An inexact Newton-Krylov algorithm for constrained diffeomorphic image registration

Abstract

We propose numerical algorithms for solving large deformation diffeomorphic image registration problems. We formulate the nonrigid image registration problem as a problem of optimal control. This leads to an infinite-dimensional partial differential equation (PDE) constrained optimization problem. The PDE constraint consists, in its simplest form, of a hyperbolic transport equation for the evolution of the image intensity. The control variable is the velocity field. Tikhonov regularization on the control ensures well-posedness. We consider standard smoothness regularization based on $H^1$- or $H^2$-seminorms. We augment this regularization scheme with a constraint on the divergence of the velocity field rendering the deformation incompressible and thus ensuring that the determinant of the deformation gradient is equal to one, up to the numerical error. We use a Fourier pseudospectral discretization in space and a Chebyshev pseudospectral discretization in time. We use a preconditioned, globalized, matrix-free, inexact Newton-Krylov method for numerical optimization. A parameter continuation is designed to estimate an optimal regularization parameter. Regularity is ensured by controlling the geometric properties of the deformation field. Overall, we arrive at a black-box solver. We study spectral properties of the Hessian, grid convergence, numerical accuracy, computational efficiency, and deformation regularity of our scheme. We compare the designed Newton-Krylov methods with a globalized preconditioned gradient descent. We study the influence of a varying number of unknowns in time. The reported results demonstrate excellent numerical accuracy, guaranteed local deformation regularity, and computational efficiency with an optional control on local mass conservation. The Newton-Krylov methods clearly outperform the Picard method if high accuracy of the inversion is required.

32 pages; 10 figures; 9 tables

Cited by in corpus (15)

• Integrated Biophysical Modeling and Image Analysis: Application to Neuro-Oncology
• Constrained $H^1$-regularization schemes for diffeomorphic image registration
• PDE-constrained optimization in medical image analysis
• A Lagrangian Gauss-Newton-Krylov Solver for Mass- and Intensity-Preserving Diffeomorphic Image Registration
• Coupling Brain-Tumor Biophysical Models and Diffeomorphic Image Registration
• CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration
• Fast GPU 3D Diffeomorphic Image Registration
• A Semi-Lagrangian two-level preconditioned Newton-Krylov solver for constrained diffeomorphic image registration
• Image-Driven Biophysical Tumor Growth Model Calibration
• Distributed-memory large deformation diffeomorphic 3D image registration
• PDE-constrained LDDMM via geodesic shooting and inexact Gauss-Newton-Krylov optimization using the incremental adjoint Jacobi equations
• Multi-Node Multi-GPU Diffeomorphic Image Registration for Large-Scale Imaging Problems
• Diffeomorphic Shape Matching by Operator Splitting in 3D Cardiology Imaging
• Stochastic Neural Networks for Automatic Cell Tracking in Microscopy Image Sequences of Bacterial Colonies
• Wavelet-Based Multiscale Flow For Realistic Image Deformation in the Large Diffeomorphic Deformation Model Framework