Localization of Origins of Premature Ventricular Contraction by Means of Convolutional Neural Network From 12-Lead ECG

Yang, Ting; Yu, Long; Qi, Jin; Wu, Liqun; He, Bin

doi:10.1109/tbme.2017.2756869

Cited by 70 publications

(53 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work by Li and He [4] solves the inverse problem by means of heart-model parameters (onset activation location) and was validated with in vivo studies [14]. It was further developed for localizing PVC origins from convolutional neural networks [15]. With a known onset activation location, the estimation of heterogeneous myocardial conduction using a Bayesian framework has been recently studied by Dhamala et al [6].…”

Section: A Ep Model-based Inverse Problem Of Electrocardiographymentioning

confidence: 99%

“…Yet, it has been also shown that some adapted ventricle-torso standard model were able to get good ECGI results while excluding local geometrical details [20], [21]. Lastly, a recent study uses a generic ventricle-torso model in order to build an EP model training set [15], however the training phase had to be patient-specific as the generic geometry was first registered to every patient geometry. To the best of our knowledge, the goals of these geometrical models were only to simplify the anatomical modelling process.…”

Section: B Reference Anatomy In Ecgimentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy

Giffard‐Roisin

Delingette²,

Jackson

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Goal: Non-invasive cardiac electrophysiology (EP) model personalisation has raised interest for instance in the scope of predicting EP cardiac resynchronization therapy (CRT) response. However, the restricted clinical applicability of current methods is due in particular to the limitation to simple situations and the important computational cost. Methods: We propose in this manuscript an approach to tackle these two issues. First, we analyse more complex propagation patterns (multiple onsets and scar tissue) using relevance vector regression and shape dimensionality reduction on a large simulated database. Second, this learning is performed offline on a reference anatomy and transferred onto patient-specific anatomies in order to achieve fast personalised predictions online. Results: We evaluated our method on a dataset composed of 20 dyssynchrony patients with a total of 120 different cardiac cycles. The comparison with a commercially available electrocardiographic imaging (ECGI) method shows a good identification of the cardiac activation pattern. From the cardiac parameters estimated in sinus rhythm, we predicted 5 different paced patterns for each patient. The comparison with the body surface potential mappings (BSPM) measured during pacing and the ECGI method indicates a good predictive power. Conclusion: We showed that learning offline from a large simulated database on a reference anatomy was able to capture the main cardiac EP characteristics from non-invasive measurements for fast patient-specific predictions. Significance: The fast CRT pacing predictions are a step forward to a noninvasive CRT patient selection and therapy optimisation, to help clinicians in these difficult tasks.

show abstract

Section: A Ep Model-based Inverse Problem Of Electrocardiographymentioning

confidence: 99%

Section: B Reference Anatomy In Ecgimentioning

confidence: 99%

Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy

Giffard‐Roisin

Delingette²,

Jackson

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…We compared cIBP-VAE to: 1) a supervised CNN with three-layered convolution blocks (dropout, 2d convolution, batch normalization, ReLU, and max-pool layer) followed by two fully connected layers, and 2) c-VAE with the same parameters and architecture of cIBP-VAE. The design choice of the supervised CNN was inspired by [42].…”

