StyCona

This repo is the PyTorch implementation for the paper:

"Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentation"

Usage

0. Requirements

The code is developed using Python 3.8 with PyTorch 1.11.0. All experiments in our paper were conducted on a single NVIDIA A40 GPU with 48G GPU memory.

Install the main packages:

pytorch == 1.11.0
torchvision == 0.12.0

1. Data Preparation

1.1. Download data

The dataset can be downloaded in following links:

• MSCMR Dataset - Link
• Fundus Dataset - Link

PS: Please cite the papers of original dataset when using the data in your publications.

1.2. Split Dataset

Following the list files (within the "data" folders) to split the datasets

2. Training

python train_stycona.py

3. Evaluation

python eval.py

Citation

If you find this project useful, please consider citing:

@article{shen2025style,
  title={Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentation},
  author={Shen, Zhiqiang and Cao, Peng and Yang, Jinzhu and Zaiane, Osmar R and Chen, Zhaolin},
  journal={arXiv preprint arXiv:2502.20619},
  year={2025}
}

Contact

If you have any questions or suggestions, please feel free to contact me (xxszqyy@gmail.com).

Acknowledgements

• TriD

Thanks to the authors for providing the processed data.