Deep learning based assessment of hemodynamics in the coarctation of the aorta: comparison of bidirectional recurrent and convolutional neural networks.

The utilization of numerical methods, such as computational fluid dynamics (CFD), has been widely established for modeling patient-specific hemodynamics based on medical imaging data. Hemodynamics assessment plays a crucial role in treatment decisions for the coarctation of the aorta (CoA), a congenital heart disease, with the pressure drop (PD) being a crucial biomarker for CoA treatment decisions. However, implementing CFD methods in the clinical environment remains challenging due to their computational cost and the requirement for expert knowledge. This study proposes a deep learning approach to mitigate the computational need and produce fast results. Building upon a previous proof-of-concept study, we compared the effects of two different artificial neural network (ANN) architectures trained on data with different dimensionalities, both capable of predicting hemodynamic parameters in CoA patients: a one-dimensional bidirectional recurrent neural network (1D BRNN) and a three-dimensional convolutional neural network (3D CNN). The performance was evaluated by median point-wise root mean square error (RMSE) for pressures along the centerline in 18 test cases, which were not included in a training cohort. We found that the 3D CNN (median RMSE of 3.23 mmHg) outperforms the 1D BRNN (median RMSE of 4.25 mmHg). In contrast, the 1D BRNN is more precise in PD prediction, with a lower standard deviation of the error (±7.03 mmHg) compared to the 3D CNN (±8.91 mmHg). The differences between both ANNs are not statistically significant, suggesting that compressing the 3D aorta hemodynamics into a 1D centerline representation does not result in the loss of valuable information when training ANN models. Additionally, we evaluated the utility of the synthetic geometries of the aortas with CoA generated by using a statistical shape model (SSM), as well as the impact of aortic arch geometry (gothic arch shape) on the model's training. The results show that incorporating a synthetic cohort obtained through the SSM of the clinical cohort does not significantly increase the model's accuracy, indicating that the synthetic cohort generation might be oversimplified. Furthermore, our study reveals that selecting training cases based on aortic arch shape (gothic versus non-gothic) does not improve ANN performance for test cases sharing the same shape.

Experimental validation of the power law hemolysis model using a Couette shearing device.

BACKGROUND: The study of blood trauma, such as hemolysis in blood-carrying devices, is crucial due to the high incidence of adverse events like alteration of blood function, bleeding, and multi-organ failure. The extent of flow-induced hemolysis, predominantly influenced by stress duration and intensity, is described by established model parameters based on the power law approach. In recent years, various parameters were determined using different Couette shearing devices and donor species. However, they have not been validated due to limited experimental data. METHODS: This study provides hemolysis measurements in a Couette shearing device and evaluates the suitability of different power law parameters. The revised Couette shearing device generates well-defined dynamic stress loads that are repeatedly applied to blood samples at a defined temperature. Human blood samples with an adjusted hematocrit of 30%, were tested with varying repetitions (20 to 80 times). The half-sinusoidal stress loads had amplitudes of 73 to 140 Pa and exposure times of 24 msec per repetition. The parameters of five common power law hemolysis approaches were then compared with the experimental data. RESULTS: The prediction with the power law model parameters C = 3.458 × 10-6, α = 0.2777 and ß = 2.0639 showed a good agreement with the experimental results. CONCLUSION: The effect of multiple short-time stresses on hemolysis was investigated to validate the power law hemolysis model with the Couette shearing device of this study.

CT-based comparison of porcine, ovine, and human pulmonary arterial morphometry.

