The European Union (EU) Medical Device Regulation increased regulatory scrutiny to improve the safety and performance of new medical devices. An equally important goal is providing timely access to innovative devices to benefit patient care. The European Society of Cardiology strongly advocates for the evolution of the Medical Device Regulation system to facilitate priority access for innovative devices for unmet needs and orphan cardiovascular (CV) medical devices in EU countries. Although device approval is currently executed by Notified Bodies in the EU, it will be advantageous in the mid-term to consider a single EU regulatory agency for devices. In the short term, steps can be taken to transform the current system into a more efficient, predictable, cost-effective, and user-friendly service. Key strategies include the following: enhancing predictability of the approval process through use of early scientific advice from regulators; establishing unique regulatory pathways for CV orphan, paediatric, and innovative devices; promoting more efficient (re)certification of essential legacy CV devices; improving transparency of sponsor interactions with Notified Bodies; expanding the roles of the Expert Panels to assist in the approval of CV devices; promoting global regulatory harmonization, considering streamlined authorization of CV medical technologies across selected jurisdictions; developing an efficient system to monitor device safety; and ensuring funding for data collection platforms. Some strategies that could help include considering a pilot programme for joint approval processes of selected devices in partnership with other regions (i.e. US Food and Drug Administration); developing priority pathways for accelerated access to innovative or orphan devices; and increasing recognition of the importance of early feasibility studies in the EU.

The morphology of the mitral annulus plays an important role in diagnosing and treating mitral valve disorders. Automated segmentation has the promise to be time-saving and improve consistency in clinical practice. In the past years, segmentation has been dominated by methods based on deep learning. Deep learning-based segmentation methods have shown good results, but their consistency and robustness are still subjects of active research. In this work, we introduce a method that combines Graph Convolutional Networks with a 3D CNN model to integrate an anatomical shape template for the predictions. Our method leverages the feature extraction capability of CNN models to provide input features to the graph neural networks. The proposed method leverages strengths from a shape model approach with the strengths of deep learning. Further, we propose loss functions for the CNN designed to guide the graph model training. The CNN was trained with transfer learning, using a limited number of labeled transesophageal echocardiography volumes to adapt to the mitral annulus segmentation task. When comparing the segmentation of the mitral annulus achieved by the proposed method with the test set annotations, the method showed a high degree of accuracy, achieving a curve-to-curve error of 2.00 ± 0.81 mm and a relative perimeter error of 4.42 ± 3.33

BackgroundSpeckle tracking echocardiography (STE) provides quantification of left ventricular (LV) deformation and is useful in the assessment of LV function. STE is increasingly being used clinically, and every effort to simplify and standardize STE is important. Manual outlining of regions of interest (ROIs) is labor intensive and may influence assessment of strain values.PurposeWe hypothesized that a deep learning (DL) model, trained on clinical echocardiographic exams, can be combined with a readily available echocardiographic analysis software, to automate strain calculation with comparable fidelity to trained cardiologists.MethodsData consisted of still frame echocardiographic images with cardiologist-defined ROIs from 672 clinical echocardiographic exams from a university hospital outpatient clinic. Exams included patients with ischemic heart disease, heart failure, valvular disease, and conduction abnormalities, and some healthy subjects. An EfficientNetB1-based architecture was employed, and different techniques and properties including data set size, data quality, augmentations, and transfer learning were evaluated. DL predicted ROIs were reintroduced into commercially available echocardiographic analysis software to automatically calculate strain values.ResultsDL-automated strain calculations had an average absolute difference of 0.75 (95% CI 0.58-0.92) for global longitudinal strain (GLS), and 1.16 (95% CI 1.03-1.29) for single-projection longitudinal strain (LS), compared to operators. A Bland-Altman plot revealed no obvious bias, though there were fewer outliers in the lower average LS ranges. Techniques and data properties yielded no significant increase/decrease in performance.ConclusionThe study demonstrates that DL-assisted, automated strain measurements are feasible, and provide results within interobserver variation. Employing DL in echocardiographic analyses could further facilitate adoption of STE parameters in clinical practice and research, and improve reproducibility.

