Evaluation of cardiac biventricular segmentation from multiaxis MRI data: A multicenter study

Jyrki Lötjönen (Corresponding Author), Vesa Järvinen, Cheong Benjamin, Edwin Wu, Sari Kivistö, Juha Koikkalainen, Jussi Mattila, Helena Kervinen, Raja Muthupillai, Florence Sheehan, Kirsi Lauerma

Research output: Contribution to journalArticleScientificpeer-review

22 Citations (Scopus)

Abstract

Purpose: To validate a volumetric biventricular segmentation solution for multiaxis cardiac magnetic resonance (CMR) images.

Materials and Methods: The study population comprised 40 subjects. Biventricular end‐diastolic and ‐systolic phases were segmented from both short‐axis and horizontal long‐axis or transaxial cine CMR images. Segmentation was based on fitting nonrigidly a 3D surface model to multiaxis CMR images. Five segmentations were performed: two manual segmentations by experts, automatic segmentation, and two segmentations where a user was allowed to correct errors in the automatic segmentation for 2 minutes and without time limits. Volumetry, distance measures, and visual grading were used to evaluate the quality of the segmentation.

Results: No difference was observed between automatic and manual segmentations in volumetric measures of the ventricles. The manual segmentation performed better for left‐ventricular myocardial volume. The distance between surfaces as well as visual analysis did not show differences between automatic and manual segmentation for the endocardial border of the left ventricle but some corrections are needed for the right ventricle.

Conclusion: Fully automatic segmentation produces good results in the assessment of left ventricular volume andendocardial border. Two minutes of user interaction are needed to obtain accurate results for the right ventricle.
Original languageEnglish
Pages (from-to)626-636
JournalJournal of Magnetic Resonance Imaging
Volume28
Issue number3
DOIs
Publication statusPublished - 2008
MoE publication typeA1 Journal article-refereed

Fingerprint

Multicenter Studies
Heart Ventricles
Magnetic Resonance Spectroscopy
Population

Keywords

  • segmentation
  • cardiac CMR
  • volumetry
  • right ventricle

Cite this

Lötjönen, J., Järvinen, V., Benjamin, C., Wu, E., Kivistö, S., Koikkalainen, J., ... Lauerma, K. (2008). Evaluation of cardiac biventricular segmentation from multiaxis MRI data: A multicenter study. Journal of Magnetic Resonance Imaging, 28(3), 626-636. https://doi.org/10.1002/jmri.21520
Lötjönen, Jyrki ; Järvinen, Vesa ; Benjamin, Cheong ; Wu, Edwin ; Kivistö, Sari ; Koikkalainen, Juha ; Mattila, Jussi ; Kervinen, Helena ; Muthupillai, Raja ; Sheehan, Florence ; Lauerma, Kirsi. / Evaluation of cardiac biventricular segmentation from multiaxis MRI data : A multicenter study. In: Journal of Magnetic Resonance Imaging. 2008 ; Vol. 28, No. 3. pp. 626-636.
@article{778779b9b6bf4d079217e1456fcee89a,
title = "Evaluation of cardiac biventricular segmentation from multiaxis MRI data: A multicenter study",
abstract = "Purpose: To validate a volumetric biventricular segmentation solution for multiaxis cardiac magnetic resonance (CMR) images.Materials and Methods: The study population comprised 40 subjects. Biventricular end‐diastolic and ‐systolic phases were segmented from both short‐axis and horizontal long‐axis or transaxial cine CMR images. Segmentation was based on fitting nonrigidly a 3D surface model to multiaxis CMR images. Five segmentations were performed: two manual segmentations by experts, automatic segmentation, and two segmentations where a user was allowed to correct errors in the automatic segmentation for 2 minutes and without time limits. Volumetry, distance measures, and visual grading were used to evaluate the quality of the segmentation.Results: No difference was observed between automatic and manual segmentations in volumetric measures of the ventricles. The manual segmentation performed better for left‐ventricular myocardial volume. The distance between surfaces as well as visual analysis did not show differences between automatic and manual segmentation for the endocardial border of the left ventricle but some corrections are needed for the right ventricle.Conclusion: Fully automatic segmentation produces good results in the assessment of left ventricular volume andendocardial border. Two minutes of user interaction are needed to obtain accurate results for the right ventricle.",
keywords = "segmentation, cardiac CMR, volumetry, right ventricle",
author = "Jyrki L{\"o}tj{\"o}nen and Vesa J{\"a}rvinen and Cheong Benjamin and Edwin Wu and Sari Kivist{\"o} and Juha Koikkalainen and Jussi Mattila and Helena Kervinen and Raja Muthupillai and Florence Sheehan and Kirsi Lauerma",
year = "2008",
doi = "10.1002/jmri.21520",
language = "English",
volume = "28",
pages = "626--636",
journal = "Journal of Magnetic Resonance Imaging",
issn = "1053-1807",
publisher = "Wiley",
number = "3",

