Reliability of Human Lumbar Facet Joint Degeneration Severity Assessed by Magnetic Resonance Imaging

Automated magnetic resonance imaging-based grading of the lumbar intervertebral disc and facet joints

Background

Degeneration of both intervertebral discs (IVDs) and facet joints in the lumbar spine has been associated with low back pain, but whether and how IVD/joint degeneration contributes to pain remains an open question. Joint degeneration can be identified by pairing T1 and T2 magnetic resonance imaging (MRI) with analysis techniques such as Pfirrmann grades (IVD degeneration) and Fujiwara scores (facet degeneration). However, these grades are subjective, prompting the need to develop an automated technique to enhance inter-rater reliability. This study introduces an automated convolutional neural network (CNN) technique trained on clinical MRI images of IVD and facet joints obtained from public-access Lumbar Spine MRI Dataset. The primary goal of the automated system is to classify health of lumbar discs and facet joints according to Pfirrmann and Fujiwara grading systems and to enhance inter-rater reliability associated with these grading systems.

Methods

Performance of the CNN on both the Pfirrmann and Fujiwara scales was measured by comparing the percent agreement, Pearson's correlation and Fleiss kappa value for results from the classifier to the grades assigned by an expert grader.

Results

The CNN demonstrates comparable performance to human graders for both Pfirrmann and Fujiwara grading systems, but with larger errors in Fujiwara grading. The CNN improves the reliability of the Pfirrmann system, aligning with previous findings for IVD assessment.

Conclusion

The study highlights the potential of using deep learning in classifying the IVD and facet joint health, and due to the high variability in the Fujiwara scoring system, highlights the need for improved imaging and scoring techniques to evaluate facet joint health. All codes required to use the automatic grading routines described herein are available in the Data Repository for University of Minnesota (DRUM).

Three Stages on Magnetic Resonance Imaging of Lumbar Degenerative Spine

PURPOSES

To propose a new lumbar degenerative staging system using the current radiological classification system.

METHODS

A cross-sectional analysis of retrospective databases between January 2018 and December 2022 was performed. Total of 410 patients for Modic changes, paravertebral muscle fat infiltration, disc degeneration, articular process degeneration, vertebral endplate degeneration and other structures, and disc displacement, Spondylolisthesis, and stenosis, and grouped patients according to stage were assessed. Visual analog scale, Japanese Orthopaedic Association, and Oswestry Disability Index scores were used to assess low back pain strength, neurological function, and quality of life, respectively.

RESULTS

The lumbar degeneration staging system consists of 8 variables, which can be divided into 3 steps: early, middle and late, and the correlation between each variable is strong (P < 0.05). The later the staging, the worse the Japanese Orthopaedic Association, visual analog scale, and Oswestry Disability Index scores.

CONCLUSIONS

Patients with later stages have worse clinical scores. This staging system recommends a uniform classification to assess lumbar degeneration.

Minimally Invasive Treatment of Facet Osteoarthritis Pain in Spine: A Clinical Approach Evaluating Cryotherapy

BACKGROUND

Chronic pain management remains a challenging aspect of neurosurgical care, with facet arthrosis being a significant contributor to the global burden of low back pain. This study evaluates the effectiveness of cryotherapy as a minimally invasive treatment for patients with facet arthrosis. By focusing on reducing drug dependency and pain intensity, the research aims to contribute to the evolving field of pain management techniques, offering an alternative to traditional pain management strategies.

METHODS

Through a retrospective longitudinal analysis of patients with facet osteoarthritis treated via cryotherapy between 2013 and 2023, we evaluated the impact on medication usage and pain levels, utilizing the Visual Analog Scale for pre- and posttreatment comparisons.

RESULTS

The study encompassed 118 subjects, revealing significant pain alleviation, with Visual Analog Scale scores plummeting from 9.0 initially to 2.0 after treatment. Additionally, 67 patients (56.78%) reported decreased medication consumption. These outcomes underscore cryotherapy's potential as a pivotal tool in chronic pain management.

CONCLUSIONS

The findings illuminate cryotherapy's efficacy in diminishing pain and curtailing medication dependency among patients with facet arthrosis. This study reaffirms cryotherapy's role in pain management and propels the discourse on nontraditional therapeutic avenues, highlighting the urgent need for personalized and innovative treatment frameworks.

The Relationship of Radiographic Parameters and Morphological Changes at Various Stages of Degeneration of the Lumbar Facet Joints: Cadaver Study

STUDY DESIGN

Cadaveric specimens.

OBJECTIVE

To perform a pathomorphological analysis of the degree of facet joint (FJ) degeneration utilizing fresh cadaveric models and correlating these structural changes with imaging findings.

METHODS

L1-L5 FSU including all tissue between the anterior longitudinal ligament to the posterior spinal structures were obtained on 28 patients at a mean of 5.7 hours post-mortem. The samples were fixed in an agar medium and CT and MRI were performed. The level of FJ degeneration was identified based on prior classifications Osteoarthritis Research Society International (OARSI), as was the facet angle and tropism. Pathomorphological assessment including articular cartilage cell density was performed according to prior established methodology.

RESULTS

Radiographically, a direct association was identified between FJ degeneration and patient age. Facet angle and tropism did not significantly vary by patient age. Pathomorphologically, there was a decrease in the cellular density of articular cartilage with increasing patient age. Similarly, there was a significant direct correlation between radiographic degree of degenerative changes in FJs with the age of cadavers and the degree of degeneration of FJs according to the morphological classification of OARSI, as well as a significant inverse correlation with cell density.

