Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy

TL;DR

This paper introduces a controllable, high-fidelity retinal image synthesis framework using conditional StyleGAN and latent space manipulation to enhance diabetic retinopathy detection and grading accuracy.

Contribution

It presents a novel method for generating diverse, controllable retinal images without auxiliary networks, improving dataset quality and classifier performance for diabetic retinopathy.

Findings

ResNet50 achieves over 98% accuracy with real data.

Synthetic images improve DR grading accuracy to 83.33%.

The generated images are highly realistic and enhance classifier robustness.

Abstract

Diabetic retinopathy (DR) is a consequence of diabetes mellitus characterized by vascular damage within the retinal tissue. Timely detection is paramount to mitigate the risk of vision loss. However, training robust grading models is hindered by a shortage of annotated data, particularly for severe cases. This paper proposes a framework for controllably generating high-fidelity and diverse DR fundus images, thereby improving classifier performance in DR grading and detection. We achieve comprehensive control over DR severity and visual features (optic disc, vessel structure, lesion areas) within generated images solely through a conditional StyleGAN, eliminating the need for feature masks or auxiliary networks. Specifically, leveraging the SeFa algorithm to identify meaningful semantics within the latent space, we manipulate the DR images generated conditionally on grades, further enhancing the dataset diversity. Additionally, we propose a novel, effective SeFa-based data augmentation strategy, helping the classifier focus on discriminative regions while ignoring redundant features. Using this approach, a ResNet50 model trained for DR detection achieves 98.09% accuracy, 99.44% specificity, 99.45% precision, and an F1-score of 98.09%. Moreover, incorporating synthetic images generated by conditional StyleGAN into ResNet50 training for DR grading yields 83.33% accuracy, a quadratic kappa score of 87.64%, 95.67% specificity, and 72.24% precision. Extensive experiments conducted on the APTOS 2019 dataset demonstrate the exceptional realism of the generated images and the superior performance of our classifier compared to recent studies.