Senior Researcher, Jarvis Lab@Tencent, Shenzhen, China
| Method | Domain | Original Link |
|---|---|---|
| InDuDoNet (MICCAI2021) | Dual-Domain | https://github.com/hongwang01/InDuDoNet |
| InDuDoNet+ (MedIA2023) | Dual-Domain | https://github.com/hongwang01/InDuDoNet_plus |
| DICDNet (TMI2021) | Image-Domain | https://github.com/hongwang01/DICDNet |
| ACDNet (IJCAI2022) | Image-Domain | https://github.com/hongwang01/ACDNet |
| OSCNet (MICCAI2022, TMI2023) | Image-Domain | https://github.com/hongwang01/OSCNet |
- Descriptions:
- Clean CT Images: Download 1200 CT images from the DeepLesion dataset
- Simulation Protocol: Refer to [1][2] with the imaging parameters in bulid_geometory.py
- Simulation Tool: Python.
- Training Data: Pairing 1000 clean images with 90 metals collected from [1]. Following [2], in each training iteration, we randomly chose one CT image with synthesized metal artifacts from the pool of 90 different metal mask pairs
- Testing Data: Pairing another 200 clean CT images with another 10 metals collected from [1] with sizes [2061, 890, 881, 451, 254, 124, 118, 112, 53, 35]
- SynDeepLesion
- Download Link for the complete SynDeepLesion: NetDisk with pwd: dicd
- Please refer to InDuDoNet and DICDNet for the data pre-processing
If this dataset is helpful for your research, please cite our work.
@inproceedings{wang2021indudonet,
title={InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction},
author={Wang, Hong and Li, Yuexiang and Zhang, Haimiao and Chen, Jiawei and Ma, Kai and Meng, Deyu and Zheng, Yefeng},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={107--118},
year={2021},
organization={Springer}
}
@article{wang2023indudonet+,
title={InDuDoNet+: A deep unfolding dual domain network for metal artifact reduction in CT images},
author={Wang, Hong and Li, Yuexiang and Zhang, Haimiao and Meng, Deyu and Zheng, Yefeng},
journal={Medical Image Analysis},
volume={85},
pages={102729},
year={2023}
}
@article{wang2021dicdnet,
title={DICDNet: Deep Interpretable Convolutional Dictionary Network for Metal Artifact Reduction in CT Images},
author={Wang, Hong and Li, Yuexiang and He, Nanjun and Ma, Kai and Meng, Deyu and Zheng, Yefeng},
journal={IEEE Transactions on Medical Imaging},
volume={41},
number={4},
pages={869--880},
year={2021},
publisher={IEEE}
}
@inproceedings{wang2022ada,
title={Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction},
author={Wang, Hong and Li, Yuexiang and Meng, Deyu and Zheng, Yefeng},
booktitle={The 31st International Joint Conference on Artificial Intelligence},
year={2022},
organization={IEEE}
}
@inproceedings{wang2022orientation,
title={Orientation-Shared Convolution Representation for CT Metal Artifact Learning},
author={Wang, Hong and Xie, Qi and Li, Yuexiang and Huang, Yawen and Meng, Deyu and Zheng, Yefeng},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={665--675},
year={2022},
organization={Springer}
}
@article{wang2023oscnet,
title={OSCNet: Orientation-Shared Convolutional Network for CT Metal Artifact Learning},
author={Wang, Hong and Xie, Qi and Zeng, Dong and Ma, Jianhua and Meng, Deyu and Zheng, Yefeng},
journal={IEEE Transactions on Medical Imaging},
year={2023}
}
The authors would like to thank Dr. Lequan Yu for providing the related reference code. If necessary, please contact the author about the original synthesis code.
[1] Y. Zhang and H. Yu, “Convolutional neural network based metal artifact reduction in X-ray computed tomography,”IEEE Transactions on Medical Imaging, vol. 37, no. 6, pp. 1370–1381, 2018.
[2] Yu, L., Zhang, Z., Li, X., Xing, L.: Deep sinogram completion with image prior for metal artifact reduction in CT images. IEEE Transactions on Medical Imaging40(1), 228–238 (2020).
If you have any questions, please feel free to contact Hong Wang (Email: [email protected])