Enhancement of Detection of Diabetic Retinopathy Using Harris Hawks Optimization with Deep Learning Model

Area of Science:

• Ophthalmology
• Medical Imaging
• Artificial Intelligence

Background:

• Diabetic retinopathy is a leading cause of blindness globally, stemming from high blood sugar damaging retinal blood vessels.
• Early diagnosis is critical to prevent vision loss and save lives.
• Existing machine learning and deep learning models struggle with accuracy in preprocessing, classification, and feature extraction for diabetic retinopathy.

Purpose of the Study:

• To develop an optimized deep learning model for accurate diabetic retinopathy detection.
• To address limitations in feature extraction and optimization in current diagnostic systems.

Main Methods:

• Utilized the Diabetic Retinopathy Debrecen Data Set from the UCI machine learning repository.
• Implemented a deep learning model incorporating Principal Component Analysis (PCA) for dimensionality reduction.
• Employed the Harris Hawks Optimization algorithm for enhanced feature extraction and classification optimization.

Main Results:

• The proposed deep learning model demonstrated satisfactory performance metrics, including specificity, precision, accuracy, and recall.
• Achieved superior results compared to existing systems in diagnosing diabetic retinopathy.

Conclusions:

• The developed deep learning model with PCA and Harris Hawks Optimization offers a promising approach for accurate and efficient diabetic retinopathy diagnosis.
• This method can significantly improve early detection rates, potentially reducing vision impairment and blindness.