Automated, machine learning-based, 3D echocardiographic quantification of left ventricular mass

Valentina Volpato, Victor Mor-Avi, Akhil Narang, David Prater, Alexandra Gonçalves, Gloria Tamborini, Laura Fusini, Mauro Pepi, Amit R. Patel, Roberto M. Lang

Research output: Contribution to journalArticle

Abstract

Background: Although 3D echocardiography (3DE) circumvents many limitations of 2D echocardiography by allowing direct measurements of left ventricular (LV) mass, it is seldom used in clinical practice due to time-consuming analysis. A recently developed 3DE machine learning (ML) approach allows automated determination of LV mass. We aimed to evaluate the accuracy of this new approach by comparing it to cardiac magnetic resonance (CMR) reference and to conventional 3DE volumetric analysis. Methods: We prospectively studied 23 patients who underwent 3DE (Philips EPIQ) and CMR imaging on the same day. Single-beat wide-angle 3D datasets of the left ventricle were acquired. LV mass was quantified using the new automated software (Philips HeartModel) with manual corrections when necessary and using conventional volumetric analysis (TomTec). CMR analysis was performed by manual slice-by-slice tracing of LV endo- and epicardial boundaries. Reproducibility of the ML approach was assessed using repeated measurements and quantified by intra-class correlation (ICC) and coefficients of variation (CoV). Results: Automated LV mass measurements were feasible in 20 patients (87%). The results were similar to CMR-derived values (Bland-Altman bias 5 g, limits of agreement ±37 g) and also to the conventional 3DE analysis (bias 7 g, ±27 g). Processing time was considerably shorter: 1.02 ± 0.24 minutes (CMR: 2.20 ± 0.13 minutes; TomTec: 2.36 ± 0.09 minutes), although manual corrections were performed in most patients. Repeated measurements showed high reproducibility: ICC = 0.99; CoV = 4 ± 5%. Conclusions: 3D Echocardiography analysis of LV mass using novel ML-based algorithm is feasible, fast, and accurate and may thus facilitate the incorporation of 3DE measurements of LV mass into clinical practice.

Original languageEnglish
JournalEchocardiography
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Three-Dimensional Echocardiography
Magnetic Resonance Spectroscopy
Machine Learning
Heart Ventricles
Echocardiography
Software
Magnetic Resonance Imaging

Keywords

  • 2D echocardiography
  • 3D echocardiography
  • cardiac magnetic resonance imaging
  • left ventricular mass
  • machine learning

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Cite this

Automated, machine learning-based, 3D echocardiographic quantification of left ventricular mass. / Volpato, Valentina; Mor-Avi, Victor; Narang, Akhil; Prater, David; Gonçalves, Alexandra; Tamborini, Gloria; Fusini, Laura; Pepi, Mauro; Patel, Amit R.; Lang, Roberto M.

In: Echocardiography, 01.01.2018.

Research output: Contribution to journalArticle

Volpato, Valentina ; Mor-Avi, Victor ; Narang, Akhil ; Prater, David ; Gonçalves, Alexandra ; Tamborini, Gloria ; Fusini, Laura ; Pepi, Mauro ; Patel, Amit R. ; Lang, Roberto M. / Automated, machine learning-based, 3D echocardiographic quantification of left ventricular mass. In: Echocardiography. 2018.
@article{b969f94a17e7412ca013fbdd2c1c6f97,
title = "Automated, machine learning-based, 3D echocardiographic quantification of left ventricular mass",
abstract = "Background: Although 3D echocardiography (3DE) circumvents many limitations of 2D echocardiography by allowing direct measurements of left ventricular (LV) mass, it is seldom used in clinical practice due to time-consuming analysis. A recently developed 3DE machine learning (ML) approach allows automated determination of LV mass. We aimed to evaluate the accuracy of this new approach by comparing it to cardiac magnetic resonance (CMR) reference and to conventional 3DE volumetric analysis. Methods: We prospectively studied 23 patients who underwent 3DE (Philips EPIQ) and CMR imaging on the same day. Single-beat wide-angle 3D datasets of the left ventricle were acquired. LV mass was quantified using the new automated software (Philips HeartModel) with manual corrections when necessary and using conventional volumetric analysis (TomTec). CMR analysis was performed by manual slice-by-slice tracing of LV endo- and epicardial boundaries. Reproducibility of the ML approach was assessed using repeated measurements and quantified by intra-class correlation (ICC) and coefficients of variation (CoV). Results: Automated LV mass measurements were feasible in 20 patients (87{\%}). The results were similar to CMR-derived values (Bland-Altman bias 5 g, limits of agreement ±37 g) and also to the conventional 3DE analysis (bias 7 g, ±27 g). Processing time was considerably shorter: 1.02 ± 0.24 minutes (CMR: 2.20 ± 0.13 minutes; TomTec: 2.36 ± 0.09 minutes), although manual corrections were performed in most patients. Repeated measurements showed high reproducibility: ICC = 0.99; CoV = 4 ± 5{\%}. Conclusions: 3D Echocardiography analysis of LV mass using novel ML-based algorithm is feasible, fast, and accurate and may thus facilitate the incorporation of 3DE measurements of LV mass into clinical practice.",
keywords = "2D echocardiography, 3D echocardiography, cardiac magnetic resonance imaging, left ventricular mass, machine learning",
author = "Valentina Volpato and Victor Mor-Avi and Akhil Narang and David Prater and Alexandra Gon{\cc}alves and Gloria Tamborini and Laura Fusini and Mauro Pepi and Patel, {Amit R.} and Lang, {Roberto M.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1111/echo.14234",
language = "English",
journal = "Echocardiography",
issn = "0742-2822",
publisher = "Blackwell Publishing Inc.",

