Fully Automated Construction of Three-dimensional Finite Element Simulations from Optical Coherence Tomography.

Despite recent advances in diagnosis and treatment, atherosclerotic coronary artery diseases remain a leading cause of death worldwide. Various imaging modalities and metrics can detect lesions and predict patients at risk; however, identifying unstable lesions is still difficult. Current techniques cannot fully capture the complex morphology-modulated mechanical responses that affect plaque stability, leading to catastrophic failure and mute the benefit of device and drug interventions. Finite Element (FE) simulations utilizing intravascular imaging OCT (Optical Coherence Tomography) are effective in defining physiological stress distributions. However, creating 3D FE simulations of coronary arteries from OCT images is challenging to fully automate given OCT frame sparsity, limited material contrast, and restricted penetration depth. To address such limitations, we developed an algorithmic approach to automatically produce 3D FE-ready digital twins from labeled OCT images. The 3D models are anatomically faithful and recapitulate mechanically relevant tissue lesion components, automatically producing morphologies structurally similar to manually constructed models whilst including more minute details. A mesh convergence study highlighted the ability to reach stress and strain convergence with average errors of just 5.9% and 1.6% respectively in comparison to FE models with approximately twice the number of elements in areas of refinement. Such an automated procedure will enable analysis of large clinical cohorts at a previously unattainable scale and opens the possibility for in-silico methods for patient specific diagnoses and treatment planning for coronary artery disease.

A transformer-based pyramid network for coronary calcified plaque segmentation in intravascular optical coherence tomography images.

Characterizing coronary calcified plaque (CCP) provides essential insight into diagnosis and treatment of atherosclerosis. Intravascular optical coherence tomography (OCT) offers significant advantages for detecting CCP and even automated segmentation with recent advances in deep learning techniques. Most of current methods have achieved promising results by adopting existing convolution neural networks (CNNs) in computer vision domain. However, their performance can be detrimentally affected by unseen plaque patterns and artifacts due to inherent limitation of CNNs in contextual reasoning. To overcome this obstacle, we proposed a Transformer-based pyramid network called AFS-TPNet for robust, end-to-end segmentation of CCP from OCT images. Its encoder is built upon CSWin Transformer architecture, allowing for better perceptual understanding of calcified arteries at a higher semantic level. Specifically, an augmented feature split (AFS) module and residual convolutional position encoding (RCPE) mechanism are designed to effectively enhance the capability of Transformer in capturing both fine-grained features and global contexts. Extensive experiments showed that AFS-TPNet trained using Lovasz Loss achieved superior performance in segmentation CCP under various contexts, surpassing prior state-of-the-art CNN and Transformer architectures by more than 6.58% intersection over union (IoU) score. The application of this promising method to extract CCP features is expected to enhance clinical intervention and translational research using OCT.

Single-Cell RNA Sequencing Reveals That Adaptation of Human Aortic Endothelial Cells to Antiproliferative Therapies Is Modulated by Flow-Induced Shear Stress.

BACKGROUND: Endothelial cells (ECs) are capable of quickly responding in a coordinated manner to a wide array of stresses to maintain vascular homeostasis. Loss of EC cellular adaptation may be a potential marker for cardiovascular disease and a predictor of poor response to endovascular pharmacological interventions such as drug-eluting stents. Here, we report single-cell transcriptional profiling of ECs exposed to multiple stimulus classes to evaluate EC adaptation. METHODS: Human aortic ECs were costimulated with both pathophysiological flows mimicking shear stress levels found in the human aorta (laminar and turbulent, ranging from 2.5 to 30 dynes/cm2) and clinically relevant antiproliferative drugs, namely paclitaxel and rapamycin. EC state in response to these stimuli was defined using single-cell RNA sequencing. RESULTS: We identified differentially expressed genes and inferred the TF (transcription factor) landscape modulated by flow shear stress using single-cell RNA sequencing. These flow-sensitive markers differentiated previously identified spatially distinct subpopulations of ECs in the murine aorta. Moreover, distinct transcriptional modules defined flow- and drug-responsive EC adaptation singly and in combination. Flow shear stress was the dominant driver of EC state, altering their response to pharmacological therapies. CONCLUSIONS: We showed that flow shear stress modulates the cellular capacity of ECs to respond to paclitaxel and rapamycin administration, suggesting that while responding to different flow patterns, ECs experience an impairment in their transcriptional adaptation to other stimuli.

