Device innovation in cardiovascular medicine: a report from the European Society of Cardiology Cardiovascular Round Table.

Research performed in Europe has driven cardiovascular device innovation. This includes, but is not limited to, percutaneous coronary intervention, cardiac imaging, transcatheter heart valve implantation, and device therapy of cardiac arrhythmias and heart failure. An important part of future medical progress involves the evolution of medical technology and the ongoing development of artificial intelligence and machine learning. There is a need to foster an environment conducive to medical technology development and validation so that Europe can continue to play a major role in device innovation while providing high standards of safety. This paper summarizes viewpoints on the topic of device innovation in cardiovascular medicine at the European Society of Cardiology Cardiovascular Round Table, a strategic forum for high-level dialogue to discuss issues related to the future of cardiovascular health in Europe. Devices are developed and improved through an iterative process throughout their lifecycle. Early feasibility studies demonstrate proof of concept and help to optimize the design of a device. If successful, this should ideally be followed by randomized clinical trials comparing novel devices vs. accepted standards of care when available and the collection of post-market real-world evidence through registries. Unfortunately, standardized procedures for feasibility studies across various device categories have not yet been implemented in Europe. Cardiovascular imaging can be used to diagnose and characterize patients for interventions to improve procedural results and to monitor devices long term after implantation. Randomized clinical trials often use cardiac imaging-based inclusion criteria, while less frequently trials randomize patients to compare the diagnostic or prognostic value of different modalities. Applications using machine learning are increasingly important, but specific regulatory standards and pathways remain in development in both Europe and the USA. Standards are also needed for smart devices and digital technologies that support device-driven biomonitoring. Changes in device regulation introduced by the European Union aim to improve clinical evidence, transparency, and safety, but they may impact the speed of innovation, access, and availability. Device development programmes including dialogue on unmet needs and advice on study designs must be driven by a community of physicians, trialists, patients, regulators, payers, and industry to ensure that patients have access to innovative care.

Deep learning for automated left ventricular outflow tract diameter measurements in 2D echocardiography.

BACKGROUND: Measurement of the left ventricular outflow tract diameter (LVOTd) in echocardiography is a common source of error when used to calculate the stroke volume. The aim of this study is to assess whether a deep learning (DL) model, trained on a clinical echocardiographic dataset, can perform automatic LVOTd measurements on par with expert cardiologists. METHODS: Data consisted of 649 consecutive transthoracic echocardiographic examinations of patients with coronary artery disease admitted to a university hospital. 1304 LVOTd measurements in the parasternal long axis (PLAX) and zoomed parasternal long axis views (ZPLAX) were collected, with each patient having 1-6 measurements per examination. Data quality control was performed by an expert cardiologist, and spatial geometry data was preserved for each LVOTd measurement to convert DL predictions into metric units. A convolutional neural network based on the U-Net was used as the DL model. RESULTS: The mean absolute LVOTd error was 1.04 (95% confidence interval [CI] 0.90-1.19) mm for DL predictions on the test set. The mean relative LVOTd errors across all data subgroups ranged from 3.8 to 5.1% for the test set. Generally, the DL model had superior performance on the ZPLAX view compared to the PLAX view. DL model precision for patients with repeated LVOTd measurements had a mean coefficient of variation of 2.2 (95% CI 1.6-2.7) %, which was comparable to the clinicians for the test set. CONCLUSION: DL for automatic LVOTd measurements in PLAX and ZPLAX views is feasible when trained on a limited clinical dataset. While the DL predicted LVOTd measurements were within the expected range of clinical inter-observer variability, the robustness of the DL model requires validation on independent datasets. Future experiments using temporal information and anatomical constraints could improve valvular identification and reduce outliers, which are challenges that must be addressed before clinical utilization.

Automatic alignment of standard views for transesophageal echocardiographic images.

