Lumbar Spine X-ray Images Research Articles

489 - Evaluation of the degenerative changes in lumbar spine X-ray Images from elderly patients in Hong Kong

489 - Evaluation of the degenerative changes in lumbar spine X-ray Images from elderly patients in Hong Kong

Development of a Method for Estimating the Angle of Lumbar Spine X-ray Images Using Deep Learning with Pseudo X-ray Images Generated from Computed Tomography

Background and Objectives: In lumbar spine radiography, the oblique view is frequently utilized to assess the presence of spondylolysis and the morphology of facet joints. It is crucial to instantly determine whether the oblique angle is appropriate for the evaluation and the necessity of retakes after imaging. This study investigates the feasibility of using a convolutional neural network (CNN) to estimate the angle of lumbar oblique images. Since there are no existing lumbar oblique images with known angles, we aimed to generate synthetic lumbar X-ray images at arbitrary angles from computed tomography (CT) images and to estimate the angles of these images using a trained CNN. Methods: Synthetic lumbar spine X-ray images were created from CT images of 174 individuals by rotating the lumbar spine from 0° to 60° in 5° increments. A line connecting the center of the spinal canal and the spinous process was used as the baseline to define the shooting angle of the synthetic X-ray images based on how much they were tilted from the baseline. These images were divided into five subsets and trained using ResNet50, a CNN for image classification, implementing 5-fold cross-validation. The models were trained for angle estimation regression and image classification into 13 classes at 5° increments from 0° to 60°. For model evaluation, mean squared error (MSE), root mean squared error (RMSE), and the correlation coefficient (r) were calculated for regression analysis, and the area under the curve (AUC) was calculated for classification. Results: In the regression analysis for angles from 0° to 60°, the MSE was 14.833 degree2, the RMSE was 3.820 degrees, and r was 0.981. The average AUC for the 13-class classification was 0.953. Conclusion: The CNN developed in this study was able to estimate the angle of an lumbar oblique image with high accuracy, suggesting its usefulness.

Reliability Analysis of Vertebral Landmark Labelling on Lumbar Spine X-ray Images.

Vertebral landmark labelling on X-ray images is important for objective and quantitative diagnosis. Most studies related to the reliability of labelling focus on the Cobb angle, and it is difficult to find studies describing landmark point locations. Since points are the most fundamental geometric feature that can generate lines and angles, the assessment of landmark point locations is essential. The aim of this study is to provide a reliability analysis of landmark points and vertebral endplate lines with a large number of lumbar spine X-ray images. A total of 1000 pairs of anteroposterior and lateral view lumbar spine images were prepared, and 12 manual medicine experts participated in the labelling process as raters. A standard operating procedure (SOP) was proposed by consensus of the raters based on manual medicine and provided guidelines for reducing sources of error in landmark labelling. High intraclass correlation coefficients ranging from 0.934 to 0.991 verified the reliability of the labelling process using the proposed SOP. We also presented means and standard deviations of measurement errors, which could be a valuable reference for evaluating both automated landmark detection algorithms and manual labelling by experts.

Architecture entropy sampling-based evolutionary neural architecture search and its application in osteoporosis diagnosis

In recent years, neural architecture search (NAS) has achieved unprecedented development because of its ability to automatically achieve high-performance neural networks in various tasks. Among these, the evolutionary neural architecture search (ENAS) has impressed the researchers due to the excellent heuristic exploration capability. However, the evolutionary algorithm-based NAS are prone to the loss of population diversity in the search process, causing that the structure of the surviving individuals is exceedingly similar, which will lead to premature convergence and fail to explore the search space comprehensively and effectively. To address this issue, we propose a novel indicator, named architecture entropy, which is used to measure the architecture diversity of population. Based on this indicator, an effective sampling strategy is proposed to select the candidate individuals with the potential to maintain the population diversity for environmental selection. In addition, an unified encoding scheme of topological structure and computing operation is designed to efficiently express the search space, and the corresponding population update strategies are suggested to promote the convergence. The experimental results on several image classification benchmark datasets CIFAR-10 and CIFAR-100 demonstrate the superiority of our proposed method over the state-of-the-art comparison ones. To further validate the effectiveness of our method in real applications, our proposed NAS method is applied in the identification of lumbar spine X-ray images for osteoporosis diagnosis, and can achieve a better performance than the commonly used methods. Our source codes are available at https://github.com/LabyrinthineLeo/AEMONAS.