To facilitate pre-clinical animal and in-silico clinical trials for implantable pulmonary artery pressure sensors, understanding the respective species pulmonary arteries (PA) anatomy is important. Thus, morphological parameters describing PA of pigs and sheep, which are common animal models, were compared with humans. Retrospective computed tomography data of 41 domestic pigs (82.6 ± 18.8 kg), 14 sheep (49.1 ± 6.9 kg), and 49 patients (76.8 ± 18.2 kg) were used for reconstruction of the subject-specific PA anatomy. 3D surface geometries including main, left, and right PA as well as LPA and RPA side branches were manually reconstructed. Then, specific geometric parameters (length, diameters, taper, bifurcation angle, curvature, and cross-section enlargement) affecting device implantation and post-interventional device effect and efficacy were automatically calculated. For both animal models, significant differences to the human anatomy for most geometric parameters were found, even though the respective parameters' distributions also featured relevant overlap. Out of the two animal models, sheep seem to be better suitable for a preclinical study when considering only PA morphology. Reconstructed geometries are provided as open data for future studies. These findings support planning of preclinical studies and will help to evaluate the results of animal trials.

In-silico enhanced animal study of pulmonary artery pressure sensors: assessing hemodynamics using computational fluid dynamics.

To assess whether in-silico models can be used to predict the risk of thrombus formation in pulmonary artery pressure sensors (PAPS), a chronic animal study using pigs was conducted. Computed tomography (CT) data was acquired before and immediately after implantation, as well as one and three months after the implantation. Devices were implanted into 10 pigs, each one in the left and right pulmonary artery (PA), to reduce the required number of animal experiments. The implantation procedure aimed at facilitating optimal and non-optimal positioning of the devices to increase chances of thrombus formation. Eight devices were positioned non-optimally. Three devices were positioned in the main PA instead of the left and right PA. Pre-interventional PA geometries were reconstructed from the respective CT images, and the devices were virtually implanted at the exact sites and orientations indicated by the follow-up CT after one month. Transient intra-arterial hemodynamics were calculated using computational fluid dynamics. Volume flow rates were modelled specifically matching the animals body weights. Wall shear stresses (WSS) and oscillatory shear indices (OSI) before and after device implantation were compared. Simulations revealed no relevant changes in any investigated hemodynamic parameters due to device implantation. Even in cases, where devices were implanted in a non-optimal manner, no marked differences in hemodynamic parameters compared to devices implanted in an optimal position were found. Before implantation time and surface-averaged WSS was 2.35±0.47 Pa, whereas OSI was 0.08±0.17, respectively. Areas affected by low WSS magnitudes were 2.5±2.7 cm2, whereas the areas affected by high OSI were 18.1±6.3 cm2. After device implantation, WSS and OSI were 2.45±0.49 Pa and 0.08±0.16, respectively. Surface areas affected by low WSS and high OSI were 2.9±2.7 cm2, and 18.4±6.1 cm2, respectively. This in-silico study indicates that no clinically relevant differences in intra-arterial hemodynamics are occurring after device implantation, even at non-optimal positioning of the sensor. Simultaneously, no embolic events were observed, suggesting that the risk for thrombus formation after device implantation is low and independent of the sensor position.

Modelling blood flow in patients with heart valve disease using deep learning: A computationally efficient method to expand diagnostic capabilities in clinical routine.

Introduction: The computational modelling of blood flow is known to provide vital hemodynamic parameters for diagnosis and treatment-support for patients with valvular heart disease. However, most diagnosis/treatment-support solutions based on flow modelling proposed utilize time- and resource-intensive computational fluid dynamics (CFD) and are therefore difficult to implement into clinical practice. In contrast, deep learning (DL) algorithms provide results quickly with little need for computational power. Thus, modelling blood flow with DL instead of CFD may substantially enhances the usability of flow modelling-based diagnosis/treatment support in clinical routine. In this study, we propose a DL-based approach to compute pressure and wall-shear-stress (WSS) in the aorta and aortic valve of patients with aortic stenosis (AS). Methods: A total of 103 individual surface models of the aorta and aortic valve were constructed from computed tomography data of AS patients. Based on these surface models, a total of 267 patient-specific, steady-state CFD simulations of aortic flow under various flow rates were performed. Using this simulation data, an artificial neural network (ANN) was trained to compute spatially resolved pressure and WSS using a centerline-based representation. An unseen test subset of 23 cases was used to compare both methods. Results: ANN and CFD-based computations agreed well with a median relative difference between both methods of 6.0% for pressure and 4.9% for wall-shear-stress. Demonstrating the ability of DL to compute clinically relevant hemodynamic parameters for AS patients, this work presents a possible solution to facilitate the introduction of modelling-based treatment support into clinical practice.

