PyTorch implementation of the paper "Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series". This paper is accepted by the 8th International Conference on Image Formation in X-Ray Computed Tomography, Bamberg, Germany.

The code is developed using Python 3.11 and PyTorch 2.0.0. Installation guide can be found in pyronn.

Low-dose CT data can be found here.

python main.py 

Please cite the following paper and star this project if you use this repository in your research. Thank you!

@article{sun2024data,
  title={Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series},
  author={Sun, Yipeng and Schneider, Linda-Sophie and Fan, Fuxin and Thies, Mareike and Gu, Mingxuan and Mei, Siyuan and Zhou, Yuzhong and Bayer, Siming and Maier, Andreas},
  journal={arXiv preprint arXiv:2401.16039},
  year={2024}
}