Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning

Bayesian Optimization-Based Inverse Finite Element Analysis for Atrioventricular Heart Valves

Inverse finite element analysis (iFEA) of the atrioventricular heart valves (AHVs) can provide insights into the in-vivo valvular function, such as in-vivo tissue strains; however, there are several limitations in the current state-of-the-art that iFEA has not been widely employed to predict the in-vivo, patient-specific AHV leaflet mechanical responses. In this exploratory study, we propose the use of Bayesian optimization (BO) to study the AHV functional behaviors in-vivo. We analyzed the efficacy of Bayesian optimization to estimate the isotropic Lee-Sacks material coefficients in three benchmark problems: (i) an inflation test, (ii) a simplified leaflet contact model, and (iii) an idealized AHV model. Then, we applied the developed BO-iFEA framework to predict the leaflet properties for a patient-specific tricuspid valve under a congenital heart defect condition. We found that the BO could accurately construct the objective function surface compared to the one from a [Formula: see text] grid search analysis. Additionally, in all cases the proposed BO-iFEA framework yielded material parameter predictions with average element errors less than 0.02 mm/mm (normalized by the simulation-specific characteristic length). Nonetheless, the solutions were not unique due to the presence of a long-valley minima region in the objective function surfaces. Parameter sets along this valley can yield functionally equivalent outcomes (i.e., closing behavior) and are typically observed in the inverse analysis or parameter estimation for the nonlinear mechanical responses of the AHV. In this study, our key contributions include: (i) a first-of-its-kind demonstration of the BO method used for the AHV iFEA; and (ii) the evaluation of a candidate AHV in-silico modeling approach wherein the chordae could be substituted with equivalent displacement boundary conditions, rendering the better iFEA convergence and a smoother objective surface.

Imaging and guiding intervention for tricuspid valve disorders using 3-dimensional transesophageal echocardiography in pediatric and congenital heart disease

In the pediatric and congenital heart disease (CHD) population, tricuspid valve (TV) disorders are complex due to the variable TV morphology, its sophisticated interaction with the right ventricle as well as associated congenital and acquired lesions. While surgery is the standard of care for TV dysfunction in this patient population, transcatheter treatment for bioprosthetic TV dysfunction has been performed successfully. Detailed and accurate anatomic assessment of the abnormal TV is essential in the preoperative/preprocedural planning. Three-dimensional transthoracic and 3D transesophageal echocardiography (3DTEE) provides added value to 2-dimensional imaging in the characterization of the TV to guide therapy and 3DTEE serves as an excellent tool for intraoperative assessment and procedural guidance of transcatheter treatment. Notwithstanding advances in imaging and therapy, the timing and indication for intervention for TV disorders in this population are not well defined. In this manuscript, we aim to review the available literature, provide our institutional experience with 3DTEE, and briefly discuss the perceived challenges and future directions in the assessment, surgical planning, and procedural guidance of (1) congenital TV malformations, (2) acquired TV dysfunction from transvenous pacing leads, or following cardiac surgeries, and (3) bioprosthetic TV dysfunction.

A deep learning-based method for pediatric congenital heart disease detection with seven standard views in echocardiography

Background

With the aggregation of clinical data and the evolution of computational resources, artificial intelligence-based methods have become possible to facilitate clinical diagnosis. For congenital heart disease (CHD) detection, recent deep learning-based methods tend to achieve classification with few views or even a single view. Due to the complexity of CHD, the input images for the deep learning model should cover as many anatomical structures of the heart as possible to enhance the accuracy and robustness of the algorithm. In this paper, we first propose a deep learning method based on seven views for CHD classification and then validate it with clinical data, the results of which show the competitiveness of our approach.

Methods

A total of 1411 children admitted to the Children's Hospital of Zhejiang University School of Medicine were selected, and their echocardiographic videos were obtained. Then, seven standard views were selected from each video, which were used as the input to the deep learning model to obtain the final result after training, validation and testing.

Results

In the test set, when a reasonable type of image was input, the area under the curve (AUC) value could reach 0.91, and the accuracy could reach 92.3%. During the experiment, shear transformation was used as interference to test the infection resistance of our method. As long as appropriate data were input, the above experimental results would not fluctuate obviously even if artificial interference was applied.

