Abstract :

Retinal Diseases Are Among The Leading Causes Of Vision Impairment And Blindness Worldwide, Affecting Millions Of Individuals Each Year. Early Diagnosis And Timely Treatment Are Critical For Preventing Irreversible Vision Loss Caused By Conditions Such As Diabetic Retinopathy, Agerelated Macular Degeneration, Glaucoma, And Retinal Vein Occlusion. Traditional Retinal Disease Diagnosis Relies On Manual Examination Of Fundus Images By Ophthalmologists, Which Can Be Timeconsuming, Subjective, And Resource-intensive, Particularly In Regions With Limited Access To Specialized Healthcare. Consequently, There Is A Growing Need For Automated And Reliable Retinal Image Analysis Systems Capable Of Supporting Clinical Decision-making And Large-scale Screening Programs. This Study Presents A Local Binary Pattern (LBP)-based Approach For Automated Retinal Disease Detection And Assessment Using Digital Fundus Images. The Proposed Framework Employs Image Preprocessing Techniques To Enhance Retinal Image Quality, Followed By Local Binary Pattern Feature Extraction To Capture Significant Texture Characteristics Associated With Retinal Abnormalities. The Extracted Features Are Utilized For Disease Classification And Severity Assessment Through Machine Learning Algorithms. The Methodology Aims To Distinguish Healthy Retinal Images From Pathological Cases While Improving Diagnostic Accuracy And Computational Efficiency. Experimental Evaluation Demonstrates That LBP-based Texture Analysis Effectively Identifies Disease-related Patterns And Provides Robust Performance In Retinal Image Classification. The Results Indicate Improvements In Detection Accuracy, Sensitivity, And Specificity Compared With Conventional Texture Analysis Methods. The Proposed System Offers A Cost-effective And Efficient Solution For Early Retinal Disease Screening And Can Assist Ophthalmologists In Rapid Diagnosis, Reducing Workload And Facilitating Timely Medical Intervention. The Study Concludes That Local Binary Pattern-based Retinal Image Analysis Represents A Promising Approach For Automated Ophthalmic Disease Detection And Future Computer-aided Diagnostic Systems.

Published:

15-11-2023

Issue:

Vol. 23 No. 11 (2023)

Page Nos:

289 - 298

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite