Progressive back-projection network for COVID-CT super-resolution

Background and Objective: Recently, the COVID-19 epidemic has become more and more serious around the world, how to improve the image resolution of COVID-CT is a very important task. The network based on progressive upsampling for COVID-CT super-resolution increases the reconstruction error. This paper proposes a progressive back-projection network (PBPN) for COVID-CT super-resolution to solve this problem. Methods: In this paper, we propose a progressive back-projection network (PBPN) for COVID-CT super-resolution. PBPN is divided into two stages, and each stage consists of back-projection, deep feature ex-traction and upscaling. We design an up-projection and down-projection residual module to minimize the reconstruction error and construct a residual attention module to extract deep features. In each stage, firstly, PBPN performs back-projection to extract shallow features by two up-projection and down-projection residual modules; then, PBPN extracts deep features from the shallow features by two residual attention modules; finally, PBPN upsamples the deep features through sub-pixel convolution. Results: The proposed method achieves the improvements of about 0.14-0.47 dB/0.0 012-0.0 060 for x 2 scale factor, 0.02-0.08 dB/0.0 024-0.0 059 for x 3 scale factor, and 0.08-0.41 dB/ 0.0040-0.0147 for x 4 scale factor than state-of-the-art methods (Bicubic, SRCNN, FSRCNN, VDSR, LapSRN, DRCN and DSRN) in terms of PSNR/SSIM on benchmark datasets. Conclusions: The proposed mehtod obtains better performance for COVID-CT super-resolution and recon-structs high-quality high-resolution COVID-CT images that contain more details and edges. (c) 2021 Elsevier B.V. All rights reserved.