CT-based bone mineral density estimation using HU, radiomics, and deep learning

To develop and test models that estimate bone mineral density (BMD) from thoracolumbar junction CT images using Hounsfield unit (HU) assessment, radiomics, and convolutional neural networks (CNNs).

We retrospectively identified patients who underwent lumbar dual-energy x-ray absorptiometry and CT covering T12 and L1 within 6 months at four hospitals between 2014 and 2025. In total, 465 patients were eligible for T12 analysis, and 448 for L1. Data from two institutions were used for training/validation and data from the other two for external testing. We developed five models: region-of-interest-based HU regression; volume-of-interest (VOI)-based HU regression; radiomics; CNN; and an ensemble combining VOI, radiomics, and CNN. Performance was assessed using mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R²), and Bland-Altman limits of agreement (LoA).

For T12, the CNN model performed best among the single models (MAE: 0.122, RMSE: 0.157, R²: 0.603), whereas the ensemble model showed a slightly higher MAE (0.128) but lower RMSE (0.154) and higher R² (0.620). For L1, the radiomics model was the best single model (MAE: 0.124, RMSE: 0.155, R²: 0.582), while the ensemble showed numerically improved performance (MAE: 0.116, RMSE: 0.145, R²: 0.633). Pairwise comparisons showed no significant difference in absolute prediction errors between the ensemble and the best single model at either T12 or L1.

We developed an ensemble framework integrating volumetric HU assessment, radiomics, and CNNs to estimate BMD from thoracolumbar junction CT images. External testing across two independent institutions demonstrated promising performance for BMD estimation.