-
Notifications
You must be signed in to change notification settings - Fork 104
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
Generate grids #7
Comments
Hello. Generating the grid tuple is entirely up to you and it depends on what data you are using. In our lb we deal with WSI and generally they come with a lot of background regions. While I could use all the tiles even if they have no tissue, it is much more efficient to only use the ones that do contain tissue. To do that we use a thumbnail of the whole slide and use simple image processing techniques no figure what tiles have tissue. About the read_region function, that comes from openslide. You just need to give it a tuple of coordinates from the ones you calculate before. I hope this was helpful. |
Hello, I am working with rat brain sections, scanned with VS120, I have a *.vsi file. On the zoomed out view I have two brain sections. |
@PlanetsR it seems that your situation may be different. In the code I use openslide to open WSIs and extract small tiles. If you do not use openslide in your application then you would need to custom design a torch dataset class to load images. |
@gabricampanella Hi, I'm also going to deal with WSI with a lot of background regions. Could you share your code for extracting small tiles from the WSI? Like shown in the extended data figure 7 in the paper. Thanks! |
@gabricampanella I'd like to third this request. I'm also attempting to create a method to exclude background regions, and it would be helpful to see how you all extracted your tiles. Thank you for this fantastic project and your continued responses. |
Hi!
First, thanks for the great tool!
I was wondering how do you generate the
grid
tuple in the dictionary for a given image. I am struggling with coordinates and I guess I misunderstood howread_region
works.Any hints on this?
The text was updated successfully, but these errors were encountered: