A generic interpolator for multi-label images

Joël Schaerer1*,Florent Roche,Boubakeur Belaroussi
1.Bioclinica SAS, Lyon
Abstract
A generic interpolator for multi-label images

Abstract

We present a generic interpolator for label images. The basic idea is to interpolate each label with an ordinary image interpolator, and return the label with the highest value. This is the idea used by the itk::LabelImageGaussianInterpolateImageFunction interpolator. Unfortunately, this class is currently limited to Gaussian interpolation. Using generic programming, our proposed interpolator extends this idea to any image interpolator. Combined with linear interpolation, this results in similar or better accuracy and much improved computation speeds on a test image.

Keywords

InterpolationITK
Manuscript
Source Code and Data

Source Code and Data

.gitignore71 B.ycm_extra_conf.py5.1 KBDocumentresultsgl_linear.png7 KBgl_bspline.png7.8 KBlabel_gaussian.png7.6 KBgl_nearest.png8.3 KBlinear.png5.5 KBnearest.png8.3 KBoriginal.png6.9 KBGeneric label interpolation.odt95.8 KBresults.ods43.4 KBresults.txt1.4 KBLICENSE11.1 KBREADME.md495 BSourceCMakeLists.txt288 BRotateLabels.cxx6.9 KBclassification.mha210.4 KBitkLabelImageGenericInterpolateImageFunction.h3.5 KBitkLabelSelectionAdaptor.h2.6 KBitkLabelImageGenericInterpolateImageFunction.hxx2.6 KBoutput.gitignore14 B

Select a file to preview