Temporal sparse free-form deformations

Shi, Wenzhe; Jantsch, M; Aljabar, Paul; Pizarro, Luis; Bai, Wenjia; Wang, Haiyan; O’Regan, Declan P; Zhuang, Xiahai; Rueckert, Daniel

doi:10.1016/j.media.2013.04.010

Cited by 56 publications

(54 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…linear and cubic) of B-splines while enforcing sparsity constraints on the coefficients of those basis functions. A similar approach was introduced in [28] in the context of estimating smooth cardiac motion using cubic Bsplines with different grid spacing.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Isotropic Total Variation Regularization of Displacements in Parametric Image Registration

Vishnevskiy

Gass

Székely

et al. 2017

IEEE Trans. Med. Imaging

167

119

View full text Add to dashboard Cite

Abstract-Spatial regularization is essential in image registration, which is an ill-posed problem. Regularization can help to avoid both physically implausible displacement fields and local minima during optimization. Tikhonov regularization (squared 2-norm) is unable to correctly represent non-smooth displacement fields, that can, for example, occur at sliding interfaces in the thorax and abdomen in image time-series during respiration. In this paper, isotropic Total Variation (TV) regularization is used to enable accurate registration near such interfaces. We further develop the TV-regularization for parametric displacement fields and provide an efficient numerical solution scheme using the Alternating Directions Method of Multipliers (ADMM). The proposed method was successfully applied to four clinical databases which capture breathing motion, including CT lung and MR liver images. It provided accurate registration results for the whole volume. A key strength of our proposed method is that it does not depend on organ masks that are conventionally required by many algorithms to avoid errors at sliding interfaces. Furthermore, our method is robust to parameter selection, allowing the use of the same parameters for all tested databases. The average target registration error (TRE) of our method is superior (10% to 40%) to other techniques in the literature. It provides precise motion quantification and sliding detection with sub-pixel accuracy on the publicly available breathing motion databases (mean TREs of 0.95 mm for DIR 4D CT, 0.96 mm for DIR COPDgene, 0.91 mm for POPI databases).

show abstract

Section: Discussionmentioning

confidence: 99%

“…As in the free-form deformations (FFD) framework [20], [28], we parametrize the displacement field d via interpolation of the displacements k on a regularly spaced (K n -pixel span in n-th direction) control point grid, i.e. d = d(k).…”

Section: Parametrizing Displacement Fieldsmentioning

confidence: 99%

Isotropic Total Variation Regularization of Displacements in Parametric Image Registration

Vishnevskiy

Gass

Székely

et al. 2017

IEEE Trans. Med. Imaging

167

119

View full text Add to dashboard Cite

show abstract

“…To build a statistical motion model, first of all, we perform motion tracking for each subject using the spatio-temporal B-spline image registration with a sparseness regularisation term (TSFFD) (Shi et al, 2013b). The motion field estimate is represented by a displacement vector at each point and at each temporal frame t, which measures the displacement from the 0-th frame (the ED frame according to the imaging protocol) to the t-th frame.…”

Section: Statistical Motion Modelmentioning

confidence: 99%

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

Bai

Shi

Marvao

et al. 2015

Medical Image Analysis

Self Cite

125

116

View full text Add to dashboard Cite

“…One main difficulty of the FFD approach is to cope with the conflict between global robustness and local accuracy [29,30] . Shi et al [30] defined the robustness as the ability to recover the deformation in the presence of noise, and the accuracy as the ability to reconstruct the highly-localized and potentially discontinuous deformation with as little error as possible. The trade-off between accuracy and robustness stems from the fact that the FFD approach uses a smooth B-spline basis to model the contribution of each control point to the deformation.…”

Section: Introductionmentioning

confidence: 99%

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

Temporal sparse free-form deformations

Cited by 56 publications

References 40 publications

Isotropic Total Variation Regularization of Displacements in Parametric Image Registration

Isotropic Total Variation Regularization of Displacements in Parametric Image Registration

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

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

Contact Info

Product

Resources

About