Spline-Based Hybrid Image Registration using Landmark and Intensity Information based on Matrix-Valued Non-radial Basis Functions

We introduce a new approach for spline-based elastic image registration using both point landmarks and intensity information. With this approach, both types of information as well as a regularization based on the Navier equation are directly integrated in a single energy minimizing functional. For this functional we have derived an analytic solution, which is based on matrix-valued non-radial basis functions. With our approach the full 3D intensity information is exploited, i.e., all voxels are considered and subsampling using a grid is not required. A special case of our hybrid approach is obtained by disregarding the landmark information, which results in a pure intensity-based elastic registration approach. We have successfully applied our approach to 3D synthetic images, 2D MR images of the human brain, 2D gel electrophoresis images, and 3D CT lung images.