scholarly journals 545 Deep learning/artificial intelligence for automatic measurement of global longitudinal strain by echocardiography

2020 ◽  
Vol 21 (Supplement_1) ◽  
Author(s):  
I M Salte ◽  
A Oestvik ◽  
E Smistad ◽  
D Melichova ◽  
T M Nguyen ◽  
...  

Abstract Funding Acknowledgements The Norwegian Health Association, South-Eastern Norway regional health Authority and the national program for clinical therapy research (KLINBEFORSK). Background Global longitudinal strain (GLS) by echocardiography has incremental prognostic value in patients with acute myocardial infarction and heart failure compared to left ventricular (LV) ejection fraction and provides more reproducible measurements of LV function. Recent advances in machine learning for image analysis now open the possibility for robust fully automated tracing of the LV and measurement of global longitudinal strain (GLS), without any operator input. This could make real-time GLS possible and remove inter-reader variability, thus resulting in saved time and improved test-retest reliability. The aim of the present study was to investigate how measurements by this novel automatic method compares to conventional speckle tracking analyses of GLS. Methods 100 transthoracic echocardiographic examinations were included from a clinical database of patients with acute myocardial infarction or de-novo heart failure. Examinations were included consecutively and regardless of image quality. Simpson biplane LV ejection fraction ranged from 7 to 70%. Images of three standard apical planes from each examination were analysed using our novel and fully automated GLS method based on deep learning technology. The automated GLS measurements were compared to conventional speckle tracking GLS measurements of the same acquisitions using vendor specific format and software (EchoPAC, GE Healthcare), performed by a single experienced observer. Results GLS was -11.6 ± 4.5% and -12.8 ± 5.0% for the deep learning method and the conventional method, respectively. Bland-Altman analysis showed a bias of -0.7 ± 1,9% and 95% limits of agreement of -4,6 to 3.1. No clear value dependent bias was found by visual inspection (Figure A). Feasibility for measurement of GLS was 93% for the deep learning based method and 99% for the conventional method. The limits of agreement found in our study is comparable to findings in the intervendor comparison study by the EASCVI/ASE/Industry Task force to standardize deformation imaging. Conclusion This novel deep learning based method succeeds without any operator input to automatically identify and classify the three apical standard views, trace the myocardium, perform motion estimation and measure global longitudinal strain. This could further facilitate the clinical use of GLS as an important tool for enhancing clinical decision-making. Abstract 545 Figure.

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
B Luvsansuren ◽  
S Chimed

Abstract Background Depression of left ventricular function is common phenomenon after acute myocardial infarction and it's often associated with poor prognosis. However, substantial portion of patients with acute myocardial infarction had normal left ventricular function by assessment of left ventricular ejection fraction. Purpose In this study, we examined role of left ventricular global longitudinal strain assessment in patients who had normal ejection fraction after acute myocardial infarction. Methods We choose patients with acute myocardial infarction who were successfully treated with primary percutaneous coronary intervention (PCI). All of those patients had normal ejection fraction (EF≥55%) in routine echocardiographic examination within 3 days after acute myocardial infarction. Two dimensional speckle tracking echocardiography was used to assess left ventricular global longitudinal strain. Based on existence of newly onset clinical signs (pulmonary edema, lung crackles, peripherial edema etc.) of heart failure patients divided into case and control group. Patients who had other etiology or previous heart failure were excluded. Results A total of 153 patients with AMI were selected and newly onset heart failure is occurred in 20 patients. Left ventricular global strain was significantly different between patients with clinical heart failure and patients without clinical heart failure (−11.1±1.85% vs. −16.6±3.38%, p<0.001). After adjustment of possible predictors of impaired left ventricular function such as, age, gender, hypertension, diabetes, previous coronary artery disease, cardiac troponin, mitral inflow EA ratio, deceleration time, left ventricular end diastolic volume, ejection fraction, mitral annulus EE' ratio and wall motion score index, global longitudinal strain was independent predictor of clinical heart failure (odds ratio 1.79, 95% CI 1.22–2.65, p=0.003). Adding global longitudinal strain into above mentioned predictors of clinical heart failure after acute myocardial infarction is associated with significantly increased c-statistic (0.93, 95% CI 0.87–0.99 vs. 0.97, 95% CI 0.94–0.99, p<0.001). Conclusion Left ventricular global longitudinal strain is independently associated with clinical heart failure in patients with preserved ejection fraction after acute myocardial infarction. Adding global longitudinal strain parameter into screening model may increase rate of precise determination of clinical heart failure after acute myocardial infarction. Funding Acknowledgement Type of funding source: None


2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Laura Houard ◽  
Mihaela S. Amzulescu ◽  
Geoffrey Colin ◽  
Helene Langet ◽  
Sebastian Militaru ◽  
...  

