Deep learning–based MR fingerprinting ASL ReconStruction (DeepMARS)

• Published in: Magnetic resonance in medicine Vol. 84; no. 2; pp. 1024 - 1034
• Main Authors: Zhang, Qiang, Su, Pan, Chen, Zhensen, Liao, Ying, Chen, Shuo, Guo, Rui, Qi, Haikun, Li, Xuesong, Zhang, Xue, Hu, Zhangxuan, Lu, Hanzhang, Chen, Huijun
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.08.2020
• Subjects: Angiography; Arteries; Blood flow; Cerebral blood flow; Cerebrovascular Circulation; Computer simulation; Computing time; Correlation coefficients; Deep Learning; DeepMARS; Fingerprinting; Humans; Machine learning; Magnetic Resonance Imaging; Mathematical models; Moyamoya Disease; MRF‐ASL; Neural networks; Parameters; Perfusion; Random noise; Reconstruction; Reproducibility; Spin labeling; Spin Labels; deep learning; reconstruction; MRF-ASL; DeepMARS; reproducibility

Purpose To develop a reproducible and fast method to reconstruct MR fingerprinting arterial spin labeling (MRF‐ASL) perfusion maps using deep learning. Method A fully connected neural network, denoted as DeepMARS, was trained using simulation data and added Gaussian noise. Two MRF‐ASL models were us...