Application of L1-norm regularization to epicardial potential solution of the inverse electrocardiography problem

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.

Frequency-Enhanced Geometric-Constrained Reconstruction for Localizing Myocardial Infarction in 12-Lead Electrocardiograms

Determining the location of myocardial infarction is crucial for clinical management and therapeutic stratagem. However, existing diagnostic tools either sacrifice ease of use or are limited by their spatial resolution. Addressing this, we aim to refine myocardial infarction localization via surface potential reconstruction of the ventricles in 12-lead electrocardiograms (ECG). A notable obstacle is the ill-posed nature of such reconstructions. To overcome this, we introduce the frequency-enhanced geometric-constrained iterative network (FGIN). FGIN begins by mining the latent features from ECG data across both time and frequency domains. Subsequently, it increases the data dimensionality of ECG and captures intricate features using convolutional layers. Finally, FGIN incorporates ventricular geometry as a constraint on surface potential distribution. It allocates variable weights to distinct edges. Experimental validation of FGIN confirms its efficacy over synthetic and clinical datasets. On the synthetic dataset, FGIN outperforms seven existing reconstruction methods, attaining the highest Pearson Correlation Coefficient of 0.8624, the lowest Root Mean Square Error of 0.1548, and the highest Structural Similarity Index Measure of 0.7988. On the clinical public dataset (2007 PhysioNet/Computers in Cardiology Challenge), FGIN achieves better localization results than other approaches, according to the clinical standard 17-segment model, achieving an average Segment Overlap of 87.2%. Clinical trials on 50 patients demonstrate FGIN's effectiveness, showing an average accuracy of 91.6% and an average Segment Overlap of 88.2%.

Hybrid Neural State-Space Modeling for Supervised and Unsupervised Electrocardiographic Imaging

State-space modeling (SSM) provides a general framework for many image reconstruction tasks. Error in a priori physiological knowledge of the imaging physics, can bring incorrectness to solutions. Modern deep-learning approaches show great promise but lack interpretability and rely on large amounts of labeled data. In this paper, we present a novel hybrid SSM framework for electrocardiographic imaging (ECGI) to leverage the advantage of state-space formulations in data-driven learning. We first leverage the physics-based forward operator to supervise the learning. We then introduce neural modeling of the transition function and the associated Bayesian filtering strategy. We applied the hybrid SSM framework to reconstruct electrical activity on the heart surface from body-surface potentials. In unsupervised settings of both in-silico and in-vivo data without cardiac electrical activity as the ground truth to supervise the learning, we demonstrated improved ECGI performances of the hybrid SSM framework trained from a small number of ECG observations in comparison to the fixed SSM. We further demonstrated that, when in-silico simulation data becomes available, mixed supervised and unsupervised training of the hybrid SSM achieved a further 40.6% and 45.6% improvements, respectively, in comparison to traditional ECGI baselines and supervised data-driven ECGI baselines for localizing the origin of ventricular activations in real data.

An expert review of the inverse problem in electrocardiographic imaging for the non-invasive identification of atrial fibrillation drivers

BACKGROUND AND OBJECTIVE

Electrocardiographic imaging (ECGI) has emerged as a non-invasive approach to identify atrial fibrillation (AF) driver sources. This paper aims to collect and review the current research literature on the ECGI inverse problem, summarize the research progress, and propose potential research directions for the future.

METHODS AND RESULTS

The effectiveness and feasibility of using ECGI to map AF driver sources may be influenced by several factors, such as inaccuracies in the atrial model due to heart movement or deformation, noise interference in high-density body surface potential (BSP), inconvenient and time-consuming BSP acquisition, errors in solving the inverse problem, and incomplete interpretation of the AF driving source information derived from the reconstructed epicardial potential. We review the current research progress on these factors and discuss possible improvement directions. Additionally, we highlight the limitations of ECGI itself, including the lack of a gold standard to validate the accuracy of ECGI technology in locating AF drivers and the challenges associated with guiding AF ablation based on post-processed epicardial potentials due to the intrinsic difference between epicardial and endocardial potentials.

CONCLUSIONS

Before performing ablation, ECGI can provide operators with predictive information about the underlying locations of AF driver by non-invasively and globally mapping the biatrial electrical activity. In the future, endocardial catheter mapping technology may benefit from the use of ECGI to enhance the diagnosis and ablation of AF.

Comparison of dipole-based and potential-based ECGI methods for premature ventricular contraction beat localization with clinical data

Introduction: Localization of premature ventricular contraction (PVC) origin to guide the radiofrequency ablation (RFA) procedure is one of the prominent clinical goals of non-invasive electrocardiographic imaging. However, the results reported in the literature vary significantly depending on the source model and the level of complexity in the forward model. This study aims to compare the paced and spontaneous PVC localization performances of dipole-based and potential-based source models and corresponding inverse methods using the same clinical data and to evaluate the effects of torso inhomogeneities on these performances. Methods: The publicly available EP solution data from the EDGAR data repository (BSPs from a maximum of 240 electrodes) with known pacing locations and the Bratislava data (BSPs in 128 leads) with spontaneous PVCs from patients who underwent successful RFA procedures were used. Homogeneous and inhomogeneous torso models and corresponding forward problem solutions were used to relate sources on the closed epicardial and epicardial-endocardial surfaces. The localization error (LE) between the true and estimated pacing site/PVC origin was evaluated. Results: For paced data, the median LE values were 25.2 and 13.9 mm for the dipole-based and potential-based models, respectively. These median LE values were higher for the spontaneous PVC data: 30.2-33.0 mm for the dipole-based model and 28.9-39.2 mm for the potential-based model. The assumption of inhomogeneities in the torso model did not change the dipole-based solutions much, but using an inhomogeneous model improved the potential-based solutions on the epicardial-endocardial ventricular surface. Conclusion: For the specific task of localization of pacing site/PVC origin, the dipole-based source model is more stable and robust than the potential-based source model. The torso inhomogeneities affect the performances of PVC origin localization in each source model differently. Hence, care must be taken in generating patient-specific geometric and forward models depending on the source model representation used in electrocardiographic imaging (ECGI).

Improving Generalization by Learning Geometry-Dependent and Physics-Based Reconstruction of Image Sequences

Deep neural networks have shown promise in image reconstruction tasks, although often on the premise of large amounts of training data. In this paper, we present a new approach to exploit the geometry and physics underlying electrocardiographic imaging (ECGI) to learn efficiently with a relatively small dataset. We first introduce a non-Euclidean encoding-decoding network that allows us to describe the unknown and measurement variables over their respective geometrical domains. We then explicitly model the geometry-dependent physics in between the two domains via a bipartite graph over their graphical embeddings. We applied the resulting network to reconstruct electrical activity on the heart surface from body-surface potentials. In a series of generalization tasks with increasing difficulty, we demonstrated the improved ability of the network to generalize across geometrical changes underlying the data using less than 10% of training data and fewer variations of training geometry in comparison to its Euclidean alternatives. In both simulation and real-data experiments, we further demonstrated its ability to be quickly fine-tuned to new geometry using a modest amount of data.

