By Tengfei Liang, Yi Jin, Yidong Li, Tao Wang.

This repository is an official implementation of the paper EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising. ArXiv IEEEXplore

Notes:

This repository provides model and loss implementation code, which can be easily integrated into the user's project.

EDCNN is a new end-to-end Low-Dose CT Denoiser. Designed as the FCN structure, it can effectively realize the low-dose CT image denoising in the way of post-processing. With the noval edge enhancement module, densely connection and compound loss, the model has a good performance in preserving details and suppressing noise in this denoising task. (For more details, please refer to the original paper)

Fig. 1: Overall architecture of the proposed EDCNN model.

For fairness, we choose the REDCNN, WGAN and CPCE for comparison, because of their design of the single model, which is the same as our EDCNN model. All these models adopt the structure of convolutional neural networks.

Fig. 2: Comparison with existing Models on the AAPM-Mayo Dataset.

In the experiment of our study, we utilize the dataset of the 2016 NIH AAPM-Mayo Clinic Low-Dose CT Grand Challenge, which is used by current mainstream methods in the field of low-dose CT image denoising. It contains the paired normal-dose CT (NDCT) images and synthetic quarter-dose CT images (LDCT) with a size of 512x512 pixels, collected from 10 patients. So there are LDCT images for inputs of the model and NDCT images as targets, which can support the supervised training process. Download

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

@article{Liang_2020,
   title={EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising},
   ISBN={9781728144801},
   url={http://dx.doi.org/10.1109/ICSP48669.2020.9320928},
   DOI={10.1109/icsp48669.2020.9320928},
   journal={2020 15th IEEE International Conference on Signal Processing (ICSP)},
   publisher={IEEE},
   author={Liang, Tengfei and Jin, Yi and Li, Yidong and Wang, Tao},
   year={2020},
   month={Dec}
}

This repository is released under the Apache 2.0 license. Please see the LICENSE file for more information.