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

Zhaoyang Song; Xiaoqiang Zhao; Yongyong Hui; Hongmei Jiang

doi:10.1016/j.cmpb.2021.106193

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

Comput Methods Programs Biomed. 2021 Sep:208:106193. doi: 10.1016/j.cmpb.2021.106193. Epub 2021 May 24.

Authors

Zhaoyang Song¹, Xiaoqiang Zhao², Yongyong Hui³, Hongmei Jiang⁴

Affiliations

¹ College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China. Electronic address: szylut@126.com.
² College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China. Electronic address: xqzhao@lut.cn.
³ College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China. Electronic address: hyylut@163.com.
⁴ College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China; Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou 730050, China; National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China. Electronic address: jhm@lut.cn.

Abstract

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 extraction 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/0.0012~0.0060 for × 2 scale factor, 0.02~0.08 dB/0.0024~0.0059 for × 3 scale factor, and 0.08~0.41 dB/ 0.0040~0.0147 for × 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 reconstructs high-quality high-resolution COVID-CT images that contain more details and edges.

Keywords: COVID-CT; Progressive back-projection network; Residual attention module; Super-resolution; Up-projection and down-projection residual module.

MeSH terms

Algorithms
COVID-19*
Humans
Image Processing, Computer-Assisted*
Neural Networks, Computer
SARS-CoV-2
Tomography, X-Ray Computed