Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 4, 2025International Journal of Environmental Sciences

Deep Learning Methods For Classifying Multiple Retinal Diseases Using Fundus Images

View Full Paper
Ask AI
Bookmark
Share

Authors

CSC Sharmila SutturUPU PoornimaSKShreya Kulkarni

Discussion

Loading...

Member takes

Overview

Analysis demonstrates improved classification of retinal diseases using deep learning models, indicating clinical potential.

Key Points

  • The Customized CNN achieved an accuracy of 91.37%, outperforming other models in classifying retinal diseases.
  • Among the evaluated architectures, performance metrics like accuracy and F1-score highlighted the strengths of deep learning.
  • Evaluation included multiple models, such as VGG16 and ResNet50, tested on 600 fundus images across six disease classes.
  • The findings emphasize the importance of tailored deep learning models for enhancing clinical diagnostic tools.

Cite This Study

Suttur et al. (2025) studied this question.

synapsesocial.com/papers/68af4eb9ad7bf08b1ead7a29https://doi.org/10.64252/t0pztt54
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Early retinal disease detection from fundus images using deep neural networks2026 · 1 citations
  2. 2Harnessing Deep Learning Methods for Detecting Different Retinal Diseases: A Multi-Categorical Classification Methodology2024 · 5 citations
  3. 3A deep learning framework for the early detection of multi-retinal diseases2024 · 49 citations
  4. 4Enhancing Clinical Decision Support: A Deep Learning Approach for Automated Diagnosis of Eye Diseases from Fundus Images2025
  5. 5Multi-disease Classification of retinal images using Convolutional Neural Network2024