Search

Introduction Left atrial (LA) size is a dynamic variable that changes during stress echocardiography (SE) and provides valuable information within and beyond coronary artery disease. However, its measurement remains subjective, time-consuming and based on manual tracings. Recent advances in deep learning might save analysis time and deflate variability by removing the subjectivity of LA assessment. Purpose In this proof of principle study we aim to validate the potential of an automated machine learning system for the evaluation of LA in SE. Methods From the image data bank of Stress Echo 2030 study, we selected 20 consecutive patients who underwent SE (using a variety of stress methods) in 2 recruiting centers. Imaging data was acquired in DICOM format and anonymized. The studies were reviewed by an expert cardiologist trained in SE evaluation who selected apical four chamber (A4Ch) view images during stress and rest phases and marked end-systolic (ES) and end-diastolic frames to be used in further evaluation. Endocardial borders for LA were traced in ES. The tracings were repeated by three different evaluators (expert cardiologist [C1], cardiologist from external center [C2] and a machine learning [ML] model – a convolutional neural network trained on an unrelated set of images). LA area (LAA), volume (LAV) using area-length formula and proportional LAV changes between stress and rest (ΔLAV = [rest − stress] / rest) were calculated. Each evaluator was blinded from each other's measurements. Results In total, 40 A4Ch images were acquired (20 at rest and 20 at stress) of which all were of sufficient quality for performing LA measurements using an automated system. Pearson correlation coefficients (R) for LAA were 0.95 (C1-ML), 0.96 (C2-ML) at rest and 0.88 (C1-ML), 0.79 (C2-ML) at stress. The C1-C2 pair had R of 0.98 and 0.86 for LAA at rest and stress. LAV also showed good correlation between different raters with R values of 0.90 (C1-ML), 0.94 (C2-ML), 0.94 (C1-C2) at rest and 0.86 (C1-ML), 0.87 (C2-ML), 0.84 (C1-C2) at stress. Root mean squared errors (RMSEs) for LAV were 13.48 ml (C1-ML), 7.44 ml (C2-ML), 10.26 ml (C1-C2) at rest and 14.03 ml (C1-ML), 8.53 ml (C2-ML), 13.69 ml (C1-C2) at stress. There were high level correlations between all raters for ΔLAV with R values of 0.93, 0.94 and 0.95 for C1-ML, C2-ML and C1-C2 pairs respectively. Mean (95% CI) ΔLAV values were −20.1 (−51.59 to +11.39), −14.95 (−43.77 to +13.87) and −14.37 (−34.46 to +5.72) for ML, C1 and C2. Comparison with one-way ANOVA did not show significant differences in mean ΔLAV values between operators (p=0.94). Conclusions Automated ML based system produces LA measurements that are comparable to human operators and can reduce the need for manual tracing. There was a tendency for all operators to have lower levels of agreement in stress images compared to rest, further showing the need for additional standardization of SE evaluation for machine and human operators. Funding Acknowledgement Type of funding sources: None.

