[Insight-users] FastMarchingSegmentation problems with .mha*

[Luis Ibanez]

Hi Michal,


Here are some of the key steps that you may want to try:

1)  Save our Speed image to a file and look at it with an decent Viewer
     (e.g. the ImageViewer from InsightApplications).

     The image should *ALMOST* look like a segmentation of the structure
    you are trying to get. The object should be almost set to 1.0, its edges
   should be almost set to 0.0

   For examples on how the Speed image should look like,
   please look at the ITK Software Guide

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

   in particular to the Level Sets section.


2) Verify that the seed points that you are providing are indeed inside
    the 1.0 region, inside of the object that you want to extract.


3) Also pay attention the pixel type that you are using for storing the
output
    (that you see to be zeros) and the file format that you are using for
that
    output (is that also a MetaImage ?)


 Please let us know what you find,


     Thanks


         Luis


----------------------
On 7/25/07, Michal Plotkowiak <michal.plotkowiak at bnc.ox.ac.uk> wrote:
>
> Hi,
>
> I've just started working with ITK few days ago. I'm trying to segment 3d
> mri data
> (in mha format)using the Fast Marching Segmentation but I'm getting zeros
> as a
> final result. I tried different parameters but didnt succeed. The filters
> parameters are alright as I get outputs 1-3. I run the program for 2d mri
> slice
> (taken from my 3d data as a png) and it was fine. Could someone please
> help me?
>
> many thanks
> michal
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://public.kitware.com/pipermail/insight-users/attachments/20070725/4af6d2b8/attachment.htm