Section: B Quantitative Benchmarkmentioning

confidence: 99%

Improving Disentangled Representation Learning with the Beta Bernoulli Process

Gyawali

Knight

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

To improve the ability of variational auto-encoders (VAE) to disentangle in the latent space, existing works mostly focus on enforcing the independence among the learned latent factors. However, the ability of these models to disentangle often decreases as the complexity of the generative factors increases. In this paper, we investigate the little-explored effect of the modeling capacity of a posterior density on the disentangling ability of the VAE. We note that the independence within and the complexity of the latent density are two different properties we constrain when regularizing the posterior density: while the former promotes the disentangling ability of VAE, the latter -if overly limitedcreates an unnecessary competition with the data reconstruction objective in VAE. Therefore, if we preserve the independence but allow richer modeling capacity in the posterior density, we will lift this competition and thereby allow improved independence and data reconstruction at the same time. We investigate this theoretical intuition with a VAE that utilizes a non-parametric latent factor model, the Indian Buffet Process (IBP), as a latent density that is able to grow with the complexity of the data. Across three widely-used benchmark data sets (MNIST, 3D Chairs and dSprites) and two clinical data sets little explored for disentangled learning, we qualitatively and quantitatively demonstrated the improved disentangling performance of IBP-VAE over the state of the art. In the latter two clinical data sets riddled with complex factors of variations, we further demonstrated that unsupervised disentangling of nuisance factors via IBP-VAE -when combined with a supervised objective -can not only improve task accuracy in comparison to relevant supervised deep architectures, but also facilitate knowledge discovery related to task decision-making. A shorter version of this work will appear in the ICDM 2019 conference proceedings.

show abstract

“…Because of its simplicity, noninvasiveness and low cost, standard 12-lead electrocardiography (ECG) is used as the primary clinical tool to diagnose changes in heart conditions. It has been shown as the single adequate source to diagnose cardiac rhythm 1 and morphology 2 , such as cardiac arrhythmia 3 , acute and prior myocardial infarctions 4 , pericardial disease 5 and atrial or ventricular enlargement 6 .…”

Section: Introductionmentioning

confidence: 99%

“…These methods comprise a deep genetic ensemble of classifiers 12,13 , attention mechanisms on ECG strip 14 , feature extraction and voting methods 15 , different pattern recognitions based on transforms, e.g., wavelet transform 16 , unique feature utilization, e.g., output of Welch transform 17 , discrete Fourier transform 17 , spectral power density transform 17 and evolutionary neural systems 18 . However, to date, all these methods have only been applied on open 1 Computer Science Department, Technion-IIT, Haifa, Israel. 2 Laboratory of Bioenergetic and Bioelectric Systems, Biomedical Engineering Faculty, Technion-IIT, Haifa, Israel.…”

mentioning

confidence: 99%

Automatic classification of healthy and disease conditions from images or digital standard 12-lead electrocardiograms

Gliner

Keidar

Makarov

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Standard 12-lead electrocardiography (ECG) is used as the primary clinical tool to diagnose changes in heart function. The value of automated 12-lead ECG diagnostic approaches lies in their ability to screen the general population and to provide a second opinion for doctors. Yet, the clinical utility of automated ECG interpretations remains limited. We introduce a two-way approach to an automated cardiac disease identification system using standard digital or image 12-lead ECG recordings. Two different network architectures, one trained using digital signals (CNN-dig) and one trained using images (CNN-ima), were generated. An open-source dataset of 41,830 classified standard ECG recordings from patients and volunteers was generated. CNN-ima was trained to identify atrial fibrillation (AF) using 12-lead ECG digital signals and images that were also transformed to mimic mobile device camera-acquired ECG plot snapshots. CNN-dig accurately (92.9–100%) identified every possible combination of the eight most-common cardiac conditions. Both CNN-dig and CNN-ima accurately (98%) detected AF from standard 12-lead ECG digital signals and images, respectively. Similar classification accuracy was achieved with images containing smartphone camera acquisition artifacts. Automated detection of cardiac conditions in standard digital or image 12-lead ECG signals is feasible and may improve current diagnostic methods.

show abstract

Localization of Origins of Premature Ventricular Contraction by Means of Convolutional Neural Network From 12-Lead ECG

Abstract: This paper suggests a new approach for cardiac source localization of origin of arrhythmias using only the 12-lead ECG by means of CNN, and may have important applications for future real-time monitoring and localizing origins of cardiac arrhythmias guiding ablation treatment.

Cited by 70 publications

References 45 publications

Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy

Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy

Improving Disentangled Representation Learning with the Beta Bernoulli Process

Automatic classification of healthy and disease conditions from images or digital standard 12-lead electrocardiograms

Contact Info

Product

Resources

About