EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Disease-specific data augmentation enhances deep learning classification of age-related macular degeneration, diabetic retinopathy, and glaucoma

Carl Halladay Abraham, Emmanuel Kwasi Abu, Paul Owusu iD, Thomas Osei Mensah, Ebenezer Botchway, Philip Abakah Mensah, Albert Kofi Dadzie, Samuel Kyei iD

DIGITAL HEALTH · 2026-02 · 12

DOI: 10.1177/20552076261461391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 22.06.2026. Verfasst von Carl Halladay Abraham und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmic Science, School of Optometry and Vision Science, College of Health and Allied Sciences, University of Cape Coast, Cape Coast…. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To determine which data augmentation technique yields the best performance for deep learning models in classifying age-related macular degeneration (AMD), diabetic retinopathy (DR), glaucoma, and normal fundus images.

Methods

This study employed an in silico experimental study design. Six data augmentation techniques: Colour Jitter, Contrast-Limited Adaptive Histogram Equalisation (CLAHE), Rotation, Translation, Gaussian Noise, and Poisson Noise were evaluated using controlled experiments with an EfficientNet-B0 model on a balanced dataset of 1,200 fundus photographs, 250 cases each for AMD, DR and glaucoma, and 450 normal fundus images curated from four main publicly available databases. The experiments were conducted in four phases: baseline, single augmentations, combined augmentations, and the impact of augmented dataset volume. Evaluation metrics and visualisations were computed with Python-based statistical and visualisation libraries.

Results

The results from this study show that data augmentation consistently increased the area under the curve (AUC) from 96.55% to 97.23% and accuracy from 85.83% (baseline) to 89.58%. The results indicate that augmentation effectiveness is disease-specific: Rotation and Colour Jitter yielded the highest sensitivity for AMD (99%), CLAHE maximised sensitivity for Diabetic Retinopathy (96%), and Translation was most effective for Glaucoma (83%). While single augmentations provided descriptive clinical improvements, the comprehensive combination of photometric, geometric, and noise augmentations yielded the best overall performance and achieved a statistically significant improvement over the baseline (Mean bootstrapped AUC = 0.9800, 95% CI: 0.9678, 0.9895; p = 0.0050).

Conclusion

Data augmentation effectiveness is disease-dependent; specific pathologies respond better to distinct augmentation techniques due to different retinal biomarkers.

Schlagwörter

Stichwörter der Autor:innen

age-related macular degenerationdata augmentationdeep learningdiabetic retinopathyglaucoma

Autor:innen und Institutionen

  • Department of Ophthalmic Science, School of Optometry and Vision Science, College of Health and Allied Sciences, University of Cape Coast, Cape Coast, Ghana.
  • Department of Vision Science, School of Optometry and Vision Science, College of Health and Allied Sciences, University of Cape Coast, Cape Coast, Ghana.
  • Department of Biomedical Engineering, University of Illinois Chicago, Chicago, IL, USA.
  • Biomedical and Clinical Research Centre, College of Health and Allied Sciences, University of Cape Coast, Cape Coast, Ghana.

ORCID-Profile: Paul Owusu, Samuel Kyei

Zitieren

APA

Abraham, C. H., Abu, E. K., Owusu, P., Mensah, T. O., Botchway, E., Mensah, P. A., Dadzie, A. K., & Kyei, S. (2026). Disease-specific data augmentation enhances deep learning classification of age-related macular degeneration, diabetic retinopathy, and glaucoma. DIGITAL HEALTH, 12. https://doi.org/10.1177/20552076261461391

Vancouver

Abraham CH, Abu EK, Owusu P, Mensah TO, Botchway E, Mensah PA, et al. Disease-specific data augmentation enhances deep learning classification of age-related macular degeneration, diabetic retinopathy, and glaucoma. DIGITAL HEALTH. 2026;12. doi:10.1177/20552076261461391

BibTeX
@article{Abraham2026,
  author = {Abraham, Carl Halladay and Abu, Emmanuel Kwasi and Owusu, Paul and Mensah, Thomas Osei and Botchway, Ebenezer and Mensah, Philip Abakah and Dadzie, Albert Kofi and Kyei, Samuel},
  title = {Disease-specific data augmentation enhances deep learning classification of age-related macular degeneration, diabetic retinopathy, and glaucoma},
  journal = {DIGITAL HEALTH},
  year = {2026},
  volume = {12},
  doi = {10.1177/20552076261461391}
}
Kostenlos starten →