Impact of turbulence modeling on the simulation of blood flow in aortic coarctation.

Numerical simulations of pulsatile blood flow in an aortic coarctation require the use of turbulence modeling. This paper considers three models from the class of large eddy simulation (LES) models (Smagorinsky, Vreman, σ -model) and one model from the class of variational multiscale models (residual-based) within a finite element framework. The influence of these models on the estimation of clinically relevant biomarkers used to assess the degree of severity of the pathological condition (pressure difference, secondary flow degree, normalized flow displacement, wall shear stress) is investigated in detail. The simulations show that most methods are consistent in terms of severity indicators such as pressure difference and stenotic velocity. Moreover, using second-order velocity finite elements, different turbulence models might lead to considerably different results concerning other clinically relevant quantities such as wall shear stresses. These differences may be attributed to differences in numerical dissipation introduced by the turbulence models.

Comparison of hemodynamics in biological surgical aortic valve replacement and transcatheter aortic valve implantation: An in-silico study.

OBJECTIVES: In aortic valve replacement (AVR), the treatment strategy as well as the model and size of the implanted prosthesis have a major impact on the postoperative hemodynamics and thus on the clinical outcome. Preinterventional prediction of the hemodynamics could support the treatment decision. Therefore, we performed paired virtual treatment with transcatheter AVR (TAVI) and biological surgical AVR (SAVR) and compared hemodynamic outcomes using numerical simulations. METHODS: 10 patients with severe aortic stenosis (AS) undergoing TAVI were virtually treated with both biological SAVR and TAVI to compare post-interventional hemodynamics using numerical simulations of peak-systolic flow. Virtual treatment procedure was done using an in-house developed tool based on position-based dynamics methodology, which was applied to the patient's anatomy including LVOT, aortic root and aorta. Geometries were automatically segmented from dynamic CT-scans and patient-specific flow rates were calculated by volumetric analysis of the left ventricle. Hemodynamics were assessed using the STAR CCM+ software by solving the RANS equations. RESULTS: Virtual treatment with TAVI resulted in realistic hemodynamics comparable to echocardiographic measurements (median difference in transvalvular pressure gradient [TPG]: -0.33 mm Hg). Virtual TAVI and SAVR showed similar hemodynamic functions with a mean TPG with standard deviation of 8.45 ± 4.60 mm Hg in TAVI and 6.66 ± 3.79 mm Hg in SAVR (p = 0.03) while max. Wall shear stress being 12.6 ± 4.59 vs. 10.2 ± 4.42 Pa (p = 0.001). CONCLUSIONS: Using the presented method for virtual treatment of AS, we were able to reliably predict post-interventional hemodynamics. TAVI and SAVR show similar hemodynamics in a pairwise comparison.

3D modeling and printing for complex biventricular repair of double outlet right ventricle.

