stnava
is the order correct? seems like should be ``` 1. 1Warp( y ) ---> y' 2. 0GenericAffine.mat( y ) ---> y'' ``` see fig 8 and 9 in ants2.pdf
i'm thinking of both ,,, eg to take a point in an image from fixed to moving physical space then it does: x_world = point in fixed image warp( x_world...
registration is very much about getting details right and being very specific. so i find it hard to answer the questions above except to say that none of the short...
in ITK, we interpolate transforms s.t. we can always use physical space. even displacement fields. x = InvW( InvA( y ) ) is correct. if you write this out in...
All metrics minimize - so we return negative MI On Mon, Jan 10, 2022 at 3:51 AM IlvaHou55 ***@***.***> wrote: > Hi, > > After applying a SyN registration, I...
the "surface" in kellykapowski is treated probabilistically. its normal direction is determined by the gradient of the probability map and thus is also probabilistic. brian On Wed, Mar 6, 2019...
i recommend reading through this discussion: https://github.com/dorianps/LESYMAP/issues/11 because SCCAN rescales the data, you need to check the outside of SCCAN correlations by doing: cor( originalDataX %*% abs( canonicalVariatesX ), originalDataY...
yes - @dorianps is correct just note that this also assumes you've restricted weights to be unsigned ( that is the most common case ) brian On Fri, Mar 22,...
no - it's not the same. it's more like this: correlation( A_1 - A_2 , B_1 - B_2 ) ie looking at correlations between pattern differences. brian On Fri, Mar...
should have written it like this: correlation( A_pos - A_neg , B_pos - B_neg ) where A is a single component from modality A and B is a single component...