Feasibility study shows concordance between image-based virtual-heart ablation targets and predicted ECG-based arrhythmia exit-sites.

INTRODUCTION: We recently developed two noninvasive methodologies to help guide VT ablation: population-derived automated VT exit localization (PAVEL) and virtual-heart arrhythmia ablation targeting (VAAT). We hypothesized that while very different in their nature, limitations, and type of ablation targets (substrate-based vs. clinical VT), the image-based VAAT and the ECG-based PAVEL technologies would be spatially concordant in their predictions. OBJECTIVE: The objective is to test this hypothesis in ischemic cardiomyopathy patients in a retrospective feasibility study. METHODS: Four post-infarct patients who underwent LV VT ablation and had pre-procedural LGE-CMRs were enrolled. Virtual hearts with patient-specific scar and border zone identified potential VTs and ablation targets. Patient-specific PAVEL based on a population-derived statistical method localized VT exit sites onto a patient-specific 238-triangle LV endocardial surface. RESULTS: Ten induced VTs were analyzed and 9-exit sites were localized by PAVEL onto the patient-specific LV endocardial surface. All nine predicted VT exit sites were in the scar border zone defined by voltage mapping and spatially correlated with successful clinical lesions. There were 2.3 ± 1.9 VTs per patient in the models. All five VAAT lesions fell within regions ablated clinically. VAAT targets correlated well with 6 PAVEL-predicted VT exit sites. The distance between the center of the predicted VT-exit-site triangle and nearest corresponding VAAT ablation lesion was 10.7 ± 7.3 mm. CONCLUSIONS: VAAT targets are concordant with the patient-specific PAVEL-predicted VT exit sites. These findings support investigation into combining these two complementary technologies as a noninvasive, clinical tool for targeting clinically induced VTs and regions likely to harbor potential VTs.

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.

Non-invasive epicardial and endocardial electrocardiographic imaging for scar-related ventricular tachycardia.

Aims: Contact mapping is currently used to guide catheter ablation of scar-related ventricular tachycardia (VT) but usually provides incomplete assessment of 3D re-entry circuits and their arrhythmogenic substrates. This study investigates the feasibility of non-invasive electrocardiographic imaging (ECGi) in mapping scar substrates and re-entry circuits throughout the epicardium and endocardium. Methods and results: Four patients undergoing endocardial and epicardial mapping and ablation of scar-related VT had computed tomography scans and a 120-lead electrocardiograms, which were used to compute patient-specific ventricular epicardial and endocardial unipolar electrograms (CEGMs). Native-rhythm CEGMs were used to identify sites of myocardial scar and signal fractionation. Computed electrograms of induced VT were used to localize re-entrant circuits and exit sites. Results were compared to in vivo contact mapping data and epicardium-based ECGi solutions. During native rhythm, an average of 493 ± 18 CEGMs were analysed on each patient. Identified regions of scar and fractionation comprised, respectively, 25 ± 4% and 2 ± 1% of the ventricular surface area. Using a linear mixed-effects model grouped at the level of an individual patient, CEGM voltage and duration were significantly associated with contact bipolar voltage. During induced VT, the inclusion of endocardial layer in ECGi made it possible to identify two epicardial vs. three endocardial VT exit sites among five reconstructed re-entry circuits. Conclusion: Electrocardiographic imaging may be used to reveal sites of signal fractionation and to map short-lived VT circuits. Its capacity to map throughout epicardial and endocardial layers may improve the delineation of 3D re-entry circuits and their arrhythmogenic substrates.

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.

Criteria for ECG detection of acute myocardial ischemia: Sensitivity versus specificity.

BACKGROUND: Criteria for electrocardiographic detection of acute myocardial ischemia recommended by the Consensus Document of ESC/ACCF/AHA/WHF consist of two parts: The ST elevation myocardial infarction (STEMI) criteria based on ST elevation (ST↑) in 10 pairs of contiguous leads and the other on ST depression (ST↓) in the same 10 contiguous pairs. Our aim was to assess sensitivity (SE) and specificity (SP) of these criteria-and to seek their possible improvements-in three databases of 12­lead ECGs. METHODS: We used (1) STAFF III data of controlled ischemic episodes recorded from 99 patients (pts) during percutaneous coronary intervention (PCI) involving either left anterior descending (LAD) coronary artery, right coronary artery (RCA), or left circumflex (LCx) coronary artery. (2) Data from the University of Glasgow for 58 pts with acute myocardial infarction (AMI) and 58 pts without AMI, as confirmed by MRI. (3) Data from Lund University retrieved from a centralized ECG management system for 100 pts with various pathological ST changes-other than acute coronary occlusion-including ventricular pre-excitation, acute pericarditis, early repolarization syndrome, left ventricular hypertrophy, and left bundle branch block. ST measurements at J-point in ECGs of all 315 pts were obtained automatically on the averaged beat with manual review and the recommended criteria as well as their proposed modifications, were applied. Performance measures included SE, SP, positive predictive value (PPV), and benefit-to-harm ratio (BHR), defined as the ratio of true-positive vs. false-positive detections. RESULTS: We found that the SE of widely-used STEMI criteria can be indeed improved by the additional ST↓ criteria, but at the cost of markedly decreased SP. In contrast, using ST↑ in only 3 additional contiguous pairs of leads (STEMI13) can boost SE without any loss of SP. In the STAFF III database, SE/SP/PPV were 56/98/97% for the STEMI, 79/79/79% for the STEMI with added ST↓ and 67/97/96% for the STEMI13. In the Glasgow database, corresponding SE/SP/PPV were 43/98/96%, 84/90/89%, and 55/98/97%. For the Lund database, SP was 56% for the STEMI, 24% for the STEMI with ST↓, and 56% for the STEMI13. CONCLUSION: Current recommended criteria for detecting acute myocardial ischemia, involving ST↓, boost SE of widely-used STEMI criteria, at the cost of SP. To keep the SP high, we propose either the adjustment of threshold for the added ST↓ criteria or a selective use of ST↓ only in contiguous leads V2 and V3 plus ST↑ in lead pairs (aVL, -III) and (III, -aVL).

Insights from Novel Noninvasive CT and ECG Imaging Modalities on Electromechanical Myocardial Activation in a Canine Model of Ischemic Dyssynchronous Heart Failure.

INTRODUCTION: The interplay between electrical activation and mechanical contraction patterns is hypothesized to be central to reduced effectiveness of cardiac resynchronization therapy (CRT). Furthermore, complex scar substrates render CRT less effective. We used novel cardiac computed tomography (CT) and noninvasive electrocardiographic imaging (ECGI) techniques in an ischemic dyssynchronous heart failure (DHF) animal model to evaluate electrical and mechanical coupling of cardiac function, tissue viability, and venous accessibility of target pacing regions. METHODS AND RESULTS: Ischemic DHF was induced in 6 dogs using coronary occlusion, left bundle ablation and tachy RV pacing. Full body ECG was recorded during native rhythm followed by volumetric first-pass and delayed enhancement CT. Regional electrical activation were computed and overlaid with segmented venous anatomy and scar regions. Reconstructed electrical activation maps show consistency with LBBB starting on the RV and spreading in a "U-shaped" pattern to the LV. Previously reported lines of slow conduction are seen parallel to anterior or inferior interventricular grooves. Mechanical contraction showed large septal to lateral wall delay (80 ± 38 milliseconds vs. 123 ± 31 milliseconds, P = 0.0001). All animals showed electromechanical correlation except dog 5 with largest scar burden. Electromechanical decoupling was largest in basal lateral LV segments. CONCLUSION: We demonstrated a promising application of CT in combination with ECGI to gain insight into electromechanical function in ischemic dyssynchronous heart failure that can provide useful information to study regional substrate of CRT candidates.

Noninvasive epicardial and endocardial electrocardiographic imaging of scar-related ventricular tachycardia.

