Statistical shape modeling of the left ventricle: myocardial infarct classification challenge

SDF4CHD: Generative modeling of cardiac anatomies with congenital heart defects

Congenital heart disease (CHD) encompasses a spectrum of cardiovascular structural abnormalities, often requiring customized treatment plans for individual patients. Computational modeling and analysis of these unique cardiac anatomies can improve diagnosis and treatment planning and may ultimately lead to improved outcomes. Deep learning (DL) methods have demonstrated the potential to enable efficient treatment planning by automating cardiac segmentation and mesh construction for patients with normal cardiac anatomies. However, CHDs are often rare, making it challenging to acquire sufficiently large patient cohorts for training such DL models. Generative modeling of cardiac anatomies has the potential to fill this gap via the generation of virtual cohorts; however, prior approaches were largely designed for normal anatomies and cannot readily capture the significant topological variations seen in CHD patients. Therefore, we propose a type- and shape-disentangled generative approach suitable to capture the wide spectrum of cardiac anatomies observed in different CHD types and synthesize differently shaped cardiac anatomies that preserve the unique topology for specific CHD types. Our DL approach represents generic whole heart anatomies with CHD type-specific abnormalities implicitly using signed distance fields (SDF) based on CHD type diagnosis. To capture the shape-specific variations, we then learn invertible deformations to morph the learned CHD type-specific anatomies and reconstruct patient-specific shapes. After training with a dataset containing the cardiac anatomies of 67 patients spanning 6 CHD types and 14 combinations of CHD types, our method successfully captures divergent anatomical variations across different types and the meaningful intermediate CHD states across the spectrum of related CHD diagnoses. Additionally, our method demonstrates superior performance in CHD anatomy generation in terms of CHD-type correctness and shape plausibility. It also exhibits comparable generalization performance when reconstructing unseen cardiac anatomies. Moreover, our approach shows potential in augmenting image-segmentation pairs for rarer CHD types to significantly enhance cardiac segmentation accuracy for CHDs. Furthermore, it enables the generation of CHD cardiac meshes for computational simulation, facilitating a systematic examination of the impact of CHDs on cardiac functions.

Modeling 3D Cardiac Contraction and Relaxation With Point Cloud Deformation Networks

Global single-valued biomarkers, such as ejection fraction, are widely used in clinical practice to assess cardiac function. However, they only approximate the heart's true 3D deformation process, thus limiting diagnostic accuracy and the understanding of cardiac mechanics. Metrics based on 3D shape have been proposed to alleviate these shortcomings. In this work, we present the Point Cloud Deformation Network (PCD-Net) as a novel geometric deep learning approach for direct modeling of 3D cardiac mechanics of the biventricular anatomy between the extreme ends of the cardiac cycle. Its encoder-decoder architecture combines a low-dimensional latent space with recent advances in point cloud deep learning for effective multi-scale feature learning directly on flexible and memory-efficient point cloud representations of the cardiac anatomy. We first evaluate the PCD-Net's predictive capability for both cardiac contraction and relaxation on a large UK Biobank dataset of over 10,000 subjects and find average Chamfer distances between the predicted and ground truth anatomies below the pixel resolution of the underlying image acquisition. We then show the PCD-Net's ability to capture subpopulation-specific differences in 3D cardiac mechanics between normal and myocardial infarction (MI) subjects and visualize abnormal phenotypes between predicted normal 3D shapes and corresponding observed ones. Finally, we demonstrate that the PCD-Net's learned 3D deformation encodings outperform multiple clinical and machine learning benchmarks by 11% in terms of area under the receiver operating characteristic curve for the tasks of prevalent MI detection and incident MI prediction and by 7% in terms of Harrell's concordance index for MI survival analysis.

Automated segmentation of the left-ventricle from MRI with a fully convolutional network to investigate CTRCD in breast cancer patients

Purpose: The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). Approach: A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha (C - α ) intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. Results: Myocardial classification results against ground-truth were Dice = 0.89 , APD = 2.4    mm , and accuracy = 97 % for the validation set and Dice = 0.90 , APD = 2.5    mm , and accuracy = 97 % for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were CI = - 1.36 % to 2.42%, p-value < 0.001 for LVEF (58 ± 5 % versus 57 ± 6 % ), and CI = - 0.71 % to 0.63%, p-value < 0.001 for longitudinal strain (- 15 ± 2 % versus - 15 ± 3 % ). Conclusions: The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.

SDF4CHD: Generative Modeling of Cardiac Anatomies with Congenital Heart Defects

Congenital heart disease (CHD) encompasses a spectrum of cardiovascular structural abnormalities, often requiring customized treatment plans for individual patients. Computational modeling and analysis of these unique cardiac anatomies can improve diagnosis and treatment planning and may ultimately lead to improved outcomes. Deep learning (DL) methods have demonstrated the potential to enable efficient treatment planning by automating cardiac segmentation and mesh construction for patients with normal cardiac anatomies. However, CHDs are often rare, making it challenging to acquire sufficiently large patient cohorts for training such DL models. Generative modeling of cardiac anatomies has the potential to fill this gap via the generation of virtual cohorts; however, prior approaches were largely designed for normal anatomies and cannot readily capture the significant topological variations seen in CHD patients. Therefore, we propose a type- and shape-disentangled generative approach suitable to capture the wide spectrum of cardiac anatomies observed in different CHD types and synthesize differently shaped cardiac anatomies that preserve the unique topology for specific CHD types. Our DL approach represents generic whole heart anatomies with CHD type-specific abnormalities implicitly using signed distance fields (SDF) based on CHD type diagnosis, which conveniently captures divergent anatomical variations across different types and represents meaningful intermediate CHD states. To capture the shape-specific variations, we then learn invertible deformations to morph the learned CHD type-specific anatomies and reconstruct patient-specific shapes. Our approach has the potential to augment the image-segmentation pairs for rarer CHD types for cardiac segmentation and generate cohorts of CHD cardiac meshes for computational simulation.

Computational analysis of thrombosis risk with variations in left ventricular assist device inflow cannula design in a multi-patient model

BACKGROUND AND OBJECTIVES

Left ventricular assist devices (LVADs) are mechanical pumps used to support patients with end-stage heart failure. The inflow cannula is a critical component of the LVAD as it connects the pump to the left ventricle, allowing blood to be drawn from the heart. However, the design of the cannula can significantly impact LV hemodynamics and cause complications, including thrombosis. Therefore, this study aimed to analyze the numerical effects of left ventricle (LV) size on cannula design in order to enhance hemodynamic performance using post-operative left ventricular assist device (LVAD) models.

METHODS

A parametric design evaluation of two different inflow cannulas were carried out on left ventricles (LV) of varying sizes (ranging from 154 to 430 ml) constructed from computerized tomography (CT) data from VAD patients using computational fluid dynamics (CFD) simulations. The study analyzed three key factors contributing to thrombosis formation: blood residence time, blood stagnation ratio, and wall shear stress.

RESULTS

Results showed higher blood residence time and stagnation ratio for larger left ventricular sizes. In addition, increasing the insertion length of the cannula reduced the average wall shear stress.

CONCLUSION

Overall, the study's findings suggest that the optimal cannula shape for LVADs varies with left ventricular size.

