Hi Chengcheng,
 the segmentation itself makes no assumptions on the fact that the lumen is 
brighter
than the outside, however the initialization - like colliding fronts and fast 
marching - does
by default. A trivial way to go around this is to negate the image before 
running the segmentation.
There's actually no script in vmtk to do that, but this pipe should do the 
trick:

vmtkimagecompose -ifile image.vti -i2file image.vti --pipe vmtkimagecompose 
-i2file image.vti -negatei2 1 -ofile negated_image.vti

I just added a switch to vmtkimageinitialization that allows to negate the 
image while initializing.

I'm curious to see if this helps, please keep me posted.

Best regards


Luca


On Nov 10, 2010, at 7:08 PM, Chengcheng Zhu wrote:

> Hi,
> 
> I have tried to segment carotid artery bifurcation using black-blood
> T1 or T2 weighted MR images, but the result was very bad. However, it
> works quite well on time-of-fight MR images. Does the vessel must be
> bright (hyperintense) for VMTK to segment? Thank you.
> 
> Best Wishes
> 
> Chengcheng
> 
> ------------------------------------------------------------------------------
> The Next 800 Companies to Lead America's Growth: New Video Whitepaper
> David G. Thomson, author of the best-selling book "Blueprint to a 
> Billion" shares his insights and actions to help propel your 
> business during the next growth cycle. Listen Now!
> http://p.sf.net/sfu/SAP-dev2dev
> _______________________________________________
> vmtk-users mailing list
> vmtk-users@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/vmtk-users


------------------------------------------------------------------------------
Centralized Desktop Delivery: Dell and VMware Reference Architecture
Simplifying enterprise desktop deployment and management using
Dell EqualLogic storage and VMware View: A highly scalable, end-to-end
client virtualization framework. Read more!
http://p.sf.net/sfu/dell-eql-dev2dev
_______________________________________________
vmtk-users mailing list
vmtk-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/vmtk-users

Reply via email to