scholarly journals The TVDMFFDVR Algorithm

2012 ◽  
Author(s):  
Nicholas J. Tustison ◽  
Brian Avants
Keyword(s):  
Free Form ◽  
Command Line ◽  
Characteristic Velocity ◽  
Displacement Fields ◽  
B Spline ◽  
B Splines ◽  
Registration Algorithm ◽  
Image Registration Algorithm ◽  
The Family ◽  
Free Form Deformation

The recent ITKv4 refactoring includes several enhancements to the existing registration framework. These additional transform classes provide access to mappings described by dense displacement fields and their corresponding optimization which complement the popular free-form deformation (FFD) ap- proach already in ITK. Innovation motivated by previous work [5] and recent diffeomorphic image regis- tration developments in which the characteristic velocity field is represented by spatiotemporal B-splines [2], resulted in a diffeomorphic B-spline-based image registration algorithm combining and extending these techniques which we make available in ITK through the gerrit system. Additionally, we include two command line tools showcasing the new elements of the registration refactoring for 1) computing mappings between two images (antsRegistration) including the family of transforms discussed in this article and 2) applying those transformations to images (antsApplyTransforms). NB: The user must download the patch available at http://review.source.kitware.com/#/c/3606/ in or- der to compile the code accompanying this article.

A Non-Rigid Image Registration Algorithm Based on NURBS

2012 ◽  
Vol 170-173 ◽  
pp. 3521-3524
Author(s):  
Jing Jing Wang ◽  
Hong Jun Wang
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Research Work ◽  
Medical Image Processing ◽  
Free Form ◽  
Uniform Grid ◽  
B Spline ◽  
Registration Algorithm ◽  
Image Registration Algorithm ◽  
Challenging Research

Non-rigid image registration is an interesting and challenging research work in medical image processing, computer vision and remote sensing fields. In this paper we present a free form deformable algorithm based on NURBS because NURBS (Non-uniform Rational B Spline ) with a non-uniform grid has a higher registration precision and a higher registration speed in comparison with B spline. In our experiment we compare the NURBS based FFD method with the B spline based FFD method quantitatively. The experiment result shows that the algorithm can improve highly the registration precision.

Comparison of B-Spline Surface and Free-Form Deformation Geometry Control for Aerodynamic Optimization

AIAA Journal ◽  
2017 ◽  
Vol 55 (1) ◽  
pp. 228-240 ◽  
Author(s):  
Christopher Lee ◽  
David Koo ◽  
David W. Zingg
Keyword(s):  
Free Form ◽  
Aerodynamic Optimization ◽  
B Spline ◽  
Spline Surface ◽  
Free Form Deformation

scholarly journals A Parallel Nonrigid Registration Algorithm Based on B-Spline for Medical Images

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Xiaogang Du ◽  
Jianwu Dang ◽  
Yangping Wang ◽  
Song Wang ◽  
Tao Lei
Keyword(s):  
Parallel Computing ◽  
Medical Image ◽  
Medical Images ◽  
Computing Time ◽  
Free Form ◽  
Nonrigid Registration ◽  
Processing Unit ◽  
Registration Accuracy ◽  
B Spline ◽  
Registration Algorithm

The nonrigid registration algorithm based on B-spline Free-Form Deformation (FFD) plays a key role and is widely applied in medical image processing due to the good flexibility and robustness. However, it requires a tremendous amount of computing time to obtain more accurate registration results especially for a large amount of medical image data. To address the issue, a parallel nonrigid registration algorithm based on B-spline is proposed in this paper. First, the Logarithm Squared Difference (LSD) is considered as the similarity metric in the B-spline registration algorithm to improve registration precision. After that, we create a parallel computing strategy and lookup tables (LUTs) to reduce the complexity of the B-spline registration algorithm. As a result, the computing time of three time-consuming steps including B-splines interpolation, LSD computation, and the analytic gradient computation of LSD, is efficiently reduced, for the B-spline registration algorithm employs the Nonlinear Conjugate Gradient (NCG) optimization method. Experimental results of registration quality and execution efficiency on the large amount of medical images show that our algorithm achieves a better registration accuracy in terms of the differences between the best deformation fields and ground truth and a speedup of 17 times over the single-threaded CPU implementation due to the powerful parallel computing ability of Graphics Processing Unit (GPU).

Sign in / Sign up

Export Citation Format

Share Document