Learning Domain Shift in Simulated and Clinical Data: Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms

Solving the Inverse Problem of Electrocardiography for Cardiac Digital Twins: A Survey

Cardiac digital twins (CDTs) are personalized virtual representations used to understand complex cardiac mechanisms. A critical component of CDT development is solving the ECG inverse problem, which enables the reconstruction of cardiac sources and the estimation of patient-specific electrophysiology (EP) parameters from surface ECG data. Despite challenges from complex cardiac anatomy, noisy ECG data, and the ill-posed nature of the inverse problem, recent advances in computational methods have greatly improved the accuracy and efficiency of ECG inverse inference, strengthening the fidelity of CDTs. This paper aims to provide a comprehensive review of the methods for solving ECG inverse problems, their validation strategies, their clinical applications, and their future perspectives. For the methodologies, we broadly classify state-of-the-art approaches into two categories: deterministic and probabilistic methods, including both conventional and deep learning-based techniques. Integrating physics laws with deep learning models holds promise, but challenges such as capturing dynamic electrophysiology accurately, accessing accurate domain knowledge, and quantifying prediction uncertainty persist. Integrating models into clinical workflows while ensuring interpretability and usability for healthcare professionals is essential. Overcoming these challenges will drive further research in CDTs.

A transferable in-silico augmented ischemic model for virtual myocardial perfusion imaging and myocardial infarction detection

This paper proposes an innovative approach to generate a generalized myocardial ischemia database by modeling the virtual electrophysiology of the heart and the 12-lead electrocardiography projected by the in-silico model can serve as a ready-to-use database for automatic myocardial infarction/ischemia (MI) localization and classification. Although the virtual heart can be created by an established technique combining the cell model with personalized heart geometry to observe the spatial propagation of depolarization and repolarization waves, we developed a strategy based on the clinical pathophysiology of MI to generate a heterogeneous database with a generic heart while maintaining clinical relevance and reduced computational complexity. First, the virtual heart is simplified into 11 regions that match the types and locations, which can be diagnosed by 12-lead ECG; the major arteries were divided into 3-5 segments from the upstream to the downstream based on the general anatomy. Second, the stenosis or infarction of the major or minor coronary artery branches can cause different perfusion drops and infarct sizes. We simulated the ischemic sites in different branches of the arteries by meandering the infarction location to elaborate on possible ECG representations, which alters the infraction's size and changes the transmembrane potential (TMP) of the myocytes associated with different levels of perfusion drop. A total of 8190 different case combinations of cardiac potentials with ischemia and MI were simulated, and the corresponding ECGs were generated by forward calculations. Finally, we trained and validated our in-silico database with a sparse representation classification (SRC) and tested the transferability of the model on the real-world Physikalisch Technische Bundesanstalt (PTB) database. The overall accuracies for localizing the MI region on the PTB data achieved 0.86, which is only 2% drop compared to that derived from the simulated database (0.88). In summary, we have shown a proof-of-concept for transferring an in-silico model to real-world database to compensate for insufficient data.

Non-invasive localization of the ventricular excitation origin without patient-specific geometries using deep learning

Cardiovascular diseases account for 17 million deaths per year worldwide. Of these, 25% are categorized as sudden cardiac death, which can be related to ventricular tachycardia (VT). This type of arrhythmia can be caused by focal activation sources outside the sinus node. Catheter ablation of these foci is a curative treatment in order to inactivate the abnormal triggering activity. However, the localization procedure is usually time-consuming and requires an invasive procedure in the catheter lab. To facilitate and expedite the treatment, we present two novel localization support techniques based on convolutional neural networks (CNNs) that address these clinical needs. In contrast to existing methods, our approaches were designed to be independent of the patient-specific geometry and directly applicable to surface ECG signals, while also delivering a binary transmural position. Moreover, one of the method's outputs can be interpreted as several ranked solutions. The CNNs were trained on a dataset containing only simulated data and evaluated both on simulated test data and clinical data. On a novel large and open simulated dataset, the median test error was below 3 mm. The median localization error on the unseen clinical data ranged from 32 mm to 41 mm without optimizing the pre-processing and CNN to the clinical data. Interpreting the output of one of the approaches as ranked solutions, the best median error of the top-3 solutions decreased to 20 mm on the clinical data. The transmural position was correctly detected in up to 82% of all clinical cases. These results demonstrate a proof of principle to utilize CNNs to localize the activation source without the intrinsic need for patient-specific geometrical information. Furthermore, providing multiple solutions can assist physicians in identifying the true activation source amongst more than one possible location. With further optimization to clinical data, these methods have high potential to accelerate clinical interventions, replace certain steps within these procedures and consequently reduce procedural risk and improve VT patient outcomes.

