EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated retinal disease classification using deep learning and AlexNet with statistical models analysis

El-Sayed M Elkenawy, Nima Khodadadi iD, Khaled Sh Gaber, Ehsan Khodadadi iD, Amel Ali Alhussan, Doaa Sami Khafaga, Marwa M Eid

PLOS One · 06.01.2026 · 21 (1) · e0338415

DOI: 10.1371/journal.pone.0338415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.01.2026. Verfasst von El-Sayed M Elkenawy und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Communications and Electronics, Delta Higher Institute of Engineering and Technology, Mansoura, Egypt. Hauptthemen laut MEDLINE: Deep Learning, Retinal Diseases. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic Retinopathy, Cataract, and Glaucoma are major retinal diseases that require early detection to prevent irreversible vision loss. This study proposes a deep learning-based framework for the automated classification of retinal images into four categories: Normal, Diabetic Retinopathy, Cataract, and Glaucoma. The dataset was compiled from publicly available retinal imaging databases, including IDRiD and HRF. Four convolutional neural network architectures—EfficientNet-B0, EfficientNet-B7, a build-from-scratch model, and AlexNet—were evaluated using multiple performance metrics. Among these, AlexNet achieved the highest overall performance, attaining an accuracy of 93.65%, sensitivity of 94.39%, specificity of 98.05%, PPV of 93.65%, NPV of 97.95%, and an F1-score of 93.74%. EfficientNet-B7 followed with an accuracy of 92.82%, confirming the strength of transfer learning in retinal feature extraction. A five-fold cross-validation further validated AlexNet’s robustness, yielding a mean R 2 of 0.8891 with low variance, indicating consistent generalization across folds. Computational efficiency analysis showed that AlexNet achieved high diagnostic accuracy with a moderate processing time of approximately 14 minutes. Model interpretability using SHapley Additive exPlanations (SHAP) revealed that AlexNet highlighted clinically relevant retinal regions, such as the optic disc and macula, thereby enhancing transparency and clinical trust. In summary, the proposed framework demonstrates that interpretable deep learning models can deliver accurate, consistent, and explainable retinal disease classification, offering a foundation for real-time, AI-assisted ophthalmic screening systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRetinal DiseasesHumansDiabetic RetinopathyNeural Networks, ComputerModels, StatisticalGlaucomaRetinaDatabases, FactualCataractConvolutional Neural Networks

Autor:innen und Institutionen

  • Department of Communications and Electronics, Delta Higher Institute of Engineering and Technology, Mansoura, Egypt.
  • Applied Science Research Center. Applied Science Private University, Amman, Jordan.
  • Department of Civil, Architectural and Environmental Engineering, University of Miami, Coral Gables, Florida, United States of America.
  • Computer Science and Intelligent Systems Research Center, Blacksburg, Virginia, United States of America.
  • Department of Chemistry and Biochemistry, University of Arkansas, Fayetteville, Arkansas, United States of America.
  • Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.

ORCID-Profile: Nima Khodadadi, Ehsan Khodadadi

Zitieren

APA

Elkenawy, E. M., Khodadadi, N., Gaber, K. S., Khodadadi, E., Alhussan, A. A., Khafaga, D. S., & Eid, M. M. (2026). Automated retinal disease classification using deep learning and AlexNet with statistical models analysis. PLOS One, 21(1), e0338415. https://doi.org/10.1371/journal.pone.0338415

Vancouver

Elkenawy EM, Khodadadi N, Gaber KS, Khodadadi E, Alhussan AA, Khafaga DS, et al. Automated retinal disease classification using deep learning and AlexNet with statistical models analysis. PLOS One. 2026;21(1):e0338415. doi:10.1371/journal.pone.0338415

BibTeX
@article{Elkenawy2026,
  author = {Elkenawy, El-Sayed M and Khodadadi, Nima and Gaber, Khaled Sh and Khodadadi, Ehsan and Alhussan, Amel Ali and Khafaga, Doaa Sami and Eid, Marwa M},
  title = {Automated retinal disease classification using deep learning and AlexNet with statistical models analysis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {1},
  pages = {e0338415},
  doi = {10.1371/journal.pone.0338415}
}
Kostenlos starten →