EXTRACTION OF SPATIOTEMPORAL SIGNATURES FROM DEPTH EEG SEIZURE SIGNALS BASED ON OBJECTIVE MATCHING IN WARPED VECTORIAL OBSERVATIONS

In the field of epilepsy, the analysis of stereoelectroencephalographi c (SEEG) signals recorded with depth electrodes provides major informa tion on interactions between brain structures during seizures, A compr ehensive methodology of comparing SEEG seizure recordings is presented . It proceeds in three steps: 1) segmentation of SEEG signals; 2) char acterization and labeling of segments; and 3) comparison of observatio ns coded as sequences of symbol vectors, The third step reports a vect orial extension of the Wagner and Fischer's algorithm to first, quanti fy similarities between observations and second, extract invariant seq uences of events, referred to as spatiotemporal signatures, The study shows that two observations of nonequal duration can be matched by def orming the first one to optimally fit the second, under cost constrain ts, Results show that the methodology allows to exhibit signatures occ urring during epileptic seizures and to point out different types of s eizure patterns. The study brings objective results on reproducible in teractions between brain structures during ictal periods and may help in the understanding of epileptogenic networks.