Topology preserving deformable image matching using constrained hierarchical parametric models

  title={Topology preserving deformable image matching using constrained hierarchical parametric models},
  author={Olivier Musse and Fabrice Heitz and Jean-Paul Armspach},
  journal={Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)},
  pages={505-508 vol.1}
  • O. Musse, F. Heitz, J. Armspach
  • Published 10 September 2000
  • Computer Science
  • Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)
We present a topology preserving image matching method, based on a hierarchical parametric model of the deformation map. The transformation is parameterized at different scales, using a decomposition of the deformation vector field over a sequence of nested subspaces, generated from a single compactly supported scaling function. To preserve topology, the positivity of the Jacobian of the continuous deformation is enforced. We establish that, for the proposed hierarchical parametric model, the… 

Figures from this paper

Topology-Preserving Registration: A Solution via Graph Cuts

A topology-preserving registration method based on a discrete Markov random field of deformations and a block-matching procedure that shows the efficiency of using graph cuts based fusion moves for the optimization of the field even though its potentials are neither sparse nor separable and the reduced fused problem turns to be non-submodular.

Topology Preservation and Regularity in Estimated Deformation Fields

A general formalism to impose topology preserving regularity on a given irregular deformation field is presented, and a comparative analysis of the proposed algorithm with respect to a Gaussian regularizer that enforces the same topology preservation conditions.

A Non-local Topology-Preserving Segmentation-Guided Registration Model

This paper addresses the issue of designing a theoretically well-motivated segmentation-guided registration method capable of handling large and smooth deformations and investigates both a pure quadratic penalization method and an augmented Lagrangian technique with convergence results.

Estimating topology preserving and smooth displacement fields

The proposed smoothing method can render morphometric analysis methods that are based on displacement field of shape transformations more robust to noise without removing important morphologic characteristics.

Topology preservation for image-registration-related deformation fields

Numerical simulations based on OpenMP parallelization and MKL multi-threading demonstrating the ability of the model to handle large deformations (contrary to classical methods) and the interest of having decomposed the problem into smaller ones are provided.

On the construction of topology-preserving deformations

A new method to enforce topology preservation on two/three-dimensional deformation fields for non-parametric registration problems involving large-magnitude deformations for brain mapping and comparisons with existing methods demonstrate the efficiency and the competitiveness of the method.

3-D deformable image registration: a topology preservation scheme based on hierarchical deformation models and interval analysis optimization

Results on multipatient 3-D MRI registration illustrate the ability of the nontrivial extension of the method to preserve topology on the continuous image domain, by resorting to interval analysis optimization techniques.

A Fast Nonrigid Image Registration With Constraints on the Jacobian Using Large Scale Constrained Optimization

  • M. Sdika
  • Engineering
    IEEE Transactions on Medical Imaging
  • 2008
A new nonrigid monomodality image registration algorithm based on B-splines is presented which is efficiently solved by a combination of the multipliers method and the L-BFGS algorithm to handle the large number of variables and constraints of the registration of 3-D images.

A Markov Random Field Approach for Topology-Preserving Registration: Application to Object-Based Tomographic Image Interpolation

A topology-preserving multiresolution elastic registration method based on a discrete Markov random field of deformations and a block-matching procedure applied to the object-based interpolation of tomographic slices that shows an overall improvement in performance with respect to related works in the literature.



3D deformable image matching using multiscale minimization of global energy functions

  • O. MusseF. HeitzJ. Armspach
  • Computer Science
    Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)
  • 1999
This paper presents a hierarchical framework to perform deformable matching of three dimensional (3D) images, using a decomposition of the continuous deformation vector field over a sequence of nested subspaces, generated from a single scaling function.

Estimating Optical Flow in Segmented Images Using Variable-Order Parametric Models With Local Deformations

A new model for estimating optical flow based on the motion of planar regions plus local deformations which exploits the strong constraints of parametric approaches while retaining the adaptive nature of regularization approaches.

A Nonlinear Variational Problem for Image Matching

  • Y. Amit
  • Mathematics
    SIAM J. Sci. Comput.
  • 1994
Minimizing a nonlinear functional is presented as a way of obtaining a planar mapping that matches two similar images by adding a smoothing term to penalize discontinuous and irregular solutions.

Multimodal image registration using statistically constrained deformable multimodels

A deformable model-based technique is presented for the rigid registration of 2D and 3D multimodal images and it is shown that the spatial relations between head and brain as well as the anatomical variations of these two structures are learned.

Multiscale minimization of global energy functions in some visual recovery problems

A new comprehensive approach to minimize global energy functions using a multiscale relaxation algorithm that appears to be far less sensitive to local minima than standard relaxation algorithms is investigated.

Elastically Deforming 3D Atlas to Match Anatomical Brain Images

To evaluate the system for elastically deforming a three-dimensional atlas to match anatomical brain images, six deformed versions of an atlas were generated and the accuracy of the resultant matches was evaluated.

High-Dimensional Image Registration Using Symmetric Priors

A high-dimensional model is used, whereby a finite element approach is employed to estimate translations at the location of each voxel in the template image, and Bayesian statistics are used to obtain a maximum a posteriori (MAP) estimate of the deformation field.

Image matching as a diffusion process: an analogy with Maxwell's demons

Characterization of Neuropathological Shape Deformations

A mathematical model is developed describing the deformation of any brain structure whose shape is affected by both gross and detailed physical processes, and by modeling the brain's elastic properties, it is able to compensate for some of the nonpathological modes of shape variation.