Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography

Didem Yamak, Prasad Panse, William Pavlicek, Thomas Boltz, Metin Akay

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Coronary heart disease (CHD) is the most prevalent cause of death worldwide. Atherosclerosis which is the condition of plaque buildup on the inside of the coronary artery wall is the main cause of CHD. Rupture of unstable atherosclerotic coronary plaque is known to be the cause of acute coronary syndrome. Vulnerability of atherosclerotic plaque has been related to a large lipid core covered by a fibrous cap. Non-invasive assessment of plaque characterization is necessary due to prognostic importance of early stage identification. The purpose of this study is to use the additional attenuation data provided by dual energy computed tomography (DECT) for plaque characterization. We propose to train supervised learners on pixel values recorded from DECT monochromatic X-ray and material basis pairs images, for more precise classification of fibrous and lipid plaques. The interaction of the pixel values from different image types is taken into consideration, as single pixel value might not be informative enough to separate fibrous from lipid. Organic phantom plaques scanned in a fabricated beating heart phantom were used as ground truth to train the learners. Our results show that support vector machines, artificial neural networks and random forests provide accurate results both on phantom and patient data.

Original languageEnglish (US)
Article number6690122
Pages (from-to)939-945
Number of pages7
JournalIEEE Journal of Biomedical and Health Informatics
Volume18
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Atherosclerotic Plaques
Lipids
Tomography
Pixels
Coronary Disease
X Ray Computed Tomography
Acute Coronary Syndrome
Support vector machines
Rupture
Cause of Death
Atherosclerosis
Coronary Vessels
Neural networks
X rays

Keywords

  • Atherosclerosis
  • dual energy computed tomography (DECT)
  • Supervised learning

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management
  • Medicine(all)

Cite this

Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography. / Yamak, Didem; Panse, Prasad; Pavlicek, William; Boltz, Thomas; Akay, Metin.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 18, No. 3, 6690122, 2014, p. 939-945.

Research output: Contribution to journalArticle

Yamak, Didem ; Panse, Prasad ; Pavlicek, William ; Boltz, Thomas ; Akay, Metin. / Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography. In: IEEE Journal of Biomedical and Health Informatics. 2014 ; Vol. 18, No. 3. pp. 939-945.
@article{640e16337d444f3db7dbb7a56cdc79e8,
title = "Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography",
abstract = "Coronary heart disease (CHD) is the most prevalent cause of death worldwide. Atherosclerosis which is the condition of plaque buildup on the inside of the coronary artery wall is the main cause of CHD. Rupture of unstable atherosclerotic coronary plaque is known to be the cause of acute coronary syndrome. Vulnerability of atherosclerotic plaque has been related to a large lipid core covered by a fibrous cap. Non-invasive assessment of plaque characterization is necessary due to prognostic importance of early stage identification. The purpose of this study is to use the additional attenuation data provided by dual energy computed tomography (DECT) for plaque characterization. We propose to train supervised learners on pixel values recorded from DECT monochromatic X-ray and material basis pairs images, for more precise classification of fibrous and lipid plaques. The interaction of the pixel values from different image types is taken into consideration, as single pixel value might not be informative enough to separate fibrous from lipid. Organic phantom plaques scanned in a fabricated beating heart phantom were used as ground truth to train the learners. Our results show that support vector machines, artificial neural networks and random forests provide accurate results both on phantom and patient data.",
keywords = "Atherosclerosis, dual energy computed tomography (DECT), Supervised learning",
author = "Didem Yamak and Prasad Panse and William Pavlicek and Thomas Boltz and Metin Akay",
year = "2014",
doi = "10.1109/JBHI.2013.2295534",
language = "English (US)",
volume = "18",
pages = "939--945",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography

AU - Yamak, Didem

AU - Panse, Prasad

AU - Pavlicek, William

AU - Boltz, Thomas

AU - Akay, Metin

PY - 2014

Y1 - 2014

N2 - Coronary heart disease (CHD) is the most prevalent cause of death worldwide. Atherosclerosis which is the condition of plaque buildup on the inside of the coronary artery wall is the main cause of CHD. Rupture of unstable atherosclerotic coronary plaque is known to be the cause of acute coronary syndrome. Vulnerability of atherosclerotic plaque has been related to a large lipid core covered by a fibrous cap. Non-invasive assessment of plaque characterization is necessary due to prognostic importance of early stage identification. The purpose of this study is to use the additional attenuation data provided by dual energy computed tomography (DECT) for plaque characterization. We propose to train supervised learners on pixel values recorded from DECT monochromatic X-ray and material basis pairs images, for more precise classification of fibrous and lipid plaques. The interaction of the pixel values from different image types is taken into consideration, as single pixel value might not be informative enough to separate fibrous from lipid. Organic phantom plaques scanned in a fabricated beating heart phantom were used as ground truth to train the learners. Our results show that support vector machines, artificial neural networks and random forests provide accurate results both on phantom and patient data.

AB - Coronary heart disease (CHD) is the most prevalent cause of death worldwide. Atherosclerosis which is the condition of plaque buildup on the inside of the coronary artery wall is the main cause of CHD. Rupture of unstable atherosclerotic coronary plaque is known to be the cause of acute coronary syndrome. Vulnerability of atherosclerotic plaque has been related to a large lipid core covered by a fibrous cap. Non-invasive assessment of plaque characterization is necessary due to prognostic importance of early stage identification. The purpose of this study is to use the additional attenuation data provided by dual energy computed tomography (DECT) for plaque characterization. We propose to train supervised learners on pixel values recorded from DECT monochromatic X-ray and material basis pairs images, for more precise classification of fibrous and lipid plaques. The interaction of the pixel values from different image types is taken into consideration, as single pixel value might not be informative enough to separate fibrous from lipid. Organic phantom plaques scanned in a fabricated beating heart phantom were used as ground truth to train the learners. Our results show that support vector machines, artificial neural networks and random forests provide accurate results both on phantom and patient data.

KW - Atherosclerosis

KW - dual energy computed tomography (DECT)

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=84900797319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900797319&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2013.2295534

DO - 10.1109/JBHI.2013.2295534

M3 - Article

C2 - 24808227

AN - SCOPUS:84900797319

VL - 18

SP - 939

EP - 945

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

M1 - 6690122

ER -