Approximated Curvature Penalty in Non-rigid Registration Using Pairwise MRFs

Glocker, Ben; Komodakis, Nikos; Paragios, Nikos; Navab, Nassir

doi:10.1007/978-3-642-10331-5_102

Cited by 16 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(d) shows the deformed image from Image 1 using the pro- In this example, we compare our proposed QCHR model with other existing registration algorithms using Examples 5-8. We compare our method with TPS [1], LD-DMM [13], diffeomorphic Demons (DDemons) [55], DROP hybrid registration (TPS landmarkmatching + MRF intensity-matching registration) [7,8,6], and Elastix [56,57]. Two measurements are introduced to quantitatively compare the registration results.…”

Section: Hybrid Registration Modelsupporting

confidence: 44%

Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps

Lam¹,

Lui²

2014

SIAM J. Imaging Sci.

View full text Add to dashboard Cite

We present a new approach to obtain diffeomorphic registrations with large deformations using landmark and intensity information via quasi-conformal maps. The basic idea is to minimize an energy functional involving a Beltrami coefficient term, which measures the distortion of the quasiconformal map. The Beltrami coefficient effectively controls the bijectivity and smoothness of the registration. In this paper, we first propose the quasi-conformal landmark registration (QCLR) algorithm to obtain diffeomorphic (1-1 and onto) registrations between images or surfaces. Using QCLR, landmark-aligned diffeomorphisms between images or surfaces can be obtained, even with a large geometric difference or a large number of landmark constraints. This algorithm is then extended to the quasi-conformal hybrid registration (QCHR) algorithm, which combines landmark and intensity (such as image intensity or surface curvature) information to achieve a more accurate registration result. Experiments have been carried out on both synthetic and real data. Results demonstrate the stability and efficacy of the proposed algorithm to obtain diffeomorphic registrations between images or surfaces.

show abstract

Section: Hybrid Registration Modelsupporting

confidence: 44%

Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps

Lam¹,

Lui²

2014

SIAM J. Imaging Sci.

View full text Add to dashboard Cite

show abstract

“…One other limitation of the discrete optimisation approach is that including higher order regularization functions becomes very difficult (Glocker et al, 2009; Kwon et al, 2011), even though the similarity measure can be chosen very flexibly. However, we have found that the advantages of the discrete optimisation framework outweigh the disadvantages for our application.…”

Section: Introductionmentioning

confidence: 99%

MSM: A new flexible framework for Multimodal Surface Matching

et al. 2014

View full text Add to dashboard Cite

Surface-based cortical registration methods that are driven by geometrical features, such as folding, provide sub-optimal alignment of many functional areas due to variable correlation between cortical folding patterns and function. This has led to the proposal of new registration methods using features derived from functional and diffusion imaging. However, as yet there is no consensus over the best set of features for optimal alignment of brain function. In this paper we demonstrate the utility of a new Multimodal Surface Matching (MSM) algorithm capable of driving alignment using a wide variety of descriptors of brain architecture, function and connectivity. The versatility of the framework originates from adapting the discrete Markov Random Field (MRF) registration method to surface alignment. This has the benefit of being unconstrained by choice of a similarity measure and relatively insensitive to local minima. The method offers significant flexibility in the choice of feature set, and we demonstrate the advantages of this by performing registrations using univariate descriptors of surface curvature and myelination, multivariate feature sets derived from resting fMRI, and multimodal descriptors of surface curvature and myelination. We compare the results with two state of the art surface registration methods that use geometric features: FreeSurfer and Spherical Demons. In the future, the MSM technique will allow explorations into the best combinations of features and alignment strategies for inter-subject alignment of cortical functional areas for a wide range of neuroimaging datasets.

show abstract

“…We selected NMI as the similarity measure for it, which performed better than other metrics in the following tests. In the Drop implementation, FastPD [40] was used as the optimizer, and we selected approximated curvature penalty [42] as the regularization function, which penalizes the approximated second-order derivatives of the displacement field. Moreover, we have empirically found that 500 iterations were sufficient to achieve a registration result with no further improvements and the suitable value for the registration parameter was 10.…”

Section: Parameter Settingsmentioning

confidence: 47%

A TV-l 1 based nonrigid image registration by coupling parametric and non-parametric transformation

Xie

et al. 2015

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Abstract:To overcome the conflict between the global robustness and the local accuracy in the dense nonrigid image registration, we propose a union registration approach using a l1-norm based term to couple the parametric transformation and the non-parametric transformation. On one hand, we take the parametric deformation field as a constraint for the non-parametric registration, which is a strong constraint that guarantees the robustness of the non-parametric registration result. On the other hand, the non-parametric deformation field is taken as a force to improve the accuracy of the parametric registration. Then, an alternating optimization scheme is carried out to improve the accuracy of both the parametric registration and the non-parametric registration. Moreover, accounting for the effect of spatially-varying intensity distortions and the sparse gradient prior of the deformation field, we adopt the residual complexity (RC) as the similarity metric and the total variation (TV) as the regularization. Because of the TV-l1-l2 composite property of the objective function in our union image registration, we resort to the split Bregman iteration for the complex problem solving. Experiments with both synthetic and real images in different domains illustrate that this approach outperforms the separately performed parametric registration or non-parametric registration.

show abstract

Approximated Curvature Penalty in Non-rigid Registration Using Pairwise MRFs

Cited by 16 publications

References 19 publications

Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps

Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps

MSM: A new flexible framework for Multimodal Surface Matching

A TV-l 1 based nonrigid image registration by coupling parametric and non-parametric transformation

Contact Info

Product

Resources

About