Performance of blind source separation in localizing seizure onset from routine scalp-EEG
- 7 November 2025
- journal article
- research article
- Published by Springer Nature in Journal of Neurology
- Vol. 272 (12) , 1-14
Abstract
Objective Blind source separation (BSS), decomposing signals into mixed sources, remains underexplored in ictal source imaging. We evaluated its ability to extract ictal components localizing the seizure onset zone (SOZ) using routine low-density scalp EEG across multiple settings. Methods We analyzed 20 seizures from ten patients with stereo-EEG-defined SOZs, all seizure-free after surgery or RF-thermocoagulation. BSS was computed over 10-, 30-, and 300-s periods preceding clinically and EEG-defined seizure onsets, using FastICA, InfoMax, and SOBI algorithms. Components were visually categorized as ictal or non-ictal. For each computation, the clearest ictal component was labeled best-of-BSS; one per seizure was further labeled unique when enhancing the ictal discharge. We estimated distances between components’ localization and the SOZ and assessed sublobar concordance. Results Across 360 BSS computations (8164 components), sublobar SOZ localization occurred in 38.5% of ictal components (mean distance: 44.4 mm), 48.2% of best-of-BSS (36.8 mm), 56.7% of unique (28.9 mm), versus 17.9% of non-ictal components (62.9 mm). InfoMax computed on 300-s periods preceding clinical onset achieved the highest F-scores. Conclusions Under these settings, best-of-BSS components localized the SOZ in 13/20 seizures (8/10 patients), with a median distance of 29.9 mm. Significance InfoMax algorithm incorporating longer time windows improves SOZ localization from routine scalp-EEG.Keywords
This publication has 43 references indexed in Scilit:
- Correspondence between scalp‐EEG and stereoelectroencephalography seizure‐onset patterns in patients with MRI‐negative drug‐resistant focal epilepsyEpilepsia Open, 2024
- The role of quantitative markers in surgical prognostication after stereoelectroencephalographyAnnals of Clinical and Translational Neurology, 2023
- Automated Interpretation of Clinical Electroencephalograms Using Artificial IntelligenceJAMA Neurology, 2023
- Extracting the Invisible: Mesial Temporal Source Detection in Simultaneous EEG and SEEG RecordingsBrain Topography, 2023
- Seizure Onset Zone Localization from Ictal High-Density EEG in Refractory Focal EpilepsyBrain Topography, 2016
- Catching the Invisible: Mesial Temporal Source Contribution to Simultaneous EEG and SEEG RecordingsBrain Topography, 2014
- Seizure source imaging by means of FINE spatio-temporal dipole localization and directed transfer function in partial epilepsy patientsClinical Neurophysiology, 2012
- Spatiotemporospectral characteristics of scalp ictal EEG in mesial temporal lobe epilepsy with hippocampal sclerosisBrain Research, 2009
- Analysis of the EEG dynamics of epileptic activity in gelastic seizures using decomposition in independent componentsClinical Neurophysiology, 2006
- Independent component analysis, A new concept?Signal Processing, 1994