Real-Time Localization of Ventricular Tachycardia Origin From the 12-Lead Electrocardiogram

Sapp, John L.; Bar-Tal, Meir; Howes, Adam J.; Toma, Jonathan; El-Damaty, Ahmed; Warren, James W.; MacInnis, Paul J.; Zhou, Shijie; Horáček, B. Milan

doi:10.1016/j.jacep.2017.02.024

Cited by 49 publications

(60 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…here the exit site of the VT circuit) directly from multi-channel surface ECG data recorded during VT, and even potentially from the standard 12-lead ECG recording [24]. Alternatively, artificial intelligence has shown promising results to predict the exit site of the VT circuit from the 12-lead ECG of the VT, based on machine learning [25] or deep learning [26]. In particular, in Ref.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Catheter Treatment of Ventricular Tachycardia: A Reference-Less Pace-Mapping Method to Identify Ablation Targets

Odille

Battaglia

Hoyland

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

A novel method is developed to identify ablation targets for the catheter treatment of ventricular tachycardia (VT). Methods: The method is based on pacemapping, which is a validated technique to determine the catheter ablation targets. Conventionally, it consists of stimulating the heart ventricle from various sites and comparing the resulting activation pathways to that of a clinical VT, by analysis of surface electrocardiograms (ECG). In this work a novel pace-mapping method is presented, that does not require a reference ECG recording of the VT. A 3D correlation gradient map is reconstructed by semi-automatic analysis of ECG morphological changes within the network of pace-mapping sites. In these maps, abnormal points are identified by high correlation gradient values (i.e. corresponding to slow propagation of the electric influx, as in the core of the reentrant VT circuit). The relation between the conventional and reference-less method is described theoretically and evaluated in a retrospective study including 24 VT ablation procedures. Results: The "reference-less" method was able to identify normal points with a high accuracy (negative predictive value: NPV=97%) and to detect more abnormal points, as predicted by the theory. Correlation gradients computed by the proposed method were significantly higher in ablation zones than in other zones of the ventricle (p<10-12), indicating excellent prediction of the ablation targets. Significance: The reference-less method might either be used in complement of the conventional method, or to treat patients in whom VT cannot be induced during the intervention.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In particular, in Ref. [25], it was shown that the relation between pacing location and the lead-wise QRS energy distribution can be learnt (using a population-based and/or patient-specific training) and used to predict the location of the VT exit site. Both ECGI and artificial intelligence necessitate a VT reference ECG.…”

Section: Discussionmentioning

confidence: 99%

Catheter Treatment of Ventricular Tachycardia: A Reference-Less Pace-Mapping Method to Identify Ablation Targets

Odille

Battaglia

Hoyland

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…For example, a 5 mm error in PVC localization is more significant than a much larger error in distance, if the location is incorrectly identified as the LV instead of the RV compared to when both correct and incorrect sites are in the same chamber. Some authors have quantified localization to a predefined segment of the heart [e.g., segmentation according to the AHA classification ( Austen et al, 1975 )] but these indicators can also be misleading, for example if the correct location lies just on one side of a segment boundary and the reconstructed location is nearby but just on the other ( Sapp et al, 2017 ). Moreover, estimation of activation time and site of first activation from reconstructed electrograms is itself a difficult problem that is currently the topic of active investigation by many groups ( Erem et al, 2011 ; Duchateau et al, 2016 ), including the CEI workgroup on Activation and Recovery times 4 .…”

