LDDMM meets GANs: Generative Adversarial Networks for diffeomorphic registration

TL;DR

This paper introduces an adversarial learning approach within the LDDMM framework for 3D diffeomorphic image registration, achieving fast, competitive, and unsupervised registration performance.

Contribution

It combines GANs with LDDMM for diffeomorphic registration, presenting two models with stationary and non-stationary parameterizations, and demonstrates competitive results with rapid computation.

Findings

Achieved registration in under one second.

Performed comparably to supervised, data-rich methods.

Showed effectiveness of unsupervised adversarial approach.

Abstract

The purpose of this work is to contribute to the state of the art of deep-learning methods for diffeomorphic registration. We propose an adversarial learning LDDMM method for pairs of 3D mono-modal images based on Generative Adversarial Networks. The method is inspired by the recent literature for deformable image registration with adversarial learning. We combine the best performing generative, discriminative, and adversarial ingredients from the state of the art within the LDDMM paradigm. We have successfully implemented two models with the stationary and the EPDiff-constrained non-stationary parameterizations of diffeomorphisms. Our unsupervised and data-hungry approach has shown a competitive performance with respect to a benchmark supervised and rich-data approach. In addition, our method has shown similar results to model-based methods with a computational time under one second.