Background: Double outlet right ventricle (DORV) describes a group of congenital heart defects where pulmonary artery and aorta originate completely or predominantly from the right ventricle. The individual anatomy of DORV patients varies widely with multiple subtypes classified. Although the majority of morphologies is suitable for biventricular repair (BVR), complex DORV anatomy can render univentricular palliation (UVP) the only option. Thus, patient-specific decision-making is critical for optimal surgical treatment planning. The evolution of image processing and rapid prototyping techniques facilitate the generation of detailed virtual and physical 3D models of the patient-specific anatomy which can support this important decision process within the Heart Team. Materilas and methods: The individual cardiovascular anatomy of nine patients with complex DORV, in whom surgical decision-making was not straightforward, was reconstructed from either computed tomography or magnetic resonance imaging data. 3D reconstructions were used to characterize the morphologic details of DORV, such as size and location of the ventricular septal defect (VSD), atrioventricular valve size, ventricular volumes, relationship between the great arteries and their spatial relation to the VSD, outflow tract obstructions, coronary artery anatomy, etc. Additionally, physical models were generated. Virtual and physical models were used in the preoperative assessment to determine surgical treatment strategy, either BVR vs. UVP. Results: Median age at operation was 13.2 months (IQR: 9.6-24.0). The DORV transposition subtype was present in six patients, three patients had a DORV-ventricular septal defect subtype. Patient-specific reconstruction was feasible for all patients despite heterogeneous image quality. Complex BVR was feasible in 5/9 patients (55%). Reasons for unsuitability for BVR were AV valve chordae interfering with potential intraventricular baffle creation, ventricular hypoplasia and non-committed VSD morphology. Evaluation in particular of qualitative data from 3D models was considered to support comprehension of complex anatomy. Conclusion: Image-based 3D reconstruction of patient-specific intracardiac anatomy provides valuable additional information supporting decision-making processes and surgical planning in complex cardiac malformations. Further prospective studies are required to fully appreciate the benefits of 3D technology.

Geometric uncertainty in intracranial aneurysm rupture status discrimination: a two-site retrospective study.

OBJECTIVES: Assessing the risk associated with unruptured intracranial aneurysms (IAs) is essential in clinical decision making. Several geometric risk parameters have been proposed for this purpose. However, performance of these parameters has been inconsistent. This study evaluates the performance and robustness of geometric risk parameters on two datasets and compare it to the uncertainty inherent in assessing these parameters and quantifies interparameter correlations. METHODS: Two datasets containing 244 ruptured and unruptured IA geometries from 178 patients were retrospectively analysed. IAs were stratified by anatomical region, based on the PHASES score locations. 37 geometric risk parameters representing four groups (size, neck, non-dimensional, and curvature parameters) were assessed. Analysis included standardised absolute group differences (SADs) between ruptured and unruptured IAs, ratios of SAD to median relative uncertainty (MRU) associated with the parameters, and interparameter correlation. RESULTS: The ratio of SAD to MRU was lower for higher dimensional size parameters (ie, areas and volumes) than for one-dimensional size parameters. Non-dimensional size parameters performed comparatively well with regard to SAD and MRU. SAD was higher in the posterior anatomical region. Correlation of parameters was strongest within parameter (sub)groups and between size and curvature parameters, while anatomical region did not strongly affect correlation patterns. CONCLUSION: Non-dimensional parameters and few parameters from other groups were comparatively robust, suggesting that they might generalise better to other datasets. The data on discriminative performance and interparameter correlations presented in this study may aid in developing and choosing robust geometric parameters for use in rupture risk models.

Effect of transcatheter edge-to-edge repair device position on diastolic hemodynamic parameters: An echocardiography-based simulation study.

Background: Transcatheter edge-to-edge repair (TEER) has developed from innovative technology to an established treatment strategy of mitral regurgitation (MR). The risk of iatrogenic mitral stenosis after TEER is, however, a critical factor in the conflict of interest between maximal reduction of MR and minimal impairment of left ventricular filling. We aim to investigate systematically the impact of device position on the post treatment hemodynamic outcome by involving the patient-specific segmentation of the diseased mitral valve. Materials and methods: Transesophageal echocardiographic image data of ten patients with severe MR (age: 57 ± 8 years, 20% female) were segmented and virtually treated with TEER at three positions by using a position based dynamics approach. Pre- and post-interventional patient geometries were preprocessed for computational fluid dynamics (CFD) and simulated at peak-diastole with patient-specific blood flow boundary conditions. Simulations were performed with boundary conditions mimicking rest and stress. The simulation results were compared with clinical data acquired for a cohort of 21 symptomatic MR patients (age: 79 ± 6 years, 43% female) treated with TEER. Results: Virtual TEER reduces the mitral valve area (MVA) from 7.5 ± 1.6 to 2.6 ± 0.6 cm2. Central device positioning resulted in a 14% smaller MVA than eccentric device positions. Furthermore, residual MVA is better predictable for central than for eccentric device positions (R 2 = 0.81 vs. R 2 = 0.49). The MVA reduction led to significantly higher maximal diastolic velocities (pre: 0.9 ± 0.2 m/s, post: 2.0 ± 0.5 m/s) and pressure gradients (pre: 1.5 ± 0.6 mmHg, post: 16.3 ± 9 mmHg) in spite of a mean flow rate reduction by 23% due to reduced MR after the treatment. On average, velocities were 12% and pressure gradients were 25% higher with devices in central compared to lateral or medial positions. Conclusion: Virtual TEER treatment combined with CFD is a promising tool for predicting individual morphometric and hemodynamic outcomes. Such a tool can potentially be used to support clinical decision making, procedure planning, and risk estimation to prevent post-procedural iatrogenic mitral stenosis.

