EUVIMEDEUVIMED entdecken
Crossref

A Deep Learning–Driven CNN Framework for Early Identification of Retinal Disorders

Jalaldeen Khan Mohamed, Y Ramchitra, C Gayathri, G Karthiyayini, S Shanmuga Priya, S Lakshmana Nainar Sundar

International Journal of Medical Toxicology and Forensic Medicine · 11.08.2026

DOI: 10.22037/ijmtfm.v16.51925 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Medical Toxicology and Forensic Medicine, erschienen am 11.08.2026. Verfasst von Jalaldeen Khan Mohamed und 5 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early detection of retinal disorders is crucial to prevent vision loss. Traditional methods are time-consuming and prone to error. This study investigates a CNN-based deep learning framework for automating retinal disorder identification.

Methods

The study, conducted from January to April 2025 at the Department of Electronics and Communication Engineering, used publicly available retinal image datasets. The CNN model was trained on preprocessed retinal fundus images, with performance evaluated using accuracy, sensitivity, specificity, precision, recall, and F1-score.

Results

The proposed CNN framework exhibited excellent classification performance, achieving an overall accuracy of 94.6%, sensitivity of 93.2%, and specificity of 95.8%. The model successfully identified early-stage retinal abnormalities and demonstrated consistent results across various image samples. These findings suggest that the deep learning approach significantly outperforms conventional methods in early retinal disorder detection.

Conclusion

The CNN-based deep learning framework developed in this study provides a highly accurate and reliable tool for the early identification of retinal disorders. This approach has significant potential for integration into computer-aided diagnosis systems and tele-ophthalmology platforms, aiding early clinical decision-making and potentially preventing vision loss.

Schlagwörter

retinal diseaseearly detectionfundus imagesconvolutional neural networkscomputer-aided diagnosisteleophthalmologyblindness preventionretinal image classification

Zitieren

APA

Mohamed, J. K., Ramchitra, Y., Gayathri, C., Karthiyayini, G., Priya, S. S., & Sundar, S. L. N. (2026). A Deep Learning–Driven CNN Framework for Early Identification of Retinal Disorders. International Journal of Medical Toxicology and Forensic Medicine. https://doi.org/10.22037/ijmtfm.v16.51925

Vancouver

Mohamed JK, Ramchitra Y, Gayathri C, Karthiyayini G, Priya SS, Sundar SLN. A Deep Learning–Driven CNN Framework for Early Identification of Retinal Disorders. International Journal of Medical Toxicology and Forensic Medicine. 2026. doi:10.22037/ijmtfm.v16.51925

BibTeX
@article{Mohamed2026,
  author = {Mohamed, Jalaldeen Khan and Ramchitra, Y and Gayathri, C and Karthiyayini, G and Priya, S Shanmuga and Sundar, S Lakshmana Nainar},
  title = {A Deep Learning–Driven CNN Framework for Early Identification of Retinal Disorders},
  journal = {International Journal of Medical Toxicology and Forensic Medicine},
  year = {2026},
  doi = {10.22037/ijmtfm.v16.51925}
}
Kostenlos starten →