Reference values for vertebral shape in young Chinese women: implication for assessment of vertebral deformity

3D U-Net Neural Network Architecture-Assisted LDCT to Acquire Vertebral Morphology Parameters: A Vertebral Morphology Comprehensive Analysis in a Chinese Population

To evaluate the feasibility of acquiring vertebral height from chest low-dose computed tomography (LDCT) images using an artificial intelligence (AI) system based on 3D U-Net vertebral segmentation technology and the correlation and features of vertebral morphology with sex and age of the Chinese population. Patients who underwent chest LDCT between September 2020 and April 2023 were enrolled. The Altman and Pearson's correlation analyses were used to compare the correlation and consistency between the AI software and manual measurement of vertebral height. The anterior height (Ha), middle height (Hm), posterior height (Hp), and vertebral height ratios (VHRs) (Ha/Hp and Hm/Hp) were measured from T1 to L2 using an AI system. The VHR is the ratio of Ha to Hp or the ratio of Hm to Hp of the vertebrae, which can reflect the shape of the anterior wedge and biconcave vertebrae. Changes in these parameters, particularly the VHR, were analysed at different vertebral levels in different age and sex groups. The results of the AI methods were highly consistent and correlated with manual measurements. The Pearson's correlation coefficients were 0.855, 0.919, and 0.846, respectively. The trend of VHRs showed troughs at T7 and T11 and a peak at T9; however, Hm/Hp showed slight fluctuations. Regarding the VHR, significant sex differences were found at L1 and L2 in all age bands. This innovative study focuses on vertebral morphology for opportunistic analysis in the mainland Chinese population and the distribution tendency of vertebral morphology with ageing using a chest LDCT aided by an AI system based on 3D U-Net vertebral segmentation technology. The AI system demonstrates the potential to automatically perform opportunistic vertebral morphology analyses using LDCT scans obtained during lung cancer screening. We advocate the use of age-, sex-, and vertebral level-specific criteria for the morphometric evaluation of vertebral osteoporotic fractures for a more accurate diagnosis of vertebral fractures and spinal pathologies.

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.

Vertebral heights and ratios are not only race-specific, but also gender- and region-specific: establishment of reference values for mainland Chinese

This study established gender-specific reference values in mainland Chinese (MC) and is important for quantitative morphometry for diagnosis and epidemiological study of osteoporotic vertebral compressive fracture. Comparisons of reference values among different racial populations are then performed to demonstrate the MC-specific characteristic.

PURPOSE

Osteoporotic vertebral compressive fracture (OVCF) is a common complication of osteoporosis in the elder population. Clinical diagnosis and epidemiological study of OVCF often employ quantitative morphometry, which relies heavily on the comparison of patients' vertebral parameters to existing reference values derived from the normal population. Thus, reference values are crucial in clinical diagnosis. To our knowledge, this is the first study to establish reference values of the mainland Chinese (MC) for quantitative morphometry.

METHODS

Vertebral heights including anterior (Ha), middle (Hm), posterior (Hp) heights, and predicted posterior height (pp) from T4 to L5 were obtained; and ratios of Ha/Hp, Hm/Hp and Hp/pp. were calculated from 585 MC (both female and male) for establishing reference values and subsequent comparisons with other studies.

RESULTS

Vertebral heights increased progressively from T4 to L3 but then decreased in L4 and L5. Both genders showed similar ratios of vertebral dimensions, but male vertebrae were statistically larger than those of female (P < 0.01). Vertebral size of MC population was smaller than that of US and UK population, but was surprisingly larger than that of Hong Kong Chinese, although these two are commonly considered as one race. Data from different racial populations showed similar dimensional ratios in all vertebrae.

CONCLUSIONS

We established gender-specific reference values for MC. Our results also indicated the necessity of establishing reference values that are not only race- and gender-specific, but also population- or region-specific for accurate quantitative morphometric assessment of OVCF.

Reference ranges for vertebral heights and prevalence of asymptomatic (undiagnosed) vertebral fracture in Vietnamese men and women

Based on quantitative measurements of vertebral heights, the prevalence of undiagnosed vertebral fracture in Vietnamese men and women aged 50 years and older was 23 and 26 %, respectively.

BACKGROUND

The present study sought to develop reference ranges for vertebral heights and to determine the prevalence of asymptomatic vertebral fracture in Vietnamese men and women.

METHODS

The study included 312 men and 657 women aged over 18 who were randomly selected from the community. The ImageJ software program was used to measure anterior height (H(a)), middle height (H(m)), and posterior height (H(p)) for each vertebra (T4 to T12 and L1 to L5). Four vertebral ratios were determined: H(a)/H(p), H(m)/H(p), H(p)/H(p + 1), and H(p)/H(p − 1). Reference ranges for the ratios were then developed by the method of Winsorized mean. Vertebral fracture was diagnosed as a ratio lower than three standard deviations from the normal mean.

RESULTS

For any given vertebra, H(a), H(m), and H(p) in men were higher than in women. In both sexes, H(a) and H(m) increased in a stepwise fashion from T4 to L3 and then gradually reduced in L4–L5. Vertebral heights for T4–T9 tended to decrease, while vertebral height for T10–L5 tended to increase with advancing age. Among those aged over 50 years, the prevalence of vertebral fracture in men was 23.3 % (95 % confidence interval (CI) 16.8–31.3 %) which was lower than that in women (26.5 %; 95 % CI 22.4–31.1 %). The prevalence increased with advancing age, such that from the age of over 70, 41 % of men and 42 % women had at least one vertebral fracture.

CONCLUSION

One fourth of Vietnamese men and women aged 50 years and older have a symptomatic vertebral fracture. This prevalence is equivalent to that in Caucasian populations.