Severity and Cobb angle of scoliosis patients quantified with markerless trunk surface topography using k-NN search and multivariate regression analysis

Abstract

ABSTRACT Adolescent Idiopathic Scoliosis (AIS) is a complex 3D condition that affects the shape of the torso by increasing bilateral asymmetries. To analyse the 3D torso shape and consequently the severity of scoliosis, markerless surface topography (ST) has been successfully applied in combination with asymmetry contour maps. The main benefits are a reduction of X-ray radiation to patients and an impression of the 3D torso asymmetric shape pattern. The purpose of this work is to improve the classification accuracy for severity based on k-NN search and to provide a prediction tool for the Cobb angle based on multivariate linear regression.