Automated Recognition of Regional Wall Motion Abnormalities Through Deep Neural Network Interpretation of Transthoracic Echocardiography

Deep learning supported echocardiogram analysis: A comprehensive review

An echocardiogram is a sophisticated ultrasound imaging technique employed to diagnose heart conditions. The transthoracic echocardiogram, one of the most prevalent types, is instrumental in evaluating significant cardiac diseases. However, interpreting its results heavily relies on the clinician's expertise. In this context, artificial intelligence has emerged as a vital tool for helping clinicians. This study critically analyzes key state-of-the-art research that uses deep learning techniques to automate transthoracic echocardiogram analysis and support clinical judgments. We have systematically organized and categorized articles that proffer solutions for view classification, enhancement of image quality and dataset, segmentation and identification of cardiac structures, detection of cardiac function abnormalities, and quantification of cardiac functions. We compared the performance of various deep learning approaches within each category, identifying the most promising methods. Additionally, we highlight limitations in current research and explore promising avenues for future exploration. These include addressing generalizability issues, incorporating novel AI approaches, and tackling the analysis of rare cardiac diseases.

Echocardiographic Detection of Regional Wall Motion Abnormalities Using Artificial Intelligence Compared to Human Readers

BACKGROUND

Although regional wall motion abnormality (RWMA) detection is foundational to transthoracic echocardiography, current methods are prone to interobserver variability. We aimed to develop a deep learning (DL) model for RWMA assessment and compare it to expert and novice readers.

METHODS

We used 15,746 transthoracic echocardiography studies-including 25,529 apical videos-which were split into training, validation, and test datasets. A convolutional neural network was trained and validated using apical 2-, 3-, and 4-chamber videos to predict the presence of RWMA in 7 regions defined by coronary perfusion territories, using the ground truth derived from clinical transthoracic echocardiography reports. Within the test cohort, DL model accuracy was compared to 6 expert and 3 novice readers using F1 score evaluation, with the ground truth of RWMA defined by expert readers. Significance between the DL model and novices was assessed using the permutation test.

RESULTS

Within the test cohort, the DL model accurately identified any RWMA with an area under the curve of 0.96 (0.92-0.98). The mean F1 scores of the experts and the DL model were numerically similar for 6 of 7 regions: anterior (86 vs 84), anterolateral (80 vs 74), inferolateral (83 vs 87), inferoseptal (86 vs 86), apical (88 vs 87), inferior (79 vs 81), and any RWMA (90 vs 94), respectively, while in the anteroseptal region, the F1 score of the DL model was lower than the experts (75 vs 89). Using F1 scores, the DL model outperformed both novices 1 (P = .002) and 2 (P = .02) for the detection of any RWMA.

CONCLUSIONS

Deep learning provides accurate detection of RWMA, which was comparable to experts and outperformed a majority of novices. Deep learning may improve the efficiency of RWMA assessment and serve as a teaching tool for novices.

Deep learning from latent spatiotemporal information of the heart: Identifying advanced bioimaging markers from echocardiograms

A key strength of echocardiography lies in its integration of comprehensive spatiotemporal cardiac imaging data in real-time, to aid frontline or bedside patient risk stratification and management. Nonetheless, its acquisition, processing, and interpretation are known to all be subject to heterogeneity from its reliance on manual and subjective human tracings, which challenges workflow and protocol standardization and final interpretation accuracy. In the era of advanced computational power, utilization of machine learning algorithms for big data analytics in echocardiography promises reduction in cost, cognitive errors, and intra- and inter-observer variability. Novel spatiotemporal deep learning (DL) models allow the integration of temporal arm information based on unlabeled pixel echocardiographic data for convolution of an adaptive semantic spatiotemporal calibration to construct personalized 4D heart meshes, assess global and regional cardiac function, detect early valve pathology, and differentiate uncommon cardiovascular disorders. Meanwhile, data visualization on spatiotemporal DL prediction models helps extract latent temporal imaging features to develop advanced imaging biomarkers in early disease stages and advance our understanding of pathophysiology to support the development of personalized prevention or treatment strategies. Since portable echocardiograms have been increasingly used as point-of-care imaging tools to aid rural care delivery, the application of these new spatiotemporal DL techniques show the potentials in streamlining echocardiographic acquisition, processing, and data analysis to improve workflow standardization and efficiencies, and provide risk stratification and decision supporting tools in real-time, to prompt the building of new imaging diagnostic networks to enhance rural healthcare engagement.

Deep learning from atrioventricular plane displacement in patients with Takotsubo syndrome: lighting up the black-box

Aims

The spatiotemporal deep convolutional neural network (DCNN) helps reduce echocardiographic readers' erroneous 'judgement calls' on Takotsubo syndrome (TTS). The aim of this study was to improve the interpretability of the spatiotemporal DCNN to discover latent imaging features associated with causative TTS pathophysiology.

