Machine Learning-Based Three-Dimensional Echocardiographic Quantification of Right Ventricular Size and Function: Validation Against Cardiac Magnetic Resonance.

BACKGROUND: Three-dimensional echocardiography (3DE) allows accurate and reproducible measurements of right ventricular (RV) size and function. However, widespread implementation of 3DE in routine clinical practice is limited because the existing software packages are relatively time-consuming and skill demanding. The aim of this study was to test the accuracy and reproducibility of new machine learning- (ML-) based, fully automated software for three-dimensional quantification of RV size and function. METHODS: Fifty-six unselected patients with a wide range of RV size and function and image quality, referred for clinically indicated cardiac magnetic resonance (CMR) imaging, underwent a transthoracic 3DE exam on the same day. End-systolic and end-diastolic RV volumes (ESV, EDV) and ejection fraction (EF) were measured using the ML-based algorithm and compared with CMR reference values using Bland-Altman and linear regression analyses. RESULTS: RV function quantification by echocardiography was feasible in all patients. The automatic approach was accurate in 32% patients with analysis time of 15 ± 1 seconds and 100% reproducible. Endocardial contour editing was necessary after the automated postprocessing in the remaining 68% patients, prolonging analysis time to 114 ± 71 seconds. With these minimal adjustments, RV volumes and EF measurements were accurate in comparison with CMR reference (biases: EDV, -25.6 ± 21.1 mL; ESV, -7.4 ± 16 mL; EF, -3.3% ± 5.2%) and showed excellent reproducibility reflected by coefficients of variation <7% and intraclass correlations ≥0.95 for all measurements. CONCLUSIONS: The new ML-based 3DE algorithm provided accurate and completely reproducible RV volume and EF measurements in one-third of unselected patients without any boundary editing. In the remaining patients, quick minimal editing resulted in reasonably accurate measurements with excellent reproducibility. This approach provides a promising solution for fast three-dimensional quantification of RV size and function.

Machine learning based automated dynamic quantification of left heart chamber volumes.

AIMS: Studies have demonstrated the ability of a new automated algorithm for volumetric analysis of 3D echocardiographic (3DE) datasets to provide accurate and reproducible measurements of left ventricular and left atrial (LV, LA) volumes at end-systole and end-diastole. Recently, this methodology was expanded using a machine learning (ML) approach to automatically measure chamber volumes throughout the cardiac cycle, resulting in LV and LA volume-time curves. We aimed to validate ejection and filling parameters obtained from these curves by comparing them to independent well-validated reference techniques. METHODS AND RESULTS: We studied 20 patients referred for cardiac magnetic resonance (CMR) examinations, who underwent 3DE imaging the same day. Volume-time curves were obtained for both LV and LA chambers using the ML algorithm (Philips HeartModel), and independently conventional 3DE volumetric analysis (TomTec), and CMR images (slice-by-slice, frame-by-frame manual tracing). Automatically derived LV and LA volumes and ejection/filling parameters were compared against both reference techniques. Minor manual correction of the automatically detected LV and LA borders was needed in 4/20 and 5/20 cases, respectively. Time required to generate volume-time curves was 35 ± 17 s using ML algorithm, 3.6 ± 0.9 min using conventional 3DE analysis, and 96 ± 14 min using CMR. Volume-time curves obtained by all three techniques were similar in shape and magnitude. In both comparisons, ejection/filling parameters showed no significant inter-technique differences. Bland-Altman analysis confirmed small biases, despite wide limits of agreement. CONCLUSION: The automated ML algorithm can quickly measure dynamic LV and LA volumes and accurately analyse ejection/filling parameters. Incorporation of this algorithm into the clinical workflow may increase the utilization of 3DE imaging.

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

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.

Transthoracic 3D Echocardiographic Left Heart Chamber Quantification Using an Automated Adaptive Analytics Algorithm.

OBJECTIVES: The goal of this study was to test the feasibility and accuracy of an automated algorithm that simultaneously quantifies 3-dimensional (3D) transthoracic echocardiography (TTE)-derived left atrial (LA) and left ventricular (LV) volumes and left ventricular ejection fraction (LVEF). Conventional manual 3D TTE tracings and cardiac magnetic resonance (CMR) images were used as a reference for comparison. BACKGROUND: Cardiac chamber quantification from 3D TTE is superior to 2D TTE measurements. However, integration of 3D quantification into clinical practice has been limited by time-consuming workflow and the need for 3D expertise. A novel automated software was developed that provides LV and LA volumetric quantification from 3D TTE datasets that reflect real-life manual 3-dimensional echocardiography measurements and values comparable to CMR. METHODS: A total of 159 patients were studied in 2 separate protocols. In protocol 1, 94 patients underwent 3D TTE imaging (EPIQ, iE33, X5-1, Philips Healthcare, Andover, Massachusetts) covering the left atrium and left ventricle. LA and LV volumes and LVEF were obtained using the automated software (HeartModel, Philips Healthcare) with and without contour correction, and compared with the averaged manual 3D volumetric measurements from 3 readers. In protocol 2, automated measurements from 65 patients were compared with a CMR reference. The Pearson correlation coefficient, Bland-Altman analysis, and paired Student t tests were used to assess inter-technique agreement. RESULTS: Correlations between the automated and manual 3D TTE measurements were strong (r = 0.87 to 0.96). LVEF was underestimated and automated LV end-diastolic, LV end-systolic, and LA volumes were overestimated compared with manual measurements. Agreement between the automated analysis and CMR was also strong (r = 0.84 to 0.95). Test-retest variability was low. CONCLUSIONS: Automated simultaneous quantification of LA and LV volumes and LVEF is feasible and requires minimal 3D software analysis training. The automated measurements are not only comparable to manual measurements but also to CMR. This technique is highly reproducible and timesaving, and it therefore promises to facilitate the integration of 3D TTE-based left-heart chamber quantification into clinical practice.

Two-dimensional speckle tracking echocardiography: standardization efforts based on synthetic ultrasound data.

AIMS: Speckle tracking echocardiography has already demonstrated its clinical potential. However, its use in routine practice is jeopardized by recent reports on high inter-vendor variability of the measurements. As such, the European Association of CardioVascular Imaging (EACVI) and the American Society of Echocardiography (ASE) set up a standardization task force, which was joined by all manufacturers of echocardiographic equipment as well as by companies offering software solutions only, with the ambition to tackle this problem by standardization and quality assurance (QA). METHODS AND RESULTS: In this study, a first step towards QA of all commercially available tracking solutions based on computer-generated ultrasound images is presented. The accuracy of the products was acceptable with relative errors below 10% and intra-vendor reproducibility within 5%. CONCLUSION: Whether these results can be extrapolated to the clinical setting is the topic of an ongoing study of the EACVI/ASE/Industry Task Force to standardize deformation imaging. This study was an important first step in the development of generally accepted tools for QA of speckle tracking echocardiography.