[Insight-users] Model-Image registration

[Julien Jomier]

Hi Gavin,

 > Does this mean that the final parameters define a transform that must
 > be _composed_ with the transform of the original MovingShape in order
 > to calculate the final fit?  Otherwise, how does one obtain the
 > transformed model according to the final optimization result?

The MovingShape is a group containing three ellipses. The ellipses have 
different transforms wrt the group. The result of the registration is 
the transformation applied to the group and therefore, (as you wrote) 
you should compose the resulting transformation (from the optimization) 
which each individual ellipse's transform. The group should really be 
seen as one object composed of 3 ellipses.

 > What I would like to do is also be able to optimise the _parameters_
 > of some parametric form of a model.  In the case of the ellipse, we
 > might want to perform a rigid body registration, thus getting a
 > rotation and translation transform, but as well we want to adjust the
 > major and minor axis lengths to best fit.

This is very good point. We had some discussion before on that topic. 
The main issue in adding parameters to each SpatialObject is that 
sometimes it doesn't make any sense and/or we don't want to optimize all 
the parameters. I have an idea on how to solve this but I need to 
experiment it before.
For the moment, you should be able to solve the problem in the metric. 
In the metric you can increase the dimension of the parameters array and 
use the extra parameters to change the size of the ellipse. However, you 
will need to modify the ModelImageRegistration1.cxx example and 
recompute the IsInside() at each iteration.

Julien

Gavin Baker wrote:
> Hi,
> 
> I have some questions about the ModelImageRegistration1.cxx example.
> As I understand it, the result of the optimization process is a
> transform that maps the MovingShape onto the FixedImage.  But the
> original shape already had its own model-world transform.
> 
> Does this mean that the final parameters define a transform that must
> be _composed_ with the transform of the original MovingShape in order
> to calculate the final fit?  Otherwise, how does one obtain the
> transformed model according to the final optimization result?
> 
> . . .
> 
> Now the model-image registration we have above is optimised by finding
> parameters to a transform that best maps the model to the image data
> according to some fitness function.
> 
> What I would like to do is also be able to optimise the _parameters_
> of some parametric form of a model.  In the case of the ellipse, we
> might want to perform a rigid body registration, thus getting a
> rotation and translation transform, but as well we want to adjust the
> major and minor axis lengths to best fit.
> 
> Can someone suggest how might this be done?
> 
> Thanks!
> 
>   :: Gavin
>