Non-Rigid Registration Based on Local Uncertainty Quantification and Fluid Models for Multiparametric MR Images

摘要

In this work, we present a novel fully automated elastic registration method for magnetic resonance (MR) images with mismatched intensities, which combines a novel mapping based on an intensity uncertainty quantification in a local region, with a fluid-like registration technique. The proposed methodology can be summarized in two global steps: first, a mapping over the target and source images is applied, which provides information about the intensities uncertainty of the pixels in a neighborhood; and second, a monomodal non-rigid registration is achieved between the transformed images based on fluid-models: demons, diffeomorphic-demons, and a variation of the classical optical-flow. To evaluate the algorithm, a set composed by 12 multiparametric MR images of the head (T1, T2 and proton density) were taken from a brain model, and these images were modified by a set of controlled elastic deformations (based on splines), in order to generate ground-truths to be registered with the proposed technique. The evaluation results showed an average error of less than 1.3 mm by combining the local uncertainty quantification with the diffeomorphic-demons technique, which also ensures to obtain only feasible physical deformations. These results suggest that the proposed methodology could be considered as a good option for fully automated non-rigid registrations between images with mismatched intensities on medical applications.