[Insight-users] Re: Image or Mesh to Tubes

Luis Ibanez luis.ibanez at kitware.com
Thu Aug 3 18:05:02 EDT 2006


Hi Kevin,

Addional methods related to extacting tubes from images
are available at

      InsightApplications/
                DuctExtractor

and using the Hessian filter in

      InsightApplications/
                Curve3DExtractor

There is also a Vesselness filter in

http://www.itk.org/Insight/Doxygen/html/classitk_1_1Hessian3DToVesselnessMeasureImageFilter.html


The challenging aspect in your application is the large size
of the images. In that case you may find more appropriate
a model of tube tracking such as the ones described in Stephen's
publications or like the Crawlers implemented in the Deformable
Organisms papers that Chirs McIntosh and Ghassan Hamarreh suggested.


You will find code for the Deformable Organisms in their recent
paper posted to the Insight Journal

        http://hdl.handle.net/1926/228



Regards,


      Luis



----------------------
Kevin H. Hobbs wrote:
> On Wed, 2006-08-02 at 11:13 -0400, Julien Jomier wrote:
> 
>>Aylward S, Jomier J, Weeks S, Bullitt E, "Registration of Vascular 
>>Images," International Journal of Computer Vision, March 2003, pages 15
> 
> 
> It seems to me that before I can proceed with ANY registration I need to
> have what you call Vessel Modeling working.
> 
> Most of the math is over my head, but I've already noticed that we don't
> have such a well defined central ridge. The images are almost binary:
> 
> http://crab-lab.zool.ohiou.edu/kevin/dend.png This image is a slice of a
> small piece of the whole cell.
> 
> http://crab-lab.zool.ohiou.edu/kevin/dend_cont_255.png This image is the
> same but with the contour at the level 255 overlaid. It looks like the
> sensor was almost completely saturated... It was bright die.
> 
> http://crab-lab.zool.ohiou.edu/kevin/dend_grad_mag_thresh_10.png Again
> this is the same view but of the gradient magnitude thresholded to show
> only values above 10.
> 
> I'm looking at the methods itk::ApproximateSignedDistanceMapImageFilter
> and itk::SignedDanielssonDistanceMapImageFilter to add some fake info
> into the dendrites.
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users




More information about the Insight-users mailing list