TY - GEN
T1 - Graphical models for localization of the seizure focus from interictal intracranial EEG
AU - Dauwels, Justin
AU - Eskandar, Emad
AU - Cole, Andy
AU - Hoch, Dan
AU - Zepeda, Rodrigo
AU - Cash, Sydney S.
PY - 2011
Y1 - 2011
N2 - Decision algorithms are developed that use periods of intracranial non-seizure (interictal) EEG to localize epileptogenic networks. Depth and surface recordings are considered from 5 and 6 patients respectively. The proposed algorithms combine spectral and multivariate statistics in a decision-theoretic framework to automatically delineate the seizure onset area. In the case of depth recordings, we apply standard binary classification algorithms, including linear and quadratic discriminative analysis. For the surface recordings, novel decision algorithms are developed, based upon graphical models. The outcomes from the algorithms for both depth and surface recordings are in good agreement with the determination of the seizure focus by clinicians from ictal EEG. In the long term, the proposed approach may lead to shorter hospitalization of intractable-epilepsy patients, since it does not rely on ictal EEG.
AB - Decision algorithms are developed that use periods of intracranial non-seizure (interictal) EEG to localize epileptogenic networks. Depth and surface recordings are considered from 5 and 6 patients respectively. The proposed algorithms combine spectral and multivariate statistics in a decision-theoretic framework to automatically delineate the seizure onset area. In the case of depth recordings, we apply standard binary classification algorithms, including linear and quadratic discriminative analysis. For the surface recordings, novel decision algorithms are developed, based upon graphical models. The outcomes from the algorithms for both depth and surface recordings are in good agreement with the determination of the seizure focus by clinicians from ictal EEG. In the long term, the proposed approach may lead to shorter hospitalization of intractable-epilepsy patients, since it does not rely on ictal EEG.
UR - http://www.scopus.com/inward/record.url?scp=80051635038&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80051635038&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2011.5946511
DO - 10.1109/ICASSP.2011.5946511
M3 - Conference contribution
AN - SCOPUS:80051635038
SN - 9781457705397
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 745
EP - 748
BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Y2 - 22 May 2011 through 27 May 2011
ER -