BackgroundConsumer smartwatches have gained attention as mobile health (mHealth) tools able to detect atrial fibrillation (AF) using photoplethysmography (PPG) or a short strip of electrocardiogram (ECG). PPG has limited accuracy due to the movement artifacts, whereas ECG cannot be used continuously, is usually displayed as a single-lead signal and is limited in asymptomatic cases.ObjectiveDoubleCheck-AF is a validation study of a wrist-worn device dedicated to providing both continuous PPG-based rhythm monitoring and instant 6-lead ECG with no wires. We evaluated its ability to differentiate between AF and sinus rhythm (SR) with particular emphasis on the challenge of frequent premature beats.Methods and ResultsWe performed a prospective, non-randomized study of 344 participants including 121 patients in AF. To challenge the specificity of the device two control groups were selected: 95 patients in stable SR and 128 patients in SR with frequent premature ventricular or atrial contractions (PVCs/PACs). All ECG tracings were labeled by two independent diagnosis-blinded cardiologists as “AF,” “SR” or “Cannot be concluded.” In case of disagreement, a third cardiologist was consulted. A simultaneously recorded ECG of Holter monitor served as a reference. It revealed a high burden of ectopy in the corresponding control group: 6.2 PVCs/PACs per minute, bigeminy/trigeminy episodes in 24.2% (31/128) and runs of ≥3 beats in 9.4% (12/128) of patients. AF detection with PPG-based algorithm, ECG of the wearable and combination of both yielded sensitivity and specificity of 94.2 and 96.9%; 99.2 and 99.1%; 94.2 and 99.6%, respectively. All seven false-positive PPG-based cases were from the frequent PVCs/PACs group compared to none from the stable SR group (P < 0.001). In the majority of these cases (6/7) cardiologists were able to correct the diagnosis to SR with the help of the ECG of the device (P = 0.012).ConclusionsThis is the first wearable combining PPG-based AF detection algorithm for screening of AF together with an instant 6-lead ECG with no wires for manual rhythm confirmation. The system maintained high specificity despite a remarkable amount of frequent single or multiple premature contractions.

With stress echo (SE) 2020 study, a new standard of practice in stress imaging was developed and disseminated: the ABCDE protocol for functional testing within and beyond CAD. ABCDE protocol was the fruit of SE 2020, and is the seed of SE 2030, which is articulated in 12 projects: 1-SE in coronary artery disease (SECAD), 2-SE in diastolic heart failure (SEDIA), 3-SE in hypertrophic cardiomyopathy (SEHCA), 4-SE post-chest radiotherapy and chemotherapy (SERA), 5-Artificial intelligence SE evaluation (AI-SEE), 6-Environmental stress echocardiography and air pollution (ESTER), 7-SE in repaired Tetralogy of Fallot (SETOF), 8-SE in post-COVID-19 (SECOV), 9: Recovery by stress echo of conventionally unfit donor good hearts (RESURGE), 10-SE for mitral ischemic regurgitation (SEMIR), 11-SE in valvular heart disease (SEVA), 12-SE for coronary vasospasm (SESPASM). The study aims to recruit in the next 5 years (2021–2025) ≥10,000 patients followed for ≥5 years (up to 2030) from ≥20 quality-controlled laboratories from ≥10 countries. In this COVID-19 era of sustainable health care delivery, SE2030 will provide the evidence to finally recommend SE as the optimal and versatile imaging modality for functional testing anywhere, any time, and in any patient.

Objective: Left ventricle (LV) geometry and dyssynchrony are associated with LV remodeling after acute myocardial infarction (AMI). The aim of this prospective study was to assess the diagnostic value of new three-dimensional echocardiography (3DE) parameters [sphericity (SI) and systolic dyssynchrony indexes (SDI)] for the prediction of LV remodeling after AMI and to compare them with two-dimensional echocardiography (2DE) parameters. Methods: 2DE and 3DE were performed in 75 patients with AMI within 3 days from the onset of MI and 6 months later. LV remodeling was defined as a ≥15% increase in the LV end-diastolic volume (EDV) at follow-up. 3D SI was calculated by dividing EDV by the volume of a sphere whose diameter was derived from the major end-diastolic LV long axis. SDI was considered as a standard deviation of the time from cardiac cycle onset to minimum systolic volume in 16 LV segments. Results: LV remodeling was identified in 34 (45%) patients using the 2DE method and in 22 (29%) patients using the 3DE method. Evaluated 3DE parameters, such as EDV [area under the receiver operating characteristic (ROC) curve (AUC) 0.742, sensitivity 71%, specificity 79%], end-systolic volume (AUC 0.729, sensitivity 69%, specificity 78%), SDI (AUC 0.777, sensitivity 73%, specificity 77%), and SI, had significant prognostic value for LV remodeling. According to the AUC, the highest predictive value had 3D SI (AUC 0.957, sensitivity 90%, specificity 91%). Conclusion: 3DE parameters, especially 3D SI and SDI, play important roles in the prediction of LV remodeling after AMI and can be used in clinical practice.

Funding Acknowledgements Type of funding sources: None. INTRODUCTION Deep learning (DL) has been successfully applied in the automated assessment of some transthoracic echocardiography (TTE) parameters such as left-ventricular ejection fraction. Nevertheless, automation of the right-sided heart assessment has not been widely studied, partially due to the relative difficulty involved in some of the right-sided heart measurement evaluation and time constraints in routine practice. Here we have explored the feasibility of a DL-based system capable of performing different tasks involved in the right-sided heart functional and geometric evaluation. PURPOSE To develop a DL-based system assessing right atrium (RA) and right ventricle (RV) functional and geometric parameters and compare its accuracy to board-certified cardiologists. METHODS A total of 2,014 frames from 349 patients (with various indications for TTE) were used to train and validate four convolutional neural networks (CNNs) to perform either segmentation or landmark detection across four different TTE views: apical four-chamber (A4Ch), parasternal long-axis (PLAX), M-mode of tricuspid annulus and tissue Doppler imaging (TDI) of the right ventricular lateral wall. The CNNs were optimised to perform different right-sided heart measurements, namely, right atrial area in end-systole (RAA) and fractional area change (FAC) of RV in A4Ch view, proximal right ventricular outflow tract diameter (pRVOT) in PLAX view, tricuspid annular plane systolic excursion (TAPSE) in M-mode and S’ in TDI. Model performance was compared with two board-certified cardiologists using their average measurements on 20 test set patients. RESULTS CNN predicted pRVOT diameter with a mean absolute error (MAE) of 1.02 mm and root mean squared error (RMSE) of 3.08 mm. The intersection over union (IoU) for the segmentation of RV and RA was 0.89 and 0.87, respectively. We then used RV and RA segmentation predictions to calculate additional parameters which resulted in RMSE of 8.34% for FAC and 4.93cm2 for RAA. In the M-mode and TDI, the model achieved RMSE of 4.48 mm and 0.84 cm/s for the detection of TAPSE and S’, respectively. CONCLUSIONS We have demonstrated the feasibility of a DL-based system performing different measurements involved in right-sided heart evaluation. In a routine practice, where limited time resources might be available, such could assist in the thorough assessment of the right-sided heart geometry and function. Additional studies using cardiac magnetic resonance imaging to establish more precise accuracy of such systems is needed.

Introduction Deep convolutional neural networks (CNNs) have been shown to be reliable in evaluating geometrically assessed systolic heart function, however, studies evaluating diastolic heart function, which reflects hemodynamic status, are scarce. This study presents a novel CNNs approach for recognition and evaluation of different diastolic left ventricular (LV) function measurements. Purpose To create a new CNNs approach in the assessment of LV diastolic function and compare the results with clinicians' measurements. Methods A total of 4586 2D echocardiographic images were extracted from the studies of 330 patients referred with varying indications. The ensemble of four CNNs was trained (80/20% training/validation patient split) for the assessment of transmitral inflow (E and A wave peak velocities), mitral septal and lateral annular velocities (e'), tricuspid regurgitation systolic velocity (Vmax) and detection the left atrial endocardium in apical four-chamber views. Additionally, E/A ratio, average E/e' ratio and left atrial volume index (LAVi) values were calculated for the evaluation of diastolic dysfunction according to the 2016 ASE/EACVI recommendations. CNNs performance in detecting diastolic dysfunction was compared to expert cardiologists on a set of 20 separate cases. Results Study results on the validation data showed that CNNs accurately predicted peak E/A ratio, average E/e' ratio (R2=0.88 and R2=0.89, respectively) and tricuspid regurgitation Vmax (R2=0.82). Figure 1 illustrates different functional LV measurements among the obtained echocardiographic images. Regarding the geometrical assessment of diastolic function, the segmentation model traced the left atrial endocardial border (intersection over union = 0.94) and subsequently was used in predicting the LAVi (R2=0.92). The ensemble of four CNNs had the area under the ROC curve of 0.93 for the detection of diastolic dysfunction when compared to expert cardiologists. Conclusion Deep CNNs demonstrate the capacity to detect peak velocities across different Doppler imaging modes and delineate left atrial endocardium border while using a relatively small dataset. Combining multiple CNNs has the potential of performing an accurate assessment of the diastolic LV function. Funding Acknowledgement Type of funding source: None

