CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration

TL;DR

CLAIRE is a scalable distributed-memory solver for large deformation diffeomorphic image registration, utilizing advanced numerical techniques to achieve high accuracy and speed on high-performance computing platforms.

Contribution

The paper introduces CLAIRE, a novel distributed-memory solver with an improved preconditioner, enabling fast and scalable 3D image registration for large datasets.

Findings

Achieves registration in 2-4 minutes on standard 20-core nodes.

Demonstrates high registration accuracy on neuroimaging data.

Reports up to 17x speedup over previous methods.

Abstract

With this work, we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diffeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss--Newton--Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an effective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against different flavors of the Demons algorithm for diffeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5$\times$ with a peak performance of up to 17$\times$ compared to our former work.