Enhancing Early Diabetic Retinopathy Detection through Synthetic DR1 Image Generation: A StyleGAN3 Approach

TL;DR

This paper demonstrates that StyleGAN3 can generate highly realistic synthetic DR1 fundus images, which can augment training datasets and improve early diabetic retinopathy detection accuracy.

Contribution

The study introduces a novel application of StyleGAN3 for generating diverse, high-fidelity synthetic DR1 images to address data scarcity in diabetic retinopathy detection.

Findings

StyleGAN3 achieved a FID score of 17.29, outperforming baseline metrics.

Human ophthalmologists rated synthetic images as highly realistic.

Synthetic images effectively augment datasets for improved classifier performance.

Abstract

Diabetic Retinopathy (DR) is a leading cause of preventable blindness. Early detection at the DR1 stage is critical but is hindered by a scarcity of high-quality fundus images. This study uses StyleGAN3 to generate synthetic DR1 images characterized by microaneurysms with high fidelity and diversity. The aim is to address data scarcity and enhance the performance of supervised classifiers. A dataset of 2,602 DR1 images was used to train the model, followed by a comprehensive evaluation using quantitative metrics, including Frechet Inception Distance (FID), Kernel Inception Distance (KID), and Equivariance with respect to translation (EQ-T) and rotation (EQ-R). Qualitative assessments included Human Turing tests, where trained ophthalmologists evaluated the realism of synthetic images. Spectral analysis further validated image quality. The model achieved a final FID score of 17.29, outperforming the mean FID of 21.18 (95 percent confidence interval - 20.83 to 21.56) derived from bootstrap resampling. Human Turing tests demonstrated the model's ability to produce highly realistic images, though minor artifacts near the borders were noted. These findings suggest that StyleGAN3-generated synthetic DR1 images hold significant promise for augmenting training datasets, enabling more accurate early detection of Diabetic Retinopathy. This methodology highlights the potential of synthetic data in advancing medical imaging and AI-driven diagnostics.