[Insight-users] little double about the output of Geodesic Active Contours Segmentation with Shape Guidance

[Juan Cardelino]

Hey Haiyong,
         Thanks for answering so quickly. I've just realized that I
misspelled doubt in the title :(

On Wed, May 19, 2010 at 11:56 AM, Haiyong Xu <haiyeong at gmail.com> wrote:
> Hi Juan,
>
> I assumed you are using
> itk::GeodesicActiveContourShapePriorLevelSetImageFilter< >. In brief,
> the transform parameters given in output are to define a
> itk::Transform object (translation and rotation) that will transform
> the target shape to the source shape.
>

Yes, you are right, I'm using
itk::GeodesicActiveContourShapePriorLevelSetImageFilter. However, I
always find the ITK learning curve too steep, particularly in trivial
things like a transform. For that reason,  I was doing the transform
in matlab, with the resulting parameters of the filter. I was lazy to
learn to use the itk::Transform. I'm in a evaluation stage of my
project, meaning that I'm deciding whether to use this filter or not.

> To use this filter, it's really important to understand how
> itk::Transform works. This object transforms a point from target to
> source, very important, ** not** from source to target. Thinking in
> the feature image coordinate system, the source is the original pose
> of shape model, which is located at the coordinate origin (0,0) and
> rotated by 0 radius. The target is the final pose of shape model,
> which is probably located at some position, say (10, 15), and rotated
> by pi/4 radius, clockwise. In this example, the output transform
> parameters from the ITK program would be: translation (-10, -15),
> rotation (-pi/4). In your case, you may need inverse the transform in
> order to register the final shape with the image.
>

So, what your are saying is that I should create a Transform, plug the
output shape (of the GeodesicBlahBlahFilter) as source, the target
will be the registered shape, and the set parameters of the transform
to the inverse of those given by the GeodesicBlahBlahFilter.
Am I getting it right?

> There is probably a bug in itk's GeodesicActiveContour segmentation
> with Shape Prior framework. I think it mess up with the order of
> rotation/translation in itk::Transform object, and still waiting for
> the confirmation from ITK developer community. That will cause an
> invalid segmentation output. Please see the bug report in
> http://www.itk.org/Bug/view.php?id=10617.
>

I see, Is there any way I can get your fix? Because the bug seems to
be unanswered.

> Regards,
> Haiyong
>

Thanks again. Best regards,
                                             Juan