Search

This paper describes a method of characterizing the torso shape deformity associated with scoliosis by both its type and severity. This problem is challenging because regular human torsos show an astounding range of variations that is only compounded by scoliosis, and it is difficult to isolate natural shape variations from those caused by scoliosis. Torso shape characterization is important in the clinical management of scoliosis because torso aesthetics is a key concern that influences a patient's quality of life. Our method involves modeling 3-D torso range images into structured sequences of 3-D spline curves stacked along the spine. We obtain local shape measures from points of maximal curvature (dominant points) along each torso cross section by evaluating the relative symmetry of the spline curve at that cross section. This results in a scalable characterization scheme for torso deformity type and a measure of torso deformity severity. We assess the accuracy and precision of this shape characterization scheme, and its relationship to the actual deformities present in the underlying spine. Index Terms--Dominant points, object recognition, scoliosis, shape analysis, splines.

This paper presents a technique for evaluating torso shape and asymmetry in scoliosis using indices of point-set data obtained from torso surface scans. Point-set data are the maximum curvature points of a surface scan and contain key shape information. The centroids, distributions and densities of point-set data are indices of shape and asymmetry. The mean-squared deviations of the centroids per-cross-section from the medial plane are indicative of asymmetry. The distribution and density of point-set data are indicative of shape. Evaluations using point-set data indices were 100% in accord with those based on the cosmetic score. Indices of point-set data have more degrees of freedom and were able to distinguish between scans that have similar cosmetic scores. [ABSTRACT FROM AUTHOR]

This paper presents a procedure for pre-processing and reconstructing surface scans comprising an interactive technique for cropping stray points and extremities. The procedure involves three stages: cross-sectioning and clipping, hole-filling and sub-sampling, and surface re-generation. The accuracy of the reconstruction obtained was assessed by creating different patterns of holes and stray points on 30 models of the torso and pre-processing the models using the proposed procedure and existing procedures based on Bezier interpolation and Moving Least Squares (MLS) interpolation. Results obtained indicate that the proposed procedure was at least as good as the better of Bezier and MLS interpolation for all the models tested, particularly outperforming both procedures when holes account for up to 5% of the surface. Its accuracy of reconstruction ranged from 90–100% compared to 80–100% for Bezier and 50–100% for MLS. This work is a crucial step in developing techniques for understanding and assessing changes in torso shape and symmetry from torso surface scans of scoliosis patients. [ABSTRACT FROM AUTHOR]

A support vector machines (SVM) classifier was used to assess the severity of idiopathic scoliosis (IS) based on surface topographic images of human backs. Scoliosis is a condition that involves abnormal lateral curvature and rotation of the spine that usually causes noticeable trunk deformities. Based on the hypothesis that combining surface topography and clinical data using a SVM would produce better assessment results, we conducted a study using a dataset of 111 IS patients. Twelve surface and clinical indicators were obtained for each patient. The result of testing on the dataset showed that the system achieved 69–85% accuracy in testing. It outperformed a linear discriminant function classifier and a decision tree classifier on the dataset. [ABSTRACT FROM AUTHOR]

A support vector classifier (SVC) approach was employed in predicting the risk of progression of adolescent idiopathic scoliosis (AIS), a condition that causes visible trunk asymmetries. As the aetiology of AIS is unknown, its risk of progression can only be predicted from measured indicators. Previous studies suggest that individual indicators of AIS do not reliably predict its risk of progression. Complex indicators with better predictive values have been developed but are unsuitable for clinical use as obtaining their values is often onerous, involving much skill and repeated measurements taken over time. Based on the hypothesis that combining common indicators of AIS using an SVC approach would produce better prediction results more quickly, we conducted a study using three datasets comprising a total of 44 moderate AIS patients (30 observed, 14 treated with brace). Of the 44 patients, 13 progressed less than 5° and 31 progressed more than 5°. One dataset comprised all the patients. A second dataset comprised all the observed patients and a third comprised all the brace-treated patients. Twenty-one radiographic and clinical indicators were obtained for each patient. The result of testing on the three datasets showed that the system achieved 100% accuracy in training and 65%-80% accuracy in testing. It outperformed a "statistically equivalent" logistic regression model and a stepwise linear regression model on the said datasets. It took less than 20 min per patient to measure the indicators, input their values into the system, and produce the needed results, making the system viable for use in a clinical environment. [ABSTRACT FROM AUTHOR]

Morphological shape analysis refers to the ability to understand how anatomical structures tend to vary due to various reasons such as: development of certain pathology, aging, and surgery. The medical imaging research community is constantly concerned with enhancing the ability to distinguish between anatomy of healthy individuals and those with pathology. This paper focuses on analysis of human vertebral structures. Medical experts often examine hundreds of spine x-rays to determine existence of various vertebral pathologies. In this paper, we present a novel framework for analysis of vertebral structures. We propose to perform shape-based morphological analysis of vertebral structures using parameters of a multi-scale shape model. The framework uses wavelet-ICA shape representation in combination with regression analysis and hypothesis testing methods. The new framework incorporates the following: rich multi-scale representation of vertebral shapes using wavele t-ICA, feature selection approaches, and statistical analysis techniques. We aim at the following: (a) Discriminate between two groups of normal and pathological vertebrae. (b) Establish relationship between localized modes of variations and clinical outcome variables. We demonstrate the ability of the proposed framework to localize shape changes in vertebral structures related to various pathologies. Experiments have demonstrated the ability of the proposed framework to discriminate between classes of normal and pathological vertebrae. Within a regression analysis framework, we were able to establish a statistically relevant relationship between the wavelet-ICA modes of deformations and clinical information. [ABSTRACT FROM AUTHOR]

The study of external back shape deformity in scoliosis is often dependent on 3D imaging of the torso, which use 3D laser scanners, rasterography etc. Use of a stereo digital camera imaging system to construct the 3D image provides a cheaper alternative. Calibration of the pair of digital cameras is an essential part of this process. Calibration is done to determine the geometry between the pair of cameras and the patient. Firstly, calibration requires acquisition of one or more images of an object containing landmarks of known position and dimensions such as checkerboard, pegboard etc. Then, manual identification of these landmarks are performed. Both of these steps are tedious and time consuming. This paper presents a novel approach of automated template matching on a pegboard image followed by Hartley's 8-Point algorithm to determine the underlying geometry. We use a pair of stereo cameras, the pegboard and the subject in a unique setup to eliminate the need for aquiring images as part of the calibration process. The method was compared to commonly used methods of calibration such as Direct Linear Transform (DLT) and the Camera Calibration Matlab Toolbox developed by Jean-Yves Bouguet. Results indicate that the procedure was atleast 75% faster than the existing methods. It‘s accuracy ranged from 90–100% compared to 75–100% for existing methods. This work provides a faster alternative to existing calibration processes which are prone to human errors. It is an important step towards making stereo digital camera systems a useful clinical tool in 3D torso imaging. [ABSTRACT FROM AUTHOR]

Introduction: Most of the computer vision techniques used to analyze the scoliosis deformities are based on studying the internal deformation of the spine. The imaging techniques used in these algorithms are mostly based on MRI and Xray imaging. Repetitive exposure to these imaging techniques could yield severe side effects. Recent approaches for assessing spinal deformities study the exterior surface topography of the torso. Photogrammetry can be used in the measurement of the patient's torso and in the surface reconstruction of the human back. Objective: This paper contributes to this line of research by developing an intensity based image registration method to align smooth featureless images of the human back. The output of the registration process is then used to reconstruct the shape of the human back. Materials and methods: A modified coarse-to-fine scheme is adopted in order to contend with larger deformations while still capturing small deformations. A steerable pyramid is built for both the source and target images. The calculated field is accumulated with the field at the next level of the pyramid. A new field is computed at new level and the process is repeated through each level. To register stereo images, epipolar constraints are employed in the registration process. The proposed method put into consideration the change in object appearance due to lighting conditions. Results: Images for volunteers at the University of Alberta are used in our experiments. Additionally, three dimensional objects with known dimensions are used to measure the accuracy of the stereo reconstruction process. Conclusions: In this paper, new framework for reconstructing the surface of the human back for scoliotic patients is proposed and tested. Experimental results show the ability of optical flow registration algorithms to generate accurate disparities that could be used in the 3D reconstruction problem. [ABSTRACT FROM AUTHOR]

This paper presents a procedure for pre-processing and reconstructing surface scans comprising an interactive technique for cropping stray points and extremities. The procedure involves three stages: cross-sectioning and clipping, hole-filling and sub-sampling, and surface re-generation. The accuracy of the reconstruction obtained was assessed by creating different patterns of holes and stray points on 30 models of the torso and pre-processing the models using the proposed procedure and existing procedures based on Bezier interpolation and Moving Least Squares (MLS) interpolation. Results obtained indicate that the proposed procedure was at least as good as the better of Bezier and MLS interpolation for all the models tested, particularly outperforming both procedures when holes account for up to 5% of the surface. Its accuracy of reconstruction ranged from 90-100% compared to 80-100% for Bezier and 50-100% for MLS. This work is a crucial step in developing techniques for understanding and assessing changes in torso shape and symmetry from torso surface scans of scoliosis patients.

This paper presents a technique for evaluating torso shape and asymmetry in scoliosis using indices of point-set data obtained from torso surface scans. Point-set data are the maximum curvature points of a surface scan and contain key shape information. The centroids, distributions and densities of point-set data are indices of shape and asymmetry. The mean-squared deviations of the centroids per-cross-section from the medial plane are indicative of asymmetry. The distribution and density of point-set data are indicative of shape. Evaluations using point-set data indices were 100% in accord with those based on the cosmetic score. Indices of point-set data have more degrees of freedom and were able to distinguish between scans that have similar cosmetic scores.

In order to study a physiotherapeutic approach to idiopathic scoliosis treatment a posture monitoring system is being built. The system is a small, lightweight, fully portable system capable of monitoring and providing feedback to a patient regarding their posture. Using the combination of accelerometer and electromagnetic technology, distance and angle measurements can be obtained for receivers placed strategically on the patient's back. This data is recorded for further analysis of the patient's progress and to provide immediate feedback to the patient on the status of their posture. Preliminary testing has shown that angular changes of one degree can be detected by the system and that the speed of the electromagnetic field detection has been increased ten times greater than the previous architecture.