by Yunhao Bai, Duowen Chen, Qingli Li, Wei Shen, and Yan Wang.

Official code for "Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation". (CVPR 2023)

This repository is based on PyTorch 1.8.0, CUDA 11.1 and Python 3.6.13. All experiments in our paper were conducted on NVIDIA GeForce RTX 3090 GPU with an identical experimental setting.

2024/3/27

1.Many issues interest in KDE plot, we provide code/KDE_demo.py to show how we draw the KDE distribution.

2.We provide BCP model parameters trained on 20% NIH-Pancreas. 链接: https://pan.baidu.com/s/1kGqRsEF4BX_yChKV3kMNVQ?pwd=hsjb 提取码: hsjb

2023/07

We provide NIH-Pancreas dataset codes code/pancreas, data split (and other information) could be got at CoraNet

We provide code, data_split and models for LA and ACDC dataset.

Data could be got at LA and ACDC.

To train a model,

python ./code/LA_BCP_train.py  #for LA training
python ./code/ACDC_BCP_train.py  #for ACDC training

To test a model,

python ./code/test_LA.py  #for LA testing
python ./code/test_ACDC.py  #for ACDC testing

If you find these projects useful, please consider citing:

@article{DBLP:journals/corr/abs-2305-00673,
  author       = {Yunhao Bai and
                  Duowen Chen and
                  Qingli Li and
                  Wei Shen and
                  Yan Wang},
  title        = {Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation},
  journal      = {CoRR},
  volume       = {abs/2305.00673},
  year         = {2023}
}

Our code is largely based on SS-Net. Thanks for these authors for their valuable work, hope our work can also contribute to related research.

If you have any questions, welcome contact me at '[email protected]'