Comparison Between Parzen Window Interpolation and Generalised Partial Volume Estimation for Nonrigid Image Registration Using Mutual Information

摘要

Because of its robustness and accuracy for a variety of applications, either monomodal or multimodal, mutual information (MI) is a very popular similarity measure for (medical) image registration. Calculation of MI is based on the joint histogram of the two images to be registered, expressing the statistical relationship between image intensities at corresponding positions. However, the calculation of the joint histogram is not straightforward. The discrete nature of digital images, sampled as well in the intensity as in the spatial domain, impedes the exact calculation of the joint histogram. Moreover, during registration often an intensity will be sought at a non grid position of the floating image. This article compares the robustness and accuracy of two common histogram estimators in the context of nonrigid multiresolution medical image registration: a Parzen window intensity interpolator (IIP) and generalised partial volume histogram estimation (GPV). Starting from the Brain Web data and realistic deformation fields obtained from patient images, the experiments show that GPV is more robust, while IIP is more accurate. Using a combined approach, an average registration error of 0.12 mm for intramodal and 0.30 mm for intermodal registration is achieved.