用膝关节X光片+深度学习估骨密度，还给结果加了可信区间。
Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification
- 用EfficientNet模型从双侧膝关节X光片预测骨密度。
- 多样本TTA方法生成更紧的置信区间，且覆盖率达90%以上。
- 适合想用常规X光做骨密度筛查的临床医生和研究者。
DXA设备获取受限，影响骨质疏松筛查。本概念验证研究提出利用广泛存在的膝关节X光片，通过深度学习进行骨密度（BMD）的机遇性估计，并强调临床应用中稳健的不确定性量化至关重要。采用EfficientNet模型在OAI数据集上训练，基于双侧膝关节X光片预测BMD。比较了两种测试时增强（TTA）方法：传统平均法与多样本方法。关键在于，采用分割合宜预测（Split Conformal Prediction）构建具有统计保证、患者个性化的预测区间，确保覆盖率。结果显示，传统TTA方法相关系数达0.68。尽管传统方法点预测更优，但多样本方法生成的90%、95%、99%置信区间略更紧凑，同时保持良好覆盖率。该框架对复杂病例能合理表达更高不确定性。虽然膝关节X光与标准DXA存在解剖不匹配，限制即时临床应用，但该方法为利用常规放射影像实现可信的AI辅助骨密度筛查奠定了基础，有望提升骨质疏松早期检测效率。
原文摘要 · Abstract (English)
Limited DXA access hinders osteoporosis screening. This proof-of-concept study proposes using widely available knee X-rays for opportunistic Bone Mineral Density (BMD) estimation via deep learning, emphasizing robust uncertainty quantification essential for clinical use. An EfficientNet model was trained on the OAI dataset to predict BMD from bilateral knee radiographs. Two Test-Time Augmentation (TTA) methods were compared: traditional averaging and a multi-sample approach. Crucially, Split Conformal Prediction was implemented to provide statistically rigorous, patient-specific prediction intervals with guaranteed coverage. Results showed a Pearson correlation of 0.68 (traditional TTA). While traditional TTA yielded better point predictions, the multi-sample approach produced slightly tighter confidence intervals (90%, 95%, 99%) while maintaining coverage. The framework appropriately expressed higher uncertainty for challenging cases. Although anatomical mismatch between knee X-rays and standard DXA limits immediate clinical use, this method establishes a foundation for trustworthy AI-assisted BMD screening using routine radiographs, potentially improving early osteoporosis detection.
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。