Open AccessERA-WGAT: Edge-enhanced residual autoencoder with a window-based graph attention convolutional network for low-dose CT denoising
Author(s) -
Han Liu,
Peixi Liao,
Hu Chen,
Yi Zhang
Publication year - 2022
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.471340
Subject(s) - convolutional neural network , computer science , artificial intelligence , smoothing , residual , autoencoder , noise reduction , deep learning , pattern recognition (psychology) , graph , image quality , convolution (computer science) , enhanced data rates for gsm evolution , computer vision , artificial neural network , algorithm , image (mathematics) , theoretical computer science
Computed tomography (CT) has become a powerful tool for medical diagnosis. However, minimizing X-ray radiation risk for the patient poses significant challenges to obtain suitable low dose CT images. Although various low-dose CT methods using deep learning techniques have produced impressive results, convolutional neural network based methods focus more on local information and hence are very limited for non-local information extraction. This paper proposes ERA-WGAT, a residual autoencoder incorporating an edge enhancement module that performs convolution with eight types of learnable operators providing rich edge information and a window-based graph attention convolutional network that combines static and dynamic attention modules to explore non-local self-similarity. We use the compound loss function that combines MSE loss and multi-scale perceptual loss to mitigate the over-smoothing problem. Compared with current low-dose CT denoising methods, ERA-WGAT confirmed superior noise suppression and perceived image quality.