A method for automatic detection of epilepsy magnetoencephalogram spikes and a traceable positioning system

Abstract

The invention discloses a spike wave automatic detection method and a traceability positioning system of an epileptic magnetoencephalogram. The method is as follows: 1) Segment the magnetoencephalogram data of each sample to obtain multiple magnetoencephalogram data fragments; wherein each magnetoencephalogram data fragment is a data set in the form of a two-dimensional matrix with a size of M*N; 2 ) Use the MEG data fragments to train the MEG multi-view spike detection model; 3) Perform the artifact removal operation on the MEG signals to be processed, and then segment the MEG data to obtain multiple MEG data fragments; 4) Input the obtained magnetoencephalogram data fragments into the trained multi-view spike detection model of magnetoencephalogram, and obtain the spike classification results of the corresponding magnetoencephalogram data fragments; The presence or absence of spikes in the processed MEG signal. The invention simplifies the doctor's work flow and can effectively assist the doctor in preoperative assessment of epileptic patients.

Description

Technical field [0001] The invention belongs to the field of magnetoencephalogram signal recognition in the field of biometric recognition, and is specifically a multi-view spike detection method and traceability positioning system for epileptic magnetoencephalogram 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 world’s population, and almost 30% to 40% of patients do not respond to drugs, which has a significant impact on their physical, psychological and social health. Negative impact. Surgery is an effective way to treat patients with drug-resistant epilepsy. The key is to determine the brain area (epileptogenic area) that produces epilepsy. Epilepsy spike is a widely accepted typical biomarker used to identify epilepsy areas. Therefore, spike wave analysis can be used for preoperative evaluation of patients with epilepsy. [0003] Magnetoencephalography...

AI Technical Summary

Problems solved by technology

Despite great success, in clinical practice, none of the methods proposed so far can compare favorably with human visual inspection, i.e., routine detection of MEG signals or by human visual inspection.

Images