Background: Pulmonary transit time (PTT) from first-pass perfusion imaging is a novel parameter to evaluate hemodynamic congestion by cardiac magnetic resonance (cMR). We sought to evaluate the additional prognostic value of PTT in heart failure with reduced ejection fraction over other well-validated predictors of risk including the Meta-Analysis Global Group in Chronic Heart Failure risk score and ischemic cause. Methods: We prospectively followed 410 patients with chronic heart failure with reduced ejection fraction (61±13 years, left ventricular (LV) ejection fraction 24±7%) who underwent a clinical cMR to assess the prognostic value of PTT for a primary endpoint of overall mortality and secondary composite endpoint of cardiovascular death and heart failure hospitalization. Normal reference values of PTT were evaluated in a population of 40 asymptomatic volunteers free of cardiovascular disease. Results PTT was significantly increased in patients with heart failure with reduced ejection fraction as compared to controls (9±6 beats and 7±2 beats, respectively, P <0.001), and correlated not only with New York Heart Association class, cMR–LV and cMR–right ventricular (RV) volumes, cMR-RV and cMR-LV ejection fraction, and feature tracking global longitudinal strain, but also with cardiac output. Over 6-year median follow-up, 182 patients died and 200 reached the secondary endpoint. By multivariate Cox analysis, PTT was an independent and significant predictor of both endpoints after adjustment for Meta-Analysis Global Group in Chronic Heart Failure risk score and ischemic cause. Importantly in multivariable analysis, PTT in beats had significantly higher additional prognostic value to predict not only overall mortality (χ 2 to improve, 12.3; hazard ratio, 1.35 [95% CI, 1.16–1.58]; P <0.001) but also the secondary composite endpoints (χ 2 to improve=20.1; hazard ratio, 1.23 [95% CI, 1.21–1.60]; P <0.001) than cMR-LV ejection fraction, cMR-RV ejection fraction, LV–feature tracking global longitudinal strain, or RV–feature tracking global longitudinal strain. Importantly, PTT was independent and complementary to both pulmonary artery pressure and reduced RV ejection fraction<42% to predict overall mortality and secondary combined endpoints. Conclusions: Despite limitations in temporal resolution, PTT derived from first-pass perfusion imaging provides higher and independent prognostic information in heart failure with reduced ejection fraction than clinical and other cMR parameters, including LV and RV ejection fraction or feature tracking global longitudinal strain. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03969394.


2021 ◽  
Vol 5 (4) ◽  
pp. 169-175
Author(s):  
E.G. Akramova ◽  
◽  
Е.V. Vlasova ◽  
◽  

