Code for TMI 2020 "Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis"
Usage
-
The original implementation of Hi-Net is Pytorch. The code has been tested in Mac and Linux.
-
To run the code, you should first install dependencies:
pip install fire
-
Setup all parameters in config.py
-
Put your data into ./data (Some samples from BraTs2018 have been stored out in this file)
-
Train
CUDA_VISIBLE_DEVICES=0,1 python main.py train --batch_size=16 --task_id=2 --gpu_id=[0,1]
(you can set your parameters when runing the code)
If you use this code, please cite the following papers:
[1] Tao Zhou, Huazhu Fu, Geng Chen, Jianbing Shen, Ling Shao. "Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis". IEEE Transactions on Medical Imaging (IEEE TMI), 2020. (Offical version)(arXiv version)
Datsets: you can download multi-modal medical datastes from:
[1] BraTs 2018: [HERE]
[2] BraTs 2019: [HERE]
[3] ISLES2015: [HERE]