Predicting Perfusion Augmentation Using Deep Learning without Vasodilators

Moss Zhao, Ramy Hussein, Michael E. Moseley, Greg ZaharchukProceedings 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

We present a deep learning technique to predict cerebral perfusion after vasodilation challenges. A 3D convolutional neural network (CNN)-based encoder-decoder architecture was constructed to transform ASL perfusion images acquired pre-vasodilation into post-vasodilation images using an improved attention-gated 3D U-Net. Results showed that the prediction and ground truth were not significantly different. This technique will enable a drug-free MR procedure to study the hemodynamic of patients with high risk cerebrovascular diseases.
BibTeX
@inproceedings{zhao2023predicting,
  author = {Moss Zhao and Ramy Hussein and Michael E. Moseley and Greg Zaharchuk},
  title = {{Predicting Perfusion Augmentation Using Deep Learning without Vasodilators}},
  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 = {10.58530/2022/1789},
}

Loading related content...

Figure