Key result
Deep learning using domain alignment and self-supervised pretraining improves diabetic retinopathy grading over Empirical Risk Minimization.
Why the study?
Deep learning models for diabetic retinopathy grading often falter on out-of-distribution data, impeding their widespread clinical application.
A novel deep learning approach using domain alignment loss and self-supervised pretraining improves domain generalization for diabetic retinopathy grading compared to existing methods.
May enhance automated DR screening across domains; leaves open need for prospective clinical validation.
Diabetic Retinopathy (DR) constitutes 5% of global blindness cases. While numerous deep learning approaches have sought to enhance traditional DR grading methods, they often falter when confronted with new out-of-distribution data thereby impeding their widespread application. In this study, we introduce a novel deep learning method for achieving domain generalization (DG) in DR grading and make the following contributions. First, we propose a new way of generating image-to-image diagnostically relevant fundus augmentations conditioned on the grade of the original fundus image. These augmentations are tailored to emulate the types of shifts in DR datasets thus increase the model's robustness. Second, we address the limitations of the standard classification loss in DG for DR fundus datasets by proposing a new DG-specific loss - domain alignment loss; which ensures that the feature vectors from all domains corresponding to the same class converge onto the same manifold for better domain generalization. Third, we tackle the coupled problem of data imbalance across DR domains and classes by proposing to employ Focal loss which seamlessly integrates with our new alignment loss. Fourth, due to inevitable observer variability in DR diagnosis that induces label noise, we propose leveraging self-supervised pretraining. This approach ensures that our DG model remains robust against early susceptibility to label noise, even when only a limited dataset of non-DR fundus images is available for pretraining. Our method demonstrates significant improvements over the strong Empirical Risk Minimization baseline and other recently proposed state-of-the-art DG methods for DR grading. Code is available at dg-adr.
No takes yet. Share an insight, caveat, or question.
Chokuwa et al. (2025) studied Diabetic Retinopathy. Novel deep learning method for domain generalization vs. Empirical Risk Minimization baseline and state-of-the-art DG methods was evaluated on Diabetic retinopathy grading performance. A novel deep learning method utilizing domain alignment loss and self-supervised pretraining significantly improved diabetic retinopathy grading over the Empirical Risk Minimization baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: