Probabilistic Diffeomorphic Registration: Representing Uncertainty - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Probabilistic Diffeomorphic Registration: Representing Uncertainty

Résumé

This paper presents a novel mathematical framework for representing uncertainty in large deformation diffeomorphic image registration. The Bayesian posterior distribution over the deformations aligning a moving and a fixed image is approximated via a variational formulation. A stochastic differential equation (SDE) modeling the deformations as the evolution of a time-varying velocity field leads to a prior density over deformations in the form of a Gaussian process. This permits estimating the full posterior distribution in order to represent uncertainty, in contrast to methods in which the posterior is approximated via Monte Carlo sampling or maximized in maximum a-posteriori (MAP) estimation. The frame-work is demonstrated in the case of landmark-based image registration, including simulated data and annotated pre and intra-operative 3D images.
Fichier principal
Vignette du fichier
wbir2014.pdf (985.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01095091 , version 1 (15-12-2014)
hal-01095091 , version 2 (11-01-2017)

Identifiants

Citer

Demian Wassermann, Matt Toews, Marc Niethammer, William (sandy) Wells Iii. Probabilistic Diffeomorphic Registration: Representing Uncertainty. Biomedical Image Registration, 2014, London, United Kingdom. pp.72 - 82, ⟨10.1007/978-3-319-08554-8_8⟩. ⟨hal-01095091v2⟩

Collections

INRIA INRIA2
163 Consultations
212 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More