fix(brain_extraction): Remove duplicated code, problematic deviation from antsBrainExtraction #931
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #931 +/- ##
==========================================
+ Coverage 69.37% 71.12% +1.74%
==========================================
Files 86 87 +1
Lines 8474 8477 +3
Branches 1057 1057
==========================================
+ Hits 5879 6029 +150
+ Misses 2373 2220 -153
- Partials 222 228 +6 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
|
@mgxd I would appreciate a review here. |
mgxd
reviewed
Mar 6, 2025
antsBrainExtraction.sh passes the original N4 corrected image to Atropos, where we have been running a masked N4 before Atropos. We have examples where this difference leads to failures that do not occur in the original ANTs workflow. Further, if we do run Atropos, then this result is discarded and N4 is run using a white-matter mask. This patch therefore simply passes the original N4 image to the Atropos workflow, but otherwise leaves the workflow unchanged.
effigies
force-pushed
the
fix/brain-extraction-flow
branch
from
0ba6838 to
f8a20dc
Compare
Sure. I also changed |
effigies
force-pushed
the
fix/brain-extraction-flow
branch
from
f8a20dc to
5aa974d
Compare
effigies
force-pushed
the
fix/brain-extraction-flow
branch
from
5aa974d to
4483782
Compare
effigies
commented
Mar 6, 2025
niworkflows/anat/ants.py
Outdated
Comment on lines
436
to
445
| # Check ANTs version | ||
| try: | ||
| inu_n4_final.inputs.rescale_intensities = True | ||
| except ValueError: | ||
| warn( | ||
| "N4BiasFieldCorrection's --rescale-intensities option was added in ANTS 2.1.0 " | ||
| f'({inu_n4.interface.version} found.) Please consider upgrading.', | ||
| UserWarning, | ||
| stacklevel=1, | ||
| ) |
There was a problem hiding this comment.
Rebased to re-add this check, which was removed in passing. If we want to remove these, that can be a separate PR.
|
@mgxd Good to go? |
Co-authored-by: Mathias Goncalves <[email protected]>
effigies
added a commit
that referenced
this pull request
Mar 20, 2025
1.13.0 (March 20, 2025) New feature release in the 1.13.x series. This release restructures the ANTs brain extraction workflow. This should be a backwards compatible change, but a minor release is used out of caution. * FIX: Remove duplicated code, problematic deviation from antsBrainExtraction (#931) * FIX: Listify numbers (#925) * ENH: Allow + symbol in label entities (#926, #927) * STY: Apply various ruff checks (#913, #915, #917, #918, #919, #930)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As discussed in #928, running a masked N4 before calling Atropos can lead to failures, although I don't fully understand why. Nonetheless, passing the output of the first N4 correction resolves the issue in the case I'm looking at as well as brings the workflow into line with
antsBrainExtraction.sh, which does not do this step.Furthermore, if
atropos_wfis called, then N4 is called using the white matter mask at the end, which means this is duplicated effort. This PR rearranges the workflow so that the second top-level N4 is only called ifatropos_wfisn't created. It also shifts from the pattern:to:
I personally find this logic easier to follow and compare between the conditions.
One thing that I discovered was that the
lap_{tmpl,target}andmrg_{tmpl,target}nodes were defined twice, but only connected ifuse_laplacian. Here we always define and connectmrg_{tmpl,target}, and only create and connectlap_{tmpl,target}ifuse_laplacian.