Aim: to assess the results of speckle tracking echocardiography (STE) in patients of working age with acute inferior wall myocardial infarction (MI) in the early period after coronary stenting. Patients and Methods: STE was performed using EPIQ-7 Ultrasound Machine (Philips, USA) in 55 patients with acute inferior wall MI one week after percutaneous coronary intervention and 29 healthy individuals of working age. Patients with acute inferior wall MI were divided into two subgroups, i.e., with (n=45) or without (n=10) areas of local contractile impairment (dyskinesia, akinesia, hypokinesia). Results: the most common cause of MI was the occlusion of the right coronary artery (82.4% in subgroup 1 and 60% in subgroup 2) in multivascular involvement (84.4% and 90%. respectively). In patients with local contractile impairment, reduced left ventricular ejection fraction (EF) was reported in 28.9%, global longitudinal strain in 86.7%, and global circular strain in 76.7%. Meanwhile, in patients without local contractile impairment, left ventricular ejection fraction (LV EF) was within normal ranges, global longitudinal strain was reported in 100% and global circumferential strain in 70%. The presence and severity of local dysfunction did not affect the reduction in segmental strain (median varied from -9% to -15%). In inferior wall MI, the abnormal regional longitudinal strain of 6 LV segments (basal and mid inferoseptal, inferior, and inferolateral) was reported in both hypokinesia and normokinesia. Conclusions: ultrasound evaluation of systolic LV function using STE is characterized by greater diagnostic value compared to the measurement of EF only and objectifies the efficacy of surgery. Quantitative assessment of the recovery of both global and local systolic contractility is another advantage of STE allowing for personalized treatment. KEYWORDS: inferior wall myocardial infarction, echocardiography, speckle tracking technology, percutaneous coronary intervention, ejection fraction. FOR CITATION: Akramova E.G., Vlasova Е.V. Assessment of left ventricular contractility in acute inferior wall myocardial infarction by speckle tracking echocardiography. Russian Medical Inquiry. 2021;5(4):169–175 (in Russ.). DOI: 10.32364/2587-6821-2021-5-4-169-175.


2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
K Ablasser ◽  
D Von Lewinski ◽  
E Kolesnik ◽  
M Gangl ◽  
L Kattnig ◽  
...  

Abstract Background In chronic heart failure (CHF) NT-proBNP and left ventricular ejection fraction (LVEF) by echocardiography are standard diagnostic as well as follow-up markers and are known to correlate with prognosis. Speckle-tracking echocardiography is a more recent technique to quantify myocardial deformation as a measurement of left ventricular function with potential benefits over LVEF. Purpose The purpose of this investigation was to analyse the cross-sectional relationship between 2D speckle tracking-derived global longitudinal strain (GLS) and NT-proBNP plasma levels in a prospective cohort of ischemic and non-ischemic CHF patients. Methods We enrolled 205 patients with chronic heart failure. Major inclusion criteria were age over 18 years, stable disease with absence of unplanned hospitalization or change in medication or device therapy in the previous month or major surgery in the previous 3 months. CHF treatment had to be according to the recommendations of the ESC CHF guidelines 2016 and LVEF had to be below 50%. Patient history, physical examination and an extensive echocardiography exam were performed. Lab results included NT-proBNP. Manual longitudinal strain was calculated using EchoPAC (General Electric Medical Systems, Horten, Norway) by a single and blinded examiner. LVEF was measured using Simpson's biplane method. Results 205 patients included in the study. The baseline characteristics included mean age 65.0 years and 75% male. Mean GLS was −9.6% (SD ±4.5%) and median NT-proBNP 1269.5 (IQR 379.5–2759.5) ng/ml. The CHF aetiology was 70.0% ischemic vs 30.0% non-ischemic. There was a significant negative correlation between GLS and NT-proBNP (Pearson r=0.239, p=0.029), this was not significant for LVEF and NT-proBNP (Pearson r=0.149, p=0.228).In a multivariate regression analysis adjusted for age, sex, NYHA classification and HF aetiology, GLS remained significantly correlated with NT-proBNP (adjusted beta-coefficient= 0.289, p=0.011). Furthermore, in contrast to LVEF, GLS showed a significant correlation to NT-proBNP in patients with ischemic (Pearson r=0.266, p=0.049) as well as non-ischemic aetiology of heart failure (Pearson r=0.434, p=0.034). Conclusion Global longitudinal strain, not LVEF, was significantly correlated with NT-proBNP in patients with CHF, independently of age, sex, symptoms or heart failure aetiology. This shows that speckle-tracking might be superior to LVEF for the assessment of left ventricular function in CHF.


