Scribd
Upload
19 views2 pages

Abstract

This study presents a computer-aided approach for glaucoma detection using MATLAB, focusing on Histogram Analysis and the Cup-to-Disc Ratio (CDR) method applied to retinal fundus images. The methodology enhances diagnostic accuracy by preprocessing images, segmenting optic structures, and correlating CDR values with abnormal histogram distributions. The proposed system offers a low-cost screening tool for early glaucoma detection, with potential future enhancements through machine learning integration.

Uploaded by

anil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
19 views2 pages

Abstract

This study presents a computer-aided approach for glaucoma detection using MATLAB, focusing on Histogram Analysis and the Cup-to-Disc Ratio (CDR) method applied to retinal fundus images. The methodology enhances diagnostic accuracy by preprocessing images, segmenting optic structures, and correlating CDR values with abnormal histogram distributions. The proposed system offers a low-cost screening tool for early glaucoma detection, with potential future enhancements through machine learning integration.

Uploaded by

anil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

"Glaucoma Detection Using Histogram-Based Analysis and

Cup-to-Disc Ratio (CDR) Method in MATLAB"


Abstract

Glaucoma is a progressive optic neuropathy that leads to irreversible vision loss if not diagnosed and

managed early. This study presents a computer-aided approach for the detection of glaucoma using

MATLAB, focusing on two primary diagnostic indicators: Histogram Analysis and the Cup-to-Disc Ratio

(CDR) method. These techniques are applied to retinal fundus images to evaluate structural changes in the

optic nerve head—key markers of glaucomatous damage.

The proposed method begins with preprocessing of the fundus image to enhance contrast and remove

noise, followed by optic disc and optic cup segmentation using morphological operations and edge

detection. The CDR is calculated by dividing the vertical diameter of the optic cup by that of the optic

disc, providing a quantitative measure of optic nerve cupping. A higher CDR value is a strong indicator of

glaucoma. In parallel, histogram analysis is used to evaluate the intensity distribution within the optic

nerve region, helping to identify areas of nerve fiber layer thinning and asymmetry—typical in

glaucomatous eyes.

The system was implemented using MATLAB’s image processing toolbox, and tested on a set of annotated

retinal images. Results showed a significant correlation between increased CDR values, abnormal

histogram distributions, and clinically diagnosed glaucoma cases. This dual-approach enhances diagnostic

accuracy by combining structural and statistical image features.


The methodology offers a low-cost, automated screening tool for early glaucoma detection, particularly

beneficial in resource-limited settings. Future work may include integrating machine learning models for

improved classification and expanding the system for large-scale screening applications.

You might also like