[Insight-users] Vesselness Enhancement filter
Luis Ibanez
luis.ibanez at kitware.com
Wed Apr 8 12:31:09 EDT 2009
Hi Wen,
I assume that you are referring to the code from the
Insight Journal paper:
http://www.insight-journal.org/browse/publication/163
(http://hdl.handle.net/1926/558)
Is that right ?
If so,
Please note that this will only work for 3D images.
This is mainly due to the fact that the class:
itkAnisotropicDiffusionVesselEnhancementFunction.h
uses the class
itkHessianSmoothed3DToVesselnessMeasureImageFilter.h
Which only work for 3D images (as the name indicates).
In principle, it should be possible to convert (adapt)
this code to also work in 2D images.
If you are interested in trying to to so, we will be
happy to assist you.... and of course... we will
strongly encourage you to share the resulting code
with the ITK community by submitting a follow up
paper to the Insight Journal.
Regards,
Luis
----------------
Wen Shi wrote:
> Hi Guys,
>
> Have you ever tried to use the VED(Vesselness Enhancement filter) in ITK.
> I got a question, is the filter able to process 2D vessel images?
> Since in the code when I change the dimension parameter to 2, then there is debug errors. The followings are what I changed(actually just the dimension) and the debug error information:
>
> // Define the dimension of the images
> const unsigned int Dimension = 2; // I modified this
> typedef short InputPixelType;
> typedef double OutputVesselnessPixelType;
>
> The error says the input image is not thick enough, the axis2 should least has 4 pixels.
>
> So I think that VED can just deal with 3D images.
> Is that right>?
>
> Wen Shi
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Please keep messages on-topic and check the ITK FAQ at: http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users
>
More information about the Insight-users
mailing list