[Insight-users] segmenting delay update
Joshua Cates
cates@sci.utah.edu
Wed, 2 Apr 2003 10:58:44 -0700 (MST)
Hi,
One trick is to add processors. Curvature flow will automatically
multithread giving near linear speedup.
Also, I would recommend using one of the anisotropic diffusion filters
instead of curvature flow. You will get better edge preservation
and may be able to decrease the number of iterations by playing around
with higher "conductance" parameter values.
Be careful increasing the timestep. Your solution may not be stable
in 3D with a .25 time step.
Josh.
______________________________
Josh Cates
School of Computer Science
University of Utah
Email: cates@sci.utah.edu
Phone: (801) 587-7697
URL: http://www.sci.utah.edu/~cates
On Wed, 2 Apr 2003, Robin Gandhi wrote:
> By using parameters as below
> i was able to drop down the time to 25 seconds but it
> still appears to be a long wait.
>
> Smoothing filter CurvatureFlowImageFilter
>
> smoothing->SetNumberOfIterations( 5 );
> smoothing->SetTimeStep( 0.25 );
>
> Confidenceconnected filter
>
> confidenceConnected->SetMultiplier( 3.0 );
> confidenceConnected->SetNumberOfIterations( 5 );
> confidenceConnected->SetReplaceValue( 255 );
> confidenceConnected->SetInitialNeighborhoodRadius(2)
>
> Thanks
>
> --Robin.
>
> --- Robin Gandhi <itkmail@yahoo.com> wrote:
> > hi everyone,
> > I am semgmenting a brain tumour out of a MRI
> > volume
> > (256x256x24) using the ConfidenceConnected.cxx
> > example
> > in the Examples/Segmentation directory.
> >
> > These are the parameters that I am using for this
> > example, (I have changed the example to work on a 3D
> > volume.)
> >
> > Smoothing filter CurvatureFlowImageFilter
> >
> > smoothing->SetNumberOfIterations( 10 );
> > smoothing->SetTimeStep( 0.125 );
> >
> > Confidenceconnected filter
> >
> > confidenceConnected->SetMultiplier( 2.5 );
> > confidenceConnected->SetNumberOfIterations( 5 );
> > confidenceConnected->SetReplaceValue( 255 );
> > confidenceConnected->SetInitialNeighborhoodRadius( 5
> > );
> >
> > The results of segmenting the tumor are good but it
> > takes around 30 to 40 seconds to do the segmentation
> > for a very small tumour volume.
> >
> > Can any one suggest me the parameters I can tune
> > to reduce the processing time for this 3D volume.
> >
> > thanks in advance
> > --Robin.
>
>
> __________________________________________________
> Do you Yahoo!?
> Yahoo! Tax Center - File online, calculators, forms, and more
> http://tax.yahoo.com
> _______________________________________________
> Insight-users mailing list
> Insight-users@public.kitware.com
> http://public.kitware.com/mailman/listinfo/insight-users
>