Classifying torso deformity in scoliosis using orthogonal maps of the torso

Ajemba, Peter O.; Durdle, N.G.; Hill, Doug; Raso, V.J.

doi:10.1007/s11517-007-0192-z

Cited by 19 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They are not with correlation between trunk asymmetry and cob angle and there is risk of obtaining false negativity is low (high sensitivity) but false positivity is high (low specificity) of those methods of examinations [25][26][27][28][29]. There is one quantitative method with spine mouse device, and we have personal experiences with it, but it is significant only for spine deformity in sagital plane [30][31][32].…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Scoliosis Deviation with Clinical Measurements during Physical Therapy

Ramova

Poposka²,

Lazović³

et al. 2013

Maced J Med Sci

View full text Add to dashboard Cite

Aim: Scoliosis is a 3D deformation, in a vast related medical literature, we can find quit a few scoliosis evaluation indices, which are based on back surface data and are generally measured along three planes. The purpose of this study was to assess the usefulness of surface clinical measurements for evaluation of condition by patients with scoliosis in shorter terms. Materials and Method:A total of 40 scoliosis patients, with an average age of 13 years, the average Risser sign 3 and an average angle of curvature of 23.67° according to Cobb were included in this study. In research were looking a correlation between convexity of curve by xray picture and asymmetry of measurement distances.Results: the data analyze is showing a correlation between decrease of clinical asymmetry and reduction of curve by treatment with significance p < 0.01. The trunk surface asymmetry is still difficult to objectify and it depended of new examination technique shall be done more. Conclusion:External measurements of some anatomical points can be use in physical therapy practice for evaluation of condition by patients with scoliosis with significant correlation of convexity of curve.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of Scoliosis Deviation with Clinical Measurements during Physical Therapy

Ramova

Poposka²,

Lazović³

et al. 2013

Maced J Med Sci

View full text Add to dashboard Cite

show abstract

“…O sistema de mapas ortogonais ao avaliar indivíduos com escoliose apresentou precisão na classificação de alterações posturais de 95.5% (Ajemba, Durdle, Hill, & Raso, 2007). Entretanto, os resultados do sistema de mapas ortogonais foram comparados ao exame médico clínico e não com o exame radiográfico, fragilizando esses resultados.…”

Section: Estudosunclassified

Métodos não invasivos de avaliação postural da escoliose: Uma revisão sistemática

Sedrez¹,

Candotti²

2013

Motricidade

View full text Add to dashboard Cite

ARTIGO DE REVISÃO | REVIEW ARTICLE RESUMOA escoliose é um desvio tridimensional da linha vertical da coluna vertebral, muitas vezes de difícil visualização e quantificação. Por isso, diversos estudos desenvolveram metodologias para a sua avaliação, mas ainda é incipiente uma discussão aprofundada, a fim de facilitar a escolha do método. O objetivo dessa revisão sistemática é verificar a existência de evidências científicas sobre os métodos alternativos para avaliação não invasiva da escoliose. Adopting the following inclusion criteria: addressing patients with scoliosis and involve assessment postural noninvasive, and exclusion: not describe the evaluation method used or approach treatment and not be written in English. At the beginning, 200 articles were found. After checking the titles and abstracts, eight articles were selected and 12 articles were included in the bibliographical references (i.e. an overall number of 20 articles). Of these, 18 studies were included in the quality criteria. Overall, the studies showed satisfactory results for the evaluation of scoliosis, being observed differences between the methods in time needed to perform the evaluation, system cost, complexity of the procedures to be carried out and data collected. These systems do not replace X-ray as gold-standard, even though it can be used to reduce the radiation exposure.

show abstract

“…In fact, significant correlations were found between scoliosis deformities and Moire fringe deviations, but the false-positive rate was as high as 50 percent and the Moire fringe is sensitive to small movement of the patient [4,7]. New studies were extended to the acquisition and the analysis of the entire trunk in order to take into account the whole trunk asymmetry [11][12][13][14][15][16]. However, human torso shape has many variations and its analysis is very challenging.…”

Section: Introductionmentioning

confidence: 99%

Non invasive classification system of scoliosis curve types using least-squares support vector machines

Adankon

Dansereau

Cheriet

2012

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Non invasive classification system of scoliosis curve types using least-squares support vector machines." Artificial Intelligence in Medicine, Vol. 56, no. 2 (2012): pp. 99-107.The final publication is available via the DOI: http://dx.doi.org/10.1016/j.artmed.2012.07.002The manuscript, in a draft version prior to being accepted by the publisher, is reproduced in the following pages. Mathias AbstractObjective: To determine scoliosis curve types using non invasive acquisition, without any prior knowledge on X-ray data.Methods: Classification of scoliosis deformities according to curve type is used to plan management of scoliosis patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of 3D back surface of the patients. The 3D image of back surface of the trunk is divided into patches and local geometric descriptors characterizing the surface of the back are computed from each patch and forming the features. We perform the reduction of the dimensionality by using principal component analysis and retain 53 components using overlap criterion combined with the total variance in the observed variables. In this work a multi-class classifier is built with leastsquares support vector machine (LS-SVM). The original LS-SVM formulation was modified by weighting differently the positive and negative samples and a new kernel was designed in order to achieve a robust classifier. The proposed system was validated using data of 165 patients with different scoliosis curve types. A comparison of the results of a non invasive classification was done with those obtained by an expert using X-ray images.Results: The average rate of successful classification was computed using * Corresponding author Email addresses: mathias-mahouzonsou.adankon@polymtl.ca (Mathias M. Adankon), jean.dansereau@polymtl.ca (Jean Dansereau), hubert.labelle@recherche-ste-justine.qc.ca (Hubert Labelle), farida.cheriet@polymtl.ca (Farida Cheriet) Preprint submitted to ElsevierJuly 16, 2012 leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. Considering the correct classification rate per class, we obtained 96%, 84% and 97% respectively for thoracic major curve, double major curve and lumbar/thoracolumbar major curve. Conclusion: This study shows that it is possible to find a relationship between the internal deformity and the back surface deformity in scoliosis with machine learning methods.The proposed system uses non invasive acquisition which is safety for the patient, no radiation. Also, a design of a specific kernel improved classification performance.

show abstract

Classifying torso deformity in scoliosis using orthogonal maps of the torso

Cited by 19 publications

References 20 publications

Evaluation of Scoliosis Deviation with Clinical Measurements during Physical Therapy

Evaluation of Scoliosis Deviation with Clinical Measurements during Physical Therapy

Métodos não invasivos de avaliação postural da escoliose: Uma revisão sistemática

Non invasive classification system of scoliosis curve types using least-squares support vector machines

Contact Info

Product

Resources

About