Structure-based level set method for automatic retinal vasculature segmentation

Bekir Dizdaroğlu, Esra Ataer-Cansizoglu, Jayashree Kalpathy-Cramer, Katie Keck, Michael Chiang, Deniz Erdogmus

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.

Original languageEnglish (US)
Article number39
JournalEurasip Journal on Image and Video Processing
Volume2014
Issue number1
DOIs
StatePublished - Aug 11 2014

Fingerprint

Edge detection
Seed
Experiments

Keywords

  • Color retinal fundus images
  • Phase map
  • Segmentation of retinal vasculature
  • Structure and texture parts of retinal fundus image
  • Structure-based level set method

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Information Systems

Cite this

Structure-based level set method for automatic retinal vasculature segmentation. / Dizdaroğlu, Bekir; Ataer-Cansizoglu, Esra; Kalpathy-Cramer, Jayashree; Keck, Katie; Chiang, Michael; Erdogmus, Deniz.

In: Eurasip Journal on Image and Video Processing, Vol. 2014, No. 1, 39, 11.08.2014.

Research output: Contribution to journalArticle

Dizdaroğlu, Bekir ; Ataer-Cansizoglu, Esra ; Kalpathy-Cramer, Jayashree ; Keck, Katie ; Chiang, Michael ; Erdogmus, Deniz. / Structure-based level set method for automatic retinal vasculature segmentation. In: Eurasip Journal on Image and Video Processing. 2014 ; Vol. 2014, No. 1.
@article{face0b84f8de499ba710bd5a376ebedd,
title = "Structure-based level set method for automatic retinal vasculature segmentation",
abstract = "Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.",
keywords = "Color retinal fundus images, Phase map, Segmentation of retinal vasculature, Structure and texture parts of retinal fundus image, Structure-based level set method",
author = "Bekir Dizdaroğlu and Esra Ataer-Cansizoglu and Jayashree Kalpathy-Cramer and Katie Keck and Michael Chiang and Deniz Erdogmus",
year = "2014",
month = "8",
day = "11",
doi = "10.1186/1687-5281-2014-39",
language = "English (US)",
volume = "2014",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",
number = "1",

}

TY - JOUR

T1 - Structure-based level set method for automatic retinal vasculature segmentation

AU - Dizdaroğlu, Bekir

AU - Ataer-Cansizoglu, Esra

AU - Kalpathy-Cramer, Jayashree

AU - Keck, Katie

AU - Chiang, Michael

AU - Erdogmus, Deniz

PY - 2014/8/11

Y1 - 2014/8/11

N2 - Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.

AB - Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.

KW - Color retinal fundus images

KW - Phase map

KW - Segmentation of retinal vasculature

KW - Structure and texture parts of retinal fundus image

KW - Structure-based level set method

UR - http://www.scopus.com/inward/record.url?scp=84938088395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938088395&partnerID=8YFLogxK

U2 - 10.1186/1687-5281-2014-39

DO - 10.1186/1687-5281-2014-39

M3 - Article

AN - SCOPUS:84938088395

VL - 2014

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

IS - 1

M1 - 39

ER -