Left ventricular ejection fraction using manual and semi-automated biplane method of discs in very preterm infants

Development of automated neural network prediction for echocardiographic left ventricular ejection fraction

Introduction

The echocardiographic measurement of left ventricular ejection fraction (LVEF) is fundamental to the diagnosis and classification of patients with heart failure (HF).

Methods

This paper aimed to quantify LVEF automatically and accurately with the proposed pipeline method based on deep neural networks and ensemble learning. Within the pipeline, an Atrous Convolutional Neural Network (ACNN) was first trained to segment the left ventricle (LV), before employing the area-length formulation based on the ellipsoid single-plane model to calculate LVEF values. This formulation required inputs of LV area, derived from segmentation using an improved Jeffrey's method, as well as LV length, derived from a novel ensemble learning model. To further improve the pipeline's accuracy, an automated peak detection algorithm was used to identify end-diastolic and end-systolic frames, avoiding issues with human error. Subsequently, single-beat LVEF values were averaged across all cardiac cycles to obtain the final LVEF.

Results

This method was developed and internally validated in an open-source dataset containing 10,030 echocardiograms. The Pearson's correlation coefficient was 0.83 for LVEF prediction compared to expert human analysis (p < 0.001), with a subsequent area under the receiver operator curve (AUROC) of 0.98 (95% confidence interval 0.97 to 0.99) for categorisation of HF with reduced ejection (HFrEF; LVEF<40%). In an external dataset with 200 echocardiograms, this method achieved an AUC of 0.90 (95% confidence interval 0.88 to 0.91) for HFrEF assessment.

Conclusion

The automated neural network-based calculation of LVEF is comparable to expert clinicians performing time-consuming, frame-by-frame manual evaluations of cardiac systolic function.

The association between patterns of early respiratory disease and diastolic dysfunction in preterm infants

BACKGROUND

This study aims to determine the association between clinical patterns of early respiratory disease and diastolic dysfunction in preterm infants.

METHODS

Preterm infants <29 weeks' gestation underwent cardiac ultrasounds around day 7 and 14-21. Respiratory dysfunction patterns were classified as stable (ST), respiratory deterioration (RD) or early persistent respiratory dysfunction (EPRD) according to oxygen need. Diastolic dysfunction was diagnosed using a multi-parameter approach including left atrial strain (LASR) to help differentiate between cardiac or pulmonary pathophysiology.

RESULTS

98 infants (mean 27 weeks) were included. The prevalence of ST, RD and EPRD was 53%, 21% and 26% respectively. Diastolic dysfunction was more prevalent in the RD and EPRD groups with patent ductus arteriosus and significant growth restriction as risk factors. Not all infants with a PDA developed diastolic dysfunction. LASR was lower in the EPDR group.

CONCLUSION

Respiratory dysfunction patterns are associated with diastolic dysfunction in preterm infants.

Echocardiography algorithms to assess high left atrial pressure and grade diastolic function in preterm infants

BACKGROUND

Relaxation, restoring forces, myocardial stiffness and atrial function determine left ventricular (LV) diastolic function. This study aims to provide a comprehensive assessment of diastolic function in preterm infants using conventional echocardiography and speckle tracking imaging and determine the diagnostic accuracy of various algorithms to detect high left atrial pressure (LAP).

METHODS

Preterm infants received an echocardiogram 1 week after birth and diastolic reference values were derived from the outer percentiles of stable preterm infants. Impaired relaxation, LV stiffness and high LAP were defined by using algorithms where at least half of the parameters were outside the normal range. Diastolic function was graded using the 2016 American Society of Echocardiography algorithm and expanded with the EA ratio and left atrial strain. The diagnostic accuracy of various algorithms to detect high LAP was determined with sensitivity analysis.

RESULTS

We studied 146 infants (59 stable) with a mean of 27(1) weeks gestation. Impaired relaxation, LV stiffness and high LAP were found in 8%, 7%, and 14% of infants. The patent ductus arteriosus was a contributing factor to high LAP and LV stiffness, not impaired relaxation. Diagnostic accuracy improved from 90% to 96% and sensitivity from 40% to 90% by adding left atrial strain to the 2016 algorithm.

