by Quande Liu, Qi Dou, Lequan Yu, Pheng-Ann Heng.

The Tensorflow implementation for our TMI 2020 paper 'Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data'.

python==2.7.17
numpy==1.16.6
scipy==1.2.1
tensorflow-gpu==1.12.0
tensorboard==1.12.2
SimpleITK==1.2.0

1. Train the model: First, you need to specify the training configurations (can simply use the default setting) in main.py. Then run:

   python main.py --phase=train

2. Evaluate the model:

   Run:

   python main.py --phase=test --restore_model='xxxx'

   You will see the output results in the folder ./output/.

If this repository is useful for your research, please cite:

@article{liu2020ms,
  title={Ms-net: Multi-site network for improving prostate segmentation with heterogeneous mri data},
  author={Liu, Quande and Dou, Qi and Yu, Lequan and Heng, Pheng Ann},
  journal={IEEE Transactions on Medical Imaging},
  year={2020},
  publisher={IEEE}
}

Please contact '[email protected]'