This is a source codes in MATLAB and Python to reproduce some of the results that are described in the paper: "Accelerated multi-contrast reconstruction for Synthetic MRI using Joint Parallel Imaging and Variable Splitting Network". For any questions about the code, please contact me (Kanghyun Ryu) at: kanghyun@stanford.edu
The dataset used in this work has been collected with a collaboration between the Medical Imaging LABoratory (MILAB) at Yonsei University and University of Ulsan College of Medicine, Asan Medical Center.
If needed, please request the dataset to donghyunkim@yonsei.ac.kr.
For J-LORAKS, you will need to download ACS-LORAKS Recon code from http://mr.usc.edu/download/LORAKS2/ Please refer to the reference of the code from
[1] T. H. Kim, J. P. Haldar. LORAKS Software Version 2.0: Faster Implementation and Enhanced Capabilities. University of Southern California, Los Angeles, CA, Technical Report USC-SIPI-443, May 2018.
[2] J. P. Haldar. Autocalibrated LORAKS for Fast Constrained MRI Reconstruction. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, New York City, 2015, pp. 910-913.
For original version of VS-Net, please refer to https://github.com/j-duan/VS-Net or refer to the paper,
[1] Duan J, Schlemper J, Qin C, Ouyang C, Bai W, Biffi C, Bello G, Statton B, O'Regan DP, Rueckert D. VS-Net: Variable splitting network for accelerated parallel MRI reconstruction. arXiv preprint arXiv:1907.10033. MICCAI (2019).
Our work has been accepted in Medical Physics 2021: Accelerated multi‐contrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks. When using our code or dataset for research publications, please cite our paper.