Electroencephalogram abnormal discharge detection method, device, medium and equipment

Abstract

An electroencephalogram abnormal discharge detection method, device, medium and equipment. The method comprises the following steps: acquiring an electroencephalogram original signal (101); performing hyperpolarization detection on the electroencephalogram original signal to obtain a predicted discharge position (102); acquiring a lead combination signal from the electroencephalogram original signal, and performing discharge detection on the lead combination signal according to the predicted discharge position (103); and generating a discharge probability graph containing discharge position information and discharge probability information (104). The method, device, medium and equipment realize automatic detection of electroencephalogram abnormal discharge, and improve the detection accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of electroencephalogram (EEG) detection technology, and includes, but is not limited to, a method, apparatus, medium, and device for detecting abnormal EEG discharges. Background Technology

[0002] Electroencephalography (EEG) is a sensitive indicator for assessing brain function and central nervous system status, and is widely used in the research and diagnosis of central nervous system diseases and mental illnesses. For example, in the qualitative and localization of paroxysmal brain dysfunction such as epilepsy, EEG is a diagnostic technique that cannot be replaced by other methods.

[0003] Abnormal waveforms in electroencephalograms (EEGs) are diverse, and clinically they are mainly divided into background activity abnormalities and paroxysmal abnormalities. Background activity abnormalities include changes in normal rhythm and slow-wave abnormalities; while paroxysmal abnormalities include epileptiform discharges, rhythmic bursts, and periodic waves. Epileptiform discharges (defined as IFSECN) serve as biomarkers for epilepsy, caused by rapid hypersynchronous depolarization of a group of neurons, reflecting abnormally increased neuronal excitability. Epileptiform discharges play a crucial role in the daily diagnosis and treatment of epilepsy; however, due to their low frequency, they consume a significant amount of time for physicians in routine EEG interpretation. Furthermore, the shortage of human resources for EEG interpretation in hospitals leads to a decline in the ability to interpret EEGs effectively. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] This disclosure presents a method, apparatus, medium, and device for detecting abnormal brainwave discharges.

[0006] According to a first aspect of the present disclosure, a method for detecting abnormal brainwave discharges is provided, the method comprising:

[0007] Acquire raw EEG signals;

[0008] Hyperpolarization detection is performed on the raw EEG signal to obtain the predicted discharge location;

[0009] The lead combination signal is obtained from the raw EEG signal, and the discharge detection is performed on the lead combination signal according to the predicted discharge location;

[0010] Generate a discharge probability map that includes discharge location information and discharge probability information.

[0011] In some embodiments, acquiring the raw EEG signals further includes:

[0012] The raw EEG signal is data collected by an EEG instrument through reference electrodes.

[0013] In some embodiments, the step of performing hyperpolarization detection on the raw EEG signal to obtain the predicted discharge location further includes:

[0014] The data from each channel of the raw EEG signal is filtered to obtain the lead data;

[0015] The lead data are superimposed to obtain the superimposed waveform;

[0016] Hyperpolarization detection is performed on the superimposed waveform to obtain a hyperpolarization probability map;

[0017] The predicted discharge location is determined based on the hyperpolarization probability diagram.

[0018] In some embodiments, performing hyperpolarization detection on the superimposed waveform to obtain the hyperpolarization probability map includes:

[0019] Select waveform positions whose recall rate exceeds 0.99 based on the feature parameters of the superimposed waveform;

[0020] The waveform positions are combined;

[0021] Obtain the hyperpolarization probability map;

[0022] In some embodiments, the characteristic parameters include the waveform height, peak rise time, peak fall time, and peak angle.

[0023] In some embodiments, obtaining the lead combination signal from the raw EEG signal and detecting the discharge of the lead combination signal according to the predicted discharge location further includes:

[0024] Based on the original EEG signal, a bipolar reference EEG signal, an auricular reference EEG signal, and an average reference EEG signal are obtained, wherein the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal together form the lead combination signal;

[0025] The number of detectors is determined based on the number of EEG signals contained in the lead combination signal, and the number of detectors corresponds one-to-one with the number of EEG signals contained in the lead combination signal.

[0026] The detectors are used to detect discharges at the positions corresponding to the predicted discharge positions in the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal, respectively.

[0027] According to a second aspect of the present disclosure, a device for detecting abnormal brainwave discharges is also provided, the device including an acquisition module, the acquisition module being configured to:

[0028] Obtain raw EEG signals.

[0029] In some embodiments, the apparatus further includes a processing module, the processing module being configured to:

[0030] The data from each channel of the raw EEG signal is filtered to obtain the lead data; the lead data is superimposed to obtain the superimposed waveform; hyperpolarization detection is performed on the superimposed waveform to obtain a hyperpolarization probability map; and the predicted discharge location is determined based on the hyperpolarization probability map.

[0031] In some embodiments, the apparatus further includes a detection module, the detection module being configured to:

[0032] Based on the raw EEG signal, a bipolar reference EEG signal, an auricular reference EEG signal, and an average reference EEG signal are acquired, wherein the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal together form the lead combination signal; the number of detectors is determined based on the number of EEG signals contained in the lead combination signal, and the number of detectors corresponds one-to-one with the number of EEG signals contained in the lead combination signal; multiple detectors are used to detect discharges at the positions corresponding to the predicted discharge positions in the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal, respectively.