CT-Based Analysis of Left Ventricular Hemodynamics Using Statistical Shape Modeling and Computational Fluid Dynamics.

Background: Cardiac computed tomography (CCT) based computational fluid dynamics (CFD) allows to assess intracardiac flow features, which are hypothesized as an early predictor for heart diseases and may support treatment decisions. However, the understanding of intracardiac flow is challenging due to high variability in heart shapes and contractility. Using statistical shape modeling (SSM) in combination with CFD facilitates an intracardiac flow analysis. The aim of this study is to prove the usability of a new approach to describe various cohorts. Materials and Methods: CCT data of 125 patients (mean age: 60.6 ± 10.0 years, 16.8% woman) were used to generate SSMs representing aneurysmatic and non-aneurysmatic left ventricles (LVs). Using SSMs, seven group-averaged LV shapes and contraction fields were generated: four representing patients with and without aneurysms and with mild or severe mitral regurgitation (MR), and three distinguishing aneurysmatic patients with true, intermediate aneurysms, and globally hypokinetic LVs. End-diastolic LV volumes of the groups varied between 258 and 347 ml, whereas ejection fractions varied between 21 and 26%. MR degrees varied from 1.0 to 2.5. Prescribed motion CFD was used to simulate intracardiac flow, which was analyzed regarding large-scale flow features, kinetic energy, washout, and pressure gradients. Results: SSMs of aneurysmatic and non-aneurysmatic LVs were generated. Differences in shapes and contractility were found in the first three shape modes. Ninety percent of the cumulative shape variance is described with approximately 30 modes. A comparison of hemodynamics between all groups found shape-, contractility- and MR-dependent differences. Disturbed blood washout in the apex region was found in the aneurysmatic cases. With increasing MR, the diastolic jet becomes less coherent, whereas energy dissipation increases by decreasing kinetic energy. The poorest blood washout was found for the globally hypokinetic group, whereas the weakest blood washout in the apex region was found for the true aneurysm group. Conclusion: The proposed CCT-based analysis of hemodynamics combining CFD with SSM seems promising to facilitate the analysis of intracardiac flow, thus increasing the value of CCT for diagnostic and treatment decisions. With further enhancement of the computational approach, the methodology has the potential to be embedded in clinical routine workflows and support clinicians.

Comparison of rhinomanometric and computational fluid dynamic assessment of nasal resistance with respect to measurement accuracy.

