Geostatistical medical image registration

Abstract

We propose a novel approach to landmark-based medical image registration based on the geostatical method of Kriging prediction. Our method exploits the spatial statistical relation between two images, as estimated using general-purpose registration algorithms, in order to construct an optimum predictor of the displacement field. High accuracy is achieved by using an estimated spatial model of the displacement field directly from the image data, while practically circumventing the difficulties that prevented Kriging from being widely used in image registration.