Stationary Velocity Fields on Matrix Groups for Deformable Image Registration
This work addresses a specific bottleneck in medical imaging for inter-patient brain registration, offering an incremental improvement over existing methods.
The paper tackled the challenge of handling large deformations in deformable image registration by extending the stationary velocity field approach to matrix groups, specifically SE(3), which improved motion recovery in 3D MRI brain image registration.
The stationary velocity field (SVF) approach allows to build parametrizations of invertible deformation fields, which is often a desirable property in image registration. Its expressiveness is particularly attractive when used as a block following a machine learning-inspired network. However, it can struggle with large deformations. We extend the SVF approach to matrix groups, in particular $\SE(3)$. This moves Euclidean transformations into the low-frequency part, towards which network architectures are often naturally biased, so that larger motions can be recovered more easily. This requires an extension of the flow equation, for which we provide sufficient conditions for existence. We further prove a decomposition condition that allows us to apply a scaling-and-squaring approach for efficient numerical integration of the flow equation. We numerically validate the approach on inter-patient registration of 3D MRI images of the human brain.