• This project was originally developed for our two previous works WORD and WSL4MIS (MICCAI2022, early accept & student travel award). If you use this project in your research, please cite the following works:

    @article{luo2022scribbleseg,
    title={Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision},
    author={Xiangde Luo, Minhao Hu, Wenjun Liao, Shuwei Zhai, Tao Song, Guotai Wang, Shaoting Zhang},
    journal={MICCAI},
    year={2022}}
    
    @article{luo2021word,
    title={{WORD}: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image},
    author={Xiangde Luo, Wenjun Liao, Jianghong Xiao, Tao Song, Xiaofan Zhang, Kang Li, Dimitris N. Metaxas, Guotai Wang, and Shaoting Zhang},
    journal={arXiv preprint arXiv:2111.02403},
    year={2021}}
    
    @misc{wsl4mis2020,
    title={{WSL4MIS}},
    author={Luo, Xiangde},
    howpublished={\url{https://github.com/Luoxd1996/WSL4MIS}},
    year={2021}}
  

• The ACDC dataset with mask annotations can be downloaded from: ACDC.
• The Scribble annotations of ACDC can be downloaded from: Scribble.
• The data processing code in Here the pre-processed ACDC data in Here.
• To simulate the scribble annotation for other datasets, we further provide the simulation code at Here.

Some important required packages include:

• Pytorch version >=0.4.1.
• TensorBoardX
• Python >= 3.6
• Efficientnet-Pytorch pip install efficientnet_pytorch
• Some basic python packages such as Numpy, Scikit-image, SimpleITK, Scipy ......

Follow official guidance to install Pytorch.

1. Clone this project.

git clone https://github.com/Luoxd1996/WSL4MIS
cd WSL4MIS

2. Data pre-processing os used or the processed data.

cd code
python dataloaders/acdc_data_processing.py

3. Train the model

cd code
bash train_wss.sh # train model with scribble or dense annotations.
bash train_ssl.sh  # train model with mix-supervision (mask annotations and without annotation).

4. Test the model

python test_2D_fully.py --sup_type scribble/label --exp ACDC/the trained model fold --model unet
python test_2D_fully_sps.py --sup_type scribble --exp ACDC/the trained model fold --model unet_cct

5. Training curves on the fold1: Note: pCE means partially cross-entropy, TV means total variation, label denotes supervised by mask, scribble represents just supervised by scribbles.

• pCE
• pCE + TV
• pCE + Entropy Minimization
• pCE + GatedCRFLoss
• pCE + Intensity Variance Minimization
• pCE + Random Walker
• pCE + MumfordShah_Loss
• Scribble2Label
• USTM

• The GatedCRFLoss is adapted from GatedCRFLoss for medical image segmentation.
• The codebase is adapted from our previous work SSL4MIS.
• The WORD dataset will be presented at WORD.