PURPOSE: Computational fluid dynamics (CFD)-based calculation of intranasal airflow became an important method in rhinologic research. Current evidence shows weak to moderate correlation as well as a systematic underprediction of nasal resistance by numerical simulations. In this study, we investigate whether these differences can be explained by measurement uncertainties caused by rhinomanometric devices and procedures. Furthermore, preliminary findings regarding the impact of tissue movements are reported. METHODS: A retrospective sample of 17 patients, who reported impaired nasal breathing and for which rhinomanometric (RMM) measurements using two different devices as well as computed tomography scans were available, was investigated in this study. Three patients also exhibited a marked collapse of the nasal valve. Agreement between both rhinomanometric measurements as well as between rhinomanometry and CFD-based calculations was assessed using linear correlation and Bland-Altman analyses. These analyses were performed for the volume flow rates measured at trans-nasal pressure differences of 75 and 150 Pa during inspiration and expiration. RESULTS: The correlation between volume flow rates measured using both RMM devices was good (R2 > 0.72 for all breathing states), and no relevant differences in measured flow rates was observed (21.6 ml/s and 14.8 ml/s for 75 and 150 Pa, respectively). In contrast, correlation between RMM and CFD was poor (R2 < 0.5) and CFD systematically overpredicted RMM-based flow rate measurements (231.8 ml/s and 328.3 ml/s). No differences between patients with and without nasal valve collapse nor between inspiration and expiration were observed. CONCLUSION: Biases introduced during RMM measurements, by either the chosen device, the operator or other aspects as for example the nasal cycle, are not strong enough to explain the gross differences commonly reported between RMM- and CFD-based measurement of nasal resistance. Additionally, tissue movement during breathing is most likely also no sufficient explanation for these differences.

Hemodynamic Changes During Physiological and Pharmacological Stress Testing in Patients With Heart Failure: A Systematic Review and Meta-Analysis.

Although disease etiologies differ, heart failure patients with preserved and reduced ejection fraction (HFpEF and HFrEF, respectively) both present with clinical symptoms when under stress and impaired exercise capacity. The extent to which the adaptation of heart rate (HR), stroke volume (SV), and cardiac output (CO) under stress conditions is altered can be quantified by stress testing in conjunction with imaging methods and may help to detect the diminishment in a patient's condition early. The aim of this meta-analysis was to quantify hemodynamic changes during physiological and pharmacological stress testing in patients with HF. A systematic literature search (PROSPERO 2020:CRD42020161212) in MEDLINE was conducted to assess hemodynamic changes under dynamic and pharmacological stress testing at different stress intensities in HFpEF and HFrEF patients. Pooled mean changes were estimated using a random effects model. Altogether, 140 study arms with 7,248 exercise tests were analyzed. High-intensity dynamic stress testing represented 73% of these data (70 study arms with 5,318 exercise tests), where: HR increased by 45.69 bpm (95% CI 44.51-46.88; I 2 = 98.4%), SV by 13.49 ml (95% CI 6.87-20.10; I 2 = 68.5%), and CO by 3.41 L/min (95% CI 2.86-3.95; I 2 = 86.3%). No significant differences between HFrEF and HFpEF groups were found. Despite the limited availability of comparative studies, these reference values can help to estimate the expected hemodynamic responses in patients with HF. No differences in chronotropic reactions, changes in SV, or CO were found between HFrEF and HFpEF. When compared to healthy individuals, exercise tolerance, as well as associated HR and CO changes under moderate-high dynamic stress, was substantially impaired in both HF groups. This may contribute to a better disease understanding, future study planning, and patient-specific predictive models. Systematic Review Registration: [https://www.crd.york.ac.uk/prospero/], identifier [CRD42020161212].

CT-Based Simulation of Left Ventricular Hemodynamics: A Pilot Study in Mitral Regurgitation and Left Ventricle Aneurysm Patients.

