Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  A unified model for reconstruction and R2*mapping of accelerated 7T data using the quantitative recurrent inference machine

Zhang, C., Karkalousos, D., Bazin, P.-L., Coolen, B. F., Vrenken, H., Sonke, J.-J., et al. (2022). A unified model for reconstruction and R2*mapping of accelerated 7T data using the quantitative recurrent inference machine. NeuroImage, 264: 119680. doi:10.1016/j.neuroimage.2022.119680.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Zeitschriftenartikel

Dateien

einblenden: Dateien
ausblenden: Dateien
:
Zhang_Karkalousos_2022.pdf (Verlagsversion), 5MB
Name:
Zhang_Karkalousos_2022.pdf
Beschreibung:
-
OA-Status:
Gold
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Zhang, Chaoping1, 2, 3, Autor
Karkalousos, Dimitrios1, 2, Autor
Bazin, Pierre-Louis4, 5, Autor                 
Coolen, Bram F.1, Autor
Vrenken, Hugo2, 6, Autor
Sonke, Jan-Jakob3, Autor
Forstmann, Birte U.4, Autor
Poot, Dirk H. J.7, Autor
Caan, Matthan W. A.1, 2, 8, Autor
Affiliations:
1Department of Biomedical Engineering and Physics, VU University Medical Center, Amsterdam, the Netherlands, ou_persistent22              
2Amsterdam Neuroscience - Brain Imaging, the Netherlands, ou_persistent22              
3Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands, ou_persistent22              
4Integrative Model-Based Cognitive Neuroscience Research Unit (IMCN), University of Amsterdam, the Netherlands, ou_persistent22              
5Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              
6Department of Radiology, VU University Amsterdam, the Netherlands, ou_persistent22              
7Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus Medical Center, Rotterdam, the Netherlands, ou_persistent22              
8Computational Radiology and Artificial Intelligence, Division of Radiology and Nuclear Medicine, Oslo University Hospital, Norway, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Magnetic resonance imaging; Quantitative MRI; Image reconstruction mapping; Deep learning; Subcortex
 Zusammenfassung: Quantitative MRI (qMRI) acquired at the ultra-high field of 7 Tesla has been used in visualizing and analyzing subcortical structures. qMRI relies on the acquisition of multiple images with different scan settings, leading to extended scanning times. Data redundancy and prior information from the relaxometry model can be exploited by deep learning to accelerate the imaging process. We propose the quantitative Recurrent Inference Machine (qRIM), with a unified forward model for joint reconstruction and -mapping from sparse data, embedded in a Recurrent Inference Machine (RIM), an iterative inverse problem-solving network. To study the dependency of the proposed extension of the unified forward model to network architecture, we implemented and compared a quantitative End-to-End Variational Network (qE2EVN). Experiments were performed with high-resolution multi-echo gradient echo data of the brain at 7T of a cohort study covering the entire adult life span. The error in reconstructed from undersampled data relative to reference data significantly decreased for the unified model compared to sequential image reconstruction and parameter fitting using the RIM. With increasing acceleration factor, an increasing reduction in the reconstruction error was observed, pointing to a larger benefit for sparser data. Qualitatively, this was following an observed reduction of image blurriness in -maps. In contrast, when using the U-Net as network architecture, a negative bias in in selected regions of interest was observed. Compressed Sensing rendered accurate, but less precise estimates of . The qE2EVN showed slightly inferior reconstruction quality compared to the qRIM but better quality than the U-Net and Compressed Sensing. Subcortical maturation over age measured by a linearly increasing interquartile range of in the striatum was preserved up to an acceleration factor of 9. With the integrated prior of the unified forward model, the proposed qRIM can exploit the redundancy among repeated measurements and shared information between tasks, facilitating relaxometry in accelerated MRI.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2022-09-162022-03-302022-10-102022-10-122022-12-01
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1016/j.neuroimage.2022.119680
Anderer: epub 2022
PMID: 36240989
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden: ausblenden:
Projektname : -
Grant ID : -
Förderprogramm : -
Förderorganisation : NWO Vici
Projektname : -
Grant ID : -
Förderprogramm : -
Förderorganisation : ERC-CoG
Projektname : -
Grant ID : -
Förderprogramm : -
Förderorganisation : NWO STW
Projektname : -
Grant ID : -
Förderprogramm : -
Förderorganisation : Health Holland, Top Sector Life Sciences & Health

Quelle 1

einblenden:
ausblenden:
Titel: NeuroImage
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Orlando, FL : Academic Press
Seiten: - Band / Heft: 264 Artikelnummer: 119680 Start- / Endseite: - Identifikator: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166