用集成学习提升膝关节骨性关节炎分级准确率
KneeXNeT: An Ensemble-Based Approach for Knee Radiographic Evaluation
- 采用十种深度模型并行评估，通过加权采样缓解类别不平衡
- 最终集成模型准确率达72%，优于单模型的69%和70%
- 结合可视化技术增强可解释性，适合临床辅助诊断场景
膝关节骨性关节炎（OA）是最常见的关节疾病，也是致残的主要原因。传统诊断依赖专家对X光片进行评估，通常采用Kellgren-Lawrence分级系统，过程耗时。本研究旨在开发一种自动化深度学习模型，用于分类膝关节OA严重程度，减少对专家评估的依赖。首先，我们评估了十种前沿深度学习模型，单模型最高准确率为0.69。为应对类别不平衡问题，采用加权采样，准确率提升至0.70。进一步应用Smooth-GradCAM++可视化决策影响区域，增强最优模型的可解释性。最后，通过多数投票和浅层神经网络构建集成模型。所提出的集成模型KneeXNet达到最高准确率0.72，展现出作为自动化膝关节OA评估工具的潜力。
原文摘要 · Abstract (English)
Knee osteoarthritis (OA) is the most common joint disorder and a leading cause of disability. Diagnosing OA severity typically requires expert assessment of X-ray images and is commonly based on the Kellgren-Lawrence grading system, a time-intensive process. This study aimed to develop an automated deep learning model to classify knee OA severity, reducing the need for expert evaluation. First, we evaluated ten state-of-the-art deep learning models, achieving a top accuracy of 0.69 with individual models. To address class imbalance, we employed weighted sampling, improving accuracy to 0.70. We further applied Smooth-GradCAM++ to visualize decision-influencing regions, enhancing the explainability of the best-performing model. Finally, we developed ensemble models using majority voting and a shallow neural network. Our ensemble model, KneeXNet, achieved the highest accuracy of 0.72, demonstrating its potential as an automated tool for knee OA assessment.
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。