Bayesian estimation of regularization and atlas building in diffeomorphic image registration

Authors:
Miaomiao Zhang;Nikhil Singh;P. Thomas Fletcher
Affiliations:
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT;Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT;Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT
Venue:
IPMI'13 Proceedings of the 23rd international conference on Information Processing in Medical Imaging
Year:
2013

Citing 7
Cited 0

Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms

International Journal of Computer Vision
Geodesic Shooting for Computational Anatomy

Journal of Mathematical Imaging and Vision
A marginalized MAP approach and EM optimization for pair-wise registration

IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Bayesian estimation of deformation and elastic parameters in non-rigid registration

WBIR'10 Proceedings of the 4th international conference on Biomedical image registration
Summarizing and visualizing uncertainty in non-rigid registration

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
A unified information-theoretic approach to groupwise non-rigid registration and model building

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a generative Bayesian model for diffeomorphic image registration and atlas building. We develop an atlas estimation procedure that simultaneously estimates the parameters controlling the smoothness of the diffeomorphic transformations. To achieve this, we introduce a Monte Carlo Expectation Maximization algorithm, where the expectation step is approximated via Hamiltonian Monte Carlo sampling on the manifold of diffeomorphisms. An added benefit of this stochastic approach is that it can successfully solve difficult registration problems involving large deformations, where direct geodesic optimization fails. Using synthetic data generated from the forward model with known parameters, we demonstrate the ability of our model to successfully recover the atlas and regularization parameters. We also demonstrate the effectiveness of the proposed method in the atlas estimation problem for 3D brain images.