Improving localization accuracy for non-invasive automated early left ventricular origin localization approach

Background: We previously developed a non-invasive approach to localize the site of early left ventricular activation origin in real time using 12-lead ECG, and to project the predicted site onto a generic LV endocardial surface using the smallest angle between two vectors algorithm (SA). Objectives: To improve the localization accuracy of the non-invasive approach by utilizing the K-nearest neighbors algorithm (KNN) to reduce projection errors. Methods: Two datasets were used. Dataset #1 had 1012 LV endocardial pacing sites with known coordinates on the generic LV surface and corresponding ECGs, while dataset #2 included 25 clinically-identified VT exit sites and corresponding ECGs. The non-invasive approach used "population" regression coefficients to predict the target coordinates of a pacing site or VT exit site from the initial 120-m QRS integrals of the pacing site/VT ECG. The predicted site coordinates were then projected onto the generic LV surface using either the KNN or SA projection algorithm. Results: The non-invasive approach using the KNN had a significantly lower mean localization error than the SA in both dataset #1 (9.4 vs. 12.5 mm, p < 0.05) and dataset #2 (7.2 vs. 9.5 mm, p < 0.05). The bootstrap method with 1,000 trials confirmed that using KNN had significantly higher predictive accuracy than using the SA in the bootstrap assessment with the left-out sample (p < 0.05). Conclusion: The KNN significantly reduces the projection error and improves the localization accuracy of the non-invasive approach, which shows promise as a tool to identify the site of origin of ventricular arrhythmia in non-invasive clinical modalities.

ECGNet: An Efficient Network for Detecting Premature Ventricular Complexes Based on ECG Images

BACKGROUND

Preoperative prediction of the origin site of premature ventricular complexes (PVCs) is critical for the success of operations. However, current methods are not efficient or accurate enough. In addition, among the proposed strategies, there are few good prediction methods for electrocardiogram (ECG) images combined with deep learning aspects.

METHODS

We propose ECGNet, a new neural network for the classification of 12-lead ECG images. In ECGNet, 609 ECG images from 310 patients who had undergone successful surgery in the Division of Cardiology, the First Affiliated Hospital of Soochow University, are utilized to construct the dataset. We adopt dense blocks, special convolution kernels and divergent paths to improve the performance of ECGNet. In addition, a new loss function is designed to address the sample imbalance situation, whose cause is the uneven distribution of cases themselves, which often occurs in the medical field. We also conduct extensive experiments in terms of network prediction accuracy to compare ECGNet with other networks, such as ResNet and DarkNet.

RESULTS

Our ECGNet achieves extremely high prediction accuracy (91.74%) and efficiency with very small datasets. Our newly proposed loss function can solve the problem of sample imbalance during the training process.

CONCLUSION

The proposed ECGNet can quickly and accurately realize the multiclassification of PVCs after training with little data. Our network has the potential to be helpful to doctors with a preoperative diagnosis of PVCs. We will continue to collect similar cases and perfect our network structure to further improve the accuracy of our network's prediction.

Training machine learning models with synthetic data improves the prediction of ventricular origin in outflow tract ventricular arrhythmias

In order to determine the site of origin (SOO) in outflow tract ventricular arrhythmias (OTVAs) before an ablation procedure, several algorithms based on manual identification of electrocardiogram (ECG) features, have been developed. However, the reported accuracy decreases when tested with different datasets. Machine learning algorithms can automatize the process and improve generalization, but their performance is hampered by the lack of large enough OTVA databases. We propose the use of detailed electrophysiological simulations of OTVAs to train a machine learning classification model to predict the ventricular origin of the SOO of ectopic beats. We generated a synthetic database of 12-lead ECGs (2,496 signals) by running multiple simulations from the most typical OTVA SOO in 16 patient-specific geometries. Two types of input data were considered in the classification, raw and feature ECG signals. From the simulated raw 12-lead ECG, we analyzed the contribution of each lead in the predictions, keeping the best ones for the training process. For feature-based analysis, we used entropy-based methods to rank the obtained features. A cross-validation process was included to evaluate the machine learning model. Following, two clinical OTVA databases from different hospitals, including ECGs from 365 patients, were used as test-sets to assess the generalization of the proposed approach. The results show that V2 was the best lead for classification. Prediction of the SOO in OTVA, using both raw signals or features for classification, presented high accuracy values (>0.96). Generalization of the network trained on simulated data was good for both patient datasets (accuracy of 0.86 and 0.84, respectively) and presented better values than using exclusively real ECGs for classification (accuracy of 0.84 and 0.76 for each dataset). The use of simulated ECG data for training machine learning-based classification algorithms is critical to obtain good SOO predictions in OTVA compared to real data alone. The fast implementation and generalization of the proposed methodology may contribute towards its application to a clinical routine.

