Automated diabetic retinopathy classification using vision transformers on optical confocal microscopy images
Applied Optics · 2025
DOI: 10.1364/ao.562201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, 2025. Verfasst von Mohamed R Shoaib und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Diabetic Retinopathy, Image Interpretation, Computer-Assisted. Die Arbeit nennt 36 Literaturangaben. Gefördert von: King Khalid University.
Abstract (Originalsprache)
In this paper, we employed the Vision Transformer architecture to effectively classify diabetic retinopathy (DR) in retinal images. Our dataset consisted of validated images, categorized into two classes: “normal” and “abnormal.” The model demonstrated robust performance, achieving a training accuracy of 98.91% and a validation accuracy of 98.79%, alongside a commendable test accuracy of 100%. The training process spanned 30 epochs, during which the model exhibited consistent improvements in accuracy and reductions in loss. We further evaluated the model efficacy through a classification report, which revealed precision, recall, and F1-scores of 1.00 for both classes, indicating perfect classification performance on the test set. The results highlight the model potential for clinical applications in DR detection, ensuring its capability to assist healthcare professionals in diagnosing DR with high accuracy. Future work will focus on enhancing the model generalizability across diverse datasets and exploring the integration of additional clinical features.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- King Khalid University
Zitieren
APA
Shoaib, M. R., Esmaiel, H., Al Ayidh, A., Hussein, H. S., & Abd El-Samie, F. E. (2025). Automated diabetic retinopathy classification using vision transformers on optical confocal microscopy images. Applied Optics. https://doi.org/10.1364/ao.562201
Vancouver
Shoaib MR, Esmaiel H, Al Ayidh A, Hussein HS, Abd El-Samie FE. Automated diabetic retinopathy classification using vision transformers on optical confocal microscopy images. Applied Optics. 2025. doi:10.1364/ao.562201
BibTeX
@article{Shoaib2025,
author = {Shoaib, Mohamed R and Esmaiel, Hamada and Al Ayidh, Abdulrahman and Hussein, Hany S and Abd El-Samie, Fathi E},
title = {Automated diabetic retinopathy classification using vision transformers on optical confocal microscopy images},
journal = {Applied Optics},
year = {2025},
doi = {10.1364/ao.562201}
}
EUVIMED