New Approximating Gaussian Elastic Body Splines for Landmark-Based Registration of Medical Images

We introduce a new approximation scheme for landmark-based elastic image registration using Gaussian elastic body splines (GEBS). The scheme is based on an extended energy functional related to the Navier equation under Gaussian forces and allows to individually weight the landmarks according to their localization uncertainties. We demonstrate the applicability of the registration scheme based on 3D synthetic image data as well as 2D MR images of the human brain. From the experiments it turns out that the new approximating GEBS approach achieves more accurate registration results in comparison to previously proposed interpolating GEBS as well as TPS.