Machine learning prediction of right ventricular volume and ejection fraction from two-dimensional echocardiography in patients with pulmonary regurgitation

Right ventricular (RV) end-diastolic volume (RVEDV) and ejection fraction (RVEF) by cardiac MRI (cMRI) guide management in chronic pulmonary regurgitation (PR). Two-dimensional echocardiography suboptimally correlate with RV volumes. This study tested whether combination of guideline-directed RV measures in a machine learning (ML) framework improves quantitative assessment of RVEDV and RVEF. RV measurements were obtained on subjects with > mild PR who had cMRI and echocardiogram within 90 days. A gradient-boosted trees algorithm predicted cMRI RV dilation (RVEDV > 160 ml/m2) and RV dysfunction (RVEF<47%), first with "guideline-only" measures, and then with "expanded-features" to include 44 total echocardiographic, clinical, and demographic variables. Model performance was compared to clinician visual assessment. Of 232 studies (56% tetralogy of Fallot, 20% pulmonary stenosis), the median age was 21.5 years, 21 (9%) had RV dilation, and 42 (18%) had RV dysfunction. For RV dilation prediction, the guideline-only model area under the receiver operating characteristic (AUROC)=0.68, and expanded-features model AUROC=0.85. At 90% sensitivity, the expanded-features model had 73% specificity, 25% positive predictive value (PPV), and 99% negative predictive value (NPV) This was similar to clinician performance (sensitivity 81%, specificity 81%, PPV 29%, NPV 98%). For prediction of RV dysfunction, the guideline-only AUROC= 0.71, additional features did not improve the model, and clinicians outperformed the model. In patients with PR, a ML model combining guidelines for RV assessment with demographic and additional echocardiographic parameters may effectively rule-out those with significant RV dilation at clinical thresholds for intervention, and performs similarly to expert clinicians.

Bedside right ventricle quantification using three-dimensional echocardiography in children with congenital heart disease: A comparative study with cardiac magnetic resonance imaging

BACKGROUND

Accurate quantification of right ventricular (RV) volumes and function is crucial for the management of congenital heart diseases.

AIMS

We aimed to assess the feasibility and accuracy of bedside analysis using new RV quantification software from three-dimensional transthoracic echocardiography in children with or without congenital heart disease, and to compare measurements with cardiac magnetic resonance imaging.

METHODS

We included paediatric patients with congenital heart disease (106 patients) responsible for RV volume overload and a control group (30 patients). All patients underwent three-dimensional transthoracic echocardiography using a Vivid E95 ultrasound system. RV end-diastolic and end-systolic volumes and RV ejection fraction were obtained using RV quantification software. Measurements were compared between RV quantification and cardiac magnetic resonance imaging in 27 patients.

RESULTS

Bedside RV quantification analysis was feasible in 133 patients (97.8%). Manual contour adjustment was necessary in 126 patients (93%). The mean time of analysis was 62±42s. RV end-diastolic and end-systolic volumes were larger in the congenital heart disease group than the control group: median 85.0 (interquartile range 29.5) mL/m2 vs 55.0 (interquartile range 20.5) mL/m2 for RV end-diastolic volume and 42.5 (interquartile range 15.3) mL/m2 vs 29.0 (interquartile range 11.8) mL/m2 for RV end-systolic volume, respectively. Good agreement for RV end-diastolic and end-systolic volumes and RV ejection fraction was found between RV quantification and magnetic resonance imaging measurements. RV quantification software underestimated RV end-diastolic volume/body surface area by 3mL/m2 and RV ejection fraction by 2.1%, and overestimated RV end-systolic volume/body surface area by 0.2mL/m2.

CONCLUSIONS

We found good feasibility and accuracy of bedside RV quantification analysis from three-dimensional transthoracic echocardiography in children with or without congenital heart disease. RV quantification could be a reliable and non-invasive method for RV assessment in daily practice, facilitating appropriate management and follow-up care.

Evolving Role of Three-Dimensional Echocardiography for Right Ventricular Volume Analysis in Pediatric Heart Disease: Literature Review and Clinical Applications

Accurate knowledge of right ventricular (RV) volumes and ejection fraction is fundamental to providing optimal care for pediatric patients with congenital and acquired heart disease, as well as pulmonary hypertension. Traditionally, these volumes have been measured using cardiac magnetic resonance because of its accuracy, reproducibility, and freedom from geometric assumptions. More recently, an increasing number of studies have described the measurement of RV volumes using three-dimensional (3D) echocardiography. In addition, volumes by 3D echocardiography have also been used for outcome research studies in congenital heart surgery. Importantly, 3D echocardiographic acquisitions can be obtained over a small number of cardiac cycles, do not require general anesthesia, and are less costly than CMR. The ease and safety of the 3D echocardiographic acquisitions allow serial studies in the same patient. Moreover, the studies can be performed in various locations, including the intensive care unit, catheterization laboratory, and general clinic. Because of these advantages, 3D echocardiography is ideal for serial evaluation of the same patient. Despite these potential advantages, 3D echocardiography has not become a standard practice in children with congenital and acquired heart conditions. In this report, the authors review the literature on the feasibility, reproducibility, and accuracy of 3D echocardiography in pediatric patients. In addition, the authors investigate the advantages and limitations of 3D echocardiography in RV quantification and offer a pathway for its potential to become a standard practice in the assessment, planning, and follow-up of congenital and acquired heart disease.

Repaired Tetralogy of Fallot: Have We Understood the Right Timing of PVR?