Reconstruction and completion of high-resolution 3D cardiac shapes using anisotropic CMRI segmentations and continuous implicit neural representations

Since the onset of computer-aided diagnosis in medical imaging, voxel-based segmentation has emerged as the primary methodology for automatic analysis of left ventricle (LV) function and morphology in cardiac magnetic resonance images (CMRI). In standard clinical practice, simultaneous multi-slice 2D cine short-axis MR imaging is performed under multiple breath-holds resulting in highly anisotropic 3D images. Furthermore, sparse-view CMRI often lacks whole heart coverage caused by large slice thickness and often suffers from inter-slice misalignment induced by respiratory motion. Therefore, these volumes only provide limited information about the true 3D cardiac anatomy which may hamper highly accurate assessment of functional and anatomical abnormalities. To address this, we propose a method that learns a continuous implicit function representing 3D LV shapes by training an auto-decoder. For training, high-resolution segmentations from cardiac CT angiography are used. The ability of our approach to reconstruct and complete high-resolution shapes from manually or automatically obtained sparse-view cardiac shape information is evaluated by using paired high- and low-resolution CMRI LV segmentations. The results show that the reconstructed LV shapes have an unconstrained subvoxel resolution and appear smooth and plausible in through-plane direction. Furthermore, Bland-Altman analysis reveals that reconstructed high-resolution ventricle volumes are closer to the corresponding reference volumes than reference low-resolution volumes with bias of [limits of agreement] -3.51 [-18.87, 11.85] mL, and 12.96 [-10.01, 35.92] mL respectively. Finally, the results demonstrate that the proposed approach allows recovering missing shape information and can indirectly correct for limited motion-induced artifacts.

Computer-aided shape features extraction and regression models for predicting the ascending aortic aneurysm growth rate

OBJECTIVE

ascending aortic aneurysm growth prediction is still challenging in clinics. In this study, we evaluate and compare the ability of local and global shape features to predict the ascending aortic aneurysm growth.

MATERIAL AND METHODS

70 patients with aneurysm, for which two 3D acquisitions were available, are included. Following segmentation, three local shape features are computed: (1) the ratio between maximum diameter and length of the ascending aorta centerline, (2) the ratio between the length of external and internal lines on the ascending aorta and (3) the tortuosity of the ascending tract. By exploiting longitudinal data, the aneurysm growth rate is derived. Using radial basis function mesh morphing, iso-topological surface meshes are created. Statistical shape analysis is performed through unsupervised principal component analysis (PCA) and supervised partial least squares (PLS). Two types of global shape features are identified: three PCA-derived and three PLS-based shape modes. Three regression models are set for growth prediction: two based on gaussian support vector machine using local and PCA-derived global shape features; the third is a PLS linear regression model based on the related global shape features. The prediction results are assessed and the aortic shapes most prone to growth are identified.

RESULTS

the prediction root mean square error from leave-one-out cross-validation is: 0.112 mm/month, 0.083 mm/month and 0.066 mm/month for local, PCA-based and PLS-derived shape features, respectively. Aneurysms close to the root with a large initial diameter report faster growth.

CONCLUSION

global shape features might provide an important contribution for predicting the aneurysm growth.

3D Shape-Based Myocardial Infarction Prediction Using Point Cloud Classification Networks

Myocardial infarction (MI) is one of the most prevalent cardiovascular diseases with associated clinical decision-making typically based on single-valued imaging biomarkers. However, such metrics only approximate the complex 3D structure and physiology of the heart and hence hinder a better understanding and prediction of MI outcomes. In this work, we investigate the utility of complete 3D cardiac shapes in the form of point clouds for an improved detection of MI events. To this end, we propose a fully automatic multi-step pipeline consisting of a 3D cardiac surface reconstruction step followed by a point cloud classification network. Our method utilizes recent advances in geometric deep learning on point clouds to enable direct and efficient multi-scale learning on high-resolution surface models of the cardiac anatomy. We evaluate our approach on 1068 UK Biobank subjects for the tasks of prevalent MI detection and incident MI prediction and find improvements of ∼13% and ∼5% respectively over clinical benchmarks. Furthermore, we analyze the role of each ventricle and cardiac phase for 3D shape-based MI detection and conduct a visual analysis of the morphological and physiological patterns typically associated with MI outcomes.Clinical relevance- The presented approach enables the fast and fully automatic pathology-specific analysis of full 3D cardiac shapes. It can thus be employed as a real-time diagnostic tool in clinical practice to discover and visualize more intricate biomarkers than currently used single-valued metrics and improve predictive accuracy of myocardial infarction.

MRXCAT2.0: Synthesis of realistic numerical phantoms by combining left-ventricular shape learning, biophysical simulations and tissue texture generation

BACKGROUND

Standardised performance assessment of image acquisition, reconstruction and processing methods is limited by the absence of images paired with ground truth reference values. To this end, we propose MRXCAT2.0 to generate synthetic data, covering healthy and pathological function, using a biophysical model. We exemplify the approach by generating cardiovascular magnetic resonance (CMR) images of healthy, infarcted, dilated and hypertrophic left-ventricular (LV) function.

METHOD

In MRXCAT2.0, the XCAT torso phantom is coupled with a statistical shape model, describing population (patho)physiological variability, and a biophysical model, providing known and detailed functional ground truth of LV morphology and function. CMR balanced steady-state free precession images are generated using MRXCAT2.0 while realistic image appearance is ensured by assigning texturized tissue properties to the phantom labels.

FINDING

Paired CMR image and ground truth data of LV function were generated with a range of LV masses (85-140 g), ejection fractions (34-51%) and peak radial and circumferential strains (0.45 to 0.95 and - 0.18 to - 0.13, respectively). These ranges cover healthy and pathological cases, including infarction, dilated and hypertrophic cardiomyopathy. The generation of the anatomy takes a few seconds and it improves on current state-of-the-art models where the pathological representation is not explicitly addressed. For the full simulation framework, the biophysical models require approximately two hours, while image generation requires a few minutes per slice.

CONCLUSION

MRXCAT2.0 offers synthesis of realistic images embedding population-based anatomical and functional variability and associated ground truth parameters to facilitate a standardized assessment of CMR acquisition, reconstruction and processing methods.

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.

Multi-Ethnic Study of Atherosclerosis: Relationship between Left Ventricular Shape at Cardiac MRI and 10-year Outcomes

Background Left ventricular (LV) subclinical remodeling is associated with adverse outcomes and indicates mechanisms of disease development. Standard metrics such as LV mass and volumes may not capture the full range of remodeling. Purpose To quantify the relationship between LV three-dimensional shape at MRI and incident cardiovascular events over 10 years. Materials and Methods In this retrospective study, 5098 participants from the Multi-Ethnic Study of Atherosclerosis who were free of clinical cardiovascular disease underwent cardiac MRI from 2000 to 2002. LV shape models were automatically generated using a machine learning workflow. Event-specific remodeling signatures were computed using partial least squares regression, and random survival forests were used to determine which features were most associated with incident heart failure (HF), coronary heart disease (CHD), and cardiovascular disease (CVD) events over a 10-year follow-up period. The discrimination improvement of adding LV shape to traditional cardiovascular risk factors, coronary artery calcium scores, and N-terminal pro-brain natriuretic peptide levels was assessed using the index of prediction accuracy and time-dependent area under the receiver operating characteristic curve (AUC). Kaplan-Meier survival curves were used to illustrate the ability of remodeling signatures to predict the end points. Results Overall, 4618 participants had sufficient three-dimensional MRI information to generate patient-specific LV models (mean age, 60.6 years ± 9.9 [SD]; 2540 women). Among these participants, 147 had HF, 317 had CHD, and 455 had CVD events. The addition of LV remodeling signatures to traditional cardiovascular risk factors improved the mean AUC for 10-year survival prediction and achieved better performance than LV mass and volumes; HF (AUC, 0.83 ± 0.01 and 0.81 ± 0.01, respectively; P < .05), CHD (AUC, 0.77 ± 0.01 and 0.75 ± 0.01, respectively; P < .05), and CVD (AUC, 0.78 ± 0.0 and 0.76 ± 0.0, respectively; P < .05). Kaplan-Meier analysis demonstrated that participants with high-risk HF remodeling signatures had a 10-year survival rate of 56% compared with 95% for those with low-risk scores. Conclusion Left ventricular event-specific remodeling signatures were more predictive of heart failure, coronary heart disease, and cardiovascular disease events over 10 years than standard mass and volume measures and enable an automatic personalized medicine approach to tracking remodeling. © RSNA, 2022 Online supplemental material is available for this article.

Interpretable cardiac anatomy modeling using variational mesh autoencoders

Cardiac anatomy and function vary considerably across the human population with important implications for clinical diagnosis and treatment planning. Consequently, many computer-based approaches have been developed to capture this variability for a wide range of applications, including explainable cardiac disease detection and prediction, dimensionality reduction, cardiac shape analysis, and the generation of virtual heart populations. In this work, we propose a variational mesh autoencoder (mesh VAE) as a novel geometric deep learning approach to model such population-wide variations in cardiac shapes. It embeds multi-scale graph convolutions and mesh pooling layers in a hierarchical VAE framework to enable direct processing of surface mesh representations of the cardiac anatomy in an efficient manner. The proposed mesh VAE achieves low reconstruction errors on a dataset of 3D cardiac meshes from over 1,000 patients with acute myocardial infarction, with mean surface distances between input and reconstructed meshes below the underlying image resolution. We also find that it outperforms a voxelgrid-based deep learning benchmark in terms of both mean surface distance and Hausdorff distance while requiring considerably less memory. Furthermore, we explore the quality and interpretability of the mesh VAE's latent space and showcase its ability to improve the prediction of major adverse cardiac events over a clinical benchmark. Finally, we investigate the method's ability to generate realistic virtual populations of cardiac anatomies and find good alignment between the synthesized and gold standard mesh populations in terms of multiple clinical metrics.

Analysing functional implications of differences in left ventricular morphology using statistical shape modelling

Functional implications of left ventricular (LV) morphological characterization in congenital heart disease are not widely explored. This study qualitatively and quantitatively assessed LV shape associations with a) LV function and b) thoracic aortic morphology in patients with aortic coarctation (CoA) with/without bicuspid aortic valve (BAV), and healthy controls. A statistical shape modelling framework was employed to analyse three-dimensional (3D) LV shapes from cardiac magnetic resonance (CMR) data in isolated CoA (n = 25), CoA + BAV (n = 30), isolated BAV (n = 30), and healthy controls (n = 25). Average 3D templates and deformations were computed. Correlations between shape data and CMR-derived morphometric parameters (i.e., sphericity, conicity) or global and apical strain values were assessed to elucidate possible functional implications. The relationship between LV shape features and arch architecture was also explored. The LV template was shorter and more spherical in CoA patients. Sphericity was overall associated with global and apical radial (p = 0.001, R² = 0.09; p < 0.0001, R² = 0.17) and circumferential strain (p = 0.001, R² = 0.10; p = 0.04, R² = 0.04), irrespective of the presence of aortic stenosis and/or regurgitation and controlling for age and hypertension status. LV strain was not associated with arch architecture. Differences in LV morphology were observed between CoA and BAV patients. Increasing LV sphericity was associated with reduced strain, independent of aortic arch architecture and functional aortic valve disease.

Regional left ventricle scar detection from routine cardiac computed tomography angiograms using latent space classification

OBJECTIVES

The aim of this study is to develop an automated method of regional scar detection on clinically standard computed tomography angiography (CTA) using encoder-decoder networks with latent space classification.

BACKGROUND

Localising scar in cardiac patients can assist in diagnosis and guide interventions. Magnetic resonance imaging (MRI) with late gadolinium enhancement (LGE) is the clinical gold standard for scar imaging; however, it is commonly contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is widely used as a first-line imaging modality of cardiac applications.

METHODS

A dataset of 79 patients with both clinically indicated MRI LGE and subsequent CTA scans was used to train and validate networks to classify septal and lateral scar presence within short axis left ventricle slices. Two designs of encoder-decoder networks were compared, with one encoding anatomical shape in the latent space. Ground truth was established by segmenting scar in MRI LGE and registering this to the CTA images. Short axis slices were taken from the CTA, which served as the input to the networks. An independent external set of 22 cases (27% the size of the cross-validation set) was used to test the best network.

RESULTS

A network classifying lateral scar only achieved an area under ROC curve of 0.75, with a sensitivity of 0.79 and specificity of 0.62 on the independent test set. The results of septal scar classification were poor (AUC < 0.6) for all networks. This was likely due to a high class imbalance. The highest AUC network encoded anatomical shape information in the network latent space, indicating it was important for the successful classification of lateral scar.

CONCLUSIONS

Automatic lateral wall scar detection can be performed from a routine cardiac CTA with reasonable accuracy, without any scar specific imaging. This requires only a single acquisition in the cardiac cycle. In a clinical setting, this could be useful for pre-procedure planning, especially where MRI is contraindicated. Further work with more septal scar present is warranted to improve the usefulness of this approach.

Understanding and Improving Risk Assessment After Myocardial Infarction Using Automated Left Ventricular Shape Analysis

BACKGROUND

Left ventricular ejection fraction (LVEF) and end-systolic volume (ESV) remain the main imaging biomarkers for post-acute myocardial infarction (AMI) risk stratification. However, they are limited to global systolic function and fail to capture functional and anatomical regional abnormalities, hindering their performance in risk stratification.

OBJECTIVES

This study aimed to identify novel 3-dimensional (3D) imaging end-systolic (ES) shape and contraction descriptors toward risk-related features and superior prognosis in AMI.

METHODS

A multicenter cohort of AMI survivors (n = 1,021; median age 63 years; 74.5% male) who underwent cardiac magnetic resonance (CMR) at a median of 3 days after infarction were considered for this study. The clinical endpoint was the 12-month rate of major adverse cardiac events (MACE; n = 73), consisting of all-cause death, reinfarction, and new congestive heart failure. A fully automated pipeline was developed to segment CMR images, build 3D statistical models of shape and contraction in AMI, and find the 3D patterns related to MACE occurrence.

