A Novel Prediction Method for Glaucoma Detection Using Retinographies.

Area of Science:

• Ophthalmology
• Medical Imaging
• Computer Vision

Background:

• Glaucoma is a leading cause of vision loss in the U.S., characterized by retinal nerve damage.
• The progressive nature of glaucoma often makes early detection challenging for patients.
• Effective management requires accurate and timely diagnostic solutions.

Purpose of the Study:

• To develop and evaluate a novel detection model for glaucoma using retinography images.
• To improve the accuracy and performance of glaucoma detection systems.
• To identify key features for distinguishing healthy eyes from those with glaucoma.

Main Methods:

• Utilized retinography images as input for a novel detection model.
• Integrated and extracted features from 3D meshes for enhanced analysis.
• Compared the performance of Classification Decision Trees (CDT), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms.

Main Results:

• The proposed model achieved 100% accuracy in glaucoma detection using CDT and SVM.
• The K-Nearest Neighbor (KNN) algorithm demonstrated 83.3% accuracy with the proposed model.
• The methodology proved efficient in classifying retinographies for glaucoma detection.

Conclusions:

• The novel detection model shows high efficacy in identifying glaucoma from retinographies.
• The use of 3D mesh features significantly contributes to the model's performance.
• This approach offers a valuable tool for early glaucoma diagnosis and patient management.