Ordinal Diffusion Models for Color Fundus Images

TL;DR

This paper introduces an ordinal latent diffusion model for generating color fundus images that explicitly encodes the ordered progression of diabetic retinopathy, leading to more realistic and clinically consistent image synthesis.

Contribution

The authors propose a novel ordinal diffusion model that incorporates disease severity order into image generation, improving realism and clinical relevance over standard categorical models.

Findings

Reduced Fréchet inception distance across DR stages

Increased quadratic weighted κ from 0.79 to 0.87

Captured continuous disease progression through interpolation

Abstract

It has been suggested that generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat disease stages as independent classes, ignoring the continuous nature of disease progression. This mismatch is problematic in medical imaging because continuous pathological processes are typically only observed through coarse, discrete but ordered labels as in ophthalmology for diabetic retinopathy (DR). We propose an ordinal latent diffusion model for generating color fundus images that explicitly incorporates the ordered structure of DR severity into the generation process. Instead of categorical conditioning, we used a scalar disease representation, enabling a smooth transition between adjacent stages. We evaluated our approach using visual realism metrics and classification-based clinical consistency analysis on the EyePACS dataset. Compared to a standard conditional diffusion model, our model reduced the Fr\'echet inception distance for four of the five DR stages and increased the quadratic weighted $\kappa$ from 0.79 to 0.87. Furthermore, interpolation experiments showed that the model captured a continuous spectrum of disease progression learned from ordered, coarse class labels.