Jae-Hun Lee1, Jaeuk Yi1, Kanghyun Ryu2, Soozy Jung1, and Dong-Hyun Kim1
1Department of Electrical & Electronic Engineering, Yonsei Univ., Seoul, Korea, Republic of, 2Department of Radiology, Stanford Univ., Stanford, CA, United States
1Department of Electrical & Electronic Engineering, Yonsei Univ., Seoul, Korea, Republic of, 2Department of Radiology, Stanford Univ., Stanford, CA, United States
We explored a reconstruction method using advanced parallel imaging with deep learning, which can utilize joint information. The proposed method shows improved quantitative values compared to conventional methods and can achieve high acceleration factors for mGRE based 3D MWI.
Figure 1. Proposed reconstruction algorithm schematic.
Figure 4. MWF maps of the different method reconstructed images with difference maps (R=2*2).