Fundus to Fluorescein Angiography Video Generation as a Retinal Generative Foundation Model

TL;DR

Fundus2Video is a novel GAN-based model that generates realistic dynamic fluorescein angiography videos from single color fundus images, offering a non-invasive diagnostic alternative with broad clinical and research applications.

Contribution

The paper introduces Fundus2Video, the first model to generate dynamic FFA videos from static CF images, demonstrating high fidelity and transferability across multiple retinal tasks.

Findings

Achieved an FVD of 1497.12 and PSNR of 11.77 in video generation.

Validated by clinical experts for video fidelity.

Demonstrated zero-shot and few-shot transferability across ten external datasets.

Abstract

Fundus fluorescein angiography (FFA) is crucial for diagnosing and monitoring retinal vascular issues but is limited by its invasive nature and restricted accessibility compared to color fundus (CF) imaging. Existing methods that convert CF images to FFA are confined to static image generation, missing the dynamic lesional changes. We introduce Fundus2Video, an autoregressive generative adversarial network (GAN) model that generates dynamic FFA videos from single CF images. Fundus2Video excels in video generation, achieving an FVD of 1497.12 and a PSNR of 11.77. Clinical experts have validated the fidelity of the generated videos. Additionally, the model's generator demonstrates remarkable downstream transferability across ten external public datasets, including blood vessel segmentation, retinal disease diagnosis, systemic disease prediction, and multimodal retrieval, showcasing impressive zero-shot and few-shot capabilities. These findings position Fundus2Video as a powerful, non-invasive alternative to FFA exams and a versatile retinal generative foundation model that captures both static and temporal retinal features, enabling the representation of complex inter-modality relationships.