Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3

scoliosis Related Abstracts

3 An Image Stitching Approach for Scoliosis Analysis

Authors: Siti Salbiah Samsudin, Hamzah Arof, Ainuddin Wahid Abdul Wahab, Mohd Yamani Idna Idris


Standard X-ray spine images produced by conventional screen-film technique have a limited field of view. This limitation may obstruct a complete inspection of the spine unless images of different parts of the spine are placed next to each other contiguously to form a complete structure. Another solution to producing a whole spine image is by assembling the digitized x-ray images of its parts automatically using image stitching. This paper presents a new Medical Image Stitching (MIS) method that utilizes Minimum Average Correlation Energy (MACE) filters to identify and merge pairs of x-ray medical images. The effectiveness of the proposed method is demonstrated in two sets of experiments involving two databases which contain a total of 40 pairs of overlapping and non-overlapping spine images. The experimental results are compared to those produced by the Normalized Cross Correlation (NCC) and Phase Only Correlation (POC) methods for comparison. It is found that the proposed method outperforms those of the NCC and POC methods in identifying both the overlapping and non-overlapping medical images. The efficacy of the proposed method is further vindicated by its average execution time which is about two to five times shorter than those of the POC and NCC methods.

Keywords: image stitching, MACE filter, panorama image, scoliosis

Procedia PDF Downloads 257
2 Evaluation the Influence of Trunk Bracing in Joint Contact Forces in Subjects with Scoliosis

Authors: Azadeh Jafari, Mohammad Taghi Karimi, Azadeh Nadi


Background: Scoliosis is the lateral curvature of the spine which may influence the abilities of the subjects during standing and walking. Most of the scoliotic subjects use orthosis to reduce the curve and to decrease the risk of curve progression. There was lack of information regarding the effects of orthosis on kinematic and joint contact force. Therefore, this research was done to highlight the effects of orthosis on the aforementioned parameters. Method: 5 scoliotic subjects were recruited in this study, with single curve less than 40 (females with age 13.2 ± 1.7). They were asked to walk with and without orthosis. The kinematic of the joints, force applied on the legs, moments transmitted through the joints and joint contact forces were evaluated in this study. Moreover, the lengths of muscles were determined by use of computer muscle control approach in OpenSim. Results: There was a significant difference between the second peak of vertical ground reaction force while walking with and without orthosis (p-value < 0.05). There was no difference between spatiotemporal gait parameters while walking with and without orthosis (P-value > 0.05). The mean values of joint contact forces (vertical component) increased by the use of orthosis, but the difference was not significant (p-value > 0.05). Conclusion: Although the kinematic of most of the body joints was not influenced by the use of orthosis, the joint contact force may be increased by orthosis. The increase in joint contact force may be due to the performance of orthosis which restricts the motions of pelvic and increases compensatory mechanism used by the subjects to decrease the side effects of the orthosis.

Keywords: kinetic, kinematic, scoliosis, joint contact force

Procedia PDF Downloads 68
1 Cobb Angle Measurement from Coronal X-Rays Using Artificial Neural Networks

Authors: Andrew N. Saylor, James R. Peters


Scoliosis is a complex 3D deformity of the thoracic and lumbar spines, clinically diagnosed by measurement of a Cobb angle of 10 degrees or more on a coronal X-ray. The Cobb angle is the angle made by the lines drawn along the proximal and distal endplates of the respective proximal and distal vertebrae comprising the curve. Traditionally, Cobb angles are measured manually using either a marker, straight edge, and protractor or image measurement software. The task of measuring the Cobb angle can also be represented by a function taking the spine geometry rendered using X-ray imaging as input and returning the approximate angle. Although the form of such a function may be unknown, it can be approximated using artificial neural networks (ANNs). The performance of ANNs is affected by many factors, including the choice of activation function and network architecture; however, the effects of these parameters on the accuracy of scoliotic deformity measurements are poorly understood. Therefore, the objective of this study was to systematically investigate the effect of ANN architecture and activation function on Cobb angle measurement from the coronal X-rays of scoliotic subjects. The data set for this study consisted of 609 coronal chest X-rays of scoliotic subjects divided into 481 training images and 128 test images. These data, which included labeled Cobb angle measurements, were obtained from the SpineWeb online database. In order to normalize the input data, each image was resized using bi-linear interpolation to a size of 500 × 187 pixels, and the pixel intensities were scaled to be between 0 and 1. A fully connected (dense) ANN with a fixed cost function (mean squared error), batch size (10), and learning rate (0.01) was developed using Python Version 3.7.3 and TensorFlow 1.13.1. The activation functions (sigmoid, hyperbolic tangent [tanh], or rectified linear units [ReLU]), number of hidden layers (1, 3, 5, or 10), and number of neurons per layer (10, 100, or 1000) were varied systematically to generate a total of 36 network conditions. Stochastic gradient descent with early stopping was used to train each network. Three trials were run per condition, and the final mean squared errors and mean absolute errors were averaged to quantify the network response for each condition. The network that performed the best used ReLU neurons had three hidden layers, and 100 neurons per layer. The average mean squared error of this network was 222.28 ± 30 degrees2, and the average mean absolute error was 11.96 ± 0.64 degrees. It is also notable that while most of the networks performed similarly, the networks using ReLU neurons, 10 hidden layers, and 1000 neurons per layer, and those using Tanh neurons, one hidden layer, and 10 neurons per layer performed markedly worse with average mean squared errors greater than 400 degrees2 and average mean absolute errors greater than 16 degrees. From the results of this study, it can be seen that the choice of ANN architecture and activation function has a clear impact on Cobb angle inference from coronal X-rays of scoliotic subjects.

Keywords: Artificial Neural Networks, Medical Imaging, scoliosis, cobb angle

Procedia PDF Downloads 1