Open access
SynthPET: A 3D generative AI approach for FDG‐PET image synthesis from T1‐weighted MRI and ASL CBF in Alzheimer's disease
Xavier Beltran-Urbano
Katie R. Jobson
I. Nasrallah
Ajay Kumar
Manuel Taso
Sandhitsu R. Das
Christopher A. Brown
Si-Pei Li
Long Xie
Corey T. McMillan
Paul A. Yushkevich
D. Wolk
G. Zaharchuk
S. Dolui
John A. Detre
Medicine
Abstract
Fluorodeoxyglucose (FDG) positron emission tomography (PET) is widely used for detecting metabolic changes associated with neurodegeneration in Alzheimer's disease (AD) and other dementias but is costly and involves ionizing radiation. Here we developed SynthPET, a multimodal deep learning framework that synthesizes FDG PET images from T1‐weighted (T1w) and arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) data.