Name
Abstract | ||
|---|---|---|
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 framework is demonstrated in the case of landmark-based image registration, including simulated data and annotated pre and intra-operative 3D images. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1007/978-3-319-08554-8_8 | BIOMEDICAL IMAGE REGISTRATION (WBIR 2014) |
Field | DocType | Volume |
Computer vision,Mathematical optimization,Monte Carlo method,Computer science,Vector field,Stochastic differential equation,Posterior probability,Artificial intelligence,Gaussian process,Probabilistic logic,Image registration,Bayesian probability | Conference | 8545 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.35 |
References | Authors | |
7 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Demian Wassermann | 1 | 76 | 11.03 |
| Matthew Toews | 2 | 247 | 20.60 |
| Marc Niethammer | 3 | 731 | 68.16 |
| William M. Wells III | 4 | 5267 | 833.10 |