Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm

Abstract

Background: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. Methods: A retrospective study of 196 patients aged 50 years or greater who underwent CT scans of the wrist/forearm and dual-energy X-ray absorptiometry (DEXA) scans within 12 months of each other was performed. Volumetric segmentation of the forearm, carpal, and metacarpal bones was performed to obtain the mean CT attenuation of each bone. The correlations of the CT attenuations of each of the wrist/forearm bones and their correlations to the DEXA measurements were calculated. The study was divided into training/validation (n = 96) and test (n = 100) datasets. The performance of multivariable support vector machines (SVMs) was evaluated in the test dataset and compared to the CT attenuation of the distal third of the radial shaft (radius 33%). Results: There were positive correlations between each of the CT attenuations of the wrist/forearm bones, and with DEXA measurements. A threshold hamate CT attenuation of 170.2 Hounsfield units had a sensitivity of 69.2% and a specificity of 77.1% for identifying patients with osteoporosis. The radial-basis-function (RBF) kernel SVM (AUC = 0.818) was the best for predicting osteoporosis with a higher AUC than other models and better than the radius 33% (AUC = 0.576) (p = 0.020). Conclusions: Opportunistic screening for osteoporosis could be performed using CT scans of the wrist/forearm. Multivariable machine learning techniques, such as SVM with RBF kernels, that use data from multiple bones were more accurate than using the CT attenuation of a single bone.

Keywords: CT attenuation; DEXA; bone mineral density; capitate; computed tomography; hamate; lunate; metacarpal; pisiform; radius; scaphoid; trapezium; trapezoid; triquetrum; ulna.

Figure 1

Semi-automated volumetric segmentation mask of the bones of the wrist and forearm. Coronal mask of the wrist/forearm demonstrating segmentation of the distal radius, ulna, carpal bones, and bases of the metacarpals.

Figure 2

Box and whisker plots of the CT attenuation of each bone of the wrist and forearm by diagnosis: 2—osteoporosis, 1—osteopenia, and 0—normal.

Figure 3

Hierarchical cluster analysis of the correlations between the CT attenuation of each bone of the wrist and forearm. Radius—distal third of the radius; radius UD—ultradistal radius (radius epiphysis and metaphysis); radius 33%—distal third of the radial shaft; ulna—distal third of the ulna; ulna UD—distal ulna (ulnar epiphysis and metaphysis); ulna 33%—distal third of the ulnar shaft; 1st metacarpal—proximal third of the first metacarpal; 2nd metacarpal—proximal third of the second metacarpal; 3rd metacarpal—proximal third of the third metacarpal; 4th metacarpal—proximal third of the fourth metacarpal; 5th metacarpal—proximal third of the fifth metacarpal.