scholarly journals Semi-automated left ventricular endocardial detection versus hand-tracing in the measurement of left ventricular volumes and ejection fraction in daily clinical practice

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
L.S Chen ◽  
Y.Y Oon ◽  
C Rawlings ◽  
K Sabeng ◽  
S Adam ◽  
...  
Keyword(s):  
Clinical Practice ◽  
Ejection Fraction ◽  
Left Ventricular ◽  
Daily Clinical Practice ◽  
Endocardial Border ◽  
Volume Curve ◽  
Lv Volumes ◽  
Level Of Experience ◽  
Automated Tracing ◽  
Tracing Method

Abstract Background The common method of assessing left ventricle (LV) volumes and ejection fraction (EF) is hand-tracing Biplane Simpson method. Alternatively, ultrasound vendors offer different semi-automated LV endocardial border detection software with anatomical intelligence to assess LV volumes and EF. By using speckle-tracking technique, this software tracks the LV endocardium throughout the cardiac cycle and computes the LV volumes in every image frame using the disk summation method from which a volume-curve is generated, and the EF is calculated using the maximum and minimum volumes obtained. Data on the performance of this method in comparison with the hand-tracing Biplane Simpson method in daily clinical practice is scarce. Purpose To determine the accuracy of LV volumes and EF using semi-automated LV endocardial detection tracing, and to compare the reproducibility of this method with the hand-tracing Biplane Simpson method, among operators with varying level of experience in echocardiography. Methods This was a single center retrospective observational study, conducted in year 2020. 127 patients, aged >18 years, who underwent clinically indicated transthoracic echocardiography were recruited. The echocardiographic images were analyzed independently in a blinded fashion by 3 operators – a sonographer, a fellow-in-training and a cardiologist specialized in echocardiography. The LV volumes and EF were first measured using hand-tracing Biplane Simpson method, then repeated using semi-automated tracing at a different time and the operator were blinded to the initial hand-tracing measurements. Results The mean age of patients was 50±16 years, 35.4% were male, mean body surface area was 1.62±0.18m2, 92.1% were in sinus rhythm, and 61.4% had good acoustic window. Table 1 shows the LV end-diastolic volume (EDV), end-systolic volume (ESV) and EF, measured using different method, by the 3 operators. There were excellent correlation and agreement between semi-automated tracing measurements and hand-tracing measurements of LV EDV (r=0.985, LOA [mean ± 1.96 SD] 16.9 ml, ICC 0.991), ESV (r=0.990, LOA 12.7 ml, ICC 0.994) and EF (r=0.962, LOA 7.43%, ICC 0.967) by experienced cardiologist. The limit of agreement (LOA) between cardiologist and sonographer for semi-automated tracing measurement of LV EDV, ESV and EF were 29.13 ml, 19.74 ml and 9.25% respectively, which was comparable with that of hand-tracing measurement. The agreement between cardiologist and fellow-in-training for semi-automated tracing measurement of LV volumes and EF was slightly better than hand-tracing method, with a LOA of 25.60 ml, 17.48 ml and 7.08%, for EDV, ESV and EF respectively (Table 2). Conclusion In daily clinical practice, measurement of LV volumes and EF using semi-automated LV endocardial tracing method is accurate and demonstrates comparable reproducibility with hand-tracing Biplane Simpson method among operators with different level of experience in echocardiography. FUNDunding Acknowledgement Type of funding sources: None.

scholarly journals Non-Invasive Assessment of Left Ventricle Ejection Fraction: Where Do We Stand?

2021 ◽  
Vol 11 (11) ◽  
pp. 1153
Author(s):  
Alessandra Scatteia ◽  
Angelo Silverio ◽  
Roberto Padalino ◽  
Francesco De Stefano ◽  
Raffaella America ◽  
...  
Keyword(s):  
Clinical Practice ◽  
Ejection Fraction ◽  
Systolic Function ◽  
Left Ventricular ◽  
Left Ventricle Ejection Fraction ◽  
Advantages And Disadvantages ◽  
Non Invasive ◽  
Lv Ejection Fraction ◽  
Lv Systolic Function ◽  
Invasive Evaluation

The left ventricular (LV) ejection fraction (EF) is the preferred parameter applied for the non-invasive evaluation of LV systolic function in clinical practice. It has a well-recognized and extensive role in the clinical management of numerous cardiac conditions. Many imaging modalities are currently available for the non-invasive assessment of LVEF. The aim of this review is to describe their relative advantages and disadvantages, proposing a hierarchical application of the different imaging tests available for LVEF evaluation based on the level of accuracy/reproducibility clinically required.

