search

Yaziwel / All-In-One-Medical-Image-Restoration-via-Task-Adaptive-Routing

[MICCAI 2024] All-In-One Medical Image Restoration via Task-Adaptive Routing (AMIR).
Apache License 2.0
34 stars 2 forks source link
all-in-one ct ct-denoising image-restoration low-level medical-image-processing mri mri-super-resolution pet pet-image-reconstruction

readme

All-In-One Medical Image Restoration via Task-Adaptive Routing (AMIR)

PyTorch implementation for All-In-One Medical Image Restoration via Task-Adaptive Routing arXiv (MICCAI 2024).

Network Architecture

Dataset

You can download the preprocessed datasets for MRI super-resolution, CT denoising, and PET synthesis from Baidu Netdisk here.

The original dataset for MRI super-resolution and CT denoising are as follows:

Visualization

You can use AMIDE to visualize the ".nii" file. Note that the color map for MRI and CT images is "black/white linear," while the color map for PET images is "white/black linear." Additionally, you need to rescale the PET image according to the voxel size specified in the paper.

Citation

If you find AMIR useful in your research, please consider citing:

@inproceedings{yang2024amir,
  title={All-In-One Medical Image Restoration via Task-Adaptive Routing},
  author={Yang, Zhiwen and Chen, Haowei and Qian, Ziniu and Yi, Yang and Zhang, Hui and Zhao, Dan and Wei, Bingzheng and Xu, Yan},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={67--77},
  year={2024},
  organization={Springer}
}