AUTHOR=Ladefoged Claes Nøhr , Henriksen Otto Mølby , Mathiasen René , Schmiegelow Kjeld , Andersen Flemming Littrup , Højgaard Liselotte , Borgwardt Lise , Law Ian , Marner Lisbeth 

TITLE=Automatic detection and delineation of pediatric gliomas on combined [18F]FET PET and MRI

JOURNAL=Frontiers in Nuclear Medicine

VOLUME=Volume 2 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/nuclear-medicine/articles/10.3389/fnume.2022.960820

DOI=10.3389/fnume.2022.960820

ISSN=2673-8880

ABSTRACT=Brain and central nervous system (CNS) tumors are the second most common cancer type in children and adolescents. Positron emission tomography (PET) imaging with radiolabeled amino acids visualizes the amino acid uptake in brain tumor cells compared to healthy brain tissue, which provides additional information over magnetic resonance imaging (MRI) for differential diagnosis, treatment planning, and the differentiation of tumor relapse from treatment-related changes. However, tumor delineation is a time-consuming task subject to inter-rater variability. We propose a deep learning method for automatic delineation of [18F]FET PET pediatric CNS tumors. 

A total of 109 [18F]FET PET and MRI scans were included from 66 pediatric patients with manually delineated reference. We trained an artificial neural network (ANN) for automatic delineation and compared its performance against the manual reference on delineation accuracy and subsequent clinical metric accuracy. For clinical metrics we extracted the biological tumor volume (BTV) and tumor-to-background mean and max (TBRmean, TBRmax).

The ANN produced high tumor overlap (median dice-similarity coefficient 0.93). The clinical metrics extracted with the manual reference and the ANN were highly correlated (r≥0.99). The spatial location of TBRmax was identical in almost all cases (96%). The ANN and the manual reference produced similar changes of the clinical metrics between baseline and follow-up scans.

The proposed ANN achieved high concordance with the manual reference and may be an important tool for decision aid, to limit inter-reader variance, improve longitudinal evaluation in clinical routine, and for future multicenter studies of pediatric CNS tumors.