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

Generalized Stain Normalization #4006

Open
bhashemian opened this issue Mar 25, 2022 · 2 comments
Open

Generalized Stain Normalization #4006

bhashemian opened this issue Mar 25, 2022 · 2 comments
Labels
Feature request Pathology/Microscopy Digital Pathology and Microscopy related

Comments

@bhashemian
Copy link
Member

bhashemian commented Mar 25, 2022

Stain normalization in MONAI consists of two components stain extraction and stain normalization. Right now, they are specific to Hematoxylin and Eosin stains but both of these components can be generalized to supports any or at least many stains.

#3505 generalized normalization part to be independent of the stain matrix but the stain extraction needs further investigation to see whether it can be generalized to common stains in histopathology. Also it would be great to know if we can use our stain normalization with arbitrary predefined stain matrices.

Moreover, changes are needed to be fit into the overall structure of MONAI Pathology #4005.

@bhashemian
Copy link
Member Author

Hi @shaneahmed,

Thank you very much for the references. We also were looking into make it compatible with scikit-image operations: https://scikit-image.org/docs/stable/auto_examples/color_exposure/plot_ihc_color_separation.html

Also a discussion here: scikit-image/scikit-image#6333

What do you think?

@bhashemian bhashemian added the Pathology/Microscopy Digital Pathology and Microscopy related label Jul 26, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Feature request Pathology/Microscopy Digital Pathology and Microscopy related
Projects
Status: No status
Development

No branches or pull requests

2 participants