Deep learning based multiplexed sensitivity-encoding (DL-MUSE) for high-resolution multi-shot DWI

• Published in: NeuroImage (Orlando, Fla.) Vol. 244; p. 118632
• Main Authors: Zhang, Hui, Wang, Chengyan, Chen, Weibo, Wang, Fanwen, Yang, Zidong, Xu, Shuai, Wang, He
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2021; Elsevier Limited; Elsevier
• Subjects: Accuracy; Adult; Aged; Algorithms; Brain Neoplasms - diagnostic imaging; Deep Learning; Diffusion; Diffusion Magnetic Resonance Imaging - methods; Echo-Planar Imaging; Efficiency; Female; High resolution; Humans; Male; Middle Aged; Multi-shot EPI; Neural networks; Neural Networks, Computer; Neuroimaging; Neuroimaging - methods; Patients; Phase correction; Phase Variation; Phase variations; Substantia alba; Tumors; Young Adult; High resolution; GSR; DL; SSH-EPI; Phase correction; Multi-shot EPI; deep learning; SNR; DWI; DTI; Diffusion; MSH-EPI; MUSE

•A deep learning-based phase reconstruction scheme is proposed for high-resolution multi-shot (MSH) DWI reconstruction.•Higher SNR (especially with high acceleration rates), fewer aliasing artifacts, lower ghost-to-signal-ratio (GSR), higher tracked fiber counts, and finer fiber delineation can be o...