Differential Evolution for Medical Image Registration

摘要

A common framework for 3D image registration consists in minimizing a cost (or energy) function that expresses the pixel or voxel similarity of the images to be aligned. Standard cost functions, based on voxel similarity measures, are highly non-linear, non-convex, exhibit many local minima and thus yield hard optimization problems. In this paper we consider a general purpose global optimization algorithm based on random sampling and evolutionary principles: differential evolution. Beside yielding accurate registrations, differential evolution appears as a robust algorithm, exhibits fast convergence and is easy to use, since few parameters are required.