Clustering property of spinal deformity classification with simplified 3-D model and principal component analysis

In this paper, the clustering property of spinal deformity classification is examined by principal component analysis (PCA). The high dimensional features of the scoliosis patterns were reduced into two-dimensional (2-D) and showed on the 2-D Principal Component plane. King spinal deformity classification system was used for study. The dataset used had 25 scoliosis patterns. Such dataset was further divided into 5 subgroups. In each subgroup there were exactly 5 King scoliosis patterns. At the first step the simplified three- dimensional (3-D) spine model was constructed based on the coronal and sagittal x-ray images. The features of the central axis curve of the scoliosis patterns in 3-D space were extracted by the Total Curvature analysis. The discrete form of the Total Curvature, including the curvature and the torsion of the central axis of the simplified 3-D spine model was derived from the Difference Quotients. The Total Curvature values of 17 vertebrae from the first thoracic to the fifth lumbar spine formed a Euclidean space of 17 dimensions. For the purpose of classification, each pattern of spinal deformity was labeled to identify it from others. Principal component analysis (PCA) was applied on the Total Curvature of these 25 scoliosis patterns. By PCA dimensional reduction, the 17-D pattern characters of scoliosis spine were reduced into 2-D and the clustering property of scoliosis classification can be visualized in a 2-D Principal Component plane.