Conclusions

These results indicate that the deep learning model based on the seven standard echocardiographic views can effectively detect CHD in children, and this approach has considerable value in practical application.

Video-Based Deep Learning for Automated Assessment of Left Ventricular Ejection Fraction in Pediatric Patients

BACKGROUND

Significant interobserver and interstudy variability occurs for left ventricular (LV) functional indices despite standardization of measurement techniques. Artificial intelligence models trained on adult echocardiograms are not likely to be applicable to a pediatric population. We present EchoNet-Peds, a video-based deep learning algorithm, which matches human expert performance of LV segmentation and ejection fraction (EF).

METHODS

A large pediatric data set of 4,467 echocardiograms was used to develop EchoNet-Peds. EchoNet-Peds was trained on 80% of the data for segmentation of the left ventricle and estimation of LVEF. The remaining 20% was used to fine-tune and validate the algorithm.

RESULTS

In both apical 4-chamber and parasternal short-axis views, EchoNet-Peds segments the left ventricle with a Dice similarity coefficient of 0.89. EchoNet-Peds estimates EF with a mean absolute error of 3.66% and can routinely identify pediatric patients with systolic dysfunction (area under the curve of 0.95). EchoNet-Peds was trained on pediatric echocardiograms and performed significantly better to estimate EF (P < .001) than an adult model applied to the same data.

CONCLUSIONS

Accurate, rapid automation of EF assessment and recognition of systolic dysfunction in a pediatric population are feasible using EchoNet-Peds with the potential for far-reaching clinical impact. In addition, the first large pediatric data set of annotated echocardiograms is now publicly available for efforts to develop pediatric-specific artificial intelligence algorithms.

Tricuspid Valve Regurgitation in Hypoplastic Left Heart Syndrome: Current Insights and Future Perspectives

Hypoplastic Left Heart Syndrome (HLHS) is a congenital heart defect that requires a three-stage surgical palliation to create a single ventricle system in the right side of the heart. Of patients undergoing this cardiac palliation series, 25% will develop tricuspid regurgitation (TR), which is associated with an increased mortality risk. Valvular regurgitation in this population has been extensively studied to understand indicators and mechanisms of comorbidity. In this article, we review the current state of research on TR in HLHS, including identified valvular anomalies and geometric properties as the main reasons for the poor prognosis. After this review, we present some suggestions for future TR-related studies to answer the central question: What are the predictors of TR onset during the three palliation stages? These studies involve (i) the use of engineering-based metrics to evaluate valve leaflet strains and predict tissue material properties, (ii) perform multivariate analyses to identify TR predictors, and (iii) develop predictive models, particularly using longitudinally tracked patient cohorts to foretell patient-specific trajectories. Regarded together, these ongoing and future efforts will result in the development of innovative tools that can aid in surgical timing decisions, in prophylactic surgical valve repair, and in the refinement of current intervention techniques.

Modeling of the Tricuspid Valve and Right Ventricle in Hypoplastic Left Heart Syndrome With a Fontan Circulation

BACKGROUND

In hypoplastic left heart syndrome, tricuspid regurgitation (TR) is associated with circulatory failure and death. We hypothesized that the tricuspid valve (TV) structure of patients with hypoplastic left heart syndrome with a Fontan circulation and moderate or greater TR differs from those with mild or less TR, and that right ventricle volume is associated with TV structure and dysfunction.

METHODS

TV of 100 patients with hypoplastic left heart syndrome and a Fontan circulation were modeled using transthoracic 3-dimensional echocardiograms and custom software in SlicerHeart. Associations of TV structure to TR grade and right ventricle function and volume were investigated. Shape parameterization and analysis was used to calculate the mean shape of the TV leaflets, their principal modes of variation, and to characterize associations of TV leaflet shape to TR.

