A system is proposed which enhances transient nonstationaritiesand, in particular, epileptiform discharges in the EEG. It is based around the technique of multireferenceadaptive noise cancelling (MRANC) which attenuates the background EEG on a primary channel by using spatial andtemporal information from adjacent channels in the multichannel EEG recording. This process has beenimplemented by means of a 3-layer perceptron artificial neuralnetwork trained by a backpropagation algorithm. System performance was measured as the percentage increasein signal-to-noise ratio (SNR) of predetermined epileptiformdischarges in recorded EEG segments. The results obtained show that, due to the nonlinear nature of the artificial neural network, the improvement in SNR is significant when comparedto the performance of MRANC utilising a linear model. MRANC is proposed as the first stage of a neural networkbased multi-stage system to detect epileptiform discharges in theinterictal EEG for the diagnosis of epilepsy.
展开▼
