ECN>> HiNet>> 返回
项目作者： taozh2017

项目描述 ：
Code for TMI 2020 "Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis"
高级语言： Python
项目地址: git://github.com/taozh2017/HiNet.git
创建时间： 2020-02-09T11:17:03Z
项目社区：https://github.com/taozh2017/HiNet
开源协议：
下载


Hi-Net

Code for TMI 2020 “Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis”

alt text

Usage

  1. The original implementation of Hi-Net is Pytorch. The code has been tested in Mac and Linux.

  2. To run the code, you should first install dependencies:

    pip install fire

  3. Setup all parameters in config.py

  4. Put your data into ./data (Some samples from BraTs2018 have been stored out in this file)

  5. Train

    CUDA_VISIBLE_DEVICES=0,1 python main.py train —batch_size=128 —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]