Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis
Early diagnosis and effective treatment of age-related macular degeneration (AMD), a leading cause of vision impairment, are critically dependent on accurate grading. This paper presents a novel framework, named Mask-UnMask Regions (MUMR), designed to differentiate between normal retina, intermediat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10833638/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536174013808640 |
|---|---|
| author | Ibrahim Abdelhalim Namuunaa Nadmid Mohamed Elsharkawy Mohammed Ghazal Ali H. Mahmoud Ayman El-Baz |
| author_facet | Ibrahim Abdelhalim Namuunaa Nadmid Mohamed Elsharkawy Mohammed Ghazal Ali H. Mahmoud Ayman El-Baz |
| author_sort | Ibrahim Abdelhalim |
| collection | DOAJ |
| description | Early diagnosis and effective treatment of age-related macular degeneration (AMD), a leading cause of vision impairment, are critically dependent on accurate grading. This paper presents a novel framework, named Mask-UnMask Regions (MUMR), designed to differentiate between normal retina, intermediate AMD, geographic atrophy (GA), and wet AMD using standardized retinal fundus images with an input resolution of <inline-formula> <tex-math notation="LaTeX">$1024 \times 1024$ </tex-math></inline-formula> pixels. The framework initiates with the downscaling of images to a quarter of their original size via a Preserving High-Frequency Information (PHFI) module, which retains key details essential for further analysis. Additionally, we developed a simple, lightweight, yet efficient ResNet-like network for feature extraction and introduced a Region Interaction (RI) module. This module incorporates Adaptive Mask and UnMask Sub-Modules, identifying significant regions while reconstructing less relevant areas using a direction-constrained self-attention mechanism to ensure the learning of global structural cues critical for AMD grade classification. The proposed method was evaluated on a dataset comprising 864 retinal fundus images. Our model consistently outperforms state-of-the-art approaches, achieving mean accuracy, mean F1-score, and mean Cohen’s Kappa of 92.55%, 92.59%, and 89.97%, respectively. In the binary classification task of distinguishing between Non-AMD and AMD cases, the proposed approach also surpasses competing models, achieving mean accuracy, mean F1-score, and mean Cohen’s Kappa of 97.11%, 97.03%, and 94.06%, respectively. Furthermore, statistical analysis of these metrics confirms that the improvements are statistically significant, demonstrating the robustness and improved performance of our proposed framework in AMD grading. |
| format | Article |
| id | doaj-art-59e1ad47c59547b2b12ab88afd7477c0 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-59e1ad47c59547b2b12ab88afd7477c02025-01-15T00:03:05ZengIEEEIEEE Access2169-35362025-01-01138286829610.1109/ACCESS.2025.352694810833638Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction AnalysisIbrahim Abdelhalim0https://orcid.org/0009-0000-1544-7276Namuunaa Nadmid1Mohamed Elsharkawy2https://orcid.org/0000-0001-9242-9709Mohammed Ghazal3https://orcid.org/0000-0002-9045-6698Ali H. Mahmoud4https://orcid.org/0000-0003-2557-9699Ayman El-Baz5https://orcid.org/0000-0001-7264-1323Department of Bioengineering, University of Louisville, Louisville, KY, USADepartment of Bioengineering, University of Louisville, Louisville, KY, USADepartment of Bioengineering, University of Louisville, Louisville, KY, USAElectrical and Computer Engineering Department, Abu Dhabi University, Abu Dhabi, United Arab EmiratesDepartment of Bioengineering, University of Louisville, Louisville, KY, USADepartment of Bioengineering, University of Louisville, Louisville, KY, USAEarly diagnosis and effective treatment of age-related macular degeneration (AMD), a leading cause of vision impairment, are critically dependent on accurate grading. This paper presents a novel framework, named Mask-UnMask Regions (MUMR), designed to differentiate between normal retina, intermediate AMD, geographic atrophy (GA), and wet AMD using standardized retinal fundus images with an input resolution of <inline-formula> <tex-math notation="LaTeX">$1024 \times 1024$ </tex-math></inline-formula> pixels. The framework initiates with the downscaling of images to a quarter of their original size via a Preserving High-Frequency Information (PHFI) module, which retains key details essential for further analysis. Additionally, we developed a simple, lightweight, yet efficient ResNet-like network for feature extraction and introduced a Region Interaction (RI) module. This module incorporates Adaptive Mask and UnMask Sub-Modules, identifying significant regions while reconstructing less relevant areas using a direction-constrained self-attention mechanism to ensure the learning of global structural cues critical for AMD grade classification. The proposed method was evaluated on a dataset comprising 864 retinal fundus images. Our model consistently outperforms state-of-the-art approaches, achieving mean accuracy, mean F1-score, and mean Cohen’s Kappa of 92.55%, 92.59%, and 89.97%, respectively. In the binary classification task of distinguishing between Non-AMD and AMD cases, the proposed approach also surpasses competing models, achieving mean accuracy, mean F1-score, and mean Cohen’s Kappa of 97.11%, 97.03%, and 94.06%, respectively. Furthermore, statistical analysis of these metrics confirms that the improvements are statistically significant, demonstrating the robustness and improved performance of our proposed framework in AMD grading.https://ieeexplore.ieee.org/document/10833638/Age-related macular degenerationretinal diseasesdeep learningtransformer |
| spellingShingle | Ibrahim Abdelhalim Namuunaa Nadmid Mohamed Elsharkawy Mohammed Ghazal Ali H. Mahmoud Ayman El-Baz Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis IEEE Access Age-related macular degeneration retinal diseases deep learning transformer |
| title | Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis |
| title_full | Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis |
| title_fullStr | Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis |
| title_full_unstemmed | Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis |
| title_short | Mask-UnMask Regions (MUMR) Framework for Classifying AMD Grades Using Inter-Regional Interaction Analysis |
| title_sort | mask unmask regions mumr framework for classifying amd grades using inter regional interaction analysis |
| topic | Age-related macular degeneration retinal diseases deep learning transformer |
| url | https://ieeexplore.ieee.org/document/10833638/ |
| work_keys_str_mv | AT ibrahimabdelhalim maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis AT namuunaanadmid maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis AT mohamedelsharkawy maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis AT mohammedghazal maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis AT alihmahmoud maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis AT aymanelbaz maskunmaskregionsmumrframeworkforclassifyingamdgradesusinginterregionalinteractionanalysis |