Spike and slow wave complex detection and identification method and system based on feature fusion

Abstract

The invention provides a spike and slow wave complex detection and identification method based on feature fusion. The spike and slow wave complex detection and identification method comprises the following steps of 1, extracting time-frequency domain features according to labeled sample data of a spike and slow wave complex database and a normal brain wave database; estimating distance features by utilizing the spike and slow wave complex database, the normal brain wave database and a spike and slow wave complex template library, establishing a spike and slow wave complex feature library and a normal waveform feature library through the features, and further training a classification model; step 2, estimating the distance degree between the effective unknown type brain wave data and the spike and slow wave complex template data by using a DTW algorithm; and step 3, extracting time-frequency domain features of the unknown type brain wave data, fusing the time-frequency domain features and the distance degree features as typical features, sending the features into a classifier, and outputting a brain wave type classification result. In addition, normalization processing and effective waveform endpoint detection based on short-time energy and spike and slow wave complex structure characteristics are carried out on the input unknown type brain wave data, so that the accuracy and robustness of the recognition algorithm can be greatly improved.

Description

technical field [0001] The invention relates to the field of intelligent medical technology, in particular to a method and system for detecting and identifying spike-slow complex waves based on feature fusion. Background technique [0002] Clinically, EEG examination is to record the electrical activity of the examinee's brain through scalp electrodes, and to determine whether there are abnormal discharges in the examinee's brain by observing the waveform of the brain wave. EEG examination is an important basis for doctors to determine the classification of epilepsy patients and adjust the treatment plan, and its detection results have great clinical significance. Doctors can determine whether there is a potential cause of epileptic seizures by observing whether there is an abnormal discharge waveform in the brain wave of the examinee during the examination period, and the spike and slow complex wave is one of the most important abnormal EEG waveforms in patients with epilep...

AI Technical Summary

Problems solved by technology

Doctors can determine whether there is a potential cause of epileptic seizures by observing whether there is an abnormal discharge waveform in the brain wave of the examinee during the examination period, and the spike and slow complex wave is one of the most important abnormal EEG waveforms in patients with epilepsy. The mechanism of abnormal discharge of internal bioelectrical signals leads to the waveform structure characteristics of the spike-slow complex wave. The main waveform structure feature is a spike wave of about 20 milliseconds followed by a slow wave of 200 milliseconds to 500 milliseconds (mostly 300 milliseconds). The occurrence of spike and slow complex waves is an important basis for diagnosing epilepsy. The routine brain wave examination is usually about one hour, and in severe cases, there is usually 24 hours of brain wave monitoring. Doctors need to Reading the EEG data frame by frame during the inspection time to observe whether there are spike-slow complex waves in the EEG data is a very time-consuming task.

Images