I’d recommend applying the same spatial transform to each echo. A fundamental assumption of multi-echo analyses is that the data in each voxel represents the same underlying anatomical volume, just at a different echo time. Applying different spatial transforms to each echo would violate that assumption.
That said, spatial distortion can increase with echo time, which would also violate that assumption. A blipup blipdown correct might be able to correct for this issue and actually result in more spatial similarity within each voxel. One would need to set constraints to make sure the variation in distortion corrections across echos is plausible and the interpolation method doesn’t cause additional problems. I don’t know of anyone who has specifically looked into this in the context of multi-echo fMRI denoising. It could be a promising methodological research direction, but I wouldn’t recommend applying echo-specific distortion corrections without first doing such an evaluation.
-Dan