Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images

Ioannis S Chatzizisis, Vassilis G. Koutkias, Konstantinos Toutouzas, Andreas Giannopoulos, Ioanna Chouvarda, Maria Riga, Antonios P. Antoniadis, Grigorios Cheimariotis, Charalampos Doulaverakis, Ioannis Tsampoulatidis, Konstantina Bouki, Ioannis Kompatsiaris, Christodoulos Stefanadis, Nicos Maglaveras, George D. Giannoglou

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Objectives The analysis of intracoronary optical coherence tomography (OCT) images is based on manual identification of the lumen contours and relevant structures. However, manual image segmentation is a cumbersome and time-consuming process, subject to significant intra- and inter-observer variability. This study aims to present and validate a fully-automated method for segmentation of intracoronary OCT images. Methods We studied 20 coronary arteries (mean length = 39.7 ± 10.0 mm) from 20 patients who underwent a clinically-indicated cardiac catheterization. The OCT images (n = 1812) were segmented manually, as well as with a fully-automated approach. A semi-automated variation of the fully-automated algorithm was also applied. Using certain lumen size and lumen shape characteristics, the fully- and semi-automated segmentation algorithms were validated over manual segmentation, which was considered as the gold standard. Results Linear regression and Bland-Altman analysis demonstrated that both the fully-automated and semi-automated segmentation had a very high agreement with the manual segmentation, with the semi-automated approach being slightly more accurate than the fully-automated method. The fully-automated and semi-automated OCT segmentation reduced the analysis time by more than 97% and 86%, respectively, compared to manual segmentation. Conclusions In the current work we validated a fully-automated OCT segmentation algorithm, as well as a semi-automated variation of it in an extensive "real-life" dataset of OCT images. The study showed that our algorithm can perform rapid and reliable segmentation of OCT images.

Original languageEnglish (US)
Pages (from-to)568-580
Number of pages13
JournalInternational Journal of Cardiology
Volume172
Issue number3
DOIs
StatePublished - Apr 1 2014

Fingerprint

Optical Coherence Tomography
Observer Variation
Cardiac Catheterization
Linear Models
Coronary Vessels

Keywords

  • Image processing
  • Image segmentation
  • Method comparison study
  • Optical coherence tomography

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images. / Chatzizisis, Ioannis S; Koutkias, Vassilis G.; Toutouzas, Konstantinos; Giannopoulos, Andreas; Chouvarda, Ioanna; Riga, Maria; Antoniadis, Antonios P.; Cheimariotis, Grigorios; Doulaverakis, Charalampos; Tsampoulatidis, Ioannis; Bouki, Konstantina; Kompatsiaris, Ioannis; Stefanadis, Christodoulos; Maglaveras, Nicos; Giannoglou, George D.

In: International Journal of Cardiology, Vol. 172, No. 3, 01.04.2014, p. 568-580.

Research output: Contribution to journalArticle

Chatzizisis, IS, Koutkias, VG, Toutouzas, K, Giannopoulos, A, Chouvarda, I, Riga, M, Antoniadis, AP, Cheimariotis, G, Doulaverakis, C, Tsampoulatidis, I, Bouki, K, Kompatsiaris, I, Stefanadis, C, Maglaveras, N & Giannoglou, GD 2014, 'Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images', International Journal of Cardiology, vol. 172, no. 3, pp. 568-580. https://doi.org/10.1016/j.ijcard.2014.01.071
Chatzizisis, Ioannis S ; Koutkias, Vassilis G. ; Toutouzas, Konstantinos ; Giannopoulos, Andreas ; Chouvarda, Ioanna ; Riga, Maria ; Antoniadis, Antonios P. ; Cheimariotis, Grigorios ; Doulaverakis, Charalampos ; Tsampoulatidis, Ioannis ; Bouki, Konstantina ; Kompatsiaris, Ioannis ; Stefanadis, Christodoulos ; Maglaveras, Nicos ; Giannoglou, George D. / Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images. In: International Journal of Cardiology. 2014 ; Vol. 172, No. 3. pp. 568-580.
@article{dbcb9d585662413abab5c6e13d11f931,
title = "Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images",
abstract = "Objectives The analysis of intracoronary optical coherence tomography (OCT) images is based on manual identification of the lumen contours and relevant structures. However, manual image segmentation is a cumbersome and time-consuming process, subject to significant intra- and inter-observer variability. This study aims to present and validate a fully-automated method for segmentation of intracoronary OCT images. Methods We studied 20 coronary arteries (mean length = 39.7 ± 10.0 mm) from 20 patients who underwent a clinically-indicated cardiac catheterization. The OCT images (n = 1812) were segmented manually, as well as with a fully-automated approach. A semi-automated variation of the fully-automated algorithm was also applied. Using certain lumen size and lumen shape characteristics, the fully- and semi-automated segmentation algorithms were validated over manual segmentation, which was considered as the gold standard. Results Linear regression and Bland-Altman analysis demonstrated that both the fully-automated and semi-automated segmentation had a very high agreement with the manual segmentation, with the semi-automated approach being slightly more accurate than the fully-automated method. The fully-automated and semi-automated OCT segmentation reduced the analysis time by more than 97{\%} and 86{\%}, respectively, compared to manual segmentation. Conclusions In the current work we validated a fully-automated OCT segmentation algorithm, as well as a semi-automated variation of it in an extensive {"}real-life{"} dataset of OCT images. The study showed that our algorithm can perform rapid and reliable segmentation of OCT images.",
keywords = "Image processing, Image segmentation, Method comparison study, Optical coherence tomography",
author = "Chatzizisis, {Ioannis S} and Koutkias, {Vassilis G.} and Konstantinos Toutouzas and Andreas Giannopoulos and Ioanna Chouvarda and Maria Riga and Antoniadis, {Antonios P.} and Grigorios Cheimariotis and Charalampos Doulaverakis and Ioannis Tsampoulatidis and Konstantina Bouki and Ioannis Kompatsiaris and Christodoulos Stefanadis and Nicos Maglaveras and Giannoglou, {George D.}",
year = "2014",
month = "4",
day = "1",
doi = "10.1016/j.ijcard.2014.01.071",
language = "English (US)",
volume = "172",
pages = "568--580",
journal = "International Journal of Cardiology",
issn = "0167-5273",
publisher = "Elsevier Ireland Ltd",
number = "3",

