Diffeomorphic demons: Efficient non-parametric image registration

@article{Vercauteren2009DiffeomorphicDE,
  title={Diffeomorphic demons: Efficient non-parametric image registration},
  author={Tom Vercauteren and Xavier Pennec and Aymeric Perchant and Nicholas Ayache},
  journal={NeuroImage},
  year={2009},
  volume={45},
  pages={S61-S72}
}

Figures and Tables from this paper

An ITK Implementation of the Symmetric Log-Domain Diffeomorphic Demons Algorithm
TLDR
This article provides an implementation of the symmetric log-domain diffeomorphic image registration algorithm, or symmetric demons algorithm for short, which generalizes Thirion’s demons and the Diffeomorphic demons algorithm and reuses and extends this generic framework.
Spherical Demons: Fast Diffeomorphic Landmark-Free Surface Registration
TLDR
The Spherical Demons algorithm for registering two spherical images is presented and a large class of regularizors for the modified Demons objective function can be efficiently approximated on the sphere using iterative smoothing and the resulting registration is diffeomorphic and fast.
Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation
TLDR
The key contribution of this work is to provide an accurate estimation of the so-called initial momentum, which is a scalar function encoding the optimal deformation between two images through the Hamiltonian equations of geodesics.
Fast Diffeomorphic Image Registration via Fourier-Approximated Lie Algebras
TLDR
This paper introduces Fourier-approximated Lie algebras for shooting (FLASH), a fast geodesic shooting algorithm for diffeomorphic image registration that approximate the infinite-dimensional Lie algebra of smooth vector fields with a low-dimensional, bandlimited space.
A Novel Diffeomorphic Model for Image Registration and Its Algorithm
TLDR
This work proposes a new variational model with a special regularizer, based on the quasi-conformal theory, which can guarantee that the registration map is diffeomorphic, and proposes an iterative method to solve the resulting nonlinear optimization problem and prove the convergence of the method.
Finite-Dimensional Lie Algebras for Fast Diffeomorphic Image Registration
TLDR
A novel finite-dimensional Lie algebra structure on the space of bandlimited velocity fields is introduced that can effectively represent initial velocities for diffeomorphic image registration at much lower dimensions than typically used, with little to no loss in registration accuracy.
Frequency Diffeomorphisms for Efficient Image Registration
TLDR
A novel finite dimensional Fourier representation of diffeomorphic deformations based on the key fact that the high frequency components of a diffeomorphism remain stationary throughout the integration process when computing the deformation associated with smooth velocity fields is introduced.
Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations
TLDR
A new framework for capturing large and complex deformations in image registration and atlas construction is presented, which introduces to this effect a new direct feature matching technique that finds global correspondences between images via simple nearest-neighbor searches.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 58 REFERENCES
Non-parametric Diffeomorphic Image Registration with the Demons Algorithm
TLDR
A non-parametric diffeomorphic image registration algorithm based on Thirion's demons algorithm that provides results that are similar to the ones from the demons algorithm but with transformations that are much smoother and closer to the true ones in terms of Jacobians.
Symmetric Log-Domain Diffeomorphic Registration: A Demons-Based Approach
TLDR
This work proposes a non-linear registration algorithm perfectly fit for log-Euclidean statistics on diffeomorphisms that outperforms both the demons algorithm and the recently proposed diffeomorphic demons algorithm in terms of accuracy of the transformation while remaining computationally efficient.
Comparing algorithms for diffeomorphic registration: Stationary LDDMM and Diffeomorphic Demons
TLDR
A comparison between stationary LDDMM and diffeomorphic Demons for registration of diffeomorphisms finds that both methods have comparable performance in terms of image matching although the transformations are qualitatively different in some cases.
Insight into Efficient Image Registration Techniques and the Demons Algorithm
TLDR
It is shown in this paper that some tools that have recently been developed in the field of vision-based robot control can outperform classical solutions for non-linear image registration.
Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy
TLDR
This article provides an implementation of the non-parametric diffeomorphic image registration algorithm generalizing Thirion’s demons algorithm within the Insight Toolkit (ITK), and shows that this framework can be extended to handle Diffeomorphic transformations.
Constructing diffeomorphic representations for the groupwise analysis of nonrigid registrations of medical images
TLDR
This paper presents methods for constructing a general class of multi-dimensional diffeomorphic representations of deformations, and shows that this non-Euclidean metric is superior to the usual ad hoc Euclidean metrics in that it enables more accurate classification of legal and illegal variations.
Symmetric image registration
TLDR
This work proposes a symmetric registration approach, which improves the registration by measuring similarity in both registration directions, and shows improvements of registration consistency and also indicate the improvement of registration correctness.
DTI registration with exact finite-strain differential
TLDR
It is shown with 40 pairwise DTI registrations that using the exact gradient achieves significantly better registration, and is compared with a classic alternative that does not take into account the reorientation in the gradient computation.
Spherical Demons: Fast Surface Registration
TLDR
The Spherical Demons algorithm for registering two spherical images is presented, which is diffeomorphic and fast - registration of two cortical mesh models with more than 100k nodes takes less than 5 minutes, comparable to the fastest surface registration algorithms.
...
1
2
3
4
5
...