CVIVNov 24, 2021

LDDMM meets GANs: Generative Adversarial Networks for diffeomorphic registration

arXiv:2111.12544v16 citations
Originality Synthesis-oriented
AI Analysis

This work addresses diffeomorphic image registration for medical imaging, offering an incremental improvement by combining existing generative, discriminative, and adversarial components.

The paper tackled the problem of diffeomorphic registration for 3D mono-modal images by proposing an adversarial learning method based on Generative Adversarial Networks within the LDDMM paradigm, achieving competitive performance with benchmark supervised approaches and computational times under one second.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes