Note: If your CEST (&T1) data is acquired using different saturation parameters (B1, tsat, pulse shape, etc) at different field strengths (B0), you need to prepare training data and train your own network.
Authors: Jianpan Huang, Kannie WY Chan, et al.
Email: jp.huang@cityu.edu.hk, KannieW.Y.C@cityu.edu.hk
Affiliation: Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China
This toolbox contains demo for the following paper:
Huang J, Lai JHC, Tse K-H, Cheng GWY, Liu Y, Chen Z, Han X, Chen L, Xu J, Chan KWY. Deep neural network based CEST and AREX processing: Application in imaging a model of Alzheimer’s disease at 3 T. Magnetic Resonance in Medicine 2021. DOI: https://doi.org/10.1002/mrm.29044.
If you use the code, please consider citing our paper above. Earlier papers are recommended as well:
[1] Zaiss M, Deshmane A, Schuppert M, Herz K, Glang F, Ehses P, Lindig T, Bender B, Ernemann U, Scheffler K. DeepCEST: 9.4 T Chemical exchange saturation transfer MRI contrast predicted from 3 T data–a proof of concept study. Magnetic Resonance in Medicine 2019;81(6):3901-3914.
[2] Glang F, Deshmane A, Prokudin S, Martin F, Herz K, Lindig T, Bender B, Scheffler K, Zaiss M. DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T. Magnetic Resonance in Medicine 2020;84(1):450-466.
[3] Chen L, Schär M, Chan KW, Huang J, Wei Z, Lu H, Qin Q, Weiss RG, van Zijl PC, Xu J. In vivo imaging of phosphocreatine with artificial neural networks. Nature Communications 2020;11(1):1-10.
For the conventional multi-pool Lorenzian fitting, please visit: https://github.com/JianpanHuang/CEST-MPLF or https://github.com/cest-sources
Comments and suggestions are welcome.
For more information, please visit: https://www.jianpanhuang.com or https://sites.google.com/site/kannienicelab/home?authuser=0
Sep 22, 2021