Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Abstract

Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0-90.0%], 84.7% (95% CI 78.8-90.5%), and 87.3% (95% CI 81.9-92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.