Newton-Krylov PDE-constrained LDDMM in the space of band-limited vector fields
This work addresses computational bottlenecks in diffeomorphic registration for computational anatomy, offering incremental improvements in efficiency and accuracy.
The authors tackled the high computational complexity of PDE-constrained LDDMM in computational anatomy by proposing two methods parameterized in band-limited vector fields, which dramatically reduced computational burden and showed improved accuracy compared to benchmark methods.
PDE-constrained Large Deformation Diffeomorphic Metric Mapping is a particularly interesting framework of physically meaningful diffeomorphic registration methods. Newton-Krylov optimization has shown an excellent numerical accuracy and an extraordinarily fast convergence rate in this framework. However, the most significant limitation of PDE-constrained LDDMM is the huge computational complexity, that hinders the extensive use in Computational Anatomy applications. In this work, we propose two PDE-constrained LDDMM methods parameterized in the space of band-limited vector fields and we evaluate their performance with respect to the most related state of the art methods. The parameterization in the space of band-limited vector fields dramatically alleviates the computational burden avoiding the computation of the high-frequency components of the velocity fields that would be suppressed by the action of the low-pass filters involved in the computation of the gradient and the Hessian-vector products. Besides, the proposed methods have shown an improved accuracy with respect to the benchmark methods.