Curvature-Based Registration for Slice Interpolation of Medical Images

摘要

Slice interpolation is a fast growing field in medical image processing. Intensity-based interpolation and object-based interpolation are two major groups of methods in the literature. In this paper an object based method for slice interpolation using a modified version of curvature registration is proposed. Due to non-linear nature of image registration the results of forward and backward registration can be different. Therefore assuming a linear displacement between corresponding pixels of reference and moving image, a functional is minimized and the displacement fields for both reference and moving images with respect to the missing in-between slice are computed and used for reconstruction of the missing slice. The proposed approach is evaluated quantitatively by using the Mean Squared Difference (MSD) as metric. The produced results show significant visual improvement in preserving sharp edges in images.