用图神经网络和证据回归提升膝骨关节炎分级准确率
AGE-Net: Spectral--Spatial Fusion and Anatomical Graph Reasoning with Evidential Ordinal Regression for Knee Osteoarthritis Grading
- 融合光谱与空间特征，构建解剖图结构捕捉长程依赖
- 在公开数据集上达QWK 0.9017，误差仅0.2349
- 适合医学影像诊断中需可信度评估的场景
基于膝关节X光片的自动化Kellgren-Lawrence（KL）分级面临细微结构变化、远距离解剖关联及等级边界模糊等挑战。本文提出AGE-Net，一种基于ConvNeXt的框架，整合了谱-空间融合（SSF）、解剖图推理（AGR）与差异性精炼（DFR）。为建模预测不确定性并保持标签序数性，采用正态逆伽玛（NIG）证据回归头与成对序数排序约束。在膝关节KL数据集上，AGE-Net在三个随机种子下实现0.9017±0.0045的加权二次肯德尔系数（QWK）和0.2349±0.0028的均方误差，优于主流CNN基线，在消融实验中持续展现优势。进一步评估了不确定性质量、鲁棒性与可解释性，更多实验图表将见于完整论文。
原文摘要 · Abstract (English)
Automated Kellgren--Lawrence (KL) grading from knee radiographs is challenging due to subtle structural changes, long-range anatomical dependencies, and ambiguity near grade boundaries. We propose AGE-Net, a ConvNeXt-based framework that integrates Spectral--Spatial Fusion (SSF), Anatomical Graph Reasoning (AGR), and Differential Refinement (DFR). To capture predictive uncertainty and preserve label ordinality, AGE-Net employs a Normal-Inverse-Gamma (NIG) evidential regression head and a pairwise ordinal ranking constraint. On a knee KL dataset, AGE-Net achieves a quadratic weighted kappa (QWK) of 0.9017 +/- 0.0045 and a mean squared error (MSE) of 0.2349 +/- 0.0028 over three random seeds, outperforming strong CNN baselines and showing consistent gains in ablation studies. We further outline evaluations of uncertainty quality, robustness, and explainability, with additional experimental figures to be included in the full manuscript.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。