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.

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

Trimming of for Cellpose #19

Open
dwbaggett opened this issue Jun 7, 2022 · 1 comment
Open

Trimming of for Cellpose #19

dwbaggett opened this issue Jun 7, 2022 · 1 comment
Assignees
Labels
enhancement New feature or request

Comments

@dwbaggett
Copy link
Collaborator

🚀 Feature

An option to remove stacks with a ROI signal below a certain threshold

Motivation

When segmenting ROI such as cells or nuclei, cellpose appears to normalize the signal in each image before segmenting, particularly when doing 2D analysis. This leads to an over-extension of the cellpose mask in the z-directions, where diffuse, out-of-focus, signal is interpreted as an ROI. This over-extension leads to challenges in proper parameter selection, and segmentation.

Pitch

An additional flag to allow for "pruning" of analyzed z-frames based on the max ROI signal intensity of the z-frame.

Alternatives

This could feasibly exist either as a part of the setup_ROI_segmentation and run_ROI_segmentation notebooks, or exist as a standalone pre-processing utility script/notebook. The second option would depend on puncta analysis notebooks to be able to batch analyze stacks of different sizes. I do not know that the notebooks as-is currently allow for different sized z-stacks.

Additional context

3D_Cellpose
3D_Raw

@dwbaggett dwbaggett added the enhancement New feature or request label Jun 7, 2022
@amedyukhina amedyukhina added this to the V 0.3.0 milestone Jun 17, 2022
@amedyukhina amedyukhina self-assigned this Jun 17, 2022
@amedyukhina
Copy link
Contributor

This should be relatively straightforward to implement. Stacks of different sizes will not be an issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants