The Current Landscape of Artificial Intelligence in Imaging for Transcatheter Aortic Valve Replacement.

Purpose: This review explores the current landscape of AI applications in imaging for TAVR, emphasizing the potential and limitations of these tools for (1) automating the image analysis and reporting process, (2) improving procedural planning, and (3) offering additional insight into post-TAVR outcomes. Finally, the direction of future research necessary to bridge these tools towards clinical integration is discussed. Recent Findings: Transcatheter aortic valve replacement (TAVR) has become a pivotal treatment option for select patients with severe aortic stenosis, and its indication for use continues to broaden. Noninvasive imaging techniques such as CTA and MRA have become routine for patient selection, preprocedural planning, and predicting the risk of complications. As the current methods for pre-TAVR image analysis are labor-intensive and have significant inter-operator variability, experts are looking towards artificial intelligence (AI) as a potential solution. Summary: AI has the potential to significantly enhance the planning, execution, and post-procedural follow up of TAVR. While AI tools are promising, the irreplaceable value of nuanced clinical judgment by skilled physician teams must not be overlooked. With continued research, collaboration, and careful implementation, AI can become an integral part in imaging for TAVR, ultimately improving patient care and outcomes.

Effect of cross-platform variations on transthoracic echocardiography measurements and clinical diagnosis.

Aims: Accurate cardiac chamber quantification is essential for clinical decisions and ideally should be consistent across different echocardiography systems. This study evaluates variations between the Philips EPIQ CVx (version 9.0.3) and Canon Aplio i900 (version 7.0) in measuring cardiac volumes, ventricular function, and valve structures. Methods and results: In this gender-balanced, single-centre study, 40 healthy volunteers (20 females and 20 males) aged 40 years and older (mean age 56.75 ± 11.57 years) were scanned alternately with both systems by the same sonographer using identical settings for both 2D and 4D acquisitions. We compared left ventricular (LV) and right ventricular (RV) volumes using paired t-tests, with significance set at P < 0.05. Correlation and Bland-Altman plots were used for quantities showing significant differences. Two board-certified cardiologists evaluated valve anatomy for each platform. The results showed no significant differences in LV end-systolic volume and LV ejection fraction between platforms. However, LV end-diastolic volume (LVEDV) differed significantly (biplane: P = 0.018; 4D: P = 0.028). Right ventricular (RV) measurements in 4D showed no significant differences, but there were notable disparities in 2D and 4D volumes within each platform (P < 0.01). Significant differences were also found in the LV systolic dyssynchrony index (P = 0.03), LV longitudinal strain (P = 0.04), LV twist (P = 0.004), and LV torsion (P = 0.005). Valve structure assessments varied, with more abnormalities noted on the Philips platform. Conclusion: Although LV and RV volumetric measurements are generally comparable, significant differences in LVEDV, LV strain metrics, and 2D vs. 4D measurements exist. These variations should be considered when using different platforms for patient follow-ups.

Early Feasibility Study of a Hybrid Tissue-Engineered Mitral Valve in an Ovine Model.

Tissue engineering aims to overcome the current limitations of heart valves by providing a viable alternative using living tissue. Nevertheless, the valves constructed from either decellularized xenogeneic or purely biologic scaffolds are unable to withstand the hemodynamic loads, particularly in the left ventricle. To address this, we have been developing a hybrid tissue-engineered heart valve (H-TEHV) concept consisting of a nondegradable elastomeric scaffold enclosed in a valve-like living tissue constructed from autologous cells. We developed a 21 mm mitral valve scaffold for implantation in an ovine model. Smooth muscle cells/fibroblasts and endothelial cells were extracted, isolated, and expanded from the animal's jugular vein. Next, the scaffold underwent a sequential coating with the sorted cells mixed with collagen type I. The resulting H-TEHV was then implanted into the mitral position of the same sheep through open-heart surgery. Echocardiography scans following the procedure revealed an acceptable valve performance, with no signs of regurgitation. The valve orifice area, measured by planimetry, was 2.9 cm2, the ejection fraction reached 67%, and the mean transmitral pressure gradient was measured at 8.39 mmHg. The animal successfully recovered from anesthesia and was transferred to the vivarium. Upon autopsy, the examination confirmed the integrity of the H-TEHV, with no evidence of tissue dehiscence. The preliminary results from the animal implantation suggest the feasibility of the H-TEHV.

