Patrick Sadil

> If it helps, I've updated the synthstrip code to no longer rely on the internal 'freesurfer' python package. Now it uses the 'surfa' library, which is available on pip...

> PyTorch tends to use a lot more memory than it necessarily needs to (if space is available). Docker has a default setting that might limit container memory on your...

Hi Maintainers, Following up on this. Did that patch sound feasible? Or, how about adding a dependence on `surfa`, following the official `SynthStrip` implementation? If either of those sound okay,...

I can't share that image, but I may be able to share another that shows the same issue. If this is the problem, then it might also be that the...

Sure, they are ``` dcmmeta_shape: [256, 256, 176] dcmmeta_affine: [ [1.0, 0.0, 0.0, -122.0], [0.0, 1.0, 0.0, -117.0], [0.0, 0.0, 1.0, -102.5], [0.0, 0.0, 0.0, 1.0] ] ```

Just to confirm: was it still going to be helpful to see another example? It's my impression that the reorientation you mention is the cause of the sharp masks (when...

> Thanks for your patience, really hard for me to focus on MRIQC these days. Thanks for the fix, and in general for maintaining this package!

I would be interested in this feature and am potentially available to help with an implementation. I'm currently grading scans based on average framewise displacement, proportion of frames with motion...

Great! Happy for the buy-in. Let me know if there is a more formal procedure for specifying a design, but I'm imagining the following decision points. For values, I'm currently...

Hi @yarikoptic . I think that I'm now working on the same dataset that you were helping to convert. What do you think about having heudiconv using the private tag...