Quantitative MRI outcome measures in CMT1A using automated lower limb muscle segmentation.

Luke Francis O'Donnell Menelaos PipisJohn S ThorntonBaris KanberStephen WastlingAmy McDowellNick ZafeiropoulosMatilde LauraMariola SkorupinskaChristopher J RecordCarolynne M DohertyDavid N HerrmannHenrik ZetterbergAmanda J HeslegraveRhiannon LabanAlexander Martin RossorJasper M MorrowMary M Reilly

Published in: Journal of neurology, neurosurgery, and psychiatry (2023)

Using automated image segmentation for the first time in a longitudinal study in CMT, we have demonstrated that calf FF has similar responsiveness to previously published data, is efficient with minimal time needed for QC checks and is accurate with minimal corrections needed.

Keyphrases

deep learning
lower limb
convolutional neural network
artificial intelligence
high resolution
machine learning
big data
magnetic resonance imaging
contrast enhanced
skeletal muscle
electronic health record
randomized controlled trial
systematic review