Rethinking Diffusion-Based Image Generators for Fundus Fluorescein Angiography Synthesis on Limited Data

TL;DR

This paper introduces a diffusion model-based framework for generating fluorescein angiography images from fundus images, addressing data scarcity and disease variability to improve ophthalmic diagnostics.

Contribution

It presents a novel fine-tuning protocol for diffusion models and a new approach for multi-disease and multi-modality image synthesis in ophthalmology.

Findings

Achieves state-of-the-art results on limited datasets

Effectively generates diverse disease and modality images

Enhances potential for non-invasive eye disease diagnosis

Abstract

Fundus imaging is a critical tool in ophthalmology, with different imaging modalities offering unique advantages. For instance, fundus fluorescein angiography (FFA) can accurately identify eye diseases. However, traditional invasive FFA involves the injection of sodium fluorescein, which can cause discomfort and risks. Generating corresponding FFA images from non-invasive fundus images holds significant practical value but also presents challenges. First, limited datasets constrain the performance and effectiveness of models. Second, previous studies have primarily focused on generating FFA for single diseases or single modalities, often resulting in poor performance for patients with various ophthalmic conditions. To address these issues, we propose a novel latent diffusion model-based framework, Diffusion, which introduces a fine-tuning protocol to overcome the challenge of limited medical data and unleash the generative capabilities of diffusion models. Furthermore, we designed a new approach to tackle the challenges of generating across different modalities and disease types. On limited datasets, our framework achieves state-of-the-art results compared to existing methods, offering significant potential to enhance ophthalmic diagnostics and patient care. Our code will be released soon to support further research in this field.