[Insight-users] Segmentation

[Luis Ibanez]

Hi Suresh,

If you don't mind to do a bit of user interaction,
an easy way of getting gray matter, white matter
and csf is to use a pipeline similar to the one
used in the RegionGrowingSegmentation example:

http://www.itk.org/HTML/RegionGrowingSegmentation.htm

Which is basically:

1) Use one edge-preserving smoothing filter,
    for example:

    - CurvatureFlow
    - GradientAnisotropicDiffusion
    - CurvatureAnisotropicDiffusion

2) Use the ConfidenceConnectedImageFilter.
    Which requires three parameters:

    a) a multiplier for the variance of the
       gray level distribution of the tissue
       type you are interested on.

    b) a number of iterations

    c) a seed point lying on the tissue of
       interest.

(a) can be fixed at 2.5 for most purpouses

(b) can also be fixed to something around 5

(c) will be better if provided by a user
     clicking on the image.
     This is very easy for a user and will
     relieve your application from dealing
     with computer vision issues.


Combining effective user-interaction with
supervised methods is probably the best
trade-off in medical imaging today.

--

If you are looking to process a large number
of images and consider user-interaction to
be undesirable, a good alternative could be
to rely on a rough registration of your data
with a presegmented brain just with the aim
of obtaining three standard seed points.

A MultiResolution Rigid registration using
a metric like MeanSquare should converge
rapidly for this kind of application.

Please let us know if you will like to have
more details.


   Thanks


    Luis


========================================

suresh wrote:
> Hi Luis,
> 
> Thankyou for your elaborate reply.
> I'm not interested in detailed brain structure.Just separating { White 
> matter, Gray matter, CSF }
> will be fair enough.
> 
> Can you please help me with a little more details.
> 
> Thank you.
> 
> suresh
> 
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users@public.kitware.com
> http://public.kitware.com/mailman/listinfo/insight-users
>