Skip to content

The implementation for automatically predicting dose distribution map via beam-wise dose composition learning (BDCL) method.

Notifications You must be signed in to change notification settings

TL9792/BDCLDosePrediction

Repository files navigation

BDCLDosePrediction

The implementation of the paper "Beam-wise Dose Composition Learning for Head and Neck Cancer Dose Prediction in Radiotherapy" in Pytorch.

Performance

  • The comparison result of dose distribution map with state-of-the-art methods.

  • The quantitative result in terms of two official metrics from the AAMP OpenKBP-2020 Challenge, i.e., Dose score and DVH score. Our method achieves superior performance compared with other state-of-the-art methods.
  • The reproduction results may have certain deviations due to different GPUs used.
Dose score DVH score
2.066±0.900 0.977±1.091

Citation

@article{teng2024beam,
  title={Beam-wise dose composition learning for head and neck cancer dose prediction in radiotherapy},
  author={Teng, Lin and Wang, Bin and Xu, Xuanang and Zhang, Jiadong and Mei, Lanzhuju and Feng, Qianjin and Shen, Dinggang},
  journal={Medical Image Analysis},
  volume={92},
  pages={103045},
  year={2024},
  publisher={Elsevier}
}

About

The implementation for automatically predicting dose distribution map via beam-wise dose composition learning (BDCL) method.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages