PARAGraph：面向糖尿病视网膜病变分级的病理-解剖感知分层图
PARAGraph: Pathology-Anatomy-Aware Hierarchical Graph for Diabetic Retinopathy Grading
浏览论文内容
中文总结 AI 辅助
提出病理-解剖感知分层图框架PARAGraph，以三级分层图建模DR分级，在多数据集上实现优于现有方法的性能，预测具临床依据且对分割噪声鲁棒。
中文摘要 AI 辅助
糖尿病视网膜病变（DR）仍是全球劳动年龄成年人视力丧失的主要原因，因此可靠的严重程度分级具有重要临床意义。尽管深度模型性能强劲，但多数模型将DR分级视为图像级分类任务，未明确建模基于临床依据的证据，如病变类型与空间关系。本文提出PARAGraph，一种面向DR分级的病理-解剖感知分层图框架。PARAGraph将每张图像表示为三级分层图，包含病变级节点、中间类别与区域节点、全局解剖与语义节点。为将医学先验融入节点，我们构建了以视盘-黄斑为锚点的坐标系，提供了尺度与旋转归一化的视网膜参考系统。在该框架内，病变节点被编码为类别、归一化面积及解剖坐标。为缓解病变分割的噪声问题，PARAGraph采用双融合策略，将全局视觉上下文引入图语义节点与决策级预测分支，提升病变证据不可靠时的鲁棒性。在Messidor-2、APTOS与DDR数据集上开展的大量实验表明，PARAGraph相较于现有最优方法实现了一致的DR分级性能。可解释性与鲁棒性分析进一步证明，其预测具有临床依据，与病变证据密切相关，且对病变分割噪声具有鲁棒性。
英文摘要
Diabetic retinopathy (DR) remains a leading cause of vision loss among working-age adults worldwide, making reliable severity grading clinically important. Despite strong performance, most deep models formulate DR grading as image-level classification and do not explicitly model clinically grounded evidence, such as lesion types and spatial relations. In this paper, we propose PARAGraph, a Pathology-Anatomy-Aware Hierarchical Graph framework for DR grading. PARAGraph represents each image as a three-level hierarchical graph with lesion-level nodes, intermediate category and region nodes, and global anatomical and semantic nodes. To incorporate medical priors into nodes, we construct an optic disc-fovea-anchored coordinate frame that provides a scale- and rotation-normalized retinal reference system. Within this frame, lesion nodes are encoded with category, normalized area, and anatomical coordinates. To mitigate noisy lesion segmentation, PARAGraph uses a dual-fusion strategy that introduces global visual context into a graph semantic node and a decision-level prediction branch, improving robustness when lesion evidence is unreliable. Extensive experiments on Messidor-2, APTOS, and DDR show that PARAGraph achieves consistent DR grading performance over state-of-the-art methods. Interpretability and robustness analyses further demonstrate that its predictions are clinically grounded, closely associated with lesion evidence and robust to lesion segmentation noise.
