This is the official pytorch implementation of MDMILTargeting tumor heterogeneity: multiplex-detection-based multiple instance learning for whole slide image classification (Bioinformatics 2023).
Please install pytorch version >=1.2
Please download the official TCGA datasets of BRCA, BLCA, GBMLGG, LUAD, and UCEC. For more details of pre-processing, please refer to CLAM.
before training and testing, please update configs. Generally, we train the model with one 12 GB memory GPU. The output details in terms of loss, accuracy, and AUC will be stored in the logs folder.
python train.py
If you find this code useful for your research, please cite our paper
@article{wang2023targeting,
title={Targeting tumor heterogeneity: multiplex-detection-based multiple instance learning for whole slide image classification},
author={Wang, Zhikang and Bi, Yue and Pan, Tong and Wang, Xiaoyu and Bain, Chris and Bassed, Richard and Imoto, Seiya and Yao, Jianhua and Daly, Roger J and Song, Jiangning},
journal={Bioinformatics},
volume={39},
number={3},
pages={btad114},
year={2023},
publisher={Oxford University Press}
}
If you have any question, please feel free to contact us. E-mail: [email protected]