An automated system for epileptogenic focus localization in the electroencephalogram

This paper describes an automated system for the detection and localization of foci of epileptiform activity in the EEG. The system detects sharp EEG transients (STs) in the process, but the emphasis is on epileptic focus loc alization. A combination of techniques involving signal processing, pattern recognition, and the expert rules of an experienced electroencephalographe r, involving considerable spatiotemporal context information, is applied to multichannel EEG data. An overall context information, is applied to multi channel EEG data. An overall emphasis on minimizing the number of false-pos itive sharp transient detections drives the system design. Tested on data f rom 13 subjects with epileptiform activity and 5 controls, all areas of foc al epileptiform activity were detected by the system, although not all of t he contributing foci were reported separately. Two false-positive foci were detected as well due to nonfocal spike activity and normal spike-like acti vity not present in the training set. The system detected 95.7% of the epil eptiform events constituting the correctly detected foci, with a false dete ction rate of 11.1%.