Automated Detection of Lumbar Spinal Stenosis via Semantic Segmentation of the Area Between the Anterior and Posterior Elements in MRI Images

This paper proposes a novel methodology to help clinicians automatically diagnose spinal stenosis, one of the leading causes of chronic lower back pain (CLBP), from lumbar spine Magnetic Resonance Imaging (MRI) scans. The approach mirrors standard clinical practice, in which spinal canal stenosis is diagnosed by manually inspecting lumbar spine MRI scans. Detection is achieved by segmenting the area between the anterior and posterior vertebral elements (AAP) and then locating the key points within the delineated boundaries. Semantic segmentation and a Fine Gaussian Support Vector Machine (SVM) are used to perform this delineation, achieving pixel accuracies of 94% and 92%, respectively. An anonymized dataset of 101 patients is used, in addition to the radiologist’s report for each patient, to compare the system’s results with the corresponding reports. The minimum and maximum diagnostic accuracies achieved by the developed methodology were 76.5% and 90%, respectively. The results show that the developed methodology can speed up the diagnosis process for patients with chronic lower back pain, thereby saving lives and time and reducing costs.