A fully-automated retinal blood vessels detection using filling algorithm

Nur Badariah Ahmad Mustafa, W. Mimi Diyana W. Zaki, Aini Hussain, Jemaima Che Hamzah

Research output: Contribution to journalArticle

Abstract

This paper proposes a fully-automated retinal blood vessels detection method using image preprocessing, multi-scale line detector and post-processing approaches. In this method, a filling algorithm applied on the green channel has solved the vessel problem with central reflex. Moreover, the sum of multi-directional top-hat transformation has successfully enhanced all vessels including thin and tortuous vessels, as well as reduced the optic disk effect in retinal images. The proposed method has shown to be comparable to previous work. In addition, experimental work conducted using HRF images has also shown promising results with average 79.01% (sensitivity), 94.64%(specificity) and 93.30%(accuracy).

Original languageEnglish
Pages (from-to)665-673
Number of pages9
JournalInformation (Japan)
Volume20
Issue number1
Publication statusPublished - 01 Jan 2017

Fingerprint

Blood vessels
Optics
Detectors
Processing

All Science Journal Classification (ASJC) codes

  • Information Systems

Cite this

Ahmad Mustafa, N. B., Zaki, W. M. D. W., Hussain, A., & Hamzah, J. C. (2017). A fully-automated retinal blood vessels detection using filling algorithm. Information (Japan), 20(1), 665-673.
Ahmad Mustafa, Nur Badariah ; Zaki, W. Mimi Diyana W. ; Hussain, Aini ; Hamzah, Jemaima Che. / A fully-automated retinal blood vessels detection using filling algorithm. In: Information (Japan). 2017 ; Vol. 20, No. 1. pp. 665-673.
@article{b752dcb24d974608bd1db7d60cc2e234,
title = "A fully-automated retinal blood vessels detection using filling algorithm",
abstract = "This paper proposes a fully-automated retinal blood vessels detection method using image preprocessing, multi-scale line detector and post-processing approaches. In this method, a filling algorithm applied on the green channel has solved the vessel problem with central reflex. Moreover, the sum of multi-directional top-hat transformation has successfully enhanced all vessels including thin and tortuous vessels, as well as reduced the optic disk effect in retinal images. The proposed method has shown to be comparable to previous work. In addition, experimental work conducted using HRF images has also shown promising results with average 79.01{\%} (sensitivity), 94.64{\%}(specificity) and 93.30{\%}(accuracy).",
author = "{Ahmad Mustafa}, {Nur Badariah} and Zaki, {W. Mimi Diyana W.} and Aini Hussain and Hamzah, {Jemaima Che}",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "20",
pages = "665--673",
journal = "Information",
issn = "1343-4500",
publisher = "International Information Institute",
number = "1",

}

Ahmad Mustafa, NB, Zaki, WMDW, Hussain, A & Hamzah, JC 2017, 'A fully-automated retinal blood vessels detection using filling algorithm', Information (Japan), vol. 20, no. 1, pp. 665-673.

A fully-automated retinal blood vessels detection using filling algorithm. / Ahmad Mustafa, Nur Badariah; Zaki, W. Mimi Diyana W.; Hussain, Aini; Hamzah, Jemaima Che.

In: Information (Japan), Vol. 20, No. 1, 01.01.2017, p. 665-673.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A fully-automated retinal blood vessels detection using filling algorithm

AU - Ahmad Mustafa, Nur Badariah

AU - Zaki, W. Mimi Diyana W.

AU - Hussain, Aini

AU - Hamzah, Jemaima Che

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper proposes a fully-automated retinal blood vessels detection method using image preprocessing, multi-scale line detector and post-processing approaches. In this method, a filling algorithm applied on the green channel has solved the vessel problem with central reflex. Moreover, the sum of multi-directional top-hat transformation has successfully enhanced all vessels including thin and tortuous vessels, as well as reduced the optic disk effect in retinal images. The proposed method has shown to be comparable to previous work. In addition, experimental work conducted using HRF images has also shown promising results with average 79.01% (sensitivity), 94.64%(specificity) and 93.30%(accuracy).

AB - This paper proposes a fully-automated retinal blood vessels detection method using image preprocessing, multi-scale line detector and post-processing approaches. In this method, a filling algorithm applied on the green channel has solved the vessel problem with central reflex. Moreover, the sum of multi-directional top-hat transformation has successfully enhanced all vessels including thin and tortuous vessels, as well as reduced the optic disk effect in retinal images. The proposed method has shown to be comparable to previous work. In addition, experimental work conducted using HRF images has also shown promising results with average 79.01% (sensitivity), 94.64%(specificity) and 93.30%(accuracy).

UR - http://www.scopus.com/inward/record.url?scp=85033386345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033386345&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85033386345

VL - 20

SP - 665

EP - 673

JO - Information

JF - Information

SN - 1343-4500

IS - 1

ER -