Diabetic retinopathy (DR) is caused by long-standing diabetes and is among the fifth leading cause for visual impairments. The process of early diagnosis and treatments could be helpful in curing the disease, however, the detection procedure is rather challenging and mostly tedious. Therefore, automated diabetic retinopathy classification using deep learning techniques has gained interest in the medical imaging community. Akin to several other real-world applications of deep learning, the typical assumption of i.i.d data is also violated in DR classification that relies on deep learning. Therefore, developing DR classification methods robust to unseen distributions is of great value. In this paper, we study the problem of generalizing a model to unseen distributions or domains (a.k.a domain generalization) in DR classification. To this end, we propose a simple and effective domain generalization (DG) approach that achieves self-distillation in vision transformers (ViT) via a novel prediction softening mechanism. This prediction softening is an adaptive convex combination one-hot labels with the model's own knowledge. We perform extensive experiments on challenging open-source DR classification datasets under both multi-source and single-source DG settings with three different ViT backbones to establish the efficacy and applicability of our approach against competing methods. For the first time, we report the performance of several state-of-the-art DG methods on open-source DR classification datasets after conducting thorough experiments. Finally, our method is also capable of delivering improved calibration performance than other methods, showing its suitability for safety-critical applications, including healthcare. We hope that our contributions would investigate more DG research across the medical imaging community.

翻译：糖尿病视网膜病变（DR）由长期糖尿病引起，是导致视觉障碍的第五大原因。早期诊断与治疗有助于缓解病情，然而检测过程极具挑战且通常繁琐耗时。因此，基于深度学习的自动化糖尿病视网膜病变分类方法引起了医学影像领域的广泛关注。与深度学习其他现实应用类似，依赖深度学习的DR分类也违反了数据独立同分布（i.i.d）的典型假设。因此，开发对未见分布具有鲁棒性的DR分类方法具有重要价值。本文研究DR分类中模型对未见分布或领域（即领域泛化）的泛化问题。为此，我们提出一种简单有效的领域泛化方法，通过新颖的预测软化机制实现视觉Transformer（ViT）中的自蒸馏。该预测软化将独热标签与模型自身知识进行自适应凸组合。我们在多源和单源领域泛化设置下，基于三种不同ViT骨干网络，对多个开源DR分类数据集进行了大量实验，验证了所提方法相比竞争方法的有效性与适用性。首次通过充分实验，报告了多种前沿领域泛化方法在开源DR分类数据集上的性能表现。此外，我们的方法在标定性能上优于其他方法，表明其适用于包括医疗在内的安全关键应用。期望我们的贡献能推动医学影像领域领域泛化研究的进一步发展。