monai-mil
Archived This repository is archived: read-only and no longer maintained.
Overview
This tutorial contains a baseline method of Multiple Instance Learning (MIL) classification from Whole Slide Images (WSI). The dataset is from Prostate cANcer graDe Assessment (PANDA) Challenge - 2020 for cancer grade classification from prostate histology WSIs. The implementation is based on:
Andriy Myronenko, Ziyue Xu, Dong Yang, Holger Roth, Daguang Xu: "Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging". In MICCAI (2021). arXiv
Please install the required dependencies
For more information please check out the installation guide.
Prostate biopsy WSI dataset can be downloaded from Prostate cANcer graDe Assessment (PANDA) Challenge on Kaggle. In this tutorial, we assume it is downloaded in the /PandaChallenge2020 folder
If you need to use only specific gpus, simply add the prefix CUDA_VISIBLE_DEVICES=...
Expected validation QWK metric
From the project’s README on GitHub.
At a glance
| Repository | Kentucky-Open-Science/monai-mil |
|---|---|
| Research area | Other projects |
| Primary language | Python |
| Languages | Python 98.7%, Dockerfile 1.2%, Shell 0.1% |
| License | None specified |
| Stars / forks | 1 / 1 |
| Open issues and pull requests | 0 |
| Created | 2022-07-28 |
| Last push | 2023-05-26 |
| Default branch | master |
What the README covers
- Requirements
- Dependencies and installation
- MONAI
- Data
- Examples
- Train
- Validation
- Inference
- Stats
- Questions and bugs
Top contributors
- @codybum (142 commits)
- @alex-virodov (7 commits)
Get the code
git clone https://github.com/Kentucky-Open-Science/monai-mil.git