/mamba_dose

This is the codebase for MD-Dose: A Diffusion Model based on the Mamba for Radiotherapy Dose Prediction

Primary LanguagePython

MD-Dose

This is the codebase for [MD-Dose: A Diffusion Model based on the Mamba for Radiotherapy Dose Prediction](https://arxiv.org/abs/2403.08479).

Envs. for Pretraining

  • Python 3.10.13

    • conda create -n your_env_name python=3.10.13

  • torch 2.1.1 + cu118

    • pip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 --index-url https://download.pytorch.org/whl/cu118

  • Requirements: vim_requirements.txt

    • pip install -r vim/vim_requirements.txt

  • Install causal_conv1d and mamba

    • pip install -e causal_conv1d
    • pip install -e mamba

Train Your MD-Dose

python train.py(Training without a structural encoder)

python train_struc.py(Training with a structural encoder)

Acknowledgement ❤️

This project is based on Vim (paper, code), Causal-Conv1d (code). Thanks for their wonderful works.

Citation

If you find MD-Dose is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.

@misc{fu2024mddose,
      title={MD-Dose: A Diffusion Model based on the Mamba for Radiotherapy Dose Prediction}, 
      author={Linjie Fu and Xia Li and Xiuding Cai and Yingkai Wang and Xueyao Wang and Yali Shen and Yu Yao},
      year={2024},
      eprint={2403.08479},
      archivePrefix={arXiv},
      primaryClass={eess.IV}
}