A deep learning-based whole-body solution for PET/MRI attenuation correction.

Sahar AhangariAnders Beck OlinMarianne Kinggård FederspielBjoern JakobyThomas Lund AndersenAdam Espe HansenBarbara Malene FischerFlemming Littrup Andersen

Published in: EJNMMI physics (2022)

Experimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance.

Keyphrases

pet ct
computed tomography
positron emission tomography
deep learning
contrast enhanced
magnetic resonance imaging
pet imaging
high resolution
diffusion weighted imaging
convolutional neural network