CardioVision: A fully automated deep learning package for medical image segmentation and reconstruction generating digital twins for patients with aortic stenosis.

Aortic stenosis (AS) is the most prevalent heart valve disease in western countries that poses a significant public health challenge due to the lack of a medical treatment to prevent valve calcification. Given the aging population demographic, the prevalence of AS is projected to rise, resulting in a progressively significant healthcare and economic burden. While surgical aortic valve replacement (SAVR) has been the gold standard approach, the less invasive transcatheter aortic valve replacement (TAVR) is poised to become the dominant method for high- and medium-risk interventions. Computational simulations using patient-specific models, have opened new research avenues for optimizing emerging devices and predicting clinical outcomes. The traditional techniques of generating digital replicas of patients' aortic root, native valve, and calcification are time-consuming and labor-intensive processes requiring specialized tools and expertise in anatomy. Alternatively, deep learning models, such as the U-Net architecture, have emerged as reliable and fully automated methods for medical image segmentation. Two-dimensional U-Nets have been shown to produce comparable or more accurate results than trained clinicians' manual segmentation while significantly reducing computational costs. In this study, we have developed a fully automatic AI tool capable of reconstructing the digital twin geometry and analyzing the calcification distribution on the aortic valve. The developed automatic segmentation package enables the modeling of patient-specific anatomies, which can then be used to simulate virtual interventional procedures, optimize emerging prosthetic devices, and predict clinical outcomes.

Fully automated construction of three-dimensional finite element simulations from Optical Coherence Tomography.

Despite recent advances in diagnosis and treatment, atherosclerotic coronary artery diseases remain a leading cause of death worldwide. Various imaging modalities and metrics can detect lesions and predict patients at risk; however, identifying unstable lesions is still difficult. Current techniques cannot fully capture the complex morphology-modulated mechanical responses that affect plaque stability, leading to catastrophic failure and mute the benefit of device and drug interventions. Finite Element (FE) simulations utilizing intravascular imaging OCT (Optical Coherence Tomography) are effective in defining physiological stress distributions. However, creating 3D FE simulations of coronary arteries from OCT images is challenging to fully automate given OCT frame sparsity, limited material contrast, and restricted penetration depth. To address such limitations, we developed an algorithmic approach to automatically produce 3D FE-ready digital twins from labeled OCT images. The 3D models are anatomically faithful and recapitulate mechanically relevant tissue lesion components, automatically producing morphologies structurally similar to manually constructed models whilst including more minute details. A mesh convergence study highlighted the ability to reach stress and strain convergence with average errors of just 5.9% and 1.6% respectively in comparison to FE models with approximately twice the number of elements in areas of refinement. Such an automated procedure will enable analysis of large clinical cohorts at a previously unattainable scale and opens the possibility for in-silico methods for patient specific diagnoses and treatment planning for coronary artery disease.

Predicting one-year left ventricular mass index regression following transcatheter aortic valve replacement in patients with severe aortic stenosis: A new era is coming.

Aortic stenosis (AS) is the most common valvular heart disease in the western world, particularly worrisome with an ever-aging population wherein postoperative outcome for aortic valve replacement is strongly related to the timing of surgery in the natural course of disease. Yet, guidelines for therapy planning overlook insightful, quantified measures from medical imaging to educate clinical decisions. Herein, we leverage statistical shape analysis (SSA) techniques combined with customized machine learning methods to extract latent information from segmented left ventricle (LV) shapes. This enabled us to predict left ventricular mass index (LVMI) regression a year after transcatheter aortic valve replacement (TAVR). LVMI regression is an expected phenomena in patients undergone aortic valve replacement reported to be tightly correlated with survival one and five year after the intervention. In brief, LV geometries were extracted from medical images of a cohort of AS patients using deep learning tools, and then analyzed to create a set of statistical shape models (SSMs). Then, the supervised shape features were extracted to feed a support vector regression (SVR) model to predict the LVMI regression. The average accuracy of the predictions was validated against clinical measurements calculating root mean square error and R 2 score which yielded the satisfactory values of 0.28 and 0.67, respectively, on test data. Our work reveals the promising capability of advanced mathematical and bioinformatics approaches such as SSA and machine learning to improve medical output prediction and treatment planning.

