Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding

Research output: Contribution to journalArticle

Abstract

Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.

Original languageEnglish
Pages (from-to)1199-1207
Number of pages9
JournalIndonesian Journal of Electrical Engineering and Computer Science
Volume13
Issue number3
DOIs
Publication statusPublished - 1 Mar 2019

Fingerprint

Adaptive Thresholding
Blood Vessels
Blood vessels
Segmentation
Availability
Noise Robustness
Selectivity
Threshold Value
Specificity

Keywords

  • Adaptive thresholding
  • B-COSFIRE filter
  • Retinal blood vessel
  • Segmentation

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

@article{bda6a1276c0b4497a577800432303987,
title = "Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding",
abstract = "Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.",
keywords = "Adaptive thresholding, B-COSFIRE filter, Retinal blood vessel, Segmentation",
author = "Aziah Ali and {Wan Zaki}, {Wan Mimi Diyana} and Aini Hussain",
year = "2019",
month = "3",
day = "1",
doi = "10.11591/ijeecs.v13.i3.pp1199-1207",
language = "English",
volume = "13",
pages = "1199--1207",
journal = "Indonesian Journal of Electrical Engineering and Computer Science",
issn = "2502-4752",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

TY - JOUR

T1 - Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding

AU - Ali, Aziah

AU - Wan Zaki, Wan Mimi Diyana

AU - Hussain, Aini

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.

AB - Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.

KW - Adaptive thresholding

KW - B-COSFIRE filter

KW - Retinal blood vessel

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85063149442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063149442&partnerID=8YFLogxK

U2 - 10.11591/ijeecs.v13.i3.pp1199-1207

DO - 10.11591/ijeecs.v13.i3.pp1199-1207

M3 - Article

VL - 13

SP - 1199

EP - 1207

JO - Indonesian Journal of Electrical Engineering and Computer Science

JF - Indonesian Journal of Electrical Engineering and Computer Science

SN - 2502-4752

IS - 3

ER -