Prediction of Scoliosis Progression in Time Series Using a Hybrid Learning Technique

Scoliosis is a common and poorly understood spinal disorder that is clinically monitored with a series of full spinal X-rays. The purpose of this study was to predict scoliosis future progression at 6- and 12-month intervals with successive spinal indices and a hybrid learning technique (i.e., the combination of fuzzy c-means clustering and artificial neural network (ANN)). Ultimately this could decrease scoliotic patients' radiation exposure and the associated cancer risk in growing adolescents. Seventy-two data sets were derived from a database of 56 acquisitions from 11 subjects (29.8 plusmn 9.6deg Cobb angle, 11.4 plusmn 2.4 yr), each consisting of 4 sequential values of Cobb angle and lateral deviations at apices in 6- and 12-month intervals in the coronal plane. Progression patterns in Cobb angles (n = 10) and lateral deviations (n = 8) were successfully identified using a fuzzy c-means clustering algorithm. The accuracies of the trained ANN, having a structure of three input variables, four nonlinear hidden nodes, and one linear output variable, for training and test data sets were within 3.64deg (plusmn 2.58deg) and 4.40deg (plusmn 1.86deg) of Cobb angles, and within 3.59 (plusmn 3.96) mm and 3.98 (plusmn 3.41) mm of lateral deviations, respectively. Those results were twice the accuracy of typical clinical measurement (~10deg) and in close agreement with those using cubic spline extrapolation and adaptive neuro-fuzzy inference system (ANFIS) techniques. The adapted technique for predicting the scoliosis deformity progression holds significant promise for clinical applications

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

[2]  J. Dansereau,et al.  Three-dimensional measurement of wedged scoliotic vertebrae and intervertebral disks , 1998, European Spine Journal.

[3]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[4]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[5]  James C. Bezdek,et al.  Fuzzy Models and Digital Signal Processing(for Pattern Recognition): Is This a Good Marriage? , 1993 .

[6]  I A Stokes,et al.  Measurements of the three-dimensional shape of the rib cage. , 1988, Journal of biomechanics.

[7]  J. Jaremko,et al.  Use of Neural Networks to Correlate Spine and Rib Deformity in Scoliosis , 2000, Computer methods in biomechanics and biomedical engineering.

[8]  J. Faraway,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[9]  L. Tsimring,et al.  The analysis of observed chaotic data in physical systems , 1993 .

[10]  I A Stokes,et al.  The biomechanics of scoliosis. , 1984, Critical reviews in biomedical engineering.

[11]  Neil Davey,et al.  Traffic trends analysis using neural networks , 1997 .

[12]  B Drerup,et al.  Assessment of scoliotic deformity from back shape asymmetry using an improved mathematical model. , 1996, Clinical biomechanics.

[13]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[14]  H Labelle,et al.  Geometric Torsion in Idiopathic Scoliosis: Three-Dimensional Analysis and Proposal for a New Classification , 2001, Spine.

[15]  S. Chiu,et al.  A cluster estimation method with extension to fuzzy model identification , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[16]  Adrian R. Levy,et al.  REDUCING THE LIFETIME RISK OF CANCER FROM SPINAL RADIOGRAPHS AMONG PEOPLE WITH ADOLESCENT IDIOPATHIC SCOLIOSIS , 1997 .

[17]  J. Birch,et al.  Measurement of scoliosis and kyphosis radiographs. Intraobserver and interobserver variation. , 1990, The Journal of bone and joint surgery. American volume.

[18]  J. Dansereau,et al.  Variability of geometric measurements from three-dimensional reconstructions of scoliotic spines and rib cages , 2004, European Spine Journal.