INTRODUCTION Deep learning (DL) has been of increasing use in the field of echocardiographic cardiology. The importance of segmentation and recognition of different heart chambers was already presented in different studies. However, there are no studies made regarding the functional heart measurements. Even though, functional measurements of right ventricle (RV) remains "dark side of the moon", no doubtfully severity of RV dysfunction influences the worse outcomes. PURPOSE To evaluate DL for recognition of geometrical features of RV and measurement of RV fractional area change (FAC). METHODS A total of 896 end-systolic and end-diastolic frames from 129 patients (with various indications for the study) were used to train and validate the neural networks. Raw pixel data was extracted from EPIQ 7G (Philips) imaging platform. All of the images were from 2D echocardiography apical four chamber views. RV was annotated in each image, with 1716 images used for training and 180 for validation. We used the state of art mask regional convolutional neural network (MR-CNN) and attention U-net convolutional neural network models for the RV segmentation task. Intersection over Union (IoU) was used as the primary metric for model evaluation. IoU measures the number of pixels common between the target and the prediction masks divided by the total number of pixels present across both masks. Additionally FAC was calculated using frames with minimal and maximal segmented area by the network. RESULTS U-Net architecture demonstrated considerably faster training compared to MR-CNN with time per training step of 85 ms and 750 ms for U-Net and MR-CNN, respectively (p CONCLUSION With small dataset deep learning give us ability to recognize RV and measure RV FAC in apical four chamber view with high accuracy. This method offers assessment of RV to become daily used in the cardiologist practice, moreover, in the near future automated measurements will allow to reduce the need of observer manual evaluation. Improvements can be made in FAC calculation by also improving techniques for end-systolic and end-diastolic frame detection.

Background: The main goal of this manuscript was to evaluate the diagnostic value of the global and regional postsystolic shortening (PSS) parameters, assessed by two-dimensional (2D) speckle-tracking echocardiography, at rest and during dobutamine stress for the detection of functionally significant coronary artery stenoses in patients with moderate pretest probability of stable coronary artery disease (CAD). Methods: Dobutamine stress echocardiography (DSE) and adenosine stress myocardial perfusion imaging by cardiac magnetic resonance (CMR-MPI) were performed on 83 patients with moderate pretest probability of stable CAD and left ventricle ejection fraction ≥55%. CAD was defined as ≥50% diameter stenoses on invasive coronary artery angiography (CAA) validated as hemodynamically significant by CMR-MPI. According to invasive CAA and CMR-MPI results, patients were divided into two groups: Nonpathologic CAD (−) group: 38 (45.8%) and pathologic CAD (+) group: 45 (54.2%). Results: There were no significant differences in clinical characteristics, conventional 2D echocardiography between the two groups at rest and during low dobutamine dose. Regional postsystolic index (PSI) during recovery phase had the highest area under the receiver operating characteristic curve (AUC) (AUC 0.882, sensitivity 87%, specificity 92%) for the detection of functionally significant one-vessel disease. During high dobutamine dose, regional PSI had sensitivity 78% and specificity 81% (AUC 0.78) to detect significant CAD. Regional PSI remained the same tendency remains for the detection of multiple-vessel CAD. Other myocardial deformation parameters were less sensitive and specific during high dobutamine dose and recovery phase. Conclusions: PSS parameters showed to be sensitive and specific in detecting hemodynamically significant coronary artery stenosis in patients with stable CAD with moderate pretest probability. The study revealed that the assessment of regional PSI performed during recovery improves the diagnostic accuracy of DSE for the detection of functionally significant CAD.