2019 ◽  
Vol 5 (1) ◽  
pp. 62
Author(s):  
Dyah Adhi Kusumastuti ◽  
Nahar Taufiq ◽  
Hasanah Mumpuni

Background: Epidemiological data show that the incidence of heart failure after myocardial infarction is about 20%. The incidence of heart failure after acute myocardial infarction is also known to increase post-infarct mortality. The incidence of heart failure is related to the remodelling process after acute myocardial infarction. The acute remodelling process after acute myocardial infarction involves a mechanical mechanism in which there is a change in left ventricular geometry as an adaptive response to the incidence of infarction and then results in increased left ventricular wall stress. Increased left ventricular wall stress can be assessed by measuring global longitudinal strain (GLS) using echocardiography. On the other hand, mechanical overload in the myocardium is known to increase sST2 levels. The relationship between increased levels of sST2 and left ventricular GLS in patients with acute myocardial infarction has never been studied before.Methods: An analytic observational study with a cross-sectional design conducted from July to September 2018 at Dr Sardjito Hospital. Patients diagnosed with acute myocardial infarction and fulfilling the inclusion and exclusion criteria were included in the study. Measurement of sST2 levels and echocardiographic examination was performed on the first day after admission. Correlation test analysis was conducted to determine the relationship between sST2 levels and left ventricular GLS.Results: There were 72 subjects, with 62 STEMI subjects and 10 NSTEMI subjects. The mean level of sST2 in this study was 4,252 ± 198 pg / mL. Measurement of the left ventricular function obtained a mean ejection fraction of 47 ± 9%, LVIDd 45.79 ± 6.2 mm and GLS values of -9.3 ± 3.3%. Correlation test using Spearman test showed that there was no correlation between increased sST2 levels and decreased GLS values in patients with acute myocardial infarction (r = -0.133; p = 0.344).Conclusion: Increased sST2 levels were not correlated with decreased GLS values in patients with acute myocardial infarction.


2020 ◽  
Vol 21 (Supplement_1) ◽  
Author(s):  
H Ebeid ◽  
R Abd El Hady ◽  
K El Khashab ◽  
M Husein

Abstract Background The occurrence of in-hospital heart failure in the acute phase of myocardial infarction carries an ominous prognosis and is often preceded by abrupt loss of functioning myocardium. However ,In hospital heart failure may occur in patients with apparently only minor myocardial injury and preserved or only moderately reduced left ventricular ejection fraction and still carries a significantly increased risk of adverse outcome. In patients with clinical symptoms of heart failure despite preserved left ventricular ejection fraction(heart failure with preserved ejection fraction), abnormalities in longitudinal myocardial mechanics have been reported suggesting that the discrepancy between near normal left ventricular ejection fraction and clinical symptoms may be partially explained by theses indices. Purpose Evaluation of the role of global longitudinal strain in prediction of the occurrence of in hospital heart failure in patients presenting with acute myocardial infarction particularly in patients with normal ,or moderately impaired ejection fraction. Methods forty patients with first attack of acute myocardial infarction were ranked according to killip class during their hospital admission and course. The patients were divided into two groups: Group 1: patients having in-hospital heart failure (killip class &gt; 1).Group2: Patients not having in–hospital heart failure (killip class = 1). Echocardiogaraphic examination was done for them including global longitudinal strain within 72 hours after successful reperfusion .Comparison of different echocardiographic parameters between the two groups was done. Patients with mildly impaired ejection fraction (Ejection fraction &gt; 40%) were studied for echocardiographic parameters correlated significantly with the occurrence of in-hospital heart failure . Results Patients with in-hospital heart failure had significantly impaired global longitudinal strain(-8.63%+1.57% vs -12.41%+1.31%, p = 0.000), lower left ventricular ejection fraction (34.17%+8.17% vs 42.92 %+7.98%,p &lt; 0.001) and higher wall motion score index (1.57 + 0.32 vs 1.31 +0.24 ,p &lt; 0.006). In patients with left ventricular ejection fraction &gt;40% experienced in-hospital heart failure also exhibited significantly impaired global longitudinal strain p= 0.035 . Conclusion Global longitudinal strain can offer accurate, feasible, and non invasive predictor of hemodynamic deterioration in patients with myocardial infarction. Global longitudinal strain was superior to left ventricular ejection fraction , wall motion score index in evaluation of myocardial dysfunction specially in those with preserved left ventricular ejection fraction(EF &gt; 40%).Global longitudinal strain was also superior to left ventricular ejection fraction , wall motion score index in detection of patients with Killip class II ( those without overt heart failure ,and who can be easily missed).


Sign in / Sign up

Export Citation Format

Share Document