RESULTS

The novel ES shape markers proved to be superior to ESV (median cross-validated area under the receiver-operating characteristic curve 0.681 [IQR: 0.679-0.684] vs 0.600 [IQR: 0.598-0.602]; P < 0.001); and 3D contraction to LVEF (0.716 [IQR: 0.714-0.718] vs 0.681 [IQR: 0.679-0.684]; P < 0.001) in MACE occurrence prediction. They also contributed to a significant improvement in a multivariable setting including CMR markers, cardiovascular risk factors, and basic patient characteristics (0.747 [IQR: 0.745-0.749]; P < 0.001). Based on these novel 3D descriptors, 3 impairments caused by AMI were identified: global, anterior, and basal, the latter being the most complementary signature to already known predictors.

CONCLUSIONS

The quantification of 3D differences in ES shape and contraction, enabled by a fully automated pipeline, improves post-AMI risk prediction and identifies shape and contraction patterns related to MACE occurrence.

Explicit and automatic ejection fraction assessment on 2D cardiac ultrasound with a deep learning-based approach

BACKGROUND

Ejection fraction (EF) is a key parameter for assessing cardiovascular functions in cardiac ultrasound, but its manual assessment is time-consuming and subject to high inter and intra-observer variability. Deep learning-based methods have the potential to perform accurate fully automatic EF predictions but suffer from a lack of explainability and interpretability. This study proposes a fully automatic method to reliably and explicitly evaluate the biplane left ventricular EF on 2D echocardiography following the recommended modified Simpson's rule.

METHODS

A deep learning model was trained on apical 4 and 2-chamber echocardiography to segment the left ventricle and locate the mitral valve. Predicted segmentations are then validated with a statistical shape model, which detects potential failures that could impact the EF evaluation. Finally, the end-diastolic and end-systolic frames are identified based on the remaining LV segmentations' areas and EF is estimated on all available cardiac cycles.

RESULTS

Our approach was trained on a dataset of 783 patients. Its performances were evaluated on an internal and external dataset of respectively 200 and 450 patients. On the internal dataset, EF assessment achieved a mean absolute error of 6.10% and a bias of 1.56 ± 7.58% using multiple cardiac cycles. The approach evaluated EF with a mean absolute error of 5.39% and a bias of -0.74 ± 7.12% on the external dataset.

CONCLUSION

Following the recommended guidelines, we proposed an end-to-end fully automatic approach that achieves state-of-the-art performance in biplane EF evaluation while giving explicit details to clinicians.

Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI Images Based on Fully Convolutional Neural Network

Background: Left ventricle (LV) segmentation using a cardiac magnetic resonance imaging (MRI) dataset is critical for evaluating global and regional cardiac functions and diagnosing cardiovascular diseases. LV clinical metrics such as LV volume, LV mass and ejection fraction (EF) are frequently extracted based on the LV segmentation from short-axis MRI images. Manual segmentation to assess such functions is tedious and time-consuming for medical experts to diagnose cardiac pathologies. Therefore, a fully automated LV segmentation technique is required to assist medical experts in working more efficiently. Method: This paper proposes a fully convolutional network (FCN) architecture for automatic LV segmentation from short-axis MRI images. Several experiments were conducted in the training phase to compare the performance of the network and the U-Net model with various hyper-parameters, including optimization algorithms, epochs, learning rate, and mini-batch size. In addition, a class weighting method was introduced to avoid having a high imbalance of pixels in the classes of image’s labels since the number of background pixels was significantly higher than the number of LV and myocardium pixels. Furthermore, effective image conversion with pixel normalization was applied to obtain exact features representing target organs (LV and myocardium). The segmentation models were trained and tested on a public dataset, namely the evaluation of myocardial infarction from the delayed-enhancement cardiac MRI (EMIDEC) dataset. Results: The dice metric, Jaccard index, sensitivity, and specificity were used to evaluate the network’s performance, with values of 0.93, 0.87, 0.98, and 0.94, respectively. Based on the experimental results, the proposed network outperforms the standard U-Net model and is an advanced fully automated method in terms of segmentation performance. Conclusion: This proposed method is applicable in clinical practice for doctors to diagnose cardiac diseases from short-axis MRI images.

Deep Learning Analysis of Cardiac MRI in Legacy Datasets: Multi-Ethnic Study of Atherosclerosis

The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular magnetic resonance (CMR) to study the mechanisms of cardiovascular disease in over 5,000 initially asymptomatic participants, and there is now a wealth of follow-up data over 20 years. However, the imaging technology used to generate the CMR images is no longer in routine use, and methods trained on modern data fail when applied to such legacy datasets. This study aimed to develop a fully automated CMR analysis pipeline that leverages the ability of machine learning algorithms to enable extraction of additional information from such a large-scale legacy dataset, expanding on the original manual analyses. We combined the original study analyses with new annotations to develop a set of automated methods for customizing 3D left ventricular (LV) shape models to each CMR exam and build a statistical shape atlas. We trained VGGNet convolutional neural networks using a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views to detect landmarks. A U-Net architecture was used to detect the endocardial and epicardial boundaries in short-axis images. The landmark detection network accurately predicted mitral valve and right ventricular insertion points with average error distance &lt;2.5 mm. The agreement of the network with two observers was excellent (intraclass correlation coefficient &gt;0.9). The segmentation network produced average Dice score of 0.9 for both myocardium and LV cavity. Differences between the manual and automated analyses were small, i.e., &lt;1.0 ± 2.6 mL/m2 for indexed LV volume, 3.0 ± 6.4 g/m2 for indexed LV mass, and 0.6 ± 3.3% for ejection fraction. In an independent atlas validation dataset, the LV atlas built from the fully automated pipeline showed similar statistical relationships to an atlas built from the manual analysis. Hence, the proposed pipeline is not only a promising framework to automatically assess additional measures of ventricular function, but also to study relationships between cardiac morphologies and future cardiac events, in a large-scale population study.

The impact of shape uncertainty on aortic-valve pressure-drop computations

Patient-specific image-based computational fluid dynamics (CFD) is widely adopted in the cardiovascular research community to study hemodynamics, and will become increasingly important for personalized medicine. However, segmentation of the flow domain is not exact and geometric uncertainty can be expected which propagates through the computational model, leading to uncertainty in model output. Seventy-four aortic-valves were segmented from computed tomography images at peak systole. Statistical shape modeling was used to obtain an approximate parameterization of the original segmentations. This parameterization was used to train a meta-model that related the first five shape mode coefficients and flowrate to the CFD-computed transvalvular pressure-drop. Consequently, shape uncertainty in the order of 0.5 and 1.0 mm was emulated by introducing uncertainty in the shape mode coefficients. A global variance-based sensitivity analysis was performed to quantify output uncertainty and to determine relative importance of the shape modes. The first shape mode captured the opening/closing behavior of the valve and uncertainty in this mode coefficient accounted for more than 90% of the output variance. However, sensitivity to shape uncertainty is patient-specific, and the relative importance of the fourth shape mode coefficient tended to increase with increases in valvular area. These results show that geometric uncertainty in the order of image voxel size may lead to substantial uncertainty in CFD-computed transvalvular pressure-drops. Moreover, this illustrates that it is essential to assess the impact of geometric uncertainty on model output, and that this should be thoroughly quantified for applications that wish to use image-based CFD models.

Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds

Shape reconstruction from sparse point clouds/images is a challenging and relevant task required for a variety of applications in computer vision and medical image analysis (e.g. surgical navigation, cardiac motion analysis, augmented/virtual reality systems). A subset of such methods, viz. 3D shape reconstruction from 2D contours, is especially relevant for computer-aided diagnosis and intervention applications involving meshes derived from multiple 2D image slices, views or projections. We propose a deep learning architecture, coined Mesh Reconstruction Network (MR-Net), which tackles this problem. MR-Net enables accurate 3D mesh reconstruction in real-time despite missing data and with sparse annotations. Using 3D cardiac shape reconstruction from 2D contours defined on short-axis cardiac magnetic resonance image slices as an exemplar, we demonstrate that our approach consistently outperforms state-of-the-art techniques for shape reconstruction from unstructured point clouds. Our approach can reconstruct 3D cardiac meshes to within 2.5-mm point-to-point error, concerning the ground-truth data (the original image spatial resolution is ∼1.8×1.8×10mm³). We further evaluate the robustness of the proposed approach to incomplete data, and contours estimated using an automatic segmentation algorithm. MR-Net is generic and could reconstruct shapes of other organs, making it compelling as a tool for various applications in medical image analysis.

Intelligent Segmentation Algorithm for Diagnosis of Meniere's Disease in the Inner Auditory Canal Using MRI Images with Three-Dimensional Level Set

This paper aimed to explore segmentation effects of the magnetic resonance imaging (MRI) images of the inner auditory canal of patients with Meniere's disease under the intelligent segmentation method of the inner ear based on three-dimensional (3D) level set (IS3DLS). The statistical shape model and the level set segmentation algorithm were combined to propose the IS3DLS. First, the shape training samples of the inner ear model were determined, and the results were manually segmented to further obtain region of interest (ROI) of the inner ear. The IS3DLS was employed to accurately segment MRI images of the inner auditory canal of patients with Meniere's disease. The segmentation performance of IS3DLS was compared with the expert manual segmentation method and the region growth level set-based segmentation algorithm. Results showed that Matthews correlation coefficient (MCC), Dice similarity coefficient (DSC), false positive rate (FPR), and false negative rate (FNR) of this algorithm were 0.9599, 0.9594, 0.0325, and 0.03655, respectively. Therefore, the IS3DLS could achieve good segmentation effect in MRI images of the inner auditory canal of patients with Meniere's disease, which was helpful for diagnosis and subsequent treatment of Meniere's disease.

Automated Left Ventricle Ischemic Scar Detection in CT Using Deep Neural Networks

Objectives: The aim of this study is to develop a scar detection method for routine computed tomography angiography (CTA) imaging using deep convolutional neural networks (CNN), which relies solely on anatomical information as input and is compatible with existing clinical workflows.

Background: Identifying cardiac patients with scar tissue is important for assisting diagnosis and guiding interventions. Late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) is the gold standard for scar imaging; however, there are common instances where it is contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is faster than Cardiovascular magnetic resonance imaging but is unable to reliably image scar.

Methods: A dataset of LGE MRI (200 patients, 83 with scar) was used to train and validate a CNN to detect ischemic scar slices using segmentation masks as input to the network. MRIs were segmented to produce 3D left ventricle meshes, which were sampled at points along the short axis to extract anatomical masks, with scar labels from LGE as ground truth. The trained CNN was tested with an independent CTA dataset (25 patients, with ground truth established with paired LGE MRI). Automated segmentation was performed to provide the same input format of anatomical masks for the network. The CNN was compared against manual reading of the CTA dataset by 3 experts.

Results: Note that 84.7% cross-validated accuracy (AUC: 0.896) for detecting scar slices in the left ventricle on the MRI data was achieved. The trained network was tested against the CTA-derived data, with no further training, where it achieved an 88.3% accuracy (AUC: 0.901). The automated pipeline outperformed the manual reading by clinicians.

Conclusion: Automatic ischemic scar detection can be performed from a routine cardiac CTA, without any scar-specific imaging or contrast agents. This requires only a single acquisition in the cardiac cycle. In a clinical setting, with near zero additional cost, scar presence could be detected to triage images, reduce reading times, and guide clinical decision-making.

On the Left Ventricular Remodeling of Patients with Stenotic Aortic Valve: A Statistical Shape Analysis

The left ventricle (LV) constantly changes its shape and function as a response to pathological conditions, and this process is known as remodeling. In the presence of aortic stenosis (AS), the degenerative process is not limited to the aortic valve but also involves the remodeling of LV. Statistical shape analysis (SSA) offers a powerful tool for the visualization and quantification of the geometrical and functional patterns of any anatomic changes. In this paper, a SSA method was developed to determine shape descriptors of the LV under different degrees of AS and thus to shed light on the mechanistic link between shape and function. A total of n=86 patients underwent computed tomography (CT) for the evaluation of valvulopathy were segmented to obtain the LV surface and then were automatically aligned to a reference template by rigid registrations and transformations. Shape modes of the anatomical LV variation induced by the degree of AS were assessed by principal component analysis (PCA). The first shape mode represented nearly 50% of the total variance of LV shape in our patient population and was mainly associated to a spherical LV geometry. At Pearson's analysis, the first shape mode was positively correlated to both the end-diastolic volume (p<0.01, R=0.814) and end-systolic volume (p<0.01, and R=0.922), suggesting LV impairment in patients with severe AS. A predictive model built with PCA-related shape modes achieved better performance in stratifying the occurrence of adverse events with respect to a baseline model using clinical demographic data as risk predictors. This study demonstrated the potential of SSA approaches to detect the association of complex 3D shape features with functional LV parameters.

Parametric-based feature selection via spherical harmonic coefficients for the left ventricle myocardial infarction screening

Computer-aided diagnosis (CAD) of heart diseases using machine learning techniques has recently received much attention. In this study, we present a novel parametric-based feature selection method using the three-dimensional spherical harmonic (SHs) shape descriptors of the left ventricle (LV) for intelligent myocardial infarction (MI) classification. The main hypothesis is that the SH coefficients of the parameterized endocardial shapes in MI patients are recognizable and distinguishable from healthy subjects. The SH parameterization, expansion, and registration of the LV endocardial shapes were performed, then parametric-based features were extracted. The proposed method performance was investigated by varying considered phases (i.e., the end-systole (ES) or the end-diastole (ED) frames), the spatial alignment procedures based on three modes (i.e., the center of the apical (CoA), the center of mass (CoM), and the center of the basal (CoB)), and considered orders of SH coefficients. After applying principal component analysis (PCA) on the feature vectors, support vector machine (SVM), K-nearest neighbors (K-NN), and random forest (RF) were trained and tested using the leave-one-out cross-validation (LOOCV). The proposed method validation was performed via a dataset containing healthy and MI subjects selected from the automated cardiac diagnosis challenge (ACDC) database. The promising results show the effectiveness of the proposed classification model. SVM reached the best performance with accuracy, sensitivity, specificity, and F-score of 97.50%, 95.00%, 100.00%, and 97.56%, respectively, using the introduced optimum feature set. This study demonstrates the robustness of combining the SH coefficients and machine learning techniques. We also quantify and notably highlight the contribution of different parameters in the classification and finally introduce an optimal feature set with maximum discriminant strength for the MI classification task. Moreover, the obtained results confirm that the proposed method performs more accurately than conventional point-based methods and also the current start-of-the-art, i.e., clinical measures. We showed our method's generalizability using employing it in dilated cardiomyopathy (DCM) detection and achieving promising results too. Parametric-based feature selection via spherical harmonics coefficients for the left ventricle myocardial infarction screening.

