Fuzzy Logic-Based System for Identifying the Severity of Diabetic Macular Edema from OCT B-Scan Images Using DRIL,...

Area of Science:

• Ophthalmology
• Medical Imaging
• Artificial Intelligence

Background:

• Diabetic Macular Edema (DME) is a leading cause of vision loss in diabetic patients.
• Manual interpretation of OCT B-scan images for DME assessment is prone to errors.
• Accurate DME grading is crucial for timely and effective treatment.

Purpose of the Study:

• To develop and validate an AI-driven system for automated DME severity grading using OCT B-scan images.
• To accurately identify and quantify key DME biomarkers from OCT images.
• To provide a reliable tool for clinical decision-making in DME management.

Main Methods:

• An end-to-end AI model was developed to analyze OCT B-scan images.
• The system extracts biomarkers including Disorganization of Retinal Inner Layers (DRIL), Hyper Reflective Foci (HRF), and cystoids.
• A fuzzy logic engine, informed by current DME research, determines DME severity based on extracted biomarkers.

Main Results:

• The AI model achieved 93.3% accuracy in identifying images with DRIL.
• Successful segmentation of HRF and cystoids was demonstrated with Dice Similarity Coefficients of 91.30% and 95.07%, respectively.
• The system provides accurate and automated DME severity grading.

Conclusions:

• The proposed AI system offers a highly accurate and automated method for DME severity grading using OCT images.
• This technology has the potential to significantly enhance clinical assessment and treatment of DME.
• Automated analysis can reduce diagnostic errors and improve patient outcomes in DME management.