Methods and results

We applied gradient-weighted class activation mapping analysis to visualize an established spatiotemporal DCNN based on the echocardiographic videos to differentiate TTS (150 patients) from anterior wall ST-segment elevation myocardial infarction (STEMI, 150 patients). Forty-eight human expert readers interpreted the same echocardiographic videos and prioritized the regions of interest on myocardium for the differentiation. Based on visualization results, we completed optical flow measurement, myocardial strain, and Doppler/tissue Doppler echocardiography studies to investigate regional myocardial temporal dynamics and diastology. While human readers' visualization predominantly focused on the apex of the heart in TTS patients, the DCNN temporal arm's saliency visualization was attentive on the base of the heart, particularly at the atrioventricular (AV) plane. Compared with STEMI patients, TTS patients consistently showed weaker peak longitudinal displacement (in pixels) in the basal inferoseptal (systolic: 2.15 ± 1.41 vs. 3.10 ± 1.66, P < 0.001; diastolic: 2.36 ± 1.71 vs. 2.97 ± 1.69, P = 0.004) and basal anterolateral (systolic: 2.70 ± 1.96 vs. 3.44 ± 2.13, P = 0.003; diastolic: 2.73 ± 1.70 vs. 3.45 ± 2.20, P = 0.002) segments, and worse longitudinal myocardial strain in the basal inferoseptal (-8.5 ± 3.8% vs. -9.9 ± 4.1%, P = 0.013) and basal anterolateral (-8.6 ± 4.2% vs. -10.4 ± 4.1%, P = 0.006) segments. Meanwhile, TTS patients showed worse diastolic mechanics than STEMI patients (E'/septal: 5.1 ± 1.2 cm/s vs. 6.3 ± 1.5 cm/s, P < 0.001; S'/septal: 5.8 ± 1.3 cm/s vs. 6.8 ± 1.4 cm/s, P < 0.001; E'/lateral: 6.0 ± 1.4 cm/s vs. 7.9 ± 1.6 cm/s, P < 0.001; S'/lateral: 6.3 ± 1.4 cm/s vs. 7.3 ± 1.5 cm/s, P < 0.001; E/E': 15.5 ± 5.6 vs. 12.5 ± 3.5, P < 0.001).

Conclusion

The spatiotemporal DCNN saliency visualization helps identify the pattern of myocardial temporal dynamics and navigates the quantification of regional myocardial mechanics. Reduced AV plane displacement in TTS patients likely correlates with impaired diastolic mechanics.

Development of artificial intelligence-based slow-motion echocardiography and clinical usefulness for evaluating regional wall motion abnormalities

The diagnostic accuracy of exercise stress echocardiography (ESE) for myocardial ischemia requires improvement, given that it currently depends on the physicians' experience and image quality. To address this issue, we aimed to develop artificial intelligence (AI)-based slow-motion echocardiography using inter-image interpolation. The clinical usefulness of this method was evaluated for detecting regional wall-motion abnormalities (RWMAs). In this study, an AI-based echocardiographic image-interpolation pipeline was developed using optical flow calculation and prediction for in-between images. The accuracy for detecting RWMAs and image readability among 25 patients with RWMA and 25 healthy volunteers was compared between four cardiologists using slow-motion and conventional ESE. Slow-motion echocardiography was successfully developed for arbitrary time-steps (e.g., 0.125×, and 0.5×) using 1,334 videos. The RWMA detection accuracy showed a numerical improvement, but it was not statistically significant (87.5% in slow-motion echocardiography vs. 81.0% in conventional ESE; odds ratio: 1.43 [95% CI: 0.78-2.62], p = 0.25). Interreader agreement analysis (Fleiss's Kappa) for detecting RWMAs among the four cardiologists were 0.66 (95%CI: 0.55-0.77) for slow-motion ESE and 0.53 (95%CI: 0.42-0.65) for conventional ESE. Additionally, subjective evaluations of image readability using a four-point scale showed a significant improvement for slow-motion echocardiography (2.11 ± 0.73 vs. 1.70 ± 0.78, p < 0.001).In conclusion, we successfully developed slow-motion echocardiography using in-between echocardiographic image interpolation. Although the accuracy for detecting RWMAs did not show a significant improvement with this method, we observed enhanced image readability and interreader agreement. This AI-based approach holds promise in supporting physicians' evaluations.

