ARC–OCT

Automatic detection of lumen border in intravascular OCT images

Grigorios Aris Cheimariotis, Ioannis S Chatzizisis, Vassilis G. Koutkias, Konstantinos Toutouzas, Andreas Giannopoulos, Maria Riga, Ioanna Chouvarda, Antonios P. Antoniadis, Charalambos Doulaverakis, Ioannis Tsamboulatidis, Ioannis Kompatsiaris, George D. Giannoglou, Nicos Maglaveras

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Background and Objective Intravascular optical coherence tomography (OCT) is an invaluable tool for the detection of pathological features on the arterial wall and the investigation of post-stenting complications. Computational lumen border detection in OCT images is highly advantageous, since it may support rapid morphometric analysis. However, automatic detection is very challenging, since OCT images typically include various artifacts that impact image clarity, including features such as side branches and intraluminal blood presence. This paper presents ARC–OCT, a segmentation method for fully-automatic detection of lumen border in OCT images. Methods ARC–OCT relies on multiple, consecutive processing steps, accounting for image preparation, contour extraction and refinement. In particular, for contour extraction ARC–OCT employs the transformation of OCT images based on physical characteristics such as reflectivity and absorption of the tissue and, for contour refinement, local regression using weighted linear least squares and a 2nd degree polynomial model is employed to achieve artifact and small-branch correction as well as smoothness of the artery mesh. Our major focus was to achieve accurate contour delineation in the various types of OCT images, i.e., even in challenging cases with branches and artifacts. Results ARC–OCT has been assessed in a dataset of 1812 images (308 from stented and 1504 from native segments) obtained from 20 patients. ARC–OCT was compared against ground-truth manual segmentation performed by experts on the basis of various geometric features (e.g. area, perimeter, radius, diameter, centroid, etc.) and closed contour matching indicators (the Dice index, the Hausdorff distance and the undirected average distance), using standard statistical analysis methods. The proposed method was proven very efficient and close to the ground-truth, exhibiting non statistically-significant differences for most of the examined metrics. Conclusions ARC–OCT allows accurate and fully-automated lumen border detection in OCT images.

Original languageEnglish (US)
Pages (from-to)21-32
Number of pages12
JournalComputer Methods and Programs in Biomedicine
Volume151
DOIs
StatePublished - Nov 1 2017

Fingerprint

Optical tomography
Optical Coherence Tomography
Artifacts
Statistical Models
Least-Squares Analysis
Statistical methods
Blood
Arteries
Tissue
Processing

Keywords

  • Automatic segmentation
  • Contour extraction
  • Intravascular optical coherence tomography (OCT)
  • Lumen–Endothelium border

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Cheimariotis, G. A., Chatzizisis, I. S., Koutkias, V. G., Toutouzas, K., Giannopoulos, A., Riga, M., ... Maglaveras, N. (2017). ARC–OCT: Automatic detection of lumen border in intravascular OCT images. Computer Methods and Programs in Biomedicine, 151, 21-32. https://doi.org/10.1016/j.cmpb.2017.08.007

ARC–OCT : Automatic detection of lumen border in intravascular OCT images. / Cheimariotis, Grigorios Aris; Chatzizisis, Ioannis S; Koutkias, Vassilis G.; Toutouzas, Konstantinos; Giannopoulos, Andreas; Riga, Maria; Chouvarda, Ioanna; Antoniadis, Antonios P.; Doulaverakis, Charalambos; Tsamboulatidis, Ioannis; Kompatsiaris, Ioannis; Giannoglou, George D.; Maglaveras, Nicos.

In: Computer Methods and Programs in Biomedicine, Vol. 151, 01.11.2017, p. 21-32.