Assessment of an ECG-Based System for Localizing Ventricular Arrhythmias in Patients With Structural Heart Disease

Background

We have previously developed an intraprocedural automatic arrhythmia‐origin localization (AAOL) system to identify idiopathic ventricular arrhythmia origins in real time using a 3‐lead ECG. The objective was to assess the localization accuracy of ventricular tachycardia (VT) exit and premature ventricular contraction (PVC) origin sites in patients with structural heart disease using the AAOL system.

Methods and Results

In retrospective and prospective case series studies, a total of 42 patients who underwent VT/PVC ablation in the setting of structural heart disease were recruited at 2 different centers. The AAOL system combines 120‐ms QRS integrals of 3 leads (III, V2, V6) with pace mapping to predict VT exit/PVC origin site and projects that site onto the patient‐specific electroanatomic mapping surface. VT exit/PVC origin sites were clinically identified by activation mapping and/or pace mapping. The localization error of the VT exit/PVC origin site was assessed by the distance between the clinically identified site and the estimated site. In the retrospective study of 19 patients with structural heart disease, the AAOL system achieved a mean localization accuracy of 6.5±2.6 mm for 25 induced VTs. In the prospective study with 23 patients, mean localization accuracy was 5.9±2.6 mm for 26 VT exit and PVC origin sites. There was no difference in mean localization error in epicardial sites compared with endocardial sites using the AAOL system (6.0 versus 5.8 mm, P=0.895).

Conclusions

The AAOL system achieved accurate localization of VT exit/PVC origin sites in patients with structural heart disease; its performance is superior to current systems, and thus, it promises to have potential clinical utility.

Reconstruction of three-dimensional biventricular activation based on the 12-lead electrocardiogram via patient-specific modelling

Aims

Non-invasive imaging of electrical activation requires high-density body surface potential mapping. The nine electrodes of the 12-lead electrocardiogram (ECG) are insufficient for a reliable reconstruction with standard inverse methods. Patient-specific modelling may offer an alternative route to physiologically constraint the reconstruction. The aim of the study was to assess the feasibility of reconstructing the fully 3D electrical activation map of the ventricles from the 12-lead ECG and cardiovascular magnetic resonance (CMR).

Methods and results

Ventricular activation was estimated by iteratively optimizing the parameters (conduction velocity and sites of earliest activation) of a patient-specific model to fit the simulated to the recorded ECG. Chest and cardiac anatomy of 11 patients (QRS duration 126–180 ms, documented scar in two) were segmented from CMR images. Scar presence was assessed by magnetic resonance (MR) contrast enhancement. Activation sequences were modelled with a physiologically based propagation model and ECGs with lead field theory. Validation was performed by comparing reconstructed activation maps with those acquired by invasive electroanatomical mapping of coronary sinus/veins (CS) and right ventricular (RV) and left ventricular (LV) endocardium. The QRS complex was correctly reproduced by the model (Pearson’s correlation r = 0.923). Reconstructions accurately located the earliest and latest activated LV regions (median barycentre distance 8.2 mm, IQR 8.8 mm). Correlation of simulated with recorded activation time was very good at LV endocardium (r = 0.83) and good at CS (r = 0.68) and RV endocardium (r = 0.58).

Conclusion

Non-invasive assessment of biventricular 3D activation using the 12-lead ECG and MR imaging is feasible. Potential applications include patient-specific modelling and pre-/per-procedural evaluation of ventricular activation.

Applications of artificial intelligence in cardiovascular imaging

Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome.