STGA-MS: AI diagnosis model of regional wall motion abnormality based on 2D transthoracic echocardiography

Regional wall motion abnormality (RWMA) is a common manifestation of ischemic heart disease detected through echocardiography. Currently, RWMA diagnosis heavily relies on visual assessment by doctors, leading to limitations in experience-based dependence and suboptimal reproducibility among observers. Several RWMA diagnosis models were proposed, while RWMA diagnosis with more refined segments can provide more comprehensive wall motion information to better assist doctors in the diagnosis of ischemic heart disease. In this paper, we proposed the STGA-MS model which consists of three modules, the spatial-temporal grouping attention (STGA) module, the segment feature extraction module, and the multiscale downsampling module, for the diagnosis of RWMA for multiple myocardial segments. The STGA module captures global spatial and temporal information, enhancing the representation of myocardial motion characteristics. The segment feature extraction module focuses on specific segment regions, extracting relevant features. The multiscale downsampling module analyzes myocardial motion deformation across different receptive fields. Experimental results on a 2D transthoracic echocardiography dataset show that the proposed STGA-MS model achieves better performance compared to state-of-the-art models. It holds promise in improving the accuracy and reproducibility of RWMA diagnosis, assisting clinicians in diagnosing ischemic heart disease more reliably.

Can Artificial Intelligence Revolutionize the Diagnosis and Management of the Atrial Septal Defect in Children?

Atrial septal defects (ASDs) present a significant healthcare challenge, demanding accurate and timely diagnosis and precise management to ensure optimal patient outcomes. Artificial intelligence (AI) applications in healthcare are rapidly evolving, offering promise for enhanced medical decision-making and patient care. In the context of cardiology, the integration of AI promises to provide more efficient and accurate diagnosis and personalized treatment strategies for ASD patients. In interventional cardiology, sometimes the lack of precise measurement of the cardiac rims evaluated by transthoracic echocardiography combined with the floppy aspect of the rims can mislead and result in complications. AI software can be created to generate responses for difficult tasks, like which device is the most suitable for different shapes and dimensions to prevent embolization or erosion. This paper reviews the current state of AI in healthcare and its applications in cardiology, emphasizing the specific opportunities and challenges in applying AI to ASD diagnosis and management. By exploring the capabilities and limitations of AI in ASD diagnosis and management. This paper highlights the evolution of medical practice towards a more AI-augmented future, demonstrating the capacity of AI to unlock new possibilities for healthcare professionals and patients alike.

Artificial Intelligence-Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View

BACKGROUND

Clinical assessment and grading of left ventricular diastolic function (LVDF) requires quantification of multiple echocardiographic parameters interpreted according to established guidelines, which depends on experienced clinicians and is time consuming. The aim of this study was to develop an artificial intelligence (AI)-assisted system to facilitate the clinical assessment of LVDF.

METHODS

In total, 1,304 studies (33,404 images) were used to develop a view classification model to select six specific views required for LVDF assessment. A total of 2,238 studies (16,794 two-dimensional [2D] images and 2,198 Doppler images) to develop 2D and Doppler segmentation models, respectively, to quantify key metrics of diastolic function. We used 2,150 studies with definite LVDF labels determined by two experts to train single-view classification models by AI interpretation of strain metrics or video. The accuracy and efficiency of these models were tested in an external data set of 388 prospective studies.

RESULTS

The view classification model identified views required for LVDF assessment with good sensitivity (>0.9), and view segmentation models successfully outlined key regions of these views with intersection over union > 0.8 in the internal validation data set. In the external test data set of 388 cases, AI quantification of 2D and Doppler images showed narrow limits of agreement compared with the two experts (e.g., left ventricular ejection fraction, -12.02% to 9.17%; E/e' ratio, -3.04 to 2.67). These metrics were used to detect LV diastolic dysfunction (DD) and grade DD with accuracy of 0.9 and 0.92, respectively. Concerning the single-view method, the overall accuracy of DD detection was 0.83 and 0.75 by strain-based and video-based models, and the accuracy of DD grading was 0.85 and 0.8, respectively. These models could achieve diagnosis and grading of LVDD in a few seconds, greatly saving time and labor.

CONCLUSION

AI models successfully achieved LVDF assessment and grading that compared favorably with human experts reading according to guideline-based algorithms. Moreover, when Doppler variables were missing, AI models could provide assessment by interpreting 2D strain metrics or videos from a single view. These models have the potential to save labor and cost and to facilitate work flow of clinical LVDF assessment.

Topology-sensitive weighting model for myocardial segmentation

Accurate myocardial segmentation is crucial for the diagnosis of various heart diseases. However, segmentation results often suffer from topology structural errors, such as broken connections and holes, especially in cases of poor image quality. These errors are unacceptable in clinical diagnosis. We proposed a Topology-Sensitive Weight (TSW) model to keep both pixel-wise accuracy and topological correctness. Specifically, the Position Weighting Update (PWU) strategy with the Boundary-Sensitive Topology (BST) module can guide the model to focus on positions where topological features are sensitive to pixel values. The Myocardial Integrity Topology (MIT) module can serve as a guide for maintaining myocardial integrity. We evaluate the TSW model on the CAMUS dataset and a private echocardiography myocardial segmentation dataset. The qualitative and quantitative experimental results show that the TSW model significantly enhances topological accuracy while maintaining pixel-wise precision.

