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

2021 ◽  
Vol 12 ◽  
Author(s):  
Amel Karoui ◽  
Mostafa Bendahmane ◽  
Nejib Zemzemi
Keyword(s):  
Neural Networks ◽  
Comparative Study ◽  
Body Surface ◽  
Data Driven ◽  
Diagnostic Tools ◽  
L1 Norm ◽  
Surface Potentials ◽  
Body Surface Potential ◽  
Data Driven Approach ◽  
Classic Technique

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.

scholarly journals Non-invasive Estimation of Atrial Fibrillation Driver Position With Convolutional Neural Networks and Body Surface Potentials

2021 ◽  
Vol 12 ◽  
Author(s):  
Miguel Ángel Cámara-Vázquez ◽  
Ismael Hernández-Romero ◽  
Eduardo Morgado-Reyes ◽  
Maria S. Guillem ◽  
Andreu M. Climent ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Body Surface ◽  
Classification Problem ◽  
Surface Potentials ◽  
Non Invasive ◽  
Promising Tool ◽  
Body Surface Potential ◽  
Ill Posed

Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns, and AF onset locations and drivers responsible for its perpetuation are the main targets for ablation procedures. ECG imaging (ECGI) has been demonstrated as a promising tool to identify AF drivers and guide ablation procedures, being able to reconstruct the electrophysiological activity on the heart surface by using a non-invasive recording of body surface potentials (BSP). However, the inverse problem of ECGI is ill-posed, and it requires accurate mathematical modeling of both atria and torso, mainly from CT or MR images. Several deep learning-based methods have been proposed to detect AF, but most of the AF-based studies do not include the estimation of ablation targets. In this study, we propose to model the location of AF drivers from BSP as a supervised classification problem using convolutional neural networks (CNN). Accuracy in the test set ranged between 0.75 (SNR = 5 dB) and 0.93 (SNR = 20 dB upward) when assuming time independence, but it worsened to 0.52 or lower when dividing AF models into blocks. Therefore, CNN could be a robust method that could help to non-invasively identify target regions for ablation in AF by using body surface potential mapping, avoiding the use of ECGI.

Using data-driven approach for wind power prediction: A comparative study

2016 ◽  
Vol 118 ◽  
pp. 193-203 ◽  
Author(s):  
Ehsan Taslimi Renani ◽  
Mohamad Fathi Mohamad Elias ◽  
Nasrudin Abd. Rahim
Keyword(s):  
Comparative Study ◽  
Wind Power ◽  
Data Driven ◽  
Power Prediction ◽  
Wind Power Prediction ◽  
Data Driven Approach ◽  
Using Data

scholarly journals Clustering for Data-driven Unraveling Artificial Neural Networks

2020 ◽  
Author(s):  
Felipe Farias ◽  
Teresa Ludermir ◽  
Carmelo Bastos-Filho
Keyword(s):  
Neural Networks ◽  
Statistical Significance ◽  
Feature Space ◽  
Data Driven ◽  
P Value ◽  
Proposed Model ◽  
Data Driven Approach ◽  
Benchmark Datasets ◽  
Hidden Layer ◽  
Fold Cross Validation

This work presents an investigation on how to define Neural Networks (NN) architectures adopting a data-driven approach using clustering to create sub-labels to facilitate the learning process and to discover the number of neurons needed to compose the layers. We also increase the depth of the model aiming to represent the samples better, the more in-depth it flows into the model. We hypothesize that the clustering process identifies sub-regions in the feature space in which the samples belonging to the same cluster have strong similarities. We used seven benchmark datasets to validate our hypothesis using 10-fold cross validation 3 times. The proposed model increased the performance, while never decreased it, with statistical significance considering the p-value $< 0.05$ in comparison with a Multi-Layer Perceptron with a single hidden layer with approximately the same number of parameters of the architectures found by our approach.

A data-driven approach to weather forecast using convolutional neural networks

2020 ◽  
Author(s):  
Orlando Micolini ◽  
Luis Orlando Ventre ◽  
Agustin Martina ◽  
Ruben Esteban Ayme ◽  
Nestor J. Ortmann ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Weather Forecast ◽  
Data Driven ◽  
Data Driven Approach
Sign in / Sign up

Export Citation Format

Share Document