Image Quality Control in Lumbar Spine Radiography Using Enhanced U-Net Neural Networks.

PurposeTo standardize the radiography imaging procedure, an image quality control framework using the deep learning technique was developed to segment and evaluate lumbar spine x-ray images according to a defined quality control standard.Materials and MethodsA dataset comprising anteroposterior, lateral, and oblique position lumbar spine x-ray images from 1,389 patients was analyzed in this study. The training set consisted of digital radiography images of 1,070 patients (800, 798, and 623 images of the anteroposterior, lateral, and oblique position, respectively) and the validation set included 319 patients (200, 205, and 156 images of the anteroposterior, lateral, and oblique position, respectively). The quality control standard for lumbar spine x-ray radiography in this study was defined using textbook guidelines of as a reference. An enhanced encoder-decoder fully convolutional network with U-net as the backbone was implemented to segment the anatomical structures in the x-ray images. The segmentations were used to build an automatic assessment method to detect unqualified images. The dice similarity coefficient was used to evaluate segmentation performance.ResultsThe dice similarity coefficient of the anteroposterior position images ranged from 0.82 to 0.96 (mean 0.91 ± 0.06); the dice similarity coefficient of the lateral position images ranged from 0.71 to 0.95 (mean 0.87 ± 0.10); the dice similarity coefficient of the oblique position images ranged from 0.66 to 0.93 (mean 0.80 ± 0.14). The accuracy, sensitivity, and specificity of the assessment method on the validation set were 0.971–0.990 (mean 0.98 ± 0.10), 0.714–0.933 (mean 0.86 ± 0.13), and 0.995–1.000 (mean 0.99 ± 0.12) for the three positions, respectively.ConclusionThis deep learning-based algorithm achieves accurate segmentation of lumbar spine x-ray images. It provides a reliable and efficient method to identify the shape of the lumbar spine while automatically determining the radiographic image quality.

Radiologic assessment of abdominal aortic calcifications, atherosclerotic burden levels and statistical bias affecting the reliability

IntroductionAAC-8 and AAC-24 are two widely used scales to evaluate abdominal aortic calcification (AAC) on X-ray images. Levels of ≥3 (AAC-8) and ≥5 points (AAC-24) are of high relevance since they are associated with greater risk of cardiovascular events. Given that it is unknown, our aim was to determine the reliability of both scales at those levels of atherosclerotic burden. MethodsThe sample (93 subjects, 67.3 ± 9.7 years, BMI 28.8 ± 3.8, 57.6% smokers, 64.1% with hypertension) was classified according to quartiles of calcification. Six clinicians evaluated AAC independently with both scales on lateral lumbar spine X-ray images. We analyzed inter-rater agreement with the intraclass correlation coefficient (ICC) and the Bland-Altman scatterplots. ResultsWe assessed 15 pairs of raters. Scores in both scales were significantly correlated with cardiovascular risk (r = 0.31 and r = 0.32; p < 0.005). Agreement was very high in the first quartile and moderate in the rest (p < 0.05). At cut-off points, ICC = 0.70 (95%CI, 0.54–0.86) and ICC = 0.68 (95%CI, 0.60–0.85) with AAC-8 and AAC-24. With the Bland-Altman method, mean of the differences ranged between 0 and 0.4 (AAC-8), and between 0.2 and 1 (AAC-24), while 95% limits of agreement showed values between 2.9 and 4.4 (AAC-8), and between 6 and 11.2 (AAC-24). Analyzing entire scales, ICC = 0.97 (95%CI, 0.97–0.98) and ICC = 0.98 (95%CI, 0.97–0.98) for AAC-8 and AAC-24, respectively. ConclusionBoth scales presented only moderate reliability at levels of atherosclerotic burden. Analyzing quartiles with ICC and the Bland-Altman plot showed concordant results. High global ICC values traditionally reported with both scales are likely biased. Implications for practiceAAC predicts subsequent vascular morbidity and mortality and should implicate evaluation of cardiovascular risk. Optimal visualisation of AAC and its correct assessment are mandatory in order to maximize patient care.