BACKGROUND: The majority of life-threatening ventricular tachycardias (VTs) are sustained by heterogeneous scar substrates with narrow strands of surviving tissue. An effective treatment for scar-related VT is to modify the underlying scar substrate by catheter ablation. If activation sequence and entrainment mapping can be performed during sustained VT, the exit and isthmus of the circuit can often be identified. However, with invasive catheter mapping, only monomorphic VT that is hemodynamically stable can be mapped in this manner. For the majority of patients with poorly tolerated VTs or multiple VTs, a close inspection of the re-entry circuit is not possible. A noninvasive approach to fast mapping of unstable VTs can potentially allow an improved identification of critical ablation sites. METHODS: For patients who underwent catheter ablation of scar-related VT, CT scan was obtained prior to the ablation procedure and 120-lead body-surface electrocardiograms (ECGs) were acquired during induced VTs. These data were used for noninvasive ECG imaging to computationally reconstruct electrical potentials on the epicardium and on the endocardium of both ventricles. Activation time and phase maps of the VT circuit were extracted from the reconstructed electrograms. They were analyzed with respect to scar substrate obtained from catheter mapping, as well as VT exits confirmed through ablation sites that successfully terminated the VT. RESULTS: The reconstructed re-entry circuits correctly revealed both epicardial and endocardial origins of activation, consistent with locations of exit sites confirmed from the ablation procedure. The temporal dynamics of the re-entry circuits, particularly the slowing of conduction as indicated by the crowding and zig-zag conducting of the activation isochrones, collocated well with scar substrate obtained by catheter voltage maps. Furthermore, the results indicated that some re-entry circuits involve both the epicardial and endocardial layers, and can only be properly interpreted by mapping both layers simultaneously. CONCLUSIONS: This study investigated the potential of ECG-imaging for beat-to-beat mapping of unstable reentrant circuits. It shows that simultaneous epicardial and endocardial mapping may improve the delineation of the 3D spatial construct of a re-entry circuit and its exit. It also shows that the use of phase mapping can reveal regions of slow conduction that collocate well with suspected heterogeneous regions within and around the scar.

Validation of the vessel-specific leads (VSLs) for detection of acute ischemia on a dataset with non-ischemic ST-segment deviation.

BACKGROUND: Existing criteria recommended by ACC/ESC for identifying patients with ST elevation myocardial infarction (STEMI) from the 12-lead ECG perform with high specificity (SP) but low sensitivity (SE). In our previous studies, we found that the SE of acute ischemia detection can be markedly improved without any loss of SP by calculating, from the 12-lead ECG, ST deviation in 3 "optimal" vessel-specific leads (VSLs). To further validate the method, we evaluated the SP performance using a dataset with non-ischemic ST-segment changes. METHODS: 12-lead ECGs of 100 patients (75 males/25 females, age range 12-83years, average age 52years) were retrieved from a centralized ECG management system at Skåne University Hospital, Lund, Sweden. These ECGs were chosen to represent five subgroups with various causes of pathological ST deviation, other than acute coronary occlusion: a) ventricular preexcitation (n=12), b) acute pericarditis (n=26), c) early repolarization syndrome (ERS) (n=14), d) left ventricular hypertrophy (LVH) with "strain" (n=26), and e) left bundle branch block (LBBB) (n=22). ECGs with inadequate signal quality, heart rate exceeding 120bpm and/or atrial flutter were not selected for this study population. Both STEMI criteria and VSLs criteria with and without a new augmented LVH-specific derived lead were tested. SP, calculated for each subgroup and combined, was used as the performance measure for comparison. RESULTS: SP test results for the STEMI criteria vs. the VSLs method without the augmented LVH lead were 100% vs. 92%, 4% vs. 88%, 29% vs. 100%, 100% vs. 77%, and 64% vs. 68% for the five subgroups with preexcitation, pericarditis, ERS, LVH, and LBBB, respectively. For the whole group, SP was 57% for the STEMI criteria and 83% for the VSLs criteria; this improvement was statistically significant (p<0.001). With the augmented LVH lead, SP for the VSLs improved from 77% to 96% for the LVH subgroup and SP for the other subgroups remained unchanged. For the whole study group, SP improved from 83% to 88%. CONCLUSION: Based on these results, we conclude that the VSLs criteria are not only more sensitive in detecting acute ischemia but also more specific in recognizing patients with non-ischemic ST deviation than the existing STEMI criteria. This finding needs to be further corroborated on a larger patient population with AMI prevalence typical of the population presenting to the emergency room.