Unmet Clinical Needs for Transcatheter Pulmonary Valves.

A common feature of congenital heart disease is the presence of right ventricular outflow tract (RVOT) obstruction that can range from mild to severe and can lead to atresia of the pulmonary valve, in extreme conditions. RVOT abnormalities can frequently be corrected surgically or via interventional means. However, most of these patients will ultimately develop pulmonary valve insufficiency and eventual right ventricular dilation, which will require a pulmonary valve replacement at some point in their life to mitigate the detrimental effects of pulmonary valve regurgitation (PVR) on the right ventricle (RV). The evolution from the studies done by Philip Bonhoeffer to implant a pulmonary valve via transcatheter means, have provided a bedrock for transcatheter pulmonary valve replacement (TPVR). Yet, several areas of unmet need for a demographic of patients still exist. Here, we discuss the clinical unmet needs in children under 20 Kg and expand the use of hybrid and other TPVR approaches along with the current indications and contraindications for pulmonary valve replacement. The constraints and limitations from commercially available pulmonary valves will be discussed from a clinical standpoint. Finally, we explore the use of hybrid and periventricular delivery of transcatheter pulmonary valves in younger patients.

A model of fluid-structure and biochemical interactions for applications to subclinical leaflet thrombosis.

Subclinical leaflet thrombosis (SLT) is a potentially serious complication of aortic valve replacement with a bioprosthetic valve in which blood clots form on the replacement valve. SLT is associated with increased risk of transient ischemic attacks and strokes and can progress to clinical leaflet thrombosis. SLT following aortic valve replacement also may be related to subsequent structural valve deterioration, which can impair the durability of the valve replacement. Because of the difficulty in clinical imaging of SLT, models are needed to determine the mechanisms of SLT and could eventually predict which patients will develop SLT. To this end, we develop methods to simulate leaflet thrombosis that combine fluid-structure interaction and a simplified thrombosis model that allows for deposition along the moving leaflets. Additionally, this model can be adapted to model deposition or absorption along other moving boundaries. We present convergence results and quantify the model's ability to realize changes in valve opening and pressures. These new approaches are an important advancement in our tools for modeling thrombosis because they incorporate both adhesion to the surface of the moving leaflets and feedback to the fluid-structure interaction.

Effect of Blood Flow on Cardiac Morphogenesis and Formation of Congenital Heart Defects.

Congenital heart disease (CHD) affects about 1 in 100 newborns and its causes are multifactorial. In the embryo, blood flow within the heart and vasculature is essential for proper heart development, with abnormal blood flow leading to CHD. Here, we discuss how blood flow (hemodynamics) affects heart development from embryonic to fetal stages, and how abnormal blood flow solely can lead to CHD. We emphasize studies performed using avian models of heart development, because those models allow for hemodynamic interventions, in vivo imaging, and follow up, while they closely recapitulate heart defects observed in humans. We conclude with recommendations on investigations that must be performed to bridge the gaps in understanding how blood flow alone, or together with other factors, contributes to CHD.

Prospects of mitochondrial transplantation in clinical medicine: Aspirations and challenges.

