FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms

TL;DR

FastReg introduces an accelerated optimization method on the diffeomorphism manifold for non-rigid medical image registration, achieving significantly faster results while maintaining high registration quality.

Contribution

The paper proposes a novel averaging technique of gradients in time for diffeomorphic registration, enabling rapid and regular transformations in medical imaging.

Findings

Achieves registration speeds orders of magnitude faster than previous methods.

Successfully registers brain MRI and abdominal CT scans with high accuracy.

Provides publicly available code for reproducibility.

Abstract

We present an implementation of a new approach to diffeomorphic non-rigid registration of medical images. The method is based on optical flow and warps images via gradient flow with the standard $L^2$ inner product. To compute the transformation, we rely on accelerated optimisation on the manifold of diffeomorphisms. We achieve regularity properties of Sobolev gradient flows, which are expensive to compute, owing to a novel method of averaging the gradients in time rather than space. We successfully register brain MRI and challenging abdominal CT scans at speeds orders of magnitude faster than previous approaches. We make our code available in a public repository: https://github.com/dgrzech/fastreg