Magnetoencephalography epileptic spike wave recognition method and system

A recognition method and technology of epilepsy spines, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as energy-consuming, accuracy of classification results cannot be guaranteed, and judgment results are not the same
CN109700463AActive Publication Date: 2019-05-03SICHUAN UNIV
2 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
SICHUAN UNIV
Publication Date
2019-05-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a magnetoencephalography epileptic spike wave recognition method and system. The method comprises the following steps of dividing MEG data into spike wave data and non-spike wave data, and pretreating the MEG data to respectively obtain the spike wave data and the non-spike wave data, of which the N segment phases are the same in length; performing analytical treatment onthe obtained segments of data, performing extraction to obtain characteristic vectors of various segments of data to form a sample dataset, and dividing the sample dataset into a training set and a test set; training a radial primary kernel function support vector machine classifier through the training set to obtain a trained classifier model; and inputting the test set to the classifier model torecognize whether epileptic spike waves exist or not. Automatic recognition of epilepsy brain magnetic signals can timely judge the condition of the patients, wherein the judgment accuracy rate can achieve 93.8%, the labor intensity of doctors is reduced, the detection accuracy rate is increased, and the omission factor and the false positive rate are reduced. The magnetoencephalography epilepticspike wave recognition method and system have important significance clinically.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of machine learning, in particular to a method and system for identifying epileptic spikes in magnetoencephalography. Background technique

[0002] The main manifestations of epilepsy in the magnetoencephalogram are spikes and sharp waves, which are sometimes not distinguished and are collectively referred to as epileptic transients or spikes. Spikes and sharp waves stand out from the background activity, with a higher amplitude and a period between 20ms and 200ms.

[0003] The analysis of magnetic brain signals is mainly the detection and analysis of abnormal brain activities. These tasks are currently done by medical workers through visual detection of patients' magnetoencephalograms based on experience. There are many unfavorable factors in visual inspection. Generally, 60 minutes of data are recorded for one inspection. Finding spikes from very long data is very energy-consuming, which requires a high level of ju...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More