A convolutional neural network for fully automated blood SUV determination to facilitate SUR computation in oncological FDG-PET.

Pavel NikulinFrank HofheinzJens MausYimin LiRebecca BütofCatharina LangeChristian FurthSebastian ZschaeckMichael C KreisslJörg KotzerkeJörg van den Hoff

Published in: European journal of nuclear medicine and molecular imaging (2020)

CNNs are capable of performing robust automatic image-based BSUV determination. Integrating automatic BSUV derivation into PET data processing workflows will significantly facilitate SUR computation without increasing the workload in the clinical setting.

Keyphrases

deep learning
convolutional neural network
pet ct
positron emission tomography
pet imaging
artificial intelligence
computed tomography
solid phase extraction
machine learning
molecularly imprinted
big data
electronic health record
robot assisted
mass spectrometry
minimally invasive