Multicenter validation of synthetic FLAIR as a substitute for FLAIR sequence in acute ischemic stroke.

Guillaume HamonLaurence LegrandGhazi HmeydiaGuillaume TurcWagih Ben HassenSylvain CharronClement DebackerOlivier NaggaraBertrand ThirionBailiang ChenBertrand LapergueCatherine OppenheimJoseph Benzakoun

Published in: European stroke journal (2024)

A deep-learning-based FLAIR fine-tuned on multicenter data can provide comparable performances to real FLAIR for early AIS identification. This approach may help reducing MR protocol duration and motion artifacts.

Keyphrases

deep learning
randomized controlled trial
cross sectional
double blind
air pollution
magnetic resonance
electronic health record
big data
clinical trial
convolutional neural network
mass spectrometry
high resolution
high speed
amino acid
bioinformatics analysis