}

TY - JOUR

T1 - Automated, machine learning-based, 3D echocardiographic quantification of left ventricular mass

AU - Volpato, Valentina

AU - Mor-Avi, Victor

AU - Narang, Akhil

AU - Prater, David

AU - Gonçalves, Alexandra

AU - Tamborini, Gloria

AU - Fusini, Laura

AU - Pepi, Mauro

AU - Patel, Amit R.

AU - Lang, Roberto M.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Background: Although 3D echocardiography (3DE) circumvents many limitations of 2D echocardiography by allowing direct measurements of left ventricular (LV) mass, it is seldom used in clinical practice due to time-consuming analysis. A recently developed 3DE machine learning (ML) approach allows automated determination of LV mass. We aimed to evaluate the accuracy of this new approach by comparing it to cardiac magnetic resonance (CMR) reference and to conventional 3DE volumetric analysis. Methods: We prospectively studied 23 patients who underwent 3DE (Philips EPIQ) and CMR imaging on the same day. Single-beat wide-angle 3D datasets of the left ventricle were acquired. LV mass was quantified using the new automated software (Philips HeartModel) with manual corrections when necessary and using conventional volumetric analysis (TomTec). CMR analysis was performed by manual slice-by-slice tracing of LV endo- and epicardial boundaries. Reproducibility of the ML approach was assessed using repeated measurements and quantified by intra-class correlation (ICC) and coefficients of variation (CoV). Results: Automated LV mass measurements were feasible in 20 patients (87%). The results were similar to CMR-derived values (Bland-Altman bias 5 g, limits of agreement ±37 g) and also to the conventional 3DE analysis (bias 7 g, ±27 g). Processing time was considerably shorter: 1.02 ± 0.24 minutes (CMR: 2.20 ± 0.13 minutes; TomTec: 2.36 ± 0.09 minutes), although manual corrections were performed in most patients. Repeated measurements showed high reproducibility: ICC = 0.99; CoV = 4 ± 5%. Conclusions: 3D Echocardiography analysis of LV mass using novel ML-based algorithm is feasible, fast, and accurate and may thus facilitate the incorporation of 3DE measurements of LV mass into clinical practice.

AB - Background: Although 3D echocardiography (3DE) circumvents many limitations of 2D echocardiography by allowing direct measurements of left ventricular (LV) mass, it is seldom used in clinical practice due to time-consuming analysis. A recently developed 3DE machine learning (ML) approach allows automated determination of LV mass. We aimed to evaluate the accuracy of this new approach by comparing it to cardiac magnetic resonance (CMR) reference and to conventional 3DE volumetric analysis. Methods: We prospectively studied 23 patients who underwent 3DE (Philips EPIQ) and CMR imaging on the same day. Single-beat wide-angle 3D datasets of the left ventricle were acquired. LV mass was quantified using the new automated software (Philips HeartModel) with manual corrections when necessary and using conventional volumetric analysis (TomTec). CMR analysis was performed by manual slice-by-slice tracing of LV endo- and epicardial boundaries. Reproducibility of the ML approach was assessed using repeated measurements and quantified by intra-class correlation (ICC) and coefficients of variation (CoV). Results: Automated LV mass measurements were feasible in 20 patients (87%). The results were similar to CMR-derived values (Bland-Altman bias 5 g, limits of agreement ±37 g) and also to the conventional 3DE analysis (bias 7 g, ±27 g). Processing time was considerably shorter: 1.02 ± 0.24 minutes (CMR: 2.20 ± 0.13 minutes; TomTec: 2.36 ± 0.09 minutes), although manual corrections were performed in most patients. Repeated measurements showed high reproducibility: ICC = 0.99; CoV = 4 ± 5%. Conclusions: 3D Echocardiography analysis of LV mass using novel ML-based algorithm is feasible, fast, and accurate and may thus facilitate the incorporation of 3DE measurements of LV mass into clinical practice.

KW - 2D echocardiography

KW - 3D echocardiography

KW - cardiac magnetic resonance imaging

KW - left ventricular mass

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85059248910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059248910&partnerID=8YFLogxK

U2 - 10.1111/echo.14234

DO - 10.1111/echo.14234

M3 - Article

AN - SCOPUS:85059248910

JO - Echocardiography

JF - Echocardiography

SN - 0742-2822

ER -