Background: Cardiac CT (CCT) is well suited for a detailed analysis of heart structures due to its high spatial resolution, but in contrast to MRI and echocardiography, CCT does not allow an assessment of intracardiac flow. Computational fluid dynamics (CFD) can complement this shortcoming. It enables the computation of hemodynamics at a high spatio-temporal resolution based on medical images. The aim of this proposed study is to establish a CCT-based CFD methodology for the analysis of left ventricle (LV) hemodynamics and to assess the usability of the computational framework for clinical practice. Materials and Methods: The methodology is demonstrated by means of four cases selected from a cohort of 125 multiphase CCT examinations of heart failure patients. These cases represent subcohorts of patients with and without LV aneurysm and with severe and no mitral regurgitation (MR). All selected LVs are dilated and characterized by a reduced ejection fraction (EF). End-diastolic and end-systolic image data was used to reconstruct LV geometries with 2D valves as well as the ventricular movement. The intraventricular hemodynamics were computed with a prescribed-motion CFD approach and evaluated in terms of large-scale flow patterns, energetic behavior, and intraventricular washout. Results: In the MR patients, a disrupted E-wave jet, a fragmentary diastolic vortex formation and an increased specific energy dissipation in systole are observed. In all cases, regions with an impaired washout are visible. The results furthermore indicate that considering several cycles might provide a more detailed view of the washout process. The pre-processing times and computational expenses are in reach of clinical feasibility. Conclusion: The proposed CCT-based CFD method allows to compute patient-specific intraventricular hemodynamics and thus complements the informative value of CCT. The method can be applied to any CCT data of common quality and represents a fair balance between model accuracy and overall expenses. With further model enhancements, the computational framework has the potential to be embedded in clinical routine workflows, to support clinical decision making and treatment planning.

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge.

The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71).

Deep Learning Based Centerline-Aggregated Aortic Hemodynamics: An Efficient Alternative to Numerical Modeling of Hemodynamics.

Image-based patient-specific modelling of hemodynamics are gaining increased popularity as a diagnosis and outcome prediction solution for a variety of cardiovascular diseases. While their potential to improve diagnostic capabilities and thereby clinical outcome is widely recognized, these methods require considerable computational resources since they are mostly based on conventional numerical methods such as computational fluid dynamics (CFD). As an alternative to the numerical methods, we propose a machine learning (ML) based approach to calculate patient-specific hemodynamic parameters. Compared to CFD based methods, our approach holds the benefit of being able to calculate a patient-specific hemodynamic outcome instantly with little need for computational power. In this proof-of-concept study, we present a deep artificial neural network (ANN) capable of computing hemodynamics for patients with aortic coarctation in a centerline aggregated (i.e., locally averaged) form. Considering the complex relation between vessels shape and hemodynamics on the one hand and the limited availability of suitable clinical data on the other, a sufficient accuracy of the ANN may however not be achieved with available data only. Another key aspect of this study is therefore the successful augmentation of available clinical data. Using a statistical shape model, additional training data was generated which substantially increased the ANN's accuracy, showcasing the ability of ML based methods to perform in-silico modelling tasks previously requiring resource intensive CFD simulations.

CARDIOKIN1: Computational Assessment of Myocardial Metabolic Capability in Healthy Controls and Patients With Valve Diseases.

BACKGROUND: Many heart diseases can result in reduced pumping capacity of the heart muscle. A mismatch between ATP demand and ATP production of cardiomyocytes is one of the possible causes. Assessment of the relation between myocardial ATP production (MVATP) and cardiac workload is important for better understanding disease development and choice of nutritional or pharmacologic treatment strategies. Because there is no method for measuring MVATP in vivo, the use of physiology-based metabolic models in conjunction with protein abundance data is an attractive approach. METHOD: We developed a comprehensive kinetic model of cardiac energy metabolism (CARDIOKIN1) that recapitulates numerous experimental findings on cardiac metabolism obtained with isolated cardiomyocytes, perfused animal hearts, and in vivo studies with humans. We used the model to assess the energy status of the left ventricle of healthy participants and patients with aortic stenosis and mitral valve insufficiency. Maximal enzyme activities were individually scaled by means of protein abundances in left ventricle tissue samples. The energy status of the left ventricle was quantified by the ATP consumption at rest (MVATP[rest]), at maximal workload (MVATP[max]), and by the myocardial ATP production reserve, representing the span between MVATP(rest) and MVATP(max). RESULTS: Compared with controls, in both groups of patients, MVATP(rest) was increased and MVATP(max) was decreased, resulting in a decreased myocardial ATP production reserve, although all patients had preserved ejection fraction. The variance of the energetic status was high, ranging from decreased to normal values. In both patient groups, the energetic status was tightly associated with mechanic energy demand. A decrease of MVATP(max) was associated with a decrease of the cardiac output, indicating that cardiac functionality and energetic performance of the ventricle are closely coupled. CONCLUSIONS: Our analysis suggests that the ATP-producing capacity of the left ventricle of patients with valvular dysfunction is generally diminished and correlates positively with mechanical energy demand and cardiac output. However, large differences exist in the energetic state of the myocardium even in patients with similar clinical or image-based markers of hypertrophy and pump function. Registration: URL: https://www.clinicaltrials.gov; Unique identifiers: NCT03172338 and NCT04068740.