scholarly journals Semi-automated cardiac segmentation on cine magnetic resonance images using GVF-Snake deformable models

2009 ◽  
Author(s):  
Constantin Constantinides ◽  
Yasmina Chenoune ◽  
Nadjia Kachenoura ◽  
Elodie Roullot ◽  
Elie Mousseaux ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Ejection Fraction ◽  
Region Of Interest ◽  
Left Ventricular ◽  
Magnetic Resonance Images ◽  
Deformable Model ◽  
Papillary Muscles ◽  
Myocardial Mass ◽  
Endocardial Border ◽  
Cardiac Segmentation

The segmentation of left ventricular structures is necessary for the evaluation of the ejection fraction (EF) and the myocardial mass (LVM). A semi-automated 2D algorithm using connected filters and a deformable model allowing an accurate endocardial detection was proposed. The epicardial border was deduced using a deformable model restricted inside a region of interest defined from the endocardial border. Papillary muscles were detected using a fuzzy k-means algorithm. The method was applied to the challenge training and validation databases, consisting of 15 subjects each. The evaluation was performed using the tools provided by the challenge. For both datasets, results show a mean Dice metric of 0.89 for endocardial borders (0.92 for epicardial borders). Overall average perpendicular distance was 2.2 mm. Very good correlation was obtained for the EF and LVM parameters. Visual overall rating given by the challenge’s cardiologist was 1.2. Segmentation was robust and performed successfully on both datasets.

scholarly journals Impact of a training program incorporating cardiac magnetic resonance imaging on the accuracy and reproducibility of two-dimensional echocardiographic measurements of left ventricular volumes and ejection fraction

2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Yosuke Nabeshima ◽  
Hidehiro Namisaki ◽  
Toshihiro Teshima ◽  
Yasuhiko Kurashige ◽  
Akiko Kakio ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Ejection Fraction ◽  
Training Program ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Left Ventricular ◽  
Left Ventricular Volumes ◽  
Two Dimensional ◽  
Lv Volumes

Abstract Background Left ventricular (LV) ejection fraction (LVEF) assessed by two-dimensional echocardiography (2DE) is the most widely used parameter for clinical decision-making, but reproducibility and accuracy problems remain. We evaluated the usefulness of a novel training program based on cardiac magnetic resonance (CMR) imaging to obtain more reliable values of 2DE-derived LVEF and LV volumes. Methods Fifty-four sonographers from five hospitals independently measured LV volumes and LVEF using the same 2DE images from 15 patients who underwent CMR and 2DE. After receiving a lecture from an expert on how to properly trace the LV endocardium, each sonographer voluntary performed the measurements using the same datasets, and was invited to perform the same analysis for additional patients. The effect of the training intervention was evaluated using the coefficient of variation (CV) and coverage probability (CP). Results Before the intervention, the LV volumes were significantly underestimated and the LVEF was significantly overestimated compared to the CMR results; however, these differences were reduced after the intervention. In particular, the CP (0.52 vs. 0.76, p < 0.001) for the LVEF showed significant improvement. However, the degree of improvement differed among institutions, and the CV actually became worse in two hospitals after the intervention. Level of experience and self-practice was associated with the reproducibility after the intervention. Conclusions A training program using CMR as a reference improved the accuracy of 2DE-determined LV measurements. Since the degree of improvements differed among hospitals, individualization of training programs and periodical objective evaluation may be required to reduce inter-institutional variability.

Abstract 14182: Myocardial Fibrosis and Reverse Remodelling in Nonischaemic Dilated Cardiomyopathy

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Andrea Barison ◽  
Alessandro Ortalda ◽  
Giancarlo Todiere ◽  
Giuseppe Vergaro ◽  
Gianluca Mirizzi ◽  
...  
Keyword(s):  
Ejection Fraction ◽  
Dilated Cardiomyopathy ◽  
Myocardial Fibrosis ◽  
Left Ventricular ◽  
Idiopathic Dilated Cardiomyopathy ◽  
Post Contrast ◽  
Reverse Remodelling ◽  
Lv Volumes ◽  
Lv Ejection Fraction

