A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity

Mohammad A.U. Khan, Tariq M. Khan, D. G. Bailey, Toufique A. Soomro

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

Original languageEnglish
Pages (from-to)1177-1196
Number of pages20
JournalPattern Analysis and Applications
Volume22
Issue number3
Early online date15 Mar 2018
DOIs
Publication statusPublished - Aug 2019

Fingerprint

Detectors
Blood vessels
Pathology
Hysteresis
Masks

Cite this

Khan, Mohammad A.U. ; Khan, Tariq M. ; Bailey, D. G. ; Soomro, Toufique A. / A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity. In: Pattern Analysis and Applications. 2019 ; Vol. 22, No. 3. pp. 1177-1196.
@article{e31186e575f543deaf028aaada0d039e,
title = "A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity",
abstract = "Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.",
keywords = "Morphological opening, Morphological reconstruction, Multi-scale line detector, Orientation field, Retinal segmentation, Second-order derivative detector",
author = "Khan, {Mohammad A.U.} and Khan, {Tariq M.} and Bailey, {D. G.} and Soomro, {Toufique A.}",
year = "2019",
month = "8",
doi = "10.1007/s10044-018-0696-1",
language = "English",
volume = "22",
pages = "1177--1196",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer London",
number = "3",

}

A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity. / Khan, Mohammad A.U.; Khan, Tariq M.; Bailey, D. G.; Soomro, Toufique A.

In: Pattern Analysis and Applications, Vol. 22, No. 3, 08.2019, p. 1177-1196.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity

AU - Khan, Mohammad A.U.

AU - Khan, Tariq M.

AU - Bailey, D. G.

AU - Soomro, Toufique A.

PY - 2019/8

Y1 - 2019/8

N2 - Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

AB - Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

KW - Morphological opening

KW - Morphological reconstruction

KW - Multi-scale line detector

KW - Orientation field

KW - Retinal segmentation

KW - Second-order derivative detector

UR - http://www.scopus.com/inward/record.url?scp=85044054581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044054581&partnerID=8YFLogxK

U2 - 10.1007/s10044-018-0696-1

DO - 10.1007/s10044-018-0696-1

M3 - Article

AN - SCOPUS:85044054581

VL - 22

SP - 1177

EP - 1196

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 3

ER -