Application of geometrical measurements in the assessment of vertebral strength

Automatic measurement of anatomical parameters of the lumbar vertebral body and the intervertebral disc on radiographs by deep learning

Background

Lumbar spine disorders are one of the common causes of low back pain (LBP). Objective and reliable measurement of anatomical parameters of the lumbar spine is essential in the clinical diagnosis and evaluation of lumbar disorders. However, manual measurements are time-consuming and laborious, with poor consistency and repeatability. Here, we aim to develop and evaluate an automatic measurement model for measuring the anatomical parameters of the vertebral body and intervertebral disc based on lateral lumbar radiographs and deep learning (DL).

Methods

A model based on DL was developed with a dataset consisting of 1,318 lateral lumbar radiographs for the prediction of anatomical parameters, including vertebral body heights (VBH), intervertebral disc heights (IDH), and intervertebral disc angles (IDA). The mean of the values obtained by 3 radiologists was used as a reference standard. Statistical analysis was performed in terms of standard deviation (SD), mean absolute error (MAE), Percentage of correct keypoints (PCK), intraclass correlation coefficient (ICC), regression analysis, and Bland-Altman plot to evaluate the performance of the model compared with the reference standard.

Results

The percentage of intra-observer landmark distance within the 3 mm threshold was 96%. The percentage of inter-observer landmark distance within the 3 mm threshold was 94% (R1 and R2), 92% (R1 and R3), and 93% (R2 and R3), respectively. The PCK of the model within the 3 mm distance threshold was 94-99%. The model-predicted values were 30.22±3.01 mm, 10.40±3.91 mm, and 10.63°±4.74° for VBH, IDH, and IDA, respectively. There were good correlation and consistency in anatomical parameters of the lumbar vertebral body and disc between the model and the reference standard in most cases (R2=0.89-0.95, ICC =0.93-0.98, MAE =0.61-1.15, and SD =0.89-1.64).

Conclusions

The newly proposed model based on a DL algorithm can accurately measure various anatomical parameters on lateral lumbar radiographs. This could provide an accurate and efficient measurement tool for the quantitative evaluation of spinal disorders.

Chronic low back pain and its association with lumbar vertebrae and intervertebral disc changes in adults. A case control study

AIM

This study was done to determine the association between chronic low back pain and vertebral fractures, intervertebral disc space (IDS) narrowing, vertebral osteophytes and spondylolisthesis among adults.

METHOD

This case control study was done in Sri Lanka. Cases were patients with low back pain and controls were without low back pain. Postero-anterior and lateral radiographs of lumbar sacral spine of both groups were studied. To detect vertebral fractures in fourth and fifth lumbar vertebrae, anterior and posterior heights of vertebrae were measured using a Vernier caliper and antero-posterior ratio (A/P) was calculated. Having an A/P ratio value of < 0.89 was considered as a vertebral fracture. Presence of disc space narrowing, vertebral osteophytes and spondylolisthesis was assessed by two radiologists working independently. Bivariate and logistic regression analysis was done to find associations.

RESULTS

There were 140 cases and 140 controls. Mean (SD) age for cases was 51.6 (17) years. Mean (SD) age for controls was 50 (15) years. Females made up 62% of cases and controls. Fifth lumbar vertebral fracture (odds ratio [OR] = 10.2; P = 0.001), fourth lumbar vertebral fracture (OR = 2.5; P = 0.017) and IDS narrowing (OR = 4.15, P = 0.009) had a significant association with low back pain and vertebral osteophytes and spondylolisthesis did not have a significant association with low back pain.

CONCLUSION

Only vertebral fractures and IDS narrowing had a significant association with chronic low back pain.

The ratio of anterior and posterior vertebral heights reinforces the utility of DXA in assessment of vertebrae strength

The objective of the study was to introduce a new parameter describing bone strength with greater precision than the widely used antero-posterior DXA (dual-energy X-ray absorptiometry), which measures areal bone mineral density (aBMD). The adjusted areal bone mineral density (AaBMD) defined as the ratio between aBMD and h a/h p (h a and h p: anterior and posterior vertebral body heights measured on the lateral view, respectively) is proposed: AaBMD = aBMD/(h a/h p). The utility of AaBMD in prediction of bone strength was assessed by in vitro measurements of cadaver L3 vertebrae. The AaBMD of 31 vertebrae was correlated with the ultimate stress (P max) and load (F max) values obtained in mechanical tests. The correlations were compared to those obtained for aBMD and for volumetric bone mineral density (vBMD) measured by computed tomography. The correlation of AaBMD to F max adjusted for donor's age was significantly higher than for aBMD and vBMD (r = 0.740, 0.658, and 0.609, respectively, p < 0.05). The differences between partial correlation coefficients for P max to AaBMD, aBMD and vBMD relationships were smaller (r = 0.764, 0.720, and 0.732, respectively, p < 0.05), but also showed the superiority of AaBMD. Combining antero-posterior DXA aBMD and the lateral h a/h p ratio, measured, for example, by the Vertebral Fracture Assessment software of the new generation of DXA devices, seems to accurately predict the mechanical vertebral parameters related to bone strength. It is assumed that the proposed AaBMD parameter may be more predictive for fracture risk assessment, which requires further studies.