Diagnosis of Lumbar Spondylolisthesis via Convolutional Neural Networks

Abstract

Spondylolisthesis, due to bilateral defects of the posterior vertebral arch, refers to a slippage of a vertebral body over another, usually with the superior vertebral body slipping anteriorly relative to an adjacent inferior vertebral body. The most common site for spondylolisthesis is L4 or L5. As with most spinal diseases, radiological findings are the main ingredients in diagnosing spondylolisthesis. Therefore, computer-assisted systems can be used in diagnosing spondylolisthesis when adequate experience doctors in the outpatient clinics are not present. In this paper, we looked for a solution to the problem of diagnosis of spondylolisthesis by using two well-known artificial neural networks AlexNet and GoogleLeNet. The data set consists of 272 X-ray images in total. 136 of these images belong to patients suffering from spondylolisthesis, and 136 images without spondylolisthesis. Experimental results demonstrate that GoogleLeNet is 93.87% accuracy and performs slightly better than AlexNet with an accuracy of 91.67%.