A fast algorithm for spatiotemporal signals recovery using arbitrary dictionaries with application to electrocardiographic imaging

This paper presents a method to solve a linear regression problem subject to group lasso and ridge penalisation when the model has a Kronecker structure. This model was developed to solve the inverse problem of electrocardiography using sparse signal representation over a redundant dictionary or frame. The optimisation algorithm was performed using the block coordinate descent and proximal gradient descent methods. The explicit computation of the underlying Kronecker structure in the regression was avoided, reducing space and temporal complexity. We developed an algorithm that supports the use of arbitrary dictionaries to obtain solutions and allows a flexible group distribution.

Space-time shape uncertainties in the forward and inverse problem of electrocardiography

In electrocardiography, the "classic" inverse problem is the reconstruction of electric potentials at a surface enclosing the heart from remote recordings at the body surface and an accurate description of the anatomy. The latter being affected by noise and obtained with limited resolution due to clinical constraints, a possibly large uncertainty may be perpetuated in the inverse reconstruction. The purpose of this work is to study the effect of shape uncertainty on the forward and the inverse problem of electrocardiography. To this aim, the problem is first recast into a boundary integral formulation and then discretised with a collocation method to achieve high convergence rates and a fast time to solution. The shape uncertainty of the domain is represented by a random deformation field defined on a reference configuration. We propose a periodic-in-time covariance kernel for the random field and approximate the Karhunen-Loève expansion using low-rank techniques for fast sampling. The space-time uncertainty in the expected potential and its variance is evaluated with an anisotropic sparse quadrature approach and validated by a quasi-Monte Carlo method. We present several numerical experiments on a simplified but physiologically grounded two-dimensional geometry to illustrate the validity of the approach. The tested parametric dimension ranged from 100 up to 600. For the forward problem, the sparse quadrature is very effective. In the inverse problem, the sparse quadrature and the quasi-Monte Carlo method perform as expected, except for the total variation regularisation, where convergence is limited by lack of regularity. We finally investigate an H1/2 regularisation, which naturally stems from the boundary integral formulation, and compare it to more classical approaches.

Fetal ECG Extraction from Maternal ECG using Attention-based CycleGAN

A non-invasive fetal electrocardiogram (FECG) is used to monitor the electrical pulse of the fetal heart. Decomposing the FECG signal from the maternal ECG (MECG) is a blind source separation problem, which is hard due to the low amplitude of the FECG, the overlap of R waves, and the potential exposure to noise from different sources. Traditional decomposition techniques, such as adaptive filters, require tuning, alignment, or pre-configuration, such as modeling the noise or desired signal to map the MECG to the FECG. The high correlation between maternal and fetal ECG fragments decreases the performance of convolution layers. Therefore, the masking region of interest based on the attention mechanism was performed to improve the signal generators' precision. The sine activation function was also used to retain more details when converting two signal domains. Three available datasets from the Physionet, including the A&D FECG, NI-FECG, and NI-FECG challenge, and one synthetic dataset using FECGSYN toolbox, were used to evaluate the performance. The proposed method could map an abdominal MECG to a scalp FECG with an average of 98% R-Square [CI 95%: 97%, 99%] as the goodness of fit on the A&D FECG dataset. Moreover, it achieved 99.7 % F1-score [CI 95%: 97.8-99.9], 99.6% F1-score [CI 95%: 98.2%, 99.9%] and 99.3% F1-score [CI 95%: 95.3%, 99.9%] for fetal QRS detection on the A&D FECG, NI-FECG and NI-FECG challenge datasets, respectively. Also, the distortion was in the very good and good ranges. These results are comparable to the state-of-the-art results; thus, the proposed algorithm has the potential to be used for high-performance signal-to-signal conversion.

Impulse Data Model For Solving The Inverse Problem of Electrocardiography

OBJECTIVE

To develop, train and test neural networks for predicting heart surface potentials (HSPs) from body surface potentials (BSPs). The method re-frames traditional inverse problems of electrocardiograpy into regression problems, constraining the solution space by decomposing signals with multidimensional Gaussian impulse basis functions.

METHODS

Impulse HSPs were generated with single Gaussian basis functions at discrete heart surface locations and projected to corresponding BSPs using a volume conductor torso model. Both BSP (inputs) and HSP (outputs) were mapped to regular 2D surface meshes and used to train a neural network. Predictive capabilities of the network were tested with unseen synthetic and experimental data.

RESULTS

A dense full connected single hidden layer neural network was trained to map body surface impulses to heart surface Gaussian basis functions for reconstructing HSP. Synthetic pulses moving across the heart surface were predicted from the neural network with root mean squared error of 9.1 +/ 1.4%. Predicted signals were robust to noise up to 20 dB and errors due to displacement and rotation of the heart within the torso were bounded and predictable. A shift of the heart 40 mm toward the spine resulted in a 4% increase in signal feature localization error. The set of training impulse function data could be reduced and prediction error remained bounded. Recorded HSPs from in-vitro pig hearts were reliably decomposed using space-time Gaussian basis functions. Activation times calculated from predicted HSPs for left-ventricular pacing had a mean absolute error of 10.4 +/ 11.4 ms. Other pacing scenarios were analyzed with similar success.

CONCLUSION

Impulses from Gaussian basis functions are potentially an effective and robust way to train simple neural network data models for reconstructing HSPs from decomposed BSPs.

SIGNIFICANCE

The HSPs predicted by the neural network can be used to generate activation maps that non-invasively identify features of cardiac electrical dysfunction and can guide subsequent treatment options.

Electrocardiographic Imaging for Atrial Fibrillation: A Perspective From Computer Models and Animal Experiments to Clinical Value

Electrocardiographic imaging (ECGI) is a technique to reconstruct non-invasively the electrical activity on the heart surface from body-surface potential recordings and geometric information of the torso and the heart. ECGI has shown scientific and clinical value when used to characterize and treat both atrial and ventricular arrhythmias. Regarding atrial fibrillation (AF), the characterization of the electrical propagation and the underlying substrate favoring AF is inherently more challenging than for ventricular arrhythmias, due to the progressive and heterogeneous nature of the disease and its manifestation, the small volume and wall thickness of the atria, and the relatively large role of microstructural abnormalities in AF. At the same time, ECGI has the advantage over other mapping technologies of allowing a global characterization of atrial electrical activity at every atrial beat and non-invasively. However, since ECGI is time-consuming and costly and the use of electrical mapping to guide AF ablation is still not fully established, the clinical value of ECGI for AF is still under assessment. Nonetheless, AF is known to be the manifestation of a complex interaction between electrical and structural abnormalities and therefore, true electro-anatomical-structural imaging may elucidate important key factors of AF development, progression, and treatment. Therefore, it is paramount to identify which clinical questions could be successfully addressed by ECGI when it comes to AF characterization and treatment, and which questions may be beyond its technical limitations. In this manuscript we review the questions that researchers have tried to address on the use of ECGI for AF characterization and treatment guidance (for example, localization of AF triggers and sustaining mechanisms), and we discuss the technological requirements and validation. We address experimental and clinical results, limitations, and future challenges for fruitful application of ECGI for AF understanding and management. We pay attention to existing techniques and clinical application, to computer models and (animal or human) experiments, to challenges of methodological and clinical validation. The overall objective of the study is to provide a consensus on valuable directions that ECGI research may take to provide future improvements in AF characterization and treatment guidance.

