Deep learning-based time-of-flight (ToF) image enhancement of non-ToF PET scans.

Abolfazl MehranianScott D WollenweberMatthew D WalkerKevin M BradleyPatrick A FieldingMartin HuellnerFotis KotasidisKuan-Hao SuRobert JohnsenFloris P JansenDaniel R McGowan

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

Deep learning-based image enhancement models may provide converged ToF-equivalent image quality without ToF reconstruction. In clinical scoring DL-ToF-enhanced non-ToF images (medium and high) on average scored as high as, or higher than, ToF images. The model is generalisable and hence, could be applied to non-ToF images from BGO-based PET/CT scanners.

Keyphrases

deep learning
mass spectrometry
ms ms
pet ct
convolutional neural network
computed tomography
artificial intelligence
image quality
machine learning
positron emission tomography
optical coherence tomography