RESULTS

In univariate modeling, patients with moderate or greater TR had larger TV annular diameters and area, greater annular distance between the anteroseptal commissure and anteroposterior commissure, greater leaflet billow volume, and more laterally directed anterior papillary muscle angles compared to valves with mild or less TR (all P<0.001). In multivariate modeling greater total billow volume, lower anterior papillary muscle angle, and greater distance between the anteroposterior commissure and anteroseptal commissure were associated with moderate or greater TR (P<0.001, C statistic=0.85). Larger right ventricle volumes were associated with moderate or greater TR (P<0.001). TV shape analysis revealed structural features associated with TR, but also highly heterogeneous TV leaflet structure.

CONCLUSIONS

Moderate or greater TR in patients with hypoplastic left heart syndrome with a Fontan circulation is associated with greater leaflet billow volume, a more laterally directed anterior papillary muscle angle, and greater annular distance between the anteroseptal commissure and anteroposterior commissure. However, there is significant heterogeneity of structure in the TV leaflets in regurgitant valves. Given this variability, an image-informed patient-specific approach to surgical planning may be needed to achieve optimal outcomes in this vulnerable and challenging population.

The tricuspid valve in hypoplastic left heart syndrome: Echocardiography provides insight into anatomy and function

Tricuspid regurgitation (TR) is commonly seen in surgically palliated patients with hypoplastic left heart syndrome, and when significant, is associated with an increase in both morbidity and mortality. Tricuspid valve dysfunction appears to be the result of a combination of inherent structural malformations and the unique physiological circumstances resulting from right ventricular pressure and volume overload. Valve dysfunction evolves rapidly, and manifests early on in the surgical pathway. Whilst traditional echocardiographic imaging can identify anatomical defects and dysfunction resulting in varying degrees of regurgitation even at early stages, more sophisticated investigations such as 3D echocardiography, strain imaging and transesophageal 3DE might prove useful to better demonstrate the complex interactions between abnormal anatomy of the valve complex, ventricular function, mechanical synchrony, and TR. Recognition of specific mechanisms of TR can enhance patient-specific care by directing precise surgical interventions and by informing the best timing for intervention on the valve.

SlicerHeart: An open-source computing platform for cardiac image analysis and modeling

Cardiovascular disease is a significant cause of morbidity and mortality in the developed world. 3D imaging of the heart's structure is critical to the understanding and treatment of cardiovascular disease. However, open-source tools for image analysis of cardiac images, particularly 3D echocardiographic (3DE) data, are limited. We describe the rationale, development, implementation, and application of SlicerHeart, a cardiac-focused toolkit for image analysis built upon 3D Slicer, an open-source image computing platform. We designed and implemented multiple Python scripted modules within 3D Slicer to import, register, and view 3DE data, including new code to volume render and crop 3DE. In addition, we developed dedicated workflows for the modeling and quantitative analysis of multi-modality image-derived heart models, including heart valves. Finally, we created and integrated new functionality to facilitate the planning of cardiac interventions and surgery. We demonstrate application of SlicerHeart to a diverse range of cardiovascular modeling and simulation including volume rendering of 3DE images, mitral valve modeling, transcatheter device modeling, and planning of complex surgical intervention such as cardiac baffle creation. SlicerHeart is an evolving open-source image processing platform based on 3D Slicer initiated to support the investigation and treatment of congenital heart disease. The technology in SlicerHeart provides a robust foundation for 3D image-based investigation in cardiovascular medicine.

Visualization and Quantification of the Unrepaired Complete Atrioventricular Canal Valve Using Open-Source Software

BACKGROUND

Repair of complete atrioventricular canal (CAVC) is often complicated by residual left atrioventricular valve regurgitation. The structure of the mitral and tricuspid valves in biventricular hearts has previously been shown to be associated with valve dysfunction. However, the three-dimensional (3D) structure of the entire unrepaired CAVC valve has not been quantified. Understanding the 3D structure of the CAVC may inform optimized repair.

METHODS

Novel open-source work flows were created in SlicerHeart for the modeling and quantification of CAVC valves on the basis of 3D echocardiographic images. These methods were applied to model the annulus, leaflets, and papillary muscle (PM) structure of 35 patients (29 with trisomy 21) with CAVC using transthoracic 3D echocardiography. The mean leaflet and annular shapes were calculated and visualized using shape analysis. Metrics of the complete native CAVC valve structure were compared with those of normal mitral valves using the Mann-Whitney U test. Associations between CAVC structure and atrioventricular valve regurgitation were analyzed.

