{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T23:26:22Z","timestamp":1793834782861,"version":"4.6.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T00:00:00Z","timestamp":1793750400000},"content-version":"vor","delay-in-days":115,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C03204"],"award-info":[{"award-number":["2024C03204"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFC0118400"],"award-info":[{"award-number":["2019YFC0118400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program of the National Natural Science Foundation of China","award":["82330032"],"award-info":[{"award-number":["82330032"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation Regional Innovation and Development Joint Fund","award":["U20A20386."],"award-info":[{"award-number":["U20A20386."]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02932-8","type":"journal-article","created":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T16:04:05Z","timestamp":1783872245000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A clinician aligned vision language framework for stepwise interpretation in fundus fluorescein angiography"],"prefix":"10.1038","volume":"9","author":[{"given":"Zichang","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaocong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingtao","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"An","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xindi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoling","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"2932_CR1","doi-asserted-by":"publisher","first-page":"104029","DOI":"10.1016\/j.pdpdt.2024.104029","volume":"46","author":"X Shen","year":"2024","unstructured":"Shen, X. et al. Trends in application of fundus fluorescein angiography in fundus diseases during a recent ten-year period. Photodiagnosis Photodyn. Ther. 46, 104029 (2024).","journal-title":"Photodiagnosis Photodyn. Ther."},{"key":"2932_CR2","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s40123-025-01109-y","volume":"14","author":"T Yu","year":"2025","unstructured":"Yu, T. et al. A systematic review of advances in AI-assisted analysis of fundus fluorescein angiography (FFA) images: from detection to report generation. Ophthalmol. Ther. 14, 599\u2013619 (2025).","journal-title":"Ophthalmol. Ther."},{"key":"2932_CR3","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1016\/j.survophthal.2024.03.004","volume":"69","author":"H Nouri","year":"2024","unstructured":"Nouri, H. et al. Optical coherence tomography angiography in diabetic retinopathy: a major review. Surv. Ophthalmol. 69, 558\u2013574 (2024).","journal-title":"Surv. Ophthalmol."},{"key":"2932_CR4","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1080\/09273948.2022.2084421","volume":"31","author":"A Invernizzi","year":"2023","unstructured":"Invernizzi, A. et al. Experts opinion: OCTA vs. FFA\/ICG in uveitis - which will survive?. Ocul. Immunol. Inflamm. 31, 1561\u20131568 (2023).","journal-title":"Ocul. Immunol. Inflamm."},{"key":"2932_CR5","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.ophtha.2023.09.018","volume":"131","author":"ST Berkowitz","year":"2024","unstructured":"Berkowitz, S. T., Finn, A. P., Parikh, R., Kuriyan, A. E. & Patel, S. Ophthalmology workforce projections in the United States, 2020 to 2035. Ophthalmology 131, 133\u2013139 (2024).","journal-title":"Ophthalmology"},{"key":"2932_CR6","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1136\/bjo-2022-321472","volume":"107","author":"Z Gao","year":"2023","unstructured":"Gao, Z. et al. Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning. Br. J. Ophthalmol. 107, 1852\u20131858 (2023).","journal-title":"Br. J. Ophthalmol."},{"key":"2932_CR7","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1002\/mp.14640","volume":"48","author":"Z Tang","year":"2021","unstructured":"Tang, Z. et al. Automated segmentation of retinal nonperfusion area in fluorescein angiography in retinal vein occlusion using convolutional neural networks. Med. Phys. 48, 648\u2013658 (2021).","journal-title":"Med. Phys."},{"key":"2932_CR8","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1038\/s41746-025-01759-z","volume":"8","author":"A Shao","year":"2025","unstructured":"Shao, A. et al. Generative artificial intelligence for fundus fluorescein angiography interpretation and human expert evaluation. npj Digit. Med. 8, 396 (2025).","journal-title":"npj Digit. Med."},{"key":"2932_CR9","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41746-024-01101-z","volume":"7","author":"X Chen","year":"2024","unstructured":"Chen, X. et al. FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer. npj Digit. Med. 7, 111 (2024).","journal-title":"npj Digit. Med."},{"key":"2932_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e33108","volume":"10","author":"S Huang","year":"2024","unstructured":"Huang, S. et al. Automated interpretation of retinal vein occlusion based on fundus fluorescein angiography images using deep learning: a retrospective, multi-center study. Heliyon 10, e33108 (2024).","journal-title":"Heliyon"},{"key":"2932_CR11","doi-asserted-by":"publisher","unstructured":"Dua, R. et al. Clinically grounded agent-based report evaluation: an interpretable metric for radiology report generation. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2508.02808 (2025).","DOI":"10.48550\/ARXIV.2508.02808"},{"key":"2932_CR12","doi-asserted-by":"publisher","first-page":"111798","DOI":"10.1016\/j.ejrad.2024.111798","volume":"181","author":"S Katal","year":"2024","unstructured":"Katal, S., York, B. & Gholamrezanezhad, A. AI in radiology: from promise to practice \u2212 a guide to effective integration. Eur. J. Radiol. 181, 111798 (2024).","journal-title":"Eur. J. Radiol."},{"key":"2932_CR13","doi-asserted-by":"publisher","unstructured":"Kalpelbe, B. C., Adaambiik, A. G. & Peng, W. Vision language models in medicine. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.01863 (2025).","DOI":"10.48550\/arXiv.2503.01863"},{"key":"2932_CR14","doi-asserted-by":"publisher","unstructured":"Li, C. et al. LLaVA-med: training a large language-and-vision assistant for biomedicine in one day. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2306.00890 (2023).","DOI":"10.48550\/arXiv.2306.00890"},{"key":"2932_CR15","doi-asserted-by":"publisher","unstructured":"Jiang, S. et al. Hulu-med: a transparent generalist model towards holistic medical vision-language understanding. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2510.08668 (2025).","DOI":"10.48550\/arXiv.2510.08668"},{"key":"2932_CR16","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.aopr.2025.01.002","volume":"5","author":"T Lin","year":"2025","unstructured":"Lin, T., Lin, R. T., Mhaskar, R. & Margo, C. E. Evaluating the accuracy of advanced language learning models in ophthalmology: a comparative study of ChatGPT-4o and Meta AI\u2019s Llama 3.1. Adv. Ophthalmol. Pract. Res. 5, 95\u201399 (2025).","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"2932_CR17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/s41746-025-01772-2","volume":"8","author":"D Shi","year":"2025","unstructured":"Shi, D. et al. A multimodal visual\u2013language foundation model for computational ophthalmology. npj Digit. Med. 8, 381 (2025).","journal-title":"npj Digit. Med."},{"key":"2932_CR18","doi-asserted-by":"publisher","first-page":"11848","DOI":"10.1109\/TPAMI.2025.3598734","volume":"47","author":"Z Li","year":"2025","unstructured":"Li, Z. et al. VisionUnite: A vision-language foundation model for ophthalmology enhanced with clinical knowledge. IEEE Transactions on Pattern Analysis and Machine Intelligence 47, 11848\u201311862 (2025).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2932_CR19","doi-asserted-by":"publisher","unstructured":"Kim, Y. et al. Medical hallucinations in foundation models and their impact on healthcare. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.05777 (2025).","DOI":"10.48550\/arXiv.2503.05777"},{"key":"2932_CR20","doi-asserted-by":"publisher","unstructured":"Zhu, Z. et al. Can we trust AI doctors? A survey of medical hallucination in large language and large vision-language models. In Proc. Findings of the Association for Computational Linguistics: ACL 2025 (eds Che, W., Nabende, J., Shutova, E. & Pilehvar, M. T.) 6748\u20136769 https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.350 (Association for Computational Linguistics, 2025).","DOI":"10.18653\/v1\/2025.findings-acl.350"},{"key":"2932_CR21","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1038\/s41746-025-01893-8","volume":"8","author":"R Holland","year":"2025","unstructured":"Holland, R. et al. Specialized curricula for training vision language models in retinal image analysis. npj Digit. Med. 8, 532 (2025).","journal-title":"npj Digit. Med."},{"key":"2932_CR22","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1038\/s41746-025-01807-8","volume":"8","author":"Z Zhong","year":"2025","unstructured":"Zhong, Z. et al. Vision-language model for report generation and outcome prediction in CT pulmonary angiogram. npj Digit. Med. 8, 432 (2025).","journal-title":"npj Digit. Med."},{"key":"2932_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q. & Lee, Y. J. Visual instruction tuning. in Advances in neural information processing systems (eds Oh, A. et al.) vol. 36 34892\u201334916 (Curran Associates, Inc., 2023).","DOI":"10.52202\/075280-1516"},{"key":"2932_CR24","doi-asserted-by":"publisher","unstructured":"Bai, S. et al. Qwen2.5-VL technical report. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2502.13923 (2025).","DOI":"10.48550\/arXiv.2502.13923"},{"key":"2932_CR25","doi-asserted-by":"publisher","unstructured":"OpenAI et al. GPT-4o system card. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2410.21276 (2024).","DOI":"10.48550\/arXiv.2410.21276"},{"key":"2932_CR26","doi-asserted-by":"publisher","first-page":"102798","DOI":"10.1016\/j.media.2023.102798","volume":"86","author":"S Yang","year":"2023","unstructured":"Yang, S. et al. Radiology report generation with a learned knowledge base and multi-modal alignment. Med. Image Anal. 86, 102798 (2023).","journal-title":"Med. Image Anal."},{"key":"2932_CR27","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1097\/ICU.0000000000001091","volume":"36","author":"M Sevgi","year":"2025","unstructured":"Sevgi, M., Ruffell, E., Antaki, F., Chia, M. A. & Keane, P. A. Foundation models in ophthalmology: opportunities and challenges. Curr. Opin. Ophthalmol. 36, 90\u201398 (2025).","journal-title":"Curr. Opin. Ophthalmol."