Statistical shape analysis of the left atrial appendage predicts stroke in atrial fibrillation

The shape of the left atrium (LA) and left atrial appendage (LAA) have been shown to predict stroke in patients with atrial fibrillation (AF). Prior studies rely on qualitative assessment of shape, which limits reproducibility and clinical utility. Statistical shape analysis (SSA) allows for quantitative assessment of shape. We use this method to assess the shape of the LA and LAA and predict stroke in patients with AF. From a database of AF patients who had previously undergone MRI of the LA, we identified 43 patients with AF who subsequently had an ischemic stroke. We also identified a cohort of 201 controls with AF who did not have a stroke after the MRI. We performed SSA of the LA and LAA shape to quantify the shape of these structures. We found three of the candidate LAA shape parameters to be predictive of stroke, while none of the LA shape parameters predicted stroke. When the three predictive LAA shape parameters were added to a logistic regression model that included the CHA₂DS₂-VASc score, the area under the ROC curve increased from 0.640 to 0.778 (p = .003). The shape of the LA and LAA can be assessed quantitatively using SSA. LAA shape predicts stroke in AF patients, while LA shape does not. Additionally, LAA shape predicts stroke independent of CHA₂DS₂-VASc score. SSA for assessment of LAA shape may improve stroke risk stratification and clinical decision making for AF patients.

Personalising left-ventricular biophysical models of the heart using parametric physics-informed neural networks

We present a parametric physics-informed neural network for the simulation of personalised left-ventricular biomechanics. The neural network is constrained to the biophysical problem in two ways: (i) the network output is restricted to a subspace built from radial basis functions capturing characteristic deformations of left ventricles and (ii) the cost function used for training is the energy potential functional specifically tailored for hyperelastic, anisotropic, nearly-incompressible active materials. The radial bases are generated from the results of a nonlinear Finite Element model coupled with an anatomical shape model derived from high-resolution cardiac images. We show that, by coupling the neural network with a simplified circulation model, we can efficiently generate computationally inexpensive estimations of cardiac mechanics. Our model is 30 times faster than the reference Finite Element model used, including training time, while yielding satisfactory average errors in the predictions of ejection fraction (-3%), peak systolic pressure (7%), stroke work (4%) and myocardial strains (14%). This physics-informed neural network is well suited to efficiently augment cardiac images with functional data and to generate large sets of synthetic cases for training deep network classifiers while it provides efficient personalization to the specific patient of interest with a high level of detail.

Validation of a deep-learning semantic segmentation approach to fully automate MRI-based left-ventricular deformation analysis in cardiotoxicity

OBJECTIVE

Left-ventricular (LV) strain measurements with the Displacement Encoding with Stimulated Echoes (DENSE) MRI sequence provide accurate estimates of cardiotoxicity damage related to chemotherapy for breast cancer. This study investigated an automated and supervised deep convolutional neural network (DCNN) model for LV chamber quantification before strain analysis in DENSE images.

METHODS

The DeepLabV3 +DCNN with three versions of ResNet-50 backbone was designed to conduct chamber quantification on 42 female breast cancer data sets. The convolutional layers in the three ResNet-50 backbones were varied as non-atrous, atrous and modified, atrous with accuracy improvements like using Laplacian of Gaussian filters. Parameters such as LV end-diastolic diameter (LVEDD) and ejection fraction (LVEF) were quantified, and myocardial strains analyzed with the Radial Point Interpolation Method (RPIM). Myocardial classification was validated with the performance metrics of accuracy, Dice, average perpendicular distance (APD) and others. Repeated measures ANOVA and intraclass correlation (ICC) with Cronbach's α (C-Alpha) tests were conducted between the three DCNNs and a vendor tool on chamber quantification and myocardial strain analysis.

RESULTS

Validation results in the same test-set for myocardial classification were accuracy = 97%, Dice = 0.92, APD = 1.2 mm with the modified ResNet-50, and accuracy = 95%, Dice = 0.90, APD = 1.7 mm with the atrous ResNet-50. The ICC results between the modified ResNet-50, atrous ResNet-50 and vendor-tool were C-Alpha = 0.97 for LVEF (55±7%, 54±7%, 54±7%, p = 0.6), and C-Alpha = 0.87 for LVEDD (4.6 ± 0.3 cm, 4.6 ± 0.3 cm, 4.6 ± 0.4 cm, p = 0.7).

CONCLUSION

Similar performance metrics and equivalent parameters obtained from comparisons between the atrous networks and vendor tool show that segmentation with the modified, atrous DCNN is applicable for automated LV chamber quantification and subsequent strain analysis in cardiotoxicity.

ADVANCES IN KNOWLEDGE

A novel deep-learning technique for segmenting DENSE images was developed and validated for LV chamber quantification and strain analysis in cardiotoxicity detection.

A deep-learning semantic segmentation approach to fully automated MRI-based left-ventricular deformation analysis in cardiotoxicity

Left-ventricular (LV) strain measurements with the Displacement Encoding with Stimulated Echoes (DENSE) MRI sequence provide accurate estimates of cardiotoxicity damage related to breast cancer chemotherapy. This study investigated an automated LV chamber quantification tool via segmentation with a supervised deep convolutional neural network (DCNN) before strain analysis with DENSE images. Segmentation for chamber quantification analysis was conducted with a custom DeepLabV3+ DCNN with ResNet-50 backbone on 42 female breast cancer datasets (22 training-sets, eight validation-sets and 12 independent test-sets). Parameters such as LV end-diastolic diameter (LVEDD) and ejection fraction (LVEF) were quantified, and myocardial strains analyzed with the Radial Point Interpolation Method (RPIM). Myocardial classification was validated against ground-truth with sensitivity-specificity analysis, the metrics of Dice, average perpendicular distance (APD) and Hausdorff-distance. Following segmentation, validation was conducted with the Cronbach's Alpha (C-Alpha) intraclass correlation coefficient between LV chamber quantification results with DENSE and Steady State Free Precession (SSFP) acquisitions and a vendor tool-based method to segment the DENSE data, and similarly for myocardial strain analysis in the chambers. The results of myocardial classification from segmentation of the DENSE data were accuracy = 97%, Dice = 0.89 and APD = 2.4 mm in the test-set. The C-Alpha correlations from comparing chamber quantification results between the segmented DENSE and SSFP data and vendor tool-based method were 0.97 for LVEF (56 ± 7% vs 55 ± 7% vs 55 ± 6%, p = 0.6) and 0.77 for LVEDD (4.6 ± 0.4 cm vs 4.5 ± 0.3 cm vs 4.5 ± 0.3 cm, p = 0.8). The validation metrics against ground-truth and equivalent parameters obtained from the SSFP segmentation and vendor tool-based comparisons show that the DCNN approach is applicable for automated LV chamber quantification and subsequent strain analysis in cardiotoxicity.

