Awesome
deepMRI: Deep learning methods for MRI
Authors: Yang Gao, Zhuang Xiong, Hongfu Sun
-
This repo is devloped based on Pytorch (1.8 or later) and matlab (R2019a or later).
-
The codes in this repo were tested on Centos 7.8 with Nvdia Tesla V100 and macos12.0.1/win10/ubuntu19.10 with GTX 1060
Major Update, 31st, Jan, 2023: Delete old-version iQSM checkpoints. Will upload latest codes and checkpoints shortly.
Projects
iQSM+ for orientation-adaptive single-step QSM reconstruction
iQSM for single-step instant QSM
DCRNet for QSM and R2* acceleration
BFRnet for QSM background field removal
<span id="head5"> iQSM+ for orientation-adaptive single-step QSM reconstruction </span>
Instant tissue field and magnetic susceptibility mapping from MRI raw phase using Laplacian enabled deep neural networks
source code (github) | arXiv (pre-print) | MIA (full paper)
<span id="head4"> iQSM for single-step instant QSM </span>
Instant tissue field and magnetic susceptibility mapping from MRI raw phase using Laplacian enabled deep neural networks
source code (github) | data & checkpoints (dropbox) | arXiv (pre-print) | NeuroImage (full paper)
<span id="head3"> DCRNet for QSM and R2* acceleration </span>
Accelerating quantitative susceptibility and R2* mapping using incoherent undersampling and deep neural network reconstruction
source code (github) | data & checkpoints (dropbox) | arXiv (pre-print) | NeuroImage (full paper)
<span id="head2"> xQSM for QSM dipole inversion </span>
xQSM: quantitative susceptibility mapping with octave convolutional and noise-regularized neural networks
source code (github) | data & checkpoints (dropbox) | arXiv (pre-print) | NMR in Biomed (full paper)
<span id="head1"> BFRnet for QSM background field removal </span>
BFRnet: A deep learning-based MR background field removal method for QSM of the brain containing significant pathological susceptibility sources
source code (github) | data & checkpoints (dropbox) | arXiv (pre-print) |