[Insight-users] Deformable Model To Image Registration?

[Luis Ibanez]

Hi itkvtk123,

What you describe seems to be equivalent to an

                                "Atlas-based segmentation"

You could do this in ITK by using Deformable registration between
the two images, and then using the resulting deformation field and
the WarpImageFilter or the ResampleImageFilter to resample the
segmentation that you have from one of the images.

That said, please note that a deformation as strong as
warping a circle into a square is probably not a realistic
target...

Hopefully you don't need such a dramatic deformation for the
case that you are dealing with.

      Regards,


            Luis


---------------------------------------------------------------------------------------------
On Wed, Nov 4, 2009 at 12:41 PM,  <itkvtk123 at gmx.net> wrote:
> Hi
>
> is there a way in ITK to perform a deformable model to image registration?
> Let's say we have an image serie where you can see a circular structure.
> Over time, the circular structure deforms into a rectangular structure.
>
> Let's further say we have already segmented the circular structure in the
> first frame as a contour (e.g. an itkPolygonalSpatialObject) of K points.
>
> What I want is the transform for each of the K points, so that if you would
> apply this transform to the points on the outline of the circular structure,
> you would get outline of the rectangular structure.
>
> Do you understand what I mean? Is there something like this in ITK?
> I did some research and came across both the Model Based Registration and the
> Point Set Registration, but these seem not to be the right tools, are they?
>
>
>
>
> --
> GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
> Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.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
>