Development and validation of a deep learning pipeline to measure pericardial effusion in echocardiography

Objectives

The aim of this study was to develop a deep-learning pipeline for the measurement of pericardial effusion (PE) based on raw echocardiography clips, as current methods for PE measurement can be operator-dependent and present challenges in certain situations.

Methods

The proposed pipeline consisted of three distinct steps: moving window view selection (MWVS), automated segmentation, and width calculation from a segmented mask. The MWVS model utilized the ResNet architecture to classify each frame of the extracted raw echocardiography files into selected view types. The automated segmentation step then generated a mask for the PE area from the extracted echocardiography clip, and a computer vision technique was used to calculate the largest width of the PE from the segmented mask. The pipeline was applied to a total of 995 echocardiographic examinations.

Results

The proposed deep-learning pipeline exhibited high performance, as evidenced by intraclass correlation coefficient (ICC) values of 0.867 for internal validation and 0.801 for external validation. The pipeline demonstrated a high level of accuracy in detecting PE, with an area under the receiving operating characteristic curve (AUC) of 0.926 (95% CI: 0.902-0.951) for internal validation and 0.842 (95% CI: 0.794-0.889) for external validation.

Conclusion

The machine-learning pipeline developed in this study can automatically calculate the width of PE from raw ultrasound clips. The novel concepts of moving window view selection for image quality control and computer vision techniques for maximal PE width calculation seem useful in the field of ultrasound. This pipeline could potentially provide a standardized and objective approach to the measurement of PE, reducing operator-dependency and improving accuracy.

Blinded, randomized trial of sonographer versus AI cardiac function assessment

Artificial intelligence (AI) has been developed for echocardiography1-3, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of -10.4%, 95% confidence interval: -13.2% to -7.7%, P < 0.001 for non-inferiority, P < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of -0.96%, 95% confidence interval: -1.34% to -0.54%, P < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.

Echocardiography-based AI for detection and quantification of atrial septal defect

Objectives

We developed and tested a deep learning (DL) framework applicable to color Doppler echocardiography for automatic detection and quantification of atrial septal defects (ASDs).

Background

Color Doppler echocardiography is the most commonly used non-invasive imaging tool for detection of ASDs. While prior studies have used DL to detect the presence of ASDs from standard 2D echocardiographic views, no study has yet reported automatic interpretation of color Doppler videos for detection and quantification of ASD.

Methods

A total of 821 examinations from two tertiary care hospitals were collected as the training and external testing dataset. We developed DL models to automatically process color Doppler echocardiograms, including view selection, ASD detection and identification of the endpoints of the atrial septum and of the defect to quantify the size of defect and the residual rim.

Results

The view selection model achieved an average accuracy of 99% in identifying four standard views required for evaluating ASD. In the external testing dataset, the ASD detection model achieved an area under the curve (AUC) of 0.92 with 88% sensitivity and 89% specificity. The final model automatically measured the size of defect and residual rim, with the mean biases of 1.9 mm and 2.2 mm, respectively.

Conclusion

We demonstrated the feasibility of using a deep learning model for automated detection and quantification of ASD from color Doppler echocardiography. This model has the potential to improve the accuracy and efficiency of using color Doppler in clinical practice for screening and quantification of ASDs, that are required for clinical decision making.

High Burden of Premature Ventricular Complex Increases the Risk of New-Onset Atrial Fibrillation

Background High burden of premature ventricular complex (PVC) leads to increased cardiovascular mortality. A recent nationwide population-based study demonstrated that PVC is associated with an increased risk of atrial fibrillation (AF). However, the relationship between PVC burden and new-onset AF has not been investigated. The purpose of the study is to elucidate whether PVC burden is associated with new-onset AF. Methods and Results We designed a single-center, retrospective, large population-based cohort study to evaluate the role of PVC burden and new-onset AF in Taiwan. Patients who were AF naïve with PVC were divided into the low burden group (<1000/day) and moderate-to-high burden group (≥1000/day) based on the 24-h Holter ECG report. New-onset AF was defined as a new or first detectable event of either a persistent or paroxysmal AF. A total of 16 030 patients who were AF naïve and underwent 24-h Holter ECG monitoring were enrolled in this study, with a mean follow-up time of 973 days. A propensity score-matched analysis demonstrated that the moderate-to-high burden PVC group had a higher risk of developing new-onset AF than that of the low burden PVC group (4.91% versus 2.73%, P<0.001). Multivariate Cox regression analysis showed that moderate-to-high burden of PVC is an independent risk factor for new-onset AF. The Kaplan-Meier analysis demonstrated that patients with moderate-to-high PVC burden were associated with higher risk of new-onset AF (log-rank P<0.001). Conclusions PVC burden is associated with new-onset AF. Patients with moderate-to-high PVC burden are at a higher risk of new-onset AF. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT03877614.