Despite many advances in surgical repair during the past few decades, the majority of tetralogy of Fallot patients continue to experience residual hemodynamic and electrophysiological abnormalities. The actual issue, which has yet to be solved, is understanding how this disease evolves in each individual patient and, as a result, who is truly at risk of sudden death, as well as the proper timing of pulmonary valve replacement (PVR). Our responsibility should be to select the most appropriate time for each patient, going above and beyond imaging criteria used up to now to make such a clinically crucial decision. Despite several studies on timing, indications, procedures, and outcomes of PVR, there is still much uncertainty about whether PVR reduces arrhythmia burden or improves survival in these patients and how to appropriately manage this population. This review summarizes the most recent research on the evolution of repaired tetralogy of Fallot (from adolescence onwards) and risk factor variables that may favor or delay PVR.

Quantitative Prediction of Right Ventricular Size and Function From the ECG

BACKGROUND

Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored.

METHODS AND RESULTS

We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m2), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; P=0.031).

CONCLUSIONS

Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.

Added value of 3D echocardiography in the diagnosis and prognostication of patients with right ventricular dysfunction

Recent inroads into percutaneous-based options for the treatment of tricuspid valve disease has brought to light how little we know about the behavior of the right ventricle in both health and disease and how incomplete our assessment of right ventricular (RV) physiology and function is using current non-invasive technology, in particular echocardiography. The purpose of this review is to provide an overview of what three-dimensional echocardiography (3DE) can offer currently to enhance RV evaluation and what the future may hold if we continue to improve the 3D evaluation of the right heart.

Multimodality Imaging Assessment of Tetralogy of Fallot: From Diagnosis to Long-Term Follow-Up

Tetralogy of Fallot (TOF) is the most common complex congenital heart disease with long-term survivors, demanding serial monitoring of the possible complications that can be encountered from the diagnosis to long-term follow-up. Cardiovascular imaging is key in the diagnosis and serial assessment of TOF patients, guiding patients' management and providing prognostic information. Thorough knowledge of the pathophysiology and expected sequalae in TOF, as well as the advantages and limitations of different non-invasive imaging modalities that can be used for diagnosis and follow-up, is the key to ensuring optimal management of patients with TOF. The aim of this manuscript is to provide a comprehensive overview of the role of each modality and common protocols used in clinical practice in the assessment of TOF patients.

A comparison between the apical and subcostal view for three-dimensional echocardiographic assessment of right ventricular volumes in pediatric patients

Background

Accurate measurement of ventricular volumes is an important clinical imaging goal. Three-dimensional echocardiography (3DEcho) is used increasingly as it is more available and less costly than cardiac magnetic resonance (CMR). For the right ventricle (RV), the current practice is to acquire 3DEcho volumes from the apical view. However, in some patients the RV may be better seen from the subcostal view. Therefore, this study compared RV volume measurements from the apical vs. the subcostal view, using CMR as a reference standard.

Methods

Patients <18 years old undergoing a clinical CMR examination were prospectively enrolled. 3DEcho was performed on the day of the CMR. 3DEcho images were acquired with Philips Epic 7 ultrasound system from apical and subcostal views. Offline analysis was performed with TomTec 4DRV Function for 3DEcho images and cvi42 for CMR ones. RV end-diastolic volume and end-systolic volume were collected. Agreement between 3DEcho and CMR was assessed with Bland-Altman analysis and the intraclass correlation coefficient (ICC). Percentage (%) error was calculated using CMR as the reference standard.

Results

Forty-seven patients were included in the analysis (age range 10 months to 16 years). The ICC was moderate to excellent for all volume comparisons to CMR (subcostal vs. CMR: end-diastolic volume 0.93, end-systolic volume 0.81; apical vs. CMR: end-diastolic volume 0.94, end-systolic volume 0.74).The 3DEcho mean % error vs. CMR for end-systolic volume was 25% for subcostal and 31% for apical; for end-diastolic volume it was 15% for subcostal and 16% for apical. The % error was not significantly different between apical vs. subcostal views for end-systolic and end-diastolic volume measurements.

Conclusions

For apical and subcostal views, 3DEcho-derived ventricular volumes agree well with CMR. Neither echo view has a consistently smaller error when compared to CMR volumes. Accordingly, the subcostal view can be used as an alternative to the apical view when acquiring 3DEcho volumes in pediatric patients, particularly when the image quality from this window is superior.

Quantitative prediction of right ventricular and size and function from the electrocardiogram

Background

Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep-learning enabled 12-lead electrocardiogram analysis (DL-ECG) for estimation of RV size or function is unexplored.

Methods

We trained a DL-ECG model to predict RV dilation (RVEDV>120 mL/m2), RV dysfunction (RVEF≤40%), and numerical RVEDV/RVEF from 12-lead ECG paired with reference-standard cardiac MRI (cMRI) volumetric measurements in UK biobank (UKBB; n=42,938). We fine-tuned in a multi-center health system (MSHoriginal; n=3,019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance using area under the receiver operating curve (AUROC) for categorical and mean absolute error (MAE) for continuous measures overall and in key subgroups. We assessed association of RVEF prediction with transplant-free survival with Cox proportional hazards models.

Results

Prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. Prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts 0.91/0.81/0.92, respectively. MSHoriginal MAE was RVEF=7.8% and RVEDV=17.6 ml/m2. Performance was similar in key subgroups including with and without left ventricular dysfunction. Over median follow-up of 2.3 years, predicted RVEF was independently associated with composite outcome (HR 1.37 for each 10% decrease, p=0.046).

Conclusions

DL-ECG analysis can accurately identify significant RV dysfunction and dilation both overall and in key subgroups. Predicted RVEF is independently associated with clinical outcome.

A deep learning approach for fully automated cardiac shape modeling in tetralogy of Fallot

BACKGROUND

Cardiac shape modeling is a useful computational tool that has provided quantitative insights into the mechanisms underlying dysfunction in heart disease. The manual input and time required to make cardiac shape models, however, limits their clinical utility. Here we present an end-to-end pipeline that uses deep learning for automated view classification, slice selection, phase selection, anatomical landmark localization, and myocardial image segmentation for the automated generation of three-dimensional, biventricular shape models. With this approach, we aim to make cardiac shape modeling a more robust and broadly applicable tool that has processing times consistent with clinical workflows.

METHODS

Cardiovascular magnetic resonance (CMR) images from a cohort of 123 patients with repaired tetralogy of Fallot (rTOF) from two internal sites were used to train and validate each step in the automated pipeline. The complete automated pipeline was tested using CMR images from a cohort of 12 rTOF patients from an internal site and 18 rTOF patients from an external site. Manually and automatically generated shape models from the test set were compared using Euclidean projection distances, global ventricular measurements, and atlas-based shape mode scores.

RESULTS

The mean absolute error (MAE) between manually and automatically generated shape models in the test set was similar to the voxel resolution of the original CMR images for end-diastolic models (MAE = 1.9 ± 0.5 mm) and end-systolic models (MAE = 2.1 ± 0.7 mm). Global ventricular measurements computed from automated models were in good agreement with those computed from manual models. The average mean absolute difference in shape mode Z-score between manually and automatically generated models was 0.5 standard deviations for the first 20 modes of a reference statistical shape atlas.

CONCLUSIONS

Using deep learning, accurate three-dimensional, biventricular shape models can be reliably created. This fully automated end-to-end approach dramatically reduces the manual input required to create shape models, thereby enabling the rapid analysis of large-scale datasets and the potential to deploy statistical atlas-based analyses in point-of-care clinical settings. Training data and networks are available from cardiacatlas.org.

The value of myocardial strain imaging in the evaluation of patients with repaired Tetralogy of Fallot: a review of the literature

Tetralogy of Fallot (ToF) is considered to be the most common, complex, cyanotic congenital heart disease (CHD) representing 7-10% of all congenital heart defects, whereas the patients with ToF are the most frequently operated in their early infancy or childhood. Cardiac magnetic resonance (CMR) consists a valuable imaging technique for the diagnosis and serial follow-up of CHD patients. Furthermore, in recent years, advanced echocardiography imaging techniques have come to the fore, aiming to achieve a complete and more accurate evaluation of cardiac function using speckle tracking imaging modalities. We conducted a review of the literature in order to assess the myocardial deformation of patients with repaired ToF (rToF) using echocardiographic and CMR parameters. Patients with rToF have impaired myocardial strain parameters, that are well standardized either with the use of speckle tracking echocardiography or with the use of CMR imaging. Subclinical left ventricular dysfunction (low GLS) and myocardial dyssynchrony are commonly identified in rToF patients. Impaired left atrium (LA) and right atrium (RA) mechanics are, also, a common finding in this study population, but the studies using atrial strain are a lot fewer than those with LV and RV strain. No studies using myocardial work were identified in the literature, as far as rToF patients are concerned, which makes it an ideal field for further investigation.

Does the right ventricle size influence the left ventricle size and function in children with Ebstein anomaly?

PURPOSE

Patients with Ebstein anomaly (EA) have a variety of clinical manifestation. The assessment of structural and geometric characteristics of the heart is important for optimal management.

METHODS

We retrospectively analyzed echocardiography database from 2009 to 2020. We evaluate patients in two groups: patients with EA were in Group 1 and children without cardiovascular pathology were in Group 2. All children in both groups underwent echocardiography according to American Society of Echocardiography recommendations. The shape of the heart chambers and their function were studied in both groups.

RESULTS

There were 153 in Group 1 and 2000 children without cardiovascular disease in Group 2. It was shown that in children with EA, the shape of the ventricle became less spherical, which was accompanied by a decrease in myocardial mass, and the ejection fraction was reduced 34% of patients. The functional volume (non-atrialized part) of the right ventricle in patients with EA was reduced, and its contractility was preserved in 62% of cases. Preservation of the contractile properties of the right ventricle in most cases was associated with higher systolic pressure in its cavity.

CONCLUSION

TAPSE, TESV, and the velocity of the annulus fibrous ring movement according to tissue dopplerography in patients with EA do not allow us to assess the contractility of the right ventricle. The myocardial performance index (MPI) characterizes a decrease in the functional volume of the right ventricle.

Evaluation of ventricular function and myocardial deformation in children with repaired tetralogy of Fallot by real-time three-dimensional (four-dimensional) echocardiography

AIM

The left and right ventricular dysfunction are important clinical course indicators in patients with repaired tetralogy of Fallot. This study aimed to evaluate ventricular volumes, functions, and myocardial deformation in children with repaired tetralogy of Fallot by real-time three-dimensional (four-dimensional) echocardiography and compared with healthy children. It also aimed to investigate the relationships between ventricular volumes, functions, and myocardial deformation parameters in the patients.

MATERIALS AND METHODS

In this cross-sectional study, 35 patients (mean age 15.1 ± 2.8 years, 54% male) and 35 healthy controls of similar age, gender, and body measurements underwent echocardiography. End-diastolic volume index, end-systolic volume index, and ejection fractions of both ventricles; global longitudinal, circumferential, radial strain, twist, and torsion of the left ventricle; the longitudinal strain of the right ventricle free wall and septum were measured.

RESULTS

Left ventricular ejection fraction, global circumferential and radial strain, twist and torsion were significantly lower in patients compared with controls. Left ventricular ejection fraction correlated with global circumferential (r = -0.446, p < 0.001) and radial strain (r = -0.433, p < 0.001) in the patients. Right ventricular volumes were significantly higher, and ejection fraction was significantly lower in patients compared with controls. All right ventricular parameters correlated with each other in the patients.

