Seizure interval epilepsy discharge detection method, storage medium and equipment

Abstract

The invention provides an epileptic seizure interval epilepsy discharge detection method and device and a storage medium, wherein the detection method comprises the steps: segmenting a preprocessed electroencephalogram signal, and generating m w*256 input sample matrixes S(m); and outputting an epilepsy electric activity detection result according to the input m w*256 input sample matrixes S(m). The related features of the epilepsy electric activity are identified by using the first relevance of the epilepsy electric activity in each sensor space at the same time, the occasionality of the artifacts in each sensor space at the same time and the second relevance different from the first relevance, so that the artifacts which cannot be filtered by a filtering means can be filtered; and automatic detection can be completed without manually designing an artifact filtering unit and a feature project.

Description

[0001] This patent application is a divisional application of the Chinese patent 202011529814.6 with the title of "Detection Device and Method for Interictal Epileptiform Electrical Activity of Epilepsy Patients", which is hereby incorporated by reference in its entirety. technical field [0002] The present invention relates to the field of biomedical detection, in particular to a device and method for detecting interictal epileptiform electrical activity in epileptic patients, in particular to an interictal epileptic electrical activity detection method based on the feature analysis of sensor space EEG signals at the same time. Activity detection apparatus and method. Background technique [0003] Scalp electroencephalography (sEEG) is a non-invasive signal acquisition method used clinically to record brain-related activity. It has high temporal resolution and plays an important role in the detection, diagnosis, treatment, efficacy evaluation and pathological research of e...

AI Technical Summary

Problems solved by technology

[0007] (1) Complex preprocessing

sEEG contains a large number of artifacts that cannot be filtered out by filtering algorithms. It is difficult to accurately distinguish artifacts and IEDs using the above-mentioned traditional methods. Therefore, most of the traditional methods are equipped with individually designed artifact removal algorithms or artificial artifact removal criteria. Pathological information contained in a large and vulnerable signal

[0008] (2) poor performance in different patients

Epilepsy patients of different types, different ages, and different genders have great differences in the external manifestations of IEDs such as morphology and duration, and there may be great differences in clinical records between different hospitals due to differences in equipment, reference electrodes, environment and other factors

Additionally, one or more undesirable channels may be present in the sEEG of some patients

These reasons lead to the fact that the feature engineering based on signal processing experience in the traditional method cannot fully and deeply mine the sEEG features, making the distinction between IEDs and background signals lack of robustness, and it is difficult to cope with complex and changeable patient conditions in actual clinical applications.

Images