Deep-learning for automated detection of MSU deposits on DECT: evaluating impact on efficiency and reader confidence.

Shahriar FaghaniSoham PatelNicholas G RhodesGarret M PowellFrancis I BaffourMana MoassefiKatrina N GlazebrookBradley J EricksonChristin A Tiegs-Heiden

Published in: Frontiers in radiology (2024)

The implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.

Keyphrases

deep learning
healthcare
primary care
working memory
convolutional neural network
single cell
case control