Magnetic resonance imaging analysis of work-related chronic low back pain: comparisons of different lumbar disc patterns

Development and application of AI assisted automatic reconstruction of axial lumbar disc CT images and diagnosis of lumbar disc herniation

RATIONALE AND OBJECTIVES

To evaluate the value of artificial intelligence (AI) assisted diagnostic system in reconstructing axial lumbar disc CT images and diagnosing lumbar disc herniation.

MATERIALS AND METHODS

440 patients with lumbar disc herniation were included, with 400 cases of spiral data (320 training, 40 validations, and 40 testing) and 40 cases of axial data (testing). V-Net was used to reconstruct the axial lumbar disc images. U-Net was used to segment the herniated discs and perform MSU classification. The Dice coefficient was used to evaluate the accuracy of AI in lumbar vertebras and discs segmentation. The quality of axial CT images reconstructed by AI and radiology technician was compared. The diagnostic accuracy of AI, radiologist, and AI + radiologist for the MSU classification of lumbar disc herniation in spiral and axial data was evaluated.

RESULTS

The Dice coefficients of AI for segmenting the sacral, lumbar, and lumbar discs were 0.953, 0.940, and 0.926, respectively. The quality of the axial CT images reconstructed by AI and radiographer had non-significant difference (P＞0.05). In both the spiral and axial data, the accuracy of AI, radiologist, and AI + radiologist in diagnosing the MSU classification was significantly different (P < 0.01). The diagnostic accuracy of the AI system in MSU classification was higher in the spiral data than that of the axial data (P = 0.003).

CONCLUSION

The AI system is feasible and satisfactory for segmentation of lumbar CT image, reconstruction of axial lumbar disc CT images, and diagnosis of lumbar disc herniation.

Correlation between serum angiotensin-converting enzyme (ACE) levels and intervertebral disc degeneration

Studies have shown that the renin-angiotensin system (RAS) might play an essential role in intervertebral disc degeneration (IDD). The study aimed to investigate the relationship between serum angiotensin-converting enzyme (ACE) concentration and IDD and its predictive value for severe disc degeneration. 245 patients who came to our hospital for low back pain were recruited, and blood samples were collected for routine examination. Descriptive data and demographic parameters were collected. The cumulative grade 1 was calculated by summing up the Pfirrmann grade of all lumbar discs. ACE concentration grouping was determined via tertile split. Correlation analysis and multivariable linear regression analysis were performed to determine the relationship between ACE and IDD. The receiver's degree of disc degeneration (ROC) curve determined the ACE's predictive value. Results indicated that there was no significant difference in demographic parameters among groups. Correlation analysis and multivariate linear analysis showed that ACE was an independent risk factor for IDD. The cumulative grade 1 increased significantly with the increase in ACE concentration, which was consistent with the correlation analysis. Average Pfirrmann grade &lt; 4 indicates mild to moderate degeneration, and grade ≥ 4 indicates severe degeneration in terms of an individual disc. From L1/2 to L5/S1, the mean plasma ACE concentration was significantly higher in the severe degeneration group than in the mild to moderate degeneration group. According to the ROC curve, the cut-off value of ACE levels was 22.5. patients with ACE &gt; 22.5 had severe degeneration. The sensitivity and specificity were 0.762 and 0.521, respectively.

Imaging Analysis of the High-Intensity Zone on Lumbar Spine Magnetic Resonance Images: Classification, Features and Correlation with Low Back Pain

Aim

Early studies suggested that the high-intensity zone (HIZ) on lumbar MRI was a diagnostic sign of painful internal disc disruption (IDD). However, recent studies have questioned its diagnostic value. This study is conducted to explore imaging features of HIZ and to investigate the correlation between these characteristics and low back pain (LBP), further studying the predictive value of HIZ.

Methods

A retrospective study of 1188 cases was performed. MR images were read and analyzed by two experienced, blinded radiologists.

Results

A total of 575 (48.4%) individuals exhibited HIZ. The prevalence of posterior HIZ (32.3%) was significantly higher than that of anterior HIZ (23.6%; P < 0.01). Round type was the most common shape (61.0%) on sagittal view. Only 37 HIZs (4.6%) were identified on axial views. A total of 263 HIZ discs (32.5%) were found to have additional diagnostic signs of IDD, which is difficult to distinguish from the annulus fibrosus. In subjects with consecutive slides showing HIZ, the incidence of LBP was significantly higher than in single-slide HIZ individuals (58.0% vs 48.6%, P < 0.05).

Conclusion

MRI-visualized HIZ is a highly valuable method of screening for lumbar IDD. It is demonstrated that consecutive-slide HIZ was a more reliable indicator for discogenic LBP than single-slide HIZ.

Relationship between Endplate Defects, Modic Change, Disc Degeneration, and Facet Joint Degeneration in Patients with Low Back Pain

Purpose

The endplate defects (EDs), Modic changes (MCs), disc degeneration (DD), facet orientation (FO), and facet tropism (FT) were demonstrated to be related to the low back pain (LBP). The aim of this study was to investigate possible correlations between them.

Methods

75 patients were reviewed to evaluate the degenerative change in vertebral bodies (EDs and MCs), intervertebral discs (DD), and facet joint degeneration (FO and FT). All patients were categorized into four groups based on the grade of EDs. Clinical outcomes were evaluated with the visual analog scale (VAS) and Oswestry disability index (ODI) before and after surgery.

Results

There was no difference between the four groups in baseline characteristics except for gender and weight. FT is positively correlated with FO. The same rule exists between EDs, the size of MCs II, FO (left) and FO (right), and VAS and ODI. The grade of EDs is positively correlated with the grade of DD. L4-L5 can bear more load than other levels; thus, the grade of EDs is higher than that of other lumbar levels. The preoperative LBP was relieved in all groups in varying degrees. The change of pain and dysfunction is inversely proportional to the grade of EDs in the general trend.

Conclusion

The relationship between weight, gender, and disc degeneration provided a mechanism by which increasing weight can predispose to DD. Different grades of EDs had different effects on patients with LBP. There was a significant correlation between EDs, MCs II, DD, FT, and FO.