Recent developments in modeling, imaging, and monitoring of cardiovascular diseases using machine learning.

Cardiovascular diseases are the leading cause of mortality, morbidity, and hospitalization around the world. Recent technological advances have facilitated analyzing, visualizing, and monitoring cardiovascular diseases using emerging computational fluid dynamics, blood flow imaging, and wearable sensing technologies. Yet, computational cost, limited spatiotemporal resolution, and obstacles for thorough data analysis have hindered the utility of such techniques to curb cardiovascular diseases. We herein discuss how leveraging machine learning techniques, and in particular deep learning methods, could overcome these limitations and offer promise for translation. We discuss the remarkable capacity of recently developed machine learning techniques to accelerate flow modeling, enhance the resolution while reduce the noise and scanning time of current blood flow imaging techniques, and accurate detection of cardiovascular diseases using a plethora of data collected by wearable sensors.

Framework for lumen-based nonrigid tomographic coregistration of intravascular images.

Purpose: Modern medical imaging enables clinicians to effectively diagnose, monitor, and treat diseases. However, clinical decision-making often relies on combined evaluation of either longitudinal or disparate image sets, necessitating coregistration of multiple acquisitions. Promising coregistration techniques have been proposed; however, available methods predominantly rely on time-consuming manual alignments or nontrivial feature extraction with limited clinical applicability. Addressing these issues, we present a fully automated, robust, nonrigid registration method, allowing for coregistering of multimodal tomographic vascular image datasets using luminal annotation as the sole alignment feature. Approach: Registration is carried out by the use of the registration metrics defined exclusively for lumens shapes. The framework is primarily broken down into two sequential parts: longitudinal and rotational registration. Both techniques are inherently nonrigid in nature to compensate for motion and acquisition artifacts in tomographic images. Results: Performance was evaluated across multimodal intravascular datasets, as well as in longitudinal cases assessing pre-/postinterventional coronary images. Low registration error in both datasets highlights method utility, with longitudinal registration errors-evaluated throughout the paired tomographic sequences-of 0.29 ± 0.14 mm ( < 2 longitudinal image frames) and 0.18 ± 0.16 mm ( < 1 frame) for multimodal and interventional datasets, respectively. Angular registration for the interventional dataset rendered errors of 7.7 ° ± 6.7 ° , and 29.1 ° ± 23.2 ° for the multimodal set. Conclusions: Satisfactory results across datasets, along with additional attributes such as the ability to avoid longitudinal over-fitting and correct nonlinear catheter rotation during nonrigid rotational registration, highlight the potential wide-ranging applicability of our presented coregistration method.

Aortic Dissection is Determined by Specific Shape and Hemodynamic Interactions.

The aim of this study was to determine whether specific three-dimensional aortic shape features, extracted via statistical shape analysis (SSA), correlate with the development of thoracic ascending aortic dissection (TAAD) risk and associated aortic hemodynamics. Thirty-one patients followed prospectively with ascending thoracic aortic aneurysm (ATAA), who either did (12 patients) or did not (19 patients) develop TAAD, were included in the study, with aortic arch geometries extracted from computed tomographic angiography (CTA) imaging. Arch geometries were analyzed with SSA, and unsupervised and supervised (linked to dissection outcome) shape features were extracted with principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA), respectively. We determined PLS-DA to be effective at separating dissection and no-dissection patients ([Formula: see text]), with decreased tortuosity and more equal ascending and descending aortic diameters associated with higher dissection risk. In contrast, neither PCA nor traditional morphometric parameters (maximum diameter, tortuosity, or arch volume) were effective at separating dissection and no-dissection patients. The arch shapes associated with higher dissection probability were supported with hemodynamic insight. Computational fluid dynamics (CFD) simulations revealed a correlation between the PLS-DA shape features and wall shear stress (WSS), with higher maximum WSS in the ascending aorta associated with increased risk of dissection occurrence. Our work highlights the potential importance of incorporating higher dimensional geometric assessment of aortic arch anatomy in TAAD risk assessment, and in considering the interdependent influences of arch shape and hemodynamics as mechanistic contributors to TAAD occurrence.