IRN-MLSQR: An improved iterative reweight norm approach to the inverse problem of electrocardiography incorporating factorization-free preconditioned LSQR

The inverse problem of electrocardiography (ECG) of computing epicardial potentials from body surface potentials, is an ill-posed problem and needs to be solved by regularization techniques. The L2-norm regularization can cause considerable smoothing of the solution, while the L1-norm scheme promotes a solution with sharp boundaries/gradients between piecewise smooth regions, so L1-norm is widely used in the ECG inverse problem. However, large amount of computation and long computation time are needed in the L1-norm scheme. In this paper, by combining iterative reweight norm (IRN) with a factorization-free preconditioned LSQR algorithm (MLSQR), a new IRN-MLSQR method was proposed to accelerate the convergence speed of the L1-norm scheme. We validated the IRN-MLSQR method using experimental data from isolated canine hearts and clinical procedures in the electrophysiology laboratory. The results showed that the IRN-MLSQR method can significantly reduce the number of iterations and operation time while ensuring the calculation accuracy. The number of iterations of the IRN-MLSQR method is about 60%-70% that of the conventional IRN method, and at the same time, the accuracy of the solution is almost the same as that of the conventional IRN method. The proposed IRN-MLSQR method may be used as a new approach to the inverse problem of ECG.

Spatial-Temporal Signals and Clinical Indices in Electrocardiographic Imaging (I): Preprocessing and Bipolar Potentials

During the last years, Electrocardiographic Imaging (ECGI) has emerged as a powerful and promising clinical tool to support cardiologists. Starting from a plurality of potential measurements on the torso, ECGI yields a noninvasive estimation of their causing potentials on the epicardium. This unprecedented amount of measured cardiac signals needs to be conditioned and adapted to current knowledge and methods in cardiac electrophysiology in order to maximize its support to the clinical practice. In this setting, many cardiac indices are defined in terms of the so-called bipolar electrograms, which correspond with differential potentials between two spatially close potential measurements. Our aim was to contribute to the usefulness of ECGI recordings in the current knowledge and methods of cardiac electrophysiology. For this purpose, we first analyzed the basic stages of conventional cardiac signal processing and scrutinized the implications of the spatial-temporal nature of signals in ECGI scenarios. Specifically, the stages of baseline wander removal, low-pass filtering, and beat segmentation and synchronization were considered. We also aimed to establish a mathematical operator to provide suitable bipolar electrograms from the ECGI-estimated epicardium potentials. Results were obtained on data from an infarction patient and from a healthy subject. First, the low-frequency and high-frequency noises are shown to be non-independently distributed in the ECGI-estimated recordings due to their spatial dimension. Second, bipolar electrograms are better estimated when using the criterion of the maximum-amplitude difference between spatial neighbors, but also a temporal delay in discrete time of about 40 samples has to be included to obtain the usual morphology in clinical bipolar electrograms from catheters. We conclude that spatial-temporal digital signal processing and bipolar electrograms can pave the way towards the usefulness of ECGI recordings in the cardiological clinical practice. The companion paper is devoted to analyzing clinical indices obtained from ECGI epicardial electrograms measuring waveform variability and repolarization tissue properties.

Reduced leadset selection and performance evaluation in the inverse problem of electrocardiography for reconstructing the ventricularly paced electrograms

OBJECTIVE

Noninvasive electrocardiographic imaging (ECGI) is used for obtaining high-resolution images of the electrical activity of the heart, and is a powerful method with the potential to detect certain arrhythmias. However, there is no 'best' lead configuration in the literature to measure the torso potentials. This paper evaluates ECGI reconstructions using various reduced leadset configurations, explores whether one can find a common reduced leadset configuration that can accurately reconstruct the electrograms for datasets with different pacing sites, and compares two activation time estimation methods.

APPROACH

We used 23 ventricularly-paced datasets with pacing sites on different regions of the epicardium. Starting with a full 192‑leadset, we found "optimized" reduced leadsets specific to each dataset; we considered 64‑lead and 32‑lead configurations. Based on the histogram of individual "optimized" lead selections, we found a common reduced leadset. We compared the ECGI reconstructions and activation times of the individually optimized lead configurations with the common lead configurations.

RESULTS

Both 64‑lead configurations had similar performances to the 192‑leadset. 32‑leadset configurations, on the other hand, yielded noisy reconstructions, which affected their performance.

SIGNIFICANCE

There are no statistically significant differences in the performance of the inverse solutions when a 64‑lead common reduced leadset is used to estimate the electrograms and their respective pacing sites compared to using the full leadset. 32‑lead configurations, on the other hand, require a more careful study to improve their performance. The activation time method used significantly affects the pacing site estimation performance, especially with fewer electrodes.

A machine learning approach to reconstruction of heart surface potentials from body surface potentials

Invasive cardiac catheterisation is a precursor to ablation therapy for ventricular tachycardia. Invasive cardiac diagnostics are fraught with risks. Decades of research has been conducted on the inverse problem of electrocardiography, which can be used to reconstruct Heart Surface Potentials (HSPs) from Body Surface Potentials (BSPs), for non-invasive cardiac diagnostics. State of the art solutions to the inverse problem are unsatisfactory, since the inverse problem is known to be ill-posed. In this paper we propose a novel approach to reconstructing HSPs from BSPs using a Time-Delay Artificial Neural Network (TDANN). We first design the TDANN architecture, and then develop an iterative search space algorithm to find the parameters of the TDANN, which results in the best overall HSP prediction. We use recorded BSPs and HSPs from individuals suffering from serious cardiac conditions to validate our TDANN. The results are encouraging, in that the predicted and recorded HSPs have an average correlation coefficient of 0.7 under diseased conditions.

Noninvasive Reconstruction of Transmural Transmembrane Potential With Simultaneous Estimation of Prior Model Error

To reconstruct electrical activity in the heart from body-surface electrocardiograms (ECGs) is an ill-posed inverse problem. Electrophysiological models have been found effective in regularizing these inverse problems by incorporating a priori knowledge about how the electrical potential in the heart propagates over time. However, these models suffer from model errors arising from, for example, parameters associated with tissue properties and the earliest sites of excitation. We present a Bayesian approach to simultaneously estimate transmembrane potential (TMP) signals and prior model errors, exploiting sparsity of the error in the gradient domain in the form of a novel sparse prior based on variational lower bound of the generalized Gaussian distribution. In synthetic and real-data experiments, we demonstrate the improvement of accuracy in TMP reconstruction brought by simultaneous model error estimation. We further provide theoretical and empirical justifications for the change of performances in the presented method at the presence of different model errors.

