[Insight-users] image orientation and registration, current status ?

[J.S.Wijnhout at lumc.nl]

Hi,

 

I have faced (or am facing actually) the same problem. I found it
espacially confusing that the itk::Image has a GetDirection and
GetOrigin method, however these are apparently not used in the
TransformContinuousIndexToPhysicalPoint method. If you want that, you
should use the itk::OrientedImage. But be warned, in the calculation of
the metric the orientation is ignored while computing the gradient. I
concluded that it is best to resample your image such that both images,
fixed and moving, have the same orientation. It is a bit cumbersome, but
it works and the results should not be too different from the results
you would get if the registration would properly using the image
orientation. Still I would like that orientation and origin are
consistently used within ITK (at the very least this behavior should  be
properly documented!).

 

best,

Jeroen

 

________________________________

From: insight-users-bounces+j.s.wijnhout=lumc.nl at itk.org
[mailto:insight-users-bounces+j.s.wijnhout=lumc.nl at itk.org] On Behalf Of
Thees, Sebastian
Sent: Friday, February 01, 2008 9:50 AM
To: insight-users at itk.org
Subject: [Insight-users] image orientation and registration, current
status ?

 

Dear itk developer,

 

I am a new user of itk - so first at all, thanks for this fantastic
library and for providing it open source ! I was really surprised to
found such a comprehensive tool for image registration (and segmentation
of course) on the web.

 

However, from the medical-image-analysis point of view, there is one
thing I could absolutely not understood. Why do you ignore image
orientation in image registration ?!?!? It so extremely limits the easy
use of the toolkit. Even an option to use the orientation cosines should
be present.

 

My question: Is there an example implementation of  the solution
outlined in http://public.kitware.com/Bug/view.php?id=5081 by Luis
Ibanez, so that I can continue with that for other metrics ? Or does a
patch exsists ? Hints, code snippets (i am not too much familiar with
itk and template techniques), etc are welcome ...

 

best regards,

Sebastian

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://public.kitware.com/pipermail/insight-users/attachments/20080201/03c72f29/attachment.htm