Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks

TL;DR

This paper introduces a deep Laplacian Pyramid Network for large deformation diffeomorphic image registration, effectively handling complex transformations while preserving topology and achieving superior accuracy and speed.

Contribution

The proposed method enables large deformation registration with diffeomorphic guarantees using a coarse-to-fine deep learning approach, improving over existing methods.

Findings

Outperforms existing registration methods significantly.

Maintains bijective and topology-preserving transformations.

Achieves faster registration speeds.

Abstract

Deep learning-based methods have recently demonstrated promising results in deformable image registration for a wide range of medical image analysis tasks. However, existing deep learning-based methods are usually limited to small deformation settings, and desirable properties of the transformation including bijective mapping and topology preservation are often being ignored by these approaches. In this paper, we propose a deep Laplacian Pyramid Image Registration Network, which can solve the image registration optimization problem in a coarse-to-fine fashion within the space of diffeomorphic maps. Extensive quantitative and qualitative evaluations on two MR brain scan datasets show that our method outperforms the existing methods by a significant margin while maintaining desirable diffeomorphic properties and promising registration speed.