David Young

> Hm, I don't have a labels.csv file and I don't know how it should look like. I also don't know how to create json label file the ABA provided,...

Also posted a PR (#27) with a fix for the labels reference file loading.

@SaibotMagd are you seeing this loading issue anymore from your first comment? I haven't been able to reproduce it exactly, though I found a related issue for files with two...

PR #64 fixes the `.nii.gz`, two-extensions case.

Hi @SaibotMagd, thanks for asking! Glad to hear the later result looks better, but yes the edge gaps look strange and something I haven't see before. Could you let me...

The screenshots are really helpful, thanks for going through the scenarios and posting them! I can reproduce the gaps now on a 2D image. I extracted a single 2D plane...

Sounds good, let me know how it goes. I'll flag this issue for improving the label/binary image perimeter algorithm, particularly for 2D cases. Thanks again for reporting it!

Thanks for posting this. So the refinement worked well when using horizontal sections, but not coronal planes? And your original annotations are in coronal planes, so ideally the refinement would...

Thanks, I think I have a better understanding now. The intermediate slice b-spline registration is clever. In the coronal refinement output image you showed, are the left slices from your...

> Probably, but I think I overdid this. 62 into 270 (50um resolution) is to much for such a kind of an interpolation. I should decrease the resolution (to 100um),...