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

💡 [REQUEST] - A Tutorial on Whole Slide Image Classification using PyTorch and TIAToolbox #2669

Closed
Abdol opened this issue Nov 10, 2023 · 1 comment · Fixed by #2675
Closed
Labels

Comments

@Abdol
Copy link
Contributor

Abdol commented Nov 10, 2023

🚀 Descirbe the improvement or the new tutorial

Whole Slide Images are the digital data format from which pathologists and computational pathology researchers investigate cancer growth. To due their enormous image resolutions and and file size (in the order of several gigabytes), conventional image processing methods do not work effectively. This is why we propose writing this tutorial: to (a) explain how to load WSIs using TIAToolbox, which helps process such slides with speed and efficiency using its pyramid stack structure, and (b) show how you can use torchvision models can to analyse WSIs. We believe this tutorial will be useful to the PyTorch community, especially who is interested in using PyTorch models tackle cancer tissue research.

Existing tutorials on this topic

The tutorial will be adapted from our WSI classification example.

Additional context

Category: Image and Video

Written by Tissue Image Analytics Centre (TIA) and invited by @carljparker as part of the PyTorch Docathon H2 2023.
cc @datumbox @nairbv @fmassa @NicolasHug @YosuaMichael @sekyondaMeta @svekars @carljparker @kit1980 @subramen @measty @behnazelhaminia @DavidBAEpstein @shaneahmed @msaroufim

@NicolasHug
Copy link
Member

@niyatikarthik I'm afraid there's already a PR opened for this in #2675

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

Successfully merging a pull request may close this issue.

4 participants