Introduction The growth of artificial intelligence (AI) use in echocardiography over the past years has been exponential, proposing new paths to overcome inter-operator variability and experience of the operator. Even though the applications of AI are still in their infancy within the field of echocardiography, the potential of AI implies future directions and is eager to assist for accuracy and efficiency of manual tracings. Deep learning, a subset of machine learning algorithms, is gaining popularity in echocardiography as a state of the art in visual data analysis. Purpose To evaluate deep learning for two initial tasks in automated cardiac measurements: view recognition and end-systolic (ES) and end-diastolic (ED) frame detection. Methods A total of 230 patients' (with various indications for study) 2D echocardiography data was used to train and validate neural networks. Raw pixel data was extracted from EPIQ 7G, Vivid E95 and Vivid 7 imaging platforms. Images were labeled according to their view: parasternal long axis (PLA), basal short axis, short axis at mitral level, apical two, three and four chambers (A4C). Additionally, ES and ED frames were labeled for A4C and PLA views. Images were de-identified by applying black pixel masks to non-anatomical data and removing metadata. Convolutional Neural Network (CNN) architecture was used for the classification of 6 different views. A total of 34752 and 3972 (5792 and 662 per view) frames were used to train and validate the network, respectively. Long-term Recurrent Convolutional Network (LRCN) combining temporal and spatial cognition was used for ES and ED frame detection. A total of 195 and 35 sequences with a length of 92 frames were used to train the LRCN. Results CNN for view classification had an AUC of 0.95 (sensitivity 95%, specificity 97%). Accuracy was lower for visually similar views, namely apical three-chamber and apical two-chamber. Training for ES and ED detection was achieved when training LRCN for regression instead of classification of each frame. LRCN for cardiac cycle evaluation had an average Framed Difference (aFD) of 2.31 (SD±2.15) for ED and 1.97 (SD±2.04) frames for ES detection which corresponds to error rate of about 0.04 s. Conclusion Determining echocardiographic view and evaluating cardiac cycle are the first steps in automating cardiac measurements. We have demonstrated the potential of two deep learning algorithms in accomplishing these tasks. Initial results are promising for the development of neural networks for cardiac segmentation and measuring of anatomical structures.

Background The aim of this prospective study was to assess the usefulness of global longitudinal strain (GLS), regional diastolic and systolic strain, strain rate (SR) parameters at rest and during dobutamine stress echocardiography for detecting significant coronary artery stenosis in patients with a moderate or high probability of coronary artery disease (CAD). Methods Dobutamine stress echocardiography and adenosine magnetic resonance imaging (AMRI) were performed on 127 patients with a moderate and high probability of CAD and left ventricle ejection fraction ≥55%. CAD was defined as ≥70% diameter stenosis on coronary angiography validated as hemodynamically significant by AMRI. Patients were grouped according to coronary angiography and AMRI results: CAD (−) n=67 (52.8%) vs CAD (+) n=60 (47.2%). Results There were no significant differences of clinical characteristics, conventional echocardiography, and deformation parameters between the two groups at rest except that GLS was higher in the CAD (−) group (−21.5±2.4% vs −16.2±2.1%, P=.00). GLS at high dobutamine doses had the highest area under the ROC curve (AUC) (AUC 0.955, sensitivity 94%, specificity 92%). Radial late diastolic SR at low doses performed best out of all diastolic parameters with an AUC of 0.789, sensitivity 76.7%, specificity 91.7%. Other deformation parameters including visual assessment were inferior. Conclusions Global longitudinal strain is highly sensitive and specific in detecting hemodynamically significant coronary artery stenosis in moderate- to high-risk patients without known CAD. This is the first study showing that GLS is more sensitive and specific compared with early and late diastolic SR parameters or visual assessment in detecting CAD.

