The exploration of feature extraction and machine learning for predicting bone density from simple spine X-ray images in a Korean population.

OBJECTIVE: Osteoporosis is hard to detect before it manifests symptoms and complications. In this study, we evaluated machine learning models for identifying individuals with abnormal bone mineral density (BMD) through an analysis of spine X-ray features extracted by deep learning to alert high-risk osteoporosis populations.
MATERIALS AND METHODS: We retrospectively used data obtained from health check-ups including spine X-ray and dual-energy X-ray absorptiometry (DXA). Consecutively, we selected people with normal and abnormal bone mineral density. From the regions of interest of X-ray images, deep convolutional networks were used to generate image features. We designed prediction models for abnormal BMD using the image features trained by machine learning classification algorithms. The performances of each model were evaluated.
RESULTS: From 334 participants, 170 images of abnormal (T scores < - 1.0 standard deviations (SD)) and 164 of normal BMD (T scores > = - 1.0 SD) were used for analysis. We found that a combination of feature extraction by VGGnet and classification by random forest based on the maximum balanced classification rate (BCR) yielded the best performance in terms of the area under the curve (AUC) (0.74), accuracy (0.71), sensitivity (0.81), specificity (0.60), BCR (0.70), and F1-score (0.73).
CONCLUSION: In this study, we explored various machine learning algorithms for the prediction of BMD using simple spine X-ray image features extracted by three deep learning algorithms. We identified the combination for the best performance in predicting high-risk populations with abnormal BMD.