Glaucoma Classification Using a NFNet-Based Deep Learning Model with a Customized Hybrid Attention Mechanism
Diagnostics · 09.03.2026 · 16 (5) · 815
DOI: 10.3390/diagnostics16050815 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 09.03.2026. Verfasst von Sandeep Angara und 2 weiteren Autor:innen. Beteiligte Einrichtung: Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, MD 20892, USA. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lister Hill National Center for Biomedical Communications of the National Library of Medicine, National Institutes of Health, U.S. Department of Health and Human Services.
Abstract (Originalsprache)
Background/Objectives: Glaucoma is a leading cause of irreversible blindness worldwide, making accurate and efficient detection methods essential. One primary concern with glaucoma is that it often presents no early symptoms. Vision loss typically begins at the periphery and progresses unnoticed until it significantly affects central vision. Due to this gradual and usually silent progression, early detection through regular eye exams is vital for preventing permanent vision loss.
Methods
In this study, we propose a hybrid attention mechanism that recalibrates feature maps from the feature extractor for glaucoma detection. We explored normalization-free ResNet (NF-ResNet) architectures to evaluate the proposed attention mechanism, specifically NF-ResNet-26, NF-ResNet-50, and NF-ResNet-101, in comparison to baseline state-of-the-art ResNet variants. Our approach was evaluated on three publicly available glaucoma datasets, LAG, EyePACS, and BrG, to differentiate between normal and glaucomatous from fundus images.
Results
The experimental results demonstrate that our proposed hybrid attention module, combined with normalization-free architectures, significantly enhances performance compared to state-of-the-art ResNet variants. The proposed attention model based on the normalization-free ResNet-50 achieved an accuracy of 0.9394 on the LAG dataset, 0.9117 on the EyePACS dataset, and 0.9020 on the BrG dataset. When evaluated on the combined dataset, the model achieved an accuracy of 0.9193, sensitivity of 0.9182, and specificity of 0.9202.
Conclusions
The results from these representative datasets for glaucoma detection highlight the exceptional performance of our attention module, establishing it as a highly competitive classification model in the field of glaucoma detection.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, MD 20892, USA.
ORCID-Profile: Sandeep Angara, Loc Tran, Jongwoo Kim
Förderung
- Lister Hill National Center for Biomedical Communications of the National Library of Medicine
- National Institutes of Health
- U.S. Department of Health and Human Services
Zitieren
APA
Angara, S., Tran, L., & Kim, J. (2026). Glaucoma Classification Using a NFNet-Based Deep Learning Model with a Customized Hybrid Attention Mechanism. Diagnostics, 16(5), 815. https://doi.org/10.3390/diagnostics16050815
Vancouver
Angara S, Tran L, Kim J. Glaucoma Classification Using a NFNet-Based Deep Learning Model with a Customized Hybrid Attention Mechanism. Diagnostics. 2026;16(5):815. doi:10.3390/diagnostics16050815
BibTeX
@article{Angara2026,
author = {Angara, Sandeep and Tran, Loc and Kim, Jongwoo},
title = {Glaucoma Classification Using a NFNet-Based Deep Learning Model with a Customized Hybrid Attention Mechanism},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {5},
pages = {815},
doi = {10.3390/diagnostics16050815}
}
EUVIMED