Evaluation of a novel deep learning-based classifier for perifissural nodules.

Daiwei HanMarjolein A HeuvelmansMieneke RookMonique DorriusLuutsen van HoutenNoah Waterfield PriceLyndsey C PickupPetr NovotnyMatthijs OudkerkJerome DeclerckFergus GleesonPeter van OoijenRozemarijn Vliegenthart

Published in: European radiology (2020)

• Agreement between the PFN-CNN and radiologically trained readers is within the range of inter-reader agreement. • The CNN model for the classification of typical PFNs achieved an AUC of 95.8% (95% CI 93.3-98.4) with 95.6% (95% CI 84.9-99.5) sensitivity and 88.1% (95% CI 81.8-92.8) specificity compared to the consensus of three readers.

Keyphrases

deep learning
convolutional neural network
machine learning
artificial intelligence
resistance training
clinical practice
body composition
high intensity