QQ‐NET – using deep learning to solve quantitative susceptibility mapping and quantitative blood oxygen level dependent magnitude (QSM+qBOLD or QQ) based oxygen extraction fraction (OEF) mapping

• Published in: Magnetic resonance in medicine Vol. 87; no. 3; pp. 1583 - 1594
• Main Authors: Cho, Junghun, Zhang, Jinwei, Spincemaille, Pascal, Zhang, Hang, Hubertus, Simon, Wen, Yan, Jafari, Ramin, Zhang, Shun, Nguyen, Thanh D., Dimov, Alexey V., Gupta, Ajay, Wang, Yi
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.03.2022
• Subjects: Artificial neural networks; Blood; Brain - diagnostic imaging; Brain Mapping; cerebral metabolic rate of oxygen; Cerebrovascular Circulation; Clustering; Deep Learning; Gray Matter; Humans; Image acquisition; Image reconstruction; Ischemia; Machine learning; Magnetic Resonance Imaging; Mapping; Neural networks; Oxygen; Oxygen Consumption; oxygen extraction fraction; Oxygen Saturation; qBOLD; QQ‐NET; QSM; QSM+qBOLD; quantitative blood oxygenation level‐dependent imaging; quantitative susceptibility mapping; Spin labeling; Stroke; Unet; QQ; Unet; deep learning; qBOLD; quantitative susceptibility mapping; QQ-NET; QSM+qBOLD; DL; quantitative blood oxygenation level-dependent imaging; QSM; cerebral metabolic rate of oxygen; oxygen extraction fraction
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.29057

Purpose To improve accuracy and speed of quantitative susceptibility mapping plus quantitative blood oxygen level‐dependent magnitude (QSM+qBOLD or QQ) ‐based oxygen extraction fraction (OEF) mapping using a deep neural network (QQ‐NET). Methods The 3D multi‐echo gradient echo images were acquired i...