Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model

L. Cordero-Grande, G. Vegas-Sánchez-Ferrero, P. Casaseca-de-la-Higuera, J. Alberto San-Román-Calvar, Ana Revilla-Orodea, M. Martín-Fernández, C. Alberola-Lopez

Research output: Contribution to journalArticle

Abstract

A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.

Original languageEnglish
Pages (from-to)283-301
Number of pages19
JournalMedical Image Analysis
Volume15
Issue number3
DOIs
Publication statusPublished - Jun 2011
Externally publishedYes

Fingerprint

Myocardium
Maximum likelihood estimation
Stochastic models
Image analysis
Heart Ventricles
Myocardial Infarction
Magnetic Resonance Imaging

Keywords

  • Algorithms
  • Artificial Intelligence
  • Computer Simulation
  • Humans
  • Image Enhancement
  • Image Interpretation, Computer-Assisted
  • Imaging, Three-Dimensional
  • Magnetic Resonance Imaging, Cine
  • Markov Chains
  • Models, Biological
  • Models, Cardiovascular
  • Models, Statistical
  • Pattern Recognition, Automated
  • Reproducibility of Results
  • Sensitivity and Specificity

Cite this

Cordero-Grande, L., Vegas-Sánchez-Ferrero, G., Casaseca-de-la-Higuera, P., San-Román-Calvar, J. A., Revilla-Orodea, A., Martín-Fernández, M., & Alberola-Lopez, C. (2011). Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model. Medical Image Analysis, 15(3), 283-301. https://doi.org/10.1016/j.media.2011.01.002
Cordero-Grande, L. ; Vegas-Sánchez-Ferrero, G. ; Casaseca-de-la-Higuera, P. ; San-Román-Calvar, J. Alberto ; Revilla-Orodea, Ana ; Martín-Fernández, M. ; Alberola-Lopez, C. / Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model. In: Medical Image Analysis. 2011 ; Vol. 15, No. 3. pp. 283-301.
@article{5c8cb883cf08471ba6d304d30f15a33c,
title = "Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model",
abstract = "A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.",
keywords = "Algorithms, Artificial Intelligence, Computer Simulation, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Imaging, Three-Dimensional, Magnetic Resonance Imaging, Cine, Markov Chains, Models, Biological, Models, Cardiovascular, Models, Statistical, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity",
author = "L. Cordero-Grande and G. Vegas-S{\'a}nchez-Ferrero and P. Casaseca-de-la-Higuera and San-Rom{\'a}n-Calvar, {J. Alberto} and Ana Revilla-Orodea and M. Mart{\'i}n-Fern{\'a}ndez and C. Alberola-Lopez",
note = "Copyright {\circledC} 2011 Elsevier B.V. All rights reserved.",
year = "2011",
month = "6",
doi = "10.1016/j.media.2011.01.002",
language = "English",
volume = "15",
pages = "283--301",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier B.V.",
number = "3",

}

Cordero-Grande, L, Vegas-Sánchez-Ferrero, G, Casaseca-de-la-Higuera, P, San-Román-Calvar, JA, Revilla-Orodea, A, Martín-Fernández, M & Alberola-Lopez, C 2011, 'Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model' Medical Image Analysis, vol. 15, no. 3, pp. 283-301. https://doi.org/10.1016/j.media.2011.01.002

Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model. / Cordero-Grande, L.; Vegas-Sánchez-Ferrero, G.; Casaseca-de-la-Higuera, P.; San-Román-Calvar, J. Alberto; Revilla-Orodea, Ana; Martín-Fernández, M.; Alberola-Lopez, C.

In: Medical Image Analysis, Vol. 15, No. 3, 06.2011, p. 283-301.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model

AU - Cordero-Grande, L.

AU - Vegas-Sánchez-Ferrero, G.

AU - Casaseca-de-la-Higuera, P.

AU - San-Román-Calvar, J. Alberto

AU - Revilla-Orodea, Ana

AU - Martín-Fernández, M.

AU - Alberola-Lopez, C.

N1 - Copyright © 2011 Elsevier B.V. All rights reserved.

PY - 2011/6

Y1 - 2011/6

N2 - A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.

AB - A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.

KW - Algorithms

KW - Artificial Intelligence

KW - Computer Simulation

KW - Humans

KW - Image Enhancement

KW - Image Interpretation, Computer-Assisted

KW - Imaging, Three-Dimensional

KW - Magnetic Resonance Imaging, Cine

KW - Markov Chains

KW - Models, Biological

KW - Models, Cardiovascular

KW - Models, Statistical

KW - Pattern Recognition, Automated

KW - Reproducibility of Results

KW - Sensitivity and Specificity

U2 - 10.1016/j.media.2011.01.002

DO - 10.1016/j.media.2011.01.002

M3 - Article

VL - 15

SP - 283

EP - 301

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 3

ER -

Cordero-Grande L, Vegas-Sánchez-Ferrero G, Casaseca-de-la-Higuera P, San-Román-Calvar JA, Revilla-Orodea A, Martín-Fernández M et al. Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model. Medical Image Analysis. 2011 Jun;15(3):283-301. https://doi.org/10.1016/j.media.2011.01.002