Combined detection method of electroencephalogram epilepsy sharp and spike wave discharge based on long short term memory network (LSTM) multi-channels

Abstract

The present invention discloses a combined detection method of electroencephalogram epilepsy sharp and spike wave discharge based on long short term memory network (LSTM) multi-channels. The combineddetection method comprises the following steps: step 1, filtering input original multi-lead electroencephalogram and eliminating artifacts caused by physiological activities of electrocatdiogram, chewing and swallowing; segmenting processed signals in time domain firstly according to characteristics of target waveform duration characteristics and transforming the signals into a recognition form ofthe subsequent steps; step 2, conducting feature extraction of data of each channel in the segmented signals through the long short term memory network and conducting feature fusion through an adaptive weighted fusion algorithm; and step 3, using results obtained by the feature fusion to classify multi-channel signal fragments through fully connected neural network and finally obtaining classification results of the entire signal at different periods, so as to achieve a purpose of sharp and spike wave discharge detection. The combined detection method can realize a sharp and spike detection effect with higher precision and stronger anti-interference ability under multi-channel signal input.

Description

technical field [0001] The invention belongs to the field of intelligent medical signal processing, and relates to a multi-channel long-short-term memory neural network (LSTM)-based joint detection method for EEG epilepsy spike discharge. Background technique [0002] The traditional spike wave discharge detection method mainly extracts the features of a single channel signal and compares it with the characteristic parameters of typical spike wave signals to judge whether it is a spike wave signal, so as to achieve the spike wave discharge detection method. For the purpose of signal detection, the detection method process has the following two shortcomings: [0003] 1. It is too sensitive to the selection of features. The same feature may have different signal differences in different periods on different individuals. It is easy to produce a feature that is highly distinguishable on some individuals but not distinguishable from other individuals. Phenomenon; [0004] 2. Tr...

AI Technical Summary

Problems solved by technology

[0003]1. Too sensitive to the selection of features, the same feature may have different signal differences in different periods on different individuals, and it is easy to cause a certain feature to be distinguished on some individuals High degree, but not distinguishable phenomenon for other individuals;

[0004]2. Traditional detection algorithms often perform single-channel detection. Generally speaking, spike waves are epileptiform discharges that can occur in multiple brain regions , that is, similar characteristic waveforms can be measured on multiple detection electrodes, and the detection accuracy of only a single channel cannot meet the needs

Images