RESULTS

CAVC leaflet metrics varied throughout systole. Compared with normal mitral valves, the left CAVC PMs were more acutely angled in relation to the annular plane (P < .001). In addition, the anterolateral PM was laterally and inferiorly rotated in CAVC, while the posteromedial PM was more superiorly and laterally rotated, relative to normal mitral valves (P < .001). Lower native CAVC atrioventricular valve annular height and annular height-to-valve width ratio before repair were both associated with moderate or greater left atrioventricular valve regurgitation after repair (P < .01).

CONCLUSIONS

It is feasible to model and quantify 3D CAVC structure using 3D echocardiographic images. The results demonstrate significant variation in CAVC structure across the cohort and differences in annular, leaflet, and PM structure compared with the mitral valve. These tools may be used in future studies to catalyze future research intended to identify structural associations of valve dysfunction and to optimize repair in this vulnerable and complex population.

A pilot investigation of the tricuspid valve annulus in newborns with hypoplastic left heart syndrome

Objective

Hypoplastic left heart syndrome (HLHS) is a congenital disease characterized by an underdevelopment of the anatomical components inside the left heart. Approximately 30% of newborns with HLHS will develop tricuspid regurgitation, and it is currently unknown how the valve annulus mechanics and geometry are associated with regurgitation. Thus, we present an engineering mechanics-based analysis approach to quantify the mechanics and geometry of the HLHS-afflicted tricuspid valve (TV), using 4-dimensional echocardiograms.

Methods

Infants born with HLHS (n = 8) and healthy newborns (n = 4) had their TVs imaged, and the data were imported to 3D Slicer. The annular curves were defined at 5 points in the cardiac cycle. The geometry and deformation (strain) of the TV annulus were calculated to elucidate the mechanics of this critical structure and to compare them between neonates with and without HLHS.

Results

For the annular geometry, HLHS-afflicted newborns had significantly larger annular circumferences (20%-30%) and anteroposterior diameters (35%-45%) than the healthy patients. From a biomechanics' perspective, the HLHS patients had significantly smaller strains in the anterior segments (–0.1 ± 2.6%) during end-diastolic and end-isovolumetric relaxation (1.7 ± 3.0%) compared with the healthy counterparts (–13.3 ± 2.9% and 6.8 ± 0.9%, respectively).

Conclusions

The image-based analysis presented in this study may provide novel insights into the geometric and mechanistic differences in the TV annulus between the healthy and HLHS newborns. Future longitudinal studies of the biomechanics of TV annulus and other subvalvular structures may inform our understanding of the initiation and development of tricuspid regurgitation and the design of optimal repairs in this challenging population.

Skeletal model-based analysis of the tricuspid valve in hypoplastic left heart syndrome

Hypoplastic left heart syndrome (HLHS) is a congenital heart disease characterized by incomplete development of the left heart. Children with HLHS undergo a series of operations which result in the tricuspid valve (TV) becoming the only functional atrioventricular valve. Many HLHS patients develop tricuspid regurgitation and right ventricle enlargement which is associated with heart failure and death without surgical intervention on the valve. Understanding the connections between the geometry of the TV and its function remains extremely challenging and hinders TV repair planning. Traditional analysis methods rely on simple anatomical measures which do not capture information about valve geometry in detail. Recently, surface-based shape representations such as SPHARM-PDM have been shown to be useful for tasks such as discriminating between valves with normal or poor function. In this work we propose to use skeletal representations (s-reps), a more feature-rich geometric representation, for modeling the leaflets of the tricuspid valve. We propose an extension to previous s-rep fitting approaches to incorporate application-specific anatomical landmarks and population information to improve correspondence. We use several traditional statistical shape analysis techniques to evaluate the efficiency of this representation: using principal component analysis (PCA) we observe that it takes fewer modes of variation compared to boundary-based approaches to represent 90% of the population variation, while distance-weighted discrimination (DWD) shows that s-reps provide for more significant classification between valves with less regurgitation and those with more. These results show the power of using s-reps for modeling the relationship between structure and function of the tricuspid valve.