add script for creating folder with difficult cases

[naga-karthik]

This PR adds a script to create a list of difficult cases. This list of subjects could be used for benchmarking our segmentation models.

Resolves #131

[jcohenadad]

i would change the name of the function-- it is misleading-- eg: create_folder_of_difficult_subjects.py

[jcohenadad]

i don't think this script will be very useful in the long term-- the idea is:

• for each project (in this case, contrast-agnostic), identify the subjects based on:
  • BIDS dataset root and subj (eg: data/xxx/sub-xxx)
  • concatenate those into a YAML that goes as input into sct_run_batch
  • in the future we can run sct_run_batch -include-list
• What if subjects span across multiple BIDS datasets?
  • solution 1: create a loop (eg in shell or python) that splits the subjs across roots datasets and then run sct_run_batch
  • solution 2: post feature request in SCT to accept running across BIDS datasets: sct_run_batch: add support for multiple input datasets  spinalcordtoolbox/spinalcordtoolbox#4658