},{"key":"2932_CR28","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1136\/bjo-2023-325054","volume":"108","author":"P Xu","year":"2024","unstructured":"Xu, P., Chen, X., Zhao, Z. & Shi, D. Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis. Br. J. Ophthalmol. 108, 1384\u20131389 (2024).","journal-title":"Br. J. Ophthalmol."},{"key":"2932_CR29","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1097\/IAE.0000000000004351","volume":"45","author":"MM Carl\u00e0","year":"2025","unstructured":"Carl\u00e0, M. M., Crincoli, E. & Rizzo, S. RETINAL IMAGING ANALYSIS PERFORMED BY CHATGPT-4o AND GEMINI ADVANCED: the turning point of the revolution?. Retina 45, 694\u2013702 (2025).","journal-title":"Retina"},{"key":"2932_CR30","doi-asserted-by":"publisher","first-page":"e59823","DOI":"10.2196\/59823","volume":"14","author":"D Roustan","year":"2025","unstructured":"Roustan, D. & Bastardot, F. The clinicians\u2019 guide to large language models: a general perspective with a focus on hallucinations. Interact. J. Med. Res. 14, e59823 (2025).","journal-title":"Interact. J. Med. Res."},{"key":"2932_CR31","doi-asserted-by":"publisher","first-page":"100471","DOI":"10.1016\/j.xops.2024.100471","volume":"4","author":"D Chen","year":"2024","unstructured":"Chen, D. et al. Transparency in artificial intelligence reporting in ophthalmology-a scoping review. Ophthalmol. Sci. 4, 100471 (2024).","journal-title":"Ophthalmol. Sci."},{"key":"2932_CR32","doi-asserted-by":"publisher","first-page":"100078","DOI":"10.1016\/j.aopr.2022.100078","volume":"2","author":"K Jin","year":"2022","unstructured":"Jin, K. & Ye, J. Artificial intelligence and deep learning in ophthalmology: current status and future perspectives. Adv. Ophthalmol. Pract. Res. 2, 100078 (2022).","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"2932_CR33","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41746-024-01127-3","volume":"7","author":"L Goetz","year":"2024","unstructured":"Goetz, L., Seedat, N., Vandersluis, R. & Van Der Schaar, M. Generalization\u2014a key challenge for responsible AI in patient-facing clinical applications. npj Digit. Med. 7, 126 (2024).","journal-title":"npj Digit. Med."},{"key":"2932_CR34","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.aopr.2025.07.002","volume":"5","author":"C Liang","year":"2025","unstructured":"Liang, C., Liu, L. & Zhong, J. Multimodal data-driven approaches in retinal vein occlusion: a narrative review integrating machine learning and bioinformatics. Adv. Ophthalmol. Pract. Res. 5, 235\u2013244 (2025).","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"2932_CR35","doi-asserted-by":"publisher","unstructured":"Mangrulkar, S. et al. PEFT: state-of-the-art parameter-efficient fine-tuning methods. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2312.12148 (2022).","DOI":"10.48550\/arXiv.2312.12148"},{"key":"2932_CR36","unstructured":"Hu, E. J. et al. LoRA: low-rank adaptation of large language models. In International Conference on Learning Representations (2022)."},{"key":"2932_CR37","doi-asserted-by":"publisher","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y. & Luo, Z. LlamaFactory: unified efficient fine-tuning of 100+ language models. In Proc. 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) (eds Cao, Y., Feng, Y. & Xiong, D.) 400\u2013410 https:\/\/doi.org\/10.18653\/v1\/2024.acl-demos.38 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"2932_CR38","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770\u2013778 https:\/\/doi.org\/10.1109\/CVPR.2016.90 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2932_CR39","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T. & Zhu, W.-J. Bleu: a method for automatic evaluation of machine translation. In Proc. 40th Annual Meeting of the Association for Computational Linguistics (eds Isabelle, P., Charniak, E. & Lin, D.) 311\u2013318 https:\/\/doi.org\/10.3115\/1073083.1073135 (Association for Computational Linguistics, 2002).","DOI":"10.3115\/1073083.1073135"},{"key":"2932_CR40","unstructured":"Lin, C.-Y. ROUGE: a package for automatic evaluation of summaries. in Text Summarization Branches Out 74\u201381 (Association for Computational Linguistics, Barcelona, Spain, 2004)."},{"key":"2932_CR41","doi-asserted-by":"publisher","unstructured":"Oliveira dos Santos, G., Colombini, E. L. & Avila, S. CIDEr-R: Robust consensus-based image description evaluation. In Proc.Seventh Workshop on Noisy User-generated Text (W-NUT 2021) (eds Xu, W., Ritter, A., Baldwin, T. & Rahimi, A.) 351\u2013360 https:\/\/doi.org\/10.18653\/v1\/2021.wnut-1.39 (Association for Computational Linguistics, Online, 2021).","DOI":"10.18653\/v1\/2021.wnut-1.39"},{"key":"2932_CR42","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. BERTScore: evaluating text generation with BERT. In International Conference on Learning Representations (2020)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02932-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02932-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02932-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T23:06:31Z","timestamp":1793833591000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02932-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2932"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02932-8","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"16 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"848"}}