Automatic detection method for epilepsy electroencephalography (EEG)/magnetoencephalography (MEG) abnormal waves and positioning system

A magnetoencephalogram and electroencephalogram technology, applied in the field of epilepsy electroencephalogram/magnetoencephalogram abnormal wave detection method and traceability positioning system, can solve problems that cannot be compared with artificial visual detection, and achieve auxiliary preoperative evaluation and get rid of Unreliable issues, the effect of streamlining the workflow
CN112220485APending Publication Date: 2021-01-15北京慧脑云计算有限公司
0 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
北京慧脑云计算有限公司
Publication Date
2021-01-15

Smart Images

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

Abstract

The invention discloses an automatic detection method for epilepsy electroencephalography (EEG) / magnetoencephalography (MEG) abnormal waves and a positioning system The method comprises the followingsteps: 1) segmenting EEG / MEG data of each sample to obtain a plurality of EEG / MEG data segments, wherein each EEG / MEG data segment is a data set in a two-dimensional matrix form; 2) training an EEG / MEG multi-view abnormal wave detection model by utilizing the EEG / MEG data fragments; 3) performing artifact removal operation on an EEG / MEG signal to be processed, and then segmenting the EEG / MEG datato obtain a plurality of EEG / MEG data segments; 4) respectively inputting the obtained EEG / MEG data fragments into the trained EEG / MEG multi-view abnormal wave detection model to obtain abnormal waveclassification results corresponding to the EEG / MEG data fragments; and 5) determining whether the EEG / MEG signal to be processed has abnormal waves or not according to the obtained abnormal wave classification result.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of signal recognition in the field of biometric feature recognition, and specifically relates to a method for detecting abnormal waves of EEG / MEG in epilepsy and a traceability positioning system based on deep learning. Background technique

[0002] As one of the most common neurological brain diseases, epilepsy caused by recurrent seizures affects about 1% of the population worldwide, and almost 30% to 40% of patients do not respond to drugs, which has a significant impact on their physical, mental and social health. negative impact. Surgery is an effective treatment for patients with drug-resistant epilepsy, and the key lies in identifying the brain region (seizure-induced zone) that produces the seizure. Epilepsy spikes are a widely accepted canonical biomarker as one of the abnormal EEG / MEG waves in epilepsy to identify epilepsy-occurring regions. Therefore, abnormal wave analysis can be used in the preoperative...

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