Research of Non-rigid Medical Image Registration Based on Gradient Information

Abstract

In many clinical applications, non-rigid transforms are often used to describe the spatial relationships between images. The conventional image registration approaches often consider intensity information, ignoring the spatial information between pixels. To solve the problem, this paper proposes a non-rigid medical image registration algorithm based on gradient information. First, gradient feature of each sample point is obtained for the reference image and floating image. Second, the pixel intensity and the gradient feature are applied into non-rigid medical image registration. Comparison results of the images obtained from lung and brain images showed that the proposed algorithm provides better accuracy than both the conventional rigid registration algorithm and the non-rigid registration algorithm based on single pixel gray values.