Changed workflow for setting the masking value in the skull stripping by nicmuenster · Pull Request #171 · BrainLesion/preprocessing

nicmuenster · 2026-01-28T13:00:37Z

This change implements the the same process as in the defacing step to either use a global custom value for all inputs or the minimum value within the input image as the background value when masking an inage

… process to either a global custom value for all inputs or the minimum value within the input image

brainless-bot · 2026-01-28T13:01:01Z

🤖 Code Formatting Reminder

Hello there! 👋 It looks like the code in this pull request might benefit from some formatting improvements.
Fix the issues locally or use our auto format action by commenting /format on this PR!

nicmuenster · 2026-01-28T13:16:45Z

/format

brainless-bot · 2026-01-28T13:16:56Z

🤖 I will now format your code with black. Check the status here.

Copilot

Pull request overview

Aligns skull-stripping mask application with the defacing workflow by supporting either a global masking/background value or a per-image minimum when filling voxels outside the brain mask.

Changes:

Added masking_value support to BrainExtractor and updated apply_mask() to fill outside-mask voxels using either the provided global value or the per-image minimum.
Updated HDBetExtractor and SynthStripExtractor constructors to accept/forward masking_value.
Minor whitespace cleanup in the registration package init.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
`brainles_preprocessing/registration/__init__.py`	Removes stray blank lines/whitespace.
`brainles_preprocessing/brain_extraction/brain_extractor.py`	Introduces `masking_value` state and updates mask application to use background fill logic consistent with defacing.
`brainles_preprocessing/brain_extraction/synthstrip.py`	Adds `masking_value` parameter to the extractor constructor (currently not applied during `extract()` output writing).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-28T13:30:14Z

+    def __init__(
+        self, border: int = 1, masking_value: Optional[Union[int, float]] = None
+    ):


masking_value is added to the constructor and forwarded to BrainExtractor, but SynthStripExtractor.extract() never uses self.masking_value when writing the masked output (it still hard-codes bg = np.min([0, img_data.min()])). This makes the new parameter ineffective and the docstring misleading. Update extract() to fill background using the same masking_value/per-image-min logic as BrainExtractor.apply_mask (or drop the parameter if not supported).

Copilot · 2026-01-28T13:30:14Z

+        # check whether a global masking value was passed, otherwise choose minimum
+        if self.masking_value is None:
+            current_masking_value = np.min(input_data)
+        else:
+            current_masking_value = (
+                np.array(self.masking_value).astype(input_data.dtype).item()
+            )
+        # Apply mask (element-wise either input or masking value)
+        masked_data = np.where(
+            mask_data.astype(bool), input_data, current_masking_value
+        )


apply_mask() now supports a global masking_value and falls back to per-image minimum when unset, but the existing unit test only asserts that an output file is created. Please extend tests to assert that voxels outside the mask are set to the expected value for both cases (default min-per-image and a custom masking_value).

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

neuronflow

Do we need changes here?

preprocessing/brainles_preprocessing/brain_extraction/synthstrip.py

Line 220 in 22661a6

# write the masked output

nicmuenster · 2026-01-29T10:47:56Z

From my understanding, updating the synthstrip init is still necessary, given that while the center modality might be handled without the apply_mask function in the preprocessor workflow (as seen here)

atlas_mask = self.center_modality.extract_brain_region( brain_extractor=self.brain_extractor, bet_dir_path=bet_dir, use_gpu=self.use_gpu, )

the moving modalities are then afterwards still handled by the apply_mask function:

for moving_modality in self.moving_modalities: moving_modality.apply_bet_mask( brain_extractor=self.brain_extractor, mask_path=atlas_mask, bet_dir=bet_dir, )
One thing to consider however, is that in the synthstrip workflow the minimum between 0 and the input min is taken, so min values above 0 would be handled slightly different now, but this missmatch actually also exists for the current state as well.

neuronflow · 2026-04-24T12:52:22Z

@nicmuenster merge conflict needs to be resolved :)

brainless-bot · 2026-07-24T10:33:54Z

🤖 Code Formatting Reminder

Hello there! 👋 It looks like the code in this pull request might benefit from some formatting improvements.
Fix the issues locally or use our auto format action by commenting /format on this PR!

brainless-bot · 2026-07-24T10:48:30Z

🤖 Code Formatting Reminder

Hello there! 👋 It looks like the code in this pull request might benefit from some formatting improvements.
Fix the issues locally or use our auto format action by commenting /format on this PR!

nicmuenster · 2026-07-24T10:49:34Z

/format

brainless-bot · 2026-07-24T10:49:42Z

🤖 I will now format your code with black. Check the status here.

neuronflow · 2026-07-24T12:05:20Z

@uturkbey do you have time to look into this?

Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (1)

brainles_preprocessing/brain_extraction/brain_extractor.py:85

The masking workflow now has two branches (explicit masking_value vs per-image minimum) and changes the masking semantics from multiplication to np.where(..., current_masking_value), but existing tests only assert that an output file is created. Please add assertions covering the new behavior (e.g., that voxels outside the mask equal np.min(input_data) when masking_value=None, and equal the provided value when masking_value is set) to prevent regressions.

        # check whether a global masking value was passed, otherwise choose minimum
        if self.masking_value is None:
            current_masking_value = np.min(input_data)
        else:
            current_masking_value = (



 class HDBetExtractor(BrainExtractor):
+    def __init__(self, masking_value: Optional[Union[int, float]] = None):
+        """


Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

Comments suppressed due to low confidence (2)

brainles_preprocessing/brain_extraction/synthstrip.py:39

masking_value is now accepted and passed into BrainExtractor, but SynthStrip still hard-codes the masked background value inside extract() (see bg = np.min([0, img_data.min()]) and img_data[mask == 0] = bg at lines 225-226). This means center-modality skull-stripped outputs written by SynthStripExtractor.extract() will ignore the new masking_value behavior described in the docstring/PR.

            border (int): Mask border threshold in mm. Defaults to 1.
            masking_value (Optional[Union[int, float]], optional): global value to be inserted in the masked areas. Default is None which leads to the minimum of each respective image.

        """
        super().__init__(masking_value=masking_value)

brainles_preprocessing/brain_extraction/brain_extractor.py:79

The new masking_value behavior in apply_mask() (global override vs per-image minimum) is not covered by assertions in the existing tests. Current tests only check that an output file is created, so regressions in the chosen background value or dtype casting would go unnoticed.

        # check whether a global masking value was passed, otherwise choose minimum
        if self.masking_value is None:
            current_masking_value = np.min(input_data)
        else:
            current_masking_value = (

+from typing import Optional, Union
+from enum import Enum
+import numpy as np


+        Args:
+            masking_value (Optional[Union[int, float]], optional): global value to be inserted in the masked areas. Default is None which leads to the minimum of each respective image.
+        """
+        super().__init__(masking_value=masking_value)


neuronflow · 2026-07-24T13:02:43Z

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

Comments suppressed due to low confidence (2)
brainles_preprocessing/brain_extraction/synthstrip.py:39

masking_value is now accepted and passed into BrainExtractor, but SynthStrip still hard-codes the masked background value inside extract() (see bg = np.min([0, img_data.min()]) and img_data[mask == 0] = bg at lines 225-226). This means center-modality skull-stripped outputs written by SynthStripExtractor.extract() will ignore the new masking_value behavior described in the docstring/PR.
            border (int): Mask border threshold in mm. Defaults to 1.
            masking_value (Optional[Union[int, float]], optional): global value to be inserted in the masked areas. Default is None which leads to the minimum of each respective image.

        """
        super().__init__(masking_value=masking_value)
brainles_preprocessing/brain_extraction/brain_extractor.py:79

The new masking_value behavior in apply_mask() (global override vs per-image minimum) is not covered by assertions in the existing tests. Current tests only check that an output file is created, so regressions in the chosen background value or dtype casting would go unnoticed.
        # check whether a global masking value was passed, otherwise choose minimum
        if self.masking_value is None:
            current_masking_value = np.min(input_data)
        else:
            current_masking_value = (

@nicmuenster please also have a look at the surpressed comments

…ng value

nicmuenster · 2026-07-24T13:21:13Z

I implmented the first comment, but I am not sure about the second one to be honest. I would also maybe first implement the modality specific masking values before creating specific tests for edge cases

Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.