Introduction: In nonischaemic dilated cardiomyopathy (NICM), myocardial fibrosis can be detected by cardiovascular magnetic resonance (CMR) as late gadolinium enhancement (LGE) and is associated with worse prognosis. Hypothesis: Absence of myocardial fibrosis is associated with left ventricular reverse remodelling (LV-RR). Methods: One-hundred-and-twenty-five NICM patients (age 51±16 years, 82 male) were enrolled and underwent baseline CMR; patients with ischaemic, valvular, congenital heart disease, other cardiomyopathies or contraindications to CMR were excluded. After a 24-month follow-up on optimal medical therapy, all patients underwent a second CMR; patients who died, underwent device implantation or declined a second CMR, were also excluded from the study. LGE was quantified on post-contrast CMR images. LV-RR was defined as an increase in LV ejection fraction ≥10 U or decrease in LV end-diastolic volume ≥10% at follow-up. Results: Mean LV ejection fraction was 41±11% at baseline, 47±12% at follow-up: LV-RR was observed in 59 patients (47%), with no age or gender difference (p=NS) . LGE was present in 69 (54%) patients at baseline (mean extent 12±6 g), without significant differences at follow-up (mean extent 13±7 g). Patients experiencing LV-RR during follow-up presented a baseline worse LV ejection fraction (36±12%) than no-LV-RR patients ( 45±9%, p<0.01), greater LV volumes (123±38 vs. 110±22 ml/m2, p=0.02) and worse right ventricular ejection fraction (54±12% vs. 59±10%, p=0.02) . Nevertheless, only 17 (29%) LV-RR patients presented LGE compared to 31 (47%, p=0.04) no-LV-RR patients. Moreover, among LGE-positive patients (n=48), only 17 (35%) developed LV-RR, while among LGE-negative patients (n=77), 42 (55%) developed LV-RR (p=0.04). Multivariate regression analysis showed that the absence of LGE at baseline CMR was a strong predictor of LV-RR (p=0.02), even after correction for age, New York Heart Association class, LV volumes and systolic function. Conclusions: In patients with idiopathic dilated cardiomyopathy, absence of LGE was a strong independent predictor of LV-RR at 2-year follow-up, irrespective of the initial clinical status and the severity of ventricular dilatation and dysfunction.

scholarly journals Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction Without Volume Measurements Using a Machine Learning Algorithm Mimicking a Human Expert

2019 ◽  
Vol 12 (9) ◽  
Author(s):  
Federico M. Asch ◽  
Nicolas Poilvert ◽  
Theodore Abraham ◽  
Madeline Jankowski ◽  
Jayne Cleve ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ejection Fraction ◽  
Reference Values ◽  
Learning Algorithm ◽  
Left Ventricular ◽  
Machine Learning Algorithm ◽  
Mean Absolute Deviation ◽  
Limits Of Agreement ◽  
Absolute Deviation ◽  
Lv Volumes

Background: Echocardiographic quantification of left ventricular (LV) ejection fraction (EF) relies on either manual or automated identification of endocardial boundaries followed by model-based calculation of end-systolic and end-diastolic LV volumes. Recent developments in artificial intelligence resulted in computer algorithms that allow near automated detection of endocardial boundaries and measurement of LV volumes and function. However, boundary identification is still prone to errors limiting accuracy in certain patients. We hypothesized that a fully automated machine learning algorithm could circumvent border detection and instead would estimate the degree of ventricular contraction, similar to a human expert trained on tens of thousands of images. Methods: Machine learning algorithm was developed and trained to automatically estimate LVEF on a database of >50 000 echocardiographic studies, including multiple apical 2- and 4-chamber views (AutoEF, BayLabs). Testing was performed on an independent group of 99 patients, whose automated EF values were compared with reference values obtained by averaging measurements by 3 experts using conventional volume-based technique. Inter-technique agreement was assessed using linear regression and Bland-Altman analysis. Consistency was assessed by mean absolute deviation among automated estimates from different combinations of apical views. Finally, sensitivity and specificity of detecting of EF ≤35% were calculated. These metrics were compared side-by-side against the same reference standard to those obtained from conventional EF measurements by clinical readers. Results: Automated estimation of LVEF was feasible in all 99 patients. AutoEF values showed high consistency (mean absolute deviation =2.9%) and excellent agreement with the reference values: r =0.95, bias=1.0%, limits of agreement =±11.8%, with sensitivity 0.90 and specificity 0.92 for detection of EF ≤35%. This was similar to clinicians’ measurements: r =0.94, bias=1.4%, limits of agreement =±13.4%, sensitivity 0.93, specificity 0.87. Conclusions: Machine learning algorithm for volume-independent LVEF estimation is highly feasible and similar in accuracy to conventional volume-based measurements, when compared with reference values provided by an expert panel.

Sign in / Sign up

Export Citation Format

Share Document