Official Pytorch implementation of "Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising" (MICCAI 2022)

Chanyong Jung, Joonhyung Lee, Sunkyoung You, Jong Chul Ye

Link: https://arxiv.org/abs/2207.02377

Implementation

• We provide the source code for AAPM dataset.
  (2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset)
  We randomly select 3112 images for train set, 421 images for validation set.
  421 images are used for test set.

• Refer the following code to obtain the model:

python main.py --prj_name [folder-name] --log_name [log-file-name] \
--dataset_name AAPM --data_root [path-to-data] --gpu_ids 0

Acknowledgement

Our source code is based on the official implementation of CUT.