Purpose: 3D transesophageal echocardiography (TEE) has become an important modality for pre- and peri-operative imaging of valvular heart disease. TEE can give excellent visualization of valve morphology in 3D rendering. As a convention, 3D TEE images are reformatted in three standard views. We describe a method for automatic calculation of parameters needed to define the standard views from 3D TEE images using no manual input. Approach: An algorithm was designed to find the center of the mitral valve and the left ventricular outflow tract (OT). These parameters defined the three-chamber view. The problem was modeled as a state estimation problem in which a 3D model was deformed based on shape priors and edge detection using a Kalman filter. This algorithm is capable of running in real time after initialization. Results: The algorithm was validated by comparing the automatic alignments of 106 TEE images against manually placed landmarks. The median error for determining the mitral valve center was 7.1 mm, and the median error for determining the left ventricular OT orientation was 13.5 deg. Conclusion: The algorithm is an accurate tool for automating the process of finding standard views for TEE images of the mitral valve.

Wearables, telemedicine, and artificial intelligence in arrhythmias and heart failure: Proceedings of the European Society of Cardiology Cardiovascular Round Table.

Digital technology is now an integral part of medicine. Tools for detecting, screening, diagnosis, and monitoring health-related parameters have improved patient care and enabled individuals to identify issues leading to better management of their own health. Wearable technologies have integrated sensors and can measure physical activity, heart rate and rhythm, and glucose and electrolytes. For individuals at risk, wearables or other devices may be useful for early detection of atrial fibrillation or sub-clinical states of cardiovascular disease, disease management of cardiovascular diseases such as hypertension and heart failure, and lifestyle modification. Health data are available from a multitude of sources, namely clinical, laboratory and imaging data, genetic profiles, wearables, implantable devices, patient-generated measurements, and social and environmental data. Artificial intelligence is needed to efficiently extract value from this constantly increasing volume and variety of data and to help in its interpretation. Indeed, it is not the acquisition of digital information, but rather the smart handling and analysis that is challenging. There are multiple stakeholder groups involved in the development and effective implementation of digital tools. While the needs of these groups may vary, they also have many commonalities, including the following: a desire for data privacy and security; the need for understandable, trustworthy, and transparent systems; standardized processes for regulatory and reimbursement assessments; and better ways of rapidly assessing value.

Generating Synthetic Labeled Data From Existing Anatomical Models: An Example With Echocardiography Segmentation.

Deep learning can bring time savings and increased reproducibility to medical image analysis. However, acquiring training data is challenging due to the time-intensive nature of labeling and high inter-observer variability in annotations. Rather than labeling images, in this work we propose an alternative pipeline where images are generated from existing high-quality annotations using generative adversarial networks (GANs). Annotations are derived automatically from previously built anatomical models and are transformed into realistic synthetic ultrasound images with paired labels using a CycleGAN. We demonstrate the pipeline by generating synthetic 2D echocardiography images to compare with existing deep learning ultrasound segmentation datasets. A convolutional neural network is trained to segment the left ventricle and left atrium using only synthetic images. Networks trained with synthetic images were extensively tested on four different unseen datasets of real images with median Dice scores of 91, 90, 88, and 87 for left ventricle segmentation. These results match or are better than inter-observer results measured on real ultrasound datasets and are comparable to a network trained on a separate set of real images. Results demonstrate the images produced can effectively be used in place of real data for training. The proposed pipeline opens the door for automatic generation of training data for many tasks in medical imaging as the same process can be applied to other segmentation or landmark detection tasks in any modality. The source code and anatomical models are available to other researchers.1 1https://adgilbert.github.io/data-generation/.

User-Intended Doppler Measurement Type Prediction Combining CNNs With Smart Post-Processing.

Spectral Doppler measurements are an important part of the standard echocardiographic examination. These measurements give insight into myocardial motion and blood flow, providing clinicians with parameters for diagnostic decision making. Many of these measurements are performed automatically with high accuracy, increasing the efficiency of the diagnostic pipeline. However, full automation is not yet available because the user must manually select which measurement should be performed on each image. In this work, we develop a pipeline based on convolutional neural networks (CNNs) to automatically classify the measurement type from cardiac Doppler scans. We show how the multi-modal information in each spectral Doppler recording can be combined using a meta parameter post-processing mapping scheme and heatmaps to encode coordinate locations. Additionally, we experiment with several architectures to examine the tradeoff between accuracy, speed, and memory usage for resource-constrained environments. Finally, we propose a confidence metric using the values in the last fully connected layer of the network and show that our confidence metric can prevent many misclassifications. Our algorithm enables a fully automatic pipeline from acquisition to Doppler spectrum measurements. We achieve 96% accuracy on a test set drawn from separate clinical sites, indicating that the proposed method is suitable for clinical adoption.