CONCLUSION

Left ventricular contraction pattern was changed, circumferential and radial fibres were most affected in the patients. Right ventricular dilatation and dysfunction were detected, and right ventricular ejection fraction correlated well with strain measurements of the right ventricle.

Echocardiographic Assessment of Right Ventricular Function in Paediatric Heart Disease: A Practical Clinical Approach

As the right ventricle (RV) plays an integral role in different paediatric heart diseases, the accurate assessment of RV size and function is essential in the diagnosis, management, and prognostication of congenital and acquired cardiac lesions. Yet, echocardiographic evaluation of the RV is challenging because of its complex and variable morphology, its different physiology compared with the left ventricle, and its capability to adapt to different loading conditions associated with congenital and acquired heart diseases within certain ranges. Reliable echocardiographic detection of RV systolic and diastolic dysfunction remains challenging while important for patient management. This review provides an updated, practical approach to assessing RV function in structurally normal hearts and in children with common congenital heart defects and in those with pulmonary hypertension. We also review the impact of tricuspid valve function on RV functional parameters. There is no single functional RV parameter that uniquely describes RV function; instead a combination of different parameters is recommended in clinical practice. Qualitative and quantitative analysis of RV function will be reviewed including more recent techniques such as speckle tracking and 3D echocardiography.

Echocardiographic assessment of right ventricular volume in repaired tetralogy of Fallot: a novel approach to an older technique

BACKGROUND

In repaired tetralogy of Fallot (rTOF), right ventricular (RV) enlargement leads to poor outcomes. However, evaluating the RV has limitations; cardiac magnetic resonance (CMR) and 3D echocardiography have barriers including cost and accessibility. Traditional echocardiography is limited given the complex geometry and anterior location of the RV. We propose a novel echocardiographic evaluation of RV volume using 2 separate views.

METHODS

This is a retrospective study of rTOF patients with echocardiogram, CMR, and exercise tests. By echocardiogram, we collected RV length in parasternal long axis (PLAX), area in 4-chamber (4C) view, and measurements per standard guidelines. RV end-diastolic and end-systolic volume (RVEDV and RVESV) were calculated as 5/9 (4C area * PLAX length).

RESULTS

Forty-five patients with 66 sets of CMR, echocardiogram, and exercise tests were included (mean age 13.3 ± 3.2 years). The echocardiographic RVEDV and RVESV showed strong correlation with CMR parameters (r = 0.81 and 0.72; p≤ 0.0001), and moderate correlation with peak oxygen pulse (0.63 and 0.49; p≤0.0001). Guideline measurements had no significant correlation. Echocardiographic RVEDV and RVESV were higher in those requiring subsequent pulmonary valve replacement. Indexed echocardiographic RVEDV of 93 ml/m² had 92% sensitivity and 50% specificity (area under curve 0.75 (p = 0.001)) in predicting CMR RV/LV EDV ratio > 2, which is an early indicator for pulmonary valve replacement.

CONCLUSIONS

This novel technique correlates strongly with CMR, better than traditional parameters. While echocardiogram will not replace CMR, this method would be useful in predicting the RV volume, progression of dilation, and timing of CMR.

Can we Trust in Routine Echocardiography to Assess the Right Ventricle and Pulmonary Insufficiency? A Comparative Study with Cardiac Magnetic Resonance

BACKGROUND

Cardiac magnetic resonance (CMR) is the method of choice for assessing right ventricular (RV) dimensions and function, and pulmonary insufficiency (PI).

OBJECTIVES

To assess the accuracy of two-dimensional echocardiography (2D ECHO) in estimating RV function and dimensions, and the degree of PI, and compare the 2D ECHO and CMR findings.

METHODS

We compared ECHO and CMR reports of patients whose indication for CMR had been to assess RV and PI. A p-value < 0.05 was considered statistically significant.

RESULTS

We included 51 congenital heart disease patients, with a median age of 9.3 years (7-13.3 years). There was poor agreement between 2D ECHO and CMR for classification of the RV dimension (Kappa 0.19; 95% CI 0.05 to 0.33, p 0.004) and function (Kappa 0.16; 95% CI -0.01 to +0.34; p 0.034). The RV was undersized by 2D ECHO in 43% of the cases, and RV function was overestimated by ECHO in 29% of the cases. The degree of agreement between the methods in the classification of PI was not significant (Kappa 0.014; 95% CI -0.03 to +0.06, p 0.27). 2D ECHO tended to overestimate the degree of PI.

CONCLUSIONS

The 2D ECHO showed a low agreement with CMR regarding the RV dimensions and function, and degree of PI. In general, ECHO underestimated the dimensions of the RV and overestimated the function of the RV and the degree of PI as compared with CMR.

A comparison of artificial intelligence-based algorithms for the identification of patients with depressed right ventricular function from 2-dimentional echocardiography parameters and clinical features

Background

Recognizing low right ventricular (RV) function from 2-dimentiontial echocardiography (2D-ECHO) is challenging when parameters are contradictory. We aim to develop a model to predict low RV function integrating the various 2D-ECHO parameters in reference to cardiac magnetic resonance (CMR)-the gold standard.

Methods

We retrospectively identified patients who underwent a 2D-ECHO and a CMR within 3 months of each other at our institution (American University of Beirut Medical Center). We extracted three parameters (TAPSE, S' and FAC_RV) that are classically used to assess RV function. We have assessed the ability of 2D-ECHO derived parameters and clinical features to predict RV function measured by the gold standard CMR. We compared outcomes from four machine learning algorithms, widely used in the biomedical community to solve classification problems.