Automatic Diagnostic Tool for Detection of Regional Wall Motion Abnormality from Echocardiogram

The echocardiogram is an ultrasound imaging modality, employed to assess cardiac abnormalities. The Regional Wall Motion Abnormality (RWMA) is the occurrence of abnormal or absent contractility of a region of the heart muscle. Conventional assessment of RWMA is based on visual interpretation of endocardial excursion and myocardial thickening from the echocardiogram videos. Wall motion assessment accuracy depends on the experience of the sonographer. Current automated methods highly depend on the preprocessing steps such as segmentation of ventricle part or manually finding systole and diastole frames from an echocardiogram. Additionally, state-of-the-art methods majorly make use of images rather than videos, which specifically lack the usage of temporal information associated with an echocardiogram. The deep learning models used, employ highly complex networks with billions of trainable parameters. Further, the existing models used on video data add to the computational intensity because of the high frame rates of echocardiogram videos. We developed a novel deep learning architecture EC3D-Net (Echo-Cardio 3D Net), which captures the temporal information for identifying regional wall motion abnormality from echocardiogram. We demonstrate that EC3D-Net can extract temporal information from even raw echocardiogram videos, at low frame rates, employing minimal training parameter-based deep architecture. EC3D-Net achieves both an overall F1-Score and an Area Under Curve (AUC) score of 0.82. Further, we were able to reduce time for training and trainable parameters by 50% through minimizing frames per second. We also show the EC3D-Net is an interpretable model, thereby helping physicians understand our model prediction. RWMA detection from echocardiogram videos is a challenging process and our results demonstrate that we could achieve the state-of-the-art results even while using minimal parameters and time by our EC3D-Net. The proposed network outperforms both complex deep networks as well as fusion methods generally used in video classification.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction

Objective

To compare the performance of a newly developed deep learning (DL) framework for automatic detection of regional wall motion abnormalities (RWMAs) for patients presenting with the suspicion of myocardial infarction from echocardiograms obtained with portable bedside equipment versus standard equipment.

Background

Bedside echocardiography is increasingly used by emergency department setting for rapid triage of patients presenting with chest pain. However, compared to images obtained with standard equipment, lower image quality from bedside equipment can lead to improper diagnosis. To overcome these limitations, we developed an automatic workflow to process echocardiograms, including view selection, segmentation, detection of RWMAs and quantification of cardiac function that was trained and validated on image obtained from bedside and standard equipment.

Methods

We collected 4,142 examinations from one hospital as training and internal testing dataset and 2,811 examinations from other hospital as the external test dataset. For data pre-processing, we adopted DL model to automatically recognize three apical views and segment the left ventricle. Detection of RWMAs was achieved with 3D convolutional neural networks (CNN). Finally, DL model automatically measured the size of cardiac chambers and left ventricular ejection fraction.

Results

The view selection model identified the three apical views with an average accuracy of 96%. The segmentation model provided good agreement with manual segmentation, achieving an average Dice of 0.89. In the internal test dataset, the model detected RWMAs with AUC of 0.91 and 0.88 respectively for standard and bedside ultrasound. In the external test dataset, the AUC were 0.90 and 0.85. The automatic cardiac function measurements agreed with echocardiographic report values (e. g., mean bias is 4% for left ventricular ejection fraction).

Conclusion

We present a fully automated echocardiography pipeline applicable to both standard and bedside ultrasound with various functions, including view selection, quality control, segmentation, detection of the region of wall motion abnormalities and quantification of cardiac function.

Diagnosis of fetal total anomalous pulmonary venous connection based on the post-left atrium space ratio using artificial intelligence

OBJECTIVE

To explore whether the post-left atrium space (PLAS) ratio would be useful for prenatal diagnosis of total anomalous pulmonary venous connection (TAPVC) using echocardiography and artificial intelligence.

METHODS

We retrospectively included 642 frames of four-chamber view from 319 fetuses (32 with TAPVC and 287 without TAPVC) in end-systolic and end-diastolic periods with multiple apex directions. The average gestational age was 25.6±2.7 weeks. No other cardiac or extracardiac malformations were observed. The dataset was divided into a training set (n=540; 48 with TAPVC and 492 without TAPVC) and test set (n=102; 20 with TAPVC and 82 without TAPVC). The PLAS ratio was defined as the ratio of the epicardium-descending aortic distance to the center of the heart-descending aortic distance. Supervised learning was used in DeepLabv3+, FastFCN, PSPNet, and DenseASPP segmentation models. The area under the curve (AUC) was used on the test set.

