Accelerate Pulmonary Hyperpolarized Gas MRI with Multi-Task Learning

Zimeng Li, Sa Xiao, Cheng Wang, Chaohui Ye, Xin ZhouProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

Hyperpolarized gas MRI is a non-invasive and non-radiation imaging modality that can provide lung structure and function information. However, the problem of long imaging time limits its clinical application. Deep learning-based methods have shown great potential to accelerate MRI. In this work, we proposed a multi-task network to perform pulmonary hyperpolarized gas MRI reconstruction and lung region segmentation simultaneously, which allows sharing representations between two tasks. The results show that the proposed multi-task network has better reconstruction performance, stronger robustness and fewer model parameters than the comparison method.
BibTeX
@inproceedings{li2023accelerate,
  author = {Zimeng Li and Sa Xiao and Cheng Wang and Chaohui Ye and Xin Zhou},
  title = {{Accelerate Pulmonary Hyperpolarized Gas MRI with Multi-Task Learning}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/4307},
}

Loading related content...

Figure