Super-resolution using Deep Networks for Chest X-Ray Images

Super-resolution imaging is extensively deliberated in medical imaging modalities nowadays, there being a wide panic on the effect of COVID-19 virus impression. Generally, spatial resolutions of CXR are insufficient due to the constraints such as image acquisition time, hardware limits and physical limits. It is a clinically challenging task to recover the high resolution CXR images. A significant concern in CXR imaging is X-Ray contrast disparity and the demand to attain high quality images with adequate structural and imaging details. To address these problems, we propose an effective deep network for the super-resolution reconstruction method to recover high-resolution CXR images while retaining diagnostic capabilities. Specifically, the reinforcement subnetwork is hosted to generate sharp and informative qualitative features. The quantitative and qualitative assessments found that the proposed model based on the evaluation index improves the CXR super-resolution. In addition, the PSNR index of the proposed model has 0.30 higher than that of the SRCNN network.