Related Experiment Video
Updated: Jul 20, 2026
10:11
Fundus Photography as a Convenient Tool to Study Microvascular Responses to Cardiovascular Disease Risk Factors in Epidemiological Studies
Published on: October 22, 2014
19.2K
Automatic Screening of Diabetic Retinopathy Using Fundus Images and Machine Learning Algorithms
K K Mujeeb Rahman1, Mohamed Nasor1, Ahmed Imran1
1College of Engineering & Information Technology, Ajman University, Ajman P.O. Box 346, United Arab Emirates.
Diagnostics (Basel, Switzerland)
|September 23, 2022
Summary
Diabetic retinopathy, a diabetes complication causing vision loss, can be detected early using machine learning. This study developed AI models, achieving high accuracy in predicting diabetic retinopathy from fundus images.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Diabetic retinopathy is a leading cause of blindness, linked to diabetes.
- Current diagnostic methods rely on manual analysis of fundus images, which is time-consuming and expensive.
- Early detection is crucial to prevent vision loss and complications.
Purpose of the Study:
- To develop an accessible machine learning tool for accurate diabetic retinopathy prediction.
- To utilize digital fundus images for automated screening.
Main Methods:
- Collected and annotated fundus images from public datasets.
- Implemented and evaluated two machine learning models: Support Vector Machine (SVM) and Deep Neural Network (DNN).
Main Results:
- The Support Vector Machine (SVM) model achieved a mean Area Under the ROC Curve (AUC) of 97.11%.
- The Deep Neural Network (DNN) model demonstrated superior performance with a mean AUC of 99.15% on test data.
Conclusions:
- Machine learning models, particularly DNNs, show significant potential for accurate and efficient diabetic retinopathy detection.
- This approach can aid in early diagnosis, potentially reducing healthcare costs and improving patient outcomes.