Mitochondria, known as the powerhouse of the cell, are at the center of healthy physiology and provide cells with energy in the form of ATP. These unique organelles are also implicated in many pathological conditions affecting a variety of organs in various systems. Recently, mitochondrial transplantation, inspired by mitochondria's endosymbiotic origin, has been attempted as a potential biotherapy in mitigating a variety of pathological conditions. Mitochondrial transplantation consists of the process of isolation, transfer, and uptake of exogenous, intact mitochondria into damaged cells. Here, we discuss mitochondrial transplantation in the context of clinical medicine practiced in neurology, cardiology, pulmonary medicine, and oncology, among others. We outline the role of mitochondria in various pathologies and discuss the state-of-the-art research that potentially form the basis of new therapeutics for the treatment of a variety of diseases due to mitochondrial dysfunction. Lastly, we explore some of the challenges associated with mitochondrial transplantation that must be addressed before mitochondrial transplantation becomes a viable therapeutic option in clinical settings.

Myocardial Perfusion in Hypoplastic Left Heart Syndrome.

BACKGROUND: The status of the systemic right ventricular coronary microcirculation in hypoplastic left heart syndrome (HLHS) is largely unknown. It is presumed that the systemic right ventricle's coronary microcirculation exhibits unique pathophysiological characteristics of HLHS in Fontan circulation. The present study sought to quantify myocardial blood flow by cardiac magnetic resonance imaging and evaluate the determinants of microvascular coronary dysfunction and myocardial ischemia in HLHS. METHODS: One hundred nineteen HLHS patients (median age, 4.80 years) and 34 healthy volunteers (median age, 5.50 years) underwent follow-up cardiac magnetic resonance imaging ≈1.8 years after total cavopulmonary connection. Right ventricle volumes and function, myocardial perfusion, diffuse fibrosis, and late gadolinium enhancement were assessed in 4 anatomic HLHS subtypes. Myocardial blood flow (MBF) was quantified at rest and during adenosine-induced hyperemia. Coronary conductance was estimated from MBF at rest and catheter-based measurements of mean aortic pressure (n=99). RESULTS: Hyperemic MBF in the systemic ventricle was lower in HLHS compared with controls (1.89±0.57 versus 2.70±0.84 mL/g per min; P<0.001), while MBF at rest normalized by the rate-pressure product, was similar (1.25±0.36 versus 1.19±0.33; P=0.446). Independent risk factors for a reduced hyperemic MBF were an HLHS subtype with mitral stenosis and aortic atresia (P=0.017), late gadolinium enhancement (P=0.042), right ventricular diastolic dysfunction (P=0.005), and increasing age at total cavopulmonary connection (P=0.022). The coronary conductance correlated negatively with systemic blood oxygen saturation (r, -0.29; P=0.02). The frequency of late gadolinium enhancement increased with age at total cavopulmonary connection (P=0.014). CONCLUSIONS: The coronary microcirculation of the systemic ventricle in young HLHS patients shows significant differences compared with controls. These hypothesis-generating findings on HLHS-specific risk factors for microvascular dysfunction suggest a potential benefit from early relief of frank cyanosis by total cavopulmonary connection.

Collagen Fibrillogenesis in the Mitral Valve: It's a Matter of Compliance.

Collagen fibers are essential structural components of mitral valve leaflets, their tension apparatus (chordae tendineae), and the associated papillary muscles. Excess or lack of collagen fibers in the extracellular matrix (ECM) in any of these structures can adversely affect mitral valve function. The organization of collagen fibers provides a sophisticated framework that allows for unidirectional blood flow during the precise opening and closing of this vital heart valve. Although numerous ECM molecules are essential for the differentiation, growth, and homeostasis of the mitral valve (e.g., elastic fibers, glycoproteins, and glycans), collagen fibers are key to mitral valve integrity. Besides the inert structural components of the tissues, collagen fibers are dynamic structures that drive outside-to-inside cell signaling, which informs valvular interstitial cells (VICs) present within the tissue environment. Diversity of collagen family members and the closely related collagen-like triple helix-containing proteins found in the mitral valve, will be discussed in addition to how defects in these proteins may lead to valve disease.

Mitochondrial transplantation in cardiomyocytes: foundation, methods, and outcomes.

