Single-Site Experience with an Automated Artificial Intelligence Application for Left Ventricular Ejection Fraction Measurement in Echocardiography

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2023 Apr 13

PMID 37046515

Authors

Krunoslav Michael Sveric

Roxana Botan

Zouhir Dindane

Anna Winkler

Thomas Nowack

Christoph Heitmann

Leonhard Schleussner

Axel Linke

Affiliations

Soon will be listed here.

Abstract

Left ventricular ejection fraction (LVEF) is a key parameter in evaluating left ventricular (LV) function using echocardiography (Echo), but its manual measurement by the modified biplane Simpson (MBS) method is time consuming and operator dependent. We investigated the feasibility of a server-based, commercially available and ready-to use-artificial intelligence (AI) application based on convolutional neural network methods that integrate fully automatic view selection and measurement of LVEF from an entire Echo exam into a single workflow. We prospectively enrolled 1083 consecutive patients who had been referred to Echo for diagnostic or therapeutic purposes. LVEF was measured independently using MBS and AI. Test-retest variability was assessed in 40 patients. The reliability, repeatability, and time efficiency of LVEF measurements were compared between the two methods. Overall, 889 Echos were analyzed by cardiologists with the MBS method and by the AI. Over the study period of 10 weeks, the feasibility of both automatic view classification and seamlessly measured LVEF rose to 81% without user involvement. LVEF, LV end-diastolic and end-systolic volumes correlated strongly between MBS and AI (R = 0.87, 0.89 and 0.93, < 0.001 for all) with a mean bias of +4.5% EF, -12 mL and -11 mL, respectively, due to impaired image quality and the extent of LV function. Repeatability and reliability of LVEF measurement ( = 40, test-retest) by AI was excellent compared to MBS (coefficient of variation: 3.2% vs. 5.9%), although the median analysis time of the AI was longer than that of the operator-dependent MBS method (258 s vs. 171 s). This AI has succeeded in identifying apical LV views and measuring EF in one workflow with comparable results to the MBS method and shows excellent reproducibility. It offers realistic perspectives for fully automated AI-based measurement of LVEF in routine clinical settings.

Citing Articles

An automatic and real-time echocardiography quality scoring system based on deep learning to improve reproducible assessment of left ventricular ejection fraction.

Li X, Liao L, Wu K, Meng A, Jiang Y, Zhu Y Quant Imaging Med Surg. 2025; 15(1):770-785.

PMID: 39839058 PMC: 11744150. DOI: 10.21037/qims-24-512.

The role of artificial intelligence in standardizing global longitudinal strain measurements in echocardiography.

Sveric K, Botan R, Winkler A, Dindane Z, Alothman G, Cansiz B Eur Heart J Imaging Methods Pract. 2024; 2(4):qyae130.

PMID: 39712903 PMC: 11660427. DOI: 10.1093/ehjimp/qyae130.

Segmentation-Free Estimation of Left Ventricular Ejection Fraction Using 3D CNN Is Reliable and Improves as Multiple Cardiac MRI Cine Orientations Are Combined.

Germain P, Labani A, Vardazaryan A, Padoy N, Roy C, Ghannudi S Biomedicines. 2024; 12(10).

PMID: 39457634 PMC: 11505352. DOI: 10.3390/biomedicines12102324.

Transfer Learning Video Classification of Preserved, Mid-Range, and Reduced Left Ventricular Ejection Fraction in Echocardiography.

Decoodt P, Sierra-Sosa D, Anghel L, Cuminetti G, De Keyzer E, Morissens M Diagnostics (Basel). 2024; 14(13).

PMID: 39001328 PMC: 11241427. DOI: 10.3390/diagnostics14131439.

References

Tromp J, Seekings P, Hung C, Iversen M, Frost M, Ouwerkerk W . Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study. Lancet Digit Health. 2021; 4(1):e46-e54. DOI: 10.1016/S2589-7500(21)00235-1. View

Asch F, Descamps T, Sarwar R, Karagodin I, Singulane C, Xie M . Human versus Artificial Intelligence-Based Echocardiographic Analysis as a Predictor of Outcomes: An Analysis from the World Alliance Societies of Echocardiography COVID Study. J Am Soc Echocardiogr. 2022; 35(12):1226-1237.e7. PMC: 9293371. DOI: 10.1016/j.echo.2022.07.004. View

Knackstedt C, Bekkers S, Schummers G, Schreckenberg M, Muraru D, Badano L . Fully Automated Versus Standard Tracking of Left Ventricular Ejection Fraction and Longitudinal Strain: The FAST-EFs Multicenter Study. J Am Coll Cardiol. 2015; 66(13):1456-66. DOI: 10.1016/j.jacc.2015.07.052. View

Houard L, Militaru S, Tanaka K, Pasquet A, Vancraeynest D, Vanoverschelde J . Test-retest reliability of left and right ventricular systolic function by new and conventional echocardiographic and cardiac magnetic resonance parameters. Eur Heart J Cardiovasc Imaging. 2020; 22(10):1157-1167. DOI: 10.1093/ehjci/jeaa206. View

