Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies

Abstract Deep learning (DL) strategies applied to magnetic resonance (MR) images in positron emission tomography (PET)/MR can provide synthetic attenuation correction (AC) maps, and consequently PET images, more accurate than segmentation or atlas-registration strategies. As first objective, we aim...
Ausführliche Beschreibung

Abstract Deep learning (DL) strategies applied to magnetic resonance (MR) images in positron emission tomography (PET)/MR can provide synthetic attenuation correction (AC) maps, and consequently PET images, more accurate than segmentation or atlas-registration strategies. As first objective, we aim to investigate the best MR image to be used and the best point of the AC pipeline to insert the synthetic map in. Sixteen patients underwent a 18F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) and a PET/MR brain study in the same day. PET/CT images were reconstructed with attenuation maps obtained: (1) from CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with a 2D UNet trained on MR image/attenuation map pairs. As for MR, T1-weighted and Zero Time Echo (ZTE) images were considered; as for attenuation maps, CTs and 511 keV low-resolution attenuation maps were assessed. As second objective, we assessed the ability of DL strategies to provide proper AC maps in presence of cranial anatomy alterations due to surgery. Three 11C-methionine (METH) PET/MR studies were considered. PET images were reconstructed with attenuation maps obtained: (1) from diagnostic coregistered CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with 2D UNets trained on the sixteen FDG anatomically normal patients. Only UNets taking ZTE images in input were considered. FDG and METH PET images were quantitatively evaluated. As for anatomically normal FDG patients, UNet AC models generally provide an uptake estimate with lower bias than atlas-based or segmentation-based methods. The intersubject average bias on images corrected with UNet AC maps is always smaller than 1.5%, except for AC maps generated on too coarse grids. The intersubject bias variability is the lowest (always lower than 2%) for UNet AC maps coming from ZTE images, larger for other methods. UNet models working on MR ZTE images and generating synthetic CT or 511 keV low-resolution attenuation maps therefore provide the best results in terms of both accuracy and variability. As for METH anatomically altered patients, DL properly reconstructs anatomical alterations. Quantitative results on PET images confirm those found on anatomically normal FDG patients. Ausführliche Beschreibung

Autor*in:	Presotto, Luca [verfasserIn] Bettinardi, Valentino Bagnalasta, Matteo Scifo, Paola Savi, Annarita Vanoli, Emilia Giovanna Fallanca, Federico Picchio, Maria Perani, Daniela Gianolli, Luigi De Bernardi, Elisabetta

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	PET/MR Brain attenuation correction Deep learning UNet

Anmerkung:	© The Author(s) 2022

Übergeordnetes Werk:	Enthalten in: Journal of digital imaging - Berlin : Springer, 1988, 35(2022), 3 vom: 28. Jan., Seite 432-445
Übergeordnetes Werk:	volume:35 ; year:2022 ; number:3 ; day:28 ; month:01 ; pages:432-445

Links:	Volltext

DOI / URN:	10.1007/s10278-021-00551-1

Katalog-ID:	SPR047148268