膝-xRAI：一种用于自动膝骨关节炎Kellgren-Lawrence分级的可解释AI框架
Knee-xRAI: An Explainable AI Framework for Automatic Kellgren-Lawrence Grading of Knee Osteoarthritis
- Orthopaedic Department, Faculty of Medicine UIN Syarif Hidayatullah Jakarta（乌姆尼大学医学学院骨科部）
- Informatics Engineering, Institut Teknologi Sepuluh Nopember（十月份技术研究所信息工程系）
- Information Technology, Universitas Muhammadiyah Yogyakarta（尤科阿卡塔大学信息技术系）
- Industrial and Systems Engineering, King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学工业与系统工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出Knee-xRAI框架，通过模拟临床放射流程，结合JSN、骨刺和下骨质硬化等特征，利用XGBoost-SHAP和ConvNeXt模型实现可解释的KL分级，验证了其在膝骨关节炎诊断中的有效性。
AI中文摘要：
对平片进行膝骨关节炎（KOA）分级的可重复性差。KL评分单级分歧可能改变手术管理或将患者从保守治疗转为关节内注射。同时，超越人类读者的深度学习模型通常缺乏决策解释。我们提出了Knee-xRAI，一个分解分级过程的流程，通过模仿临床放射流程独立测量关节间隙狭窄（JSN）、骨刺和下骨质硬化，然后将这些发现组合成可解释的KL评分。具体而言，U-Net++架构通过轮廓分割量化JSN，SE-ResNet-50多任务网络在OARSI尺度上对骨刺进行解剖部位评分，混合纹理-CNN检测二进制硬化。该流程产生一个50维特征向量，通过XGBoost-SHAP分类器（路径A，审计）和ConvNeXt混合预测器（路径B，部署）进行评估。在8,260个OAI衍生的放射图像上，JSN模块的Dice得分为0.8909，mJSW ICC为0.8674。路径A达到QWK为0.6294和AUC为0.8046，证实了结构化特征向量具有显著的诊断信号。路径B达到QWK为0.8436和AUC为0.9017。SHAP分析显示JSN是主导特征，骨刺增加了一致的增量，硬化贡献微小。移除JSN证据会降低KL3-KL4召回率，而早期等级保持不变，与KL诊断标准一致。Knee-xRAI将每个预测都基于可审计的放射学发现链，提供临床透明度。
英文摘要：
Grading knee osteoarthritis (KOA) on plain radiographs is poorly reproducible across readers. A single-grade disagreement on the Kellgren-Lawrence (KL) scale can alter surgical management or redirect a patient from conservative therapy to intra-articular injection. Meanwhile, deep learning models that outperform human readers often offer no explanation for their decisions. We present Knee-xRAI, a pipeline that decomposes the grading process by mimicking clinical radiological workflows. It independently measures joint space narrowing (JSN), osteophytes, and subchondral sclerosis, then combines these findings into an explainable KL grade. Specifically, a U-Net++ architecture quantifies JSN via contour segmentation, an SE-ResNet-50 multi-task network grades osteophytes per anatomical site on the OARSI scale, and a hybrid texture-CNN detects binary sclerosis. This pipeline yields a 50-dimensional feature vector evaluated via an XGBoost-SHAP classifier (Path A, audit) and a ConvNeXt hybrid predictor (Path B, deployed). On 8,260 OAI-derived radiographs, the JSN module achieved a Dice score of 0.8909 and an mJSW ICC of 0.8674. Path A reached a QWK of 0.6294 and an AUC of 0.8046, confirming the structured feature vector carries substantial diagnostic signal. Path B achieved a QWK of 0.8436 and an AUC of 0.9017. SHAP analysis identifies JSN as the dominant feature, with osteophytes adding a consistent increment and sclerosis contributing marginally. Removing JSN evidence collapses KL3-KL4 recall while early grades remain intact, aligning with the KL diagnostic criteria. Knee-xRAI grounds every prediction in an auditable chain of measured radiographic findings, providing clinical transparency at the point of care.
