Noise2Recon: Enabling SNR-robust MRI reconstruction with semi-supervised and self-supervised learning.

Arjun D DesaiBatu M OzturklerChristopher M SandinoRobert BoutinMarc WillisShreyas VasanawalaBrian A HargreavesChristopher RéJohn M PaulyAkshay S Chaudhari

Published in: Magnetic resonance in medicine (2023)

Noise2Recon is a label-efficient reconstruction method that is robust to distribution shifts, such as changes in SNR, acceleration factors, and others, with limited or no fully sampled training data.

Keyphrases

machine learning
air pollution
big data
magnetic resonance imaging
contrast enhanced
electronic health record
artificial intelligence
computed tomography
deep learning
data analysis