Implementation of Single Image Super-Resolution Methods on Ultrasound Images

Abstract

Today, image quality has become an important factor in many areas. Especially in the field of medical imaging, high-resolution images are needed. In this study, EDSR (Enhanced Deep Residual Networks for Single Image Super-Resolution) and DCSCN (Fast and Accurate Image Super-Resolution by Deep Convolutional Neural Network with Skip Connection and Network in Network) methods were trained using the ultrasound dataset and the results were compared, considering the need for high resolution images in the medical field.