Two methods for modifed Doo-Sabin modeling of nonsmooth surfaces-applied to right ventricle modeling.

Purpose: In recent years, there has been increased clinical interest in the right ventricle (RV) of the heart. RV dysfunction is an important prognostic marker for several cardiac diseases. Accurate modeling of the RV shape is important for estimating the performance. We have created computationally effective models that allow for accurate estimation of the RV shape. Approach: Previous approaches to cardiac shape modeling, including modeling the RV geometry, has used Doo-Sabin surfaces. Doo-Sabin surfaces allow effective computation and adapt to smooth, organic surfaces. However, they struggle with modeling sharp corners or ridges without many control nodes. We modified the Doo-Sabin surface to allow for sharpness using weighting of vertices and edges instead. This was done in two different ways. For validation, we compared the standard Doo-Sabin versus the sharp Doo-Sabin models in modeling the RV shape of 16 cardiac ultrasound images, against a ground truth manually drawn by a cardiologist. A Kalman filter fitted the models to the ultrasound images, and the difference between the volume of the model and the ground truth was measured. Results: The two modified Doo-Sabin models both outperformed the standard Doo-Sabin model in modeling the RV. On average, the regular Doo-Sabin had an 8-ml error in volume, whereas the sharp models had 7- and 6-ml error, respectively. Conclusions: Compared with the standard Doo-Sabin, the modified Doo-Sabin models can adapt to a larger variety of surfaces while still being compact models. They were more accurate on modeling the RV shape and could have uses elsewhere.

Detection of Tissue Fibrosis using Natural Mechanical Wave Velocity Estimation: Feasibility Study.

In the feasibility study described here, we developed and tested a novel method for mechanical wave velocity estimation for tissue fibrosis detection in the myocardium. High-frame-rate ultrasound imaging and a novel signal processing method called clutter filter wave imaging was used. A mechanical wave propagating through the left ventricle shortly after the atrial contraction was measured in the three different apical acquisition planes, for 20 infarct patients and 10 healthy controls. The results obtained were correlated with fibrosis locations from magnetic resonance imaging, and a sensitivity ≥60% was achieved for all infarcts larger than 10% of the left ventricle. The stability of the wave through several heart cycles was assessed and found to be of high quality. This method therefore has potential for non-invasive fibrosis detection in the myocardium, but further validation in a larger group of subjects is needed.

Mitral Annulus Segmentation Using Deep Learning in 3-D Transesophageal Echocardiography.

3D Transesophageal Echocardiography is an excellent tool for evaluating the mitral valve and is also well suited for guiding cardiac interventions. We introduce a fully automatic method for mitral annulus segmentation in 3D Transesophageal Echocardiography, which requires no manual input. One hundred eleven multi-frame 3D transesophageal echocardiography recordings were split into training, validation, and test sets. Each 3D recording was decomposed into a set of 2D planes, exploiting the symmetry around the centerline of the left ventricle. A deep 2D convolutional neural network was trained to predict the mitral annulus coordinates, and the predictions from neighboring planes were regularized by enforcing continuity around the annulus. Applying the final model and post-processing to the test set data gave a mean error of 2.0 mm - with a standard deviation of 1.9 mm. Fully automatic segmentation of the mitral annulus can alleviate the need for manual interaction in the quantification of an array of mitral annular parameters and has the potential to eliminate inter-observer variability.

An image fusion tool for echo-guided left ventricular lead placement in cardiac resynchronization therapy: Performance and workflow integration analysis.

