Medical image super‐resolution using correlation filter interleaved progressive convolution network (CFIPC)

Abstract

In medical image diagnosis, performance is affected because of degradation in image resolution, imaging equipment and imaging parameters. Currently, deep learning has gained much attention from researchers due to its capability to maintain perceptual quality after reconstruction. Therefore, this letter is motivated by the advantages of deep learning and proposes a novel model termed as the correlation filter interleaved progressive convolution network (CFIPC). In this letter, dilated convolution interleaved with a correlation filter expands the receptive field without any pixel information losses. The result analysis was performed on DRIVE, CHASEB1, MRI, ultrasound and histopathological dataset medical datasets at 2x/4x/8x/16x upscaling factors and achieved the highest PSNR/SSIM value of 50.54/0.9986 at a 2x upscaling factor on the histopathological dataset.

Enhanced dual branches network for arbitrary‐scale image super‐resolution

“…Introduction: Image super-resolution, as a classic image processing technique, aims to produce a high-resolution (HR) image based on a degraded low-resolution (LR) image. In recent years, single image superresolution (SISR) methods with deep convolutional neural networks (CNNs) [1][2][3][4][5] have been significantly developed over traditional superresolution (SR) methods and extensively applied in various fields, such as medical images [6,7] and satellite imaging [8]. However, most existing SISR pre-trained models can only perform single image restoration of the LR image which increase computational costs.…”