Estimation of spinal deformity in scoliosis from torso surface cross sections

Study Design. Correlation of torso scan and three-dimensional radiographic data in 65 scans of 40 subjects. Objectives. To assess whether full-torso surface laser scan images can be e ffectively used to estimate spinal deformity with the aid of an artificial neural network. Summary of Background Data. Ouantification of torso surface asymmetry may a id diagnosis and monitoring of scoliosis and thereby minimize the use of ra diographs. Artificial neural networks are computing tools designed to relat e input and output data when the form of the relation is unknown. Methods. A three-dimensional torso scan taken concurrently with a pair of r adiographs was used to generate an integrated three-dimensional model of th e spine and torso surface. Sixty-five scan-radiograph pairs were generated during 18 months in 40 patients (Cobb angles 0-58 degrees): 34 patients wit h adolescent idiopathic scoliosis and six with juvenile scoliosis. Sixteen (25%) were randomly selected for testing and the remainder (n = 49) used to train the artificial neural network. Contours were cut through the torso m odel at each vertebral level, and the line joining the centroids of a rea o f the torso contours was generated. Lateral deviations and angles of curvat ure of this line, and the relative rotations of the principal axes of each contour were computed. Artificial neural network estimations of maximal com puter Cobb angle were made. Results. Torso-spine correlations were generally weak (r < 0.5), although t he range of torso rotation related moderately well to the maximal Cobb angl e (r = 0.64). Deformity of the torso centroid line was minimal despite sign ificant spinal deformity in the patients studied. Despite these limitations and the small data set, the artificial neural network estimated the maxima l Cobb angle within 6<degrees> in 63% of the test data set and was able to distinguish a Cobb angle greater than 30 degrees with a sensitivity of 1.0 and specificity of 0.75. Conclusions. Neural-network analysis of full-torso scan imaging shows promi se to accurately estimate scoliotic spinal deformity in a variety of patien ts.