added dynamic erosion voxel size based in input data voxel size#164
Merged
constantinpape merged 4 commits intoApr 22, 2026
Merged
Conversation
| mito_seg = scaler.scale_input(mitochondria, is_segmentation=True) | ||
| input_volume = np.stack([volume, mito_seg], axis=0) | ||
|
|
||
| erode_voxels = max(1, round(6.0 / erosion_voxel_size)) |
Contributor
There was a problem hiding this comment.
What exactly is the logic here? I.e. why 6 divided by the erosion_voxel_size.
Contributor
Author
There was a problem hiding this comment.
This assumes the average outer mito membrane is 6nm thick. The erosion voxel size is the voxel size in which the model runs inference: e.g. 1.45nm then we get 4 voxels to erode
Contributor
Author
There was a problem hiding this comment.
i've checked some of the test split tomos and it appears that the mito membrane is bigger than 6nm - for the tomos i checked it averages at approx. 10nm
lufre1
commented
Apr 21, 2026
|
|
||
| # target 10nm erosion for mitochondria | ||
| # voxel_size is the model's training voxel size, which is the space we erode in | ||
| erode_voxels = max(1, round(10.0 / voxel_size)) |
Contributor
Author
There was a problem hiding this comment.
we resize the input volume to the model's training voxel_size, so we can use this voxel_size to compute the voxels that correspond to 10nm to use for the erosion
constantinpape
approved these changes
Apr 22, 2026
constantinpape
deleted the
163-cristae-segmentation-mitochondria-erosion
branch
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.