A statistical shape model of the left ventricle from real-time 3D echocardiography and its application to myocardial segmentation of cardiac magnetic resonance images

M. C. Carminati, C. Piazzese, M. Pepi, G. Tamborini, P. Gripari, G. Pontone, R. Krause, A. Auricchio, R. M. Lang, E. G. Caiani

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Object: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. Material and methods: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. Results: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89%), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. Conclusions: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.

Original languageEnglish
Pages (from-to)241-251
Number of pages11
JournalComputers in Biology and Medicine
Volume96
DOIs
Publication statusPublished - May 1 2018

Fingerprint

Three-Dimensional Echocardiography
Echocardiography
Statistical Models
Magnetic resonance
Heart Ventricles
Magnetic Resonance Spectroscopy
Endocardium
Pericardium
Pathology
Linear regression
Testing
Processing
Linear Models
Myocardium
Databases

Keywords

  • Cine
  • Computer-assisted
  • Diagnostic imaging
  • Echocardiography
  • Image processing
  • Imaging
  • Magnetic resonance imaging
  • Three-dimensional

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

A statistical shape model of the left ventricle from real-time 3D echocardiography and its application to myocardial segmentation of cardiac magnetic resonance images. / Carminati, M. C.; Piazzese, C.; Pepi, M.; Tamborini, G.; Gripari, P.; Pontone, G.; Krause, R.; Auricchio, A.; Lang, R. M.; Caiani, E. G.

In: Computers in Biology and Medicine, Vol. 96, 01.05.2018, p. 241-251.

Research output: Contribution to journalArticle

@article{ff26af6b9e26493aaf3e5b7edba81aba,
title = "A statistical shape model of the left ventricle from real-time 3D echocardiography and its application to myocardial segmentation of cardiac magnetic resonance images",
abstract = "Object: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. Material and methods: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. Results: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89{\%}), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. Conclusions: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.",
keywords = "Cine, Computer-assisted, Diagnostic imaging, Echocardiography, Image processing, Imaging, Magnetic resonance imaging, Three-dimensional",
author = "Carminati, {M. C.} and C. Piazzese and M. Pepi and G. Tamborini and P. Gripari and G. Pontone and R. Krause and A. Auricchio and Lang, {R. M.} and Caiani, {E. G.}",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.compbiomed.2018.03.013",
language = "English",
volume = "96",
pages = "241--251",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A statistical shape model of the left ventricle from real-time 3D echocardiography and its application to myocardial segmentation of cardiac magnetic resonance images

AU - Carminati, M. C.

AU - Piazzese, C.

AU - Pepi, M.

AU - Tamborini, G.

AU - Gripari, P.

AU - Pontone, G.

AU - Krause, R.

AU - Auricchio, A.

AU - Lang, R. M.

AU - Caiani, E. G.

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Object: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. Material and methods: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. Results: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89%), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. Conclusions: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.

AB - Object: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. Material and methods: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. Results: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89%), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. Conclusions: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.

KW - Cine

KW - Computer-assisted

KW - Diagnostic imaging

KW - Echocardiography

KW - Image processing

KW - Imaging

KW - Magnetic resonance imaging

KW - Three-dimensional

UR - http://www.scopus.com/inward/record.url?scp=85045551856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045551856&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2018.03.013

DO - 10.1016/j.compbiomed.2018.03.013

M3 - Article

AN - SCOPUS:85045551856

VL - 96

SP - 241

EP - 251

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -