Methodological considerations for the evaluation of spatio-temporal source models

Abstract

The effects of physiological noise and modelling procedure on spatio-temporal source modelling (STSM) solutions were examined by adding EEG noise (3-4% of total energy) to synthetic signals from 3 dipoles producing topographies that partially cancelled at the surface of an homogeneous sphere. Three patterns of source activation profiles were each associated with two EEG records. The STSM solutions were subjected to statistical tests that detect signal left in the residuals. All models substantially accounted for noise. Essentially correct models left no consistent signal in the residuals, but other statistically acceptable models were also occasionally found. Unambiguous correct solutions were found for moderately correlated source activations. Statistically adequate 2-source and 3-source models were found for the 4 data sets incorporating nearly parallel activations of 2 sources. When all 3 sources had comparable amplitudes, the 2-source models represented compromises containing gross mislocalizations but correct 3-source models were found. When one of the parallel sources was attenuated by 75%, only 2-source models satisfactorily approximated the 2 main sources. The localization errors in the "correct" models ranged from 2.5% to 13% of the sphere radius. Thus, even with a perfect signal propagation model, STSM could at best claim approximate localizations from data containing structured noise.