ML and MAP estimation of parameters for the Kalman filter and smoother applied to electrocardiographic imaging

In electrocardiographic imaging (ECGI), one solves the inverse problem of electrocardiography (ECG) to reconstruct equivalent cardiac sources based on the body surface potential measurements and a mathematical model of the torso. Due to attenuation and spatial smoothing within the torso, this inverse problem is ill-posed. Among many regularization approaches used in the ECG literature to overcome this ill-posedness, statistical techniques have received great attention because of their flexibility to represent the data, and ability to provide performance evaluation tools for quantification of uncertainties and errors in the model. However, despite their potential to accurately reconstruct the equivalent cardiac sources, one major challenge in these methods is how to best utilize the prior information available in terms of training data. In this paper, we address the question of how to define the prior probability distributions (pdf) of the sources and the error terms so that we can obtain more accurate and robust inverse solutions. We employ two methods, maximum likelihood (ML) and maximum a posteriori (MAP), for estimating the model parameters such as the prior pdfs, error pdfs, and the state-transition matrix, based on the same training data. These model parameters are then used for the state-space representation and estimation of the epicardial potentials, which constitute the equivalent cardiac sources in this study. The performances of ML- and MAP-based model parameter estimation methods are evaluated qualitatively and quantitatively at various noise levels and geometric disturbances using two different simulated datasets. Bayesian MAP estimation, which is also a well-known statistical inversion technique, and Tikhonov regularization, which can be formulated as a special and simplified version of Bayesian MAP estimation, have been included here for comparison with the Kalman filtering method. Our results show that the state-space approach outperforms Bayesian MAP estimation in all cases; ML yields accurate results when the test and training beats come from the same physiological model, but MAP is superior to ML, especially if the test and training beats are from different physiological models. Graphical Abstract ML and MAP estimation of parameters for the Kalman filter and smoother applied to electrocardiographic imaging.

Noninvasive Imaging of Epicardial and Endocardial Potentials With Low Rank and Sparsity Constraints

In this study, we explore the use of low rank and sparse constraints for the noninvasive estimation of epicardial and endocardial extracellular potentials from body-surface electrocardiographic data to locate the focus of premature ventricular contractions (PVCs). The proposed strategy formulates the dynamic spatiotemporal distribution of cardiac potentials by means of low rank and sparse decomposition, where the low rank term represents the smooth background and the anomalous potentials are extracted in the sparse matrix. Compared to the most previous potential-based approaches, the proposed low rank and sparse constraints are batch spatiotemporal constraints that capture the underlying relationship of dynamic potentials. The resulting optimization problem is solved using alternating direction method of multipliers. Three sets of simulation experiments with eight different ventricular pacing sites demonstrate that the proposed model outperforms the existing Tikhonov regularization (zero-order, second-order) and L1-norm based method at accurately reconstructing the potentials and locating the ventricular pacing sites. Experiments on a total of 39 cases of real PVC data also validate the ability of the proposed method to correctly locate ectopic pacing sites.

Evaluation of multivariate adaptive non-parametric reduced-order model for solving the inverse electrocardiography problem: a simulation study

In the inverse electrocardiography (ECG) problem, the goal is to reconstruct the heart's electrical activity from multichannel body surface potentials and a mathematical model of the torso. Over the years, researchers have employed various approaches to solve this ill-posed problem including regularization, optimization, and statistical estimation. It is still a topic of interest especially for researchers and clinicians whose goal is to adopt this technique in clinical applications. Among the wide range of mathematical tools available in the fields of operational research, inverse problems, optimization, and parameter estimation, spline-based techniques have been applied to inverse problems in several areas. If proper spline bases are chosen, the complexity of the problem can be significantly reduced while increasing estimation accuracy. However, there are few studies within the context of the inverse ECG problem that take advantage of this property of the spline-based approaches. In this paper, we evaluate the performance of Multivariate Adaptive Regression Splines (MARS)-based method for the solution of the inverse ECG problem using two different collections of simulated data. The results show that the MARS-based method improves the inverse ECG solutions and is "robust" to modeling errors, especially in terms of localizing the arrhythmia sources. Graphical Abstract Multivariate adaptive non-parametric model for inverse ECG problem.

Evaluation of Fifteen Algorithms for the Resolution of the Electrocardiography Imaging Inverse Problem Using ex-vivo and in-silico Data

The electrocardiographic imaging inverse problem is ill-posed. Regularization has to be applied to stabilize the problem and solve for a realistic solution. Here, we assess different regularization methods for solving the inverse problem. In this study, we assess (i) zero order Tikhonov regularization (ZOT) in conjunction with the Method of Fundamental Solutions (MFS), (ii) ZOT regularization using the Finite Element Method (FEM), and (iii) the L1-Norm regularization of the current density on the heart surface combined with FEM. Moreover, we apply different approaches for computing the optimal regularization parameter, all based on the Generalized Singular Value Decomposition (GSVD). These methods include Generalized Cross Validation (GCV), Robust Generalized Cross Validation (RGCV), ADPC, U-Curve and Composite REsidual and Smoothing Operator (CRESO) methods. Both simulated and experimental data are used for this evaluation. Results show that the RGCV approach provides the best results to determine the optimal regularization parameter using both the FEM-ZOT and the FEM-L1-Norm. However for the MFS-ZOT, the GCV outperformed all the other regularization parameter choice methods in terms of relative error and correlation coefficient. Regarding the epicardial potential reconstruction, FEM-L1-Norm clearly outperforms the other methods using the simulated data but, using the experimental data, FEM based methods perform as well as MFS. Finally, the use of FEM-L1-Norm combined with RGCV provides robust results in the pacing site localization.

Localization of Activation Origin on Patient-Specific Epicardial Surface by Empirical Bayesian Method

OBJECTIVE

Ablation treatment of ventricular arrhythmias can be facilitated by pre-procedure planning aided by electrocardiographic inverse solution, which can help to localize the origin of arrhythmia. Our aim was to improve localization accuracy of the inverse solution by using a novel Bayesian approach.

METHODS

The inverse problem of electrocardiography was solved by reconstructing epicardial potentials from 120 body-surface electrocardiograms and from patient-specific geometry of the heart and torso for four patients suffering from scar-related ventricular tachycardia who underwent epicardial catheter mapping, which included pace-mapping. Simulations using dipole sources in patient-specific geometry were also performed. The proposed method, using dynamic spatio-temporal a priori constraints of the solution, was compared with classical Tikhonov methods based on fixed constraints.

RESULTS

The mean localization error of the proposed method for all available pacing sites (n=78) was significantly smaller than that achieved by Tikhonov methods; specifically, the localization accuracy for pacing in the normal tissue (n=17) was [Formula: see text] mm (mean ± SD) versus [Formula: see text] mm reported in the previous study using the same clinical data and Tikhonov regularization. Simulation experiments further supported these clinical findings.

CONCLUSION

The promising results of in vivo and in silico experiments presented in this study provide a strong incentive to pursuing further investigation of data-driven Bayesian methods in solving the electrocardiographic inverse problem.

SIGNIFICANCE

The proposed approach to localizing origin of ventricular activation sequence may have important applications in pre-procedure assessment of arrhythmias and in guiding their ablation treatment.

Rapid 12-lead automated localization method: Comparison to electrocardiographic imaging (ECGI) in patient-specific geometry

BACKGROUND

Rapid accurate localization of the site of ventricular activation origin during catheter ablation for ventricular arrhythmias could facilitate the procedure. Electrocardiographic imaging (ECGI) using large lead sets can localize the origin of ventricular activation. We have developed an automated method to identify sites of early ventricular activation in real time using the 12-lead ECG. We aim to compare the localization accuracy of ECGI and the automated method, identifying pacing sites/VT exit based on a patient-specific model.

METHODS

A patient undergoing ablation of VT on the left-ventricular endocardium and epicardium had 120-lead body-surface potential mapping (BSPM) recorded during the procedure. (1) ECGI methodology: The L1-norm regularization was employed to reconstruct epicardial potentials based on patient-specific geometry for localizing endocardial ventricular activation origin. We used the BSPM data corresponding to known endocardial pacing sites and a VT exit site identified by 3D contact mapping to analyze them offline. (2) The automatedmethod: location coordinates of pacing sites together with the time integral of the first 120 ms of the QRS complex of 3 ECG predictors (leads III, V2 and V6) were used to calculate patient-specific regression coefficients to predict the location of unknown sites of ventricular activation origin ("target" sites). Localization error was quantified over all pacing sites in millimeters by comparing the calculated location and the known reference location.

RESULTS

Localization was tested for 14 endocardial pacing sites and 1 epicardial VT exit site. For 14 endocardial pacing sites the mean localization error of the automated method was significantly lower than that of the ECGI (8.9 vs. 24.9 mm, p < 0.01), when 10 training pacing sites are used. Emulation of a clinical procedure demonstrated that the automated method achieved localization error of <5 mm for the VT-exit site; while the ECGI approach approximately correlates with the site of VT exit from the scar within a distance of 18.4 mm.

CONCLUSIONS

The automated method using only 3 ECGs shows promise to localize the origin of ventricular activation as tested by pacing, and the VT-exit site and compares favourably to inverse solution calculation, avoiding cumbersome lead sets. As 12-lead ECG data is acquired by current 3D mapping systems, it is conceivable that the algorithm could be directly incorporated into a mapping system. Further validation in a prospective cohort study is needed to confirm and extend observations reported in this study.

Characterizing the Location and Extent of Myocardial Infarctions With Inverse ECG Modeling and Spatiotemporal Regularization

Myocardial infarction (MI) is among the leading causes of death in the United States. It is imperative to identify and characterize MIs for timely delivery of life-saving medical interventions. Cardiac electrical activity propagates in space and evolves over time. Traditional works focus on the analysis of time-domain ECG (e.g., 12-lead ECG) on the body surface for the detection of MIs, but tend to overlook spatiotemporal dynamics in the heart. Body surface potential mappings (BSPMs) provide high-resolution distribution of electric potentials over the entire torso, and therefore provide richer information than 12-lead ECG. However, BSPM are available on the body surface. Clinicians are in need of a closer look of the electric potentials in the heart to investigate cardiac pathology and optimize treatment strategies. In this paper, we applied the method of spatiotemporal inverse ECG (ST-iECG) modeling to map electrical potentials from the body surface to the heart, and then characterize the location and extent of MIs by investigating the reconstructed heart-surface electrograms. First, we investigate the impact of mesh resolution on the inverse ECG modeling. Second, we solve the inverse ECG problem and reconstruct heart-surface electrograms using the ST-iECG model. Finally, we propose a wavelet-clustering method to investigate the pathological behaviors of heart-surface electrograms, and thereby characterize the extent and location of MIs. The proposed methodology is evaluated and validated with real data of MIs from human subjects. Experimental results show that negative QRS waves in heart-surface electrograms indicate potential regions of MI, and the proposed ST-iECG model yields superior characterization results of MIs on the heart surface over existing methods.

A new approach to the intracardiac inverse problem using Laplacian distance kernel

Background

The inverse problem in electrophysiology consists of the accurate estimation of the intracardiac electrical sources from a reduced set of electrodes at short distances and from outside the heart. This estimation can provide an image with relevant knowledge on arrhythmia mechanisms for the clinical practice. Methods based on truncated singular value decomposition (TSVD) and regularized least squares require a matrix inversion, which limits their resolution due to the unavoidable low-pass filter effect of the Tikhonov regularization techniques.

Methods

We propose to use, for the first time, a Mercer’s kernel given by the Laplacian of the distance in the quasielectrostatic field equations, hence providing a Support Vector Regression (SVR) formulation by following the principles of the Dual Signal Model (DSM) principles for creating kernel algorithms.

Results

Simulations in one- and two-dimensional models show the performance of our Laplacian distance kernel technique versus several conventional methods. Firstly, the one-dimensional model is adjusted for yielding recorded electrograms, similar to the ones that are usually observed in electrophysiological studies, and suitable strategy is designed for the free-parameter search. Secondly, simulations both in one- and two-dimensional models show larger noise sensitivity in the estimated transfer matrix than in the observation measurements, and DSM−SVR is shown to be more robust to noisy transfer matrix than TSVD.

Conclusion

These results suggest that our proposed DSM−SVR with Laplacian distance kernel can be an efficient alternative to improve the resolution in current and emerging intracardiac imaging systems.

Localization of ventricular activation origin using patient-specific geometry: Preliminary results

BACKGROUND AND OBJECTIVES

Catheter ablation of ventricular tachycardia (VT) may include induction of VT and localization of VT-exit site. Our aim was to assess localization performance of a novel statistical pace-mapping method and compare it with performance of an electrocardiographic inverse solution.

METHODS

Seven patients undergoing ablation of VT (4 with epicardial, 3 with endocardial exit) aided by electroanatomic mapping underwent intraprocedural 120-lead body-surface potential mapping (BSPM). Two approaches to localization of activation origin were tested: (1) A statistical method, based on multiple linear regression (MLR), which required only the conventional 12-lead ECG for a sufficient number of pacing sites with known origin together with patient-specific geometry of the endocardial/epicardial surface obtained by electroanatomic mapping; and (2) a classical deterministic inverse solution for recovering heart-surface potentials, which required BSPM and patient-specific geometry of the heart and torso obtained via computed tomography (CT).

RESULTS

For the MLR method, at least 10-15 pacing sites with known coordinates, together with their corresponding 12-lead ECGs, were required to derive reliable patient-specific regression equations, which then enabled accurate localization of ventricular activation with unknown origin. For 4 patients who underwent epicardial mapping, the median of localization error for the MLR was significantly lower than that for the inverse solution (10.6 vs. 27.3 mm, P  =  0.034); a similar result held for 3 patients who underwent endocardial mapping (7.7 vs. 17.1 mm, P  =  0.017). The pooled localization error for all epicardial and endocardial sites was also significantly smaller for the MLR compared with the inverse solution (P  =  0.005).

CONCLUSIONS

The novel pace-mapping approach to localizing the origin of ventricular activation offers an easily implementable supplement and/or alternative to the preprocedure inverse solution; its simplicity makes it suitable for real-time applications during clinical catheter-ablation procedures.

Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling: A Novel Approach to Solve the Inverse ECG Problem

This paper presents a novel physics-driven spatiotemporal regularization (STRE) method for high-dimensional predictive modeling in complex healthcare systems. This model not only captures the physics-based interrelationship between time-varying explanatory and response variables that are distributed in the space, but also addresses the spatial and temporal regularizations to improve the prediction performance. The STRE model is implemented to predict the time-varying distribution of electric potentials on the heart surface based on the electrocardiogram (ECG) data from the distributed sensor network placed on the body surface. The model performance is evaluated and validated in both a simulated two-sphere geometry and a realistic torso-heart geometry. Experimental results show that the STRE model significantly outperforms other regularization models that are widely used in current practice such as Tikhonov zero-order, Tikhonov first-order and L1 first-order regularization methods.

Physiology-based regularization of the electrocardiographic inverse problem

The inverse problem of electrocardiography aims at noninvasively reconstructing electrical activity of the heart from recorded body-surface electrocardiograms. A crucial step is regularization, which deals with ill-posedness of the problem by imposing constraints on the possible solutions. We developed a regularization method that includes electrophysiological input. Body-surface potentials are recorded and a computed tomography scan is performed to obtain the torso–heart geometry. Propagating waveforms originating from several positions at the heart are simulated and used to generate a set of basis vectors representing spatial distributions of potentials on the heart surface. The real heart-surface potentials are then reconstructed from the recorded body-surface potentials by finding a sparse representation in terms of this basis. This method, which we named ‘physiology-based regularization’ (PBR), was compared to traditional Tikhonov regularization and validated using in vivo recordings in dogs. PBR recovered details of heart-surface electrograms that were lost with traditional regularization, attained higher correlation coefficients and led to improved estimation of recovery times. The best results were obtained by including approximate knowledge about the beat origin in the PBR basis.

Noninvasive Personalization of a Cardiac Electrophysiology Model From Body Surface Potential Mapping

GOAL

We use noninvasive data (body surface potential mapping, BSPM) to personalize the main parameters of a cardiac electrophysiological (EP) model for predicting the response to different pacing conditions.

METHODS

First, an efficient forward model is proposed, coupling the Mitchell-Schaeffer transmembrane potential model with a current dipole formulation. Then, we estimate the main parameters of the cardiac model: activation onset location and tissue conductivity. A large patient-specific database of simulated BSPM is generated, from which specific features are extracted to train a machine learning algorithm. The activation onset location is computed from a Kernel Ridge Regression and a second regression calibrates the global ventricular conductivity.

RESULTS

The evaluation of the results is done both on a benchmark dataset of a patient with premature ventricular contraction (PVC) and on five nonischaemic implanted cardiac resynchonization therapy (CRT) patients with a total of 21 different pacing conditions. Good personalization results were found in terms of the activation onset location for the PVC (mean distance error, MDE = 20.3 mm), for the pacing sites (MDE = 21.7 mm) and for the CRT patients (MDE = 24.6 mm). We tested the predictive power of the personalized model for biventricular pacing and showed that we could predict the new electrical activity patterns with a good accuracy in terms of BSPM signals.

CONCLUSION

We have personalized the cardiac EP model and predicted new patient-specific pacing conditions.

SIGNIFICANCE

This is an encouraging first step towards a noninvasive preoperative prediction of the response to different pacing conditions to assist clinicians for CRT patient selection and therapy planning.

Regularization Techniques for ECG Imaging during Atrial Fibrillation: A Computational Study

The inverse problem of electrocardiography is usually analyzed during stationary rhythms. However, the performance of the regularization methods under fibrillatory conditions has not been fully studied. In this work, we assessed different regularization techniques during atrial fibrillation (AF) for estimating four target parameters, namely, epicardial potentials, dominant frequency (DF), phase maps, and singularity point (SP) location. We use a realistic mathematical model of atria and torso anatomy with three different electrical activity patterns (i.e., sinus rhythm, simple AF, and complex AF). Body surface potentials (BSP) were simulated using Boundary Element Method and corrupted with white Gaussian noise of different powers. Noisy BSPs were used to obtain the epicardial potentials on the atrial surface, using 14 different regularization techniques. DF, phase maps, and SP location were computed from estimated epicardial potentials. Inverse solutions were evaluated using a set of performance metrics adapted to each clinical target. For the case of SP location, an assessment methodology based on the spatial mass function of the SP location, and four spatial error metrics was proposed. The role of the regularization parameter for Tikhonov-based methods, and the effect of noise level and imperfections in the knowledge of the transfer matrix were also addressed. Results showed that the Bayes maximum-a-posteriori method clearly outperforms the rest of the techniques but requires a priori information about the epicardial potentials. Among the purely non-invasive techniques, Tikhonov-based methods performed as well as more complex techniques in realistic fibrillatory conditions, with a slight gain between 0.02 and 0.2 in terms of the correlation coefficient. Also, the use of a constant regularization parameter may be advisable since the performance was similar to that obtained with a variable parameter (indeed there was no difference for the zero-order Tikhonov method in complex fibrillatory conditions). Regarding the different targets, DF and SP location estimation were more robust with respect to pattern complexity and noise, and most algorithms provided a reasonable estimation of these parameters, even when the epicardial potentials estimation was inaccurate. Finally, the proposed evaluation procedure and metrics represent a suitable framework for techniques benchmarking and provide useful insights for the clinical practice.

Examining the Impact of Prior Models in Transmural Electrophysiological Imaging: A Hierarchical Multiple-Model Bayesian Approach

Noninvasive cardiac electrophysiological (EP) imaging aims to mathematically reconstruct the spatiotemporal dynamics of cardiac sources from body-surface electrocardiographic (ECG) data. This ill-posed problem is often regularized by a fixed constraining model. However, a fixed-model approach enforces the source distribution to follow a pre-assumed structure that does not always match the varying spatiotemporal distribution of actual sources. To understand the model-data relation and examine the impact of prior models, we present a multiple-model approach for volumetric cardiac EP imaging where multiple prior models are included and automatically picked by the available ECG data. Multiple models are incorporated as an Lp-norm prior for sources, where p is an unknown hyperparameter with a prior uniform distribution. To examine how different combinations of models may be favored by different measurement data, the posterior distribution of cardiac sources and hyperparameter p is calculated using a Markov Chain Monte Carlo (MCMC) technique. The importance of multiple-model prior was assessed in two sets of synthetic and real-data experiments, compared to fixed-model priors (using Laplace and Gaussian priors). The results showed that the posterior combination of models (the posterior distribution of p) as determined by the ECG data differed substantially when reconstructing sources with different sizes and structures. While the use of fixed models is best suited in situations where the prior assumption fits the actual source structures, the use of an automatically adaptive set of models may have the ability to better address model-data mismatch and to provide consistent performance in reconstructing sources with different properties.

Noninvasive reconstruction of cardiac transmembrane potentials using a kernelized extreme learning method

Non-invasively reconstructing the cardiac transmembrane potentials (TMPs) from body surface potentials can act as a regression problem. The support vector regression (SVR) method is often used to solve the regression problem, however the computational complexity of the SVR training algorithm is usually intensive. In this paper, another learning algorithm, termed as extreme learning machine (ELM), is proposed to reconstruct the cardiac transmembrane potentials. Moreover, ELM can be extended to single-hidden layer feed forward neural networks with kernel matrix (kernelized ELM), which can achieve a good generalization performance at a fast learning speed. Based on the realistic heart-torso models, a normal and two abnormal ventricular activation cases are applied for training and testing the regression model. The experimental results show that the ELM method can perform a better regression ability than the single SVR method in terms of the TMPs reconstruction accuracy and reconstruction speed. Moreover, compared with the ELM method, the kernelized ELM method features a good approximation and generalization ability when reconstructing the TMPs.

Variational Bayesian electrophysiological imaging of myocardial infarction

The presence, size, and distribution of ischemic tissue bear significant prognostic and therapeutic implication for ventricular arrhythmias. While many approaches to 3D infarct detection have been developed via electrophysiological (EP) imaging from noninvasive electrocardiographic data, this ill-posed inverse problem remains challenging especially for septal infarcts that are hidden from body-surface data. We propose a variational Bayesian framework for EP imaging of 3D infarct using a total-variation prior. The posterior distribution of intramural action potential and all regularization parameters are estimated from body-surface data by minimizing the Kullback-Leibler divergence. Because of the uncertainty introduced in prior models, we hypothesize that the solution uncertainty plays as important a role as the point estimate in interpreting the reconstruction. This is verified in a set of phantom and real-data experiments, where regions of low confidence help to eliminate false-positives and to accurately identify infarcts of various locations (including septum) and distributions. Owing to the ability of total-variation prior in extracting the boundary between smooth regions, the presented method also has the potential to outline infarct border that is the most critical region responsible for ventricular arrhvthmias.

Investigations of sensitivity and resolution of ECG and MCG in a realistically shaped thorax model

Solving the inverse problem of electrocardiography (ECG) and magnetocardiography (MCG) is often referred to as cardiac source imaging. Spatial properties of ECG and MCG as imaging systems are, however, not well known. In this modelling study, we investigate the sensitivity and point-spread function (PSF) of ECG, MCG, and combined ECG+MCG as a function of source position and orientation, globally around the ventricles: signal topographies are modelled using a realistically-shaped volume conductor model, and the inverse problem is solved using a distributed source model and linear source estimation with minimal use of prior information. The results show that the sensitivity depends not only on the modality but also on the location and orientation of the source and that the sensitivity distribution is clearly reflected in the PSF. MCG can better characterize tangential anterior sources (with respect to the heart surface), while ECG excels with normally-oriented and posterior sources. Compared to either modality used alone, the sensitivity of combined ECG+MCG is less dependent on source orientation per source location, leading to better source estimates. Thus, for maximal sensitivity and optimal source estimation, the electric and magnetic measurements should be combined.

Noninvasive transmural electrophysiological imaging based on minimization of total-variation functional

While tomographic imaging of cardiac structure and kinetics has improved substantially, electrophysiological mapping of the heart is still restricted to the surface with little or no depth information beneath. The progress in reconstructing 3-D action potential from surface voltage data has been hindered by the intrinsic ill-posedness of the problem and the lack of a unique solution in the absence of prior assumptions. In this work, we propose a novel adaption of the total-variation (TV) prior to exploit the unique spatial property of transmural action potential of being piecewise smooth with a steep boundary (gradient) separating depolarized and repolarized regions. We present a variational TV-prior instead of a common discrete TV-prior for improved robustness to mesh resolution, and solve the TV-minimization by a sequence of weighted, first-order L2-norm minimization. In a large set of phantom experiments, the proposed method is shown to outperform existing quadratic methods in preserving the steep gradient of action potential along the border of infarcts, as well as in capturing the disruption to the normal path of electrical wavefronts. Real-data experiments also further demonstrate the potential of the proposed method in revealing the location and shape of infarcts when quadratic methods fail to do so.

A novel total variation based noninvasive transmural electrophysiological imaging

While tomographic imaging of cardiac structure and kinetics has improved substantially, electrophysiological mapping of the heart is still restricted to the body or heart surface with little or no depth information beneath. The progress in reconstructing transmural action potentials from surface voltage data has been hindered by the challenges of intrinsic ill-posedness and the lack of a unique solution in the absence of prior assumptions. In this work, we propose to exploit the unique spatial property of transmural action potentials that it is often piece-wise smooth with a steep boundary (gradient) separating the depolarized and repolarized regions. This steep gradient could reveal normal or disrupted electrical propagation wavefronts, or pinpoint the border between viable and necrotic tissue. In this light, we propose a novel adaption of the total-variation (TV) prior into the reconstruction of transmural action potentials, where a variational TV operator is defined instead of a common discrete operator, and the TV-minimization is solved by a sequence of weighted, first-order L2-norm minimizations. In a large set of phantom experiments performed on image-derived human heart-torso models, the proposed method is shown to outperform existing quadratic methods in preserving the steep gradient of action potentials along the border of infarcts, as well as in capturing the disruption to the normal path of electrical wavefronts. The former is further attested by real-data experiments on two post-infarction human subjects, demonstrating the potential of the proposed method in revealing the location and shape of the underlying infarcts when existing quadratic methods fail to do so.

Hierarchical multiple-model Bayesian approach to transmural electrophysiological imaging

Noninvasive electrophysiological (EP) imaging of the heart aims to mathematically reconstruct the spatiotemporal dynamics of cardiac current sources from body-surface electrocardiographic (ECG) data. This ill-posed problem is often regularized by a fixed constraining model. However, this approach enforces the source distribution to follow a preassumed spatial structure that does not always match the varying spatiotemporal distribution of current sources. We propose a hierarchical Bayesian approach to transmural EP imaging that employs a continuous combination of multiple models, each reflecting a specific spatial property for current sources. Multiple models are incorporated as an Lp-norm prior for current sources, where p is an unknown hyperparameter with a prior probabilistic distribution. The current source estimation is obtained as an optimally weighted combination of solutions across all models, the weight being determined from the posterior distribution of p inferred from ECG data. The accuracy of our approach is assessed in a set of synthetic and real-data experiments on human heart-torso models. While the use of fixed models (L1- and L2-norm) only properly recovers sources with specific structures, our method delivers consistent performance in reconstructing sources with various extents and structures.

Assessment of regularization techniques for electrocardiographic imaging

A widely used approach to solving the inverse problem in electrocardiography involves computing potentials on the epicardium from measured electrocardiograms (ECGs) on the torso surface. The main challenge of solving this electrocardiographic imaging (ECGI) problem lies in its intrinsic ill-posedness. While many regularization techniques have been developed to control wild oscillations of the solution, the choice of proper regularization methods for obtaining clinically acceptable solutions is still a subject of ongoing research. However there has been little rigorous comparison across methods proposed by different groups. This study systematically compared various regularization techniques for solving the ECGI problem under a unified simulation framework, consisting of both 1) progressively more complex idealized source models (from single dipole to triplet of dipoles), and 2) an electrolytic human torso tank containing a live canine heart, with the cardiac source being modeled by potentials measured on a cylindrical cage placed around the heart. We tested 13 different regularization techniques to solve the inverse problem of recovering epicardial potentials, and found that non-quadratic methods (total variation algorithms) and first-order and second-order Tikhonov regularizations outperformed other methodologies and resulted in similar average reconstruction errors.

Inverse Electrocardiographic Source Localization of Ischemia: An Optimization Framework and Finite Element Solution

With the goal of non-invasively localizing cardiac ischemic disease using body-surface potential recordings, we attempted to reconstruct the transmembrane potential (TMP) throughout the myocardium with the bidomain heart model. The task is an inverse source problem governed by partial differential equations (PDE). Our main contribution is solving the inverse problem within a PDE-constrained optimization framework that enables various physically-based constraints in both equality and inequality forms. We formulated the optimality conditions rigorously in the continuum before deriving finite element discretization, thereby making the optimization independent of discretization choice. Such a formulation was derived for the L₂-norm Tikhonov regularization and the total variation minimization. The subsequent numerical optimization was fulfilled by a primal-dual interior-point method tailored to our problem's specific structure. Our simulations used realistic, fiber-included heart models consisting of up to 18,000 nodes, much finer than any inverse models previously reported. With synthetic ischemia data we localized ischemic regions with roughly a 10% false-negative rate or a 20% false-positive rate under conditions up to 5% input noise. With ischemia data measured from animal experiments, we reconstructed TMPs with roughly 0.9 correlation with the ground truth. While precisely estimating the TMP in general cases remains an open problem, our study shows the feasibility of reconstructing TMP during the ST interval as a means of ischemia localization.

