Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging
Age-related macular degeneration (AMD) is a leading cause of vision loss in older people and is characterized by subtle retinal changes that make early identification difficult. Previous studies have demonstrated the efficacy of Vision Transformers (ViTs) in classifying medical images by successfull...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815928/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563397509873664 |
|---|---|
| author | Ainhoa Osa-Sanchez Hossam Magdy Balaha Ali Mahmoud Ashraf Sewelam Mohammed Ghazal Begonya Garcia-Zapirain Ayman El-Baz |
| author_facet | Ainhoa Osa-Sanchez Hossam Magdy Balaha Ali Mahmoud Ashraf Sewelam Mohammed Ghazal Begonya Garcia-Zapirain Ayman El-Baz |
| author_sort | Ainhoa Osa-Sanchez |
| collection | DOAJ |
| description | Age-related macular degeneration (AMD) is a leading cause of vision loss in older people and is characterized by subtle retinal changes that make early identification difficult. Previous studies have demonstrated the efficacy of Vision Transformers (ViTs) in classifying medical images by successfully detecting retinal disorders such as AMD. This paper addresses multiple shortcomings in conventional AMD diagnostic techniques by exploring the detection and explanation of various AMD subtypes from numerical features extracted with a ViT model from fundus images through cascaded artificial intelligence (AI) models using transformers, convolutional neural networks (CNNs), and multilayer perceptrons (MLPs). The data were preprocessed to recognize intricate disease-related patterns. The best test results using the cascade method for each model type show that the MLP model achieved an accuracy of 91.86% (with a sensitivity of 92.22% and a specificity of 95.74%). The Transformer model achieved its highest accuracy of 83.72% (with a sensitivity of 83.86% and a specificity of 89.74%). The CNN model demonstrated the best performance, with an accuracy of 94.19% (with a sensitivity of 93.84% and a specificity of 96.00%). This work helps clinicians interpret AMD cases and supports decision-making revealing hidden features of AMD that are not visible to the human eye. Future research will focus on improving these systems by expanding the databases in aggregate and incorporating multimodal data. |
| format | Article |
| id | doaj-art-d81ea96e3ad44e738a8844cd11070c91 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d81ea96e3ad44e738a8844cd11070c912025-01-03T00:01:33ZengIEEEIEEE Access2169-35362025-01-011334136010.1109/ACCESS.2024.352286210815928Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus ImagingAinhoa Osa-Sanchez0https://orcid.org/0000-0001-5871-168XHossam Magdy Balaha1https://orcid.org/0000-0002-0686-4411Ali Mahmoud2https://orcid.org/0000-0003-2557-9699Ashraf Sewelam3Mohammed Ghazal4https://orcid.org/0000-0002-9045-6698Begonya Garcia-Zapirain5https://orcid.org/0000-0002-9356-1186Ayman El-Baz6https://orcid.org/0000-0001-7264-1323Department of Bioengineering, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USADepartment of Bioengineering, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USADepartment of Bioengineering, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAOphthalmology Department, Faculty of Medicine, Mansoura University, Mansoura, Egyptand Biomedical Engineering Department, Electrical, Computer, Abu Dhabi University, Abu Dhabi, United Arab EmirateseVIDA Research Group, University of Deusto, Bilbao, SpainDepartment of Bioengineering, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAAge-related macular degeneration (AMD) is a leading cause of vision loss in older people and is characterized by subtle retinal changes that make early identification difficult. Previous studies have demonstrated the efficacy of Vision Transformers (ViTs) in classifying medical images by successfully detecting retinal disorders such as AMD. This paper addresses multiple shortcomings in conventional AMD diagnostic techniques by exploring the detection and explanation of various AMD subtypes from numerical features extracted with a ViT model from fundus images through cascaded artificial intelligence (AI) models using transformers, convolutional neural networks (CNNs), and multilayer perceptrons (MLPs). The data were preprocessed to recognize intricate disease-related patterns. The best test results using the cascade method for each model type show that the MLP model achieved an accuracy of 91.86% (with a sensitivity of 92.22% and a specificity of 95.74%). The Transformer model achieved its highest accuracy of 83.72% (with a sensitivity of 83.86% and a specificity of 89.74%). The CNN model demonstrated the best performance, with an accuracy of 94.19% (with a sensitivity of 93.84% and a specificity of 96.00%). This work helps clinicians interpret AMD cases and supports decision-making revealing hidden features of AMD that are not visible to the human eye. Future research will focus on improving these systems by expanding the databases in aggregate and incorporating multimodal data.https://ieeexplore.ieee.org/document/10815928/Age-related macular degeneration (AMD)computer aided diagnosis (CAD)deep learning (DL)eXplainable artificial intelligence (XAI) |
| spellingShingle | Ainhoa Osa-Sanchez Hossam Magdy Balaha Ali Mahmoud Ashraf Sewelam Mohammed Ghazal Begonya Garcia-Zapirain Ayman El-Baz Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging IEEE Access Age-related macular degeneration (AMD) computer aided diagnosis (CAD) deep learning (DL) eXplainable artificial intelligence (XAI) |
| title | Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging |
| title_full | Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging |
| title_fullStr | Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging |
| title_full_unstemmed | Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging |
| title_short | Explainable AI-Based Approach for Age-Related Macular Degeneration (AMD) Detection via Fundus Imaging |
| title_sort | explainable ai based approach for age related macular degeneration amd detection via fundus imaging |
| topic | Age-related macular degeneration (AMD) computer aided diagnosis (CAD) deep learning (DL) eXplainable artificial intelligence (XAI) |
| url | https://ieeexplore.ieee.org/document/10815928/ |
| work_keys_str_mv | AT ainhoaosasanchez explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT hossammagdybalaha explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT alimahmoud explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT ashrafsewelam explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT mohammedghazal explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT begonyagarciazapirain explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging AT aymanelbaz explainableaibasedapproachforagerelatedmaculardegenerationamddetectionviafundusimaging |