Cargando…

Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning

High-resolution (HR) medical imaging data provide more anatomical details of human body, which facilitates early-stage disease diagnosis. But it is challenging to get clear HR medical images because of the limiting factors, such as imaging systems, imaging environments, and human factors. This work...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Lina, Dai, Haidong, Sang, Yu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9210125/
https://www.ncbi.nlm.nih.gov/pubmed/35747717
http://dx.doi.org/10.1155/2022/1744969
_version_ 1784730093978910720
author Zhang, Lina
Dai, Haidong
Sang, Yu
author_facet Zhang, Lina
Dai, Haidong
Sang, Yu
author_sort Zhang, Lina
collection PubMed
description High-resolution (HR) medical imaging data provide more anatomical details of human body, which facilitates early-stage disease diagnosis. But it is challenging to get clear HR medical images because of the limiting factors, such as imaging systems, imaging environments, and human factors. This work presents a novel medical image super-resolution (SR) method via high-resolution representation learning based on generative adversarial network (GAN), namely, Med-SRNet. We use GAN as backbone of SR considering the advantages of GAN that can significantly reconstruct the visual quality of the images, and the high-frequency details of the images are more realistic in the image SR task. Furthermore, we employ the HR network (HRNet) in GAN generator to maintain the HR representations and repeatedly use multi-scale fusions to strengthen HR representations for facilitating SR. Moreover, we adopt deconvolution operations to recover high-quality HR representations from all the parallel lower resolution (LR) streams with the aim to yield richer aggregated features, instead of simple bilinear interpolation operations used in HRNetV2. When evaluated on a home-made medical image dataset and two public COVID-19 CT datasets, the proposed Med-SRNet outperforms other leading edge methods, which obtains higher peak signal to noise ratio (PSNR) values and structural similarity (SSIM) values, i.e., maximum improvement of 1.75 and minimum increase of 0.433 on the PSNR metric for “Brain” test sets under 8× and maximum improvement of 0.048 and minimum increase of 0.016 on the SSIM metric for “Lung” test sets under 8× compared with other methods.
format Online
Article
Text
id pubmed-9210125
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-92101252022-06-22 Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning Zhang, Lina Dai, Haidong Sang, Yu Comput Intell Neurosci Research Article High-resolution (HR) medical imaging data provide more anatomical details of human body, which facilitates early-stage disease diagnosis. But it is challenging to get clear HR medical images because of the limiting factors, such as imaging systems, imaging environments, and human factors. This work presents a novel medical image super-resolution (SR) method via high-resolution representation learning based on generative adversarial network (GAN), namely, Med-SRNet. We use GAN as backbone of SR considering the advantages of GAN that can significantly reconstruct the visual quality of the images, and the high-frequency details of the images are more realistic in the image SR task. Furthermore, we employ the HR network (HRNet) in GAN generator to maintain the HR representations and repeatedly use multi-scale fusions to strengthen HR representations for facilitating SR. Moreover, we adopt deconvolution operations to recover high-quality HR representations from all the parallel lower resolution (LR) streams with the aim to yield richer aggregated features, instead of simple bilinear interpolation operations used in HRNetV2. When evaluated on a home-made medical image dataset and two public COVID-19 CT datasets, the proposed Med-SRNet outperforms other leading edge methods, which obtains higher peak signal to noise ratio (PSNR) values and structural similarity (SSIM) values, i.e., maximum improvement of 1.75 and minimum increase of 0.433 on the PSNR metric for “Brain” test sets under 8× and maximum improvement of 0.048 and minimum increase of 0.016 on the SSIM metric for “Lung” test sets under 8× compared with other methods. Hindawi 2022-06-20 /pmc/articles/PMC9210125/ /pubmed/35747717 http://dx.doi.org/10.1155/2022/1744969 Text en Copyright © 2022 Lina Zhang et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Zhang, Lina
Dai, Haidong
Sang, Yu
Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title_full Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title_fullStr Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title_full_unstemmed Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title_short Med-SRNet: GAN-Based Medical Image Super-Resolution via High-Resolution Representation Learning
title_sort med-srnet: gan-based medical image super-resolution via high-resolution representation learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9210125/
https://www.ncbi.nlm.nih.gov/pubmed/35747717
http://dx.doi.org/10.1155/2022/1744969
work_keys_str_mv AT zhanglina medsrnetganbasedmedicalimagesuperresolutionviahighresolutionrepresentationlearning
AT daihaidong medsrnetganbasedmedicalimagesuperresolutionviahighresolutionrepresentationlearning
AT sangyu medsrnetganbasedmedicalimagesuperresolutionviahighresolutionrepresentationlearning