Fundus to fluorescein angiography video generation as a retinal generative foundation model
Weiyi Zhang, Jiancheng Yang, Ruoyu Chen, Siyu Huang, Pusheng Xu, Xiaolan Chen, Zhenhan Wang, Shanfu Lu, Hongyu Cao, Xianwen Shang, Danli Shi, Mingguang He · 2026
Read Fundus to fluorescein angiography video generation as a retinal generative foundation model by Weiyi Zhang, Jiancheng Yang, Ruoyu Chen, Siyu Huang, Pusheng Xu, Xiaolan Chen, Zhenhan Wang, Shanfu Lu, Hongyu Cao, Xianwen Shang, Danli Shi, Mingguang He (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13562737.txt.
Description
Weiyi Zhang and colleagues built a model that generates retinal angiography videos from a single ordinary eye photograph. Fundus fluorescein angiography, which films dye moving through retinal vessels, is vital for vascular eye disease but invasive and hard to access. Colour fundus photos are cheap and simple, yet static images miss how lesions change over time. Their 2026 model, Fundus2Video, uses a generative network to turn one photo into a moving angiography sequence.
Experts judged the generated videos faithful, and the model transferred across ten external datasets to tasks including vessel segmentation, disease diagnosis, and systemic disease prediction. It also handled new tasks with little or no extra training. The authors present it as a non-invasive alternative to dye angiography and a versatile foundation model for retinal imaging.
Catalog record
| CREATOR | Weiyi Zhang, Jiancheng Yang, Ruoyu Chen, Siyu Huang, Pusheng Xu, Xiaolan Chen, Zhenhan Wang, Shanfu Lu, Hongyu Cao, Xianwen Shang, Danli Shi, Mingguang He |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |