[ITK-users] Vessel Segmentation

[Nissim Hadar]

The array of shorts I supply is a block of raw DICOM data (with, or without
windowing).  The result is an array of similar size, containing a lot of
zeros, but the non-zero values seem to be quite random.  Does each short
represent a filtered voxel, or do the values have a specific meaning, like
they do in the Segmentation algorithms?  When I view the result as an image
it seems very noisy, even though there /is/ some resemblance to the blood
vessels.
I don't know if my understanding is wrong, my parameters are way off, or
there is a bug in the method....
The images I am using are MRI scans of brain aneurysms and the like.

Thanks



--
View this message in context: http://itk-users.7.n7.nabble.com/Vessel-Segmentation-tp35113p35117.html
Sent from the ITK - Users mailing list archive at Nabble.com.