Official repository for "OTMorph: Unsupervised Multi-domain Abdominal Medical Image Registration Using Neural Optimal Transport", published in IEEE Transactions on Medical Imaging.
To test the proposed OTMorph, we may need Conda environment. You can download Anaconda from this link. Then, please run:
conda env create โf OTMorph.yml
To train our model, run this command:
sh ./scripts/train.sh
To test the trained our model, run:
sh ./scripts/test.sh
When you run the code, "./results" folder is generated. And the registration results are saved in this directory.
@article{kim2024otmorph,
title={OTMorph: Unsupervised Multi-domain Abdominal Medical Image Registration Using Neural Optimal Transport},
author={Kim, Boah and Zhuang, Yan and Mathai, Tejas Sudharshan and Summers, Ronald M},
journal={IEEE Transactions on Medical Imaging},
year={2024},
publisher={IEEE}
}