RESULTS

Expert annotations showed that this ratio was not related to the period or apex direction. It was higher in the TAPVC group than in the control group detected by expert and the four models. The AUC of expert annotations, DeepLabv3+, FastFCN, PSPNet, and DenseASPP were 0.977, 0.941, 0.925, 0.856, and 0.887, respectively.

CONCLUSION

Segmentation models achieve good diagnostic accuracy for TAPVC based on the PLAS ratio. This article is protected by copyright. All rights reserved.

Using deep learning method to identify left ventricular hypertrophy on echocardiography

BACKGROUND

Left ventricular hypertrophy (LVH) is an independent prognostic factor for cardiovascular events and it can be detected by echocardiography in the early stage. In this study, we aim to develop a semi-automatic diagnostic network based on deep learning algorithms to detect LVH.

METHODS

We retrospectively collected 1610 transthoracic echocardiograms, included 724 patients [189 hypertensive heart disease (HHD), 218 hypertrophic cardiomyopathy (HCM), and 58 cardiac amyloidosis (CA), along with 259 controls]. The diagnosis of LVH was defined by two experienced clinicians. For the deep learning architecture, we introduced ResNet and U-net++ to complete classification and segmentation tasks respectively. The models were trained and validated independently. Then, we connected the best-performing models to form the final framework and tested its capabilities.

RESULTS

In terms of individual networks, the view classification model produced AUC = 1.0. The AUC of the LVH detection model was 0.98 (95% CI 0.94-0.99), with corresponding sensitivity and specificity of 94.0% (95% CI 85.3-98.7%) and 91.6% (95% CI 84.6-96.1%) respectively. For etiology identification, the independent model yielded good results with AUC = 0.90 (95% CI 0.82-0.95) for HCM, AUC = 0.94 (95% CI 0.88-0.98) for CA, and AUC = 0.88 (95% CI 0.80-0.93) for HHD. Finally, our final integrated framework automatically classified four conditions (Normal, HCM, CA, and HHD), which achieved an average of AUC 0.91, with an average sensitivity and specificity of 83.7% and 90.0%.

CONCLUSION

Deep learning architecture has the ability to detect LVH and even distinguish the latent etiology of LVH.

Automated detection scheme for acute myocardial infarction using convolutional neural network and long short-term memory

The early detection of acute myocardial infarction, which is caused by lifestyle-related risk factors, is essential because it can lead to chronic heart failure or sudden death. Echocardiography, among the most common methods used to detect acute myocardial infarction, is a noninvasive modality for the early diagnosis and assessment of abnormal wall motion. However, depending on disease range and severity, abnormal wall motion may be difficult to distinguish from normal myocardium. As abnormal wall motion can lead to fatal complications, high accuracy is required in its detection over time on echocardiography. This study aimed to develop an automatic detection method for acute myocardial infarction using convolutional neural networks (CNNs) and long short-term memory (LSTM) in echocardiography. The short-axis view (papillary muscle level) of one cardiac cycle and left ventricular long-axis view were input into VGG16, a CNN model, for feature extraction. Thereafter, LSTM was used to classify the cases as normal myocardium or acute myocardial infarction. The overall classification accuracy reached 85.1% for the left ventricular long-axis view and 83.2% for the short-axis view (papillary muscle level). These results suggest the usefulness of the proposed method for the detection of myocardial infarction using echocardiography.

The Burden of Ventricular Premature Complex Is Associated With Cardiovascular Mortality

Background

Ventricular premature complex (VPC) is one of the most common ventricular arrhythmias. The presence of VPC is associated with an increased risk of heart failure (HF).

Method

We designed a single-center, retrospective, and large population-based cohort to clarify the role of VPC burden in long-term prognosis in Taiwan. We analyzed the database from the National Cheng Kung University Hospital-Electronic Medical Record (NCKUH-EMR) and NCKUH-Holter (NCKUH-Holter). A total of 19,527 patients who underwent 24-h Holter ECG monitoring due to palpitation, syncope, and clinical suspicion of arrhythmias were enrolled in this study.

Results

The clinical outcome of interests involved 5.65% noncardiovascular death and 1.53% cardiovascular-specific deaths between 2011 and 2018. Multivariate Cox regression analysis, Fine and Gray's competing risk model, and propensity score matching demonstrated that both moderate (1,000–10,000/day) and high (>10,000/day) VPC burdens contributed to cardiovascular death in comparison with a low VPC burden (<1,000/day).

Conclusion

A higher VPC burden via Holter ECG is an independent risk factor of cardiovascular mortality.

Radiomics in Cardiovascular Disease Imaging: from Pixels to the Heart of the Problem

Purpose of Review

This review of the literature aims to present potential applications of radiomics in cardiovascular radiology and, in particular, in cardiac imaging.

Recent Findings

Radiomics and machine learning represent a technological innovation which may be used to extract and analyze quantitative features from medical images. They aid in detecting hidden pattern in medical data, possibly leading to new insights in pathophysiology of different medical conditions. In the recent literature, radiomics and machine learning have been investigated for numerous potential applications in cardiovascular imaging. They have been proposed to improve image acquisition and reconstruction, for anatomical structure automated segmentation or automated characterization of cardiologic diseases.

Summary

The number of applications for radiomics and machine learning is continuing to rise, even though methodological and implementation issues still limit their use in daily practice. In the long term, they may have a positive impact in patient management.

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

Electrocardiography Score for Left Ventricular Systolic Dysfunction in Non-ST Segment Elevation Acute Coronary Syndrome

Background: Few studies have characterized electrocardiography (ECG) patterns correlated with left ventricular (LV) systolic dysfunction in patients with non-ST segment elevation acute coronary syndrome (NSTE-ACS).

Objectives: This study aims to develop ECG pattern-derived scores to predict LV systolic dysfunction in NSTE-ACS patients.

Methods: A total of 466 patients with NSTE-ACS were retrospectively enrolled. LV ejection fraction (LVEF) was assessed by echocardiography within 72 h after the first triage ECG acquisition; there was no coronary intervention in between. ECG score was developed to predict LVEF < 40%. Performance of LVEF, the Global Registry of Acute Coronary Events (GRACE), Thrombolysis in Myocardial Infarction (TIMI) and ECG scores to predict 24-month all-cause mortality were analyzed. Subgroups with varying LVEF, GRACE and TIMI scores were stratified by ECG score to identify patients at high risk of mortality.

Results: LVEF < 40% was present in 20% of patients. We developed the PQRST score by multivariate logistic regression, including poor R wave progression, QRS duration > 110 ms, heart rate > 100 beats per min, and ST-segment depression ≥ 1 mm in ≥ 2 contiguous leads, ranging from 0 to 6.5. The score had an area under the curve (AUC) of 0.824 in the derivation cohort and 0.899 in the validation cohort for discriminating LVEF < 40%. A PQRST score ≥ 3 could stratify high-risk patients with LVEF ≥ 40%, GRACE score > 140, or TIMI score ≥ 3 regarding 24-month all-cause mortality.

Conclusions: The PQRST score could predict LVEF < 40% in NSTE-ACS patients and identify patients at high risk of mortality in the subgroups of patients with LVEF ≥ 40%, GRACE score > 140 or TIMI score ≥ 3.

Automated Analysis of Doppler Echocardiographic Videos as a Screening Tool for Valvular Heart Diseases

OBJECTIVES

This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs).

BACKGROUND

Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs.

METHODS

We developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set.

RESULTS

Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 [95% CI: 0.86-0.90] for MR; 0.97 [95% CI: 0.95-0.99] for AS; and 0.90 [95% CI: 0.88-0.92]) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from -0.60 to 0.77 cm² vs -0.48 to 0.44 cm² for MV area; from -0.27 to 0.25 vs -0.23 to 0.08 for MR jet area/left atrial area; from -0.86 to 0.52 m/s vs -0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from -10.6 to 9.5 mm Hg vs -10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from -0.39 to 0.32 vs -0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter.

CONCLUSIONS

The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.

Catecholamine-Induced Secondary Takotsubo Syndrome in Children With Severe Enterovirus 71 Infection and Acute Heart Failure: A 20-year Experience of a Single Institute

Background: Acute heart failure (AHF) is the major cause of death in children with severe enterovirus 71 (EV71) infection. This study aimed to report our clinical experience with EV71-related AHF, as well as to discuss its pathogenesis and relationship to Takotsubo syndrome (TTS).

Methods: A total 27 children with EV71-related AHF between 1998 and 2018 were studied. The TTS diagnosis was based on the International Takotsubo Diagnostic Criteria.

Results: Acute heart failure-related early death occurred in 10 (37%) of the patients. Sinus tachycardia, systemic hypertension, and pulmonary edema in 100, 85, and 81% of the patients, respectively, preceded AHF. Cardiac biomarkers were significantly increased in most patients. The main echocardiographic findings included transient and reversible left ventricular (LV) regional wall motion abnormality (RWMA) with apical ballooning. High concentrations of catecholamines either preceded or coexisted with AHF. Myocardial pathology revealed no evidence of myocarditis, which was consistent with catecholamine-induced cardiotoxic damage. Patients with EV71-related AHF who had received close monitoring of their cardiac function, along with early intervention involving extracorporeal life support (ECLS), had a higher survival rate (82 vs. 30%, p = 0.013) and better neurological outcomes (59 vs. 0%, p = 0.003).

