Scientific article

English

Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging

ContributorsSanaat, Amirhossein

; Shiri Lord, Isaac

; Arabi, Hossein; Mainta, Ismini Charis; Nkoulou, René; Zaidi, Habib

Published inEuropean Journal of Nuclear Medicine and Molecular Imaging, vol. 48, no. 8, p. 2405-2415

Publication date2021

Abstract

Tendency is to moderate the injected activity and/or reduce acquisition time in PET examinations to minimize potential radiation hazards and increase patient comfort. This work aims to assess the performance of regular full-dose (FD) synthesis from fast/low-dose (LD) whole-body (WB) PET images using deep learning techniques.

Keywords

Deep learning
Lesion detectability
Low-dose imaging
PET/CT
Whole-body imaging

Notefichier pdf à jour:https://www.hug.ch/sites/interhug/files/structures/pinlab/documents/ejnmmi2021.pdf

Affiliation entities

Faculté de médecine / Section de médecine clinique / Département de radiologie et informatique médicale

Research groups

Imagerie Médicale (TEP et TEMP) (542)

Funding

Swiss National Science Foundation - Towards patient-specific hybrid whole-body PET parametric imaging [320030_176052]
Autre - the Eurostars programme of the European commission under grant E! 114021 ProVision

Citation (ISO format)

SANAAT, Amirhossein et al. Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging. In: European Journal of Nuclear Medicine and Molecular Imaging, 2021, vol. 48, n° 8, p. 2405–2415. doi: 10.1007/s00259-020-05167-1

Article (Published version)

Appendix

Identifiers

PID : unige:148871
DOI : 10.1007/s00259-020-05167-1
PMID : 33495927

Additional URL for this publicationhttp://link.springer.com/10.1007/s00259-020-05167-1

Journal ISSN1619-7070

332views

300downloads

Creation26/01/2021 11:12:00

First validation26/01/2021 11:12:00

Update16/03/2023 00:01:24

Status update16/03/2023 00:01:23

Last indexation31/10/2024 21:14:45