BACKGROUND: The response rate to cardiac resynchronization therapy (CRT) may be improved if echocardiographic-derived parameters are used to guide the left ventricular (LV) lead deployment. Tools to visually integrate deformation imaging and fluoroscopy to take advantage of the combined information are lacking. METHODS: An image fusion tool for echo-guided LV lead placement in CRT was developed. A personalized average 3D cardiac model aided visualization of patient-specific LV function in fluoroscopy. A set of coronary venography-derived landmarks facilitated registration of the 3D model with fluoroscopy into a single multimodality image. The fusion was both performed and analyzed retrospectively in 30 cases. Baseline time-to-peak values from echocardiography speckle-tracking radial strain traces were color-coded onto the fused LV. LV segments with suspected scar tissue were excluded by cardiac magnetic resonance imaging. The postoperative augmented image was used to investigate: (a) registration accuracy and (b) agreement between LV pacing lead location, echo-defined target segments, and CRT response. RESULTS: Registration time (264 ± 25 seconds) and accuracy (4.3 ± 2.3 mm) were found clinically acceptable. A good agreement between pacing location and echo-suggested segments was found in 20 (out of 21) CRT responders. Perioperative integration of the proposed workflow was successfully tested in 2 patients. No additional radiation, compared with the existing workflow, was required. CONCLUSIONS: The fusion tool facilitates understanding of the spatial relationship between the coronary veins and the LV function and may help targeted LV lead delivery.

Detection of Regional Mechanical Activation of the Left Ventricular Myocardium Using High Frame Rate Ultrasound Imaging.

We have investigated the feasibility of noninvasive mapping of mechanical activation patterns in the left ventricular (LV) myocardium using high frame rate ultrasound imaging for the purpose of detecting conduction abnormalities. Five anesthetized, open-chest dogs with implanted combined sonomicrometry and electromyography (EMG) crystals were studied. The animals were paced from the specified locations of the heart, while crystal and ultrasound data were acquired. Isochrone maps of the mechanical activation patterns were generated from the ultrasound data using a novel signal processing method called clutter filter wave imaging (CFWI). The isochrone maps showed the same mechanical activation pattern as the sonomicrometry crystals in 90% of the cases. For electrical activation, the activation sequences from ultrasound were the same in 92% of the cases. The coefficient of determination between the activation delay measured with EMG and ultrasound was R 2 = 0.79 , indicating a strong correlation. These results indicate that high frame rate ultrasound imaging processed with CFWI has the potential to be a valuable tool for mechanical activation detection.

Adaptive Color Gain for Vena Contracta Quantification in Valvular Regurgitation.

Severe valvular regurgitation can lead to pulmonary hypertension, atrial fibrillation and heart failure. Vena contracta width is used to estimate the severity of the regurgitation. Parameters affecting visualization of color Doppler have a significant impact on the measurement. We propose a data-driven method for automated adjustment of color gain based on the peak power of the color Doppler signal in the vicinity of the vena contracta. A linear regression model trained on the peak power was used to predict the orifice diameter. According to our study, the color gain should be set to about 6 dB above where color Doppler data completely disappears from the image. Based on our method, orifices with reference diameters of 4, 6.5 and 8.5 mm were estimated with relative diameter errors within 18%, 12% and 14%, respectively.

Estimation of myocardial work from pressure-strain loops analysis: an experimental evaluation.

Purpose: The area of left ventricular (LV) pressure-strain loop (PSL) is used as an index of regional myocardial work. The purpose of the present work is to compare the main segmental PSL markers and the derived global work indices, when they are calculated using an estimated pressure signal or an observed pressure signal. Methods and results: In nine patients implanted with a bi-ventricular pace-maker (CRT), LV pressure was invasively measured in five conditions: CRT-off, LV-pacing, right ventricular-pacing and two different CRT-pacing. For each condition, systolic blood pressure was measured by brachial artery cuff-pressure and transthoracic echocardiography loops were recorded simultaneously. The error and relative root mean square error (rRMSE) between measured and estimated pressure were calculated for each patient and each configuration. Correlation coefficient (R2) and Bland-Altman (BA) analysis were performed for PSL area and work indices. A total of 43 different haemodynamic conditions were compared (774 segmental PSL). The global rRMSE between estimated and measured LV-pressure was 12.3 mmHg. The estimated and measured segmental LV-PSL were strongly correlated, with an R2 of 0.98. BA analysis shows that the mean bias for the estimation of segmental LV-PSL area is 86.0 mmHg.%. A significant bias effect with linearly increasing error with pressure values is observed. R2 ≥ 0.88 and a mean bias in BA analysis ≤41.4 mmHg.% was observed for the estimation of global myocardial work indices. Conclusion: The non-invasive estimation for LV pressure-strain loop area and the global myocardial work indices obtained from LV-PSL strongly correlates with invasive measurements.

