Project-MONAI / Project-MONAI/MONAI

Develop a dataset for global stain extraction

Open
#4,015 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Feature request Pathology/Microscopy
Dominant language
Python
Stars
8.7k
Forks
1.6k
Avg merge
5d 1h
Merged PRs (30d)
20

Description

Stain normalization requires a stain matrix that are particular to an image or a set of image acquired under the same condition and settings. In MONAI pathology, we have this functionality to extract the stain matrix from a patch of a whole slide image (WSI) with deconvolution; however, to make this process robust, we need to have pipeline to perform it on all the patches of one WSI (or several WSIs), which requires a specific dataset that handles loading and feeding all patches into this transform.
This dataset shares a lot of similarities with a general patch-based inference dataset so it would be better to design and implement such inference dataset with having this application in mind.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Review the existing general patch-based inference dataset and the pathology stain deconvolution functionality mentioned in the issue. Define how the new dataset should load patches from one or several WSIs and feed them into the transform pipeline; done means it supports robust global stain-matrix extraction across those patches.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
data, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.