{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:12:26Z","timestamp":1789081946700,"version":"build-2803163510"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":97,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Hong Kong Polytechnic University","award":["P0048623"],"award-info":[{"award-number":["P0048623"]}]},{"name":"Hong Kong Polytechnic University","award":["P0048623"],"award-info":[{"award-number":["P0048623"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02804-1","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T03:35:01Z","timestamp":1780716901000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fundus to fluorescein angiography video generation as a retinal generative foundation model"],"prefix":"10.1038","volume":"9","author":[{"given":"Weiyi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pusheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanfu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianwen","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danli","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingguang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"2804_CR1","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.survophthal.2019.02.004","volume":"64","author":"IS Kornblau","year":"2019","unstructured":"Kornblau, I. S. & El-Annan, J. F. Adverse reactions to fluorescein angiography: A comprehensive review of the literature. Surv. Ophthalmol. 64, 679\u2013693 (2019).","journal-title":"Surv. Ophthalmol."},{"key":"2804_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2023.100401","volume":"3","author":"D Shi","year":"2023","unstructured":"Shi, D. et al. Translation of Color Fundus photography into fluorescein angiography using deep learning for enhanced diabetic retinopathy screening. Ophthalmol. Sci. 3, 100401 (2023).","journal-title":"Ophthalmol. Sci."},{"key":"2804_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01018-7","volume":"7","author":"R Chen","year":"2024","unstructured":"Chen, R. et al. Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening. NPJ Digit. Med. 7, 34 (2024).","journal-title":"NPJ Digit. Med."},{"key":"2804_CR4","doi-asserted-by":"crossref","unstructured":"Chen, R. et al. Noninvasive synthesis of multi-frame ultrawide-field fluorescein angiography from color fundus photographs. Ophthalmol. Retina 10, 176\u2013184 (2026).","DOI":"10.1016\/j.oret.2025.08.002"},{"key":"2804_CR5","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.aopr.2023.11.001","volume":"3","author":"F Song","year":"2023","unstructured":"Song, F., Zhang, W., Zheng, Y., Shi, D. & He, M. A deep learning model for generating fundus autofluorescence images from color fundus photography. Adv. Ophthalmol. Pract. Res. 3, 192\u2013198 (2023).","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"2804_CR6","doi-asserted-by":"publisher","DOI":"10.1186\/s40662-022-00277-3","volume":"9","author":"A You","year":"2022","unstructured":"You, A., Kim, J. K., Ryu, I. H. & Yoo, T. K. Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey. Eye Vis. 9, 6 (2022).","journal-title":"Eye Vis."},{"key":"2804_CR7","doi-asserted-by":"publisher","first-page":"2666","DOI":"10.1002\/mrm.28912","volume":"86","author":"V Ghodrati","year":"2021","unstructured":"Ghodrati, V. et al. Temporally aware volumetric generative adversarial network-based MR image reconstruction with simultaneous respiratory motion compensation: Initial feasibility in 3D dynamic cine cardiac MRI. Magn. Reson. Med. 86, 2666\u20132683 (2021).","journal-title":"Magn. Reson. Med."},{"key":"2804_CR8","unstructured":"Vukadinovic, M., Kwan, A. C., Li, D. & Ouyang, D. GANcMRI: Cardiac magnetic resonance video generation and physiologic guidance using latent space prompting. In Machine Learning for Health (ML4H) 594\u2013606 (PMLR, 2023)."},{"key":"2804_CR9","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1001\/jamaophthalmol.2025.1419","volume":"143","author":"X Wu","year":"2025","unstructured":"Wu, X. et al. Generation of fundus fluorescein angiography videos for health care data sharing. JAMA Ophthalmol. 143, 623\u2013632 (2025).","journal-title":"JAMA Ophthalmol."},{"key":"2804_CR10","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":"2804_CR11","doi-asserted-by":"publisher","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":"2804_CR12","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M. et al. Foundation models for generalist medical artificial intelligence. Nature 616, 259\u2013265 (2023).","journal-title":"Nature"},{"key":"2804_CR13","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","volume":"622","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y. et al. A foundation model for generalizable disease detection from retinal images. Nature 622, 156\u2013163 (2023).","journal-title":"Nature"},{"key":"2804_CR14","unstructured":"Shi, D. et al. EyeFound: a multimodal generalist foundation model for ophthalmic imaging. arXiv preprint arXiv:2405.11338 (2024)."},{"key":"2804_CR15","doi-asserted-by":"publisher","first-page":"AIoa2300221","DOI":"10.1056\/AIoa2300221","volume":"1","author":"J Qiu","year":"2024","unstructured":"Qiu, J. et al. Development and validation of a multimodal multitask vision foundation model for generalist ophthalmic artificial intelligence. NEJM AI 1, AIoa2300221 (2024).","journal-title":"NEJM AI"},{"key":"2804_CR16","doi-asserted-by":"publisher","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":"2804_CR17","doi-asserted-by":"publisher","first-page":"103357","DOI":"10.1016\/j.media.2024.103357","volume":"99","author":"J Silva-Rodriguez","year":"2025","unstructured":"Silva-Rodriguez, J., Chakor, H., Kobbi, R., Dolz, J. & Ayed, I. B. A foundation language-image model of the retina (flair): Encoding expert knowledge in text supervision. Med. Image Anal. 99, 103357 (2025).","journal-title":"Med. Image Anal."},{"key":"2804_CR18","unstructured":"Cheng, D. et al. SAM on medical images: a comprehensive study on three prompt modes. arXiv preprint arXiv:2305.00035 (2023)."},{"key":"2804_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01852-3","volume":"8","author":"J Morano","year":"2025","unstructured":"Morano, J. et al. Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis. NPJ Digit. Med. 8, 576 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2804_CR20","doi-asserted-by":"crossref","unstructured":"Pan, J. et al. Video generation from single semantic label map. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 3733\u20133742 (2019).","DOI":"10.1109\/CVPR.2019.00385"},{"key":"2804_CR21","doi-asserted-by":"crossref","unstructured":"Dorjsembe, Z., Pao, H.-K., Odonchimed, S. & Xiao, F. Conditional diffusion models for semantic 3D brain MRI synthesis. IEEE J. Biomed. Health Inform. 28, 4084\u20134093 (2024).","DOI":"10.1109\/JBHI.2024.3385504"},{"key":"2804_CR22","unstructured":"Ren, W. et al. Consisti2v: Enhancing visual consistency for image-to-video generation. arXiv preprint arXiv:2402.04324 (2024)."},{"key":"2804_CR23","doi-asserted-by":"crossref","unstructured":"Henschel, R. et al. Streamingt2v: Consistent, dynamic, and extendable long video generation from text. In Proc. Computer Vision and Pattern Recognition Conference 2568\u20132577 (2025).","DOI":"10.1109\/CVPR52734.2025.00245"},{"key":"2804_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, 25 (2018).","journal-title":"Data"},{"key":"2804_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01388-1","volume":"9","author":"O Kovalyk","year":"2022","unstructured":"Kovalyk, O. et al. PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment. Sci. Data 9, 291 (2022).","journal-title":"Sci. Data"},{"key":"2804_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25138-w","volume":"12","author":"L-P 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, 4828 (2021).","journal-title":"Nat. Commun."},{"key":"2804_CR27","doi-asserted-by":"publisher","first-page":"e025077","DOI":"10.1136\/bmjopen-2018-025077","volume":"9","author":"SYL Chua","year":"2019","unstructured":"Chua, S. Y. L. et al. Cohort profile: design and methods in the eye and vision consortium of UK Biobank. BMJ Open 9, e025077 (2019).","journal-title":"BMJ Open"},{"key":"2804_CR28","first-page":"436","volume":"16","author":"Q Hu","year":"2013","unstructured":"Hu, Q., Abramoff, M. D. & Garvin, M. K. Automated separation of binary overlapping trees in low-contrast color retinal images. Med. Image Comput Comput. Assist. Inter. 16, 436\u2013443 (2013).","journal-title":"Med. Image Comput Comput. Assist. Inter."},{"key":"2804_CR29","doi-asserted-by":"crossref","unstructured":"Wang, T.-C. et al. High-resolution image synthesis and semantic manipulation with conditional GANs. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8798\u20138807 (2018).","DOI":"10.1109\/CVPR.2018.00917"},{"key":"2804_CR30","unstructured":"Zhu, J., Hamdi, A., Qi, Y., Jin, Y. & Wu, J. Medical Sam 2: Segment medical images as video via segment anything model 2. arXiv preprint arXiv:2408.00874 (2024)."},{"key":"2804_CR31","doi-asserted-by":"publisher","first-page":"e0207982","DOI":"10.1371\/journal.pone.0207982","volume":"13","author":"JM Ahn","year":"2018","unstructured":"Ahn, J. M. et al. A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PloS One 13, e0207982 (2018).","journal-title":"PloS One"},{"key":"2804_CR32","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1136\/bjo-2024-327006","volume":"109","author":"P Xu","year":"2025","unstructured":"Xu, P. et al. AngioReport: dataset and baseline methods for fundus angiography report generation. Br. J. Ophthalmol. 109, 1283\u20131288 (2025).","journal-title":"Br. J. Ophthalmol."},{"key":"2804_CR33","unstructured":"Retina Image Bank, available at https:\/\/imagebank.asrs.org\/."},{"key":"2804_CR34","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/S2213-8587(18)30128-1","volume":"7","author":"C Sabanayagam","year":"2019","unstructured":"Sabanayagam, C. et al. Incidence and progression of diabetic retinopathy: a systematic review. Lancet Diab Endocrinol. 