Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners.

Hasan SariMohammadreza TeimoorisichaniClemens MingelsIan AlbertsVladimir PaninDeepak BharkhadaSong XueGeorge PrenosilKuangyu ShiMaurizio ContiAxel Rominger

Published in: European journal of nuclear medicine and molecular imaging (2022)

We describe a deep learning-based method to accurately generate µ-maps from PET emission data and LSO background radiation, enabling CT-free attenuation and scatter correction in LAFOV PET scanners.

Keyphrases

deep learning
positron emission tomography
computed tomography
pet ct
pet imaging
artificial intelligence
convolutional neural network
machine learning
big data
radiation induced
magnetic resonance imaging
electronic health record
high resolution
radiation therapy
mass spectrometry