[Insight-users] Validation of deformable registration

[Marta]

Hello once again,

I still have the questions below, but I also have a new one that  
bothers me to the topic.

What is a good way to find data for my synthetic deformation field? I  
mean, it isn't enough to deform the image "anyhow", it's important to
have a realistic deformation, right? How can I imitate that? Are there  
any tools to create an synthetic deformation field?

Thanks for any comments to my questions! It's important for my master  
thesis.

Best regards,
Marta


Am 05.03.2009 um 17:38 schrieb Marta:

> Hi,
>
> I try to validate my deformable registration method and I do already  
> know that there is no standard for it.
> Anyway, I found in older posts a way to do it by generating an  
> artificially deformation field and compare it with the result  
> deformation field.
> Luis told (e.g.) so in http://www.itk.org/pipermail/insight-users/2006-July/018634.html 
> :
>
> "The common approach is to artificially generate a
> deformation field by using ThinPlateSplines, use this artificial  
> deformation field in order to create a deformed version of your image.
> Then use your registration method between the original and the  
> deformed image, and finally compare the artificial deformation field  
> against the one that
> you produced with the registration method."
>
> However, I'm not sure what is the best way to compare the  
> deformation fields. Can I also use a squared image difference?
> Or are there any better ways?
>
> Would be happy for any suggestions!
>
> Best regards,
> Marta
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.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