Conclusion: EV 71-related AHF was preceded by brain stem encephalitis-related hypercatecholaminemia, which resulted in a high mortality rate. Careful monitoring is merited so that any life-threatening cardiogenic shock may be appropriately treated. In view of the similarities in their clinical manifestations, natural course direction, pathological findings, and possible mechanisms, TTS and EV71-related AHF may represent the same syndrome. Therefore, we suggest that EV71-related AHF could constitute a direct causal link to catecholamine-induced secondary TTS.

Spatio-temporal hybrid neural networks reduce erroneous human "judgement calls" in the diagnosis of Takotsubo syndrome

BACKGROUND

We investigate whether deep learning (DL) neural networks can reduce erroneous human "judgment calls" on bedside echocardiograms and help distinguish Takotsubo syndrome (TTS) from anterior wall ST segment elevation myocardial infarction (STEMI).

METHODS

We developed a single-channel (DCNN[2D SCI]), a multi-channel (DCNN[2D MCI]), and a 3-dimensional (DCNN[2D+t]) deep convolution neural network, and a recurrent neural network (RNN) based on 17,280 still-frame images and 540 videos from 2-dimensional echocardiograms in 10 years (1 January 2008 to 1 January 2018) retrospective cohort in University of Iowa (UI) and eight other medical centers. Echocardiograms from 450 UI patients were randomly divided into training and testing sets for internal training, testing, and model construction. Echocardiograms of 90 patients from the other medical centers were used for external validation to evaluate the model generalizability. A total of 49 board-certified human readers performed human-side classification on the same echocardiography dataset to compare the diagnostic performance and help data visualization.

FINDINGS

The DCNN (2D SCI), DCNN (2D MCI), DCNN(2D+t), and RNN models established based on UI dataset for TTS versus STEMI prediction showed mean diagnostic accuracy 73%, 75%, 80%, and 75% respectively, and mean diagnostic accuracy of 74%, 74%, 77%, and 73%, respectively, on the external validation. DCNN(2D+t) (area under the curve [AUC] 0·787 vs. 0·699, P = 0·015) and RNN models (AUC 0·774 vs. 0·699, P = 0·033) outperformed human readers in differentiating TTS and STEMI by reducing human erroneous judgement calls on TTS.

INTERPRETATION

Spatio-temporal hybrid DL neural networks reduce erroneous human "judgement calls" in distinguishing TTS from anterior wall STEMI based on bedside echocardiographic videos.

FUNDING

University of Iowa Obermann Center for Advanced Studies Interdisciplinary Research Grant, and Institute for Clinical and Translational Science Grant. National Institutes of Health Award (1R01EB025018-01).

The Use of Machine Learning for the Care of Hypertension and Heart Failure

Machine learning (ML) is a branch of artificial intelligence that combines computer science, statistics, and decision theory to learn complex patterns from voluminous data. In the last decade, accumulating evidence has shown the utility of ML for prediction, diagnosis, and classification of hypertension and heart failure (HF). In addition, ML-enabled image analysis has potential value in assessing cardiac structure and function in an accurate, scalable, and efficient way. Considering the high burden of hypertension and HF in China and worldwide, ML may help address these challenges from different aspects. Indeed, prior studies have shown that ML can enhance each stage of patient care, from research and development, to daily clinical practice and population health. Through reviewing the published literature, the aims of the current systemic review are to summarize the utilities of ML for the care of those with hypertension and HF.

Predicting post-operative right ventricular failure using video-based deep learning

Despite progressive improvements over the decades, the rich temporally resolved data in an echocardiogram remain underutilized. Human assessments reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. All modern echocardiography artificial intelligence (AI) systems are similarly limited by design - automating measurements of the same reductionist metrics rather than utilizing the embedded wealth of data. This underutilization is most evident where clinical decision making is guided by subjective assessments of disease acuity. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such example. Here we describe a video AI system trained to predict post-operative RV failure using the full spatiotemporal density of information in pre-operative echocardiography. We achieve an AUC of 0.729, and show that this ML system significantly outperforms a team of human experts at the same task on independent evaluation.

Artificial intelligence-enhanced echocardiography in the emergency department

A focused cardiac ultrasound performed by an emergency physician is becoming part of the standard assessment of patients in a variety of clinical situations. The development of inexpensive, portable handheld devices promises to make point-of-care ultrasound even more accessible over the coming decades. Many of these handheld devices are beginning to integrate artificial intelligence (AI) for image analysis. The integration of AI into focused cardiac ultrasound will have a number of implications for emergency physicians. This perspective presents an overview of the current state of AI research in echocardiography relevant to the emergency physician, as well as the future possibilities, challenges and risks of this technology.