Deep learning–based BMD estimation from knee radiographs with conformal uncertainty quantification

Background Population-wide osteoporosis screening is hindered by limited access to Dual-energy X-ray Absorptiometry (DXA). Opportunistic screening using plain radiographs is a promising alternative, but safe clinical adoption requires models that can reliably quantify their uncertainty. We evaluated a deep learning model that estimates femoral-neck bone mineral density (BMD) from knee radiographs and employs conformal prediction to provide calibrated, patient-specific uncertainty intervals. Methods We utilized bilateral knee radiographs with paired femoral-neck DXA scans (within 180 days) from the Osteoarthritis Initiative. The dataset was split at the participant level into training (70%), validation (10%), test (10%), and calibration (10%) sets. An EfficientNet-V2-M model was trained to predict BMD. We implemented Split Conformal Prediction with two test-time augmentation (TTA) strategies: (1) averaging augmented predictions before conformalization (Standard TTA), and (2) treating each augmented view as a separate sample (Multisample TTA). Performance was evaluated using Pearson correlation ( r ), mean absolute error (MAE), and empirical coverage of 90%, 95%, and 99% prediction intervals. Results The model achieved a Pearson correlation of r = 0.6800 and MAE of 0.1107 g/cm 2 with standard TTA. Conformal prediction successfully produced valid uncertainty intervals, with empirical coverage matching nominal levels (e.g., ∼95% coverage for 95% intervals). Multisample TTA yielded slightly narrower 95% intervals for the bilateral model (0.2776 vs. 0.2792 g/cm 2 ) without sacrificing coverage. Crucially, interval widths correlated with prediction errors, indicating the model correctly signaled higher uncertainty for difficult cases. Conclusion Deep learning can extract BMD signals from knee radiographs, and conformal prediction provides a rigorous “safety wrapper” by quantifying uncertainty. This approach offers a foundational step towards trustworthy opportunistic osteoporosis screening in orthopedic settings.