Code for "CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy"

CHeart, a novel conditional generative model for 4D cardiac anatomy. By leveraging both imaging and non-imaging data, the model is able to generate realistic and dynamic anatomical sequences for the heart, given personalised conditions such as demographic and anthropometric factors.

train_GenCVAE_Seq.py

val_GenCVAE_Seq.py

If you make use of the code, or if you found the code useful, please cite the paper in any resulting publications.

@ARTICLE{QiaoCHeart2023,
  author={Qiao, Mengyun and Wang, Shuo and Qiu, Huaqi and De Marvao, Antonio and O’Regan, Declan P. and Rueckert, Daniel and Bai, Wenjia},
  journal={IEEE Transactions on Medical Imaging}, 
  title={CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy}, 
  year={2023},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TMI.2023.3331982}}