[Insight-users] Segmentation MRI brain data

[Luis Ibanez]

Hi Vincent,

Are you looking for the typical segmentation of White Matter,
Gray Matter, CSF ?

Or are you looking for a segmentation of brain structures at
a finer scale ?

If you are looking for the top one, you could use several of
the ITK methods:

1) Gaussian Mixture Modeling,
2) Statistical Classifiers (of which actually (1) is one form)
3) Markov Random Fields
4) K-Means

You will find some of these methods described in the
ITK Software Guide:

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

in the "Image Segmentation" and "Statistics" chapters.


You may also be interested in  Slicer 3.0 (also Open Source)

                    www.slicer.org

and its Expectation Maximization module (EMSegmenter)
http://www.na-mic.org/Wiki/index.php/Slicer3
http://www.na-mic.org/Wiki/index.php/NA-MIC/Projects/Structural/Segmentation/EMSegmenter_Software_Development


You will also find interesting to look a the validation studies
done on brain classification in InsightApplications:

         InsightApplications/IBSRValidation

in particular in the subdirectory:

             IBSRClassification


You may also find interesting to look at the application
Brains2 developed by the University of Iowa:

http://www.psychiatry.uiowa.edu/mhcrc/pdf/brains/LabManual.pdf



Regards,


     Luis



-------------------------
Vincent Keereman wrote:
> Hi,
> 
>  
> 
> I’m fairly new to ITK and I was wondering if there was any standard way 
> of segmenting (human) brain MRI images. I suppose a hybrid segmentation 
> algorithm is in order? Someone has probably already faced the same 
> problem and might give me some pointers on which combination of filters, 
> parameters, etc. to use…
> 
>  
> 
> BR
> 
>  
> 
> Vincent
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users