Motion artifact correction by applying a novel unsupervised network for arterial phase imaging of gadoxetic acid-enhanced liver MRI examinations
This is an implementation for the paper "Motion artifact correction by applying a novel unsupervised network for arterial phase imaging of gadoxetic acid-enhanced liver MRI examinations", a simple and efficient framework for unsupervised MRI motion correction, which is injected into the general domain transfer architecture. More details could be found in the original paper.
- (OS) Windows/Ubuntu
- Python >= 3.6
- Pytorch >= 1.1.0
- Python-Libs, e.g., cv2, skimage.
- Prepare your dataset.
- Update the data paths in
config.pyandutils.pyfile. - Train your model by the
train.pyfile.
A simple script to test your model:
python3 test.py
Our code is based on the LIR-for-Unsupervised-IR, which is a nice work for unsupervised image translation.