PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Corda-D'Incan, G.* ; Schnabel, J.A. ; Hammers, A.* ; Reader, A.J.*

Single-modality supervised joint PET-MR image reconstruction.

IEEE TRPMS 7, 742-754 (2023)
Verlagsversion DOI
Free by publisher
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.
We present a new approach for deep learned joint PET-MR image reconstruction inspired by conventional synergistic methods using a joint regularizer. The maximum a posteriori expectation-maximization algorithm for PET and the Landweber algorithm for MR are unrolled and interconnected through a deep learned joint regularization step. The parameters of the joint U-Net regularizer and the respective regularization strengths are learned and shared across all the iterations. Along with introducing this framework, we propose an investigation of the impact of the loss function selection on network performance. We explored how the network performs when trained with a single or a joint-modality loss. Finally, we explored under which settings a joint reconstruction was beneficial for MR reconstruction by using various undersampling factors. The results obtained on 2-D simulated data show that the joint networks outperform conventional synergistic methods and independent deep learned reconstruction methods. For PET, the network trained with only a PET loss achieves a better global reconstruction accuracy than the version trained with a weighted sum of PET and MR loss terms. More importantly, the former further improves the reconstruction of PET-specific features where MR-guided methods show their limit. Therefore, using a single-modality loss to supervise the training while still reconstructing the two modalities in parallel leads to better reconstructions and improved modality-unique lesion recovery in our proposed framework. For MR, while the same effect is observed, joint reconstruction gains only occur in the presence of highly undersampled data. Single-modality loss joint reconstruction results are also demonstrated on 3-D clinical PET-MR datasets.
Impact Factor
Scopus SNIP
Web of Science
Times Cited
Altmetric
4.400
0.000
1
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Deep Learning ; Joint Pet-mr Reconstruction ; Magnetic Resonance (mr) Reconstruction ; Positron Emission Tomography (pet) Reconstruction; Neural-networks; Algorithm
Sprache englisch
Veröffentlichungsjahr 2023
HGF-Berichtsjahr 2023
ISSN (print) / ISBN 2469-7311
e-ISSN 2469-7311
Zeitschrift IEEE transactions on radiation and plasma medical sciences
Quellenangaben Band: 7, Heft: 7, Seiten: 742-754 Artikelnummer: , Supplement: ,
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Verlagsort New York, NY
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-507100-001
Förderungen King's College London
National Institute for Health Research (NIHR) Biomedical Research Centre at Guy's, St Thomas' NHS Foundation Trust
Wellcome/EPSRC Centre for Medical Engineering
Siemens Healthineers, Erlangen, Germany
EPSRC Centre for Doctoral Training in Smart Medical Imaging
DOI 10.1109/TRPMS.2023.3283786
WOS ID 001060605700009
Scopus ID 85161485190
Erfassungsdatum 2023-12-08
[➜Korrektur melden]