Non-invasive electromechanical activation imaging as a tool to study left ventricular dyssynchronous patients: Implication for CRT therapy.

AIMS: Electromechanical de-coupling is hypothesized to explain non-response of dyssynchrony patient to cardiac resynchronization therapy (CRT). In this pilot study, we investigated regional electromechanical uncoupling in 10 patients referred for CRT using two non-invasive electrical and mechanical imaging techniques (CMR tissue tracking and ECGI). METHODS AND RESULTS: Reconstructed regional electrical and mechanical activation captured delayed LBBB propagation direction from septal to anterior/inferior and finally to lateral walls as well as from LV apical to basal. All 5 responders demonstrated significantly delayed mechanical and electrical activation on the lateral LV wall at baseline compared to the non-responders (P<.05). On follow-up ECGI, baseline electrical activation patterns were preserved in native rhythm and global LV activation time was reduced with biventricular pacing. CONCLUSIONS: The combination of novel imaging techniques of ECGI and CMR tissue tracking can be used to assess spatial concordance of LV electrical and mechanical activation to gain insight into electromechanical coupling.

Noninvasive electrocardiographic imaging of chronic myocardial infarct scar.

BACKGROUND: Myocardial infarction (MI) scar constitutes a substrate for ventricular tachycardia (VT), and an accurate delineation of infarct scar may help to identify reentrant circuits and thus facilitate catheter ablation. One of the recent advancements in characterization of a VT substrate is its volumetric delineation within the ventricular wall by noninvasive electrocardiographic imaging. This paper compares, in four specific cases, epicardial and volumetric inverse solutions, using magnetic resonance imaging (MRI) with late gadolinium enhancement as a gold standard. METHODS: For patients with chronic MI, who presented at Glasgow Western Infirmary, delayed-enhancement MRI and 120-lead body surface potential mapping (BSPM) data were acquired and 4 selected cases were later made available to a wider community as part of the 2007 PhysioNet/Computers in Cardiology Challenge. These data were used to perform patient-specific inverse solutions for epicardial electrograms and morphology-based criteria were applied to delineate infarct scar on the epicardial surface. Later, the Rochester group analyzed the same data by means of a novel inverse solution for reconstructing intramural transmembrane potentials, to delineate infarct scar in three dimensions. Comparison of the performance of three specific inverse-solution algorithms is presented here, using scores based on the 17-segment ventricular division scheme recommended by the American Heart Association. RESULTS: The noninvasive methods delineating infarct scar as three-dimensional (3D) intramural distribution of transmembrane action potentials outperform estimates providing scar delineation on the epicardial surface in all scores used for comparison. In particular, the extent of infarct scar (its percentage mass relative to the total ventricular mass) is rendered more accurately by the 3D estimate. Moreover, the volumetric rendition of scar border provides better clues to potential targets for catheter ablation. CONCLUSIONS: Electrocardiographic inverse solution providing transmural distribution of ventricular action potentials is a promising tool for noninvasively delineating the extent and location of chronic MI scar. Further validation on a larger data set with detailed gold-standard data is needed to confirm observations reported in this study.

Validation of improved vessel-specific leads (VSLs) for detecting acute myocardial ischemia.

