeneration categorization. IEEE J. Biomed. Health Inform. 26(8), 4111\u20134122 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Eyegraphgpt: knowledge graph enhanced multimodal large language model for ophthalmic report generation. In: BIBM (2024)","DOI":"10.1109\/BIBM62325.2024.10822152"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Wei, Q., et al.: Learn to segment retinal lesions and beyond. In: ICPR (2021)","DOI":"10.1109\/ICPR48806.2021.9412088"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Joint localization of optic disc and fovea in ultra-widefield fundus images. In: MLMI@MICCAI (2019)","DOI":"10.1007\/978-3-030-32692-0_52"},{"key":"27_CR35","unstructured":"Ye, J., et al.: GMAI-MMBench: a comprehensive multimodal evaluation benchmark towards general medical AI. In: NeurIPS (2024)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Yeh, C.H., et al.: Insight: a multi-modal diagnostic pipeline using LLMs for ocular surface disease diagnosis. In: MICCAI (2024)","DOI":"10.1007\/978-3-031-72378-0_66"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Incorporating clinical guidelines through adapting multi-modal large language model for prostate cancer PI-RADS scoring. In: MICCAI (2024)","DOI":"10.1007\/978-3-031-72086-4_34"}],"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\/978-3-032-04978-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T22:07:45Z","timestamp":1758233265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04978-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049773","9783032049780"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04978-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors\u00a0have 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"}}]}}