Research output: Contribution to journalArticle

Cheimariotis, GA, Chatzizisis, IS, Koutkias, VG, Toutouzas, K, Giannopoulos, A, Riga, M, Chouvarda, I, Antoniadis, AP, Doulaverakis, C, Tsamboulatidis, I, Kompatsiaris, I, Giannoglou, GD & Maglaveras, N 2017, 'ARC–OCT: Automatic detection of lumen border in intravascular OCT images', Computer Methods and Programs in Biomedicine, vol. 151, pp. 21-32. https://doi.org/10.1016/j.cmpb.2017.08.007
Cheimariotis, Grigorios Aris ; Chatzizisis, Ioannis S ; Koutkias, Vassilis G. ; Toutouzas, Konstantinos ; Giannopoulos, Andreas ; Riga, Maria ; Chouvarda, Ioanna ; Antoniadis, Antonios P. ; Doulaverakis, Charalambos ; Tsamboulatidis, Ioannis ; Kompatsiaris, Ioannis ; Giannoglou, George D. ; Maglaveras, Nicos. / ARC–OCT : Automatic detection of lumen border in intravascular OCT images. In: Computer Methods and Programs in Biomedicine. 2017 ; Vol. 151. pp. 21-32.
@article{e9f4a77c93764b9ab82b9459f6a66101,
title = "ARC–OCT: Automatic detection of lumen border in intravascular OCT images",
abstract = "Background and Objective Intravascular optical coherence tomography (OCT) is an invaluable tool for the detection of pathological features on the arterial wall and the investigation of post-stenting complications. Computational lumen border detection in OCT images is highly advantageous, since it may support rapid morphometric analysis. However, automatic detection is very challenging, since OCT images typically include various artifacts that impact image clarity, including features such as side branches and intraluminal blood presence. This paper presents ARC–OCT, a segmentation method for fully-automatic detection of lumen border in OCT images. Methods ARC–OCT relies on multiple, consecutive processing steps, accounting for image preparation, contour extraction and refinement. In particular, for contour extraction ARC–OCT employs the transformation of OCT images based on physical characteristics such as reflectivity and absorption of the tissue and, for contour refinement, local regression using weighted linear least squares and a 2nd degree polynomial model is employed to achieve artifact and small-branch correction as well as smoothness of the artery mesh. Our major focus was to achieve accurate contour delineation in the various types of OCT images, i.e., even in challenging cases with branches and artifacts. Results ARC–OCT has been assessed in a dataset of 1812 images (308 from stented and 1504 from native segments) obtained from 20 patients. ARC–OCT was compared against ground-truth manual segmentation performed by experts on the basis of various geometric features (e.g. area, perimeter, radius, diameter, centroid, etc.) and closed contour matching indicators (the Dice index, the Hausdorff distance and the undirected average distance), using standard statistical analysis methods. The proposed method was proven very efficient and close to the ground-truth, exhibiting non statistically-significant differences for most of the examined metrics. Conclusions ARC–OCT allows accurate and fully-automated lumen border detection in OCT images.",
keywords = "Automatic segmentation, Contour extraction, Intravascular optical coherence tomography (OCT), Lumen–Endothelium border",
author = "Cheimariotis, {Grigorios Aris} and Chatzizisis, {Ioannis S} and Koutkias, {Vassilis G.} and Konstantinos Toutouzas and Andreas Giannopoulos and Maria Riga and Ioanna Chouvarda and Antoniadis, {Antonios P.} and Charalambos Doulaverakis and Ioannis Tsamboulatidis and Ioannis Kompatsiaris and Giannoglou, {George D.} and Nicos Maglaveras",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.cmpb.2017.08.007",
language = "English (US)",
volume = "151",
pages = "21--32",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - ARC–OCT

T2 - Automatic detection of lumen border in intravascular OCT images

AU - Cheimariotis, Grigorios Aris

AU - Chatzizisis, Ioannis S

AU - Koutkias, Vassilis G.

AU - Toutouzas, Konstantinos

AU - Giannopoulos, Andreas

AU - Riga, Maria

AU - Chouvarda, Ioanna

AU - Antoniadis, Antonios P.

