A Spatial Adaptation of the Time Delay Neural Network for Solving ECGI Inverse Problem

Karoui, Amel; Bendahmane, Mostafa; Zemzemi, Néjib

doi:10.1007/978-3-030-21949-9_11

Cited by 8 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network prediction of G3D decomposed HSP left ventricular recordings is especially encouraging, as the [11], [12]. The dynamic behavior of the recorded HSP is predicted well.…”

Section: Discussionmentioning

confidence: 74%

“…However, a common problem encountered by the neural network approach is the richness of heart states found in the training data set [11], [2], [12]. Neural networks can only predict data similar to that found in the training set, therefore training a neural network to solve the cardiac inverse problem require a large amount of BSP and HSP recordings across different heart states.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impulse data models for the inverse problem of electrocardiography

Peng,

Malik,

Bear

et al. 2021

Preprint

View full text Add to dashboard Cite

Objective: This paper proposes an neural network approach for predicting heart surface potentials (HSPs) from body surface potentials (BSPs), which re-frames the traditional inverse problem of electrocardiography into a regression problem through the use of Gaussian 3D (G3D) basis function decomposition. Methods: HSPs were generated using G3D basis functions and passed through a boundary element forward model to obtain corresponding BSPs. The generated BSPs (input) and HSPs (output) were used to train a neural network, which was then used to predict a variety of synthesized and decomposed real-world HSPs. Results: Fitted G3D basis function parameters can accurately reconstruct the real-world left ventricular paced recording with percent root mean squared error (RMSE) of 1.34 ± 1.30%. The basis data trained neural network was able to predict G3D basis function synthesized data with RMSE of 8.46 ± 1.55%, and G3D representation of real-world data with RMSE of 18.5 ± 5.25%. Activation map produced from the predicted time series had a RMSE of 17.0% and mean absolute difference of 10.3 ± 10.8 ms when compared to that produced from the actual left ventricular paced recording. Conclusion: A Gaussian basis function based data driven model for re-framing the inverse problem of electrocardiography as a regression problem is successful and produces promising time series and activation map predictions of real-world recordings even when only trained using Guassian data. Significance: The HSPs predicted by the neural network can be used to create activation maps to identify cardiac dysfunctions during clinical assessment.

show abstract

“…The neural network prediction of G3D decomposed HSP left ventricular recordings is especially encouraging, as the [11], [12]. The dynamic behavior of the recorded HSP is predicted well.…”

Section: Discussionmentioning

confidence: 74%

Section: Introductionmentioning

confidence: 99%

Impulse data models for the inverse problem of electrocardiography

Peng,

Malik,

Bear

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The SATDNN-AT method was firstly introduced in Karoui et al (2019b). It consists of reconstructing a heart surface potential at a time step t from body surface potential measurements at time step t and its previous values t − 1, t − 2, etc.…”

Section: Cardiac Activation Mapping Using Reconstructed Electrograms By Satdnn-atmentioning

confidence: 99%

“…Hence, we use the spatial adjacency matrix as a representation of the relation between the target spatial location and its adjacent locations. According to Karoui et al (2019b), this model called SATDNN-AT is made with two hidden layers. The first layer is identical to the TDNN where D (d) is the time delay window of size d as represented in Figure 1B.…”

Section: Cardiac Activation Mapping Using Reconstructed Electrograms By Satdnn-atmentioning

confidence: 99%

“…In continuity with our previous works, we conduct a comparative study to evaluate quantitatively the performance of the data-driven methods: DirectMap (Karoui et al, 2019a) and the Spatial Adaptation of Time-Delay Neural Network (SATDNN-AT) (Karoui et al, 2019b) compared to the classic inverse method: Finite Element Method combined with L1-norm regularization (FEM-L1) (Karoui et al, 2018). The choice of these two methods is based on their performance results reported in Karoui et al (2018) and Karoui et al (2019b). The study is conducted using atrial paced in-silico data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cardiac Activation Maps Reconstruction: A Comparative Study Between Data-Driven and Physics-Based Methods

2021

Self Cite

View full text Add to dashboard Cite

One of the essential diagnostic tools of cardiac arrhythmia is activation mapping. Noninvasive current mapping procedures include electrocardiographic imaging. It allows reconstructing heart surface potentials from measured body surface potentials. Then, activation maps are generated using the heart surface potentials. Recently, a study suggests to deploy artificial neural networks to estimate activation maps directly from body surface potential measurements. Here we carry out a comparative study between the data-driven approach DirectMap and noninvasive classic technique based on reconstructed heart surface potentials using both Finite element method combined with L1-norm regularization (FEM-L1) and the spatial adaptation of Time-delay neural networks (SATDNN-AT). In this work, we assess the performance of the three approaches using a synthetic single paced-rhythm dataset generated on the atria surface. The results show that data-driven approach DirectMap quantitatively outperforms the two other methods. In fact, we observe an absolute activation time error and a correlation coefficient, respectively, equal to 7.20 ms, 93.2% using DirectMap, 14.60 ms, 76.2% using FEM-L1 and 13.58 ms, 79.6% using SATDNN-AT. In addition, results show that data-driven approaches (DirectMap and SATDNN-AT) are strongly robust against additive gaussian noise compared to FEM-L1.

show abstract

Electrocardiographic imaging in the atria

Hernández-Romero

Molero

Fambuena-Santos

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

The inverse problem of electrocardiography or electrocardiographic imaging (ECGI) is a technique for reconstructing electrical information about cardiac surfaces from noninvasive or non-contact recordings. ECGI has been used to characterize atrial and ventricular arrhythmias. Although it is a technology with years of progress, its development to characterize atrial arrhythmias is challenging. Complications can arise when trying to describe the atrial mechanisms that lead to abnormal propagation patterns, premature or tachycardic beats, and reentrant arrhythmias. This review addresses the various ECGI methodologies, regularization methods, and post-processing techniques used in the atria, as well as the context in which they are used. The current advantages and limitations of ECGI in the fields of research and clinical diagnosis of atrial arrhythmias are outlined. In addition, areas where ECGI efforts should be concentrated to address the associated unsatisfied needs from the atrial perspective are discussed. Graphical abstract

show abstract

A Spatial Adaptation of the Time Delay Neural Network for Solving ECGI Inverse Problem

Cited by 8 publications

References 6 publications

Impulse data models for the inverse problem of electrocardiography

Impulse data models for the inverse problem of electrocardiography

Cardiac Activation Maps Reconstruction: A Comparative Study Between Data-Driven and Physics-Based Methods

Electrocardiographic imaging in the atria

Contact Info

Product

Resources

About