Epilepsy spine wave automatic detection and peak value positioning method

Abstract

The invention discloses an epilepsy spine wave automatic detection and peak value positioning method. The method comprises the following steps: 1) splitting each magnetoencephalogram data into a plurality of data segments with the same size; 2) constructing a deep learning network model which comprises a single-channel coding module, a deep feature transmission module and a global decoding module, wherein the single-channel coding module is used for carrying out depth feature extraction on single-channel data in a data fragment to obtain a plurality of depth features of different sizes and sending the depth features to the depth feature transmission module for data dimension reduction, and the global coding module is used for carrying out convolution and up-sampling calculation on the depth features from the depth feature with the minimum size, and splicing the obtained depth features with the depth features with the correspondingly consistent size until the depth feature with the maximum size is processed; (3) training a deep learning network model by using each data segment, and (4) inputting magnetoencephalogram data to be processed into the trained deep learning network model to carry out ratchet wave detection and peak value positioning.

Description

technical field [0001] The invention belongs to the field of magnetoencephalogram signal recognition in the field of biometric feature recognition, and is specifically a method for automatic detection and peak location of epilepsy spikes based on deep learning, which can not only judge whether there are spikes in magnetoencephalogram data, but also determine The moment of the spike peak point helps clinicians reduce the workload and locate the epileptogenic focus more accurately. Background technique [0002] Epilepsy is a common neurological brain disease characterized by central nervous system dysfunction caused by excessive discharge of brain neurons. For the diagnosis and treatment of epilepsy, the key is to determine the brain area of ​​abnormal discharge, that is, the epileptogenic focus. Targeted drug suppression or surgical resection of the epileptogenic focus is an effective way to treat epilepsy. [0003] Magnetoencephalography (MEG) is a non-invasive technique f...

AI Technical Summary

Problems solved by technology

However, the current existing algorithms can only be satisfied with detecting whether a spike is included in a fixed time segment, and cannot accurately locate the moment point with the highest spike energy, that is, the peak point of the spike

Images