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

Analyzing lumbar vertebral shape and alignment in female patients with degenerative spondylolisthesis: Comparisons with spinal stenosis and risk factor exploration

PURPOSE

This study aimed to examine the vertebral body shape characteristics and spondylopelvic alignment in L4 degenerative spondylolisthesis (DS) as well as the risk factors for the development of DS.

METHODS

This cross-sectional study compared vertebral morphology and sagittal spinopelvic alignment in female patients with lumbar DS and lumbar spinal stenosis (LSS). The degree of lumbar lordosis (LL), pelvic incidence (PI), cross-sectional area (CSA), and vertebral body height ratio (ha/hp) of the lumbar spine were compared using full-length spine radiographs and computed tomography in 60 females with DS and in 60 women with LSS.

RESULTS

No significant differences in age or body mass index were observed between the two groups; however, the DS and LSS groups significantly differed in PI (mean, 58.9±10.8 vs. 47.2±11.6, P < 0.001), L4 CSA (mean, 1,166.2 m2 vs. 1,242.0 m2, P = 0.002) and ha/hp (mean, 1.134 vs. 1.007, P < 0.001). The L4 ha/hp was significantly higher in the DS group than in the LSS group. Additionally, LL values were negatively correlated with vertebral L5 CSA in the DS group (r = -0.28, P < 0.05). The LSS and DS groups demonstrated positive correlations between LL and L2, L3, and L4 ha/hp (r = 0.331, 0.267, and 0.317; P < 0.01, < 0.05, and < 0.05, respectively) and between LL and L4 and L5 ha/hp (r = 0.333, 0.331; P < 0.01, respectively). Multivariate regression analyses revealed that PI and ha/hp ratio may be independent predictors of DS development.

CONCLUSION

The DS group had significantly larger LL, PI, and L4 ha/hp and smaller L4 CSA than the LSS group. The lumbar vertebral body shape and sagittal spinopelvic alignment in females might be independent predictors of DS development.

VerteFormer: A single-staged Transformer network for vertebrae segmentation from CT images with arbitrary field of views

BACKGROUND

Spinal diseases are burdening an increasing number of patients. And fully automatic vertebrae segmentation for CT images with arbitrary field of views (FOVs), has been a fundamental research for computer-assisted spinal disease diagnosis and surgical intervention. Therefore, researchers aim to solve this challenging task in the past years.

PURPOSE

This task suffers from challenges including the intra-vertebrae inconsistency of segmentation and the poor identification of biterminal vertebrae in CT scans. And there are some limitations in existing models, which might be difficult to be applied to spinal cases with arbitrary FOVs or employ multi-stage networks with too much computational cost. In this paper, we propose a single-staged model called VerteFormer which can effectively deal with the challenges and limitations mentioned above.

METHODS

The proposed VerteFormer utilizes the advantage of Vision Transformer (ViT), which does well in mining global relations for input data. The Transformer and UNet-based structure effectively fuse global and local features of vertebrae. Beisdes, we propose the Edge Detection (ED) block based on convolution and self-attention to divide neighboring vertebrae with clear boundary lines. And it simultaneously promotes the network to achieve more consistent segmentation masks of vertebrae. To better identify the labels of vertebrae in the spine, particularly biterminal vertebrae, we further introduce global information generated from the Global Information Extraction (GIE) block.

RESULTS

We evaluate the proposed model on two public datasets: MICCAI Challenge VerSe 2019 and 2020. And VerteFormer achieve 86.39% and 86.54% of dice scores on the public and hidden test datasets of VerSe 2019, 84.53% and 86.86% of dice scores on VerSe 2020, which outperforms other Transformer-based models and single-staged methods specifically designed for the VerSe Challenge. Additional ablation experiments validate the effectiveness of ViT block, ED block and GIE block.

CONCLUSIONS

We propose a single-staged Transformer-based model for the task of fully automatic vertebrae segmentation from CT images with arbitrary FOVs. ViT demonstrates its effectiveness in modeling long-term relations. The ED block and GIE block has shown their improvements to the segmentation performance of vertebrae. The proposed model can assist physicians for spinal diseases' diagnosis and surgical intervention, and is also promising to be generalized and transferred to other applications of medical imaging.

Sequential conditional reinforcement learning for simultaneous vertebral body detection and segmentation with modeling the spine anatomy

Accurate vertebral body (VB) detection and segmentation are critical for spine disease identification and diagnosis. Existing automatic VB detection and segmentation methods may cause false-positive results to the background tissue or inaccurate results to the desirable VB. Because they usually cannot take both the global spine pattern and the local VB appearance into consideration concurrently. In this paper, we propose a Sequential Conditional Reinforcement Learning network (SCRL) to tackle the simultaneous detection and segmentation of VBs from MR spine images. The SCRL, for the first time, applies deep reinforcement learning into VB detection and segmentation. It innovatively models the spatial correlation between VBs from top to bottom as sequential dynamic-interaction processes, thereby globally focusing detection and segmentation on each VB. Simultaneously, SCRL also perceives the local appearance feature of each desirable VB comprehensively, thereby achieving accurate detection and segmentation result. Particularly, SCRL seamlessly combines three parts: 1) Anatomy-Modeling Reinforcement Learning Network dynamically interacts with the image and focuses an attention-region on the VB; 2) Fully-Connected Residual Neural Network learns rich global context information of the VB including both the detailed low-level features and the abstracted high-level features to detect the accurate bounding-box of the VB based on the attention-region; 3) Y-shaped Network learns comprehensive detailed texture information of VB including multi-scale, coarse-to-fine features to segment the boundary of VB from the attention-region. On 240 subjects, SCRL achieves accurate detection and segmentation results, where on average the detection IoU is 92.3%, segmentation Dice is 92.6%, and classification mean accuracy is 96.4%. These excellent results demonstrate that SCRL can be an efficient aided-diagnostic tool to assist clinicians when diagnosing spinal diseases.

Thoracolumbar spine loading associated with kinematics of the young and the elderly during activities of daily living

Excessive mechanical loading of the spine is a critical factor in vertebral fracture initiation. Most vertebral fractures develop spontaneously or due to mild trauma, as physiological loads during activities of daily living might exceed the failure load of osteoporotic vertebra. Spinal loading patterns are affected by vertebral kinematics, which differ between elderly and young individuals. In this study, the effects of age-related changes in spine kinematics on thoracolumbar spinal segmental loading during dynamic activities of daily living were investigated using combined experimental and modeling approach. Forty-four healthy volunteers were recruited into two age groups: young (N = 23, age = 27.1 ± 3.8) and elderly (N = 21, age = 70.1 ± 3.9). The spinal curvature was assessed with a skin-surface device and the kinematics of the spine and lower extremities were recorded during daily living tasks (flexion-extension and stand-sit-stand) with a motion capture system. The obtained data were used as input for a musculoskeletal model with a detailed thoracolumbar spine representation. To isolate the effect of kinematics on predicted loads, other model properties were kept constant. Inverse dynamics simulations were performed in the AnyBody Modeling System to estimate corresponding spinal loads. The maximum compressive loads predicted for the elderly motion patterns were lower than those of the young for L2/L3 and L3/L4 lumbar levels during flexion and for upper thoracic levels during stand-to-sit (T1/T2-T8/T9) and sit-to-stand (T3/T4-T6/T7). However, the maximum loads predicted for the lower thoracic levels (T9/T10-L1/L2), a common site of vertebral fractures, were similar compared to the young. Nevertheless, these loads acting on the vertebrae of reduced bone quality might contribute to a higher fracture risk for the elderly.