Method for intelligently detecting BECT spike waves based on multichannel electroencephalograms

Abstract

The invention provides a method for intelligently detecting BECT spike waves based on multichannel electroencephalograms. The method comprises the following steps: (1) collecting the electroencephalograms (EEG), and establishing an experimental database; (2) preprocessing data: carrying out band-pass filtering on collected EEG data, so as to obtain a standard EEG signal; (3) carrying out candidatespike wave detection, carrying out self-adaptive template matching by utilizing a screened class-center as a new template, and adding all matching results together so as to obtain candidate spike waves; (4) eliminating false-detection spike waves: determining two relevant BP channels of each candidate spike wave according to a candidate detection result of an AV channel, and removing the candidate spike waves without an "eye-for-eye" phenomenon on the two BP channels; (5) extracting characteristics of the spike waves: after the false-detection spike waves are eliminated, calculating 10 characteristics of each channel; and (6) carrying out random forest classification: training a random forest classification model by taking the extracted characteristics of the spike waves as a characteristic vector, and inputting the characteristics of the spike waves of to-be-analyzed electroencephalograms into the random forest classification model, so as to obtain a detection result of the BECT spike waves.

Description

technical field [0001] The invention relates to the field of computers, in particular to a BECT spike intelligent detection method of multi-channel electroencephalogram signals. Background technique [0002] Benign epilepsy with centro-temporal spikes (BECT) is one of the most common epilepsy syndromes in children, and its main patients are school-age children, accounting for 15%-20% of childhood epilepsy. [0003] Electroencephalogram (Electroencephalogram, EEG) is formed by the simultaneous neuron discharge of a large number of neurons in the process of brain activity. It is the most direct reflection of cerebral cortex discharge and contains a large amount of physiological and disease information. Clinical studies have shown that BECT is primary focal epilepsy with unknown etiology. It is a special form of epilepsy, mainly manifested as partial discharge in the central area and temporal area. Clinically, the diagnosis of BECT patients is mainly through the detection and ...

AI Technical Summary

Problems solved by technology

However, this method takes a long time, has a high false detection rate, and the accuracy of the detection results cannot be guaranteed. For this reason, the spike automatic detection technology has received more and more attention in recent years.

[0005] Although there have been many studies on spike detection methods, more advanced automatic spike detection is still difficult for several reasons

First, due to individual differences between people, the appearance of spikes is different, so it is difficult to automatically detect spikes in EEG signals with a simple and consistent method

Second, artifacts caused by factors such as heartbeat, eye movement, and muscle movement inevitably exist in EEG signals, which greatly affect the performance of automatic spike detection methods.

Finally, compared with fully discharged spikes, the waveform characteristics of incompletely discharged spikes are not obvious enough, which further increases the difficulty of automatic detection

Images