Impact of segmentation and discretization on radiomic features in 68Ga-DOTA-TOC PET/CT images of neuroendocrine tumor.

Virginia LiberiniBruno De SantiOsvaldo RampadoElena GallioBeatrice DionisiFrancesco CeciGiulia PolverariPhilippe ThuillierFilippo MolinariDésirée Deandreis

Published in: EJNMMI physics (2021)

RFs robustness to manual segmentation resulted higher in NET 68Ga-DOTA-TOC images compared to 18F-FDG PET/CT images. Forty percent SUVmax thresholds yield superior RFs stability among operators, however leading to a possible loss of biological information. SAEB segmentation appears to be an optimal alternative to manual segmentation, but further validations are needed. Finally, discretization settings highly impacted on RFs robustness and should always be stated.

Keyphrases

pet ct
convolutional neural network
deep learning
positron emission tomography
machine learning
healthcare