Fernando Pérez-García

These would be utilities for preprocessing before training, for convenience. Each transform could have different backends, to use the user's preferred method. Here is some code I adapted from [MRIPreprocessor](https://github.com/ReubenDo/MRIPreprocessor):...

I think a generic registration tool is too much. Why would you use TorchIO for that? I was just thinking of very specific usage cases: 1) registering a brain MRI...

> for the same reason as, you, ... Well, I wouldn't use TorchIO as a generic registration tool. > Even if you stay with your specific case, there is no...

I've never used SimpleElastix, I'm not sure. I shared an example with ANTSpy here, it works fine: https://github.com/fepegar/torchio/issues/428#issuecomment-799354311

1.9 s? Wow! You're going to perform registrations during training? Very brave :)

Looking forward to those papers! TorchIO has received a couple of citations from ARAMIS, but not from the CENIR :)

Hi @sairampillai. Thanks for your interest! Yes, this might be a good one. I had in mind something like what I did for NiftyNet: https://github.com/NifTK/NiftyNet/blob/7421b013e5d7852f2eab1861de0bc768995ec82b/niftynet/layer/rand_spatial_scaling.py#L67-L73 You can start by 1....

Hi, @jxchen01. Thanks for reporting. Can you please try to provide a reproducible example?

I coded this transform a long time ago reading [Richard Shaw's paper](http://proceedings.mlr.press/v102/shaw19a.html). My version is a bit simplified, but works. I am now away at a conference, but I'll try...

If you like this approach, we can add this behavior to `RandomMotion`.