Curvature Based Registration with Applications to MR-Mammography

@inproceedings{Fischer2002CurvatureBR,
  title={Curvature Based Registration with Applications to MR-Mammography},
  author={Bernd Fischer and Jan Modersitzki},
  booktitle={International Conference on Computational Science},
  year={2002}
}
We introduce a new non-linear registration model based on a curvature type regularizer. We show that affine linear transformations belong to the kernel of this regularizer. Consequently, an additional global registration is superfluous. Furthermore, we present an implementation of the new scheme based on the numerical solution of the underlying Euler-Lagrange equations. The real discrete cosine transform is the backbone of our implementation and leads to a stable and fast O(nlogn) algorithm… 

An improved model for joint segmentation and registration based on linear curvature smoother

This article presents an improved variational model for a joint segmentation and registration based on active contour without edges and the linear curvature model and shows that the proposed model gives correct registration results when there are different features inside the object to be segmented or features that have clear boundaries but without fine details.

Local similarity measures for lesion registration in DCE-MRI of the breast

An evaluation of three similarity measures for local region of interest registration of lesions in DCE-MRI finds the best results are achieved with non-rigid transformation and a post-contrast fixed image leading to an average improvement in the fitting quality to the pharmacokinetic model.

Multi-modality image registration using the decomposition model

A decomposition model combining parametric and non-parametric deformation for multi-modality image registration is proposed and numerical results show that the normalised gradient field perform better than the mutual information with the decomposition models.

A combined algorithm for breast MRI motion correction

A novel iterative scheme combining local and global registration into one single algorithm, limiting computational overhead, reducing interpolation artifacts and generally improving the quality of registration results is presented, allowing for a sound combination of both registration types and a potentially wider range of computable transformations.

Unifying framework for decomposition models of parametric and non-parametric image registration

This paper provides a unifying framework for decomposition models for image registration which combine parametric and non-parametric models and presents several variants of the models with focus on the affine, diffusion and linear curvature models.

A novel variational model for image registration using Gaussian curvature

A novel variational model for image registration using the Gaussian curvature as a regulariser is proposed using the surface restoration work in geometric processing and outperforms three competing models based on a linear curvature.

Projection Technique for Vortex-Free Image Registration

A new strategy is presented which does not change the registration method itself but continuously correct the solution during the registration process to prevent unwanted vortices in the displacement field.

Influence of the boundary conditions on the result of non-linear image registration

  • U. BraumannJ. Kuska
  • Physics, Mathematics
    IEEE International Conference on Image Processing 2005
  • 2005
This work offers a simple solution procedure therefor based on discrete Fourier transform for non-linear curvature-based registration of non-parametric image registration algorithms.

A New Equation for Nonlinear Image Registration with Control over the Vortex Structure in the Displacement Field

A new partial differential equation is presented that can be used for the registration of images with textured and complex shaped motifs and allows to control the vortex structure in the registration field.

References

SHOWING 1-10 OF 31 REFERENCES

Fast Curvature-Based Registration of MR Mammography Images

A new non-linear registration model based on a curvature type regularizer is introduced and it is shown that affine linear transformations belong to the kernel of this regularizer and an additional global registration is superfluous.

A Super Fast Registration Algorithm

A novel scheme for automatic registration by introducing a specific regularizing term is proposed and it is shown that the complexity of its implementation is linear with respect to the size of the images and its performance is demonstrated.

Fast Fluid Registration of Medical Images

A new fast algorithm for non-rigid Viscous Fluid Registration of medical images that is at least an order of magnitude faster than the previous method by Christensen et al.

B-spline registration of 3D images with Levenberg-Marquardt optimization

A Levenberg-Marquardt type optimization routine for B-splines for non-rigid image registration embedded in a multi-scale framework providing additional regularization, an increased capture range and speed-up.

Optimal Image Registration with a Guaranteed One-to-one Point Match

A framework for novel registration techniques which are capable to combine automatic and landmark driven approaches in order to benefit from the advantages of both strategies is proposed.

Combination of automatic non-rigid and landmark based registration: the best of both worlds

A framework for novel registration techniques which are capable to combine automatic and landmark driven approaches in order to benefit from the advantages of both strategies is proposed.

FLIRT: A Flexible Image Registration Toolbox

Some of the most promising non-linear registration strategies currently used in medical imaging are reviewed and it is shown that all these techniques may be phrased in terms of a variational problem and allow for a unified treatment.

Free-Form Registration Using Mutual Information and Curvature Regularization

In this paper we present a novel 3-D free-form non-rigid registration algorithm which combines the mutual information similarity measure with a particular curvature based regularizer, which has been

Fast Computation of Mutual Information in a Variational Image Registration Approach

A novel method for computing the Mutual Information of images using recently developed non-equidistant fast Fourier-transform (NFFT) techniques which leads to an improved registration accuracy and a straight forward implementation.

Combining landmark and intensity driven registrations

A general variational based approach for image registration which allows the choice of a user supplied similarity measure and a users supplied regularizer as well as the integration of external knowledge, like, for example, the location of outstanding points, is presented.