Small retinal vessels extraction towards proliferative diabetic retinopathy screening

Girish Singh Ramlugun, Vivek Krishna Nagarajan, Chandan Chakraborty

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

This paper introduces a systematic approach for segmentation of retinal blood vessels towards the diagnosis of proliferative diabetic retinopathy (PDR) from digital fundus images. Here, 2D-Match (Gabor) filters are used on digital fundus images in which the vessels are enhanced by contrast-limited adaptive histogram equalization (CLAHE). A double sided thresholding scheme is then used to segment the vessels. Hysteresis thresholding is performed with the large and small vessels clipped at different intensity levels in order to reconstruct the vessels in the image. This vessel extraction technique leads to high accuracy (93.1%) in comparison with the ground truth images provided in the DRIVE database.

Original languageEnglish
Pages (from-to)1141-1146
Number of pages6
JournalExpert Systems with Applications
Volume39
Issue number1
DOIs
Publication statusPublished - 01-01-2012
Externally publishedYes

Fingerprint

Gabor filters
Blood vessels
Hysteresis
Screening

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Ramlugun, Girish Singh ; Nagarajan, Vivek Krishna ; Chakraborty, Chandan. / Small retinal vessels extraction towards proliferative diabetic retinopathy screening. In: Expert Systems with Applications. 2012 ; Vol. 39, No. 1. pp. 1141-1146.
@article{162ddc68143e41279f857cc41f2a5af7,
title = "Small retinal vessels extraction towards proliferative diabetic retinopathy screening",
abstract = "This paper introduces a systematic approach for segmentation of retinal blood vessels towards the diagnosis of proliferative diabetic retinopathy (PDR) from digital fundus images. Here, 2D-Match (Gabor) filters are used on digital fundus images in which the vessels are enhanced by contrast-limited adaptive histogram equalization (CLAHE). A double sided thresholding scheme is then used to segment the vessels. Hysteresis thresholding is performed with the large and small vessels clipped at different intensity levels in order to reconstruct the vessels in the image. This vessel extraction technique leads to high accuracy (93.1{\%}) in comparison with the ground truth images provided in the DRIVE database.",
author = "Ramlugun, {Girish Singh} and Nagarajan, {Vivek Krishna} and Chandan Chakraborty",
year = "2012",
month = "1",
day = "1",
doi = "10.1016/j.eswa.2011.07.115",
language = "English",
volume = "39",
pages = "1141--1146",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "1",

}

Small retinal vessels extraction towards proliferative diabetic retinopathy screening. / Ramlugun, Girish Singh; Nagarajan, Vivek Krishna; Chakraborty, Chandan.

In: Expert Systems with Applications, Vol. 39, No. 1, 01.01.2012, p. 1141-1146.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Small retinal vessels extraction towards proliferative diabetic retinopathy screening

AU - Ramlugun, Girish Singh

AU - Nagarajan, Vivek Krishna

AU - Chakraborty, Chandan

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper introduces a systematic approach for segmentation of retinal blood vessels towards the diagnosis of proliferative diabetic retinopathy (PDR) from digital fundus images. Here, 2D-Match (Gabor) filters are used on digital fundus images in which the vessels are enhanced by contrast-limited adaptive histogram equalization (CLAHE). A double sided thresholding scheme is then used to segment the vessels. Hysteresis thresholding is performed with the large and small vessels clipped at different intensity levels in order to reconstruct the vessels in the image. This vessel extraction technique leads to high accuracy (93.1%) in comparison with the ground truth images provided in the DRIVE database.

AB - This paper introduces a systematic approach for segmentation of retinal blood vessels towards the diagnosis of proliferative diabetic retinopathy (PDR) from digital fundus images. Here, 2D-Match (Gabor) filters are used on digital fundus images in which the vessels are enhanced by contrast-limited adaptive histogram equalization (CLAHE). A double sided thresholding scheme is then used to segment the vessels. Hysteresis thresholding is performed with the large and small vessels clipped at different intensity levels in order to reconstruct the vessels in the image. This vessel extraction technique leads to high accuracy (93.1%) in comparison with the ground truth images provided in the DRIVE database.

UR - http://www.scopus.com/inward/record.url?scp=81855164930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81855164930&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.07.115

DO - 10.1016/j.eswa.2011.07.115

M3 - Article

VL - 39

SP - 1141

EP - 1146

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 1

ER -