[Insight-users] 2D/3D Intensity based registration

[Luis Ibanez]

Hi Pafal,


1) The 3D/2D registration is currently performed only between
    one 3D dataset and one 2D dataset.

    If you take your 3 independent 2D datasets, you could compute
    the pose of the 3D dataset with respect to each individual
    2D dataset.


2) Yes you can initialize the transformation to identity,
    but that is not necessarily a good idea, specially if
    the actual final transform is too far from identity.

    That is, you should rather initialize the transform with
    a value that is close to the real pose.


3) This example has several independent command line executables.
    You don't have to run them in sequence. What the readme file
    is describing, is a procedure for performing a self-validation
    experiment. That is, you take a 3D image, produce its DRR as
    a 2D image, and then feed that 2D image in the 2D/3D registration,
    and should get as outcome the same transform parameters that you
    used during the DRR generation.

    In a real problem, you would skip the DRR independent generation.


4) The commands shown in the README.txt file are "almost" copy/pasted
    from real commands as typed in a Linux machine.  You could convert
    them to a batch file (for your platform) with a bit of retouching.



   Regards,


      Luis



---------------
pafal wrote:
> I have searched the forums for IntensityBased2D3DRegistration and as of yet I
> have not come with a concrete response to my question.
> 
> By sifting through the IntensityBased2D3DRegistration.cxx code in great
> detail, I gather the pipeline is as follows:
> 
> a) read 3D volume
> b) raycast the 3D volume into a DRR image
> c) similarity metric between DRR image and user input 2D image
> d) optimizwe transforms.
> 
> 
> Questions:
> 
> 1- if I have three 2D images, can I use these images to estimate the pose (6
> d.o.f) of the volume, or is this .cxx file only valid for a single 2D image
> to 3D volume registration?
> 
> 2- Is it possible initializing the transforms to identity, just like in the
> 3D/3D registration examples and hope that the algorithm will optimize the
> transforms close to their true values?
> 
> 3- I'm confused with the Readme.txt file. The pipeline is to first execute
> GenerateProjection by projecting brainweb165a10f17.mha and saving into
> projection.mhd. 
> 
> Then we take  projection.mhd  and compare it with our own 2D image by
> calling IntensityBased2D3DRegistration??
> 
> 
> 4- Are the command lines in Readme.txt copy pasted into batch files?
> 
> 
> 
> any insight on this would be monumental for me.
> 
> thank you 
> 
> regards
> 
> P.