Abstract
Mutual information (MI) is a widely used entropy-based similarity metric for medical image registration. It can be used for both mono-modality and multi-modality registration. Recently an improved mutual information metric named regional mutual information (RMI) has been proposed for robust image registration by including some regional or special information. Though RMI has been demonstrated more effective and more robust than traditional MI, it takes larger computation cost because of computation of high-dimensional joint distribution. For improvement of RMI, we propose a novel PCA based regional mutual information (PRMI) to implement a more robust and faster medical image registration.