Myocardium segmentation in strain-encoded (SENC) magnetic resonance images using graph-cuts

Ahmed O. Al-Agamy, Nael Fakhry Osman, Ahmed S. Fahmy

Research output: Contribution to journalArticle

Abstract

Evaluation of cardiac functions using Strain Encoded (SENC) magnetic resonance (MR) imaging is a powerful tool for imaging the deformation of left and right ventricles. However, automated analysis of SENC images is hindered due to the low signal-to-noise ratio SENC images. In this work, the authors propose a method to segment the left and right ventricles myocardium simultaneously in SENC-MR short-axis images. In addition, myocardium seed points are automatically selected using skeletonisation algorithm and used as hard constraints for the graph-cut optimization algorithm. The method is based on a modified formulation of the graph-cuts energy term. In the new formulation, a signal probabilistic model is used, rather than the image histogram, to capture the characteristics of the blood and tissue signals and include it in the cost function of the graph-cuts algorithm. The method is applied to SENC datasets for 11 human subjects (five normal and six patients with known myocardial wall motion abnormality). The segmentation results of the proposed method are compared with those resulting from both manual segmentation and the conventional histogram-based graph-cuts segmentation algorithm. The results show that the proposed method outperforms the histogram-based graph-cuts algorithm especially to segment the thin structure of the right ventricle.

Original languageEnglish (US)
Pages (from-to)415-422
Number of pages8
JournalIET Image Processing
Volume7
Issue number5
DOIs
StatePublished - 2013

Fingerprint

Magnetic resonance
Imaging techniques
Cost functions
Seed
Signal to noise ratio
Blood
Tissue

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Software
  • Computer Vision and Pattern Recognition

Cite this

Myocardium segmentation in strain-encoded (SENC) magnetic resonance images using graph-cuts. / Al-Agamy, Ahmed O.; Osman, Nael Fakhry; Fahmy, Ahmed S.

In: IET Image Processing, Vol. 7, No. 5, 2013, p. 415-422.

Research output: Contribution to journalArticle

@article{3fe940673fff46418eacc52ac9c0ec7c,
title = "Myocardium segmentation in strain-encoded (SENC) magnetic resonance images using graph-cuts",
abstract = "Evaluation of cardiac functions using Strain Encoded (SENC) magnetic resonance (MR) imaging is a powerful tool for imaging the deformation of left and right ventricles. However, automated analysis of SENC images is hindered due to the low signal-to-noise ratio SENC images. In this work, the authors propose a method to segment the left and right ventricles myocardium simultaneously in SENC-MR short-axis images. In addition, myocardium seed points are automatically selected using skeletonisation algorithm and used as hard constraints for the graph-cut optimization algorithm. The method is based on a modified formulation of the graph-cuts energy term. In the new formulation, a signal probabilistic model is used, rather than the image histogram, to capture the characteristics of the blood and tissue signals and include it in the cost function of the graph-cuts algorithm. The method is applied to SENC datasets for 11 human subjects (five normal and six patients with known myocardial wall motion abnormality). The segmentation results of the proposed method are compared with those resulting from both manual segmentation and the conventional histogram-based graph-cuts segmentation algorithm. The results show that the proposed method outperforms the histogram-based graph-cuts algorithm especially to segment the thin structure of the right ventricle.",
author = "Al-Agamy, {Ahmed O.} and Osman, {Nael Fakhry} and Fahmy, {Ahmed S.}",
year = "2013",
doi = "10.1049/iet-ipr.2012.0513",
language = "English (US)",
volume = "7",
pages = "415--422",
journal = "IET Image Processing",
issn = "1751-9659",
publisher = "Institution of Engineering and Technology",
number = "5",

}

TY - JOUR

T1 - Myocardium segmentation in strain-encoded (SENC) magnetic resonance images using graph-cuts

AU - Al-Agamy, Ahmed O.

AU - Osman, Nael Fakhry

AU - Fahmy, Ahmed S.

PY - 2013

Y1 - 2013

N2 - Evaluation of cardiac functions using Strain Encoded (SENC) magnetic resonance (MR) imaging is a powerful tool for imaging the deformation of left and right ventricles. However, automated analysis of SENC images is hindered due to the low signal-to-noise ratio SENC images. In this work, the authors propose a method to segment the left and right ventricles myocardium simultaneously in SENC-MR short-axis images. In addition, myocardium seed points are automatically selected using skeletonisation algorithm and used as hard constraints for the graph-cut optimization algorithm. The method is based on a modified formulation of the graph-cuts energy term. In the new formulation, a signal probabilistic model is used, rather than the image histogram, to capture the characteristics of the blood and tissue signals and include it in the cost function of the graph-cuts algorithm. The method is applied to SENC datasets for 11 human subjects (five normal and six patients with known myocardial wall motion abnormality). The segmentation results of the proposed method are compared with those resulting from both manual segmentation and the conventional histogram-based graph-cuts segmentation algorithm. The results show that the proposed method outperforms the histogram-based graph-cuts algorithm especially to segment the thin structure of the right ventricle.

AB - Evaluation of cardiac functions using Strain Encoded (SENC) magnetic resonance (MR) imaging is a powerful tool for imaging the deformation of left and right ventricles. However, automated analysis of SENC images is hindered due to the low signal-to-noise ratio SENC images. In this work, the authors propose a method to segment the left and right ventricles myocardium simultaneously in SENC-MR short-axis images. In addition, myocardium seed points are automatically selected using skeletonisation algorithm and used as hard constraints for the graph-cut optimization algorithm. The method is based on a modified formulation of the graph-cuts energy term. In the new formulation, a signal probabilistic model is used, rather than the image histogram, to capture the characteristics of the blood and tissue signals and include it in the cost function of the graph-cuts algorithm. The method is applied to SENC datasets for 11 human subjects (five normal and six patients with known myocardial wall motion abnormality). The segmentation results of the proposed method are compared with those resulting from both manual segmentation and the conventional histogram-based graph-cuts segmentation algorithm. The results show that the proposed method outperforms the histogram-based graph-cuts algorithm especially to segment the thin structure of the right ventricle.

UR - http://www.scopus.com/inward/record.url?scp=84884543013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884543013&partnerID=8YFLogxK

U2 - 10.1049/iet-ipr.2012.0513

DO - 10.1049/iet-ipr.2012.0513

M3 - Article

AN - SCOPUS:84884543013

VL - 7

SP - 415

EP - 422

JO - IET Image Processing

JF - IET Image Processing

SN - 1751-9659

IS - 5

ER -