Osteoporosis is a common chronic metabolic bone disease that is often under-diagnosed and under-treated due to the limited access to bone mineral density (BMD) examinations, e.g., Dual-energy X-ray Absorptiometry (DXA). In this paper, we propose a method to predict BMD from Chest X-ray (CXR), one of the most common, accessible and low-cost medical image examinations. Our method first automatically detects Regions of Interest (ROIs) of local and global bone structures from the CXR. Then a multi-ROI model is developed to exploit both local and global information in the chest X-ray image for accurate BMD estimation. Our method is evaluated on 1651 CXR cases with ground truth BMD measured by gold standard DXA. The model predicted BMD has a strong correlation with the ground truth (Pearson correlation coefficient 0.853). When applied for osteoporosis screening, it achieves a high classification performance (AUC 0.928). As the first effort in the field using CXR scans to predict the BMD, the proposed algorithm holds a strong potential in early osteoporosis screening and public health promotion.
- Bone mineral density estimation
- Chest X-ray
- Multi-ROI model