Ct Image Denoising With Encoder-Decoder Based Graph Convolutional Networks

Yu-Jen Chen, Cheng-Yen Tsai, Xiaowei Xu, Yiyu Shi, Tsung-Yi Ho, Meiping Huang, Haiyun Yuan, Jian Zhuang

Abstract

Image denoising of low-dose CT images is a key problem in modern medical practice. Recently, several works adopted Convolutional Neural Network (CNN) to precisely capture the similarity between local features resulting in significant improvements. However, we discovered that the main drawback of existing works is the lack of non-local feature processing. On the other hand, currently, graph convolutional networks (GCN) have been widely used to process non-Euclidean geometry data considering both local and non-local features. Motivated by the property of GCN, in this paper, we propose an encoder-decoder-based graph convolutional network (ED-GCN) for CT image denoising. Particularly, we combine local convolutions and graph convolutions to process both local and non-local features. We collected seven CT volumes with Gaussian noise and Poisson noise in the experiment. Experimental results show that the proposed method outperforms existing CNN-based approaches significantly.
BibTeX
@inproceedings{chen2021ct,
  author = {Yu-Jen Chen and Cheng-Yen Tsai and Xiaowei Xu and Yiyu Shi and Tsung-Yi Ho and Meiping Huang and Haiyun Yuan and Jian Zhuang},
  title = {{Ct Image Denoising With Encoder-Decoder Based Graph Convolutional Networks}},
  booktitle = {ISBI},
  year = {2021},
  doi = {10.1109/isbi48211.2021.9433900},
}

Loading related content...

Figure