Can Diffuse Idiopathic Skeletal Hyperostosis Be Diagnosed by Plain Lumbar Spine X-Ray Findings Alone?

Study Design:Retrospective case-control studyObjectives:To determine whether diffuse idiopathic skeletal hyperostosis (DISH) can be diagnosed based on anterior longitudinal ligamental ossification in the lumbar spine using plain lumbar spine X-ray images.Methods:This study included 100 patients (59 men and 41 women; mean age, 64.8 ± 13.8 years; range, 27-89 years) who underwent computed tomography (CT) of the chest to the pelvis in our hospital and plain lumbar spine radiography within 6 months before and after CT scanning. DISH was diagnosed based on the thoracolumbar spine CT findings using Resnick’s diagnostic criteria. The patients were grouped according to DISH diagnosis into the DISH (+) and DISH (−) groups. On the frontal and lateral lumbar spine X-ray images, each spinal level from Th11/12 to L5/S was scored based on the Mata scoring system. The distribution of the Mata scores was compared between the 2 groups.Results:Forty (40%) patients were diagnosed with DISH based on the CT findings. A cutoff value ≥8 provided a sensitivity of 75% and specificity of 100% for diagnosing DISH, thus, indicating the validity of the cutoff value. In the DISH (−) group, no patient had ≥3 consecutive spinal levels with a Mata score ≥2, suggesting that DISH can be diagnosed on the basis of at least 3 consecutive spinal levels with a Mata score ≥2.Conclusion:On lumbar spine X-ray images of the T11/12 to L5/S levels, a Mata score ≥2 for at least 3 consecutive levels or a total score ≥8 strongly indicates the presence of DISH.

Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study.

Osteoporosis is a prevalent but underdiagnosed condition. As compared to dual-energy X-ray absorptiometry (DXA) measures, we aimed to develop a deep convolutional neural network (DCNN) model to classify osteopenia and osteoporosis with the use of lumbar spine X-ray images. Herein, we developed the DCNN models based on the training dataset, which comprising 1616 lumbar spine X-ray images from 808 postmenopausal women (aged 50 to 92years). DXA-derived bone mineral density (BMD) measures were used as the reference standard. We categorized patients into three groups according to DXA BMD T-score: normal (T≥-1.0), osteopenia (-2.5<T<-1.0), and osteoporosis (T≤-2.5). T-scores were calculated by using the BMD dataset of young Chinese female aged 20-40years as a reference. A 3-class DCNN model was trained to classify normal BMD, osteoporosis, and osteopenia. Model performance was tested in a validation dataset (204 images from 102 patients) and two test datasets (396 images from 198 patients and 348 images from 147 patients respectively). Model performance was assessed by the receiver operating characteristic (ROC) curve analysis. The results showed that in the test dataset 1, the model diagnosing osteoporosis achieved an AUC of 0.767 (95% confidence interval [CI]: 0.701-0.824) with sensitivity of 73.7% (95% CI: 62.3-83.1), the model diagnosing osteopenia achieved an AUC of 0.787 (95% CI: 0.723-0.842) with sensitivity of 81.8% (95% CI: 67.3-91.8); In the test dataset 2, the model diagnosing osteoporosis yielded an AUC of 0.726 (95% CI: 0.646-0.796) with sensitivity of 68.4% (95% CI: 54.8-80.1), the model diagnosing osteopenia yielded an AUC of 0.810 (95% CI, 0.737-0.870) with sensitivity of 85.3% (95% CI, 68.9-95.0). Accordingly, a deep learning diagnostic network may have the potential in screening osteoporosis and osteopenia based on lumbar spine radiographs. However, further studies are necessary to verify and improve the diagnostic performance of DCNN models.

Trabecular bone score (TBS) is associated with sub-clinical vertebral fractures in HIV-infected patients.

