Spinal deformity detection based on Fourier descriptor from moire images

Abstract

Spinal deformity is one of serious diseases, mainly suffered by teenagers during their growth stage. In order to detect the spinal deformity in early stage, orthopedists have traditionally performed a painless examination called a forward bending test or moire topographic image test in mass screening of school. It is, however, inspection base on the forward bending method takes much time, and the moire images and visual examination also require a large amount of moire images because from elementary as well as junior high schools are collected. This causes exhaustion of doctors and therefore leads to misjudgment. Therefore automated scoliosis inspection based on the moire images has long been desired among orthopedists. In this paper, we propose a method for automatic detection of spinal deformity from moire topographic images by using a new asymmetric feature which is obtained difference of left- and right-hand side density features based on scapula area and shape of moire fringes which is obtained by Fourier descriptor. The proposed technique applied 1200 real moire topographic images and satisfactory performance was achieved. Obtained some experimental results are shown along with the discussions.