a b/README.md 

  1
  
# DirectionalFeature





  
  

  2
  





  
  

  3
  
This repository contains the code of the following paper "**Learning Directional Feature Maps for Cardiac MRI Segmentation (published in MICCAI2020)**", https://arxiv.org/abs/2007.11349





  
  

  4
  





  
  

  5
  
![](./pipeline.png)





  
  

  6
  
## Citation





  
  

  7
  





  
  

  8
  
Please cite the related works in your publications if it helps your research:





  
  

  9
  





  
  

  10
  
```





  
  

  11
  
@inproceedings{cheng2020learning,





  
  

  12
  
  title={Learning directional feature maps for cardiac mri segmentation},





  
  

  13
  
  author={Cheng, Feng and Chen, Cheng and Wang, Yukang and Shi, Heshui and Cao, Yukun and Tu, Dandan and Zhang, Changzheng and Xu, Yongchao},





  
  

  14
  
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},





  
  

  15
  
  pages={108--117},





  
  

  16
  
  year={2020},





  
  

  17
  
  organization={Springer}





  
  

  18
  
}





  
  

  19
  





  
  

  20
  
```





  
  

  21
  
## Usage





  
  

  22
  





  
  

  23
  
### ACDC Data Preparation





  
  

  24
  
1. Register and download ACDC-2017 dataset from https://www.creatis.insa-lyon.fr/Challenge/acdc/index.html





  
  

  25
  
2. Create a folder outside the project with name **ACDC_DataSet** and copy the dataset.





  
  

  26
  
3. From the project folder open file acdc_data_preparation.py.





  
  

  27
  
4. In the file, set the path to ACDC training dataset is pointed as: ```complete_data_path = '../../ACDC_DataSet/training' ```.





  
  

  28
  
5. Run the script acdc_data_preparation.py.





  
  

  29
  
6. The processed data for training is generated outside the project folder named *processed_acdc_dataset*.





  
  

  30
  
7. Run the ./libs/datastes/gen_acdcjson.py to generate the data list for ACDC training and validation.





  
  

  31
  





  
  

  32
  
### Training





  
  

  33
  
```





  
  

  34
  
cd ./tools





  
  

  35
  
python -m torch.distributed.launch --nproc_per_node 4 --master_port $RANDOM train.py --batch_size 12 --mgpus 0,1,2,3 --output_dir logs/... --train_with_eval





  
  

  36
  
```