Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR.

翻译：糖尿病视网膜病变（DR）是最常见的糖尿病并发症，常导致视网膜损伤、视力下降甚至失明。计算机辅助的DR分级系统对协助眼科医生进行快速筛查和诊断具有重要意义。眼底照相技术的进步推动了新型视网膜成像相机的研发及其在临床实践中的应用。然而，大多数基于深度学习的DR分级算法在跨领域泛化方面表现有限。这种性能缺陷源于成像协议与设备差异引发的领域偏移。我们认为，领域间模型性能下降的原因是模型学习了数据中的虚假关联。将因果分析中的do算子融入模型架构可缓解此问题并提升泛化能力。具体而言，本文提出了一种新颖的通用结构因果模型（SCM）以分析眼底成像中的虚假关联，并在此基础上开发了名为CauDR的因果启发式糖尿病视网膜病变分级框架，旨在消除虚假关联并实现更具泛化性的DR诊断。此外，现有数据集被重组为面向领域泛化（DG）场景的4DR基准。实验结果表明了CauDR的有效性及其最先进（SOTA）性能。