An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features

Abstract Image denoising is a critical problem in low-level computer vision, where the aim is to reconstruct a clean, noise-free image from a noisy input, such as a mammogram image. In recent years, deep learning, particularly convolutional neural networks (CNNs), has shown great success in various...

Full description

Saved in:
Bibliographic Details
Main Authors: A. Robert Singh, Suganya Athisayamani, Faten Khalid Karim, Ahmed Zohair Ibrahim, Sameer Alshetewi, Samih M. Mostafa
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-89451-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849767324808118272
author A. Robert Singh
Suganya Athisayamani
Faten Khalid Karim
Ahmed Zohair Ibrahim
Sameer Alshetewi
Samih M. Mostafa
author_facet A. Robert Singh
Suganya Athisayamani
Faten Khalid Karim
Ahmed Zohair Ibrahim
Sameer Alshetewi
Samih M. Mostafa
author_sort A. Robert Singh
collection DOAJ
description Abstract Image denoising is a critical problem in low-level computer vision, where the aim is to reconstruct a clean, noise-free image from a noisy input, such as a mammogram image. In recent years, deep learning, particularly convolutional neural networks (CNNs), has shown great success in various image processing tasks, including denoising, image compression, and enhancement. While CNN-based approaches dominate, Transformer models have recently gained popularity for computer vision tasks. However, there have been fewer applications of Transformer-based models to low-level vision problems like image denoising. In this study, a novel denoising network architecture called DeepTFormer is proposed, which leverages Transformer models for the task. The DeepTFormer architecture consists of three main components: a preprocessing module, a local-global feature extraction module, and a reconstruction module. The local-global feature extraction module is the core of DeepTFormer, comprising several groups of ITransformer layers. Each group includes a series of Transformer layers, convolutional layers, and residual connections. These groups are tightly coupled with residual connections, which allow the model to capture both local and global information from the noisy images effectively. The design of these groups ensures that the model can utilize both local features for fine details and global features for larger context, leading to more accurate denoising. To validate the performance of the DeepTFormer model, extensive experiments were conducted using both synthetic and real noise data. Objective and subjective evaluations demonstrated that DeepTFormer outperforms leading denoising methods. The model achieved impressive results, surpassing state-of-the-art techniques in terms of key metrics like PSNR, FSIM, EPI, and SSIM, with values of 0.41, 0.93, 0.96, and 0.94, respectively. These results demonstrate that DeepTFormer is a highly effective solution for image denoising, combining the power of Transformer architecture with convolutional layers to enhance both local and global feature extraction.
format Article
id doaj-art-db3ed38aeeb14f068681b938905eb5d3
institution DOAJ
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-db3ed38aeeb14f068681b938905eb5d32025-08-20T03:04:16ZengNature PortfolioScientific Reports2045-23222025-02-0115112010.1038/s41598-025-89451-wAn enhanced denoising system for mammogram images using deep transformer model with fusion of local and global featuresA. Robert Singh0Suganya Athisayamani1Faten Khalid Karim2Ahmed Zohair Ibrahim3Sameer Alshetewi4Samih M. Mostafa5Department of Computational Intelligence, SRM Institute of Science and TechnologySchool of Computing, Sastra Deemed to be UniversityDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityGeneral Information Technology Department, Ministry of Defense, The Executive Affairs, Excellence Services Directorate, P.O. Box 11564, 56688Computer Science Department, Faculty of Computers and Information, South Valley UniversityAbstract Image denoising is a critical problem in low-level computer vision, where the aim is to reconstruct a clean, noise-free image from a noisy input, such as a mammogram image. In recent years, deep learning, particularly convolutional neural networks (CNNs), has shown great success in various image processing tasks, including denoising, image compression, and enhancement. While CNN-based approaches dominate, Transformer models have recently gained popularity for computer vision tasks. However, there have been fewer applications of Transformer-based models to low-level vision problems like image denoising. In this study, a novel denoising network architecture called DeepTFormer is proposed, which leverages Transformer models for the task. The DeepTFormer architecture consists of three main components: a preprocessing module, a local-global feature extraction module, and a reconstruction module. The local-global feature extraction module is the core of DeepTFormer, comprising several groups of ITransformer layers. Each group includes a series of Transformer layers, convolutional layers, and residual connections. These groups are tightly coupled with residual connections, which allow the model to capture both local and global information from the noisy images effectively. The design of these groups ensures that the model can utilize both local features for fine details and global features for larger context, leading to more accurate denoising. To validate the performance of the DeepTFormer model, extensive experiments were conducted using both synthetic and real noise data. Objective and subjective evaluations demonstrated that DeepTFormer outperforms leading denoising methods. The model achieved impressive results, surpassing state-of-the-art techniques in terms of key metrics like PSNR, FSIM, EPI, and SSIM, with values of 0.41, 0.93, 0.96, and 0.94, respectively. These results demonstrate that DeepTFormer is a highly effective solution for image denoising, combining the power of Transformer architecture with convolutional layers to enhance both local and global feature extraction.https://doi.org/10.1038/s41598-025-89451-wTransformerDenoisingGlobal featuresLocal featuresMammogram
spellingShingle A. Robert Singh
Suganya Athisayamani
Faten Khalid Karim
Ahmed Zohair Ibrahim
Sameer Alshetewi
Samih M. Mostafa
An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
Scientific Reports
Transformer
Denoising
Global features
Local features
Mammogram
title An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
title_full An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
title_fullStr An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
title_full_unstemmed An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
title_short An enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
title_sort enhanced denoising system for mammogram images using deep transformer model with fusion of local and global features
topic Transformer
Denoising
Global features
Local features
Mammogram
url https://doi.org/10.1038/s41598-025-89451-w
work_keys_str_mv AT arobertsingh anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT suganyaathisayamani anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT fatenkhalidkarim anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT ahmedzohairibrahim anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT sameeralshetewi anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT samihmmostafa anenhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT arobertsingh enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT suganyaathisayamani enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT fatenkhalidkarim enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT ahmedzohairibrahim enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT sameeralshetewi enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures
AT samihmmostafa enhanceddenoisingsystemformammogramimagesusingdeeptransformermodelwithfusionoflocalandglobalfeatures