Impact and implications of mixed plaque class in automated characterization of complex atherosclerotic lesions.

Atherosclerosis is a complex disease altering vasculature morphology, and subsequently flow, with progressive plaque formation, mural disruption, and lumen occlusion. Determination of clinically-relevant plaque components-particularly calcium, lipid, and fibrous tissue-has driven automated image-based tissue characterization. Atherosclerotic tissue of mixed composition type arises when these principal components interdigitate and combine during the course of progressive atherosclerosis. Nevertheless, such mixed plaque is treated non-uniformly, and often neglected, as a distinct class in image analysis. We therefore quantitatively investigate frameworks to characterize mixed and other plaque tissue types, and examine their implications. Convolutional neural networks operated on labeled intravascular optical coherence tomography images using various characterization frameworks. The treatment of mixed plaque by image-based classifiers influenced the accuracy and homogeneity of the segmented classes. Excluding mixed plaque as a class on to itself necessarily assigns heterogeneous lesion subcomponents to one of the three homogeneous subtypes; when included, 61.7% of mixed tissue is labeled as calcium, reducing specificity in homogeneous calcium detection by 34.8%. Segmenting mixed plaque as distinct from homogeneous, non-mixed tissue improves lesion classification. This can be achieved either on the basis of homogeneous tissue classifier prediction uncertainty (77.8% overall accuracy) or by training classifiers to identify mixed plaque as a discrete tissue class (82.9% overall accuracy). Alternatively, mixed plaque can be grouped with one of the homogeneous classes, yielding a single histologically diverse class that helps preserve the homogeneity of the others. Ultimately, the best approach depends upon the alignment of histological and functional distinctions. While no vascular lesion characterization framework or method is universally optimal or appropriate, context should remain central in selecting tissue characterization techniques.

Effect of anatomical variation on extracorporeal membrane oxygenation circulatory support: A computational study.

BACKGROUND: Extracorporeal membrane oxygenation (ECMO) via femoral cannulation is a vital intervention capable of rapidly restoring perfusion for patients in shock. Despite increasing use to provide circulatory support, its hemodynamic effects are poorly understood and the impact of patient-specific anatomical variation on perfusion is unknown. This study investigates the complex failing heart-mechanical circulatory support circulation and analyzes the effect of patient-specific vascular anatomical variations on hemodynamics and end-organ perfusion. METHODS: Patient-specific vascular geometries were constructed from segmenting clinical computerized tomography angiography images and quantitatively compared using tortuosity, curvature, torsion, and lumen diameter. Computational fluid dynamic simulations were performed on a subset of geometries selected to represent a range of anatomical variation. Heart failure severity was modeled by varying the relative fraction of total flow provided by the heart and the extracorporeal circuit. A 3-element lumped parameter model was applied to accurately and dynamically model distal perfusion boundary conditions. Hemodynamic parameters and end-organ perfusion were analyzed and compared to assess the effect of anatomical variation. RESULTS: Pulsatile antegrade cardiac perfusion and ECMO retrograde perfusion collide in the aorta to form a dynamic watershed region. The size, position, and variation of this region over the cardiac cycle is substantially altered by patient anatomical region. Increased vascular tortuosity reduces the proximal extent of flow from circulatory support and decreases the size of the watershed region. CONCLUSIONS: Patient vascular anatomy is a key determinant of the ECMO-failing heart circulation that alters the location and extent of the watershed region and affects the tissues at risk for differential hypoxia and circuit-derived thromboemboli for a given level of support.

