Fast 4D elastic group-wise image registration. Convolutional interpolation revisited

Menchón-Lara, Rosa-María; Royuela-del-Val, Javier; Simmross-Wattenberg, Federico; Casaseca‐de‐la‐Higuera, Pablo; Martı́n-Fernández, Marcos; Alberola-López, Carlos

doi:10.1016/j.cmpb.2020.105812

Cited by 11 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Point

is transformed by the n -th transformation as:

with

the spacing between two consecutive points along dimension l and

representing the uniform B-spline function of order E [ 20 ]. We chose

, since those B-splines showed a good balance between smoothness and the support region [ 21 , 22 ]. Since B-spline functions have compact support, only the control points

within the neighborhood

of point

enter the summation.…”

Section: Methodsmentioning

confidence: 99%

Elastic AlignedSENSE for Dynamic MR Reconstruction: A Proof of Concept in Cardiac Cine

Godino-Moya

Menchón-Lara

Martı́n-Fernández

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

Numerous methods in the extensive literature on magnetic resonance imaging (MRI) reconstruction exploit temporal redundancy to accelerate cardiac cine. Some of them include motion compensation, which involves high computational costs and long runtimes. In this work, we proposed a method—elastic alignedSENSE (EAS)—for the direct reconstruction of a motion-free image plus a set of nonrigid deformations to reconstruct a 2D cardiac sequence. The feasibility of the proposed approach was tested in 2D Cartesian and golden radial multi-coil breath-hold cardiac cine acquisitions. The proposed approach was compared against parallel imaging compressed sense (sPICS) and group-wise motion corrected compressed sense (GWCS) reconstructions. EAS provides better results on objective measures with considerable less runtime when an acceleration factor is higher than 10×. Subjective assessment of an expert, however, invited proposing the combination of EAS and GWCS as a preferable alternative to GWCS or EAS in isolation.

show abstract

“…Point

is transformed by the n -th transformation as:

with

the spacing between two consecutive points along dimension l and

representing the uniform B-spline function of order E [ 20 ]. We chose

, since those B-splines showed a good balance between smoothness and the support region [ 21 , 22 ]. Since B-spline functions have compact support, only the control points

within the neighborhood

of point

enter the summation.…”

Section: Methodsmentioning

confidence: 99%

Elastic AlignedSENSE for Dynamic MR Reconstruction: A Proof of Concept in Cardiac Cine

Godino-Moya

Menchón-Lara

Martı́n-Fernández

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Interpolation using convolutions is a well-known topic [6][7][8] ; however, the implementation of FFDs has been based on tensor products since its onset [1,9] and, to the best of our knowledge, reported implementations [10][11][12][13][14] have not made use of convolutions. As for the convolution-based implementation in [5] , it was fully developed for a monomodal registration metric only, namely, the sum of squared differences.…”

Section: Introductionmentioning

confidence: 99%

Efficient Convolution-Based Pairwise Elastic Image Registration on Three Multimodal Similarity Metrics

Menchón-Lara¹,

Simmross-Wattenberg²,

Rodríguez-Cayetano³

et al. 2022

SSRN Journal

Self Cite

View full text Add to dashboard Cite

“…Bsplines are considered one of the effective transformations used in the image registration method. It is used to optimize the correlation between images by adjusting a series of parameters [3,4], which have different varieties, including the convex nuclear B-splines, linear interpolation B-splines, and the cubic B-splines [5]. After transformation between corresponding points in the fixed and moving images, the similarity measurement is calculated during the optimization of the transformation process to determine whether the optimal match between the two images is achieved by measuring the similarity between them.…”

Section: Introductionmentioning

confidence: 99%

Nonrigid Medical Image Registration using Adaptive Gradient Optimizer

Arab

El-Khobby

Ashour³

2021

Journal of Engineering Research

View full text Add to dashboard Cite

Medical image registration has a significant role in several applications. It has sequential processes, including transformation, similarity metric calculation, diffusion regularization, and optimization of the transformation parameters (i.e., rotation, translation, and shear). The optimization process for determining the optimal set of the transformation vectors is considered the main stage affecting the performance of the registration process. Hence, medical image registration can be deliberated as an optimization problem for computing the geometric transformations to realize maximum similarity between the moving image and the fixed one. In this paper a mono-modal nonrigid image registration using B-spline is designed for the alignment of Computed Tomography (CT) images using Adaptive Gradient algorithm (AdaGrad) optimizer. In addition, a comparative study with other first order optimizers, such as Stochastic Gradient Descent (SGD), Adaptive Moment Estimation (Adam) algorithm (AdaMaX), AdamP, and RangerQH were conducted. Also, a comparison with the limited memory Broyden-Fletcher-Goldfarb-Shannon (LBFGS) as a second order optimizer was also carried out. The results showed the superiority of the AdaGrad optimizer by 56.99% and 48.37% improvement in the target registration error (TRE) compared to the SGD, and the LBFGS optimizer, respectively.

show abstract

Fast 4D elastic group-wise image registration. Convolutional interpolation revisited

Cited by 11 publications

References 38 publications

Elastic AlignedSENSE for Dynamic MR Reconstruction: A Proof of Concept in Cardiac Cine

Elastic AlignedSENSE for Dynamic MR Reconstruction: A Proof of Concept in Cardiac Cine

Efficient Convolution-Based Pairwise Elastic Image Registration on Three Multimodal Similarity Metrics

Nonrigid Medical Image Registration using Adaptive Gradient Optimizer

Contact Info

Product

Resources

About