The application of key feature extraction algorithm based on Gabor wavelet transformation in the diagnosis of lumbar intervertebral disc degenerative changes

Abstract

ObjectiveBased on the theoretical basis of Gabor wavelet transformation, the application effects of feature extraction algorithm in Magnetic Resonance Imaging (MRI) and the role of feature extraction algorithm in the diagnosis of lumbar vertebra degenerative diseases were explored. Q, et al. (2020) The application of key feature extraction algorithm based on Gabor wavelet transformation in the diagnosis of lumbar intervertebral disc degenerative changes. PLoS ONE 15(2): e0227894. https://doi.org/10. ConclusionThe feature extraction algorithm based on Gabor wavelet transformation could easily and quickly realize the localization of the lumbar intervertebral disc, and the accuracy of the results was ensured. In addition, from the aspect of vertebral body tracking, the tracking effects based on the KLT algorithm were better and faster than those based on the maximum mutual information method.

The Clinical Diagnostic Value of Lumbar Intervertebral Disc Herniation Based on MRI Images

“…Lumbar facet joints (LFJ) degeneration, lumber disc herniation (LDH) stimulation, or compression of the corresponding segmental nerve roots are among the causes of low back pain. Whether the structural abnormality of the functional unit of the spine caused by LFJ degeneration causes the abnormal force of the lumbar intervertebral disc herniation is unclear, and whether lumbar facet joint angle changes are common in patients with lumbar disc herniation is still unclear [ 2 ]. A full understanding of the relationship between lumbar facet joint angle changes and lumbar disc herniation is helpful to the prevention and treatment of low back pain.…”

Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

“…With regards to feature extraction, which is the capacity of a system to recognize a specific set of relevant features, all included studies collectively showed an accuracy > 80% in identifying the location of vertebrae [24] and IVDs [8,[20][21][22][23][24], with the ability to even detect annular tears and lumbar disc herniation [21][22][23]. Although the majority of the studies were conducted on MRI images [8,[20][21][22][23][24], one study utilized X-ray imaging [10] and another study built a 3D model of patients' backs using a noninvasive surface acquisition technology [19].…”

“…With regards to feature extraction, which is the capacity of a system to recognize a specific set of relevant features, all included studies collectively showed an accuracy > 80% in identifying the location of vertebrae [24] and IVDs [8,[20][21][22][23][24], with the ability to even detect annular tears and lumbar disc herniation [21][22][23]. Although the majority of the studies were conducted on MRI images [8,[20][21][22][23][24], one study utilized X-ray imaging [10] and another study built a 3D model of patients' backs using a noninvasive surface acquisition technology [19]. Moreover, some of these studies also reported the capacity of the described systems to perform classification and regression tasks on extracted data, such as estimating the degree of IVD degeneration [8,[22][23][24], scoliosis curve type classification [19] and prediction of curve progression [10], the presence of spinal stenosis [23] and to explore the correlation between degenerative changes and the presence of LBP [24].…”

“…With regards to classification, Adankon et al [19] were the only ones to use 3D images of the surface of the human back: they extracted features for 165 patients using local geometric descriptors, and fed them to a least-squares Support Vector Machine (SVM) for the classification of scoliosis curve types, achieving 95% accuracy. Yang et al [8] used a Gabor wavelet transform to extract features from MRI of 109 subjects, and a Kanade-Lucas-Tomasi (KLT) feature tracker to identify lumbar degenerative changes with an accuracy of 88.3%. Ruiz-España et al [23] extracted features from MRI of 67 patients using Gradient Vector Flow, and tested several machine learning models to classify degenerated IVDs achieving accuracies greater than 90%.…”

“…The adoption of this ground-breaking technology is being explored in spine surgery as well [1]. Indeed, thanks to its interdisciplinary nature and the wide utilization of radiological images to inspect the anatomical structures of the spine, the use of AI may be of particular value in determining, for example, which are the pathological discs [8], classifying a scoliotic curve [9] and predict its progression [10]. In this study, we have systematically reviewed the available literature on the use of AI, and more specifically computer vision, in the prevention, diagnosis, and treatment of chronic Low Back Pain (LBP).…”