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

Beginner's question #275

Open
dlysiak opened this issue Dec 7, 2023 · 1 comment
Open

Beginner's question #275

dlysiak opened this issue Dec 7, 2023 · 1 comment

Comments

@dlysiak
Copy link

dlysiak commented Dec 7, 2023

I am a new HistoQC user. I would like to ask what the variables: deconv_c0, deconv_c1, deconv_c2 stand for.
I am asking in the relation to the IHC H-DAB staining.

@CielAl
Copy link
Contributor

CielAl commented Dec 19, 2023

Please refer to skimage's documentation of "separate_stains"

In general, it follows Ruifrok's color deconvolution (https://pubmed.ncbi.nlm.nih.gov/11531144/) such that, with a given RGB image, and a given stain matrix, it converts the RGB color of each pixel to the target stain space. For instance, Assume your input is RGB, and in the config you use the following setting:

[DeconvolutionModule.separateStains]
stain: hed_from_rgb
use_mask: True

The RGB colored space will be converted to HED, with deconv_c[n] as n-th channel. In this case, deconv_c0 will be the pixel intensity of H stain, deconv_c1 be that of the E stain, and deconv_c2 be the DAB.

However you should be careful since color deconvolution itself is pretty much a primitive way for stain separation and it is applied here for simplicity and only for compute color space statistics.

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

No branches or pull requests

2 participants