Computing ischemic regions in the heart with the bidomain model--first steps towards validation

We investigate whether it is possible to use the bidomain model and body surface potential maps (BSPMs) to compute the size and position of ischemic regions in the human heart. This leads to a severely ill posed inverse problem for a potential equation. We do not use the classical inverse problems of electrocardiography, in which the unknown sources are the epicardial potential distribution or the activation sequence. Instead we employ the bidomain theory to obtain a model that also enables identification of ischemic regions transmurally. This approach makes it possible to distinguish between subendocardial and transmural cases, only using the BSPM data. The main focus is on testing a previously published algorithm on clinical data, and the results are compared with images taken with perfusion scintigraphy. For the four patients involved in this study, the two modalities produce results that are rather similar: The relative differences between the center of mass and the size of the ischemic regions, suggested by the two modalities, are 10.8% ± 4.4% and 7.1% ± 4.6%, respectively. We also present some simulations which indicate that the methodology is robust with respect to uncertainties in important model parameters. However, in contrast to what has been observed in investigations only involving synthetic data, inequality constraints are needed to obtain sound results.

A hybrid model of maximum margin clustering method and support vector regression for noninvasive electrocardiographic imaging

Noninvasive electrocardiographic imaging, such as the reconstruction of myocardial transmembrane potentials (TMPs) distribution, can provide more detailed and complicated electrophysiological information than the body surface potentials (BSPs). However, the noninvasive reconstruction of the TMPs from BSPs is a typical inverse problem. In this study, this inverse ECG problem is treated as a regression problem with multi-inputs (BSPs) and multioutputs (TMPs), which will be solved by the Maximum Margin Clustering- (MMC-) Support Vector Regression (SVR) method. First, the MMC approach is adopted to cluster the training samples (a series of time instant BSPs), and the individual SVR model for each cluster is then constructed. For each testing sample, we find its matched cluster and then use the corresponding SVR model to reconstruct the TMPs. Using testing samples, it is found that the reconstructed TMPs results with the MMC-SVR method are more accurate than those of the single SVR method. In addition to the improved accuracy in solving the inverse ECG problem, the MMC-SVR method divides the training samples into clusters of small sample sizes, which can enhance the computation efficiency of training the SVR model.

Application of L1-norm regularization to epicardial potential reconstruction based on gradient projection

The epicardial potential (EP)-targeted inverse problem of electrocardiography (ECG) has been widely investigated as it is demonstrated that EPs reflect underlying myocardial activity. It is a well-known ill-posed problem as small noises in input data may yield a highly unstable solution. Traditionally, L2-norm regularization methods have been proposed to solve this ill-posed problem. But the L2-norm penalty function inherently leads to considerable smoothing of the solution, which reduces the accuracy of distinguishing abnormalities and locating diseased regions. Directly using the L1-norm penalty function, however, may greatly increase computational complexity due to its non-differentiability. We propose an L1-norm regularization method in order to reduce the computational complexity and make rapid convergence possible. Variable splitting is employed to make the L1-norm penalty function differentiable based on the observation that both positive and negative potentials exist on the epicardial surface. Then, the inverse problem of ECG is further formulated as a bound-constrained quadratic problem, which can be efficiently solved by gradient projection in an iterative manner. Extensive experiments conducted on both synthetic data and real data demonstrate that the proposed method can handle both measurement noise and geometry noise and obtain more accurate results than previous L2- and L1-norm regularization methods, especially when the noises are large.

Finite-element-based discretization and regularization strategies for 3-D inverse electrocardiography

We consider the inverse electrocardiographic problem of computing epicardial potentials from a body-surface potential map. We study how to improve numerical approximation of the inverse problem when the finite-element method is used. Being ill-posed, the inverse problem requires different discretization strategies from its corresponding forward problem. We propose refinement guidelines that specifically address the ill-posedness of the problem. The resulting guidelines necessitate the use of hybrid finite elements composed of tetrahedra and prism elements. Also, in order to maintain consistent numerical quality when the inverse problem is discretized into different scales, we propose a new family of regularizers using the variational principle underlying finite-element methods. These variational-formed regularizers serve as an alternative to the traditional Tikhonov regularizers, but preserves the L(2) norm and thereby achieves consistent regularization in multiscale simulations. The variational formulation also enables a simple construction of the discrete gradient operator over irregular meshes, which is difficult to define in traditional discretization schemes. We validated our hybrid element technique and the variational regularizers by simulations on a realistic 3-D torso/heart model with empirical heart data. Results show that discretization based on our proposed strategies mitigates the ill-conditioning and improves the inverse solution, and that the variational formulation may benefit a broader range of potential-based bioelectric problems.

Non-invasive imaging of cardiac activation and recovery

The sequences of activation and recovery of the heart have physiological and clinical relevance. We report on progress made over the last years in the method that images these timings based on an equivalent double layer on the myocardial surface serving as the equivalent source of cardiac activity, with local transmembrane potentials (TMP) acting as their strength. The TMP wave forms were described analytically by timing parameters, found by minimizing the difference between observed body surface potentials and those based on the source description. The parameter estimation procedure involved is non-linear, and consequently requires the specification of initial estimates of its solution. Those of the timing of depolarization were based on the fastest route algorithm, taking into account properties of anisotropic propagation inside the myocardium. Those of recovery were based on electrotonic effects. Body surface potentials and individual geometry were recorded on: a healthy subject, a WPW patient and a Brugada patient during an Ajmaline provocation test. In all three cases, the inversely estimated timing agreed entirely with available physiological knowledge. The improvements to the inverse procedure made are attributed to our use of initial estimates based on the general electrophysiology of propagation. The quality of the results and the required computation time permit the application of this inverse procedure in a clinical setting.

Non-invasive imaging of cardiac activation and recovery

The sequences of activation and recovery of the heart have physiological and clinical relevance. We report on progress made over the last years in the method that images these timings based on an equivalent double layer on the myocardial surface serving as the equivalent source of cardiac activity, with local transmembrane potentials (TMP) acting as their strength. The TMP wave forms were described analytically by timing parameters, found by minimizing the difference between observed body surface potentials and those based on the source description. The parameter estimation procedure involved is non-linear, and consequently requires the specification of initial estimates of its solution. Those of the timing of depolarization were based on the fastest route algorithm, taking into account properties of anisotropic propagation inside the myocardium. Those of recovery were based on electrotonic effects. Body surface potentials and individual geometry were recorded on: a healthy subject, a WPW patient and a Brugada patient during an Ajmaline provocation test. In all three cases, the inversely estimated timing agreed entirely with available physiological knowledge. The improvements to the inverse procedure made are attributed to our use of initial estimates based on the general electrophysiology of propagation. The quality of the results and the required computation time permit the application of this inverse procedure in a clinical setting.