Transformer based deep learning denoising of single and multi-delay 3D Arterial Spin Labeling.

Qinyang Shou Chenyang Zhao Xingfeng Shao Kay Jann Karl G Helmer Hanzhang Lu Danny J J Wang

Published in: medRxiv : the preprint server for health sciences (2023)

Swin Transformer DL models provided better performance than CNN methods for denoising both single and multi-delay 3D ASL data. The proposed model offers flexibility to improve image quality and/or reduce scan time for 3D ASL to facilitate its clinical use.

Keyphrases

convolutional neural network
image quality
deep learning
computed tomography
cerebral blood flow
dual energy
electronic health record
room temperature
big data
single molecule
artificial intelligence
magnetic resonance imaging
machine learning
magnetic resonance