Home

 About

 Sponsors

 Download

 Documentation

 FAQ

 Mailing Lists

 Testing

 News

 Bug Tracking

 Data

 Related Software

 Applications

 Copyright

 Marketplace

This application illustrates the use of the KernelBase Spline transform classes. In particular it compares the behavior of Spline transforms in Insight with the equivalent classes available in VTK. This application requires VTK (version 4.2) to compile. It also uses FLTK for supporting the Graphic User Interface. It is a good example of a complete application in which image processing, visualization and user interaction are integrated using three Open-Source toolkits.

What Is The Purpose Of This Application ?

The object of this application is to illustrate the use of deformable Transformations in Insight. A Deformable Transformation is determined by a set of landmarks placed in the input space and a set of associated landmarks placed on the output space. The transforms in this application will map any other point of the input space into a point on the output space. The transformation corresponding to an arbitrary point is calculated by interpolation from the displacement already defined by the input and output landmarks. These sets of landmarks are ususally refereed to a as Source landmarks and Target landmarks. The Splines Transforms in Insight have been implemented directly form the IEEE-TMI paper by Davis, Khotanzad, Flaming and Harms [1].

About the GUI

This application presents a workbench on which a set of landmarks is placed on an input space (at left on the image) and another set of landmarks is placed on the output space (at right on the image). The positions of the

Visualization is performed using VTK the Visualization Toolkit http://www.vtk.org. The GUI for this application uses FLTK which is an open source multiplatform toolkit for GUI development. It can be downloaded from http://www.fltk.org.

Graphical User Interface
Graphic User Interface using FLTK




What ITK Classes Made This Application Possible ?

The ITK filters used to compute these images are the following:

  • itk::RecursiveGaussianImageFilter
  • itk::AddImageFilter
  • itk::MultiplyImageFilter
  • itk::BinaryMagnitudeImageFilter



    References

    [1] M.H. Davis, A. Khotanzad, D.P. Flaming, S.E. Harms, "A Physics-Based Coordinate Transformation for 3-D Image Matching", IEEE Transactions on Medical Imaging, Vol 16, No. 3, June 1997, pp.317-328.

    Go to next application.