A penalized semi-algebraic deflation ICA algorithm for the efficient extraction of interictal epileptic signals

Hanna Becker 1 Laurent Albera 2, 3 Pierre Comon 1 Amar Kachenoura 2 Isabelle Merlet 2
1 GIPSA-CICS - CICS
GIPSA-DIS - Département Images et Signal
3 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE, Inria Rennes – Bretagne Atlantique
Abstract : As a non-invasive technique, Electroencephalogra-phy (EEG) is commonly used to monitor the brain signals of patients with epilepsy such as the interictal epileptic spikes. However, the recorded data are often corrupted by artifacts originating, for example, from muscle activities, which may have much higher amplitudes than the interictal epileptic signals of interest. To remove these artifacts, a number of Independent Component Analysis (ICA) techniques were successfully applied. In this paper, we propose a new deflation ICA algorithm, called Penalized Semi-Algebraic Unitary Deflation (P-SAUD) algorithm, that improves upon classical ICA methods by leading to a considerably reduced computational complexity at equivalent performance. This is achieved by employing a penalized semi-algebraic extraction scheme, which permits us to identify the epileptic components of interest (interictal spikes) first and obviates the need of extracting subsequent components. The proposed method is evaluated on physiologically plausible simulated EEG data and actual measurements of three patients. The results are compared to those of several popular ICA algorithms as well as second order blind source separation methods, demonstrating that P-SAUD extracts the epileptic spikes with the same accuracy as the best ICA methods, but reduces the computational complexity by a factor of 10 for 32-channel recordings. This superior computational efficiency is of particular interest considering the increasing use of high-resolution EEG recordings, whose analysis requires algorithms with low computational cost.
Type de document :
Article dans une revue
IEEE Journal of Biomedical and Health Informatics, Institute of Electrical and Electronics Engineers, 2015
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01246030
Contributeur : Laurent Albera <>
Soumis le : jeudi 17 décembre 2015 - 22:54:01
Dernière modification le : mercredi 16 mai 2018 - 11:24:07
Document(s) archivé(s) le : vendredi 18 mars 2016 - 16:00:45

Fichier

cSAUD_final2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01246030, version 1

Citation

Hanna Becker, Laurent Albera, Pierre Comon, Amar Kachenoura, Isabelle Merlet. A penalized semi-algebraic deflation ICA algorithm for the efficient extraction of interictal epileptic signals. IEEE Journal of Biomedical and Health Informatics, Institute of Electrical and Electronics Engineers, 2015. 〈hal-01246030〉

Partager

Métriques

Consultations de la notice

837

Téléchargements de fichiers

352