Multitask Learning for Estimating Multitype Cardiac Indices in MRI and CT Based on Adversarial Reverse Mapping

The estimation of multitype cardiac indices from cardiac magnetic resonance imaging (MRI) and computed tomography (CT) images attracts great attention because of its clinical potential for comprehensive function assessment. However, the most exiting model can only work in one imaging modality (MRI or CT) without transferable capability. In this article, we propose the multitask learning method with the reverse inferring for estimating multitype cardiac indices in MRI and CT. Different from the existing forward inferring methods, our method builds a reverse mapping network that maps the multitype cardiac indices to cardiac images. The task dependencies are then learned and shared to multitask learning networks using an adversarial training approach. Finally, we transfer the parameters learned from MRI to CT. A series of experiments were conducted in which we first optimized the performance of our framework via ten-fold cross-validation of over 2900 cardiac MRI images. Then, the fine-tuned network was run on an independent data set with 2360 cardiac CT images. The results of all the experiments conducted on the proposed adversarial reverse mapping show excellent performance in estimating multitype cardiac indices.

Radiomics Signatures of Cardiovascular Risk Factors in Cardiac MRI: Results From the UK Biobank

Cardiovascular magnetic resonance (CMR) radiomics is a novel technique for advanced cardiac image phenotyping by analyzing multiple quantifiers of shape and tissue texture. In this paper, we assess, in the largest sample published to date, the performance of CMR radiomics models for identifying changes in cardiac structure and tissue texture due to cardiovascular risk factors. We evaluated five risk factor groups from the first 5,065 UK Biobank participants: hypertension (n = 1,394), diabetes (n = 243), high cholesterol (n = 779), current smoker (n = 320), and previous smoker (n = 1,394). Each group was randomly matched with an equal number of healthy comparators (without known cardiovascular disease or risk factors). Radiomics analysis was applied to short axis images of the left and right ventricles at end-diastole and end-systole, yielding a total of 684 features per study. Sequential forward feature selection in combination with machine learning (ML) algorithms (support vector machine, random forest, and logistic regression) were used to build radiomics signatures for each specific risk group. We evaluated the degree of separation achieved by the identified radiomics signatures using area under curve (AUC), receiver operating characteristic (ROC), and statistical testing. Logistic regression with L1-regularization was the optimal ML model. Compared to conventional imaging indices, radiomics signatures improved the discrimination of risk factor vs. healthy subgroups as assessed by AUC [diabetes: 0.80 vs. 0.70, hypertension: 0.72 vs. 0.69, high cholesterol: 0.71 vs. 0.65, current smoker: 0.68 vs. 0.65, previous smoker: 0.63 vs. 0.60]. Furthermore, we considered clinical interpretation of risk-specific radiomics signatures. For hypertensive individuals and previous smokers, the surface area to volume ratio was smaller in the risk factor vs. healthy subjects; perhaps reflecting a pattern of global concentric hypertrophy in these conditions. In the diabetes subgroup, the most discriminatory radiomics feature was the median intensity of the myocardium at end-systole, which suggests a global alteration at the myocardial tissue level. This study confirms the feasibility and potential of CMR radiomics for deeper image phenotyping of cardiovascular health and disease. We demonstrate such analysis may have utility beyond conventional CMR metrics for improved detection and understanding of the early effects of cardiovascular risk factors on cardiac structure and tissue.

Combining statistical shape modeling, CFD, and meta-modeling to approximate the patient-specific pressure-drop across the aortic valve in real-time

BACKGROUND

Advances in medical imaging, segmentation techniques, and high performance computing have stimulated the use of complex, patient-specific, three-dimensional Computational Fluid Dynamics (CFD) simulations. Patient-specific, CFD-compatible geometries of the aortic valve are readily obtained. CFD can then be used to obtain the patient-specific pressure-flow relationship of the aortic valve. However, such CFD simulations are computationally expensive, and real-time alternatives are desired.

AIM

The aim of this work is to evaluate the performance of a meta-model with respect to high-fidelity, three-dimensional CFD simulations of the aortic valve.

METHODS

Principal component analysis was used to build a statistical shape model (SSM) from a population of 74 iso-topological meshes of the aortic valve. Synthetic meshes were created with the SSM, and steady-state CFD simulations at flow-rates between 50 and 650 mL/s were performed to build a meta-model. The meta-model related the statistical shape variance, and flow-rate to the pressure-drop.

RESULTS

Even though the first three shape modes account for only 46% of shape variance, the features relevant for the pressure-drop seem to be captured. The three-mode shape-model approximates the pressure-drop with an average error of 8.8% to 10.6% for aortic valves with a geometric orifice area below 150 mm² . The proposed methodology was least accurate for aortic valve areas above 150 mm² . Further reduction to a meta-model introduces an additional 3% error.

CONCLUSIONS

Statistical shape modeling can be used to capture shape variation of the aortic valve. Meta-models trained by SSM-based CFD simulations can provide an estimate of the pressure-flow relationship in real-time.

Automatic estimation of aortic and mitral valve displacements in dynamic CTA with 4D graph-cuts

The location of the mitral and aortic valves in dynamic cardiac imaging is useful for extracting functional derived parameters such as ejection fraction, valve excursions, and global longitudinal strain, and when performing anatomical structures tracking using slice following or valve intervention's planning. Completely automatic segmentation methods are still challenging tasks because of their fast movements and the different positions that prevent good visibility of the leaflets along the full cardiac cycle. In this article, we propose a processing pipeline to track the displacement of the aortic and mitral valve annuli from high-resolution cardiac four-dimensional computed tomographic angiography (4D-CTA). The proposed method is based on the dynamic separation of left ventricle, left atrium and aorta using statistical shape modeling and an energy minimization algorithm based on graph-cuts and has been evaluated on a set of 15 electrocardiography-gated 4D-CTAs. We report a mean agreement distance between manual annotations and our proposed method of 2.52±1.06 mm for the mitral annulus and 2.00±0.69 mm for the aortic valve annulus based on valve locations detected from manual anatomical landmarks. In addition, we show the effect of detecting the valvular planes on derived functional parameters (ejection fraction, global longitudinal strain, and excursions of the mitral and aortic valves).

AI in Medical Imaging Informatics: Current Challenges and Future Directions

This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.

Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy

In many cardiovascular pathologies, the shape and motion of the heart provide important clues to understanding the mechanisms of the disease and how it progresses over time. With the advent of large-scale cardiac data, statistical modeling of cardiac anatomy has become a powerful tool to provide automated, precise quantification of the status of patient-specific heart geometry with respect to reference populations. Powered by supervised or unsupervised machine learning algorithms, statistical cardiac shape analysis can be used to automatically identify and quantify the severity of heart diseases, to provide morphometric indices that are optimally associated with clinical factors, and to evaluate the likelihood of adverse outcomes. Recently, statistical cardiac atlases have been integrated with deep neural networks to enable anatomical consistency of cardiac segmentation, registration, and automated quality control. These combinations have already shown significant improvements in performance and avoid gross anatomical errors that could make the results unusable. This current trend is expected to grow in the near future. Here, we aim to provide a mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging.

