imed-lab/re-net

3D cerebrovascular volume segmentation in Pytorch.

MICCAI 2020 Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network

This repo is the official implementation of Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network

I. Experiment Results:

II. Usage:

Using the train3d.py and predict3d.py to train and test the model on your own dataset, respectively.

The proposed network model RE-Net is defined in the model.py in models folder. It can be easily edited and embed in your own code.

III. Requirements:

• PyTorch = 1.2.0
• tqdm
• SimpleITK
• visdom

IV. Citation：

If our paper or code is helpful to you, please cite our paper. If you have any questions, please feel free to ask me.

@inproceedings{zhang2020cerebrovascular,
  title={Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network},
  author={Zhang, Hao and Xia, Likun and Song, Ran and Yang, Jianlong and Hao, Huaying and Liu, Jiang and Zhao, Yitian},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={66--75},
  year={2020},
  organization={Springer}
}