Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 8, 2026Mesopotamian Journal of Big DataOpen Access

Deep Learning-Based Multi-Class Classification Approach for Diabetic Eye Diseases

View Full Paper
Ask AI
Bookmark
Share

Authors

RJRuqaia JawdAAArwa AlqudsiASAhmad Sabah

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates effective classification of diabetic eye diseases in diverse populations, suggesting improved early detection.

Key Points

  • The aim is to develop a deep learning model for early classification of diabetic eye diseases from retinal images.
  • Utilized a convolutional neural network (CNN) model with EfficientNetB3 architecture for classification.
  • Applied transfer learning on a diverse dataset of over 4,000 retinal images collected from various sources.
  • Focused on clinically relevant regions in retinal images for decision-making.
  • Achieved an overall accuracy of 91.3% in classifying diabetic eye diseases.
  • Class-specific sensitivities ranged from 87.6% to 94.2% and specificities from 92.1% to 95.8%.
  • The approach could enhance early detection capabilities in resource-limited settings.

Cite This Study

Jawd et al. (2026) studied this question.

synapsesocial.com/papers/6a265c69ad53cfb9357c59a8https://doi.org/10.58496/2958-6453.1083
View Full Paper
Ask AI
Bookmark
Share