Method comparison for cardiac image registration of coronary computed tomography angiography and 3-D echocardiography.

Treatment decision for coronary artery disease (CAD) is based on both morphological and functional information. Image fusion of coronary computed tomography angiography (CCTA) and three-dimensional echocardiography (3DE) could combine morphology and function into a single image to facilitate diagnosis. Three semiautomatic feature-based methods for CCTA/3DE registration were implemented and applied on CAD patients. Methods were verified and compared using landmarks manually identified by a cardiologist. All methods were found feasible for CCTA/3DE fusion.

Role of myocardial constructive work in the identification of responders to CRT.

Aims: Cardiac resynchronization therapy (CRT) plays a pivotal role in the management of patients with heart failure (HF) and wide QRS complex. However, the treatment is plagued by numerous non-responders. Aim of the study is to evaluate the role myocardial work estimated by pressure-strain loops (PSLs) in the comprehension of physiological mechanisms associated with CRT and in the prediction of CRT response. Methods and results: Ninety-seven patients with symptomatic HF (ejection fraction: 27 ± 6%, QRS duration 164 ± 18 ms) undergoing CRT implantation according to current recommendations were retrospectively included in the study. Standard 2D and speckle tracking echocardiography were performed before CRT and at the 6-month follow-up (FU). PSL analysis allowed the calculation of global and regional myocardial constructive work (CW) and wasted work (WW). A > 15% reduction in left ventricular (LV) end-systolic volume at FU defined CRT-positive response (CRT-PR). At FU, 63 (65%) patients responded to CRT. Global CW (CWtot) was significantly increased in CRT-responders. At multivariate analysis, CWtot > 1057 mmHg% (OR 14.69, P = 0.005) and septal flash (OR 8.05, P = 0.004) were the only significant predictors of CRT-PR. CWtot was associated with the entity of CRT-induced myocardial remodelling in both ischaemic (r = -0.55, P < 0.0001) and non-ischaemic patients (r = 0.65, P < 0.0001). A CWtot < 1057 mmHg% identified 85% of non-responders with a positive predictive value of 88%. Conclusion: Patients with higher CWtot exhibit a favourable response to CRT. These data encourage further studies for the assessment of the myocardial substrate related to the functional response to CRT.

Value of Myocardial Work Estimation in the Prediction of Response to Cardiac Resynchronization Therapy.

BACKGROUND: Cardiac resynchronization therapy (CRT) in heart failure is plagued by too many nonresponders. The aim of the present study is to evaluate whether the estimation of myocardial performance by pressure-strain loops (PSLs) is useful for the selection of CRT candidates. METHODS: Ninety-seven patients undergoing CRT were included in the study. Bidimensional and speckle-tracking echocardiography were performed before CRT and at the 6-month follow-up (FU). Conventional dyssynchrony parameters were evaluated. Left ventricular (LV) constructive work (CW) and wasted work (WW) were estimated by PSLs. Positive response to CRT (CRT+) was defined as ≥15% reduction in LV end-systolic volume at FU and was observed in 63 (65%) patients. RESULTS: The addition of CW > 1,057 mm Hg% (area under the curve, 0.72, P < .0001) and WW > 384 mm  Hg% (area under the curve, 0.67, P = .005) to a baseline model including clinical, echocardiographic, and conventional dyssynchrony parameters significantly increased the model power (χ2, 25.11 vs 47.5, P < .0001). In this model, septal flash (odds ratio [OR] = 2.78; P = .001), CW > 1,057 mm Hg% (OR = 9.49; P = .002), and WW > 384 mm Hg% (OR = 16.24, P < .006) remained the only parameters associated with CRT+. The combination of CW > 1,057 mm Hg% and WW > 384 mm Hg% showed a good specificity (100%) and positive predictive value (100%) but a low sensitivity (22%), negative predictive value (41%), and accuracy (49%) for the identification of CRT+. CONCLUSIONS: The estimation of CW and WW by PSLs is a novel tool for the assessment of CRT patients. Although these parameters cannot be used by their own to select CRT candidates, they can provide further insights into the comprehension of dyssynchrony mechanisms and contribute to improving the identification of CRT responders.

