[Insight-users] Fw: ImageType::ImageDimension MRI Bias Correction

[Luis Ibanez]

Hi Xavier,

You probably already read the papers that describe this method:

http://public.kitware.com/Insight/Doxygen/html/classitk_1_1MRIBiasFieldCorrectionFilter.html

"Parametric estimate of intensity inhomogeneities applied to MRI"
Martin Styner, Guido Gerig, Christian Brechbuehler, Gabor Szekely,
IEEE TRANSACTIONS ON MEDICAL IMAGING; 19(3), pp. 153-165, 2000,

(http://www.cs.unc.edu/~styner/docs/tmi00.pdf<http://www.cs.unc.edu/%7Estyner/docs/tmi00.pdf>
)

"Evaluation of 2D/3D bias correction with 1+1ES-optimization"

Martin Styner, Prof. Dr. G. Gerig (IKT, BIWI, ETH Zuerich), TR-197

(http://www.cs.unc.edu/~styner/docs/StynerTR97.pdf<http://www.cs.unc.edu/%7Estyner/docs/StynerTR97.pdf>)



As you have seen from the papers, the method combines a segmentation
process with a bias field correction process.

That lead to several questions:

1) Is the MRI image that you are segmenting, an image of the Brain ?
    if not, you must rethink the number of classes, initial means and
   sigmas that will correspond to the Gaussian mixture model of the
   tissues present in your image.

2) Have you manually evaluated the mean intensity values of the
    tissues present in your image ?

   Have you compared those values to the means of the Gaussian
   distributions that this method is fitting to the histogram ?




   Regards,


       Luis


-----------------------------------------------------------------------------
On 3/26/07, Xavier Penya <xavier.penya at epfl.ch> wrote:
>
>  The former question doesn't matter because I suppose I can trick the
> program in order to have a 2D solution.
> The actual problem is that even in 3D the result image is all zeros (using
> the bias coefficients of an image previously bias-corrected by the
> ImageBiasCorrector).
> Is it a bug? I beg your help. Thanks a lot.
>
> ----- Original Message ----- *From:* Xavier Penya <xavier.penya at epfl.ch>
> *To:* insight-users at itk.org
> *Sent:* Monday, March 26, 2007 6:13 PM
> *Subject:* ImageType::ImageDimension
>
>  Hello,
> I insisct: I tried everything just to put the BiasImageGenerator in 2D
> mode instead of the 3D one, but everything failed...
> Can somebody tell me where is defined the var ImageType? It is the root of
> the problem, due to the part of the code:
>
>
> if(dimension != static_cast<int>(ImageType::ImageDimension))
> {
>
> std::cout << "Currently compiled to only support "
> << ImageType::ImageDimension << " dimensional images."
> << std::endl;
> exit(0);
>
> }
>
> If I put "dimension=2" it shows the error message because
> ImageType::ImageDimension is always 3. The problem is that I cannot change
> (I even cannot reach) ImageType::ImageDimension.
> I need your help please!
>
>         Xavier
>
> _______________________________________________
> 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/20070327/3bd5b892/attachment.htm