Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism

In industrial computed tomography (CT), using noisy projection data for reconstruction increases the noise in the reconstructed image and reduces the signal-to-noise ratio (SNR). When the quality of projection data is poor, classical denoising and reconstruction algorithms are ineffective in removin...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu HE, Chengxiang WANG, Wei YU
Format: Article
Language:English
Published: Editorial Office of Computerized Tomography Theory and Application 2025-07-01
Series:CT Lilun yu yingyong yanjiu
Subjects:
Online Access:https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2025.068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428264131493888
author Yu HE
Chengxiang WANG
Wei YU
author_facet Yu HE
Chengxiang WANG
Wei YU
author_sort Yu HE
collection DOAJ
description In industrial computed tomography (CT), using noisy projection data for reconstruction increases the noise in the reconstructed image and reduces the signal-to-noise ratio (SNR). When the quality of projection data is poor, classical denoising and reconstruction algorithms are ineffective in removing the noise. To improve the quality of low signal-to-noise CT reconstructed images, this study proposes a deep learning-based denoising method. The method integrates squeeze-and-excitation blocks into the decoder phase and adaptively adjusts the weights of the channels to better preserve structural details during the denoising process. Experimental results demonstrate that the proposed method significantly reduces the noise and effectively preserves edge details, outperforming other comparative methods in both visual quality and quantitative values.
format Article
id doaj-art-e0b4899c9fa84eeb879d1cb6fbb4e842
institution Kabale University
issn 1004-4140
language English
publishDate 2025-07-01
publisher Editorial Office of Computerized Tomography Theory and Application
record_format Article
series CT Lilun yu yingyong yanjiu
spelling doaj-art-e0b4899c9fa84eeb879d1cb6fbb4e8422025-08-20T03:28:44ZengEditorial Office of Computerized Tomography Theory and ApplicationCT Lilun yu yingyong yanjiu1004-41402025-07-0134454355010.15953/j.ctta.2025.0682025-068Industrial Computed Tomography Image Denoising Network Based on Channel Attention MechanismYu HE0Chengxiang WANG1Wei YU2School of Mathematical Sciences, Chongqing Normal University, Chongqing 401331, ChinaSchool of Mathematical Sciences, Chongqing Normal University, Chongqing 401331, ChinaKey Laboratory of Optoelectronic Sensing and Intelligent Control, Hubei University of Science and Technology, Xianning 437100, ChinaIn industrial computed tomography (CT), using noisy projection data for reconstruction increases the noise in the reconstructed image and reduces the signal-to-noise ratio (SNR). When the quality of projection data is poor, classical denoising and reconstruction algorithms are ineffective in removing the noise. To improve the quality of low signal-to-noise CT reconstructed images, this study proposes a deep learning-based denoising method. The method integrates squeeze-and-excitation blocks into the decoder phase and adaptively adjusts the weights of the channels to better preserve structural details during the denoising process. Experimental results demonstrate that the proposed method significantly reduces the noise and effectively preserves edge details, outperforming other comparative methods in both visual quality and quantitative values.https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2025.068deep learningchannel attention mechanismindustrial ctlow snrimage denoising
spellingShingle Yu HE
Chengxiang WANG
Wei YU
Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
CT Lilun yu yingyong yanjiu
deep learning
channel attention mechanism
industrial ct
low snr
image denoising
title Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
title_full Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
title_fullStr Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
title_full_unstemmed Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
title_short Industrial Computed Tomography Image Denoising Network Based on Channel Attention Mechanism
title_sort industrial computed tomography image denoising network based on channel attention mechanism
topic deep learning
channel attention mechanism
industrial ct
low snr
image denoising
url https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2025.068
work_keys_str_mv AT yuhe industrialcomputedtomographyimagedenoisingnetworkbasedonchannelattentionmechanism
AT chengxiangwang industrialcomputedtomographyimagedenoisingnetworkbasedonchannelattentionmechanism
AT weiyu industrialcomputedtomographyimagedenoisingnetworkbasedonchannelattentionmechanism