Mitochondrial transplantation is emerging as a novel cellular biotherapy to alleviate mitochondrial damage and dysfunction. Mitochondria play a crucial role in establishing cellular homeostasis and providing cell with the energy necessary to accomplish its function. Owing to its endosymbiotic origin, mitochondria share many features with their bacterial ancestors. Unlike the nuclear DNA, which is packaged into nucleosomes and protected from adverse environmental effects, mitochondrial DNA are more prone to harsh environmental effects, in particular that of the reactive oxygen species. Mitochondrial damage and dysfunction are implicated in many diseases ranging from metabolic diseases to cardiovascular and neurodegenerative diseases, among others. While it was once thought that transplantation of mitochondria would not be possible due to their semiautonomous nature and reliance on the nucleus, recent advances have shown that it is possible to transplant viable functional intact mitochondria from autologous, allogenic, and xenogeneic sources into different cell types. Moreover, current research suggests that the transplantation could positively modulate bioenergetics and improve disease outcome. Mitochondrial transplantation techniques and consequences of transplantation in cardiomyocytes are the theme of this review. We outline the different mitochondrial isolation and transfer techniques. Finally, we detail the consequences of mitochondrial transplantation in the cardiovascular system, more specifically in the context of cardiomyopathies and ischemia.

MRI-based comprehensive analysis of vascular anatomy and hemodynamics.

BACKGROUND: Standardized methods for mapping the complex blood flow in vessels are essential for processing the large data volume acquired from 4D Flow MRI. We present a method for systematic and efficient analysis of anatomy and flow in large human blood vessels. To attain the best outcomes in cardiac surgery, vascular modifications that lead to secondary flow patterns such as vortices should be avoided. In this work, attention was paid to the undesired cancelation of vortices with opposite directions of rotation, known as Dean flow patterns, using hemodynamic parameters such as circulation and helicity density. METHODS: Our approach is based on the multiplanar reconstruction (MPR) of a multi-dimensional feature-space along the blood vessel's centerline. Hemodynamic parameters and anatomic information were determined in-plane from the reconstructed feature-space and from the blood vessel's centerline. A modified calculation of circulation and helicity density and novel parameters for quantifying Dean flow were developed. To test the model performance, we applied our methods to three test cases. RESULTS: Comprehensive information on position, magnitude and interrelation of vascular anatomy and hemodynamics were extracted from 4D Flow MRI datasets. The results show that the Dean flow patterns can be efficiently assessed using the novel parameters. CONCLUSIONS: Our approach to comprehensively and simultaneously quantify multiple parameters of vascular anatomy and hemodynamics from 4D Flow MRI provides new insights to map complex hemodynamic conditions.

Abnormal torsion and helical flow patterns of the neo-aorta in hypoplastic left heart syndrome assessed with 4D-flow MRI.

BACKGROUND: The Norwood procedure is the first stage of correction for patients with hypoplastic left heart syndrome (HLHS) and may lead to an abnormal neoaortic anatomy. We prospectively studied the neoaorta's fluid dynamics and the abnormal twist of the neoaorta by MRI examinations of HLHS patients in Fontan circulation. This study for the first time investigates the hypothesis that the neoaorta twist is associated with increased helical flow patterns, which may lead to an increased workload for the systemic right ventricle (RV) and ultimately to RV hypertrophy. METHODS: A group of forty-two HLHS patients with a median age of 4.9 (2.9-17.0) years, at NYHA I was studied along with a control group of eleven subjects with healthy hearts and a median age of 12.1 (4.0-41.6). All subjects underwent MRI of the thoracic aorta including ECG-gated 2D balanced SSFP cine for an axial slice stack and 4D-flow MRI for a sagittal volume slab covering the thoracic aorta. The twist of the neoaortic arch was quantified by the effective geometric torsion, defined as the product of curvature and geometric torsion. Fluid dynamics and geometry in the neoaorta, including the flow helicity index, were evaluated using an in-house analysis software (MeVisLab-based). Myocardial mass of the systemic ventricle at end-diastole was estimated by planimetry of the short-axis stack. RESULTS: Compared to the control group, the neoaorta in the HLHS patients shows an increased twist (P=0.04) and higher peak helicity density (P=0.03). The maximum helicity density was correlated with maximum effective torsion of the ascending neoaorta (P<0.001). The degree of maximum twist correlated with the increase in RV myocardial mass (P<0.01). CONCLUSIONS: This study shows that the abnormal twist of the neoaortic arch in HLHS patients is associated with abnormal helical flow patterns, which may contribute to increased RV afterload and may adversely affect the systemic RV by stimulation of myocardial hypertrophy. These findings suggest that further improvements of surgical aortic reconstruction, guided by insights from 4D-flow MRI, could lead to better neoaortic fluid dynamics in patients with HLHS.