Computed Tomography-Based Assessment of Transvalvular Pressure Gradient in Aortic Stenosis.

Background: In patients with aortic stenosis, computed tomography (CT) provides important information about cardiovascular anatomy for treatment planning but is limited in determining relevant hemodynamic parameters such as the transvalvular pressure gradient (TPG). Purpose: In the present study, we aimed to validate a reduced-order model method for assessing TPG in aortic stenosis using CT data. Methods: TPGCT was calculated using a reduced-order model requiring the patient-specific peak-systolic aortic flow rate (Q) and the aortic valve area (AVA). AVA was determined by segmentation of the aortic valve leaflets, whereas Q was quantified based on volumetric assessment of the left ventricle. For validation, invasively measured TPGcatheter was calculated from pressure measurements in the left ventricle and the ascending aorta. Altogether, 84 data sets of patients with aortic stenosis were used to compare TPGCT against TPGcatheter. Results: TPGcatheter and TPGCT were 50.6 ± 28.0 and 48.0 ± 26 mmHg, respectively (p = 0.56). A Bland-Altman analysis revealed good agreement between both methods with a mean difference in TPG of 2.6 mmHg and a standard deviation of 19.3 mmHg. Both methods showed good correlation with r = 0.72 (p < 0.001). Conclusions: The presented CT-based method allows assessment of TPG in patients with aortic stenosis, extending the current capabilities of cardiac CT for diagnosis and treatment planning.

Non-invasive CMR-Based Quantification of Myocardial Power and Efficiency Under Stress and Ischemic Conditions in Landrace Pigs.

Background: Myocardial efficiency should be maintained stable under light-to-moderate stress conditions, but ischemia puts the myocardium at risk for impaired functionality. Additionally, the measurement of such efficiency typically requires invasive heart catheterization and exposure to ionizing radiation. In this work, we aimed to non-invasively assess myocardial power and the resulting efficiency during pharmacological stress testing and ischemia induction. Methods: In a cohort of n = 10 healthy Landrace pigs, dobutamine stress testing was performed, followed by verapamil-induced ischemia alongside cardiac magnetic resonance (CMR) imaging. External myocardial power, internal myocardial power, and myocardial efficiency were assessed non-invasively using geometrical and functional parameters from CMR volumetric as well as blood flow and pressure measurements. Results: External myocardial power significantly increased under dobutamine stress [2.3 (1.6-3.1) W/m2 vs. 1.3 (1.1-1.6) W/m2, p = 0.005] and significantly decreased under verapamil-induced ischemia [0.8 (0.5-0.9) W/m2, p = 0.005]. Internal myocardial power [baseline: 5.9 (4.6-8.5) W/m2] was not affected by dobutamine [7.5 (6.9-9.0) W/m2, p = 0.241] nor verapamil [5.8 (4.7-8.8) W/m2, p = 0.878]. Myocardial efficiency did not change from baseline to dobutamine [21% (15-27) vs. 31% (20-44), p = 0.059] but decreased significantly during verapamil-induced ischemia [10% (8-13), p = 0.005]. Conclusion: In healthy Landrace pigs, dobutamine stress increased external myocardial power, whereas myocardial efficiency was maintained stable. On the contrary, verapamil-induced ischemia substantially decreased external myocardial power and myocardial efficiency. Non-invasive CMR was able to quantify these efficiency losses and might be useful for future clinical studies evaluating the effects of therapeutic interventions on myocardial energetics.