We introduce a novel discrete optimization method for non-rigid image registration based on the random walker algorithm. We dis-cretize the space of deformations and formulate registration using a Gaussian MRF where continuous labels correspond to the probability of a point having a certain discrete deformation. The interaction (regu-larization) term of the corresponding MRF energy is convex and image dependent, thus being able to accommodate different types of tissue elasticity. This formulation results in a fast algorithm that can easily accommodate a large number of displacement labels, has provable robustness to noise and a close to global solution. We experimentally demonstrate the validity of our formulation on synthetic and real medical data.
展开▼
