Information-Theoretic Unification of Groupwise Non-Rigid Registration and Model Building

There is a feature common to both non-rigid registration of a group of images and building a model of a group of images: a dense, consistent correspondence across the group. The former aims to find such a correspondence, whilst the latter requires it. This paper presents the theoretical framework required to unify these two areas, providing a groupwise registration algorithm, where the inherently groupwise model of the image data becomes an integral part of the registration process. The performance of this algorithm is evaluated by using the concepts of generalisability and specificity, which provide an independent metric for comparing various registration algorithms. Experimental results on MR data of brains for various pairwise and groupwise registration algorithms is presented, and demonstrates the feasibility of the combined registration/modelling framework, as well as providing quantitative evidence for the superiority of groupwise approaches to registration.