[Overview] | [Walkthrough] | [Acknowledgement] | [Citation]
π Recent updates:
This repo provides a complete and detailed tutorial for users who intend to process TCGA Whole-Slide Images (WSIs) for downstream computational tasks, such as WSI classification and survival analysis (basically with multiple-instance learning (MIL) as the learning paradigm).
π₯ Moreover, this repo also provides an improved version of original CLAM. This improvoed version has more practical features:
π‘ A quick overview of what convenience this repo could provide for you:
π This repo is developed from PseMix, previously. Now it has been moved out as an individual project for maintaining convenience.
On updating. Stay tuned!
Feel free to post your issue in this repo if you encounter any problems.
π©βπ» Here show you how to use this repo:
π Some notes:
CONCH
in patch feature extraction (S04)CTransPath
and PLIP
are good alternatives (both are free for use). Their usage is provided in tools/scripts.truncated ResNet50
and ResNet18 w/ SimCL
are NOT recommended in patch feature extraction. We thank CLAM team for contributing such an efficient and easy-to-use tool for WSI preprocessing, and TCGA team for making WSI data publicly-available to facilitate research.
If this project helps you more or less, please cite it via
@article{liu10385148,
author={Liu, Pei and Ji, Luping and Zhang, Xinyu and Ye, Feng},
journal={IEEE Transactions on Medical Imaging},
title={Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification},
year={2024},
volume={43},
number={5},
pages={1841-1852},
doi={10.1109/TMI.2024.3351213}
}
In addition, if you paper use TCGA data and CLAM tools, please also cite them via
@article{lu2021data,
title={Data-efficient and weakly supervised computational pathology on whole-slide images},
author={Lu, Ming Y and Williamson, Drew FK and Chen, Tiffany Y and Chen, Richard J and Barbieri, Matteo and Mahmood, Faisal},
journal={Nature biomedical engineering},
volume={5},
number={6},
pages={555--570},
year={2021},
publisher={Nature Publishing Group UK London}
}
@article{kandoth2013mutational,
title={Mutational landscape and significance across 12 major cancer types},
author={Kandoth, Cyriac and McLellan, Michael D and Vandin, Fabio and Ye, Kai and Niu, Beifang and Lu, Charles and Xie, Mingchao and Zhang, Qunyuan and McMichael, Joshua F and Wyczalkowski, Matthew A and others},
journal={Nature},
volume={502},
number={7471},
pages={333--339},
year={2013},
publisher={Nature Publishing Group UK London}
}