charleygros

No worries @perone :-) We will keep you updated when you will be back, enjoy :+1:

Follow-up: We fork `medicaltorch` ([here](https://github.com/perone/medicaltorch)) and implemented the above changes (but also some limitations / other ideas in mind). We would be happy to discuss them with you when time...

@jcohenadad --> In order to mimic `sct_extract_metric`, what about including the following parameters: - `-f` (instead of `-t`) --> like [here](https://github.com/neuropoly/spinalcordtoolbox/blob/master/scripts/sct_extract_metric.py#L67) --> if specified then we compute statistics per tracts...

Many thanks for your very prompt answer and very helful insights @muellerdo ! Really appreciate it! Yes, it would be to: (i) do not apply thresholding on masks between your...

Hi there, I am having the same issue as BORJA. Could you please help us? Many thanks in advance

Deep learning for CSF: we will need to create a database of ground truths for CSF, which can be done with the "help" of `sct_propseg`. Backend the same for all...

> I can attempt to fix this and submit a pull request for your consideration once I've managed to. Wondering if you managed to fix this? I'd be interested, it'd...

@AMBarbosa : many thanks for this. I installed your branch and tested it on my data: the results all made sense to me and the functions worked as expected. I...