Oxygen extraction fraction mapping at 3 Tesla using an artificial neural network

• Verfasst von: Domsch, Sebastian [VerfasserIn]
• Verfasst von: Mürle, Bettina [VerfasserIn]
• Verfasst von: Weingärtner, Sebastian [VerfasserIn]
• Verfasst von: Zapp, Jascha [VerfasserIn]
• Verfasst von: Wenz, Frederik [VerfasserIn]
• Verfasst von: Schad, Lothar R. [VerfasserIn]
• Titel: Oxygen extraction fraction mapping at 3 Tesla using an artificial neural network
• Titelzusatz: a feasibility study
• Verf.angabe: Sebastian Domsch, Bettina Mürle, Sebastian Weingärtner, Jascha Zapp, Frederik Wenz, and Lothar R. Schad
• Jahr: 2018
• Jahr des Originals: 2017
• Umfang: 10 S.
• Fussnoten: First published: 14 May 2017 ; Gesehen am 18.07.2018
• Titel Quelle: Enthalten in: Magnetic resonance in medicine
• Ort Quelle: New York, NY [u.a.] : Wiley-Liss, 1984
• Jahr Quelle: 2018
• Band/Heft Quelle: 79(2018), 2, Seite 890-899
• ISSN Quelle: 1522-2594
• DOI: doi:10.1002/mrm.26749
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: analytical tissue model
• Sach-SW: artificial neural network
• Sach-SW: blood-oxygenation-level-dependent (BOLD)
• Sach-SW: GESSEk
• Sach-SW: least-squares regression
• Sach-SW: machine learning
• Sach-SW: oxygen extraction fraction
• K10plus-PPN: 1577729188

Abstract

Purpose The oxygen extraction fraction (OEF) is an important biomarker for tissue-viability. MRI enables noninvasive estimation of the OEF based on the blood-oxygenation-level-dependent (BOLD) effect. Quantitative OEF-mapping is commonly applied using least-squares regression (LSR) to an analytical tissue model. However, the LSR method has not yet become clinically established due to the necessity for long acquisition times. Artificial neural networks (ANNs) recently have received increasing interest for robust curve-fitting and might pose an alternative to the conventional LSR method for reduced acquisition times. This study presents in vivo OEF mapping results using the conventional LSR and the proposed ANN method. Methods In vivo data of five healthy volunteers and one patient with a primary brain tumor were acquired at 3T using a gradient-echo sampled spin-echo (GESSE) sequence. The ANN was trained with simulated BOLD data. Results In healthy subjects, the mean OEF was 36 ± 2% (LSR) and 40 ± 1% (ANN). The OEF variance within subjects was reduced from 8% to 6% using the ANN method. In the patient, both methods revealed a distinct OEF hotspot in the tumor area, whereas ANN showed less apparent artifacts in surrounding tissue. Conclusion In clinical scan times, the ANN analysis enables OEF mapping with reduced variance, which could facilitate its integration into clinical protocols. Magn Reson Med 79:890-899, 2018. © 2017 International Society for Magnetic Resonance in Medicine.