DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI

Official code of the paper "DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI" (10.1109/ACCESS.2024.3427674)

The pre-print of this work is available on ArXiv: https://arxiv.org/abs/2202.05355 and the published version is available on IEEE Xplore: https://doi.org/10.1109/ACCESS.2024.3427674

Initial version of this work was presented as an abstract at ESMRMB 2021 (Abstract available on RG: https://www.researchgate.net/publication/354888919_DDoS_Dynamic_Dual-Channel_U-Net_for_Improving_Deep_Learning_Based_Super-Resolution_of_Abdominal_Dynamic_MRI), and a "spin-off" of this work for radial MRI has been accepted as an abstract for ISMRM-ESMRMB 2022 (Abstract available on RG: https://www.researchgate.net/publication/358357562_Motion-robust_dynamic_abdominal_MRI_using_k-t_GRASP_and_dynamic_dual-channel_training_of_super-resolution_U-Net_DDoS-UNet)

The name "DDoS" is inspired by the name of the cyber-attack: distributed denial-of-service attack (DDoS attack), as this project tries to "attack" the problem of super-resolution of dynamic MRI from two aspects: spatial super-resolution and temporal prior incorporation.

Credits

If you like this repository, please click on Star!

If you use this approach in your research or use codes from this repository, please cite the following in your publications:

S. Chatterjee et al., "DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI," in IEEE Access, doi: 10.1109/ACCESS.2024.3427674

BibTeX entry:

@ARTICLE{10597433,
  author={Chatterjee, Soumick and Sarasaen, Chompunuch and Rose, Georg and Nürnberger, Andreas and Speck, Oliver},
  journal={IEEE Access}, 
  title={DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI}, 
  year={2024},
  volume={},
  number={},
  pages={1-1},
  keywords={Magnetic resonance imaging;Superresolution;Spatial resolution;Three-dimensional displays;Training;Chaos;Image reconstruction;Deep learning;MRI Reconstruction;Undersampled MRI;Dynamic MRI;Super-Resolution;Dual-channel Training;Deep Learning},
  doi={10.1109/ACCESS.2024.3427674}}