Results

One hundred fifty-five patients were identified and included in our study. Average age was 43±17.1 years old and 52/156 (33.3%) were females. According to CMR, 21 patients were identified to have RV dysfunction, with an RVEF of 34.7%±6.4%, as opposed to 54.7%±6.7% in the normal RV population (P<0.0001). The Random Forest model was able to detect low RV function with an AUC =0.80, while general linear regression performed poorly in our population with an AUC of 0.62.

Conclusions

In this study, we trained and validated an ML-based algorithm that could detect low RV function from clinical and 2D-ECHO parameters. The algorithm has two advantages: first, it performed better than general linear regression, and second, it integrated the various 2D-ECHO parameters.

Tetralogy of Fallot: cardiac imaging evaluation

Thanks to advances in pediatric cardiology, most infants with tetralogy of Fallot (TOF) now survive into adulthood. This relatively new population of adult patients may face long-term complications, including pulmonary regurgitation (PR), right ventricular (RV) tract obstruction, residual shunts, RV dysfunction, and arrythmias. They will often need to undergo pulmonary valve (PV) replacement and other invasive re-interventions. However, the optimal timing for these procedures is challenging, largely due to the complexity of evaluating RV volume and function. The options for the follow-up of these patients have rapidly evolved from an angiography-based approach to the surge of advanced imaging techniques, mainly echocardiography, cardiac magnetic resonance (CMR), and computer tomography (CT). In this review, we outline the indications, strengths and limitations of these modalities in the adult TOF population.

EDUCATIONAL SERIES IN CONGENITAL HEART DISEASE: Three-dimensional echocardiography in congenital heart disease

Three-dimensional echocardiography is a valuable tool for the assessment of cardiac function where it permits calculation of chamber volume and function. The anatomy of valvar and septal structures can be presented in unique and intuitive ways to enhance surgical planning. Guidance of interventional procedures using the technique has now become established in many clinical settings. Enhancements of image processing to include intracavity flow, image fusion and true 3D displays look set to further improve the contribution of this modality to care of the patient with congenital heart disease.

Use of 2-dimensional speckle-tracking echocardiography to assess left ventricular systolic function in dogs with systemic inflammatory response syndrome

Background

Early identification of systolic dysfunction in dogs with systemic inflammatory response syndrome (SIRS) potentially could improve the outcome and decrease mortality.

Objective

To compare 2‐dimensional speckle tracking (2D‐STE) with 2‐dimensional (2D) and M‐mode echocardiography in the evaluation of systolic function in SIRS dogs.

Animals

Seventeen SIRS and 17 healthy dogs.

Methods

Prospective observational case‐control study. Each dog underwent physical examination, conventional echocardiography, 2D‐STE, and C‐reactive protein measurement.

Results

Dogs with SIRS had lower 2D‐STE ejection fraction (X4D‐EF; 44 ± 8 versus 53 ± 8; P = .003), endocardial global longitudinal strain (ENDO‐G‐Long‐St; −14.6 ± 3.2 versus −18.5 ± 4.1; P = .003), and normalized left ventricular diameter in diastole (1.38 ± 0.25 versus 1.54 ± 0.17; P = .04) and systole (0.85 ± 0.18 versus 0.97 ± 0.11; P = .03) as compared to healthy dogs. Simpson method of disks (SMOD) right parasternal EF (55 ± 9 versus 60 ± 6; P = .07) and end systolic volume index (ESVI; 23 ± 10 versus 21 ± 6; P = .61), SMOD left apical EF (59 ± 9 versus 59 ± 6; P = .87) and ESVI (20 ± 8 versus 22 ± 6; P = .25), fractional shortening (FS; 34 ± 5 versus 33 ± 4; P = .39), M‐mode EF (64 ± 7 versus 62 ± 5; P = .35), and ESVI (23 ± 11 versus 30 ± 9; P = .06) were not significantly different between SIRS and control group, respectively.

Conclusion and Clinical Importance

Speckle tracking X4D‐EF and ENDO‐G‐Long‐St are more sensitive than 2D and M‐Mode FS, EF, and ESVI in detecting systolic impairment in dogs with SIRS.

Multimodality imaging, single center, cross-sectional study in adolescents or young adults with repaired tetralogy of Fallout

BACKGROUND

Proper integration of multiple imaging modalities in the routine follow-up of patients with repaired tetralogy of Fallout (TOF) is poorly supported by data. We report our single center comparative study between cardiac magnetic resonance (CMR) and echocardiography to assess equipoise in the clinical utility of these two imaging methods in an unselected consecutive cohort of TOF patients referred to our outpatient clinic.

MATERIAL AND METHODS

In this cross-sectional study, repaired TOF patients who underwent CMR and echocardiography within a 4-week period between 2010 and 2011 at our Center were included. Linear regression was used to analyze degree of inter modality correlation. A prediction model tested the association between functional data/probrain natriuretic peptide (Pro-BNP) with CMR.

RESULTS

Fifty patients were included in the study (mean age 31 ± 18 years). The best predictors of right ventricle (RV) ejection fraction at CMR were tricuspid anular plane systolic excursion (tricuspid valve anular plane systolic excursion, R 0.37, P < 0.0001) and RV peak S-wave velocity (R 0.40, P < 0.001). Pro-BNP levels did present weak correlation with New York Heart Association functional class (R 0.31, P < 0.002) and QRS duration (R 0.32, P < 0.002) and a moderate correlation with right atrium area at CMR (R 0.46, P < 0.0001).

CONCLUSION

We found limited correlation between the two imaging modalities in the evaluation of RV after intracardiac repair of TOF. Pro-BNP level presents moderate correlation with right atrium area measured with echocardiography. Serial CMR evaluations are needed in this patient population, but they may be interchanged by routine echocardiography in particular in patients with normal or stable echocardiographic parameters.

