Fix issues with `sct_deepseg` rootlets QC report about spinalcordtoolbox

[joshuacwnewton]

I started working on a branch for this, but realized this is a bit more involved than I first thought:

• The "center of mass" issue was quite easy to fix -- just a simple call to get_centerline.
• I noticed that the axial mosaic crop size of 30x30 is too small to fully show the rootlets seg (since they exist outside the cord, in the CSF region). Increasing it to 40x40 helped.
• However, the colormapping is trickier:
  • The resampling that we're currently doing messes up the label values. (For comparison, sct_label_vertebrae skips resampling.)
  • Even if the labels were perfect, matplotlib's colormaps aren't suited to our labels out of the box.

---

I think the main issue here is that the rootlets seg isn't a binary/softseg, it's a "labeled seg" (akin to sct_label_vertebrae). So, it's not straightforward to simply adapt the existing sct_deepseg SC/lesion seg QC to it; I think it requires an entirely separate QC report.

So, I think it might be better to fix this as part of the effort for bringing sct_label_vertebrae's QC to the qc2.py rework.