[Insight-users] 3D affine registration.

[Luis Ibanez]

Hi MJM,

The optimization process is very unlikely to correct
for rotations larger than 20 degrees.

If you know that your images are misaligned by
more than 20 degrees, then your best option is to
provide a good initialization for the transform.

For example:
via the use of the LandmarkTransformInitializer class.



Beware, however, that it is common for medical images
to be acquired at different orientations and for those
orientations to be annotated as part of the image header,
particularly if you are using DICOM.  Therefore, before
you conclude that your images are off by as much as 180
degrees, you should review if there is any orientation
information in the header of those images.

One good test is to open both images into Slicer.
Slicer is one of the few applications that will display
correctly the relative positions of medical images,
including both origin and orientation.

You can get Slicer from:
http://www.slicer.org/


      Regards,


             Luis



-----------------------------------------------------------------
On Fri, Dec 25, 2009 at 8:30 AM, Mostafa Jabarouti Moghaddam
<zavata.afnan at gmail.com> wrote:
> Hello all,
>
> If the orientations of the fixed image and moving image are not same, How
> can we expand the parameter space? for example, we could change the rotation
> parameter range between [-180,180] in each direction!
> I searched most of the e-mails in ITK, but i just found out that the best
> way is choosing the proper initial transform. Unfortunately, choosing the
> proper initial transform needs an extensive computation!
>
>
> Best,
> MJM
>
> _____________________________________
> 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
>
>