LDDMM meets GANs: generative adversarial networks for diffeomorphic registration

Ramón Júlvez, Ubaldo (Universidad de Zaragoza) ; Hernández Giménez, Mónica (Universidad de Zaragoza) ; Mayordomo Cámara, Elvira (Universidad de Zaragoza)

Resumen: 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 on 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 learning approach has shown competitive performance with respect to benchmark supervised learning and model-based methods.

Idioma: Inglés

DOI: 10.1007/978-3-031-11203-4_3

Año: 2022

Publicado en: Lecture Notes in Computer Science 13386 (2022), 18-28
ISSN: 0302-9743

Factor impacto CITESCORE: 2.2 - Mathematics (Q2) - Computer Science (Q3)

Factor impacto SCIMAGO: 0.32 - Computer Science (miscellaneous) (Q3) - Theoretical Computer Science (Q4)

Tipo y forma: Congress (PostPrint)

Área (Departamento): Área Lenguajes y Sistemas Inf. (Dpto. Informát.Ingenie.Sistms.)