A comparative analysis of 4 curvature measurement methods in early-onset scoliosis

W-Transformer: Accurate Cobb angles estimation by using a transformer-based hybrid structure

BACKGROUND

Scoliosis is a type of spinal deformity, which is harmful to a person's health. In severe cases, it can trigger paralysis or death. The measurement of Cobb angle plays an essential role in assessing the severity of scoliosis.

PURPOSE

The aim of this paper is to propose an automatic system for landmark detection and Cobb angle estimation, which can effectively help clinicians diagnose and treat scoliosis.

METHODS

A novel hybrid framework was proposed to measure Cobb angle precisely for clinical diagnosis, which was referred as W-Transformer due to its w-shaped architecture. First, a convolutional neural network of cascade residual blocks as our backbone was designed. Then a transformer was fused to learn the dependency information between spine and landmarks. In addition, a reinforcement branch was designed to improve the overlap of landmarks, and an improved prediction module was proposed to fine-tune the final coordinates of landmarks in Cobb angles estimation. Besides, the public AASCE MICCAI 2019 challenge was served as dataset. It supplies 609 manually labeled spine AP X-ray images, each of which contains a total of 68 landmark labels and three Cobb Angles tags.

RESULTS

From the perspective of the AASCE MICCAI 2019 challenge, we achieved a lower symmetric mean absolute percentage error (SMAPE) of 8.26% for all Cobb angles and the lowest averaged detection error of 50.89 in terms of landmark detection, compared with many state-of-the-art methods. We also provided the SMAPEs for the Cobb angles of the Proximal-Thoracic (PT), the Main-Thoracic (MT) and the Thoracic-Lumbar (TL) area, which are 5.27%, 14.59% and 20.97% respectively, however, these data were not covered in most previous studies. Statistical analysis demonstrates that our model has obtained a high level of Pearson correlation coefficient of 0.9398 (p<0.001), which shows excellent reliability of our model. Our model can yield 0.9489 (p<0.001), 0.8817 (p<0.001) and 0.9149 (p<0.001$) for PT, MT and TL, respectively. The overall variability of Cobb angle measurement is less than 4°, implying clinical value. And the mean absolute deviation (Standard Deviation) for three regions is 3.64° (4.13°), 3.84° (4.66°) and 3.80° (4.19°). The results of Student paired t-test indicate that no statistically significant differences are observed between manual measurement and our automatic approach (p value is always > 0.05). Regarding the diagnosis of scoliosis (Cobb angle > 10°), the proposed method achieves a high sensitivity of 0.9577 and a specificity of 0.8475 for all spinal regions.

CONCLUSIONS

This study offers a brand-new automatic approach that is potentially of great benefit of the complex task of landmark detection and Cobb angle evaluation, which can provide helpful navigation information about the early diagnosis of scoliosis. This article is protected by copyright. All rights reserved.

A computerized method for evaluating scoliotic deformities using elliptical pattern recognition in X-ray spine images

BACKGROUND AND OBJECTIVE

Several studies have evaluated the reproducibility of the Cobb angle for measuring the degree of scoliotic deformities from X-ray spine images, and proposed different geometric models for describing the spinal curvature. The ellipse was shown to be an adequate geometric form, but was not yet applied for the identification and quantification of scoliotic curvatures. The purpose of this study is therefore to propose and validate a novel computerized methodology for the detection of elliptical patterns from X-ray images to evaluate the extent of the underlying scoliotic deformity.

METHODS

For anteroposterior each X-ray spine image, the spine curve is first reconstructed from vertebral centroids. The ellipse that best fits to the obtained spine curve is the found within a least square and genetic algorithm optimization framework. The geometric parameters of the resulting best fit ellipse are finally used to define an index that quantifies the spinal curvature.

RESULTS

The proposed methodology was validated on three synthetic images and then successfully applied to 20 clinical anteroposterior X-ray spine images of patients with a different degree of scoliotic deformity, with the resulting maximal relative error of 3% for the synthetic images and an overall error of 0.5 ± 0.4 mm (mean ± standard deviation) for the clinical cases.

CONCLUSIONS

The results indicate that the proposed computerized methodology is able to reliably reproduce scoliotic curvatures using the geometric parameters of the underlying ellipses. In comparison to conventional approaches, the proposed methodology potentially produces less errors, requires a relatively low observer interaction, takes into account all vertebrae within the observed scoliotic deformity, and allows for both qualitative and quantitative evaluations that may complement the diagnosis, study and treatment of scoliosis.

Reliability of Coronal Curvature Measures in Premature Scoliosis: Comparison of 4 Methods Using Inverted Digital Luminescence Radiography

STUDY DESIGN

Observational study with 4 examiners.

OBJECTIVE

To improve the reproducibility and reliability of coronal curvature measurements.

SUMMARY OF BACKGROUND DATA

Several different methods have been developed to measure coronal curvature. Inverted digital luminescence radiography may be an additional technique to improve the reliability of measurement methods.

METHODS

A total of 114 whole spine posterior-anterior radiographs were collected to compare the reliability of 4 measurement methods used in early onset scoliosis. Each radiograph was measured twice by each of 4 examiners using 4 measurement methods with normal and inversion views. Data were analyzed to determine inter- and intraobserver reliabilities.

RESULTS

For all 4 methods, the overall intraobserver ICCs were greater than 0.926 and the interobserver ICCs were greater than 0.902, indicating excellent reliability. When intraobserver reliability was assessed in relation to scoliosis severity (<20°, 20°-40°, and >40°), the ICCs were higher for greater degrees of curvature; nonetheless, these values were in the excellent range for all methods and were higher for inversion (>0.908) than normal (>0.838) radiographs. For interobserver comparisons, the ICCs were better for the pedicle method (normal: >0.795, inversion: >0.831) than for the other methods (normal: >0.532, inversion: >0.590), with inverted digital luminescence radiography showing the higher ICCs.

CONCLUSION

Inversion radiographs showed high reliability and may increase reliability in cases of less deformed spines. In addition, the pedicle method led to higher ICCs for all measurements regardless of severity, especially on inversion radiographs.

LEVEL OF EVIDENCE

2.

Intramedullary gangliogliomas: clinical features, surgical outcomes, and neuropathic scoliosis

Intramedullary spinal cord gangliogliomas are rare tumors composed of glial components and ganglion cells. These gangliogliomas are generally considered as slow-growing tumors, corresponding histologically to WHO grade I or II. There are few reports of large case series of intramedullary spinal cord gangliogliomas from a single center. We retrospectively reviewed a consecutive series of 18 patients with pathologically diagnosed ganglioglioma. Clinical manifestations, radiological features, treatment and follow-up data, and concomitant scoliosis were investigated. The mean age at diagnosis was 27.5 years, with a slight female predominance. The primary clinical symptoms were sensorimotor deficits. Magnetic resonance (MR) imaging manifestations varied considerably. Some associated, but not necessary, features were found, such as young age at onset, large tumor dimension, and bony changes. Scoliosis was observed in seven patients. Remnant tumor progression was observed in five patients during the follow-up period, and no deaths occurred. The last neurological evaluation showed functional improvement from preoperative status in five patients. Differential diagnosis of ganglioglioma based on MR images alone is challenging, but the combination of some characteristic features can be helpful. An accurate diagnosis of ganglioglioma depends on pathological criteria. Despite the benign course of ganglioglioma, considerable growth may affect its resectability and prognosis. The extent of resection should be meticulously planned, and the potential risk of recurrence and neurological deterioration should be evaluated. The concomitant scoliosis is noteworthy.