Automated Measurements of Left Ventricular Ejection Fraction and Volumes Using the EchoPAC System

doi:10.37015/AUDT.2021.200072

Abstract

Abstract:

Objective: To evaluate the clinical value of automated measurements by AutoEF (GE EchoPAC system, version 113) in left ventricular (LV) volumes and ejection fraction (EF) estimation based on the biplane Simpson’s method (manual method) in different clinical subsets.
Methods: A total of 322 subjects participated in this study (the common group). In the common group, 112 patients with coronary heart disease (CHD) were divided into the CHD group, and 34 CHD patients with LV wall motion abnormalities (WMA) comprising the CHD group, renamed the WMA group. LV volumes and EF were assessed using both manual tracing and automated estimation. Time spent on each method was documented. The agreements in echocardiographic measurements by different methods were assessed by intraclass correlation coefficients (ICC) and Bland-Altman analysis.
Results: The average analysis time of the automated method was 12 ± 1 s/patient with excellent repeatability. ICC revealed good consistency between manual and automated EF in all groups, especially in the CHD and WMA groups, although Bland-Altman analysis showed non-negligible bias in EF estimation between the two methods. ICC analysis showed a good correlation between automated and manual EF in all the good and poor image quality subgroups.
Conclusion: Automated method by AutoEF was a time-saving, excellent reproducible, and resistant to image interference approach, with a strong potential in left ventricular function measurements, especially for patients with CHD and/or WMA.

Key words: Echocardiography; Left ventricular function; Automated measurement; Intraclass correlation coefficients

Xiaoxue Chen, MD, Shaoling Yang, PhD, Qianqian He, MD, Yin Wang, PhD, Linyan Fan, MD, Fengling Wang, MD, Kun Zhao, MD, Jing Hu, MD. Automated Measurements of Left Ventricular Ejection Fraction and Volumes Using the EchoPAC System. Advanced Ultrasound in Diagnosis and Therapy, 2021, 5(3): 226-235.

References

[1]	Hovnanians N, Win T, Makkiya M Zheng Q and Taub C. Validity of automated measurement of left ventricular ejection fraction and volume using the Philips EPIQ system. Echocardiography 2017; 34:1575-1583.
[2]	Prastaro M, Pirozzi E, Gaibazzi N, Paolillo S, Santoro C, Savarese G, et al. Expert review on the prognostic role of echocardiography after acute myocardial infarction. J Am Soc Echocardiogr 2017; 30: 431-443.e2.
[3]	Wagholikar KB, Fischer CM, Goodson A, Herrick CD, Rees M, Toscano E, et al. Extraction of ejection fraction from echocardiography notes for constructing a cohort of patients having heart failure with reduced ejection fraction (HFrEF). J Med Syst 2018; 42:209-221.
[4]	Kinno M, Nagpal P, Horgan S, Waller AH. Comparison of echocardiography, cardiac magnetic resonance, and computed tomographic imaging for the evaluation of left ventricular myocardial function: part 1 (global assessment). Curr Cardiol Rep 2017; 19:9-12.
[5]	Lang RM, Badano LP, Mor-Avi V, Afilalo J, Armstrong A, Ernande L, et al. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. Eur Heart J Cardiovasc Imaging 2015; 16:233-270.
[6]	Madani A, Ong JR, Tibrewal A, Mofrad MRK. Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ Digit Med 2018; 1:59-70.
[7]	Abdi AH, Luong C, Tsang T, Allan G, Nouranian S, Jue J, et al. Automatic quality assessment of echocardiograms using convolutional neural networks: feasibility on the apical four-chamber view. IEEE Trans Med Imaging 2017; 36:1221-1230.
[8]	Carneiro G, Nascimento JC, Freitas A. The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods. IEEE Trans Image Process 2012; 21:968-982.
[9]	Hou P, Xue HP, Mao XE, Li YN, Wu LF, Liu YB. Inflammation markers are associated with frailty in elderly patients with coronary heart disease. Aging (Albany NY) 2018; 10:2636-2645.
[10]	Khan AM, Wiegers SE. The importance of being expert: is it time to revisit the concept? Journal of the American Society of Echocardiography 2012; 25:218-219.
[11]	Knackstedt C, Bekkers SC, Schummers G, Schreckenberg M, Muraru D, Badano LP, et al. Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: the FAST-EFs multicenter study. J Am Coll Cardiol 2015; 66:1456-1466.
[12]	Kaufmann BA, Min SY, Goetschalckx K, Bernheim AM, Buser PT, Pfisterer ME, et al. How reliable are left ventricular ejection fraction cut offs assessed by echocardiography for clinical decision making in patients with heart failure? Int J Cardiovasc Imaging 2013; 29:581-588.
[13]	Pellikka PA, She L, Holly TA, Lin G, Varadarajan P, Pai RG, et al. Variability in ejection fraction measured by echocardiography, gated single-photon emission computed tomography, and cardiac magnetic resonance in patients with coronary artery disease and left ventricular dysfunction. JAMA Netw Open 2018; 1:e181456.
[14]	Kerkhof PLM, van de Ven PM, Yoo B, Peace RA, Heyndrickx GR, Handly N. Ejection fraction as related to basic components in the left and right ventricular volume domains. Int J Cardiol 2018; 255:105-110.
[15]	Jafari MH, Girgis H, Van Woudenberg N, Liao Z, Rohling R, Gin K, et al. Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training. Int J Comput Assist Radiol Surg 2019; 14:1027-1037.
[16]	Leclerc S, Smistad E, Pedrosa J, Ostvik A, Cervenansky F, Espinosa F, et al. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging 2019; 38:2198-2210.
[17]	Aurich M, Andre F, Keller M, Greiner S, Hess A, Buss SJ, et al. 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; 27:1017-1024.
[18]	Moradi S, Oghli MG, Alizadehasl A, Shiri I, Oveisi N, Oveisi M, et al. MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography. Phys Med 2019; 67:58-69.
[19]	Chen R, Xu C, Dong Z, Liu Y, Du X. DeepCQ: Deep multi-task conditional quantification network for estimation of left ventricle parameters. Comput Methods Programs Biomed 2019; 184:105288.