Automated spinal MRI-based diagnostics of disc bulge and desiccating using LS-RBRP with RF

Abstract

Low back pain occurs because of the degeneration in Intervertebral Disc (IVD) namely: Disc Desiccation, Disc Bulge, and Disc Herniation, etc. To detect disc degeneration, a doctor often physically evaluates the Magnetic Resonance Imaging (MRI), which takes time and is dependent on the doctor’s expertise and training. Degeneration diagnosis that is automated can ease some of the doctor’s workload. On 378 IVDs for 63 patients, the proposed method is trained, tested, and assessed. According to the performance evaluation, the proposed Local Sub-Rhombus Binary Relationship (LS-RBRP) and Random Forrest (RF) classifier approach gives an overall accuracy of 90.2%. The proposed approach also produces a higher sensitivity, specificity, precision, and F-score of 80.8%, 90.3%, 90.4%, and 84.5%, respectively, when diagnosing the normal IVD, disc desiccation, and disc bulge in the lumbar MRI.