Detection and Analysis of Diabetic Macular Edema (DME) Using Artificial Intelligence Techniques

Abstract

Diabetic Macular Edema (DME) is a leading cause of vision impairment among diabetic patients, underscoring the critical need for early and accurate detection to ensure effective management. This study introduces an automated diagnostic system that detects and analyzes DME based on artificial intelligence (AI) techniques. Tested on 100 retinal fundus images, the system achieved 97% accuracy, 98% sensitivity, and 96% specificity.  A comprehensive dataset including 800 real retinal images and 500 anonymized patient records was collected from Ibn Al-Haytham Eye Hospital and processed using a custom-built Python-based pipeline. The proposed system integrates advanced image processing and optical character recognition (OCR) algorithms to extract relevant diagnostic features and classify DME cases efficiently. The average processing time per image was approximately 1.2 seconds, making the system suitable for real-time clinical environments. Furthermore, all diagnostic outcomes were automatically exported to structured Excel reports to facilitate further analysis and integration with electronic health records. A user-friendly graphical user interface (GUI) was also developed to allow clinicians to upload images, review classification results, and manage patient information seamlessly. This approach offers a practical and scalable solution that enhances diagnostic workflow, supports clinical decision-making, and contributes to improved patient care in ophthalmology.