Introduction: Value of longitudinal strain and strain rate (SR) at rest and low dobutamine doses has been shown in small studies however little is known about circumferential strain, circumferential systolic and diastolic SR importance in early stages of dobutamine speckle tracking echocardiography (STE). Hypothesis: Hypothesis that circumferential strain, circumferential systolic and diastolic SR in early stages of dobutamine STE are markers of significant coronary stenosis in patients with moderate and high probability of coronary artery disease (CAD) was assessed. Methods: Dobutamine stress echocardiography and adenosine magnetic resonance imaging were perfomed to 101 patients with moderate and high probability of CAD. CAD was defined as ≥50% diameter stenosis on coronary angiography validated as hemodynamically significant by adenosine magnetic resonance. Patients were divided into two groups based on coronary angiography results: CAD (-) n=57 (56,44%) vs CAD (+) n=44 (43,56%). Circumferential strain, circumeferential systolic and early diastolic SR parameters at rest, low and high dobutamine doses were analysed using 2D STE. Results and Conclusions: There were no significant differences of clinical characteristics, conventional echocardiography and deformation parameters between the groups at rest. All analysed STE parameters at low dobutamine doses were significantly lower in patients wtih CAD (circumferential strain 23,84±7,25% vs 17,98±4,06%, p=0,01, circumferential systolic SR 2,70±0,74 s–1 vs 1,76±0,75 s–1, p=0,002; circumferential early diastolic SR 2,71±0,74 s–1 vs 1,76±0,75 s–1, p=0,002). Logistic regression analysis revealed that STE parameters at low dobutamine doses have significant predictive value for haemodinamically significant coronary stenoses. Circumferential strain, systolic and early diastolic SR obtained at low dobutamine doses are sensitive and specific markers of haemodynamically significant CAD.

Concern over biological invasions has drawn increased attention to the impacts of introduced predators or competitors, but not to the importance of introduced prey. North American forests are rich in introduced invertebrates, including species that represent relatively novel taxonomic or trophic guilds and show biased distributions among forest types. We analysed the diets of red-backed salamanders, Plethodon cinereus, from three upland and three lowland forests to determine whether introduced prey are important contributors to geographical or temporal variation in salamander food resources. We found several introduced species were volumetrically important salamander prey, and were responsible for resource differences between forest types and much of the seasonal fluctuation in food resources in both forest types. In lowland forests, rain had a stronger effect on salamander predation on non-native earthworms than native taxa, creating more dynamic resource fluctuations in resource levels than was observed in upland forests where earthworms were absent. With one exception, predation on non-native species was positively associated with predation on native species, suggesting non-native prey have added to salamander resources rather than replaced salamander predation on native taxa. We hypothesize that the novel resource gradients created by non-native prey introductions are contributing to patterns of geographical and temporal phenotypic variation among salamander populations.

Using a laboratory experiment, we tested the hypothesis that faecal inspection and squashing behaviours by female red-backed salamanders, Plethodon cinereus, function in a context other than mate assessment, in this case foraging. Because only female P. cinereus squash faecal pellets, other studies have hypothesized that the faecal squashing is a mate assessment behaviour. During the courtship season, we exposed gravid female P. cinereus maintained on a ‘high-quality’ or ‘low-quality’ diet, to the faecal pellets of male and female conspecifics fed ‘high-quality’ diets. Female diet had no effect on activity level, and, overall, P. cinereus showed greater interest in male-marked substrates than female-marked substrates. However, female diet had a large effect on faecal inspection and squashing behaviours, and females showed similar inspection and squashing rates towards both male and female faecal pellets. These results suggest that faecal squashing does not function primarily in mate assessment, but rather as a means for female P. cinereus to gain information about prey availability. We propose that male P. cinereus have evolved to exploit female faecal inspection and squashing behaviours (sensory exploitation) to attract foraging females into areas to increase male encounter rates with females.