Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks

TL;DR

This paper introduces an attention-based GAN that synthesizes Fluorescein Angiography images from retinal fundus photos, offering a non-invasive alternative to traditional dye-based imaging with high realism.

Contribution

The novel GAN architecture with attention mechanisms and residual blocks significantly improves fundus-to-angiogram translation quality over existing methods.

Findings

Outperforms recent state-of-the-art models in realism and accuracy.

Produces highly realistic angiograms indistinguishable from real images.

Reduces the need for invasive dye injections in retinal imaging.

Abstract

Fluorescein Angiography (FA) is a technique that employs the designated camera for Fundus photography incorporating excitation and barrier filters. FA also requires fluorescein dye that is injected intravenously, which might cause adverse effects ranging from nausea, vomiting to even fatal anaphylaxis. Currently, no other fast and non-invasive technique exists that can generate FA without coupling with Fundus photography. To eradicate the need for an invasive FA extraction procedure, we introduce an Attention-based Generative network that can synthesize Fluorescein Angiography from Fundus images. The proposed gan incorporates multiple attention based skip connections in generators and comprises novel residual blocks for both generators and discriminators. It utilizes reconstruction, feature-matching, and perceptual loss along with adversarial training to produces realistic Angiograms that is hard for experts to distinguish from real ones. Our experiments confirm that the proposed architecture surpasses recent state-of-the-art generative networks for fundus-to-angio translation task.