I think the mask should also be provided to the SSIM function call. As the mask variable is always present/valid (either a proper mask if provided by the user or all-ones, see variable initialisation), it should be fine to simply add the mask as parameter to the call.

In my opinion, structural_similarity_index() should work fine with this additional parameter and nothing should break. However, I did not test the suggested code change.

This really is just a very minor change so please don't be mad at me for not following the standard PR procedure UwU

Proposed Changes

• Set "mask" as optional parameter to structural_similarity_index() for the "synthesis" metric computation case.

Checklist

• I have read the CONTRIBUTING guide.
• My PR is based from the current GaNDLF master .
• Non-breaking change (does not break existing functionality): provide as many details as possible for any breaking change.
• Function/class source code documentation added/updated.
• Code has been blacked for style consistency.
• If applicable, version information has been updated in GANDLF/version.py.
• Tests added or modified to cover the changes; if coverage is reduced, please give explanation.