A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising

Computed Tomography (CT) scan, pivotal for medical diagnostics, involves exposure to electromagnetic radiation, potentially elevating the risk of leukemia and cancer. Low-dose CT (LDCT) imaging has emerged to mitigate these risks, extensively reducing radiation exposure by up to 86%. However, it sig...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Zubair, Helmi Md Rais, Talal Alazemi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10829953/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117696460423168
author Muhammad Zubair
Helmi Md Rais
Talal Alazemi
author_facet Muhammad Zubair
Helmi Md Rais
Talal Alazemi
author_sort Muhammad Zubair
collection DOAJ
description Computed Tomography (CT) scan, pivotal for medical diagnostics, involves exposure to electromagnetic radiation, potentially elevating the risk of leukemia and cancer. Low-dose CT (LDCT) imaging has emerged to mitigate these risks, extensively reducing radiation exposure by up to 86%. However, it significantly reduces the quality of LDCT images and introduces noise and artifacts, degrading the diagnostic accuracy of the Computer Aided Diagnostic (CAD) system. This study presents a novel U-Net architecture, featuring several key enhancements. The model integrates residual blocks to improve feature representation and employs a custom hybrid loss function that combines structural loss with gradient regularization using the Euclidean norm, promoting superior CT image quality retention. Additionally, incorporating Attention Gates in the up-sampling layers of a proposed model optimizes the extraction of critical features, ensuring more precise denoising of CT images. The proposed model undergoes iterative training, using a custom loss function to refine its parameters and improve CT image denoising progressively. Its performance is rigorously evaluated both qualitatively and quantitatively on the ‘2016 Low-dose CT AAPM Grand Challenge dataset’. The results, assessed through the metrics Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Square Error (RMSE), demonstrated promising improvements compared to state-of-the-art techniques. The model effectively reduces noise while preserving critical fine details, establishing itself as a highly efficient solution for LDCT image denoising.
format Article
id doaj-art-ca8c98dddbd84626b750bbbca60b1b6a
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ca8c98dddbd84626b750bbbca60b1b6a2025-08-20T02:36:02ZengIEEEIEEE Access2169-35362025-01-01136909692310.1109/ACCESS.2025.352661910829953A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image DenoisingMuhammad Zubair0https://orcid.org/0000-0002-8457-0208Helmi Md Rais1https://orcid.org/0000-0002-7878-965XTalal Alazemi2Institute of Emerging Digital Technologies (EDiT), Center For Cyber Physical Systems (C2PS), Universiti Teknologi PETRONAS, Seri Iskandar, MalaysiaInstitute of Emerging Digital Technologies (EDiT), Center For Cyber Physical Systems (C2PS), Universiti Teknologi PETRONAS, Seri Iskandar, MalaysiaDepartment of Electronic Electrical Engineering, Brunel University London, Uxbridge, U.K.Computed Tomography (CT) scan, pivotal for medical diagnostics, involves exposure to electromagnetic radiation, potentially elevating the risk of leukemia and cancer. Low-dose CT (LDCT) imaging has emerged to mitigate these risks, extensively reducing radiation exposure by up to 86%. However, it significantly reduces the quality of LDCT images and introduces noise and artifacts, degrading the diagnostic accuracy of the Computer Aided Diagnostic (CAD) system. This study presents a novel U-Net architecture, featuring several key enhancements. The model integrates residual blocks to improve feature representation and employs a custom hybrid loss function that combines structural loss with gradient regularization using the Euclidean norm, promoting superior CT image quality retention. Additionally, incorporating Attention Gates in the up-sampling layers of a proposed model optimizes the extraction of critical features, ensuring more precise denoising of CT images. The proposed model undergoes iterative training, using a custom loss function to refine its parameters and improve CT image denoising progressively. Its performance is rigorously evaluated both qualitatively and quantitatively on the ‘2016 Low-dose CT AAPM Grand Challenge dataset’. The results, assessed through the metrics Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Square Error (RMSE), demonstrated promising improvements compared to state-of-the-art techniques. The model effectively reduces noise while preserving critical fine details, establishing itself as a highly efficient solution for LDCT image denoising.https://ieeexplore.ieee.org/document/10829953/Attention gatedeep learningimage enhancementLDCT image denoisingresidual blocks
spellingShingle Muhammad Zubair
Helmi Md Rais
Talal Alazemi
A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
IEEE Access
Attention gate
deep learning
image enhancement
LDCT image denoising
residual blocks
title A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
title_full A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
title_fullStr A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
title_full_unstemmed A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
title_short A Novel Attention-Guided Enhanced U-Net With Hybrid Edge-Preserving Structural Loss for Low-Dose CT Image Denoising
title_sort novel attention guided enhanced u net with hybrid edge preserving structural loss for low dose ct image denoising
topic Attention gate
deep learning
image enhancement
LDCT image denoising
residual blocks
url https://ieeexplore.ieee.org/document/10829953/
work_keys_str_mv AT muhammadzubair anovelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising
AT helmimdrais anovelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising
AT talalalazemi anovelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising
AT muhammadzubair novelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising
AT helmimdrais novelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising
AT talalalazemi novelattentionguidedenhancedunetwithhybridedgepreservingstructurallossforlowdosectimagedenoising