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.

BackgroundMeasurement 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.MethodsData 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.ResultsThe 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.ConclusionDL 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.

Echocardiographic analysis of cardiac chamber volumes throughout the heart cycle is important to assess left- and right-heart function. We have developed and validated a method to simultaneously segment all four heart chambers in 3D echocardiography cine loops. We described the heart using several Doo Sabin models, one for each chamber and one for the pericardium. The model was fitted to 3D echo images using edge detection and a Kalman filter. The average signed error in estimating volume across all chambers was -1.0 +/- +/- 12.3 ml. These results show that the model slightly underestimates the volumes. Average signed error for the ejection fraction was -3.2 +/- 7.4 pts, with the highest error being the right atrium. This all-chamber automatic segmentation method provides high accuracy and may have utility in understanding chamber interactions.

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.

Segmentation of the mitral annulus is often an important step in cardiac examinations. We propose a robust 3D method for predicting the anatomical orientation and segmentation of the mitral annulus in 3D transesophageal echocardiography. The method takes advantage of the circular anatomy of the annulus by utilizing cylinder coordinate samples and a 3D convolutional neural network with circular convolutions. Furthermore, the paper proposes new landmark detection loss functions based on the earth mover’s distance. The method’s effectiveness was demonstrated by training a HighRes3dNet model and evaluating its performance on a separate test set consisting of 135 frames from 19 examinations. The obtained coordinate prediction error was 1.96± 1.62 mm, and the anatomical orientation prediction error was 9.7° ± 15.8°. The robust and fully automatic mitral annulus segmentation and orientation prediction provided by the method can ease the workload of clinicians and provide time savings in clinics.

Echocardiography serves as a gold standard for diagnostic imaging in cardiovascular disease since it is non-intrusive, minimally invasive, and affordable. Recent advancements in deep learning techniques allowed the practical application of computer-assisted echocardiography imaging analysis, such as view classification, image segmentation, and disease diagnosis. However, unlike the more commonly investigated brightness (B-mode) imaging, there is limited research and open-source tools for the automatic processing of color Doppler echocardiography imaging (CDI) due to its more specific application and more heterogeneous image features (color flow overlaid on brightness images). Thus in this work, we developed a general framework to perform view classification of the Doppler echocardiography by leveraging the existing view classification algorithms (e.g., EchoCV) on B-mode imaging. Specifically, we developed a deep feature embedding-based module to automatically align CDI and B-mode videos based on the distance between their low-dimensional embedding. The proposed framework was evaluated on a dataset consisting of 250 subjects with ground-truth view labels by human annotators.

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.

Abstract Background Speckle tracking echocardiography provides quantification of myocardial deformation and is useful in the assessment of myocardial function. Right ventricular (RV) strain has been suggested as a sensitive tool for diagnosing cardiomyopathies and assessing long term patient outcomes for patients with pulmonary hypertension, severe tricuspid regurgitation and COVID-19 infection. Recent advances in deep learning (DL) have made promising advances in automating the labour-intensive delineation of regions of interest (ROIs). However, compared to echocardiograms with left ventricular (LV) strain, RV strain data is scarce, making DL models difficult to train. Purpose To investigate whether annotated LV strain data could be beneficial in training a DL model for automatic RV strain when using a limited RV dataset. Methods The dataset consisted of anonymized still frames from 141 echocardiograms of the RV in the RV-focused 4 chamber view with corresponding cardiologist-defined ROI. Exams included healthy subjects and patients with heart failure, valvular disease, and conduction abnormalities. ROIs and still images were extracted at the mid-systole, and then quality assessed by an experienced cardiologist as high, medium, or low. The dataset was randomly split into 68%/17%/15% sets for training, validation, and testing. A convolutional neural network for image segmentation (U-Net) with a residual neural network (ResNet50) encoder was used, with a combination of binary cross entropy and Dice loss functions. Augmentation, predefined ImageNet weights and pre-training were also employed. For pre-training, 715 still images in the apical 4 chamber view with LV defined ROIs were used, both in their original and horizontally flipped view. Predicted ROIs were reintroduced into commercially available echocardiogram analysis software to automatically calculate longitudinal strain (LS) values. Results The model pre-trained with the flipped LV images achieved the highest performance with a mean absolute difference of 1.26 percentage points (95% confidence interval (CI): 0.62–1.89 percentage points) between manually measured and DL-assisted LS. Median absolute LS difference was 0.85 (95% CI: 0.28–1.57) percentage points. A Bland-Altman plot revealed two outliers and no obvious trends. In comparison, the mean and median absolute LS differences for the model without pre-training were 1.87 (95% CI: 0.73–3.00) and 1.09 (95% CI: 0.56–1.63) percentage points, respectively. Conclusions The current study demonstrates that DL-assisted, automated RV strain measurement is feasible even with a small dataset, and that performance can be increased by using images annotated for LV strain. While the majority of the predicted RV strain results were within the typical range of intra- and interobserver variability, a few outliers were observed. These outliers could possibly be avoided with the use of larger datasets. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Research council of Norway

