v1.1.0 - Multispectrality and Better Models

[clementpoiret]

Description

We introduce a multispectral mode, to segment from both T1 and T2 images.

Previously, we used manual segmentations registered from T2w to T1w for one dataset in order to learn how to segment hippocampal subfields. The registration lead to systematic biases, meaning constant obvious errors when segmenting T1w MRIs. We corrected manually all labels to fix the issue.

We also added more training data

Fixes #17 #18 #10

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

GitHub actions + manual QC

Test Configuration:

• OS: Arch Linux
• Python version: 3.7; 3.9
• Hardware: Intel CPU + Nvidia Quadro
• Any other relevant config detail:

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules