Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance

TL;DR

This paper introduces a novel method for generating dynamic fluorescein angiography videos from static color fundus images using an autoregressive GAN guided by clinical knowledge, improving non-invasive retinal imaging.

Contribution

It pioneers the first dynamic FFA video generation from static fundus images, integrating clinical knowledge masks into a GAN framework for enhanced focus on lesion dynamics.

Findings

Achieved state-of-the-art FVD and PSNR metrics.

Human ophthalmologist evaluation confirms high-quality video generation.

Knowledge masks outperform supervised lesion segmentation masks.

Abstract

Fundus Fluorescein Angiography (FFA) is a critical tool for assessing retinal vascular dynamics and aiding in the diagnosis of eye diseases. However, its invasive nature and less accessibility compared to Color Fundus (CF) images pose significant challenges. Current CF to FFA translation methods are limited to static generation. In this work, we pioneer dynamic FFA video generation from static CF images. We introduce an autoregressive GAN for smooth, memory-saving frame-by-frame FFA synthesis. To enhance the focus on dynamic lesion changes in FFA regions, we design a knowledge mask based on clinical experience. Leveraging this mask, our approach integrates innovative knowledge mask-guided techniques, including knowledge-boosted attention, knowledge-aware discriminators, and mask-enhanced patchNCE loss, aimed at refining generation in critical areas and addressing the pixel misalignment challenge. Our method achieves the best FVD of 1503.21 and PSNR of 11.81 compared to other common video generation approaches. Human assessment by an ophthalmologist confirms its high generation quality. Notably, our knowledge mask surpasses supervised lesion segmentation masks, offering a promising non-invasive alternative to traditional FFA for research and clinical applications. The code is available at https://github.com/Michi-3000/Fundus2Video.