Attenuation correction and truncation completion for breast PET/MR imaging using deep learning.

Xue LiJacob JohnsonRoberta M StrigelLeah C Henze BancroftSamuel A HurleyIman Zare EstakhrajiManoj KumarAmy M FowlerAlan B McMillan

Published in: Physics in medicine and biology (2024)

A 3D U-Net with MSE or perceptual loss model can be implemented into a reconstruction workflow, and the derived sCT images allow successful truncation completion and attenuation correction for breast PET/MR images.

Keyphrases

deep learning
convolutional neural network
pet ct
positron emission tomography
computed tomography
contrast enhanced
artificial intelligence
pet imaging
machine learning
working memory