BACKGROUND: Existing criteria recommended by ACC/ESC for identifying patients with ST elevation myocardial infarction (STEMI) from the 12-lead ECG perform with high specificity (SP), but low sensitivity (SE). In our previous studies, we found that the SE of ischemia detection can be markedly improved without any loss of SP by calculating, from the 12-lead ECG, ST deviation in 3 "optimal" vessel-specific leads (VSLs). Our original VSLs, based on ΔST body-surface potential maps (BSPMs), have been modified by using the more appropriate J-point BSPMs at peak ischemia (without subtraction of pre-occlusion distributions). The aim of the present study was to compare the performance of these new VSLs with that achieved by the STEMI criteria used in current practice. METHODS: Two independent datasets of 12-lead ECGs were used: the STAFF III dataset acquired during ischemic episodes caused by balloon inflation in LAD (n=35), RCA (n=47), and LCx (n=17) coronary arteries, and the Glasgow dataset comprising admission 12-lead ECGs of 116 patients who were hospitalized for chest pain and underwent contrast-enhanced cardiac MRI that confirmed AMI in 58 patients (50%). RESULTS: We found that, in the STAFF III dataset, the detection of ischemic state by the STEMI criteria attained SE/SP of 60/97%, whereas SE/SP values of VSLs were 72/98%. In the Glasgow dataset, STEMI criteria yielded SE/SP of 43/98%, whereas the VSLs improved SE/SP to 60/98%. The most significant increase in diagnostic performance appeared in patients with LCx coronary artery occlusion: in STAFF III data (n=17) SE achieved by STEMI criteria was improved by the VSLs from 35% to 71%; in Glasgow data (n=12) SE of 31% achieved by STEMI criteria was improved by the VSLs to 69%. CONCLUSION: In our study population, existing ACC/ESC STEMI criteria complemented by the new VSLs yielded much improved sensitivity of ischemia detection without any detrimental effect on specificity. This finding needs to be corroborated on a larger chest-pain patient population with typical prevalence of acute ischemia presented to the emergency rooms.

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.

Difference vectors to describe dynamics of the ST segment and the ventricular gradient in acute ischemia.

BACKGROUND: The ECG is important in the diagnosis and triage of the acute coronary syndrome (ACS), especially in the hyperacute phase, the "golden hours," during which myocardial salvage possibilities are largest. An important triaging decision to be taken is whether or not a patient requires primary PCI, for which, as mentioned in the guidelines, the presence of an ST elevation (STE) pattern in the ECG is a major criterion. However, preexisting non-zero ST amplitudes (diagnostic, but also non-diagnostic) can obscure or even preclude this diagnosis. METHODS: In this study, we investigated the potential diagnostic possibilities of ischemia detection by means of changes in the ST vector, ΔST, and changes in the VG (QRST integral) vector, ΔVG. We studied the vectorcardiograms (VCGs) synthesized of the ECGs of 84 patients who underwent elective PTCA. Mean±SD balloon occlusion times were 260±76s. The ECG ischemia diagnosis (ST elevation, STE, or non-ST-elevation, NSTE), magnitudes and orientations of the ST and VG vectors, and the differences ΔST and ΔVG with the baseline ECG were measured after 3min of balloon occlusion. RESULTS: Planar angles between the ΔST and ΔVG vectors were 14.9±14.0°. Linear regression of ΔVG on ΔST yielded ΔVG=324·ΔST (r=0.85; P<0.0001, ΔST in mV). We adopted ΔST>0.05mV, and the corresponding ΔVG>16.2mV·ms as ischemia thresholds. The classical criteria characterized the ECGs of 46/84 (55%) patients after 3min of occlusion as STE ECGs. Combined application of the ΔST and ΔVG criteria identified 73/84 (87%) of the patients as ischemic. CONCLUSION: Differential diagnosis by ΔST and ΔVG (requiring an earlier made non-ischemic baseline ECG) could dramatically improve ECG guided detection of patients who urgently require catheter intervention.

Discrimination of ST deviation caused by acute coronary occlusion from normal variants and other abnormal conditions, using computed electrocardiographic imaging based on 12-lead ECG.