AU - Doulaverakis, Charalambos

AU - Tsamboulatidis, Ioannis

AU - Kompatsiaris, Ioannis

AU - Giannoglou, George D.

AU - Maglaveras, Nicos

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Background and Objective Intravascular optical coherence tomography (OCT) is an invaluable tool for the detection of pathological features on the arterial wall and the investigation of post-stenting complications. Computational lumen border detection in OCT images is highly advantageous, since it may support rapid morphometric analysis. However, automatic detection is very challenging, since OCT images typically include various artifacts that impact image clarity, including features such as side branches and intraluminal blood presence. This paper presents ARC–OCT, a segmentation method for fully-automatic detection of lumen border in OCT images. Methods ARC–OCT relies on multiple, consecutive processing steps, accounting for image preparation, contour extraction and refinement. In particular, for contour extraction ARC–OCT employs the transformation of OCT images based on physical characteristics such as reflectivity and absorption of the tissue and, for contour refinement, local regression using weighted linear least squares and a 2nd degree polynomial model is employed to achieve artifact and small-branch correction as well as smoothness of the artery mesh. Our major focus was to achieve accurate contour delineation in the various types of OCT images, i.e., even in challenging cases with branches and artifacts. Results ARC–OCT has been assessed in a dataset of 1812 images (308 from stented and 1504 from native segments) obtained from 20 patients. ARC–OCT was compared against ground-truth manual segmentation performed by experts on the basis of various geometric features (e.g. area, perimeter, radius, diameter, centroid, etc.) and closed contour matching indicators (the Dice index, the Hausdorff distance and the undirected average distance), using standard statistical analysis methods. The proposed method was proven very efficient and close to the ground-truth, exhibiting non statistically-significant differences for most of the examined metrics. Conclusions ARC–OCT allows accurate and fully-automated lumen border detection in OCT images.

AB - Background and Objective Intravascular optical coherence tomography (OCT) is an invaluable tool for the detection of pathological features on the arterial wall and the investigation of post-stenting complications. Computational lumen border detection in OCT images is highly advantageous, since it may support rapid morphometric analysis. However, automatic detection is very challenging, since OCT images typically include various artifacts that impact image clarity, including features such as side branches and intraluminal blood presence. This paper presents ARC–OCT, a segmentation method for fully-automatic detection of lumen border in OCT images. Methods ARC–OCT relies on multiple, consecutive processing steps, accounting for image preparation, contour extraction and refinement. In particular, for contour extraction ARC–OCT employs the transformation of OCT images based on physical characteristics such as reflectivity and absorption of the tissue and, for contour refinement, local regression using weighted linear least squares and a 2nd degree polynomial model is employed to achieve artifact and small-branch correction as well as smoothness of the artery mesh. Our major focus was to achieve accurate contour delineation in the various types of OCT images, i.e., even in challenging cases with branches and artifacts. Results ARC–OCT has been assessed in a dataset of 1812 images (308 from stented and 1504 from native segments) obtained from 20 patients. ARC–OCT was compared against ground-truth manual segmentation performed by experts on the basis of various geometric features (e.g. area, perimeter, radius, diameter, centroid, etc.) and closed contour matching indicators (the Dice index, the Hausdorff distance and the undirected average distance), using standard statistical analysis methods. The proposed method was proven very efficient and close to the ground-truth, exhibiting non statistically-significant differences for most of the examined metrics. Conclusions ARC–OCT allows accurate and fully-automated lumen border detection in OCT images.

KW - Automatic segmentation

KW - Contour extraction

KW - Intravascular optical coherence tomography (OCT)

KW - Lumen–Endothelium border

UR - http://www.scopus.com/inward/record.url?scp=85027682292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027682292&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2017.08.007

DO - 10.1016/j.cmpb.2017.08.007

M3 - Article

VL - 151

SP - 21

EP - 32

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -