Automated pterygium detection method of anterior segment photographed images

Wan Mimi Diyana Wan Zaki, Marizuana Mat Daud, Siti Raihanah Abdani, Aini Hussain, Haliza Abdul Mutalib

Research output: Contribution to journalReview article

2 Citations (Scopus)

Abstract

Background and bjective Pterygium is an ocular disease caused by fibrovascular tissue encroachment onto the corneal region. The tissue may cause vision blurring if it grows into the pupil region. In this study, we propose an automatic detection method to differentiate pterygium from non-pterygium (normal) cases on the basis of frontal eye photographed images, also known as anterior segment photographed images. Methods The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network. Results The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7%, 88.3%, and 95.6% for sensitivity, specificity, and area under the curve, respectively. Conclusion A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.

Original languageEnglish
Pages (from-to)71-78
Number of pages8
JournalComputer Methods and Programs in Biomedicine
Volume154
DOIs
Publication statusPublished - 1 Feb 2018

Fingerprint

Pterygium
Tissue
Support vector machines
Screening
Feature extraction
Neural networks
Databases
Eye Diseases
Sigmoid Colon
Rural Population
Pupil
Area Under Curve
Brazil

Keywords

  • Anterior segment photographed image
  • Ocular disease
  • Pterygium screening system
  • Shape feature
  • Support vector machine

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Automated pterygium detection method of anterior segment photographed images. / Wan Zaki, Wan Mimi Diyana; Mat Daud, Marizuana; Abdani, Siti Raihanah; Hussain, Aini; Abdul Mutalib, Haliza.

In: Computer Methods and Programs in Biomedicine, Vol. 154, 01.02.2018, p. 71-78.

Research output: Contribution to journalReview article

@article{a96598ba2655421db756005a75e39564,
title = "Automated pterygium detection method of anterior segment photographed images",
abstract = "Background and bjective Pterygium is an ocular disease caused by fibrovascular tissue encroachment onto the corneal region. The tissue may cause vision blurring if it grows into the pupil region. In this study, we propose an automatic detection method to differentiate pterygium from non-pterygium (normal) cases on the basis of frontal eye photographed images, also known as anterior segment photographed images. Methods The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network. Results The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7{\%}, 88.3{\%}, and 95.6{\%} for sensitivity, specificity, and area under the curve, respectively. Conclusion A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.",
keywords = "Anterior segment photographed image, Ocular disease, Pterygium screening system, Shape feature, Support vector machine",
author = "{Wan Zaki}, {Wan Mimi Diyana} and {Mat Daud}, Marizuana and Abdani, {Siti Raihanah} and Aini Hussain and {Abdul Mutalib}, Haliza",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.cmpb.2017.10.026",
language = "English",
volume = "154",
pages = "71--78",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Automated pterygium detection method of anterior segment photographed images

AU - Wan Zaki, Wan Mimi Diyana

AU - Mat Daud, Marizuana

AU - Abdani, Siti Raihanah

AU - Hussain, Aini

AU - Abdul Mutalib, Haliza

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Background and bjective Pterygium is an ocular disease caused by fibrovascular tissue encroachment onto the corneal region. The tissue may cause vision blurring if it grows into the pupil region. In this study, we propose an automatic detection method to differentiate pterygium from non-pterygium (normal) cases on the basis of frontal eye photographed images, also known as anterior segment photographed images. Methods The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network. Results The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7%, 88.3%, and 95.6% for sensitivity, specificity, and area under the curve, respectively. Conclusion A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.

AB - Background and bjective Pterygium is an ocular disease caused by fibrovascular tissue encroachment onto the corneal region. The tissue may cause vision blurring if it grows into the pupil region. In this study, we propose an automatic detection method to differentiate pterygium from non-pterygium (normal) cases on the basis of frontal eye photographed images, also known as anterior segment photographed images. Methods The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network. Results The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7%, 88.3%, and 95.6% for sensitivity, specificity, and area under the curve, respectively. Conclusion A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.

KW - Anterior segment photographed image

KW - Ocular disease

KW - Pterygium screening system

KW - Shape feature

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85033454496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033454496&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2017.10.026

DO - 10.1016/j.cmpb.2017.10.026

M3 - Review article

VL - 154

SP - 71

EP - 78

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -