Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution

Medical imaging is widely used in medical diagnosis. The low-resolution image caused by high hardware cost and poor imaging technology leads to the loss of relevant features and even fine texture. Obtaining high-quality medical images plays an important role in disease diagnosis. A surge of deep lea...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yue Yu, Kun She, Jinhua Liu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/21a9b16a6d9449e5a9de1cf6cec39e02
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:21a9b16a6d9449e5a9de1cf6cec39e02
record_format dspace
spelling oai:doaj.org-article:21a9b16a6d9449e5a9de1cf6cec39e022021-11-25T18:23:51ZWavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution10.3390/mi121114182072-666Xhttps://doaj.org/article/21a9b16a6d9449e5a9de1cf6cec39e022021-11-01T00:00:00Zhttps://www.mdpi.com/2072-666X/12/11/1418https://doaj.org/toc/2072-666XMedical imaging is widely used in medical diagnosis. The low-resolution image caused by high hardware cost and poor imaging technology leads to the loss of relevant features and even fine texture. Obtaining high-quality medical images plays an important role in disease diagnosis. A surge of deep learning approaches has recently demonstrated high-quality reconstruction for medical image super-resolution. In this work, we propose a light-weight wavelet frequency separation attention network for medical image super-resolution (WFSAN). WFSAN is designed with separated-path for wavelet sub-bands to predict the wavelet coefficients, considering that image data characteristics are different in the wavelet domain and spatial domain. In addition, different activation functions are selected to fit the coefficients. Inputs comprise approximate sub-bands and detail sub-bands of low-resolution wavelet coefficients. In the separated-path network, detail sub-bands, which have more sparsity, are trained to enhance high frequency information. An attention extension ghost block is designed to generate the features more efficiently. All results obtained from fusing layers are contracted to reconstruct the approximate and detail wavelet coefficients of the high-resolution image. In the end, the super-resolution results are generated by inverse wavelet transform. Experimental results show that WFSAN has competitive performance against state-of-the-art lightweight medical imaging methods in terms of quality and quantitative metrics.Yue YuKun SheJinhua LiuMDPI AGarticlemedical imagingstationary wavelet transformghost moduleattention mechanismMechanical engineering and machineryTJ1-1570ENMicromachines, Vol 12, Iss 1418, p 1418 (2021)
institution DOAJ
collection DOAJ
language EN
topic medical imaging
stationary wavelet transform
ghost module
attention mechanism
Mechanical engineering and machinery
TJ1-1570
spellingShingle medical imaging
stationary wavelet transform
ghost module
attention mechanism
Mechanical engineering and machinery
TJ1-1570
Yue Yu
Kun She
Jinhua Liu
Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
description Medical imaging is widely used in medical diagnosis. The low-resolution image caused by high hardware cost and poor imaging technology leads to the loss of relevant features and even fine texture. Obtaining high-quality medical images plays an important role in disease diagnosis. A surge of deep learning approaches has recently demonstrated high-quality reconstruction for medical image super-resolution. In this work, we propose a light-weight wavelet frequency separation attention network for medical image super-resolution (WFSAN). WFSAN is designed with separated-path for wavelet sub-bands to predict the wavelet coefficients, considering that image data characteristics are different in the wavelet domain and spatial domain. In addition, different activation functions are selected to fit the coefficients. Inputs comprise approximate sub-bands and detail sub-bands of low-resolution wavelet coefficients. In the separated-path network, detail sub-bands, which have more sparsity, are trained to enhance high frequency information. An attention extension ghost block is designed to generate the features more efficiently. All results obtained from fusing layers are contracted to reconstruct the approximate and detail wavelet coefficients of the high-resolution image. In the end, the super-resolution results are generated by inverse wavelet transform. Experimental results show that WFSAN has competitive performance against state-of-the-art lightweight medical imaging methods in terms of quality and quantitative metrics.
format article
author Yue Yu
Kun She
Jinhua Liu
author_facet Yue Yu
Kun She
Jinhua Liu
author_sort Yue Yu
title Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
title_short Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
title_full Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
title_fullStr Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
title_full_unstemmed Wavelet Frequency Separation Attention Network for Chest X-ray Image Super-Resolution
title_sort wavelet frequency separation attention network for chest x-ray image super-resolution
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/21a9b16a6d9449e5a9de1cf6cec39e02
work_keys_str_mv AT yueyu waveletfrequencyseparationattentionnetworkforchestxrayimagesuperresolution
AT kunshe waveletfrequencyseparationattentionnetworkforchestxrayimagesuperresolution
AT jinhualiu waveletfrequencyseparationattentionnetworkforchestxrayimagesuperresolution
_version_ 1718411183705292800