Innovation in 3D Echocardiographic Imaging

PURPOSE OF REVIEW

The purpose of this review is to detail three-dimensional echocardiographic (3DE) innovations in pre-surgical planning of congenital heart disease, guidance of catheter interventions such as fusion imaging, and functional assessment of patients with congenital heart disease.

RECENT FINDINGS

Innovations in 3DE have helped us delineate the details of atrioventricular valve function and understand the mechanism of atrioventricular valve failure in patients with atrioventricular septal defect and single ventricle post repair. Advancement in holographic display of 3D datasets allows for better manipulation of 3D images in three dimensions and better understanding of anatomic relationships. 3DE with fusion imaging reduces radiation in catheter interventions and provides presentations of 3DE images in the similar fashion as the fluoroscopic images to improve communication between cardiologists. Lastly, 3DE allows for quantitative ventricular volumetric and functional assessment. Recent innovations in 3DE allow for pre-surgical planning for congenital heart disease, reduce radiation using fusion imaging in catheter interventions, and enable accurate assessment of ventricular volume and function without geometric assumptions.

Three-dimensional Echocardiography in Congenital Heart Disease: An Expert Consensus Document from the European Association of Cardiovascular Imaging and the American Society of Echocardiography

Three-dimensional echocardiography (3DE) has become important in the management of patients with congenital heart disease (CHD), particularly with pre-surgical planning, guidance of catheter intervention, and functional assessment of the heart. 3DE is increasingly used in children because of good acoustic windows and the non-invasive nature of the technique. The aim of this paper is to provide a review of the optimal application of 3DE in CHD including technical considerations, image orientation, application to different lesions, procedural guidance, and functional assessment.

Echocardiographic Evaluation of the Right Heart

The appropriate use of echocardiography may reduce the need for invasive diagnostic cardiac procedures. The right side of the heart has recently gained interest among cardiologists as it became clear that abnormalities of the right heart morphology and function are associated with increased morbidity and mortality. Echocardiography is easy to perform, relatively cheap, readily available and do not pose the risk of ionizing radiation. Conventional 2D and, more recently, 3D echocardiography provides pertinent anatomic and physiologic information about the right side of the heart. Because of the advantages and simplicity of echocardiography it continues to be an excellent tool for evaluating the structure and function of the right side of the heart. This review outlines the uses of echocardiography in evaluating the right heart structure and function.

Multi-institutional evaluation of the indications and radiation dose of functional cardiovascular computed tomography (CCT) imaging in congenital heart disease

Ventricular volumes and ejection fraction are often used in clinical decision making in patients with congenital heart disease (CHD). The referral diagnosis, radiation exposure and image quality of functional cardiac computed tomography (CT) in a relatively large cohort of patients of CHD has not been reported. This is a retrospective evaluation of functional CT studies performed in CHD patients from three institutions (1/2007–3/2013). Patient and scanner characteristics, radiation dose estimates and image quality were compared. Two hundred ninety-eight functional CT studies were evaluated. The most common referral diagnosis were tetralogy of Fallot (33 %), transposition complexes(24 %) single ventricle heart disease (15 %), and left sided obstruction (15 %). The reason for cardiac CT was presence of pacemaker (60 %), need for detailed coronary artery imaging (18 %), metallic artifact inC MR(12 %), evaluation of prosthetic valve function (4 %), and claustrophobia or BMI too large for the available MR scanner (6 %). 266(89.3 %) scans allowed quantification of ventricular function,25 (8.4 %) scans allowed qualitative assessment of function, and 7 (2.3 %) of the scans were non-diagnostic for functional analysis. Median DLP was 399 mGy cm (186,614), and median effective dose was 5.5 mSv (2.6, 8.5).Radiation dose and image quality varied across institutions.Cardiac CT function imaging can be performed in patients with congenital heart disease when CMR is contraindicated or has poor image quality. Radiation dose and image quality varies across institutions.

Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach

As the right ventricle's (RV) role in cardiovascular diseases is being more widely recognized, interest in RV imaging, function and quantification is growing. However, there are currently few RV quantification methods for 3D echocardiography presented in the literature or commercially available. In this paper we propose an automated RV segmentation method for 3D echocardiographic images. We represent the RV geometry by a Doo-Sabin subdivision surface with deformation modes derived from a training set of manual segmentations. The segmentation is then represented as a state estimation problem and solved with an extended Kalman filter by combining the RV geometry with a motion model and edge detection. Validation was performed by comparing surface-surface distances, volumes and ejection fractions in 17 patients with aortic insufficiency between the proposed method, magnetic resonance imaging (MRI), and a manual echocardiographic reference. The algorithm was efficient with a mean computation time of 2.0 s. The mean absolute distances between the proposed and manual segmentations were 3.6 ± 0.7 mm. Good agreements of end diastolic volume, end systolic volume and ejection fraction with respect to MRI ( -26±24 mL , -16±26 mL and 0 ± 10%, respectively) and a manual echocardiographic reference (7 ± 30 mL, 13 ± 17 mL and -5±7% , respectively) were observed.

Knowledge-based 3D reconstruction of the right ventricle: comparison with cardiac magnetic resonance in adults with congenital heart disease

Aim

Assessment of right ventricular (RV) function is a challenge, especially in patients with congenital heart disease (CHD). The aim of the present study is to assess whether knowledge-based RV reconstruction, used in the everyday practice of an echo-lab for adult CHD in a tertiary referral center, is accurate when compared to cardiac magnetic resonance (CMR) examination.

