[Insight-users] Deformation vectors in the BSplineDeformationTransform?

[Charl Botha]

2009/8/19 motes motes <mort.motes at gmail.com>:
> So basically what he says is that the difference between the pixel
> values of the fixed and moving image are accumulated. No pixel values
> in the fixed and moving images are updated (unlike when doing
> resampling) only the difference is computed after applying the
> transform.

the current transform is applied after each iteration, as the
similarity needs to be computed for the current transform.  If this is
what you mean, then I agree.

> After computing the transform it can be used in a resampling filter to
> map the moving image into the fixed image space as described earlier.

Yes.

> Is this how it works?

as far as I know. :)