Automatic analysis method of 3D images in patients with scoliosis by quantifying asymmetry in transverse contours

A preliminary study in classification of the severity of spine deformation in adolescents with lumbar/thoracolumbar idiopathic scoliosis using machine learning algorithms based on lumbosacral joint efforts during gait

To assess the severity and progression of adolescents with idiopathic scoliosis (AIS), radiography with X-rays is usually used. The methods based on statistical observations have been developed from 3D reconstruction of the trunk or topography. Machine learning has shown great potential to classify the severity of scoliosis on imaging data, generally on X-ray measurements. It is also known that AIS leads to the development of gait disorder. To our knowledge, machine learning has never been tested on spine intervertebral efforts during gait as a radiation-free method to classify the severity of spinal deformity in AIS. Develop automated machine learning algorithms in lumbar/thoracolumbar scoliosis to classify the severity of spinal deformity of AIS based on the lumbosacral joint (L5-S1) efforts during gait. The lumbosacral joint efforts of 30 individuals with lumbar/thoracolumbar AIS were used as distinctive features fed to the machine learning algorithms. Several tests were run using various classification algorithms. The labeling consisted of three classes reflecting the severity of scoliosis i.e. mild, moderate and severe. The ensemble classifier algorithm including k-nearest neighbors, support vector machine, random forest and multilayer perceptron achieved the most promising results, with accuracy scores of 91.4%. This preliminary study shows lumbosacral joint efforts can be used to classify the severity of spinal deformity in lumbar/thoracolumbar AIS. This method showed the potential of being used as an assessment tool to follow-up the progression of AIS as a radiation-free method, alternative to radiography. Future studies should be performed to test the method on other categories of AIS.

Scoliosis assessment tools to reduce follow-up X-rays

Purpose

Clinical examinations of scoliosis often includes X-rays. Regular clinical monitoring is recommended in particular at young age, because of the high risk of progression during periods of rapid growth. Supplementary methods free of ionizing radiation thus could help to reduce the potential risk of ionizing radiation related health problems.

Methods

Twelve 3D scan images from female and male patients with different types and severities of spinal deformations were analysed using body scanner image analysis tools. The scan images were captured with a 3D body scanner, which used an infrared sensor and a video camera. To calculate and compare with the patient's specific spinal deformations, simulations based on finite elements methods were performed on biomechanical models of ribcage and spinal column.

Results

The methods and parameters presented here are in good agreement with corresponding X-rays, used for comparison. High correlation coefficients of ‖ρ _s ‖ ≥ 0.87 between Cobb angle and lateral deviation, as well as between Cobb angle and rotation of the vertebrae, indicate that the parameters could provide supplementary informations in the assessment of spinal deformations. So-called apex angles, in addition introduced to relate the results of the present method with Cobb angles, show strong correlations of ‖ρ _s ‖ ≥ 0.68 and thus could be used for comparison in later follow-up examinations.

Conclusion

The user-friendly 3D body scanner image analysis tools enable orthopaedic specialists to simulate, visualize and inspect patient's specific spinal deformations. The method is intended to provide supplementary information in complement to the Cobb angle for the assessment of spinal deformations in clinical daily routine and might have the potential to reduce X-rays in follow-up examinations.

The Translational Potential of this article

The study presents a new method, based on 3D body scanner images and biomechanical modelling, that has the potential to reduce X-rays when monitoring scoliosis especially in young patients.

A non-invasive method for scoliosis assessment—A new mathematical concept using polar angle

Scoliosis is one of the most common pediatric spinal diseases that leads to a three-dimensional deformity of the spine and has a high risk of progression during growth. Regular clinical monitoring and follow-up X-rays are needed to providing proper treatment at that time. Repetitive X-rays can results in an increased risk of radiation related health problems. We present a non-invasive, ionizing radiation-free method for assessing scoliosis and its progression from the 3D images of the body torso, captured by a body scanner. A new concept is introduced based on a mathematical method in polar coordinate system to quantify and characterize the deformities in the torso from 2D transverse cross-sections of the 3D torso images at example cases for a healthy individual and for two patients with scoliosis. To capture quantitatively the characteristics of scoliosis, and to verify them at the example cases two asymmetry parameters and a linear fitting parameter are calculated: a) back side area asymmetry, b) left right area asymmetry, and c) coefficient of determination (R²). Within the analyzed patients, both the area asymmetries are maximum at the apex of scoliosis, and increase with the severity of scoliosis. R² values are smaller in the case of patients compared with the healthy. Furthermore, the parameters show a trend when compared with the Cobb angle from the X-ray and the findings match with clinical examination. Therefore, the quantities are able to capture, certain characteristics associated with scoliosis. These quantities can be compared as a measure of deformities of torso, during the follow-up examinations in the future, without ionizing radiations.

Model-Based Radiation-Free Assessment of Scoliosis: A Principle Validation Study

Purpose

Adolescent scoliosis is one of the common pediatric spinal diseases which has a high risk of progression due to the rapid growth of the skeleton during the growing stage therefore needs regular clinical monitoring including X-rays. Because X-rays could lead to ionizing radiation-related health problems, an ionizing radiation-free, non-invasive method is presented here to estimate the degree of scoliosis and to potentially support the medical assessment.

Methods

The radiation-free body scanner provides a 3D surface scan of the torso. A basic 3D structure of the human ribcage and vertebral column was modeled and simulated with computer-aided design software and finite element method calculation. For comparison with X-rays, courses of vertebral columns derived from 3D torso images and 3D models were analyzed with respect to their apex positions and angles.

Results

The methods show good results in the estimation of the apex positions of scoliosis. Strong correlations (R = 0.8924) were found between the apex and Cobb angle from X-rays. Similar correlations (R = 0.8087) was obtained between the apex angles extracted from X-rays and the combination of torso scan images with 3D model simulations. Promising agreement was obtained between the spinal trajectories extracted from X-ray and 3D torso images.

Conclusions

Very strong correlations suggest that the apex angle could potentially be used for scoliosis assessment in follow-up examinations in complement to the Cobb angle. However, further improvements of the methods and tests on a larger number of data set are necessary before their introduction into the clinical application.

Assessment of adolescent idiopathic scoliosis from body scanner image by finite element simulations

Adolescent idiopathic scoliosis, is a three-dimensional spinal deformity characterized by lateral curvature and axial rotation around the vertical body axis of the spine, the cause of which is yet unknown. The fast progression entails regular clinical monitoring, including X-rays. Here we present an approach to evaluate scoliosis from the three-dimensional image of a patient’s torso, captured by an ionizing radiation free body scanner, in combination with a model of the ribcage and spine. A skeletal structure of the ribcage and vertebral column was modelled with computer aided designed software and was used as an initial structure for macroscopic finite element method simulations. The basic vertebral column model was created for an adult female in an upright position. The model was then used to simulate the patient specific scoliotic spine configurations. The simulations showed that a lateral translation of a vertebral body results in an effective axial rotation and could reproduce the spinal curvatures. The combined method of three-dimensional body scan and finite element model simulations thus provide quantitative anatomical information about the position, rotation and inclination of the thoracic and lumbar vertebrae within a three-dimensional torso. Furthermore, the simulations showed unequal distributions of stress and strain profiles across the intervertebral discs, due to their distortions, which might help to further understand the pathogenesis of scoliosis.