CoPAS: learning Co-Plane Attention across MRI Sequences for diagnosing twelve types of knee abnormalities: A multi-center retrospective study
This is the official repository of
Learning co-plane attention across MRI sequences for diagnosing twelve types of knee abnormalities
by Zelin Qiu, Zhuoyao Xie, Yanwen Li, Huangjing Lin, Qiang Ye, Menghong Wang, Shisi Li, Yinghua Zhao, and Hao Chen
The code is based on Python 3.8.0
- Download the repository
git clone https://github.com/zqiuak/CoPAS- Go to the
mainfolder and install requested libarary.
cd main
pip install -r requirements.txtTypically, it will take few minutes to complete the installation.
- Fill the data path in
PathDict.py, the sample is given in the file. - Change parameters in
Args.pyto fit your data.
python run.pypython run.py --test --weight_path PATH_TO_WEIGHT--epochs: Maximum number of epoches in training.
--batch_size: Batch size.
--lr: Initial learning rate.
--gpu: GPU card number.
--augment: bool, use augmentation or not.
We have prepared 50 sample data for test, click here to download.
If you have any special requests, please send a email to Zelin Qiu (zqiuak@connect.ust.hk).
This project is covered under the Apache 2.0 License.
If you find this work useful, please cite our paper:
@article{qiu2024learning,
title={Learning co-plane attention across MRI sequences for diagnosing twelve types of knee abnormalities},
author={Qiu, Zelin and Xie, Zhuoyao and Lin, Huangjing and Li, Yanwen and Ye, Qiang and Wang, Menghong and Li, Shisi and Zhao, Yinghua and Chen, Hao},
journal={Nature Communications},
volume={15},
number={1},
pages={7637},
year={2024},
publisher={Nature Publishing Group UK London}
}