[Insight-users] Demons based registration

Ganesh Narayanasamy nganesh76 at hotmail.com
Thu Jan 21 11:02:25 EST 2010



Thanks Luis. The code is working fine in 3D up until a point when it runs into memory issue in my laptop. I am going to try it in a lab computer and see how it goes.

Thanks again,
Ganesh

> Hi Ganesh,
> 
> The  Demons deformable registration filter should work
> in any dimension (2D, 3D, 4D...etc).
> 
> When converting to 3D the 2D example:           DeformableRegistration17.cxx
> 
> You must change lines: 130-133"
> 
>   typedef itk::Image< PixelType, 2 > ImageType;
>   typedef itk::Image< InternalPixelType, 2 > InternalImageType;
>     typedef itk::Vector< float, 2 > VectorPixelType;
>   typedef itk::Image< VectorPixelType, 2 > DeformationFieldType;
> 
> and line 206:
> 
>   const unsigned int Dimension = 2;
> 
> Please give it a try again and let us know if you
> still find any problem.
> 
> Thanks,
>         Luis
> -----------------------------------------
> On Tue, Jan 19, 2010 at 10:07 AM, Ganesh Narayanasamy
> <nganesh76 at hotmail.com> wrote:
> >
> > This is a newbie with just a week long experience in using ITK. I would like
> > to know about demons based registration (mainly the fast-symmetric type). I
> > could run the "DeformableRegistration17.cxx" example code that uses
> > symmetric demons for 2D images. Can I make it work for 3D by just changing
> > line# 206 from
> > const unsigned int Dimension = 2;
> > into
> > const unsigned int Dimension = 3;
> >
> > I tried it but it did not work with the test ultrasound 3D images.
> >
> > Is there any code available for the Symmetric or fast-symmetric demons for
> > registering 3D image volumes ?
> >
> > Thank you,
> > Ganesh
> >

 		 	   		  
_________________________________________________________________
Hotmail: Trusted email with powerful SPAM protection.
http://clk.atdmt.com/GBL/go/196390707/direct/01/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20100121/7c798cc1/attachment.htm>


More information about the Insight-users mailing list