XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging

Age-related macular degeneration (AMD) is a leading cause of visual impairment in adults over 50 years of age and is characterized by progressive damage to the macula, leading to challenges in daily activities such as reading and driving. This study introduces the XV-AMD (An Explainable Vision Trans...

Full description

Saved in:
Bibliographic Details
Main Authors: Aya A. Abd El-Khalek, Hossam Magdy Balaha, Mohamed T. Azam, Ashraf Sewelam, Mohammed Ghazal, Abeer T. Khalil, Mohy Eldin A. Abo-Elsoud, Ayman El-Baz
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11052213/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320329334226944
author Aya A. Abd El-Khalek
Hossam Magdy Balaha
Mohamed T. Azam
Ashraf Sewelam
Mohammed Ghazal
Abeer T. Khalil
Mohy Eldin A. Abo-Elsoud
Ayman El-Baz
author_facet Aya A. Abd El-Khalek
Hossam Magdy Balaha
Mohamed T. Azam
Ashraf Sewelam
Mohammed Ghazal
Abeer T. Khalil
Mohy Eldin A. Abo-Elsoud
Ayman El-Baz
author_sort Aya A. Abd El-Khalek
collection DOAJ
description Age-related macular degeneration (AMD) is a leading cause of visual impairment in adults over 50 years of age and is characterized by progressive damage to the macula, leading to challenges in daily activities such as reading and driving. This study introduces the XV-AMD (An Explainable Vision Transformer Detection for Age-Related Macular Degeneration) framework, which uses Vision Transformers (ViTs) and SHapley Additive exPlanations (SHAPs) for the diagnosis and explainability of AMD. Through a systematic preprocessing pipeline, including average cumulative distribution function (CDF) calculation and contrast limited adaptive histogram equalization (CLAHE), our approach enhances image quality and prepares data for analysis. We classify color fundus images into four distinct AMD categories, namely, normal, geographic atrophy (GA), intermediate AMD, and wet AMD, demonstrating the framework’s effectiveness in a clinical context. The experimental results reveal that our ViT-based model not only improves diagnostic accuracy but also facilitates the understanding of decision-making processes, thus supporting early detection and intervention strategies in AMD management. In addition, a 99.54% classification accuracy was attained, with a sensitivity of 99.54%, specificity of 99.85%, precision of 99.54%, and F1 of 99.54%. This research shows the promise of AI and deep learning in improving AMD diagnoses and identifies future paths for boosting model performance and interpretability in medical imaging applications.
format Article
id doaj-art-457a0239b3f54d2eb46c3b5cfdf10565
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-457a0239b3f54d2eb46c3b5cfdf105652025-08-20T03:50:07ZengIEEEIEEE Access2169-35362025-01-011311396711398310.1109/ACCESS.2025.358355511052213XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus ImagingAya A. Abd El-Khalek0Hossam Magdy Balaha1https://orcid.org/0000-0002-0686-4411Mohamed T. Azam2Ashraf Sewelam3Mohammed Ghazal4https://orcid.org/0000-0002-9045-6698Abeer T. Khalil5Mohy Eldin A. Abo-Elsoud6Ayman El-Baz7https://orcid.org/0000-0001-7264-1323Communications and Electronics Engineering Department, Nile Higher Institute for Engineering and Technology, Mansoura, EgyptBioengineering Department, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USABioengineering Department, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAOphthalmology Department, Faculty of Medicine, Mansoura University, Mansoura, EgyptElectrical, Computer, and Biomedical Engineering Department, Abu Dhabi University, Abu Dhabi, United Arab EmiratesCommunications and Electronics Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptCommunications and Electronics Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, EgyptBioengineering Department, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAAge-related macular degeneration (AMD) is a leading cause of visual impairment in adults over 50 years of age and is characterized by progressive damage to the macula, leading to challenges in daily activities such as reading and driving. This study introduces the XV-AMD (An Explainable Vision Transformer Detection for Age-Related Macular Degeneration) framework, which uses Vision Transformers (ViTs) and SHapley Additive exPlanations (SHAPs) for the diagnosis and explainability of AMD. Through a systematic preprocessing pipeline, including average cumulative distribution function (CDF) calculation and contrast limited adaptive histogram equalization (CLAHE), our approach enhances image quality and prepares data for analysis. We classify color fundus images into four distinct AMD categories, namely, normal, geographic atrophy (GA), intermediate AMD, and wet AMD, demonstrating the framework’s effectiveness in a clinical context. The experimental results reveal that our ViT-based model not only improves diagnostic accuracy but also facilitates the understanding of decision-making processes, thus supporting early detection and intervention strategies in AMD management. In addition, a 99.54% classification accuracy was attained, with a sensitivity of 99.54%, specificity of 99.85%, precision of 99.54%, and F1 of 99.54%. This research shows the promise of AI and deep learning in improving AMD diagnoses and identifies future paths for boosting model performance and interpretability in medical imaging applications.https://ieeexplore.ieee.org/document/11052213/Deep learning (DL)computer aided diagnosis (CAD)eXplainable artificial intelligence (XAI)age-related macular degeneration (AMD)
spellingShingle Aya A. Abd El-Khalek
Hossam Magdy Balaha
Mohamed T. Azam
Ashraf Sewelam
Mohammed Ghazal
Abeer T. Khalil
Mohy Eldin A. Abo-Elsoud
Ayman El-Baz
XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
IEEE Access
Deep learning (DL)
computer aided diagnosis (CAD)
eXplainable artificial intelligence (XAI)
age-related macular degeneration (AMD)
title XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
title_full XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
title_fullStr XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
title_full_unstemmed XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
title_short XV-AMD: An Explainable Vision Transformer Detection Framework for Age-Related Macular Degeneration Using Fundus Imaging
title_sort xv amd an explainable vision transformer detection framework for age related macular degeneration using fundus imaging
topic Deep learning (DL)
computer aided diagnosis (CAD)
eXplainable artificial intelligence (XAI)
age-related macular degeneration (AMD)
url https://ieeexplore.ieee.org/document/11052213/
work_keys_str_mv AT ayaaabdelkhalek xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT hossammagdybalaha xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT mohamedtazam xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT ashrafsewelam xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT mohammedghazal xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT abeertkhalil xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT mohyeldinaaboelsoud xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging
AT aymanelbaz xvamdanexplainablevisiontransformerdetectionframeworkforagerelatedmaculardegenerationusingfundusimaging