Generalizability of Deep Learning Models for Caries Detection in Near-Infrared Light Transillumination Images.

Agnes HoltkampKarim ElhennawyJosé E Cejudo Grano de OroJoachim KroisSebastian ParisFalk Schwendicke

Published in: Journal of clinical medicine (2021)

Studies employing in vitro imagery for developing deep learning models should be critically appraised for their generalizability. Applicable deep learning models for assessing NILT imagery should be trained on in vivo data.

Keyphrases

deep learning
convolutional neural network
artificial intelligence
machine learning
big data
optical coherence tomography
loop mediated isothermal amplification
sensitive detection