Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network

Shiri Lord, Isaac; Arabi, Hossein; Geramifar, Parham; Hajianfar, Ghasem; Ghafarian, Pardis; Rahmim, Arman; Ay, Mohammad Reza; Zaidi, Habib

doi:10.1007/s00259-020-04852-5

Scientific article

English

Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network

ContributorsShiri Lord, Isaac

; Arabi, Hossein; Geramifar, Parham; Hajianfar, Ghasem; Ghafarian, Pardis; Rahmim, Arman; Ay, Mohammad Reza; Zaidi, Habib

Published inEuropean Journal of Nuclear Medicine and Molecular Imaging, vol. 47, no. 11, p. 2533-2548

Publication date2020

Abstract

We demonstrate the feasibility of direct generation of attenuation and scatter-corrected images from uncorrected images (PET-nonASC) using deep residual networks in whole-body 18F-FDG PET imaging.

Keywords

Attenuation correction
Deep learning
PET/CT
Scatter correction
Whole-body

NoteMettre à jour le pdf:https://www.hug.ch/sites/interhug/files/structures/pinlab/documents/ejnmmi2020.pdf

Affiliation entities

Research groups

Imagerie Médicale (TEP et TEMP) (542)

Funding

Swiss National Science Foundation - Towards patient-specific hybrid whole-body PET parametric imaging [176052]
Autre - Swiss Cancer Research Foundation Grant KFS-3855-02-2016

Citation (ISO format)

SHIRI LORD, Isaac et al. Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network. In: European Journal of Nuclear Medicine and Molecular Imaging, 2020, vol. 47, n° 11, p. 2533–2548. doi: 10.1007/s00259-020-04852-5