Precision of CT-derived alveolar recruitment assessed by human observers and a machine learning algorithm in moderate and severe ARDS.
Ludmilla PenarrubiaAude VerstraeteMaciej OrkiszEduardo DavilaLoic BousselHodane YonisMehdi MezidiFrancois DhelftWilliam DanjouAlwin BazzaniFlorian SigaudSam BayatNicolas TerziMehdi GirardLaurent BitkerEmmanuel RouxJean-Christophe RichardPublished in: Intensive care medicine experimental (2023)
). Human-machine and human-human inter-observer measurement errors with CT are of similar magnitude, suggesting that machine learning segmentation algorithms are credible alternative to humans for quantifying alveolar recruitment on CT.