QSMnet+

J. Yoon, E. Gong, I. Chatnuntawech, B. Bilgic, J. Lee, W. Jung, J. Ko, H. Jung, K. Setsompop, G. Zaharchuk, E.Y. Kim, J. Pauly, J. Lee. Quantitative susceptibility mapping using deep neural network: QSMnet. Neuroimage. 2018 Oct;179:199-206.

W. Jung, J. Yoon, S. Ji, J. Choi, J. Kim, Y. Nam, E. Kim, J. Lee. Exploring linearity of deep neural network trained QSM: QSMnet+. Neuroimage. 2020 May; 116619.

W. Jung, S. Bollmann, J. Lee. Overview of quantitative susceptibility mapping using deep learning: Current status, challenges and opportunities. NMR in Biomedicine. 2020 Mar; e4292.

Setup QSMnet+ for SEPIA

  1. Download QSMnet+ from GitHub
  2. If you haven’t setup QSMnet+ in python, following the instruction in https://github.com/SNU-LIST/QSMnet, including downloading the pre-trained network and creating conda environment (see Section Manual in their GitHub page)
  3. Specify the full path to QSMnet+ code as ‘QSMnet_HOME’ in setup_qsmnet_environment.m in SEPIA_HOME/addons/qsm/QSMnet/
  4. Specify the full path of the Python interpreter that has QSMnet installed as ‘python_interpreter’ in setup_qsmnet_environment.m

Your setup_qsmnet_environment.m should look something like this:

../../_images/QSMnet_setup.png

Warning

The support this method is still in an early stage and only tested on a Linux machine.

QSMnet+ panel

There is no algorithm parameter needed to be adjusted with this tool at the moment.

../../_images/QSMnet.png