Related Experiment Video
Updated: Jul 8, 2026

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential
Published on: May 25, 2020
Detection of glaucomatous change based on vessel shape analysis
George K Matsopoulos1, Pantelis A Asvestas, Konstantinos K Delibasis
1Department of Electrical and Computer Engineering, National Technical University of Athens, 9, Iroon Polytechniou Street, Zografos, 15780 Athens, Greece. gmatso@esd.ece.ntua.gr
This study presents a computer-based system using image processing to detect early glaucoma progression in patients with ocular hypertension. The system achieved an 87.5% classification rate, aiding in timely treatment to prevent vision loss.
Area of Science:
- Ophthalmology
- Medical Image Analysis
- Computational Biology
Background:
- Glaucoma is a leading cause of irreversible blindness globally, characterized by optic nerve damage and visual field loss.
- Elevated intraocular pressure (ocular hypertension) is the primary risk factor for developing glaucoma.
- Current methods for detecting early glaucomatous damage have limitations, necessitating advanced computer-based detection systems.
Purpose of the Study:
- To develop and evaluate a novel computer-based system for detecting early glaucomatous progression.
- To estimate quantitative parameters of vessel deformation for glaucoma detection.
- To classify patients with ocular hypertension into those who develop glaucoma and those who remain stable.
Main Methods:
- The system integrates image processing techniques including vessel central axis segmentation and automatic retinal image registration using self-organizing maps (SOMs).
- Retinal vessel shape attributes were calculated to identify key features indicative of glaucomatous change.
- An artificial neural network classifier was employed for subject classification based on the extracted attributes.
Main Results:
- The proposed system achieved a classification accuracy of 87.5% in distinguishing between patients with ocular hypertension who develop glaucoma and those who remain stable.
- The system effectively utilizes quantitative parameters derived from retinal vessel deformation for classification.
- Implementation involved analysis of optic disc data from 127 subjects using fundus camera images.
Conclusions:
- The developed image processing and classification system shows significant promise in assisting the early detection of glaucomatous changes.
- This automated approach can facilitate timely intervention to prevent further vision loss in glaucoma patients.
- The system's high classification rate underscores its potential value in clinical ophthalmology for managing ocular hypertension and glaucoma progression.
Related Concept Videos
Glaucoma: Overview
Open Angle Glaucoma: Treatment
Drugs such as carbonic anhydrase inhibitors, α2- and...
Angle Closure Glaucoma: Treatment