}

Lötjönen, J, Järvinen, V, Benjamin, C, Wu, E, Kivistö, S, Koikkalainen, J, Mattila, J, Kervinen, H, Muthupillai, R, Sheehan, F & Lauerma, K 2008, 'Evaluation of cardiac biventricular segmentation from multiaxis MRI data: A multicenter study', Journal of Magnetic Resonance Imaging, vol. 28, no. 3, pp. 626-636. https://doi.org/10.1002/jmri.21520

Evaluation of cardiac biventricular segmentation from multiaxis MRI data : A multicenter study. / Lötjönen, Jyrki (Corresponding Author); Järvinen, Vesa; Benjamin, Cheong; Wu, Edwin; Kivistö, Sari; Koikkalainen, Juha; Mattila, Jussi; Kervinen, Helena; Muthupillai, Raja; Sheehan, Florence; Lauerma, Kirsi.

In: Journal of Magnetic Resonance Imaging, Vol. 28, No. 3, 2008, p. 626-636.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Evaluation of cardiac biventricular segmentation from multiaxis MRI data

T2 - A multicenter study

AU - Lötjönen, Jyrki

AU - Järvinen, Vesa

AU - Benjamin, Cheong

AU - Wu, Edwin

AU - Kivistö, Sari

AU - Koikkalainen, Juha

AU - Mattila, Jussi

AU - Kervinen, Helena

AU - Muthupillai, Raja

AU - Sheehan, Florence

AU - Lauerma, Kirsi

PY - 2008

Y1 - 2008

N2 - Purpose: To validate a volumetric biventricular segmentation solution for multiaxis cardiac magnetic resonance (CMR) images.Materials and Methods: The study population comprised 40 subjects. Biventricular end‐diastolic and ‐systolic phases were segmented from both short‐axis and horizontal long‐axis or transaxial cine CMR images. Segmentation was based on fitting nonrigidly a 3D surface model to multiaxis CMR images. Five segmentations were performed: two manual segmentations by experts, automatic segmentation, and two segmentations where a user was allowed to correct errors in the automatic segmentation for 2 minutes and without time limits. Volumetry, distance measures, and visual grading were used to evaluate the quality of the segmentation.Results: No difference was observed between automatic and manual segmentations in volumetric measures of the ventricles. The manual segmentation performed better for left‐ventricular myocardial volume. The distance between surfaces as well as visual analysis did not show differences between automatic and manual segmentation for the endocardial border of the left ventricle but some corrections are needed for the right ventricle.Conclusion: Fully automatic segmentation produces good results in the assessment of left ventricular volume andendocardial border. Two minutes of user interaction are needed to obtain accurate results for the right ventricle.

AB - Purpose: To validate a volumetric biventricular segmentation solution for multiaxis cardiac magnetic resonance (CMR) images.Materials and Methods: The study population comprised 40 subjects. Biventricular end‐diastolic and ‐systolic phases were segmented from both short‐axis and horizontal long‐axis or transaxial cine CMR images. Segmentation was based on fitting nonrigidly a 3D surface model to multiaxis CMR images. Five segmentations were performed: two manual segmentations by experts, automatic segmentation, and two segmentations where a user was allowed to correct errors in the automatic segmentation for 2 minutes and without time limits. Volumetry, distance measures, and visual grading were used to evaluate the quality of the segmentation.Results: No difference was observed between automatic and manual segmentations in volumetric measures of the ventricles. The manual segmentation performed better for left‐ventricular myocardial volume. The distance between surfaces as well as visual analysis did not show differences between automatic and manual segmentation for the endocardial border of the left ventricle but some corrections are needed for the right ventricle.Conclusion: Fully automatic segmentation produces good results in the assessment of left ventricular volume andendocardial border. Two minutes of user interaction are needed to obtain accurate results for the right ventricle.

KW - segmentation

KW - cardiac CMR

KW - volumetry

KW - right ventricle

U2 - 10.1002/jmri.21520

DO - 10.1002/jmri.21520

M3 - Article

VL - 28

SP - 626

EP - 636

JO - Journal of Magnetic Resonance Imaging

JF - Journal of Magnetic Resonance Imaging

SN - 1053-1807

IS - 3

ER -