Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging

Age-related macular degeneration (AMD) is a prevalent retinal disorder in the elderly, often leading to significant vision impairment. The diagnosis of AMD is confirmed through various medical imaging modalities, with color fundus photography (CFP) being a primary tool. The detection and staging of...

Full description

Saved in:
Bibliographic Details
Main Authors: Niveen Nasr El-Den, Mohamed Elsharkawy, Ibrahim Saleh, Ali H. Mahmoud, Mohammed Ghazal, Ashraf Khalil, Ashraf Sewelam, Hani Mahdi, Ayman El-Baz
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10967262/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311163667447808
author Niveen Nasr El-Den
Mohamed Elsharkawy
Ibrahim Saleh
Ali H. Mahmoud
Mohammed Ghazal
Ashraf Khalil
Ashraf Sewelam
Hani Mahdi
Ayman El-Baz
author_facet Niveen Nasr El-Den
Mohamed Elsharkawy
Ibrahim Saleh
Ali H. Mahmoud
Mohammed Ghazal
Ashraf Khalil
Ashraf Sewelam
Hani Mahdi
Ayman El-Baz
author_sort Niveen Nasr El-Den
collection DOAJ
description Age-related macular degeneration (AMD) is a prevalent retinal disorder in the elderly, often leading to significant vision impairment. The diagnosis of AMD is confirmed through various medical imaging modalities, with color fundus photography (CFP) being a primary tool. The detection and staging of AMD severity depend on several factors, including the number and size of drusen, the presence of pigmentary changes, geographic atrophy, and neovascularization, all of which are identifiable through CFP. In this study, we introduce an innovative dual-vision transformer-based network designed to automatically detect AMD and classify its severity into either dry AMD or wet AMD using CFP. Early diagnosis and accurate staging of AMD are crucial in mitigating the progression of the disease, making this work particularly valuable. Our proposed model, Seg-Swin, leverages a dual attention-based transformer network architecture, comprising two key stages. The first stage employs the SegFormer transformer model for the precise detection of AMD-related lesions, while the second stage utilizes the Swin transformer model to classify the detected lesions into dry or wet AMD. Our extensive experimental results demonstrate that the Seg-Swin model outperforms existing approaches, achieving remarkable diagnostic accuracy with metrics such as 98.7% accuracy, 99% sensitivity, 97.95% F1-score, and 98.24% specificity. By combining the strengths of advanced transformer models in both identification and classification tasks, the Seg-Swin model offers a comprehensive and powerful solution for detecting and staging AMD. The integration of these dual attention mechanisms allows the model to more precisely interpret complex retinal images, which is crucial for early diagnosis and accurate staging of AMD.
format Article
id doaj-art-6f9cf9d0179740f19ca7db814338bab2
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-6f9cf9d0179740f19ca7db814338bab22025-08-20T03:53:28ZengIEEEIEEE Access2169-35362025-01-0113704897051110.1109/ACCESS.2025.356213510967262Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus ImagingNiveen Nasr El-Den0https://orcid.org/0009-0008-3268-3172Mohamed Elsharkawy1https://orcid.org/0000-0001-9242-9709Ibrahim Saleh2https://orcid.org/0009-0005-7753-6625Ali H. Mahmoud3https://orcid.org/0000-0003-2557-9699Mohammed Ghazal4https://orcid.org/0000-0002-9045-6698Ashraf Khalil5https://orcid.org/0000-0003-1584-8525Ashraf Sewelam6Hani Mahdi7Ayman El-Baz8https://orcid.org/0000-0001-7264-1323Department of Computer and System Engineering, Faculty of Engineering, Ain Shams University, Cairo, EgyptDepartment of Bioengineering, University of Louisville, Louisville, KY, USADepartment of Ophthalmology and Visual Sciences, University of Maryland School of Medicine, Baltimore, MD, USADepartment of Bioengineering, University of Louisville, Louisville, KY, USADepartment of Electrical and Computer Engineering, Abu Dhabi University, Abu Dhabi, United Arab EmiratesCollege of Technological Innovation, Zayed University, Abu Dhabi, United Arab EmiratesDepartment of Ophthalmology, Faculty of Medicine, Mansoura University, Mansoura, EgyptDepartment of Computer and System Engineering, Faculty of Engineering, Ain Shams University, Cairo, EgyptDepartment of Bioengineering, University of Louisville, Louisville, KY, USAAge-related macular degeneration (AMD) is a prevalent retinal disorder in the elderly, often leading to significant vision impairment. The diagnosis of AMD is confirmed through various medical imaging modalities, with color fundus photography (CFP) being a primary tool. The detection and staging of AMD severity depend on several factors, including the number and size of drusen, the presence of pigmentary changes, geographic atrophy, and neovascularization, all of which are identifiable through CFP. In this study, we introduce an innovative dual-vision transformer-based network designed to automatically detect AMD and classify its severity into either dry AMD or wet AMD using CFP. Early diagnosis and accurate staging of AMD are crucial in mitigating the progression of the disease, making this work particularly valuable. Our proposed model, Seg-Swin, leverages a dual attention-based transformer network architecture, comprising two key stages. The first stage employs the SegFormer transformer model for the precise detection of AMD-related lesions, while the second stage utilizes the Swin transformer model to classify the detected lesions into dry or wet AMD. Our extensive experimental results demonstrate that the Seg-Swin model outperforms existing approaches, achieving remarkable diagnostic accuracy with metrics such as 98.7% accuracy, 99% sensitivity, 97.95% F1-score, and 98.24% specificity. By combining the strengths of advanced transformer models in both identification and classification tasks, the Seg-Swin model offers a comprehensive and powerful solution for detecting and staging AMD. The integration of these dual attention mechanisms allows the model to more precisely interpret complex retinal images, which is crucial for early diagnosis and accurate staging of AMD.https://ieeexplore.ieee.org/document/10967262/AMD classificationfundus photographylesion detectionneovascular AMDdry AMDSegFormer
spellingShingle Niveen Nasr El-Den
Mohamed Elsharkawy
Ibrahim Saleh
Ali H. Mahmoud
Mohammed Ghazal
Ashraf Khalil
Ashraf Sewelam
Hani Mahdi
Ayman El-Baz
Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
IEEE Access
AMD classification
fundus photography
lesion detection
neovascular AMD
dry AMD
SegFormer
title Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
title_full Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
title_fullStr Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
title_full_unstemmed Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
title_short Seg-Swin: A Dual-Attention Transformer Model for Advanced AMD Classification and Lesion Detection Using Color Fundus Imaging
title_sort seg swin a dual attention transformer model for advanced amd classification and lesion detection using color fundus imaging
topic AMD classification
fundus photography
lesion detection
neovascular AMD
dry AMD
SegFormer
url https://ieeexplore.ieee.org/document/10967262/
work_keys_str_mv AT niveennasrelden segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT mohamedelsharkawy segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT ibrahimsaleh segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT alihmahmoud segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT mohammedghazal segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT ashrafkhalil segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT ashrafsewelam segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT hanimahdi segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging
AT aymanelbaz segswinadualattentiontransformermodelforadvancedamdclassificationandlesiondetectionusingcolorfundusimaging