Evaluation of a commercial deformable image registration algorithm for dual-energy CT processing.

Jessie Y HuangMichael J LawlessCharles K MatrosicLianna D Di MasoJessica R Miller

Published in: Journal of applied clinical medical physics (2020)

This work represents the first methodology for DECT image registration QA using commercial software. Our data support the clinical use of the Syngo algorithm for abdominal sites with limited motion (i.e., pancreas and liver). However, dual-energy images generated with this algorithm should be used with caution for quantitative measurements in areas with sliding motion.

Keyphrases

dual energy
deep learning
computed tomography
image quality
machine learning
convolutional neural network
artificial intelligence
contrast enhanced
big data
positron emission tomography
high speed
magnetic resonance imaging
electronic health record