Semiautomated biventricular segmentation in three-dimensional echocardiography by coupled deformable surfaces.

With the advancement of three-dimensional (3-D) real-time echocardiography in recent years, automatic creation of patient specific geometric models is becoming feasible and important in clinical decision making. However, the vast majority of echocardiographic segmentation methods presented in the literature focus on the left ventricle (LV) endocardial border, leaving segmentation of the right ventricle (RV) a largely unexplored problem, despite the increasing recognition of the RV's role in cardiovascular disease. We present a method for coupled segmentation of the endo- and epicardial borders of both the LV and RV in 3-D ultrasound images. To solve the segmentation problem, we propose an extension of a successful state-estimation segmentation framework with a geometrical representation of coupled surfaces, as well as the introduction of myocardial incompressibility to regularize the segmentation. The method was validated against manual measurements and segmentations in images of 16 patients. Mean absolute distances of [Formula: see text], [Formula: see text], and [Formula: see text] between the proposed and reference segmentations were observed for the LV endocardium, RV endocardium, and LV epicardium surfaces, respectively. The method was computationally efficient, with a computation time of [Formula: see text].

Temperature monitoring by channel data delays: Feasibility based on estimated delays magnitude for cardiac ablation.

Ultrasound thermometry is based on measuring tissue temperature by its impact on ultrasound wave propagation. This study focuses on the use of transducer array channel data (not beamformed) and examines how a layer of increased velocity (heat induced) affects the travel-times of the ultrasound backscatter signal. Based on geometric considerations, a new equation was derived for the change in time delay as a function of temperature change. The resulting expression provides insight into the key factors that link change in temperature to change in travel time. It shows that velocity enters in combination with heating geometry: complementary information is needed to compute velocity from the changes in travel time. Using the bio-heat equation as a second source of information in the derived expressions, the feasibility of monitoring the temperature increase during cardiac ablation therapy using channel data was investigated. For an intra-cardiac (ICE) probe, using this "time delay error approach" would not be feasible, while for a trans-esophageal array transducer (TEE) transducer it might be feasible.

Left atrial volumetric assessment using a novel automated framework for 3D echocardiography: a multi-centre analysis.

AIMS: This study aims at validating a software tool for automated segmentation and quantification of the left atrium (LA) from 3D echocardiography. METHODS AND RESULTS: The LA segmentation tool uses a dual-chamber model of the left side of the heart to automatically detect and track the atrio-ventricular plane and the LA endocardium in transthoracic 3D echocardiography. The tool was tested in a dataset of 121 ultrasound images from patients with several cardiovascular pathologies (in a multi-centre setting), and the resulting volumes were compared with those assessed manually by experts in a blinded analysis using conventional contouring. Bland-Altman analysis showed good agreement between the automated method and the manual references, with differences (mean ± 1.96 SD) of 0.5 ± 5.7 mL for LA minimum volume and -1.6 ± 9.7 mL for LA maximum volume (comparable to the inter-observer variability of manual tracings). The automated tool required no user interaction in 93% of the recordings, while 4% required a single click and only 2% required contour adjustments, reducing considerably the amount of time and effort required for LA volumetric analysis. CONCLUSION: The automated tool was validated in a multi-centre setting, providing quantification of the LA volume over the cardiac cycle with minimal user interaction. The results of the automated analysis were in agreement with those estimated manually by experts. This study shows that such approach has clinical utility for the assessment of the LA morphology and function, automating and facilitating the time-consuming task of analysing 3D echocardiographic recordings.