Comments suppressed due to low confidence (2)

brainles_preprocessing/brain_extraction/brain_extractor.py:6

Enum is imported but not used in this module. Keeping unused imports can confuse readers and may fail linting if/when a linter is added.

from enum import Enum
import numpy as np

brainles_preprocessing/brain_extraction/brain_extractor.py:85

New masking behavior (global masking_value vs per-image minimum) is implemented here, but existing tests only assert that an output file is created. Add unit coverage that verifies masked voxels are set to the configured value, and that None uses the input image minimum.

        # check whether a global masking value was passed, otherwise choose minimum
        if self.masking_value is None:
            current_masking_value = np.min(input_data)
        else:
            current_masking_value = (
                np.array(self.masking_value).astype(input_data.dtype).item()
            )
        # Apply mask (element-wise either input or masking value)
        masked_data = np.where(
            mask_data.astype(bool), input_data, current_masking_value
        )

Vhanged workflow for setting the masking value in the skull stripping…

c5859c4

… process to either a global custom value for all inputs or the minimum value within the input image

Autoformat with black

2395565

neuronflow requested a review from Copilot January 28, 2026 13:25

Copilot started reviewing on behalf of neuronflow January 28, 2026 13:26 View session

Copilot AI reviewed Jan 28, 2026

View reviewed changes

Update brainles_preprocessing/brain_extraction/brain_extractor.py

776cf77

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

neuronflow requested a review from uturkbey January 28, 2026 13:48

neuronflow reviewed Jan 28, 2026

View reviewed changes

Merge branch 'main' into brain_extractor_mask_value

9a523df

nicmuenster marked this pull request as draft January 29, 2026 16:45

neuronflow mentioned this pull request Jan 29, 2026

[FEATURE] modality-specific minima definitions for BET and defacing #174

Open

Merge branch 'main' into brain_extractor_mask_value

f8c99d0

Merge branch 'main' into brain_extractor_mask_value

fcf4b1d

cleaned up after failed merger

fb51ade

Autoformat with black

fc7e640

nicmuenster marked this pull request as ready for review July 24, 2026 10:55

neuronflow requested a review from Copilot July 24, 2026 12:04

Copilot started reviewing on behalf of neuronflow July 24, 2026 12:05 View session

Copilot AI reviewed Jul 24, 2026

View reviewed changes

Comment thread brainles_preprocessing/brain_extraction/hd_bet.py

Comment on lines 13 to +17

class HDBetExtractor(BrainExtractor):

def __init__(self, masking_value: Optional[Union[int, float]] = None):

"""

Removed mode from brain_extractor.py as it is only needed in hd_bet.py

6568378

neuronflow requested a review from Copilot July 24, 2026 12:52

Copilot started reviewing on behalf of neuronflow July 24, 2026 12:53 View session

Copilot AI reviewed Jul 24, 2026

View reviewed changes

changed synthstrip extract function to also use the the defined maski…

d94e078

…ng value

neuronflow requested a review from Copilot July 24, 2026 13:22

Copilot started reviewing on behalf of neuronflow July 24, 2026 13:22 View session

Copilot AI reviewed Jul 24, 2026

View reviewed changes

Uh oh!

Conversation

nicmuenster commented Jan 28, 2026

Uh oh!

brainless-bot Bot commented Jan 28, 2026

Uh oh!

nicmuenster commented Jan 28, 2026

Uh oh!

brainless-bot Bot commented Jan 28, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Copilot AI Jan 28, 2026

Choose a reason for hiding this comment

Uh oh!

neuronflow left a comment

Choose a reason for hiding this comment

Uh oh!

nicmuenster commented Jan 29, 2026

Uh oh!

neuronflow commented Apr 24, 2026

Uh oh!

brainless-bot Bot commented Jul 24, 2026

Uh oh!

brainless-bot Bot commented Jul 24, 2026

Uh oh!

nicmuenster commented Jul 24, 2026

Uh oh!

brainless-bot Bot commented Jul 24, 2026

Uh oh!

neuronflow commented Jul 24, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

neuronflow commented Jul 24, 2026

Pull request overview

Uh oh!

nicmuenster commented Jul 24, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants