Cardiac Activation Maps Reconstruction: A Comparative Study Between Data-Driven and Physics-Based Methods
| hal.structure.identifier | IHU-LIRYC | |
| dc.contributor.author | KAROUI, Amel | |
| hal.structure.identifier | Modélisation et calculs pour l'électrophysiologie cardiaque [CARMEN] | |
| hal.structure.identifier | Université de Bordeaux [UB] | |
| dc.contributor.author | BENDAHMANE, Mostafa | |
| hal.structure.identifier | IHU-LIRYC | |
| dc.contributor.author | ZEMZEMI, Nejib | |
| dc.date.accessioned | 2024-04-04T02:45:02Z | |
| dc.date.available | 2024-04-04T02:45:02Z | |
| dc.date.issued | 2021-08-26 | |
| dc.identifier.issn | 1664-042X | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/191434 | |
| dc.description.abstractEn | 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. | |
| dc.description.sponsorship | L'Institut de Rythmologie et modélisation Cardiaque - ANR-10-IAHU-0004 | |
| dc.description.sponsorship | Plateforme multi-modale d'exploration en cardiologie - ANR-11-EQPX-0030 | |
| dc.language.iso | en | |
| dc.publisher | Frontiers | |
| dc.subject.en | Data-driven approaches | |
| dc.subject.en | Physics-based approaches | |
| dc.subject.en | ECGI inverse problem | |
| dc.subject.en | Cardiac activation mapping | |
| dc.subject.en | Neural networks | |
| dc.subject.en | Deep learning | |
| dc.title.en | Cardiac Activation Maps Reconstruction: A Comparative Study Between Data-Driven and Physics-Based Methods | |
| dc.type | Article de revue | |
| dc.identifier.doi | 10.3389/fphys.2021.686136 | |
| dc.subject.hal | Informatique [cs]/Modélisation et simulation | |
| dc.subject.hal | Mathématiques [math]/Statistiques [math.ST] | |
| dc.subject.hal | Informatique [cs]/Intelligence artificielle [cs.AI] | |
| bordeaux.journal | Frontiers in Physiology | |
| bordeaux.volume | 12 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-03382399 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-03382399v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Frontiers%20in%20Physiology&rft.date=2021-08-26&rft.volume=12&rft.eissn=1664-042X&rft.issn=1664-042X&rft.au=KAROUI,%20Amel&BENDAHMANE,%20Mostafa&ZEMZEMI,%20Nejib&rft.genre=article |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||