Residual Dense Attention Networks for COVID-19 Computed Tomography Images Super Resolution

The coronavirus disease 2019 (COVID-19) is highly contagious and pathogenic, posing a serious threat to the public safety of the people. Owing to the low resolution of computed tomography (CT) images, it is essential to use super resolution (SR) reconstruction technology to improve the resolution of COVID-19 medical images. Aiming at the problems of the limited receptive field, low resolution, high complexity, and loss of edge information in the SR reconstruction method of residual learning, we present a residual dense attention network (RDAN) for COVID-19 CT image SR. First, to better extract features and reduce the number of parameters, we design the residual dense network module to extract detailed information from images. Second, we add the channel attention mechanism to enable the network to have adequate high-frequency information with larger weights to reduce the computational cost of the model. Finally, we filter and reorganize the multilayer image information by skip connections so that the network model can allow extensive use of image information of different depths. Comprehensive benchmark evaluation shows that our RDAN method dramatically improves the convergence speed of the network, solves the problem of missing information, and makes the reconstructed COVID-19 CT images have more apparent textures, richer details, and better visual effects that can effectively assist experts in diagnosis.