Simulation of Fluid-Structure Interaction in Extracorporeal Membrane Oxygenation Circulatory Support Systems.

Extracorporeal membrane oxygenation (ECMO) is a vital mechanical circulatory support modality capable of restoring perfusion for the patient in circulatory failure. Despite increasing adoption of ECMO, there is incomplete understanding of its effects on systemic hemodynamics and how the vasculature responds to varying levels of continuous retrograde perfusion. To gain further insight into the complex ECMO:failing heart circulation, computational fluid dynamics simulations focused on perfusion distribution and hemodynamic flow patterns were conducted using a patient-derived aorta geometry. Three case scenarios were simulated: (1) healthy control; (2) 90% ECMO-derived perfusion to model profound heart failure; and, (3) 50% ECMO-derived perfusion to model the recovering heart. Fluid-structure interface simulations were performed to quantify systemic pressure and vascular deformation throughout the aorta over the cardiac cycle. ECMO support alters pressure distribution while decreasing shear stress. Insights derived from computational modeling may lead to better understanding of ECMO support and improved patient outcomes.

An inverse method for mechanical characterization of heterogeneous diseased arteries using intravascular imaging.

The increasing prevalence of finite element (FE) simulations in the study of atherosclerosis has spawned numerous inverse FE methods for the mechanical characterization of diseased tissue in vivo. Current approaches are however limited to either homogenized or simplified material representations. This paper presents a novel method to account for tissue heterogeneity and material nonlinearity in the recovery of constitutive behavior using imaging data acquired at differing intravascular pressures by incorporating interfaces between various intra-plaque tissue types into the objective function definition. Method verification was performed in silico by recovering assigned material parameters from a pair of vessel geometries: one derived from coronary optical coherence tomography (OCT); one generated from in silico-based simulation. In repeated tests, the method consistently recovered 4 linear elastic (0.1 ± 0.1% error) and 8 nonlinear hyperelastic (3.3 ± 3.0% error) material parameters. Method robustness was also highlighted in noise sensitivity analysis, where linear elastic parameters were recovered with average errors of 1.3 ± 1.6% and 8.3 ± 10.5%, at 5% and 20% noise, respectively. Reproducibility was substantiated through the recovery of 9 material parameters in two more models, with mean errors of 3.0 ± 4.7%. The results highlight the potential of this new approach, enabling high-fidelity material parameter recovery for use in complex cardiovascular computational studies.

Acute Stent-Induced Endothelial Denudation: Biomechanical Predictors of Vascular Injury.

Recent concern for local drug delivery and withdrawal of the first Food and Drug Administration-approved bioresorbable scaffold emphasizes the need to optimize the relationships between stent design and drug release with imposed arterial injury and observed pharmacodynamics. In this study, we examine the hypothesis that vascular injury is predictable from stent design and that the expanding force of stent deployment results in increased circumferential stress in the arterial tissue, which may explain acute injury poststent deployment. Using both numerical simulations and ex vivo experiments on three different stent designs (slotted tube, corrugated ring, and delta wing), arterial injury due to device deployment was examined. Furthermore, using numerical simulations, the consequence of changing stent strut radial thickness on arterial wall shear stress and arterial circumferential stress distributions was examined. Regions with predicted arterial circumferential stress exceeding a threshold of 49.5 kPa compared favorably with observed ex vivo endothelial denudation for the three considered stent designs. In addition, increasing strut thickness was predicted to result in more areas of denudation and larger areas exposed to low wall shear stress. We conclude that the acute arterial injury, observed immediately following stent expansion, is caused by high circumferential hoop stresses in the interstrut region, and denuded area profiles are dependent on unit cell geometric features. Such findings when coupled with where drugs move might explain the drug-device interactions.

A platform for high-fidelity patient-specific structural modelling of atherosclerotic arteries: from intravascular imaging to three-dimensional stress distributions.

