[Insight-users] Mult-Spectral Segmentation

[Tom Nash]

Hi 

I have been using the ImageKMeansModelEstimator and the ImageClassifierBase for a multi-spectral segmentation of brain MRI. I feel the results I got are great but I still could make them better. At some parts I feel that the classifier is confused and classifies it wrongly. Any advice on fine tuning the output?Right now the outputs are equivalent to FSL's segmentation results, but I need to better it. Please give me some suggestions based on your experiences. Is there a better algorithm\class which I could use?

Sincerely
Tom

_________________________________________________________________
Searching for the best deals on travel? Visit MSN Travel.
http://in.msn.com/coxandkings
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20081107/448afe8d/attachment.htm>