Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images

Farsad Zamani Boroujeni, Rahmita Wirza O K Rahmat, Norwati Mustapha, Lilly Sudani Affendey, Oteh Maskon

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.

Original languageEnglish
Pages (from-to)443-451
Number of pages9
JournalDefence Science Journal
Volume61
Issue number5
Publication statusPublished - Sep 2011

Fingerprint

tracing
vessels
seeds
Computational efficiency
Seed
Signal to noise ratio
signal to noise ratios
filters
Direction compound

Keywords

  • Centerline extraction
  • Coronaries
  • Exploratory tracing
  • Seed point detection
  • Tracking

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Computer Science Applications
  • Physics and Astronomy(all)
  • Biomedical Engineering

Cite this

Boroujeni, F. Z., Rahmat, R. W. O. K., Mustapha, N., Affendey, L. S., & Maskon, O. (2011). Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images. Defence Science Journal, 61(5), 443-451.

Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images. / Boroujeni, Farsad Zamani; Rahmat, Rahmita Wirza O K; Mustapha, Norwati; Affendey, Lilly Sudani; Maskon, Oteh.

In: Defence Science Journal, Vol. 61, No. 5, 09.2011, p. 443-451.

Research output: Contribution to journalArticle

Boroujeni, FZ, Rahmat, RWOK, Mustapha, N, Affendey, LS & Maskon, O 2011, 'Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images', Defence Science Journal, vol. 61, no. 5, pp. 443-451.
Boroujeni FZ, Rahmat RWOK, Mustapha N, Affendey LS, Maskon O. Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images. Defence Science Journal. 2011 Sep;61(5):443-451.
Boroujeni, Farsad Zamani ; Rahmat, Rahmita Wirza O K ; Mustapha, Norwati ; Affendey, Lilly Sudani ; Maskon, Oteh. / Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images. In: Defence Science Journal. 2011 ; Vol. 61, No. 5. pp. 443-451.
@article{59cff34560594690b074a3b65db0f02e,
title = "Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images",
abstract = "Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.",
keywords = "Centerline extraction, Coronaries, Exploratory tracing, Seed point detection, Tracking",
author = "Boroujeni, {Farsad Zamani} and Rahmat, {Rahmita Wirza O K} and Norwati Mustapha and Affendey, {Lilly Sudani} and Oteh Maskon",
year = "2011",
month = "9",
language = "English",
volume = "61",
pages = "443--451",
journal = "Defence Science Journal",
issn = "0011-748X",
publisher = "Defense Scientific Information and Documentation Centre",
number = "5",

}

TY - JOUR

T1 - Automatic selection of initial points for exploratory vessel tracing in Fluoroscopic images

AU - Boroujeni, Farsad Zamani

AU - Rahmat, Rahmita Wirza O K

AU - Mustapha, Norwati

AU - Affendey, Lilly Sudani

AU - Maskon, Oteh

PY - 2011/9

Y1 - 2011/9

N2 - Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.

AB - Automatic extraction of vessel centerlines is viewed as an essential process in majority of image-guided diagnostic and therapeutic applications. Among a considerable number of methods, direct exploratory tracing method is known as an efficient solution for reliable extraction of vessel features from two-dimensional fluoroscopic images. The first step of most automatic exploratory tracing algorithms is to collect some candidate initial seed points as well as their initial tracing directions. To detect reliable initial points, a validation procedure is required to filter out the false candidates and avoid unnecessary tracing. Starting from reliable initial points, the algorithm efficiently extracts the centerline points along the initial direction until certain pre-defined criteria are met. However, most of these algorithms suffer from incomplete results due to inappropriate selection of the initial seed points. The conventional seed point selection algorithms either rely merely on signal-to-noise ratio analysis, which results in a large number of false traces, or impose a set of strict geometrical validation rules which leads to more false negatives and as a consequence more time shall be spent on computation. This paper presents a new method for efficient selection of initial points for exploratory tracing algorithms. The proposed method improves the performance upon existing methods by employing a combination of geometrical and intensity-based approaches. Moreover, it provides a tunable trade-off between the strictness of the validation procedure and computational efficiency. The results of comparative performance with other proposed techniques are included.

KW - Centerline extraction

KW - Coronaries

KW - Exploratory tracing

KW - Seed point detection

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=80054719174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054719174&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:80054719174

VL - 61

SP - 443

EP - 451

JO - Defence Science Journal

JF - Defence Science Journal

SN - 0011-748X

IS - 5

ER -