CONCLUSION

A comprehensive assessment of various signs of FJ degeneration using cadaveric material has established that, based on radiographic imaging, it is possible to assess the microstructural state of FJ, including at an early stage of the disease. This data may be useful for surgeons in guiding therapeutic strategies based on individual biometric parameters of the FJ.

Facet Joint Syndrome: Pathophysiology, Diagnosis, and Treatment

Facet joint osteoarthritis (OA) is the most frequent form of facet joint syndrome. Medical history, referred pain patterns, physical examination, and diagnostic imaging studies (standard radiographs, magnetic resonance imaging, computed tomography and single-photon emission computed tomography) may suggest but not confirm lumbar facet joint (LFJ) syndrome as a source of low back pain (LBP). However, the diagnosis and treatment of facet joint syndrome is still controversial and needs further study. It is widely acknowledged that block with local anesthetic is perhaps the most effective method to establish a diagnosis of pain from LFJ. Particularly, there are different rates of success among different populations selected for diagnostic block with various positive criteria. Currently, in addition to conservative treatments for pain such as painkillers, functional exercises, and massage, there are many other methods, including block, denervation of the nerves that innervate the joints by radiofrequency, freezing or endoscopy, and injections. Due to the limited duration of pain relief from neurolysis of medial branch, many scholars have recently turned their targets to dorsal roots and LFJ capsules. Therefore, we reviewed the latest research progress of facet joint syndrome from diagnosis to treatment.

The Role of Diagnostic Injections in Spinal Disorders: A Narrative Review

Neck and back pain is increasingly prevalent, and has increased exponentially in recent years. As more resources are dedicated to the diagnosis of pain conditions, it is increasingly important that the diagnostic techniques used are as precise and accurate as possible. Traditional diagnostic methods rely heavily upon patient history and physical examination to determine the most appropriate treatments and/or imaging studies. Though traditional means of diagnosis remain a necessity, in many cases, correlation with positive or negative responses to injections may further enhance diagnostic specificity, and improve outcomes by preventing unnecessary treatments or surgeries. This narrative review aims to present the most recent literature describing the diagnostic validity of precision injections, as well as their impact on surgical planning and outcomes. Diagnostic injections are discussed in terms of facet arthropathy, lumbar radiculopathy, discogenic pain and discography, and sacroiliac joint dysfunction. There is a growing body of evidence supporting the use of diagnostic local anesthetic injections or nerve blocks to aid in diagnosis. Spinal injections add valuable objective information that can potentially improve diagnostic precision, guide treatment strategies, and aid in patient selection for invasive surgical interventions.

Feasibility of Deep Learning Algorithms for Reporting in Routine Spine Magnetic Resonance Imaging

BACKGROUND

Artificial intelligence is gaining traction in automated medical imaging analysis. Development of more accurate magnetic resonance imaging (MRI) predictors of successful clinical outcomes is necessary to better define indications for surgery, improve clinical outcomes with targeted minimally invasive and endoscopic procedures, and realize cost savings by avoiding more invasive spine care.

OBJECTIVE

To demonstrate the ability for deep learning neural network models to identify features in MRI DICOM datasets that represent varying intensities or severities of common spinal pathologies and injuries and to demonstrate the feasibility of generating automated verbal MRI reports comparable to those produced by reading radiologists.

METHODS

A 3-dimensional (3D) anatomical model of the lumbar spine was fitted to each of the patient's MRIs by a team of technicians. MRI T1, T2, sagittal, axial, and transverse reconstruction image series were used to train segmentation models by the intersection of the 3D model through these image sequences. Class definitions were extracted from the radiologist report for the central canal: (0) no disc bulge/protrusion/canal stenosis, (1) disc bulge without canal stenosis, (2) disc bulge resulting in canal stenosis, and (3) disc herniation/protrusion/extrusion resulting in canal stenosis. Both the left and right neural foramina were assessed with either (0) neural foraminal stenosis absent, or (1) neural foramina stenosis present. Reporting criteria for the pathologies at each disc level and, when available, the grading of severity were extracted, and a natural language processing model was used to generate a verbal and written report. These data were then used to train a set of very deep convolutional neural network models, optimizing for minimal binary cross-entropy for each classification.

RESULTS

The initial prediction validation of the implemented deep learning algorithm was done on 20% of the dataset, which was not used for artificial intelligence training. Of the 17,800 total disc locations for which MRI images and radiology reports were available, 14,720 were used to train the model, and 3560 were used to validate against. The convergence of validation accuracy achieved with the deep learning algorithm for the foraminal stenosis detector was 81% (sensitivity = 72.4.4%, specificity = 83.1%) after 25 complete iterations through the entire training dataset (epoch). The accuracy was 86.2% (sensitivity = 91.1%, specificity = 82.5%) for the central stenosis detector and 85.2% (sensitivity = 81.8%, specificity = 87.4%) for the disc herniation detector.

CONCLUSIONS

Deep learning algorithms may be used for routine reporting in spine MRI. There was a minimal disparity among accuracy, sensitivity, and specificity, indicating that the data were not overfitted to the training set. We concluded that variability in the training data tends to reduce overfitting and overtraining as the deep neural network models learn to focus on the common pathologies. Future studies should demonstrate the accuracy of deep neural network models and the predictive value of favorable clinical outcomes with intervention and surgery.

LEVEL OF EVIDENCE

3.

CLINICAL RELEVANCE

Feasibility, clinical teaching, and evaluation study.