AdvBlur: Adversarial Blur for Robust Diabetic Retinopathy Classification and Cross-Domain Generalization
This addresses the challenge of domain generalization for diabetic retinopathy detection, which is crucial for early treatment but often hindered by distributional variations, though it appears incremental as it builds on existing domain generalization approaches.
The paper tackled the problem of maintaining robustness in diabetic retinopathy classification across different imaging conditions by proposing AdvBlur, a method that integrates adversarial blurred images and a dual-loss function, achieving competitive performance on unseen external datasets.
Diabetic retinopathy (DR) is a leading cause of vision loss worldwide, yet early and accurate detection can significantly improve treatment outcomes. While numerous Deep learning (DL) models have been developed to predict DR from fundus images, many face challenges in maintaining robustness due to distributional variations caused by differences in acquisition devices, demographic disparities, and imaging conditions. This paper addresses this critical limitation by proposing a novel DR classification approach, a method called AdvBlur. Our method integrates adversarial blurred images into the dataset and employs a dual-loss function framework to address domain generalization. This approach effectively mitigates the impact of unseen distributional variations, as evidenced by comprehensive evaluations across multiple datasets. Additionally, we conduct extensive experiments to explore the effects of factors such as camera type, low-quality images, and dataset size. Furthermore, we perform ablation studies on blurred images and the loss function to ensure the validity of our choices. The experimental results demonstrate the effectiveness of our proposed method, achieving competitive performance compared to state-of-the-art domain generalization DR models on unseen external datasets.