Subjects and methods

Adult patients who would undergo CMR for assessment of the RV were asked to undergo an echo of the heart for further knowledge-based reconstruction (KBR). Echocardiographic images were acquired in standard views using a predefined imaging protocol. RV volumes and ejection fraction (EF) calculated using knowledge-based technology were compared with the CMR data of the same patient.

Results

Nineteen consecutive patients with congenital right heart disease were studied. Median age of the patients was 28 years (range 46 years). Reconstruction was possible in 16 out of 19 patients (85%). RV volumes assessed with this new method were smaller than with CMR. Indexed end diastolic volumes were 114±17 ml vs 121±19 ml, P<0.05 and EFs were 45±8% vs 47±9%, P<0.05 respectively. The correlation between the methods was good with an intraclass correlation of 0.84 for EDV and 0.89 for EF, P value <0.001 in both cases.

Conclusion

KBR enables reliable measurement of RVs in patients with CHDs and can be used in clinical practice for analysis of volumes and EFs.

Multi-institutional evaluation of the indications and radiation dose of functional cardiovascular computed tomography (CCT) imaging in congenital heart disease

Ventricular volumes and ejection fraction are often used in clinical decision making in patients with congenital heart disease (CHD). The referral diagnosis, radiation exposure and image quality of functional cardiac computed tomography (CT) in a relatively large cohort of patients of CHD has not been reported. This is a retrospective evaluation of functional CT studies performed in CHD patients from three institutions (1/2007-3/2013). Patient and scanner characteristics, radiation dose estimates and image quality were compared. Two hundred ninety-eight functional CT studies were evaluated. The most common referral diagnosis were tetralogy of Fallot (33 %), transposition complexes (24 %) single ventricle heart disease (15 %), and left sided obstruction (15 %). The reason for cardiac CT was presence of pacemaker (60 %), need for detailed coronary artery imaging (18 %), metallic artifact in CMR (12 %), evaluation of prosthetic valve function (4 %), and claustrophobia or BMI too large for the available MR scanner (6 %). 266 (89.3 %) scans allowed quantification of ventricular function, 25 (8.4 %) scans allowed qualitative assessment of function, and 7 (2.3 %) of the scans were non-diagnostic for functional analysis. Median DLP was 399 mGy cm (186, 614), and median effective dose was 5.5 mSv (2.6, 8.5). Radiation dose and image quality varied across institutions. Cardiac CT function imaging can be performed in patients with congenital heart disease when CMR is contraindicated or has poor image quality. Radiation dose and image quality varies across institutions.

Advanced functional echocardiographic imaging of the failing heart in children

Over the past decade, new echocardiographic techniques such as three-dimensional echocardiography and the imaging of myocardial deformation (strain) have been developed, and are increasingly used in clinical practice. In this article, we describe the rationale and methodology, review available guidelines for practice, and discuss the advantages and limitations of each of these modalities. When available, we have also summarised the scientific evidence for the clinical application of these techniques to detect heart failure in children.

Echocardiographic assessment of ventricular function in pediatric patients: a comprehensive guide

Assessment of ventricular function is an important part of every echocardiographic examination. Specific pediatric guidelines on quantification of ventricular function are available, but technology evolves quickly and it generally takes long before newer techniques are integrated into routine clinical practice and are adopted by the guidelines. In the current overview, we would like to present our experience with integrating newer echocardiographic techniques for assessing ventricular function in children using a comprehensive state-of-the-art echocardiographic functional protocol. This protocol is used for specific patient populations such as pediatric patients with cardiomyopathy, post-transplant patients and oncology patients. We present the practical aspects of the protocols, their rationale and how this can be applied in clinical practice.

Right ventricular volumes assessed by echocardiographic three-dimensional knowledge-based reconstruction compared with magnetic resonance imaging in a clinical setting

OBJECTIVES

A technique that uses two-dimensional images to create a knowledge-based, three-dimensional model was tested and compared to magnetic resonance imaging.

BACKGROUND

Measurement of right ventricular volumes and function is important in the follow-up of patients after pulmonary valve replacement. Magnetic resonance imaging is the gold standard for volumetric assessment. Echocardiographic methods have been validated and are attractive alternatives.

METHODS

Thirty patients with tetralogy of Fallot (25 ± 14 years) after pulmonary valve replacement were examined. Magnetic resonance imaging volumetric measurements and echocardiography-based three-dimensional reconstruction were performed. End-diastolic volume, end-systolic volume, and ejection fraction were measured, and the results were compared.

RESULTS

Magnetic resonance imaging measurements gave coefficient of variation in the intraobserver study of 3.5, 4.6, and 5.3 and in the interobserver study of 3.6, 5.9, and 6.7 for end-diastolic volume, end-systolic volume, and ejection fraction, respectively. Echocardiographic three-dimensional reconstruction was highly feasible (97%). In the intraobserver study, the corresponding values were 6.0, 7.0, and 8.9 and in the interobserver study 7.4, 10.8, and 13.4. In comparison of the methods, correlations with magnetic resonance imaging were r = 0.91, 0.91, and 0.38, and the corresponding coefficient of variations were 9.4, 10.8, and 14.7. Echocardiography derived volumes (mL/m(2)) were significantly higher than magnetic resonance imaging volumes in end-diastolic volume 13.7 ± 25.6 and in end-systolic volume 9.1 ± 17.0 (both P < .05).

CONCLUSIONS

The knowledge-based three-dimensional right ventricular volume method was highly feasible. Intra and interobserver variabilities were satisfactory. Agreement with magnetic resonance imaging measurements for volumes was reasonable but unsatisfactory for ejection fraction. Knowledge-based reconstruction may replace magnetic resonance imaging measurements for serial follow-up, whereas magnetic resonance imaging should be used for surgical decision making.

Accuracy and Test-Retest Reproducibility of Two-Dimensional Knowledge-Based Volumetric Reconstruction of the Right Ventricle in Pulmonary Hypertension

Background

Right heart function is the key determinant of symptoms and prognosis in pulmonary hypertension (PH), but the right ventricle has a complex geometry that is challenging to quantify by two-dimensional (2D) echocardiography. A novel 2D echocardiographic technique for right ventricular (RV) quantitation involves knowledge-based reconstruction (KBR), a hybrid of 2D echocardiography–acquired coordinates localized in three-dimensional space and connected by reference to a disease-specific RV shape library. The aim of this study was to determine the accuracy of 2D KBR against cardiac magnetic resonance imaging in PH and the test-retest reproducibility of both conventional 2D echocardiographic RV fractional area change (FAC) and 2D KBR.

Methods

Twenty-eight patients with PH underwent same-day echocardiography and cardiac magnetic resonance imaging. Two operators performed serial RV FAC and 2D KBR acquisition and postprocessing to assess inter- and intraobserver test-retest reproducibility.

Results

Bland-Altman analysis (mean bias ± 95% limits of agreement) showed good agreement for end-diastolic volume (3.5 ± 25.0 mL), end-systolic volume (0.9 ± 19.9 mL), stroke volume (2.6 ± 23.1 mL), and ejection fraction (0.4 ± 10.2%) measured by 2D KBR and cardiac magnetic resonance imaging. There were no significant interobserver or intraobserver test-retest differences for 2D KBR RV metrics, with acceptable limits of agreement (interobserver end-diastolic volume, −0.9 ± 21.8 mL; end-systolic volume, −1.3 ± 25.8 mL; stroke volume, −0.2 ± 24.2 mL; ejection fraction, 0.7 ± 14.4%). Significant test-retest variability was observed for 2D echocardiographic RV areas and FAC.

Conclusions

Two-dimensional KBR is an accurate, novel technique for RV volumetric quantification in PH, with superior test-retest reproducibility compared with conventional 2D echocardiographic RV FAC.

Assessment of right ventricular volumes and ejection fraction by echocardiography: from geometric approximations to realistic shapes

Right ventricular volumes and ejection fraction are challenging to assess by echocardiography, but are well established as functional and prognostic parameters. Three-dimensional (3D) echocardiography has become widespread and relatively easy to use, making calculation of these parameters feasible in the large majority of patients. We review past attempts to estimate right ventricular volumes, current strengths and weaknesses of 3D echocardiography for this task, and compare with corresponding data from magnetic resonance imaging.

Evaluation of knowledge-based reconstruction for magnetic resonance volumetry of the right ventricle in tetralogy of Fallot

BACKGROUND

Cardiac magnetic resonance using the Simpson method is the gold standard for right ventricular volumetry. However, this method is time-consuming and not without sources of error. Knowledge-based reconstruction is a novel post-processing approach that reconstructs the right ventricular endocardial shape based on anatomical landmarks and a database of various right ventricular configurations.

OBJECTIVE

To assess the feasibility, accuracy and labor intensity of knowledge-based reconstruction in repaired tetralogy of Fallot (TOF).

MATERIALS AND METHODS

The short-axis cine cardiac MR datasets of 35 children and young adults (mean age 14.4 ± 2.5 years) after TOF repair were studied using both knowledge-based reconstruction and the Simpson method. Intraobserver, interobserver and inter-method variability were assessed using Bland-Altman analyses.

RESULTS

Knowledge-based reconstruction was feasible and highly accurate as compared to the Simpson method. Intra- and inter-method variability for knowledge-based reconstruction measurements showed good agreement. Volumetric assessment using knowledge-based reconstruction was faster when compared with the Simpson method (10.9 ± 2.0 vs. 7.1 ± 2.4 min, P < 0.001).

CONCLUSION

In patients with repaired tetralogy of Fallot, knowledge-based reconstruction is a feasible, accurate and reproducible method for measuring right ventricular volumes and ejection fraction. The post-processing time of right ventricular volumetry using knowledge-based reconstruction was significantly shorter when compared with the routine Simpson method.

Quantitative magnetic resonance imaging of pulmonary hypertension: a practical approach to the current state of the art

Pulmonary hypertension is a condition of varied etiology, commonly associated with poor clinical outcome. Patients are categorized on the basis of pathophysiological, clinical, radiologic, and therapeutic similarities. Pulmonary arterial hypertension (PAH) is often diagnosed late in its disease course, with outcome dependent on etiology, disease severity, and response to treatment. Recent advances in quantitative magnetic resonance imaging (MRI) allow for better initial characterization and measurement of the morphologic and flow-related changes that accompany the response of the heart-lung axis to prolonged elevation of pulmonary arterial pressure and resistance and provide a reproducible, comprehensive, and noninvasive means of assessing the course of the disease and response to treatment. Typical features of PAH occur primarily as a result of increased pulmonary vascular resistance and the resultant increased right ventricular (RV) afterload. Several MRI-derived diagnostic markers have emerged, such as ventricular mass index, interventricular septal configuration, and average pulmonary artery velocity, with diagnostic accuracy similar to that of Doppler echocardiography. Furthermore, prognostic markers have been identified with independent predictive value for identification of treatment failure. Such markers include large RV end-diastolic volume index, low left ventricular end-diastolic volume index, low RV ejection fraction, and relative area change of the pulmonary trunk. MRI is ideally suited for longitudinal follow-up of patients with PAH because of its noninvasive nature and high reproducibility and is advantageous over other biomarkers in the study of PAH because of its sensitivity to change in morphologic, functional, and flow-related parameters. Further study on the role of MRI image based biomarkers in the clinical environment is warranted.