Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
- Install TensorFlow 1.4 and CUDA 8.0
- Clone this repo
git clone https://github.com/cchen-cc/SIFA
cd SIFA
- Raw data needs to be written into
tfrecord
format to be decoded by./data_loader.py
. - Put
tfrecord
data of two domains into corresponding folders under./data
accordingly. - Run
./create_datalist.py
to generate the datalists containing the path of each data.
- Modify paramter values in
./config_param.json
- Run
./main.py
to start the training process
If you make use of the code, please cite the paper in resulting publications.
@article{chen2019synergistic,
title={Synergistic image and feature adaptation: Towards cross-modality domain adaptation for medical image segmentation},
author={Chen, Cheng and Dou, Qi and Chen, Hao and Qin, Jing and Heng, Pheng-Ann},
journal={AAAI},
year={2019}
}