3D Printing, Computational Modeling, and Artificial Intelligence for Structural Heart Disease.

Structural heart disease (SHD) is a new field within cardiovascular medicine. Traditional imaging modalities fall short in supporting the needs of SHD interventions, as they have been constructed around the concept of disease diagnosis. SHD interventions disrupt traditional concepts of imaging in requiring imaging to plan, simulate, and predict intraprocedural outcomes. In transcatheter SHD interventions, the absence of a gold-standard open cavity surgical field deprives physicians of the opportunity for tactile feedback and visual confirmation of cardiac anatomy. Hence, dependency on imaging in periprocedural guidance has led to evolution of a new generation of procedural skillsets, concept of a visual field, and technologies in the periprocedural planning period to accelerate preclinical device development, physician, and patient education. Adaptation of 3-dimensional (3D) printing in clinical care and procedural planning has demonstrated a reduction in early-operator learning curve for transcatheter interventions. Integration of computation modeling to 3D printing has accelerated research and development understanding of fluid mechanics within device testing. Application of 3D printing, computational modeling, and ultimately incorporation of artificial intelligence is changing the landscape of physician training and delivery of patient-centric care. Transcatheter structural heart interventions are requiring in-depth periprocedural understanding of cardiac pathophysiology and device interactions not afforded by traditional imaging metrics.

Fully­automated deep­learning segmentation of pediatric cardiovascular magnetic resonance of patients with complex congenital heart diseases.

BACKGROUND: For the growing patient population with congenital heart disease (CHD), improving clinical workflow, accuracy of diagnosis, and efficiency of analyses are considered unmet clinical needs. Cardiovascular magnetic resonance (CMR) imaging offers non-invasive and non-ionizing assessment of CHD patients. However, although CMR data facilitates reliable analysis of cardiac function and anatomy, clinical workflow mostly relies on manual analysis of CMR images, which is time consuming. Thus, an automated and accurate segmentation platform exclusively dedicated to pediatric CMR images can significantly improve the clinical workflow, as the present work aims to establish. METHODS: Training artificial intelligence (AI) algorithms for CMR analysis requires large annotated datasets, which are not readily available for pediatric subjects and particularly in CHD patients. To mitigate this issue, we devised a novel method that uses a generative adversarial network (GAN) to synthetically augment the training dataset via generating synthetic CMR images and their corresponding chamber segmentations. In addition, we trained and validated a deep fully convolutional network (FCN) on a dataset, consisting of [Formula: see text] pediatric subjects with complex CHD, which we made publicly available. Dice metric, Jaccard index and Hausdorff distance as well as clinically-relevant volumetric indices are reported to assess and compare our platform with other algorithms including U-Net and cvi42, which is used in clinics. RESULTS: For congenital CMR dataset, our FCN model yields an average Dice metric of [Formula: see text] and [Formula: see text] for LV at end-diastole and end-systole, respectively, and [Formula: see text] and [Formula: see text] for RV at end-diastole and end-systole, respectively. Using the same dataset, the cvi42, resulted in [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] for LV and RV at end-diastole and end-systole, and the U-Net architecture resulted in [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] for LV and RV at end-diastole and end-systole, respectively. CONCLUSIONS: The chambers' segmentation results from our fully-automated method showed strong agreement with manual segmentation and no significant statistical difference was found by two independent statistical analyses. Whereas cvi42 and U-Net segmentation results failed to pass the t-test. Relying on these outcomes, it can be inferred that by taking advantage of GANs, our method is clinically relevant and can be used for pediatric and congenital CMR segmentation and analysis.

