[Insight-users] How to use itk::SegmentationLevelSetImageFilt er

[Xu, Yanjun]

Hi, Lydia,

Thanks for the response. Is there any planning implementation of a
multilabel fast marching filter? 

Yanjun

-----Original Message-----
From: Lydia Ng [mailto:lng@insightful.com] 
Sent: Friday, December 06, 2002 11:38 AM
To: Xu, Yanjun; insight-users@public.kitware.com
Subject: RE: [Insight-users] How to use itk::SegmentationLevelSetImageFilter

Hi Yanjun,

>Does ITK have any filter supporting Multilabel  Fast Marching? 

No, the fast marching filter currently only supports a single label.

- Lydia


-----Original Message-----
From: Xu, Yanjun [mailto:yanjunxu@umich.edu]
Sent: Friday, December 06, 2002 8:01 AM
To: insight-users@public.kitware.com
Subject: [Insight-users] How to use itk::SegmentationLevelSetImageFilter


Hi,
 
I want to use SegmentationLevelSetImageFilter to do some brain MRI
segmentation, but didn't make clear how to use it. I have the following
questions about it.
 
What kind of seed image does it need? Does it accept one label (class) or
multiple label image? In SparseFieldLevelSetImageFilter<TInputImage,
OutputImage>::ConstructActiveLayer(), it seems that only pixels with
m_ValueZero  are put into ActiveLayer. Is this ActiveLayer considered
propagation front? Does it mean that seed label must be zero? Can this seed
label be point, contour, or area? 
 
Threshold SegmentationLevelSetImageFilter , a subclass of
SegmentationLevelSetImageFilter,  need upperThreshold and lowerThreshold.
What is the value range for these two thresholds? Are they the thresholds
for original image or some derived feature image( Curvature, Gradient)? 
 
Does ITK have any filter supporting Multilabel  Fast Marching? 
 
Thanks a lot.
 
Sincerely,
Yanjun