Evaluation of hierarchical elastic medical image registration method

The paper investigates the hierarchical approach to elastic medical image registration based on mutual information (MI) (Likar, B. and Pernus, F., Image and Vision Computing, vol.19, p.33-44, 2001), in which images are progressively subdivided, locally registered, and elastically interpolated using a thin-plate spline. The technique has been shown to be efficient and robust with small local transformations. However, problems do exist with this technique. First, MI is a statistical property of the two images, so the reduction in the number of samples due to the partitioning of the images into smaller sub-images reduces the statistical quality of the joint intensity histogram. Also, the partitioning scheme may lose some important information, such as edges, which lie exactly on the partition. The statistical problem of MI is resolved by resampling and combining with global MI. An overlapping scheme is implemented in which the image is subdivided into sub-images which overlap their neighbours. This helps to overcome the edge problems. Experiments show that these two methods can improve the registration results to some limited extent (PSNR) and the visual result is much better, especially for the overlapping window scheme.