Generalizable fully automated multi-label segmentation of four-chamber view echocardiograms based on deep convolutional adversarial networks.

A major issue in translation of the artificial intelligence platforms for automatic segmentation of echocardiograms to clinics is their generalizability. The present study introduces and verifies a novel generalizable and efficient fully automatic multi-label segmentation method for four-chamber view echocardiograms based on deep fully convolutional networks (FCNs) and adversarial training. For the first time, we used generative adversarial networks for pixel classification training, a novel method in machine learning not currently used for cardiac imaging, to overcome the generalization problem. The method's performance was validated against manual segmentations as the ground-truth. Furthermore, to verify our method's generalizability in comparison with other existing techniques, we compared our method's performance with a state-of-the-art method on our dataset in addition to an independent dataset of 450 patients from the CAMUS (cardiac acquisitions for multi-structure ultrasound segmentation) challenge. On our test dataset, automatic segmentation of all four chambers achieved a dice metric of 92.1%, 86.3%, 89.6% and 91.4% for LV, RV, LA and RA, respectively. LV volumes' correlation between automatic and manual segmentation were 0.94 and 0.93 for end-diastolic volume and end-systolic volume, respectively. Excellent agreement with chambers' reference contours and significant improvement over previous FCN-based methods suggest that generative adversarial networks for pixel classification training can effectively design generalizable fully automatic FCN-based networks for four-chamber segmentation of echocardiograms even with limited number of training data.

Bioenergetics Consequences of Mitochondrial Transplantation in Cardiomyocytes.

Background Mitochondrial transplantation has been recently explored for treatment of very ill cardiac patients. However, little is known about the intracellular consequences of mitochondrial transplantation. This study aims to assess the bioenergetics consequences of mitochondrial transplantation into normal cardiomyocytes in the short and long term. Methods and Results We first established the feasibility of autologous, non-autologous, and interspecies mitochondrial transplantation. Then we quantitated the bioenergetics consequences of non-autologous mitochondrial transplantation into cardiomyocytes up to 28 days using a Seahorse Extracellular Flux Analyzer. Compared with the control, we observed a statistically significant improvement in basal respiration and ATP production 2-day post-transplantation, accompanied by an increase in maximal respiration and spare respiratory capacity, although not statistically significantly. However, these initial improvements were short-lived and the bioenergetics advantages return to the baseline level in subsequent time points. Conclusions This study, for the first time, shows that transplantation of non-autologous mitochondria from healthy skeletal muscle cells into normal cardiomyocytes leads to short-term improvement of bioenergetics indicating "supercharged" state. However, over time these improved effects disappear, which suggests transplantation of mitochondria may have a potential application in settings where there is an acute stress.

Artificial intelligence in pediatric and adult congenital cardiac MRI: an unmet clinical need.

Cardiac MRI (CMR) allows non-invasive, non-ionizing assessment of cardiac function and anatomy in patients with congenital heart disease (CHD). The utility of CMR as a non-invasive imaging tool for evaluation of CHD have been growing exponentially over the past decade. The algorithms based on artificial intelligence (AI), and in particular, deep learning, have rapidly become a methodology of choice for analyzing CMR. A wide range of applications for AI have been developed to tackle challenges in various aspects of CMR, and significant advances have also been made from image acquisition to image analysis and diagnosis. We include an overview of AI definitions, different architectures, and details on well-known methods. This paper reviews the major deep learning concepts used for analyses of patients with CHD. In the end, we have summarized a list of open challenges and concerns to be considered for future studies.