[Insight-users] 2D-to-3D regsitration

[Luis Ibanez]

Hi Hanzo,

We apologize for our shameful linguistic ignorance.
Could you please have the kindness of translating
your message to English ?


Thanks


    Luis


----------------------------
Olofsen, H. (LKEB) wrote:

> Cool,
> 
> Weet jij wat itk met missing data doet? Want wij hebben probleemgevallen
> waarbij de bovenkant van het brein ontbreekt en de registratie niet gaat
> zonder veel hackwerk per geval.
> 
> Hanzo
> 
> -----Original Message-----
> From: Luis Ibanez [mailto:luis.ibanez at kitware.com]
> Sent: dinsdag 27 juli 2004 15:48
> To: Koning, P.J.H. de (LKEB)
> Cc: ITK
> Subject: Re: [Insight-users] 2D-to-3D regsitration
> 
> 
> 
> Hi Patrick,
> 
> ITK has methods for 2D-3D registration.
> 
> Those methods have been customized for the case
> of registering 3D CT scans to 2D fluoroscopic
> images. This is a comon situation in image guided
> surgery and in surgery planning.
> 
> You seem to be managing a different case.
> That is, registering one slice from a 3D
> volume against another 3D volume.
> 
> Please confirm is this is your case...
> 
> If so, we know of at least two groups that
> have implemented similar techniques using
> ITK.  In practice what you need is to create
> a customized ImageMetric.
> 
> As far as transforms go, you simply use the
> Rigid 3D transform. You set the 2D image as
> fixed image and the 3D as the moving image.
> You don't need a 2D-3D transform in this
> case.
> 
> Please let us know if you have further
> questions.
> 
> 
> Thanks
> 
> 
>    Luis
> 
> 
> ---------------------------------
> Koning, P.J.H. de (LKEB) wrote:
> 
> 
>>Hello,
>>
>>
>>I'm using ITK to do some image registration and have had some succes on 
>>3D images, but now I want to register a 2D slice to a 3D volume.
>>Searching the mailing list archives I found some mails from James Miller 
>>and Daniel Rueckert on that topic, so it looks like should be possible.
>>Is there an exmaple in ITK to show how to do this kind of registration. 
>>I can't find a suitable transform; all esxisting transforms look like 
>>2D-to-2D or 3D-to-3D transforms.
>>
>>Can anyone help me?
>>
>>Thanks in advance,
>>  Patrick de Koning
>>_______________________________________________
>>Insight-users mailing list
>>Insight-users at itk.org
>>http://www.itk.org/mailman/listinfo/insight-users
>>
> 
> 
> 
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>