Section: Consensus On Designing a Validation Studymentioning

confidence: 99%

Validation and Opportunities of Electrocardiographic Imaging: From Technical Achievements to Clinical Applications

et al. 2018

View full text Add to dashboard Cite

Electrocardiographic imaging (ECGI) reconstructs the electrical activity of the heart from a dense array of body-surface electrocardiograms and a patient-specific heart-torso geometry. Depending on how it is formulated, ECGI allows the reconstruction of the activation and recovery sequence of the heart, the origin of premature beats or tachycardia, the anchors/hotspots of re-entrant arrhythmias and other electrophysiological quantities of interest. Importantly, these quantities are directly and non-invasively reconstructed in a digitized model of the patient’s three-dimensional heart, which has led to clinical interest in ECGI’s ability to personalize diagnosis and guide therapy. Despite considerable development over the last decades, validation of ECGI is challenging. Firstly, results depend considerably on implementation choices, which are necessary to deal with ECGI’s ill-posed character. Secondly, it is challenging to obtain (invasive) ground truth data of high quality. In this review, we discuss the current status of ECGI validation as well as the major challenges remaining for complete adoption of ECGI in clinical practice. Specifically, showing clinical benefit is essential for the adoption of ECGI. Such benefit may lie in patient outcome improvement, workflow improvement, or cost reduction. Future studies should focus on these aspects to achieve broad adoption of ECGI, but only after the technical challenges have been solved for that specific application/pathology. We propose ‘best’ practices for technical validation and highlight collaborative efforts recently organized in this field. Continued interaction between engineers, basic scientists, and physicians remains essential to find a hybrid between technical achievements, pathological mechanisms insights, and clinical benefit, to evolve this powerful technique toward a useful role in clinical practice.

show abstract

“…QRS integrals are extracted by trapezoidal approximation. All QRS integrals from 12 ECG leads are used as input x is mapped to the output coordinates y via a linear model y = Wx + b, where parameters {W, b} are fitted using a least squares approach [6].x y W z W Figure 2. Denoising Autoencoder.x stands for corrupted input, y is latent representation, z is reconstructed input while W, W are weight matrices.…”

Section: Feature Based Approachmentioning

confidence: 99%

“…Finally, to build an accurate prediction model from a large population is challenged by the fact that the ECG signals have significant physiological and pathological variations across individuals. The recent work in [6] demonstrated the use of patient-specific models to predict the 3D coordinates of the VT exit. It addresses the issue of a low-resolution localization by departing from segment-based models, and it avoids inter-subject variations in ECG data by building a model for each subject.…”

Section: Introductionmentioning

confidence: 99%

Automatic Coordinate Prediction of the Exit of Ventricular Tachycardia from 12-Lead Electrocardiogram

Gyawali

Chen

Liu

et al. 2017

Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Automatic localization of the exit site of ventricular tachycardia (VT) can improve the efficiency and efficacy of catheter ablation. Because the exit site of the VT gives rise to its QRS complex on electrocardiogram (ECG), it is possible to build a predictive model to directly localize the exit of a VT from its 12-lead ECG. In previous works, prescribed features such as QRS integrals have been used to build such models. In this paper, we propose a deep network to automatically extract more discriminative features from QRS complex to localize the origin of ventricular activation. To improve the resolution of localization compared to previous works based on a small number of pre-defined segments, we localize the origin of ventricular activation as 3D coordinates. Model training and testing were performed on 12-lead ECG data of 1012 distinct pacing sites, collected from patients during routine pace-mapping procedures. Compared with the use of prescribed QRS-integral as an input feature, the presented deep model achieved an improvement of localization accuracy by approximately 4 millimeters (∼26%) on average.

show abstract

Real-Time Localization of Ventricular Tachycardia Origin From the 12-Lead Electrocardiogram

Abstract: Computational intraprocedure methods can automatically identify the segment and site of left ventricular activation using novel algorithms, with accuracy within <10 mm.

Cited by 49 publications

References 24 publications

Catheter Treatment of Ventricular Tachycardia: A Reference-Less Pace-Mapping Method to Identify Ablation Targets

Catheter Treatment of Ventricular Tachycardia: A Reference-Less Pace-Mapping Method to Identify Ablation Targets

Validation and Opportunities of Electrocardiographic Imaging: From Technical Achievements to Clinical Applications

Automatic Coordinate Prediction of the Exit of Ventricular Tachycardia from 12-Lead Electrocardiogram

Contact Info

Product

Resources

About