A Novel Model Based on Spatial and Morphological Domains to Predict the Origin of Premature Ventricular Contraction

Pace mapping is commonly used to locate the origin of ventricular arrhythmias, especially premature ventricular contraction (PVC). However, this technique relies on clinicians’ ability to rapidly interpret ECG data. To avoid time-consuming interpretation of ECG morphology, some automated algorithms or computational models have been explored to guide the ablation. Inspired by these studies, we propose a novel model based on spatial and morphological domains. The purpose of this study is to assess this model and compare it with three existing models. The data are available from the Experimental Data and Geometric Analysis Repository database in which three in vivo PVC patients are included. To measure the hit rate (A hit occurs when the predicted site is within 15 mm of the target) of different algorithms, 47 target sites are tested. Moreover, to evaluate the efficiency of different models in narrowing down the target range, 54 targets are verified. As a result, the proposed algorithm achieves the most hits (37/47) and fewest misses (9/47), and it narrows down the target range most, from 27.62 ± 3.47 mm to 10.72 ± 9.58 mm among 54 target sites. It is expected to be applied in the real-time prediction of the origin of ventricular activation to guide the clinician toward the target site.

A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms

BACKGROUND

Machine learning models may help localize the site of origin of ventricular tachycardia (VT) using 12-lead electrocardiograms. However, population-based models suffer from inter-subject anatomical variations within ECG data, while patient-specific models face the open challenge of what pacing data to collect for training.

METHODS

This study presents and validates the first hybrid model that combines population and patient-specific machine learning for rapid "computer-guided pace-mapping". A population-based deep learning model was first trained offline to disentangle inter-subject variations and regionalize the site of VT origin. Given a new patient with a target VT, an on-line patient-specific model -- after being initialized by the population-based prediction -- was then built in real time by actively suggesting where to pace next and improving the prediction with each added pacing data, progressively guiding pace-mapping towards the site of VT origin.

RESULTS

The population model was trained on pace-mapping data from 38 patients and the patient-specific model was subsequently tuned on one patient. The resulting hybrid model was tested on a separate cohort of eight patients in localizing 1) 193 LV endocardial pacing sites, and 2) nine VTs with clinically determined exit sites. The hybrid model achieved a localization error of 5.3 ± 2.6 mm using 5.4 ± 2.5 pacing sites in localizing LV pacing sites, achieving a significantly higher accuracy with a significantly smaller amount of training sites in comparison to models without active guidance.

CONCLUSION

The presented hybrid model has the potential to assist rapid pace-mapping of interventional targets in VT.

Creation and application of virtual patient cohorts of heart models

Patient-specific cardiac models are now being used to guide therapies. The increased use of patient-specific cardiac simulations in clinical care will give rise to the development of virtual cohorts of cardiac models. These cohorts will allow cardiac simulations to capture and quantify inter-patient variability. However, the development of virtual cohorts of cardiac models will require the transformation of cardiac modelling from small numbers of bespoke models to robust and rapid workflows that can create large numbers of models. In this review, we describe the state of the art in virtual cohorts of cardiac models, the process of creating virtual cohorts of cardiac models, and how to generate the individual cohort member models, followed by a discussion of the potential and future applications of virtual cohorts of cardiac models. This article is part of the theme issue 'Uncertainty quantification in cardiac and cardiovascular modelling and simulation'.

Sequential Factorized Autoencoder for Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms

OBJECTIVE

This work presents a novel approach to handle the inter-subject variations existing in the population analysis of ECG, applied for localizing the origin of ventricular tachycardia (VT) from 12-lead electrocardiograms (ECGs).

METHODS

The presented method involves a factor disentangling sequential autoencoder (f-SAE) - realized in both long short-term memory (LSTM) and gated recurrent unit (GRU) networks - to learn to disentangle the inter-subject variations from the factor relating to the location of origin of VT. To perform such disentanglement, a pair-wise contrastive loss is introduced.

RESULTS

The presented methods are evaluated on ECG dataset with 1012 distinct pacing sites collected from scar-related VT patients during routine pace-mapping procedures. Experiments demonstrate that, for classifying the origin of VT into the predefined segments, the presented f-SAE improves the classification accuracy by 8.94% from using prescribed QRS features, by 1.5% from the supervised deep CNN network, and 5.15% from the standard SAE without factor disentanglement. Similarly, when predicting the coordinates of the VT origin, the presented f-SAE improves the performance by 2.25 mm from using prescribed QRS features, by 1.18 mm from the supervised deep CNN network and 1.6 mm from the standard SAE.

CONCLUSION

These results demonstrate the importance as well as the feasibility of the presented f-SAE approach for separating inter-subject variations when using 12-lead ECG to localize the origin of VT.

SIGNIFICANCE

This work suggests the important research direction to deal with the well-known challenge posed by inter-subject variations during population analysis from ECG signals.