BACKGROUND: Many graphical methods for displaying ST-segment deviation in the ECG have been tried for enhancing decision-making in patients with suspected acute coronary syndromes. Computed electrocardiographic imaging (CEI), based on a mathematical inverse solution, has been recently applied to transform ST-J point measurements made in conventional 12-lead ECG into a display of epicardial potentials in bull's-eye format. The purpose of this study is to assess utility of CEI in the clinical setting. METHODS: In 99 patients with stable coronary disease, 12-lead ECGs were recorded during elective percutaneous coronary intervention (PCI), first before balloon-catheter insertion and then when an intracoronary balloon blocked blood supply to a region of myocardium for more than 4minutes (typically 5minutes). Four groups of patients were additionally studied, namely those with preexcitation, pericarditis, early repolarization syndrome (ERS), and left ventricular hypertrophy (LVH) with strain. Comparisons between performances of published criteria for ST-elevation myocardial infarction (STEMI) and quantitative as well as visual assessment of CEI images were based on sensitivities and specificities. RESULTS: Visual assessment of CEI outperformed STEMI criteria. This was especially evident for the capability of detecting LCx occlusion with sensitivities for STEMI criteria=35% and for visual assessment of CEI by 2 physicians=71%, i. e. twice as many patients were correctly identified by CEI. False positive rates for CEI were low in patients with LVH with strain as well as with preexcitation for both methods. For pericarditis and ERS, visual as well as quantitative assessment of CEI performed better than STEMI criteria. CONCLUSION: Visual assessment of CEI is a promising method for increasing the accuracy of ECG-based triage to PCI or conservative care.

Learning to Disentangle Inter-Subject Anatomical Variations in Electrocardiographic Data.

OBJECTIVE: This work investigates the possibility of disentangled representation learning of inter-subject anatomical variations within electrocardiographic (ECG) data. METHODS: Since ground truth anatomical factors are generally not known in clinical ECG for assessing the disentangling ability of the models, the presented work first proposes the SimECG data set, a 12-lead ECG data set procedurally generated with a controlled set of anatomical generative factors. Second, to perform such disentanglement, the presented method evaluates and compares deep generative models with latent density modeled by nonparametric Indian Buffet Process to account for the complex generative process of ECG data. RESULTS: In the simulated data, the experiments demonstrate, for the first time, concrete evidence of the possibility to disentangle key generative anatomical factors within ECG data in separation from task-relevant generative factors. We achieve a disentanglement score of 92.1% while disentangling five anatomical generative factors and the task-relevant generative factor. In both simulated and real-data experiments, this work further provides quantitative evidence for the benefit of disentanglement learning on the downstream clinical task of localizing the origin of ventricular activation. Overall, the presented method achieves an improvement of around 18.5%, and 11.3% for the simulated dataset, and around 7.2%, and 3.6% for the real dataset, over baseline CNN, and standard generative model, respectively. CONCLUSION: These results demonstrate the importance as well as the feasibility of the disentangled representation learning of inter-subject anatomical variations within ECG data. SIGNIFICANCE: This work suggests the important research direction to deal with the well-known challenge posed by the presence of significant inter-subject variations during an automated analysis of ECG data.

Comparison of epicardial potential maps derived from the 12-lead electrocardiograms with scintigraphic images during controlled myocardial ischemia.

Our aim was to cross-validate electrocardiographic (ECG) and scintigraphic imaging of acute myocardial ischemia. The former method was based on inverse calculation of heart-surface potentials from the body-surface ECGs, and the latter, on a single photon emission computed tomography (SPECT). A boundary-element torso model with 352 body-surface and 202 heart-surface nodes was used to perform the ECG inverse solution. Potentials at 352 body-surface nodes were calculated from those acquired at 12-lead ECG measurement sites using regression coefficients developed from a design set (n = 892) of body-surface potential mapping (BSPM) data. The test set (n = 18) consisted of BSPM data from patients who underwent a balloon-inflation angioplasty of either the left anterior descending coronary artery (LAD) (n = 7), left circumflex coronary artery (LCx) (n = 2), or the right coronary artery (RCA) (n = 9). Body-surface potential mapping distributions at J point for 352 nodes were estimated from the 12-lead ECG, and an agreement with those estimated from 120 leads was assessed by a correlation coefficient (CC) (in percent). These estimates yielded very similar BSPM distributions, with a CC of 91.0% ± 8.1% (mean ± SD) for the entire test set and 94.1% ± 1.4%, 96.7% ± 0.8%, and 87.4% ± 10.3% for LAD, LCx, and RCA subgroups, respectively. Corresponding heart-surface potential distributions obtained by inverse solution correlated with a lower CC of 69.3% ± 18.0% overall and 73.7% ± 10.8%, 84.7% ± 1.1%, and 62.6% ± 21.8%, respectively, for subgroups. Bull's-eye displays of heart-surface potentials calculated from estimated BSPM distributions had an area of positive potentials that qualitatively corresponded, in general, with the underperfused territory suggested by SPECT images. For the LAD and LCx groups, all 9 ECG-derived bull's-eye images indicated the expected territory; for the RCA group, 6 of 9 ECG-derived images were as expected; 2 of 3 misclassified cases had very small ECG changes in response to coronary-artery occlusion, and their SPECT images showed indiscernible patterns. In conclusion, our findings demonstrate that noninvasive ECG imaging based on just the 12-lead ECG might provide useful estimates of the regions of myocardial ischemia that agree with those provided by scintigraphic techniques.

Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning.

Probabilistic estimation of cardiac electrophysiological model parameters serves an important step toward model personalization and uncertain quantification. The expensive computation associated with these model simulations, however, makes direct Markov Chain Monte Carlo (MCMC) sampling of the posterior probability density function (pdf) of model parameters computationally intensive. Approximated posterior pdfs resulting from replacing the simulation model with a computationally efficient surrogate, on the other hand, have seen limited accuracy. In this study, we present a Bayesian active learning method to directly approximate the posterior pdf function of cardiac model parameters, in which we intelligently select training points to query the simulation model in order to learn the posterior pdf using a small number of samples. We integrate a generative model into Bayesian active learning to allow approximating posterior pdf of high-dimensional model parameters at the resolution of the cardiac mesh. We further introduce new acquisition functions to focus the selection of training points on better approximating the shape rather than the modes of the posterior pdf of interest. We evaluated the presented method in estimating tissue excitability in a 3D cardiac electrophysiological model in a range of synthetic and real-data experiments. We demonstrated its improved accuracy in approximating the posterior pdf compared to Bayesian active learning using regular acquisition functions, and substantially reduced computational cost in comparison to existing standard or accelerated MCMC sampling.

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.

Prospective Multicenter Assessment of a New Intraprocedural Automated System for Localizing Idiopathic Ventricular Arrhythmia Origins.

OBJECTIVES: The objective of this study was to present a new system, the Automatic Arrhythmia Origin Localization (AAOL) system, which used incomplete electroanatomic mapping (EAM) for localization of idiopathic ventricular arrhythmia (IVA) origin on the patient-specific geometry of left ventricular, right ventricular, and neighboring vessels. The study assessed the accuracy of the system in localizing IVA source sites on cardiac structures where pace mapping is challenging. BACKGROUND: An intraprocedural automated site of origin localization system was previously developed to identify the origin of early left ventricular activation by using 12-lead electrocardiograms (ECGs). However, it has limitations, as it could not identify the site of origin in the right ventricle and relied on acquiring a complete EAM. METHODS: Twenty patients undergoing IVA catheter ablation had a 12-lead ECG recorded during clinical arrhythmia and during pacing at various locations identified on EAM geometries. The new system combined 3-lead (III, V2, and V6) 120-ms QRS integrals and patient-specific EAM geometry with pace mapping to predict the site of earliest ventricular activation. The predicted site was projected onto EAM geometry. RESULTS: Twenty-three IVA origin sites were clinically identified by activation mapping and/or pace mapping (8, right ventricle; 15, left ventricle, including 8 from the posteromedial papillary muscle, 2 from the aortic root, and 1 from the distal coronary sinus). The new system achieved a mean localization accuracy of 3.6 mm for the 23 mapped IVAs. CONCLUSIONS: The new intraprocedural AAOL system achieved accurate localization of IVA origin in ventricles and neighboring vessels, which could facilitate ablation procedures for patients with IVAs.

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.