An improved seed point detection algorithm for centerline tracing in coronary angiograms

Farsad Zamani Boroujeni, Rahmita Wirza, Oteh Maskon, Alireza Khosravi, Majid Khalilian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a new method to detect initial seed points for automatic tracing of the vessel center lines in coronary angiograms. Vessel tracing algorithms are known to be fast and efficient among several feature extraction methods. However, most of them suffer from incomplete results due to inappropriate trade-off between the completeness of seed point detection and computational efficiency. Imposing strict validation rules decreases the number of background traces, but results in more false negatives and more computation time. We show that using the geometrical properties of gradient vectors calculated at vessel boundary points as a validation criterion, improves the performance of the seed point detection algorithm. The results illustrate that the proposed method improves upon the prior method in both performance and computation time.

Original languageEnglish
Title of host publicationITNG2010 - 7th International Conference on Information Technology: New Generations
Pages352-357
Number of pages6
DOIs
Publication statusPublished - 2010
Event7th International Conference on Information Technology - New Generations, ITNG 2010 - Las Vegas, NV
Duration: 12 Apr 201014 Apr 2010

Other

Other7th International Conference on Information Technology - New Generations, ITNG 2010
CityLas Vegas, NV
Period12/4/1014/4/10

Fingerprint

Seed
Computational efficiency
Feature extraction

Keywords

  • Feature extraction
  • Real-time systems
  • Segmentation
  • Tracking
  • Vectorial tracing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Boroujeni, F. Z., Wirza, R., Maskon, O., Khosravi, A., & Khalilian, M. (2010). An improved seed point detection algorithm for centerline tracing in coronary angiograms. In ITNG2010 - 7th International Conference on Information Technology: New Generations (pp. 352-357). [5501703] https://doi.org/10.1109/ITNG.2010.195

An improved seed point detection algorithm for centerline tracing in coronary angiograms. / Boroujeni, Farsad Zamani; Wirza, Rahmita; Maskon, Oteh; Khosravi, Alireza; Khalilian, Majid.

ITNG2010 - 7th International Conference on Information Technology: New Generations. 2010. p. 352-357 5501703.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Boroujeni, FZ, Wirza, R, Maskon, O, Khosravi, A & Khalilian, M 2010, An improved seed point detection algorithm for centerline tracing in coronary angiograms. in ITNG2010 - 7th International Conference on Information Technology: New Generations., 5501703, pp. 352-357, 7th International Conference on Information Technology - New Generations, ITNG 2010, Las Vegas, NV, 12/4/10. https://doi.org/10.1109/ITNG.2010.195
Boroujeni FZ, Wirza R, Maskon O, Khosravi A, Khalilian M. An improved seed point detection algorithm for centerline tracing in coronary angiograms. In ITNG2010 - 7th International Conference on Information Technology: New Generations. 2010. p. 352-357. 5501703 https://doi.org/10.1109/ITNG.2010.195
Boroujeni, Farsad Zamani ; Wirza, Rahmita ; Maskon, Oteh ; Khosravi, Alireza ; Khalilian, Majid. / An improved seed point detection algorithm for centerline tracing in coronary angiograms. ITNG2010 - 7th International Conference on Information Technology: New Generations. 2010. pp. 352-357
@inproceedings{171c6fd609584fb3b85e604d21b9ba84,
title = "An improved seed point detection algorithm for centerline tracing in coronary angiograms",
abstract = "This paper presents a new method to detect initial seed points for automatic tracing of the vessel center lines in coronary angiograms. Vessel tracing algorithms are known to be fast and efficient among several feature extraction methods. However, most of them suffer from incomplete results due to inappropriate trade-off between the completeness of seed point detection and computational efficiency. Imposing strict validation rules decreases the number of background traces, but results in more false negatives and more computation time. We show that using the geometrical properties of gradient vectors calculated at vessel boundary points as a validation criterion, improves the performance of the seed point detection algorithm. The results illustrate that the proposed method improves upon the prior method in both performance and computation time.",
keywords = "Feature extraction, Real-time systems, Segmentation, Tracking, Vectorial tracing",
author = "Boroujeni, {Farsad Zamani} and Rahmita Wirza and Oteh Maskon and Alireza Khosravi and Majid Khalilian",
year = "2010",
doi = "10.1109/ITNG.2010.195",
language = "English",
isbn = "9780769539843",
pages = "352--357",
booktitle = "ITNG2010 - 7th International Conference on Information Technology: New Generations",

}

TY - GEN

T1 - An improved seed point detection algorithm for centerline tracing in coronary angiograms

AU - Boroujeni, Farsad Zamani

AU - Wirza, Rahmita

AU - Maskon, Oteh

AU - Khosravi, Alireza

AU - Khalilian, Majid

PY - 2010

Y1 - 2010

N2 - This paper presents a new method to detect initial seed points for automatic tracing of the vessel center lines in coronary angiograms. Vessel tracing algorithms are known to be fast and efficient among several feature extraction methods. However, most of them suffer from incomplete results due to inappropriate trade-off between the completeness of seed point detection and computational efficiency. Imposing strict validation rules decreases the number of background traces, but results in more false negatives and more computation time. We show that using the geometrical properties of gradient vectors calculated at vessel boundary points as a validation criterion, improves the performance of the seed point detection algorithm. The results illustrate that the proposed method improves upon the prior method in both performance and computation time.

AB - This paper presents a new method to detect initial seed points for automatic tracing of the vessel center lines in coronary angiograms. Vessel tracing algorithms are known to be fast and efficient among several feature extraction methods. However, most of them suffer from incomplete results due to inappropriate trade-off between the completeness of seed point detection and computational efficiency. Imposing strict validation rules decreases the number of background traces, but results in more false negatives and more computation time. We show that using the geometrical properties of gradient vectors calculated at vessel boundary points as a validation criterion, improves the performance of the seed point detection algorithm. The results illustrate that the proposed method improves upon the prior method in both performance and computation time.

KW - Feature extraction

KW - Real-time systems

KW - Segmentation

KW - Tracking

KW - Vectorial tracing

UR - http://www.scopus.com/inward/record.url?scp=77955300207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955300207&partnerID=8YFLogxK

U2 - 10.1109/ITNG.2010.195

DO - 10.1109/ITNG.2010.195

M3 - Conference contribution

AN - SCOPUS:77955300207

SN - 9780769539843

SP - 352

EP - 357

BT - ITNG2010 - 7th International Conference on Information Technology: New Generations

ER -