/Branch-aware-centerline-extraction

Branch-aware-centerline-extraction

Code for our paper "Branch-Aware Double DQN for Centerline Extraction in Coronary CT Angiography".

  • Propose the Double Deep Q-network based coronary artery tracing method in CCTA for the first time.
  • Extracts the entire coronary tree with lower time-cost than other state-of-the-art methods, uses only one seed and terminates tracing automatically.

Requirements

Python 3.6.2

Pytorch 1.7

CUDA 11.2

Coordinate transformation

python w_coor2v_coor.py

Training

python ddqn.py
python detector.py

Inference

python app.py

Cite

Please consider citing this project in your publications if it helps your research. The following is a BibTeX reference. The BibTeX entry requires the url LaTeX package.

@inproceedings{zhang2020branch,
  title={Branch-aware double DQN for centerline extraction in coronary CT angiography},
  author={Zhang, Yuyang and Luo, Gongning and Wang, Wei and Wang, Kuanquan},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={35--44},
  year={2020},
  organization={Springer}
  }