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

OBJECTIVE To determine scoliosis curve types using non invasive surface acquisition, without prior knowledge from X-ray data. METHODS Classification of scoliosis deformities according to curve type is used in the clinical management of scoliotic patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of the 3D back surface of the patients. The 3D image of the surface of the trunk is divided into patches and local geometric descriptors characterizing the back surface are computed from each patch and constitute the features. We reduce the dimensionality by using principal component analysis and retain 53 components using an overlap criterion combined with the total variance in the observed variables. In this work, a multi-class classifier is built with least-squares support vector machines (LS-SVM). The original LS-SVM formulation was modified by weighting the positive and negative samples differently and a new kernel was designed in order to achieve a robust classifier. The proposed system is validated using data from 165 patients with different scoliosis curve types. The results of our non invasive classification were compared with those obtained by an expert using X-ray images. RESULTS The average rate of successful classification was computed using a leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. As for the correct classification rates per class, we obtained 96%, 84% and 97% for the thoracic, double major and lumbar/thoracolumbar curve types, respectively. 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 surface acquisition, which is safe for the patient as it involves no radiation. Also, the design of a specific kernel improved classification performance.

[1]  Mohamed Cheriet,et al.  Support Vector Machine , 2009, Encyclopedia of Biometrics.

[2]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[3]  Farida Cheriet,et al.  Prediction of scoliosis curve type based on the analysis of trunk surface topography , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[5]  Nelson G. Durdle,et al.  A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography , 2006, IEEE Transactions on Information Technology in Biomedicine.

[6]  A.W. Hahn,et al.  Medical instrumentation , 1980, Proceedings of the IEEE.

[7]  Mohamed Cheriet,et al.  Model selection for the LS-SVM. Application to handwriting recognition , 2009, Pattern Recognit..

[8]  R J Jefferson,et al.  A method for analysis of back shape in scoliosis. , 1988, Journal of biomechanics.

[9]  R. J. Jefferson,et al.  ISIS Scanning: A Useful Assessment Technique in the Management of Scoliosis , 1988, Spine.

[10]  Farida Cheriet,et al.  Prediction of anterior scoliotic spinal curve from trunk surface using support vector regression , 2005, Eng. Appl. Artif. Intell..

[11]  B V Reamy,et al.  Adolescent idiopathic scoliosis: review and current concepts. , 2001, American family physician.

[12]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[13]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[14]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[15]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[16]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[17]  Gavin C. Cawley,et al.  Leave-One-Out Cross-Validation Based Model Selection Criteria for Weighted LS-SVMs , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[18]  Marilyn Stovall,et al.  Breast Cancer Mortality After Diagnostic Radiography: Findings From the U.S. Scoliosis Cohort Study , 2000, Spine.

[19]  V. Vapnik,et al.  Bounds on Error Expectation for Support Vector Machines , 2000, Neural Computation.

[20]  David L. Helfet,et al.  Instructional Course Lectures , 2008 .

[21]  M. H. Pope,et al.  Moire fringe topography and spinal deformity : proceedings of an international symposium , 1981 .

[22]  Nelson G. Durdle,et al.  Classifying torso deformity in scoliosis using orthogonal maps of the torso , 2007, Medical & Biological Engineering & Computing.

[23]  M S Moreland,et al.  Moiré fringe topography of the human body. , 1981, Medical instrumentation.

[24]  H Labelle,et al.  Estimation of Spinal Deformity in Scoliosis From Torso Surface Cross Sections , 2001, Spine.

[25]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[26]  Kenneth V. Jackman,et al.  Moiré Fringe Topography and Spinal Deformity , 1982 .

[27]  L. Kanim,et al.  Optoelectronic Evaluation of Trunk Deformity in Scoliosis , 1993, Spine.

[28]  Jean Dansereau,et al.  Indices of torso asymmetry related to spinal deformity in scoliosis. , 2002, Clinical biomechanics.

[29]  H Labelle,et al.  Reconstruction of Laser-scanned 3D Torso Topography and Stereoradiographical Spine and Rib-cage Geometry in Scoliosis , 2001, Computer methods in biomechanics and biomedical engineering.

[30]  Jacob Lester Jaremko.  Estimation of scoliosis severity from the torso surface by neural networks , 2001 .

[31]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[32]  R. Lyon,et al.  Functional Classification of Patients With Idiopathic Scoliosis Assessed by the Quantec System: A Discriminant Functional Analysis to Determine Patient Curve Magnitude , 2001, Spine.

[33]  I A Stokes,et al.  Surgical correction of vertebral axial rotation in adolescent idiopathic scoliosis: prediction by lateral bending films. , 1996, Journal of spinal disorders.

[34]  M S Moreland,et al.  Concordance of Back Surface Asymmetry and Spine Shape in Idiopathic Scoliosis , 1989, Spine.

[35]  Farida Cheriet,et al.  Accuracy assessment of human trunk surface 3D reconstructions from an optical digitising system , 2006, Medical and Biological Engineering and Computing.

[36]  Johan A. K. Suykens,et al.  Improved Microarray-Based Decision Support with Graph Encoded Interactome Data , 2010, PloS one.

[37]  Nelson G. Durdle,et al.  Characterizing Torso Shape Deformity in Scoliosis Using Structured Splines Models , 2009, IEEE Transactions on Biomedical Engineering.

[38]  Cobb,et al.  Outlines for the study of scoliosis , 1948 .