A Multicomponent Approach to Nonrigid Registration of Diffusion Tensor Images

TL;DR

This paper introduces a multicomponent nonrigid registration method for diffusion tensor images that improves accuracy over affine methods by incorporating tensor reorientation and an information-theoretic measure.

Contribution

It presents a novel nonrigid registration technique using multicomponent information measures with explicit tensor reorientation for diffusion tensor images.

Findings

Significantly better registration accuracy than affine methods.

Effective handling of geometric distortions in diffusion tensor images.

Feasibility demonstrated through experimental results.

Abstract

We propose a nonrigid registration approach for diffusion tensor images using a multicomponent information-theoretic measure. Explicit orientation optimization is enabled by incorporating tensor reorientation, which is necessary for wrapping diffusion tensor images. Experimental results on diffusion tensor images indicate the feasibility of the proposed approach and a much better performance compared to the affine registration method based on mutual information in terms of registration accuracy in the presence of geometric distortion.