Adaptive FEM-based nonrigid image registration using truncated hierarchical B-splines

TL;DR

This paper introduces an adaptive FEM-based nonrigid image registration method utilizing truncated hierarchical B-splines to improve computational efficiency and accuracy by focusing refinement on regions with large deformations.

Contribution

It develops an adaptive local refinement scheme with THB-splines within FEM-based registration, enhancing efficiency and matrix sparsity over uniform subdivision methods.

Findings

Effective registration on synthetic images

Improved computational efficiency

Accurate medical image alignment

Abstract

We present an efficient approach of Finite Element Method (FEM)-based nonrigid image registration, in which the spatial transformation is constructed using truncated hierarchical B-splines (THB-splines). The image registration framework minimizes an energy functional using an FEM-based method and thus involves solving a large system of linear equations. This framework is carried out on a set of successively refined grids. However, due to the increased number of control points during subdivision, large linear systems are generated which are generally demanding to solve. Instead of using uniform subdivision, an adaptive local refinement scheme is carried out, only refining the areas of large change in deformation of the image. By incorporating the key advantages of THB-spline basis functions such as linear independence, partition of unity and reduced overlap into the FEM-based framework, we improve the matrix sparsity and computational efficiency. The performance of the proposed method is demonstrated on 2D synthetic and medical images.

Figures

Full text

See pages 2-last of AdaptiveRegistration_THBS_final_preprint.pdf