The pathophysiology of atherosclerotic lesions, including plaque rupture triggered by mechanical failure of the vessel wall, depends directly on the plaque morphology-modulated mechanical response. The complex interplay between lesion morphology and structural behaviour can be studied with high-fidelity computational modelling. However, construction of three-dimensional (3D) and heterogeneous models is challenging, with most previous work focusing on two-dimensional geometries or on single-material lesion compositions. Addressing these limitations, we here present a semi-automatic computational platform, leveraging clinical optical coherence tomography images to effectively reconstruct a 3D patient-specific multi-material model of atherosclerotic plaques, for which the mechanical response is obtained by structural finite-element simulations. To demonstrate the importance of including multi-material plaque components when recovering the mechanical response, a computational case study was conducted in which systematic variation of the intraplaque lipid and calcium was performed. The study demonstrated that the inclusion of various tissue components greatly affected the lesion mechanical response, illustrating the importance of multi-material formulations. This platform accordingly provides a viable foundation for studying how plaque micro-morphology affects plaque mechanical response, allowing for patient-specific assessments and extension into clinically relevant patient cohorts.

Understanding TAVR device expansion as it relates to morphology of the bicuspid aortic valve: A simulation study.

The bicuspid aortic valve (BAV) is a common and heterogeneous congenital heart abnormality that is often complicated by aortic stenosis. Although initially developed for tricuspid aortic valves (TAV), transcatheter aortic valve replacement (TAVR) devices are increasingly applied to the treatment of BAV stenosis. It is known that patient-device relationship between TAVR and BAV are not equivalent to those observed in TAV but the nature of these differences are not well understood. We sought to better understand the patient-device relationships between TAVR devices and the two most common morphologies of BAV. We performed finite element simulation of TAVR deployment into three cases of idealized aortic anatomies (TAV, Sievers 0 BAV, Sievers 1 BAV), derived from patient-specific measurements. Valve leaflet von Mises stress at the aortic commissures differed by valve configuration over a ten-fold range (TAV: 0.55 MPa, Sievers 0: 6.64 MPa, and Sievers 1: 4.19 MPa). First principle stress on the aortic wall was greater in Sievers 1 (0.316 MPa) and Sievers 0 BAV (0.137 MPa) compared to TAV (0.056 MPa). TAVR placement in Sievers 1 BAV demonstrated significant device asymmetric alignment, with 1.09 mm of displacement between the center of the device measured at the annulus and at the leaflet free edge. This orifice displacement was marginal in TAV (0.33 mm) and even lower in Sievers 0 BAV (0.23 mm). BAV TAVR, depending on the subtype involved, may encounter disparate combinations of device under expansion and asymmetry compared to TAV deployment. Understanding the impacts of BAV morphology on patient-device relationships can help improve device selection, patient eligibility, and the overall safety of TAVR in BAV.

Artificial intelligence to generate medical images: augmenting the cardiologist's visual clinical workflow.

Artificial intelligence (AI) offers great promise in cardiology, and medicine broadly, for its ability to tirelessly integrate vast amounts of data. Applications in medical imaging are particularly attractive, as images are a powerful means to convey rich information and are extensively utilized in cardiology practice. Departing from other AI approaches in cardiology focused on task automation and pattern recognition, we describe a digital health platform to synthesize enhanced, yet familiar, clinical images to augment the cardiologist's visual clinical workflow. In this article, we present the framework, technical fundamentals, and functional applications of the methodology, especially as it pertains to intravascular imaging. A conditional generative adversarial network was trained with annotated images of atherosclerotic diseased arteries to generate synthetic optical coherence tomography and intravascular ultrasound images on the basis of specified plaque morphology. Systems leveraging this unique and flexible construct, whereby a pair of neural networks is competitively trained in tandem, can rapidly generate useful images. These synthetic images replicate the style, and in several ways exceed the content and function, of normally acquired images. By using this technique and employing AI in such applications, one can ameliorate challenges in image quality, interpretability, coherence, completeness, and granularity, thereby enhancing medical education and clinical decision-making.