Source-free Active Domain Adaptation for Diabetic Retinopathy Grading Based on Ultra-wide-field Fundus Image

TL;DR

This paper introduces a novel source-free active domain adaptation method for diabetic retinopathy grading using ultra-wide-field fundus images, addressing domain gaps and privacy concerns to improve clinical accuracy.

Contribution

The proposed SFADA method actively selects and labels UWF fundus images, generating evolving features and adapting models with lesion prototypes, enhancing DR grading performance.

Findings

Achieves 20.9% higher accuracy over baseline

Reaches 85.36% accuracy and 92.38% kappa

Demonstrates state-of-the-art performance in DR grading

Abstract

Domain adaptation (DA) has been widely applied in the diabetic retinopathy (DR) grading of unannotated ultra-wide-field (UWF) fundus images, which can transfer annotated knowledge from labeled color fundus images. However, suffering from huge domain gaps and complex real-world scenarios, the DR grading performance of most mainstream DA is far from that of clinical diagnosis. To tackle this, we propose a novel source-free active domain adaptation (SFADA) in this paper. Specifically, we focus on DR grading problem itself and propose to generate features of color fundus images with continuously evolving relationships of DRs, actively select a few valuable UWF fundus images for labeling with local representation matching, and adapt model on UWF fundus images with DR lesion prototypes. Notably, the SFADA also takes data privacy and computational efficiency into consideration. Extensive experimental results demonstrate that our proposed SFADA achieves state-of-the-art DR grading performance, increasing accuracy by 20.9% and quadratic weighted kappa by 18.63% compared with baseline and reaching 85.36% and 92.38% respectively. These investigations show that the potential of our approach for real clinical practice is promising.