Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A framework based on hybrid Suzuki-Abe and convex Hull approach for improved classification of skin lesions.

Scientific reports·2026

Same author

Decoding basal ganglia motor circuit dysfunction from handwriting: a physics-informed neural signal interpretation framework for Parkinson's disease screening.

Frontiers in neuroinformatics·2026

Same author

Particle swarm optimized deep learning for jamming detection and throughput enhancement in cognitive radio networks.

Scientific reports·2026

Same author

Early prediction of diabetic retinopathy using a multimodal deep learning framework integrating fundus and OCT imaging.

Frontiers in medicine·2026

Same author

Explainable federated transformer framework for joint leukemia classification and stage prediction.

Scientific reports·2026

Same author

Enhanced drug-drug interaction extraction from biomedical text using deep learning-based sentence representations.

Scientific reports·2025

Search research articles

Related Experiment Video

Updated: Oct 16, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME Diagnosis.

Ghada Atteia¹, Nagwan Abdel Samee^1,2, Hassan Zohair Hassan³

¹Information Technology Department, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 11461, Saudi Arabia.

Entropy (Basel, Switzerland)

|October 23, 2021

Summary

A new deep learning system accurately diagnoses diabetic macular edema (DME) from retinal images. This automated approach aids early detection, improving treatment outcomes for diabetes patients with vision loss.

Keywords:

autoencoder deep learning diabetic macular edema pretrained convolutional neural network retinal fundus image transfer learning

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

Related Experiment Videos

Last Updated: Oct 16, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Diabetic macular edema (DME) is a leading cause of irreversible vision loss in diabetic patients.
Early diagnosis of DME is crucial for effective treatment.
Manual detection of DME in retinal images is time-consuming.

Purpose of the Study:

To propose a novel deep feature transfer-based stacked autoencoder neural network system for automated DME diagnosis.
To enhance the accuracy and efficiency of DME detection in fundus images.

Main Methods:

Integration of pretrained convolutional neural networks (ResNet-50, SqueezeNet, Inception-v3, GoogLeNet) for automatic feature extraction.
Utilizing a stacked autoencoder neural network for feature selection and semi-supervised classification.
Extracting a large feature set from a small dataset.

Main Results:

The proposed system achieved a maximum classification accuracy of 96.8%.
Sensitivity reached 97.5%, and specificity was 95.5%.
Demonstrated superior performance compared to original pretrained networks and existing state-of-the-art methods.

Conclusions:

The developed deep learning system offers a highly accurate and efficient method for automated DME diagnosis.
This system can significantly assist ophthalmologists in early DME detection and management.
The approach shows promise for improving patient outcomes in diabetic retinopathy screening.