7, 140\u2013149 (2019).","journal-title":"Lancet Diab Endocrinol."},{"key":"2804_CR35","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1001\/jama.2020.21899","volume":"325","author":"JD Stein","year":"2021","unstructured":"Stein, J. D., Khawaja, A. P. & Weizer, J. S. Glaucoma in adults-screening, diagnosis, and management: a review. JAMA 325, 164\u2013174 (2021).","journal-title":"JAMA"},{"key":"2804_CR36","doi-asserted-by":"publisher","first-page":"100363","DOI":"10.1016\/j.xops.2023.100363","volume":"4","author":"D Shi","year":"2024","unstructured":"Shi, D., He, S., Yang, J., Zheng, Y. & He, M. One-shot retinal artery and vein segmentation via cross-modality pretraining. Ophthalmol. Sci. 4, 100363 (2024).","journal-title":"Ophthalmol. Sci."},{"key":"2804_CR37","unstructured":"Wu, B. et al. Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)."},{"key":"2804_CR38","doi-asserted-by":"crossref","unstructured":"Liu, X. et al. Toward the unification of generative and discriminative visual foundation model: a survey. Visual Comput. 41, 3371\u20133412 (2024).","DOI":"10.1007\/s00371-024-03608-8"},{"key":"2804_CR39","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.maturitas.2022.05.002","volume":"163","author":"SS Lee","year":"2022","unstructured":"Lee, S. S. & Mackey, D. A. Glaucoma - risk factors and current challenges in the diagnosis of a leading cause of visual impairment. Maturitas 163, 15\u201322 (2022).","journal-title":"Maturitas"},{"key":"2804_CR40","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1136\/bjophthalmol-2016-308823","volume":"101","author":"P Tanna","year":"2017","unstructured":"Tanna, P., Strauss, R. W., Fujinami, K. & Michaelides, M. Stargardt disease: clinical features, molecular genetics, animal models and therapeutic options. Br. J. Ophthalmol. 101, 25\u201330 (2017).","journal-title":"Br. J. Ophthalmol."},{"key":"2804_CR41","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1016\/S0140-6736(11)61137-9","volume":"379","author":"H Dimaras","year":"2012","unstructured":"Dimaras, H. et al. Retinoblastoma. Lancet 379, 1436\u20131446 (2012).","journal-title":"Lancet"},{"key":"2804_CR42","doi-asserted-by":"crossref","unstructured":"Li, F., Hu, Z., Chen, W. & Kak, A. Adaptive supervised patchnce loss for learning h&e-to-ihc stain translation with inconsistent groundtruth image pairs. In International Conference on Medical Image Computing and Computer-Assisted Intervention 632\u2013641 (Springer, 2023).","DOI":"10.1007\/978-3-031-43987-2_61"},{"key":"2804_CR43","unstructured":"Unterthiner, T. et al. FVD: A new metric for video generation. In DeepGenStruct Workshop at ICLR (2019)."},{"key":"2804_CR44","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004).","journal-title":"IEEE Trans. Image Process."},{"key":"2804_CR45","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q. & Ghanbari, M. Scope of validity of PSNR in image\/video quality assessment. Electron. Lett. 44, 800\u2013801 (2008).","journal-title":"Electron. Lett."},{"key":"2804_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E. & Wang, O. The unreasonable effectiveness of deep features as a perceptual metric. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 586\u2013595 (2018).","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2804_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, W. et al. Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance. In International Conference on Medical Image Computing and Computer-Assisted Intervention 689\u2013699 (Springer, 2024).","DOI":"10.1007\/978-3-031-72378-0_64"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02804-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02804-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02804-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:57:25Z","timestamp":1789081045000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02804-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2804"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02804-1","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"2 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A patent application has been filed pertaining to the results presented in this paper. The patent (Application No.: CN 202410360491.4) is pending with The Hong Kong Polytechnic University as the applicant, and Mingguang He, Danli Shi as inventors. The patent relates to the cross-modality generative method and its applications described in this manuscript. Jiancheng Yang is an Editorial Board Member of\n                      npj Digital Medicine\n                      . He was not involved in the peer review or decision-making process for this manuscript. The remaining authors declare no competing financial or non-financial interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"696"}}