Diffeomorphic Image Registration with An Optimal Control Relaxation and Its Implementation

TL;DR

This paper introduces a novel diffeomorphic image registration model based on optimal control relaxation, ensuring large deformations are accurately mapped while maintaining diffeomorphism, with proven convergence and superior performance.

Contribution

It proposes a new registration framework using optimal control relaxation to guarantee diffeomorphic transformations for large deformations, with an efficient iterative solution and convergence analysis.

Findings

Guarantees diffeomorphic mappings for large deformations

Achieves state-of-the-art quantitative performance

Provides a robust algorithm with convergence guarantees

Abstract

Image registration has played an important role in image processing problems, especially in medical imaging applications. It is well known that when the deformation is large, many variational models cannot ensure diffeomorphism. In this paper, we propose a new registration model based on an optimal control relaxation constraint for large deformation images, which can theoretically guarantee that the registration mapping is diffeomorphic. We present an analysis of optimal control relaxation for indirectly seeking the diffeomorphic transformation of Jacobian determinant equation and its registration applications, including the construction of diffeomorphic transformation as a special space. We also provide an existence result for the control increment optimization problem in the proposed diffeomorphic image registration model with an optimal control relaxation. Furthermore, a fast iterative scheme based on the augmented Lagrangian multipliers method (ALMM) is analyzed to solve the control increment optimization problem, and a convergence analysis is followed. Finally, a grid unfolding indicator is given, and a robust solving algorithm for using the deformation correction and backtrack strategy is proposed to guarantee that the solution is diffeomorphic. Numerical experiments show that the registration model we proposed can not only get a diffeomorphic mapping when the deformation is large, but also achieves the state-of-the-art performance in quantitative evaluations in comparing with other classical models.