Ghorbani A, Ouyang D, Abid A, He B, Chen J, Harrington R . Deep learning interpretation of echocardiograms. NPJ Digit Med. 2020; 3:10. PMC: 6981156. DOI: 10.1038/s41746-019-0216-8. View

Litjens G, Ciompi F, Wolterink J, de Vos B, Leiner T, Teuwen J . State-of-the-Art Deep Learning in Cardiovascular Image Analysis. JACC Cardiovasc Imaging. 2019; 12(8 Pt 1):1549-1565. DOI: 10.1016/j.jcmg.2019.06.009. View

Yuan N, Jain I, Rattehalli N, He B, Pollick C, Liang D . Systematic Quantification of Sources of Variation in Ejection Fraction Calculation Using Deep Learning. JACC Cardiovasc Imaging. 2021; 14(11):2260-2262. PMC: 10697700. DOI: 10.1016/j.jcmg.2021.06.018. View

Asch F, Poilvert N, Abraham T, Jankowski M, Cleve J, Adams M . Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction Without Volume Measurements Using a Machine Learning Algorithm Mimicking a Human Expert. Circ Cardiovasc Imaging. 2019; 12(9):e009303. PMC: 7099856. DOI: 10.1161/CIRCIMAGING.119.009303. View

Bhuva A, Bai W, Lau C, Davies R, Ye Y, Bulluck H . A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis. Circ Cardiovasc Imaging. 2019; 12(10):e009214. DOI: 10.1161/CIRCIMAGING.119.009214. View

10.

Lang R, Badano L, Mor-Avi V, Afilalo J, Armstrong A, Ernande L . Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr. 2015; 28(1):1-39.e14. DOI: 10.1016/j.echo.2014.10.003. View

11.

Hoffmann R, Barletta G, von Bardeleben S, Vanoverschelde J, Kasprzak J, Greis C . Analysis of left ventricular volumes and function: a multicenter comparison of cardiac magnetic resonance imaging, cine ventriculography, and unenhanced and contrast-enhanced two-dimensional and three-dimensional echocardiography. J Am Soc Echocardiogr. 2014; 27(3):292-301. DOI: 10.1016/j.echo.2013.12.005. View

12.

Aurich M, Florian Andre , Keller M, Greiner S, Hess A, Buss S . Assessment of left ventricular volumes with echocardiography and cardiac magnetic resonance imaging: real-life evaluation of standard versus new semiautomatic methods. J Am Soc Echocardiogr. 2014; 27(10):1017-24. DOI: 10.1016/j.echo.2014.07.006. View

13.

Kusunose K, Haga A, Yamaguchi N, Abe T, Fukuda D, Yamada H . Deep Learning for Assessment of Left Ventricular Ejection Fraction from Echocardiographic Images. J Am Soc Echocardiogr. 2020; 33(5):632-635.e1. DOI: 10.1016/j.echo.2020.01.009. View

14.

Cannesson M, Tanabe M, Suffoletto M, McNamara D, Madan S, Lacomis J . A novel two-dimensional echocardiographic image analysis system using artificial intelligence-learned pattern recognition for rapid automated ejection fraction. J Am Coll Cardiol. 2007; 49(2):217-26. DOI: 10.1016/j.jacc.2006.08.045. View

15.

Thavendiranathan P, Grant A, Negishi T, Plana J, Popovic Z, Marwick T . Reproducibility of echocardiographic techniques for sequential assessment of left ventricular ejection fraction and volumes: application to patients undergoing cancer chemotherapy. J Am Coll Cardiol. 2012; 61(1):77-84. DOI: 10.1016/j.jacc.2012.09.035. View

16.

Samtani R, Bienstock S, Lai A, Liao S, Baber U, Croft L . Assessment and validation of a novel fast fully automated artificial intelligence left ventricular ejection fraction quantification software. Echocardiography. 2022; 39(3):473-482. DOI: 10.1111/echo.15318. View

17.

Playford D, Bordin E, Mohamad R, Stewart S, Strange G . Enhanced Diagnosis of Severe Aortic Stenosis Using Artificial Intelligence: A Proof-of-Concept Study of 530,871 Echocardiograms. JACC Cardiovasc Imaging. 2019; 13(4):1087-1090. DOI: 10.1016/j.jcmg.2019.10.013. View

18.

Zhang J, Chatham J, Young M . Circadian Regulation of Cardiac Physiology: Rhythms That Keep the Heart Beating. Annu Rev Physiol. 2019; 82:79-101. PMC: 7012667. DOI: 10.1146/annurev-physiol-020518-114349. View

19.

Zhang J, Gajjala S, Agrawal P, Tison G, Hallock L, Beussink-Nelson L . Fully Automated Echocardiogram Interpretation in Clinical Practice. Circulation. 2018; 138(16):1623-1635. PMC: 6200386. DOI: 10.1161/CIRCULATIONAHA.118.034338. View

20.

Salte I, Ostvik A, Smistad E, Melichova D, Nguyen T, Karlsen S . Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography. JACC Cardiovasc Imaging. 2021; 14(10):1918-1928. DOI: 10.1016/j.jcmg.2021.04.018. View