Diagnosis of disc bulge and disc desiccation in lumbar MRI using concatenated shape and texture features with random forest classifier

Abstract

Disc bulge and disc desiccation are the most common abnormalities occurring in the spine, which leads to severe low back pain. Despite computer-aided automatic abnormality diagnostic imaging systems are available still there is a need for betterment in diagnostic accuracy and in processing time. Image processing with combined imaging features like shape and texture has given better diagnostic ability when compared with processing with individual features. In the present study, the desiccated and bulged Intervertebral Discs (IVDs) are diagnosed automatically by combining shape features extracted using Histogram of Oriented Gradients (HOG) and texture feature extracted using novel Local Sub-Rhombus Binary Relation Pattern (LS-RBRP) techniques with Random Forest (RF) classifier. The performance analysis projects that the RF with HOG+LS-RBRP has an overall better accuracy of 94.7% when compared with HOG (87%) and LS-RBRP (90.2%) with RF classifier separately in categorizing the normal IVD, disc bulge and disc desiccation in the lumbar spine MRI. K E Y W O R D Sdisc bulge, disc desiccation, feature extraction, HOG, LS-RBRP, MRI, RF classifier

Machine Learning Applications of Surgical Imaging for the Diagnosis and Treatment of Spine Disorders: Current State of the Art

“…27 Ghosh et al 26,27 used the latter 2 methods in identifying degenerated disk disease on T2weighted midsagittal MRI scans-both achieving impressive results. Following work by Oktay et al 25 used a SVM on a substantially larger data set and found that their SVM method outperformed the 2 methods used by Ghosh et al 26,27 Later approaches used ML methods to classify degenerated disks along self-defined criteria 29 or the "gold standard" Pfirrmann grading criteria. 28,36 Sundarsingh and Kesavan 29 developed a fully automated system that identified and classified intervertebral disks on T2 MRI as "normal," "bulging," or "desiccated" through a combination of feature detection methods and ML classifiers.…”

“…Later approaches used ML methods to classify degenerated disks along self-defined criteria 29 or the “gold standard” Pfirrmann grading criteria. 28,36 Sundarsingh and Kesavan 29 developed a fully automated system that identified and classified intervertebral disks on T2 MRI as “normal,” “bulging,” or “desiccated” through a combination of feature detection methods and ML classifiers. Ruiz-España et al 36 developed a semiautomatic system that used gradient vector flow to grade degenerated disks, achieving “almost-perfect” agreement with a human expert (Cohen kappa of 0.81).…”

LSS‐net: 3‐dimensional segmentation of the spinal canal for the diagnosis of lumbar spinal stenosis

“…They emphasize in their article that although disc swelling and disc desiccation, abnormalities in the spine that cause severe low back pain, are computer‐assisted automatic abnormality diagnostic imaging systems available, there is still a need for improvement in diagnostic accuracy and processing time 14 . In this study, dried and swollen Intervertebral Discs (IVDs) are automatically diagnosed by combining shape features extracted using Histogram of Oriented Gradients (HOG) and tissue features extracted using new Local Sub‐Rhombus Binary Relationship Model (LS‐RBRP) techniques.…”

“…They emphasize in their article that although disc swelling and disc desiccation, abnormalities in the spine that cause severe low back pain, are computer-assisted automatic abnormality diagnostic imaging systems available, there is still a need for improvement in diagnostic accuracy and processing time. 14 In this study, dried and swollen Intervertebral Discs (IVDs) are automatically diagnosed by combining shape features extracted using Histogram of Oriented Gradients (HOG) and tissue features extracted using new Local Sub-Rhombus Binary Relationship Model (LS-RBRP) techniques. In the paper, the performance analysis projects that the RF with HOG+LS-RBRP has an overall better accuracy of 94.7% when compared with HOG (87%) and LS-RBRP (90.2%) with the RF classifier separately in categorizing the normal IVD, disc bulge, and disc desiccation in the lumbar spine MRI.…”

The Radial Bulging and Axial Strains of Intervertebral Discs during Creep Obtained with the 3D-DIC System

“…MRI images were mainly used to acquire shape and texture features in in vivo measurements. Mayerhoefer et al [ 16 ], Hung et al [ 17 ], and Sundarsingh et al [ 18 ] made efforts in the analysis of the parameter sensitivity. Their studies confirmed that texture features and geometric parameters were sensitive to posterior disc bulging and, thus, can be used as quantitative biomarkers that predict disease.…”