CONCLUSION

Various grades of diastolic dysfunction could be appreciated in preterm infants using a multi-parameter approach. Adding left atrial strain improved sensitivity to detect infants with high LAP.

Comprehensive Metabolomic Profiling of Cord Blood and Placental Tissue in Surviving Monochorionic Twins Complicated by Twin-Twin Transfusion Syndrome With or Without Fetoscopic Laser Coagulation Surgery: A Retrospective Cohort Study

Objectives: To investigate metabolomic perturbations caused by twin-twin transfusion syndrome, metabolic changes associated with fetoscopic laser coagulation in both placental tissue and cord plasma, and to investigate differential metabolites pertinent to varying fetal outcomes, including hemodynamic status, birth weight, and cardiac function, of live-born babies.

Methods: Placental tissue and cord plasma samples from normal term or uncomplicated preterm-born monochorionic twins and those complicated by twin-twin transfusion syndrome treated with or without fetoscopic laser coagulation were analyzed by high-performance liquid chromatography metabolomic profiling. Sixteen comparisons of different co-twin groups were performed. Partial least squares–discriminant analysis, metabolic pathway analysis, biomarker analysis, and Spearman’s correlation analysis were conducted based on differential metabolites used to determine potential biomarkers in different comparisons and metabolites that are pertinent to neonatal birth weight and left ventricular ejection fraction.

Results: These metabolomic investigations showed that the cord plasma metabolome has a better performance in discriminating fetuses among different hemodynamic groups than placental tissue. The metabolic alteration of twin-twin transfusion syndrome in these two types of samples centers on fatty acid and lipid metabolism. The fetoscopic laser coagulation procedure improves the metabolomic change brought by this syndrome, making the metabolomes of the treated group less distinguishable from those of the control and preterm birth groups. Certain compounds, especially lipids and lipid-like molecules, are noted to be potential biomarkers of this morbid disease and pertinent to neonatal birth weight and ejection fraction.

Conclusions: Fetoscopic laser coagulation can ameliorate the metabolomic alteration caused by twin-twin transfusion syndrome in placental tissue and cord plasma, which are involved mainly in fatty acid and lipid-like molecule metabolism. Certain lipids and lipid-like molecules are helpful in differentiating co-twins of different hemodynamic statuses and are significantly correlated with neonatal birth weight or ejection fraction.

Echocardiography protocol for early detection of cardiac dysfunction in childhood cancer survivors in the multicenter DCCSS LATER 2 CARD study: Design, feasibility, and reproducibility

BACKGROUND

Cardiotoxicity is a well-known side effect after anthracyclines and chest radiotherapy in childhood cancer survivors (CCS). The DCCSS LATER 2 CARD (cardiology) study includes evaluation of echocardiographic measurements for early identification of CCS at highest risk of developing heart failure. This paper describes the design, feasibility, and reproducibility of the echocardiography protocol.

METHODS

Echocardiograms from CCS and sibling controls were prospectively obtained at the participating centers and centrally analyzed. We describe the image acquisition, measurement protocol, and software-specific considerations for myocardial strain analyses. We report the feasibility of the primary outcomes of systolic and diastolic function, as well as reproducibility analyses in 30 subjects.

RESULTS

We obtained 1,679 echocardiograms. Biplane ejection fraction (LVEF) measurement was feasible in 91% and 96% of CCS and siblings, respectively, global longitudinal strain (GLS) in 80% and 91%, global circumferential strain (GCS) in 86% and 89%, and ≥2 diastolic function parameters in 99% and 100%, right ventricle free wall strain (RVFWS) in 57% and 65%, and left atrial reservoir strain (LASr) in 72% and 79%. Intra-class correlation coefficients for inter-observer variability were 0.85 for LVEF, 0.76 for GLS, 0.70 for GCS, 0.89 for RVFWS and 0.89 for LASr. Intra-class correlation coefficients for intra-observer variability were 0.87 for LVEF, 0.82 for GLS, 0.82 for GCS, 0.85 for RVFWS and 0.79 for LASr.

CONCLUSION

The DCCSS LATER 2 CARD study includes a protocolized echocardiogram, with feasible and reproducible primary outcome measurements. This ensures high-quality outcome data for prevalence estimates and for reliable comparison of cardiac function parameters.