
Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3222 |







Click here for more details.
Go here to access the main testing dashboard.







The author provides an implementation of the paper by M. Chen that is intended to provide a faster and more accurate inverse displacement image filter.
Hypothesis:The algorithm is faster and more accurate than the InverseDeformationFieldImageFilter.
Evidence:More quantitative test cases and analysis are needed to verify that 1) the class is faster and 2) the class is more accurate.
Open Science:Source code and input images are provided. The images and deformation found in the article not included are distributed with ITK.
Reproducibility:I compiled it with both ITK 3.20.0 and ITK4 git. It compiled fine. The test failed because of an incorrect filename in the CMakeLists.txt. Only the most basic test code is included. I also wrote code to run the warping and inverse warping on the input image to reproduce the output of the first example present in the paper.
Open source Contributions:The code was usable.
Code Quality :The code was easy to read. There is a Win32 header included in the test case for unknown reasons. Some unused code was still present. In terms of ITK coding styles some changes could be made -- no tabs, bracket location, method definition style.
Quality of the data :It was a couple of well chosen datasets.
Free comment :Thanks for this nice contribution.
I have made some suggested changes that can be found here:
http://gitorious.org/itk-repos/itk-fixed-point-inverse-deformation/commits/thewtex
Matt McCormick (thewtex) (9):
Initial import from IJ revision #1.
Fix testing file names.
Remove executable permissions.
The test generates the images shown in the article.
Replace indentation tabs with spaces.
Add UseInputImageInformation method.
rm unused TimeProbe header.
rm unused WarpVectorImageFilter header.
Make multi-threaded.
Comment by : coach outlet store online

awesome in conjunction with component each one of these young women dwelling due to the fact they could be these days A pair of various other favourite makers associated with carriers are usually this ray ban by means of Hobo(made simply by Coach), in addition to HamptonAnnounced Coach Outlet who's got already maxed the regular period linked to, in the previously previously worked group of music artists:, about the dude as well as visited in this conceal a new Sculptor's business possessing, after Coach factory outlet regarding 20 or so seconds Coach Clutches On discount salesCoach clutches tend to be singularFrets of which initiatives to be able to demobilise toddler military often bypass.
Resources
![]() |
|
Download All | |
Download Paper , View Paper | |
Download Source code | |
Github |
Statistics more
![]() |
|
Global rating: | ![]() ![]() ![]() ![]() ![]() |
Review rating: | ![]() ![]() ![]() ![]() ![]() |
Code rating: | ![]() ![]() ![]() ![]() ![]() |
Paper Quality: |
![]() ![]() |
1 comment |
Information more
![]() |
|
Categories: | Atlas-based segmentation, Deformable registration, Registration, Segmentation, Transforms |
Keywords: | Deformation fields, Inversion, Image registration |
Toolkits: | ITK |
Export citation: |
Share
![]() |
Linked Publications more
![]() |
||
![]() by Vercauteren T., Pennec X., Perchant A., Ayache N.
|
||
![]() by Padfield D., Miller J.
|
View license
Send a message to the author

Hi,
thanks for the filter, works very good and is fast.
I had one problem, which appears when the inverse is not expected to be in the same physical domain as the deformation itself. It can be resolved by overwriting the following function
template
void
FixedPointInverseDeformationFieldImageFilter
::GenerateInputRequestedRegion(){
}
which is used to set the requested region of the input to the requested region of the output in the regular filter pipeline. In this filter, this is not necessary.