}

TY - JOUR

T1 - Clinical validation of an algorithm for rapid and accurate automated segmentation of intracoronary optical coherence tomography images

AU - Chatzizisis, Ioannis S

AU - Koutkias, Vassilis G.

AU - Toutouzas, Konstantinos

AU - Giannopoulos, Andreas

AU - Chouvarda, Ioanna

AU - Riga, Maria

AU - Antoniadis, Antonios P.

AU - Cheimariotis, Grigorios

AU - Doulaverakis, Charalampos

AU - Tsampoulatidis, Ioannis

AU - Bouki, Konstantina

AU - Kompatsiaris, Ioannis

AU - Stefanadis, Christodoulos

AU - Maglaveras, Nicos

AU - Giannoglou, George D.

PY - 2014/4/1

Y1 - 2014/4/1

N2 - Objectives The analysis of intracoronary optical coherence tomography (OCT) images is based on manual identification of the lumen contours and relevant structures. However, manual image segmentation is a cumbersome and time-consuming process, subject to significant intra- and inter-observer variability. This study aims to present and validate a fully-automated method for segmentation of intracoronary OCT images. Methods We studied 20 coronary arteries (mean length = 39.7 ± 10.0 mm) from 20 patients who underwent a clinically-indicated cardiac catheterization. The OCT images (n = 1812) were segmented manually, as well as with a fully-automated approach. A semi-automated variation of the fully-automated algorithm was also applied. Using certain lumen size and lumen shape characteristics, the fully- and semi-automated segmentation algorithms were validated over manual segmentation, which was considered as the gold standard. Results Linear regression and Bland-Altman analysis demonstrated that both the fully-automated and semi-automated segmentation had a very high agreement with the manual segmentation, with the semi-automated approach being slightly more accurate than the fully-automated method. The fully-automated and semi-automated OCT segmentation reduced the analysis time by more than 97% and 86%, respectively, compared to manual segmentation. Conclusions In the current work we validated a fully-automated OCT segmentation algorithm, as well as a semi-automated variation of it in an extensive "real-life" dataset of OCT images. The study showed that our algorithm can perform rapid and reliable segmentation of OCT images.

AB - Objectives The analysis of intracoronary optical coherence tomography (OCT) images is based on manual identification of the lumen contours and relevant structures. However, manual image segmentation is a cumbersome and time-consuming process, subject to significant intra- and inter-observer variability. This study aims to present and validate a fully-automated method for segmentation of intracoronary OCT images. Methods We studied 20 coronary arteries (mean length = 39.7 ± 10.0 mm) from 20 patients who underwent a clinically-indicated cardiac catheterization. The OCT images (n = 1812) were segmented manually, as well as with a fully-automated approach. A semi-automated variation of the fully-automated algorithm was also applied. Using certain lumen size and lumen shape characteristics, the fully- and semi-automated segmentation algorithms were validated over manual segmentation, which was considered as the gold standard. Results Linear regression and Bland-Altman analysis demonstrated that both the fully-automated and semi-automated segmentation had a very high agreement with the manual segmentation, with the semi-automated approach being slightly more accurate than the fully-automated method. The fully-automated and semi-automated OCT segmentation reduced the analysis time by more than 97% and 86%, respectively, compared to manual segmentation. Conclusions In the current work we validated a fully-automated OCT segmentation algorithm, as well as a semi-automated variation of it in an extensive "real-life" dataset of OCT images. The study showed that our algorithm can perform rapid and reliable segmentation of OCT images.

KW - Image processing

KW - Image segmentation

KW - Method comparison study

KW - Optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=84900645169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900645169&partnerID=8YFLogxK

U2 - 10.1016/j.ijcard.2014.01.071

DO - 10.1016/j.ijcard.2014.01.071

M3 - Article

VL - 172

SP - 568

EP - 580

JO - International Journal of Cardiology

JF - International Journal of Cardiology

SN - 0167-5273

IS - 3

ER -