Combining Statistical Shape Model and Principal Component Analysis to Estimate Left Ventricular Volume and Ejection Fraction

Left ventricular ejection fraction (LVEF) assessment is instrumental for cardiac health diagnosis, patient management, and patient eligibility for participation in clinical studies. Due to its non-invasiveness and low operational cost, ultrasound (US) imaging is the most commonly used imaging modality to image the heart and assess LVEF. Even though 3D US imaging technology is becoming more available, cardiologists dominantly use 2D US imaging to visualize the LV blood pool and interpret its area changes between end-systole and end-diastole. Our previous work showed that LVEF estimates based on area changes are significantly lower than the true volume-based estimates by as much as 13%,¹ which could lead to unnecessary and costly therapeutic decisions. Acquiring volumetric information about the LV blood pool necessitates either time-consuming 3D reconstruction or 3D US image acquisition. Here, we propose a method that leverages on a statistical shape model (SSM) constructed from 13 landmarks depicting the LV endocardial border to estimate a new patient's LV volume and LVEF. Two methods to estimate the 3D LV geometry with and without size normalization were employed. The SSM was built using the 13 landmarks from 50 training patient image datasets. Subsequently, the Mahalanobis distance (with size normalization) or the vector distance (without size normalization) between an incoming patient's LV landmarks and each shape in the SSM were used to determine the weights each training patient contributed to describing the new, incoming patient's LV geometry and associated blood pool volume. We tested the proposed method to estimate the LV volumes and LVEF for 16 new test patients. The estimated LVEFs based on Mahalanobis distance and vector distance were within 2.9% and 1.1%, respectively, of the ground truth LVEFs calculated from the 3D reconstructed LV volumes. Furthermore, the viability of using fewer principal components (PCs) to estimate the LV volume was explored by reducing the number of PCs retained when projecting landmarks onto PCA space. LVEF estimated based on 3 PCs, 5 PCs, and 10 PCs are within 6.6%, 5.4%, and 3.3%, respectively, of LVEF estimates using the full set of 39 PCs.

Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Information about myocardial motion and deformation is key to differentiate normal and abnormal conditions. With the advent of approaches relying on data rather than pre-conceived models, machine learning could either improve the robustness of motion quantification or reveal patterns of motion and deformation (rather than single parameters) that differentiate pathologies. We review machine learning strategies for extracting motion-related descriptors and analyzing such features among populations, keeping in mind constraints specific to the cardiac application.

A Statistical Shape Model Approach for Computing Left Ventricle Volume and Ejection Fraction Using Multi-plane Ultrasound Images

Assessing the left ventricular ejection fraction (LVEF) accurately requires 3D volumetric data of the LV. Cardiologists either have no access to 3D ultrasound (US) systems or prefer to visually estimate LVEF based on 2D US images. To facilitate the consistent estimation of the end-diastolic and end-systolic blood pool volume and LVEF based on 3D data without extensive complicated manual input, we propose a statistical shape model (SSM) based on 13 key anchor points-the LV apex (1), mitral valve hinges (6), and the midpoints of the endocardial contours (6)-identified from the LV endocardial contour of the tri-plane 2D US images. We use principal component analysis (PCA) to identify the principle modes of variation needed to represent the LV shapes, which enables us to estimate an incoming LV as a linear combination of the principle components (PC). For a new, incoming patient image, its 13 anchor points are projected onto the PC space; its shape is compared to each LV shape in the SSM based on Mahalanobis distance, which is normalized with respect to the LV size, as well as direct vector distance (i.e., PCA distance), without any size normalization. These distances are used to determine the weight each training shape in the SSM contributes to the description of the new patient LV shape. Finally, the new patient's LV systolic and diastolic volumes are estimated as the weighted average of the training volumes in the SSM. To assess our proposed method, we compared the SSM-based estimates of diastolic, systolic, stroke volumes, and LVEF with those computed directly from 16 tri-plane 2D US imaging datasets using the GE Echo-Pac PC clinical platform. The estimated LVEF based on Mahalanobis distance and PCA distance were within 6.8% and 1.7% of the reference LVEF computed using the GE Echo-Pac PC clinical platform.

Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow

We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manually by experts, is developed to generate pixel-wise apparent flow between two time points of a 2D+t cine MRI image sequence. Combining the apparent flow maps and cardiac segmentation masks, we obtain a local apparent flow corresponding to the 2D motion of myocardium and ventricular cavities. This leads to the generation of time series of the radius and thickness of myocardial segments to represent cardiac motion. These time series of motion features are reliable and explainable characteristics of pathological cardiac motion. Furthermore, they are combined with shape-related features to classify cardiac pathologies. Using only nine feature values as input, we propose an explainable, simple and flexible model for pathology classification. On ACDC training set and testing set, the model achieves 95% and 94% respectively as classification accuracy. Its performance is hence comparable to that of the state-of-the-art. Comparison with various other models is performed to outline some advantages of our model.

Cardiac Motion Evolution Model for Analysis of Functional Changes Using Tensor Decomposition and Cross-Sectional Data

Cardiac disease can reduce the ability of the ventricles to function well enough to sustain long-term pumping efficiency. Recent advances in cardiac motion tracking have led to improvements in the analysis of cardiac function. We propose a method to study cohort effects related to age with respect to cardiac function. The proposed approach makes use of a recent method for describing cardiac motion of a given subject using a polyaffine model, which gives a compact parameterization that reliably and accurately describes the cardiac motion across populations. Using this method, a data tensor of motion parameters is extracted for a given population. The partial least squares method for higher order arrays is used to build a model to describe the motion parameters with respect to age, from which a model of motion given age is derived. Based on the cross-sectional statistical analysis with the data tensor of each subject treated as an observation along time, the left ventricular motion over time of Tetralogy of Fallot patients is analysed to understand the temporal evolution of functional abnormalities in this population compared to healthy motion dynamics.

Morphologically normalized left ventricular motion indicators from MRI feature tracking characterize myocardial infarction

We characterized motion attributes arising from LV spatio-temporal analysis of motion distributions in myocardial infarction. Time-varying 3D finite element shape models were obtained in 300 Controls and 300 patients with myocardial infarction. Inter-individual left ventricular shape differences were eliminated using parallel transport to the grand mean of all cases. The first three principal component (PC) scores were used to characterize trajectory attributes. Scores were tested with ANOVA/MANOVA using patient disease status (Infarcts vs. Controls) as a factor. Infarcted patients had significantly different magnitude, orientation and shape of left ventricular trajectories in comparison to Controls. Significant differences were found for the angle between PC scores 1 and 2 in the endocardium, and PC scores 1 and 3 in the epicardium. The largest differences were found in the magnitude of endocardial motion. Endocardial PC scores in shape space showed the highest classification power using support vector machine, with higher total accuracy in comparison to previous methods. Shape space performed better than size-and-shape space for both epicardial and endocardial features. In conclusion, LV spatio-temporal motion attributes accurately characterize the presence of infarction. This approach is easily generalizable to different pathologies, enabling more precise study of the pathophysiological consequences of a wide spectrum of cardiac diseases.