Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix QC for soft segmentations that have light regions close to 1.0 (e.g. 0.999) #4193

Merged
merged 2 commits into from Aug 16, 2023
Merged

Fix QC for soft segmentations that have light regions close to 1.0 (e.g. 0.999) #4193

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7cd8182
`slice.py`: Round values before segmentation check
joshuacwnewton Aug 11, 2023
0b8f24a
Merge branch 'master' into jn/4178-fix-softseg-qc-0.999
mguaypaq Aug 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion spinalcordtoolbox/reports/slice.py
View file
Open in desktop
Expand Up @@ -60,7 +60,7 @@ def __init__(self, images, p_resample=0.6):
# Check if image is a segmentation (binary or soft) by making sure:
# - 0/1 are the two most common voxel values
# - 0/1 account for >95% of voxels (to allow for some soft voxels)
unique, counts = np.unique(img.data, return_counts=True)
unique, counts = np.unique(np.round(img.data, decimals=1), return_counts=True)
unique, counts = unique[np.argsort(counts)[::-1]], counts[np.argsort(counts)[::-1]] # Sort by counts
binary_most_common = set(unique[0:2].astype(float)) == {0.0, 1.0}
binary_percentage = np.sum(counts[0:2]) / np.sum(counts)
Expand Down