[Insight-users] Re: Segementing Brain Tumour + Level Set Filters

[neha k]

Hello Luis,
Thank you very much for your valuable suggestions and inputs.
Neha

Luis Ibanez <luis.ibanez at kitware.com> wrote:


Hi Neha,


For the same image: tumor57.png you can also use
the ShapeDetectionLevelSetImageFiltere.

Note however that this filter defines the borders
of structures based on gradients. Therefore the
segmentation will find the internal border of the
tumor, if you initialize the level set in the center.

A segmentation of the tumor in tumor57.png is attached.

It was generated with the example in

Insight/Examples/Segmentation/
ShapeDetectionLevelSetFilter

without any modification in the source code, and just
by using the following command line arguments

ShapeDetectionLevelSetFilter
tumor57.png tumor57Segmented.png 30 63 5 1 -1 5 1 20


Where

the number 30 63 are the approximate center of the tumor
the number 5 is the radius to be used for an initial level set
the number 1 is the sigma for the gaussian used in the speed
image computation
the numbers -1 5 are alpha and beta for the Sigmoid filter used
in the speed image computation
the numbers 1 20 are the curvature and propagation scaling.


For a detailed description of this example, please look at the
ITK Software Guide

http://www.itk.org/ItkSoftwareGuide.pdf

in the Level Set Segmentation Chapter.




On way of getting the external border of the tumor is to dilate
this segmentation, and use it as the inital level set for another
run of the ShapeDetection filter. In this way the level set will
walk up to the next edge.



Regards,



Luis


-----------------
neha k wrote:

> Hello Luis,
> I did not make any changes to code. But I was trying to output image 
> mhd & raw format. It is working fine though. Thanks a lot for your input.
> Now, I tried to use shapeDetectionLevelSet Example to work with Brain 
> tumour Raw Image (Attached - tumour57.raw), I am not getting any desired 
> result. For such tumor images, do you have any suggestions for what 
> Level Set Filter to choose? Smoothing (Curvature Anisotropic diffusion 
> Filter) did not seem to help at all. Moreoever, I am not sure why 
> result of above smoothing produces output with black border. I have 
> attached original Image (tumour57.raw), output of smoothing ( 
> tumour57_CurvAnisoSmooth.mhd.raw ) and result of giving this smoothed 
> image to Shape Detection Level Set filter ( 
> tumour57_CurvAnisoSmooth_LevelSet.raw ).
> Any input on this is appreciated.
> Thanks,
> Neha
> 
> */Luis Ibanez /* wrote:
> 
> 
> Hi Neah,
> 
> Thanks a lot for posting such a detailed message.
> 
> 
> We attempted to reproduce the result that you reported,
> but the program worked fine for us.
> 
> 
> 
> Here are the command line parameters that we used,
> and the output from the program:
> 
> 
> A) Command line:
> 
> ShapeDetectionLevelSetFilter BrainT1Slice.png T1.png
> 81 113 5 1 -0.5 3 0.05 1
> 
> Output:
> 
> Max. no. iterations: 800
> Max. RMS error: 0.02
> 
> No. elpased iterations: 108
> RMS change: 0.0199696
> 
> 
> 
> B) Command line:
> 
> ShapeDetectionLevelSetFilter BrainProtonDensitySlice.png PD.png
> 81 113 5 1 -0.5 3 0.05 1
> 
> Output:
> 
> Max. no. iterations: 800
> Max. RMS error: 0.02
> 
> No. elpased iterations: 125
> RMS change: 0.0189581
> 
> 
> The output images (T1.png and PD.png) are attached.
> 
> 
> 
> 
> Did you modified th! e code of this Example
> in any way before running it ?
> 
> 
> 
> Please let us know,
> 
> 
> Thanks
> 
> 
> 
> Luis
> 
> 
> --------------------------
> neha k wrote:
> 
> > Hello,
> >
> > I am trying to check with
> ITK1.8\Example\ShapeDetectionLevelSetFilter,
> > and do not get desired output. I tried this compiled example with
> > following input images and parameters -
> >
> > *1. BrainT1Slice.png(input image from \ITK\Examples\Data) - with *
> >
> > Seed Point - (81 113) , Distance - 5.0,
> >
> > Sigma SigmoidAlpha SigmoidBeta are -- 1 .0 -0.5 3.0
> >
> > Curv. Scaling -- 0.05 Propogation Scaling -- 1
> >
> > *Output File Name Attached - ShapeDetectionLevelSetFilterOutput4.png*
> >
> > *2. BrainProtonDensitySlice.png with Seed Point - (81,114) and
> rest of
> > the parameters *have same values as above.
> >
> > Problem - Result of SigmoidFilter is Blank Image while output ! of
> > ShapeDetectionLevelSet Filter for both images is something weird.
> > (attached files)
> >
> > Any input on this appreciated.
> >
> > Thanks,
> >
> > Neha
> >
> >
> >
> 
> 
> > ATTACHMENT part 2 image/png name=T1.png
> 
> 
> > ATTACHMENT part 3 image/png name=PD.png
> 
> ------------------------------------------------------------------------
> Do you Yahoo!?
> The all-new My Yahoo! – Get yours free!



> ATTACHMENT part 2 image/png name=tumor57SegmentedShapeDetectionLevelSet.png

		
---------------------------------
Do you Yahoo!?
 Yahoo! Mail - Helps protect you from nasty viruses.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://public.kitware.com/pipermail/insight-users/attachments/20041129/b6256828/attachment.htm