Fragility fractures risk is increased among HIV infected patients. Bone microstructure alterations, in addition to bone mineral density (BMD) reduction, might be responsible for the increased risk. The aim of this study was to determine the prevalence of vertebral fractures (VFs) and their association with trabecular bone score (TBS), an indirect index of bone microstructure, in a cohort of HIV-infected subjects. One-hundred and forty-one HIV-infected patients (87% males, median age 43years, 94% on stable antiretroviral therapy with undetectable viral load) underwent viro-immunological and bone metabolism biochemical screenings. Lumbar TBS and BMD at femoral neck, total hip, and lumbar spine, were measured with dual-energy X-ray absorptiometry (DXA). VFs were identified using the semiquantitative method and quantitative morphometric analysis from thoracic and lumbar spine X-ray images. VFs were observed in 19 patients (13.5%). BMD was below the expected range for age in 18 (12.8%) subjects. No significant differences were found stratifying VFs prevalence by BMD, whereas patients with lower TBS showed a higher prevalence of VFs (p=0.03). In multivariate analysis, TBS was the only factor significantly associated to VFs (OR=0.56; 95% CI=0.33-0.96; p=0.034), with increased fracture risk for lower TBS values. VFs are prevalent and associated with low TBS among HIV-positive patients, whereas no significant association was found with BMD.

Inter-observer reliability of detecting Dynesys pedicle screw using plain X-rays: a study on 50 post-operative patients

Dynamic stabilisation system for the spine (Dynesys) relies on titanium screw purchase within the pedicle. Decision on osseointegration is important especially when the patient becomes symptomatic following initial good outcome. Loose screws make the construct non-functional especially in symptomatic patients. Removal of Dynesys may become necessary to control patient's symptoms. In this study, we report interobserver reliability of X-ray for the interpretation of Dynesys pedicle screw osseointegration based on the diagnosis of "halo zone" and "Double halo zones" surrounding loose screw. Lumbar spine X-ray images of 50 patients in two views (AP and lateral) were selected from a random sample of 420 Dynesys patients. The total number of pedicle screws reviewed in this study was 260. The investigators (observers) were asked to state whether or not each pedicle screw is loose using "radiolucent zone sign". Observers were two expert orthopaedic spine consultant surgeons and one expert consultant radiologist and four specialist registrars (SpR) in orthopaedics and radiology. SpR assessments were repeated after 4 months with instructions to use "double-halo sign" for loose screws. The evaluation of interobserver agreement was performed by obtaining a Kappa (K) index. Using "radiolucent zone sign", Kappa Index (KI) among three consultants was 0.2198 at 95% CI (0.0520, 0.4916) while for all of the seven assessors (3 consultants and 4 SpR), KI was 0.1462 at 95% CI (0.0332, 0.2592). The use of "double-halo sign" was associated with KI of 0.666 at 95% CI (SE 0.83) among all of the 4 SpR. Based on plain X-ray "radiolucent zone sign", the inter-observer reliability of detecting loose Dynesys pedicle screw was poor (Kappa index of 0.2). On the other hand, using plain X-ray "double-halo sign" was associated with improved inter-observer reliability and validity.

Lordose lombar: estudo dos valores angulares e da participação dos corpos vertebrais e discos intervertebrais

Foi estudado, em indivíduos normais, o valor angular da lordose lombar e a participação dos corpos vertebrais e discos intervertebrais na sua composição. Foram avaliadas as radiografias da coluna lombar de 350 indivíduos normais e assintomáticos com a idade variando de 18 a 50 anos (média 29,0 anos ± 8,24), sendo 143 homens e 207 mulheres. Foram medidas a curvatura lombossacra (L1S1) e a curvatura lombolombar (L1L5). As medidas das curvaturas lombares e dos seus componentes apresentaram grande variabilidade. Foram observados valores médios de -61° para a curvatura lombossacra e de -45° para a curvatura lombolombar. As medidas dos corpos vertebrais apresentaram valores cifóticos para L1, neutros para L2, e progressivamente lordóticos de L3 a L5. Os discos intervertebrais apresentaram angulação lordótica progressiva desde L1-L2. Os elementos caudais da curvatura, discos intervertebrais L4-L5 e L5-S1 e o corpo vertebral L5 corresponderam a quase 60% medida angular da curvatura lombossacra. Foi observada diferença significante entre os sexos masculino e feminino para as medidas das curvaturas lombares, e dos corpos vertebrais L2 e L4, tendo sido observados valores maiores no sexo feminino. Foram observadas diferenças relacionadas à idade na medida das curvaturas lombares e dos corpos vertebrais.