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.

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Research Council of Norway Speckle tracking echocardiography (STE) provides quantification of left ventricular (LV) deformation and is useful in the assessment of LV function. STE is increasingly being used clinically, and every effort to simplify and standardise STE is important. Manual outlining of regions of interest (ROIs) is labour intensive and may influence assessment of strain values. We hypothesised that ROIs from clinical echocardiographic exams could be used to train a deep learning (DL) model which could automate strain calculation by predicting ROIs with comparable fidelity to trained cardiologists. Data consisted of still frames with cardiologist-defined ROIs from 435 clinical echocardiographic exams from a university hospital outpatient clinic. Exams included healthy subjects and patients with ischemic heart disease, heart failure, valvular disease and conduction abnormalities. Three frames surrounding mid-systole from standard apical views were paired with the mid-systolic ROI for training. Image quality was classified as high, medium or low by an experienced cardiologist prior to model training, and low quality images were excluded. The dataset was randomly split into 68%/17%/15% sets for training, validation and testing. A standard Unet architecture was used, with a combination of binary cross entropy and Dice loss functions. A total of 1025 images were used for final model training and testing, with augmentation used to extend the dataset. Predicted ROIs were reintroduced into commercially available echocardiographic analysis software to automatically calculate longitudinal strain (LS) values. The average absolute difference between manually measured and DL-assisted LS was 0.98 percentage points (95% confidence interval 0.82-1.13) for the final model. A Bland-Altman plot revealed very few outliers and no bias in the difference between manual and DL-assisted strain measurements. The current study demonstrates that DL-assisted, automated strain measurement is feasible, and provides strain results within an acceptable range of intra- and interobserver variation. Employing DL in echocardiographic analysis could further facilitate adoption of STE parameters in clinical practice and research, and improve reproducibility. Abstract Figure. Bland-Altman plot. Manual and DL ROIs

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.11https://adgilbert.github.io/data-generation/.

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.

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.

Accurate modelling of the right ventricle of the human heart is important for both diagnosis and treatment planning. The right ventricle (RV) has a compound convex-concave shape with several sharp edges. While the RV has previously been modeled using the Doo-Sabin method, these models require several extra control nodes to accurately reproduce the relatively sharp edges. The current paper proposes a modified Doo-Sabin method which introduces weighting of vertices and edges rather than extra nodes to control sharpness. This work compares standard vs sharp Doo-Sabin models on modeling the RV from 16 3D ultrasound scans, compared to a ground truth mesh model manually drawn by a cardiologist. The modified, sharp Doo-Sabin method came closer to the ground truth RV model in 11 out of 16 cases and on average showed an 11.54 % improvement.

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.

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.

Noninvasive left ventricular (LV) myocardial work (MW) is a novel LV function parameter. It overcomes the load dependency of LV ejection fraction (LVEF) and LV strain by incorporating afterload. LVMW can be quantified noninvasively by integrating speckle tracking strain echocardiography and