Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition.

Gerald BonardelAxel DupontPierre DecazesMathieu QueneauRomain ModzelewskiJeremy CoulotNicolas Le CalvezSébastien Hapdey

Published in: EJNMMI physics (2022)

Based on our results, SubtlePET is adapted in clinical practice for half-time or half-dose acquisitions based on European recommended injected dose of 3 MBq/kg without diagnostic confidence loss.

Keyphrases

deep learning
convolutional neural network
clinical practice
pet ct
positron emission tomography
artificial intelligence
pet imaging
machine learning
computed tomography
loop mediated isothermal amplification
label free
real time pcr
magnetic resonance
optical coherence tomography
dual energy
contrast enhanced