s'authentifier
version française rss feed
Fiche concise
Surface electrocardiogram reconstruction from intracardiac electrograms using a dynamic time delay artificial neural network.
Porée F., Kachenoura A., Carrault G., Dal Molin R., Mabo P., Hernandez A. I.
IEEE Transactions on Biomedical Engineering 60, 1 (2013) 106-14 - http://www.hal.inserm.fr/inserm-00747058
 (23086502) 
Surface electrocardiogram reconstruction from intracardiac electrograms using a dynamic time delay artificial neural network.
Fabienne Porée () 1, Amar Kachenoura1, Guy Carrault1, Renzo Dal Molin2, Philippe Mabo1, 3, 4, Alfredo Hernandez1
1 :  LTSI - Laboratoire Traitement du Signal et de l'Image
http://www.ltsi.univ-rennes1.fr
INSERM : U1099 – Université de Rennes 1
Campus Universitaire de Beaulieu - Bât 22 - 35042 Rennes
France
2 :  Sorin CRM
http://www.sorin.com/
Sorin Group
Clamart, F-92140
France
3 :  CIC-IT - Dispositifs Diagnostic et Thérapeutiques
INSERM : CICIT 804
2 Rue Henri de Guilloux
France
4 :  Service de cardiologie et maladies vasculaires
http://www.chu-rennes.fr/
Hôpital Pontchaillou – Université de Rennes 1 – CHU Rennes
2 rue Henri Le Guilloux 35033 Rennes cedex 9
France
SESAME - SEPIA - METRIQ - IMPACT
SEPIA
This study proposes a method to facilitate the remote follow up of patients suffering from cardiac pathologies and treated with an implantable device, by synthesizing a 12-lead surface ECG from the intracardiac electrograms (EGM) recorded by the device. Two methods (direct and indirect), based on dynamic time-delay artificial neural networks (TDNNs) are proposed and compared with classical linear approaches. The direct method aims to estimate 12 different transfer functions between the EGM and each surface ECG signal. The indirect method is based on a preliminary orthogonalization phase of the available EGM and ECG signals, and the application of the TDNN between these orthogonalized signals, using only three transfer functions. These methods are evaluated on a dataset issued from 15 patients. Correlation coefficients calculated between the synthesized and the real ECG show that the proposed TDNN methods represent an efficient way to synthesize 12-lead ECG, from two or four EGM and perform better than the linear ones. We also evaluate the results as a function of the EGM configuration. Results are also supported by the comparison of extracted features and a qualitative analysis performed by a cardiologist.
Sciences du Vivant/Ingénierie biomédicale
Sciences de l'ingénieur/Traitement du signal et de l'image
Informatique/Traitement du signal et de l'image
Sciences du Vivant/Médecine humaine et pathologie/Cardiologie et système cardiovasculaire
Anglais
1558-2531

Articles dans des revues avec comité de lecture
10.1109/TBME.2012.2225428
IEEE Transactions on Biomedical Engineering (IEEE Trans Biomed Eng)
Publisher Institute of Electrical and Electronics Engineers (IEEE)
ISSN 0018-9294 
internationale
01/2013
18/10/2012
60
1
106-14

Implantable device – ECG reconstruction – Intracardiac electrogram – Time delay neural networks.
Algorithms – Databases – Factual – Electrocardiography – Humans – Neural Networks (Computer) – Signal Processing – Computer-Assisted – Time Factors
Liste des fichiers attachés à ce document : 
PDF
TBME_Poree_7242012.pdf(798.5 KB)
inserm-00747058_edited.pdf(601.9 KB)
XHTML
index.xhtml(75.9 KB)