[0033] In some embodiments, the apparatus further includes a generation module, the generation module being configured to:

[0034] Generate a discharge probability map that includes discharge location information and discharge probability information.

[0035] A third aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0036] A fourth aspect of this disclosure provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method of the first aspect described above.

[0037] The present disclosure discloses a method, apparatus, medium, and device for detecting abnormal brainwave discharges, which can achieve the following:

[0038] Beneficial effects:

[0039] This system achieves fully automated detection of epileptiform discharges. By utilizing hyperpolarization probability maps to determine candidate locations of abnormal discharges, the detection complexity and computation time are significantly reduced. Furthermore, the fully automated detection and location of candidate abnormal discharges in the initial stages saves on labor costs. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of these embodiments. In these drawings, similar reference numerals are used to denote similar elements. The drawings described below are some embodiments of the present disclosure, but not all embodiments. Other drawings will be readily available to those skilled in the art based on these drawings without any inventive effort.

[0041] Figure 1 This is a schematic diagram of an abnormal brainwave discharge detection scenario according to an embodiment of the present disclosure.

[0042] Figure 2 This is a flowchart of a method for detecting abnormal brainwave discharges according to an embodiment of the present disclosure.

[0043] Figure 3 This is a block diagram of an abnormal brainwave discharge detection device according to an embodiment of the present disclosure. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this disclosure can be arbitrarily combined with each other.

[0045] Currently, a significant amount of manpower is required to interpret EEG results of epileptiform discharges during diagnosis and treatment. However, due to the influence of the interpreters' experience, misinterpretations and omissions frequently occur.

[0046] This disclosure proposes a method for detecting abnormal electrical discharges in brainwaves. The method utilizes a hyperpolarization probability map to determine the selection of candidate locations for abnormal discharges, which significantly reduces the overall computational complexity and thus the computation time.

[0047] This disclosure provides a method for detecting abnormal brainwave discharges, such as... Figure 2As shown, the method includes:

[0048] Step 101: Obtain raw EEG signals;

[0049] Step 102: Perform hyperpolarization detection on the raw EEG signal to obtain the predicted discharge location;

[0050] Step 103: Obtain the lead combination signal from the raw EEG signal, and perform discharge detection on the lead combination signal according to the predicted discharge location;

[0051] Step 104: Generate a discharge probability map containing discharge location information and discharge probability information.

[0052] In this embodiment of the disclosure, during step 101, a digital multi-functional electroencephalogram (EEG) instrument can be used to acquire raw EEG signals from the human body. The digital multi-functional EEG instrument has internally stored system default settings. The user acquires signals by attaching a patch to the subject's head; therefore, EEG acquisition is achieved with simple operation. The reference electrodes used during EEG signal acquisition can be the preset system reference electrodes on the digital multi-functional EEG instrument, facilitating operation. The acquired EEG signals are stored in the digital multi-functional EEG instrument, and the raw EEG signals are discrete data. Different sampling rates can be used for different EEG signal acquisition scenarios. Commonly used sampling rates for EEG signal acquisition via scalp patch methods include 512Hz and 256Hz.

[0053] The raw EEG signals can be obtained by connecting multiple electrodes to various locations on the head according to the international 10-20 system electrode placement method, thus acquiring EEG signals at the locations of these electrodes. For example... Figure 1 As shown, the international 10-20 system involves 19 recording electrodes: Fp1, Fp2, F7, F3, FZ, F4, F8, T3, C3, CZ, C4, T4, T5, P3, PZ, P4, T6, O1, and O2. In step 101, the EEG data acquired through the system reference electrodes can be used as raw EEG data. Data from other reference electrodes can be calculated using this raw EEG data. For example, in an exemplary scenario, the system reference electrodes could be F3 / F4 or C3 / C4. In this embodiment, the acquisition location of the raw EEG signal is not limited to the 19 recording electrode locations specified in the international 10-20 system, but may include... Figure 1 Any one or more of the 19 recording electrode positions shown may also include positions in any other part of the human brain, and this disclosure does not limit them.

[0054] Step 102 above also includes:

[0055] Step 1021: Filter the data of each channel of the raw EEG signal to obtain lead data;

[0056] Step 1022: Superimpose the lead data to obtain the superimposed waveform;

[0057] Step 1023: Perform hyperpolarization detection on the superimposed waveform to obtain the hyperpolarization probability map;

[0058] Step 1024: Determine the predicted discharge location based on the hyperpolarization probability diagram.

[0059] The filtering process for each channel of the raw EEG signal in step 1021 includes:

[0060] Each channel of the raw EEG signal is filtered at the power frequency, which is typically 50Hz. The filtered EEG signal is then passed through a bandpass filter of 0.5Hz-75Hz to obtain the lead data.

[0061] The hyperpolarization detection in step 1023 includes:

[0062] Waveform locations with a recall rate exceeding 0.99 are selected based on the feature parameters of the superimposed waveforms. Recall rate refers to the probability of correctly identifying abnormal EEG discharge locations within the superimposed waveforms during hyperpolarization detection. The waveform locations are combined to obtain a hyperpolarization probability map. Feature parameters include, but are not limited to, waveform height, peak rise duration, peak fall duration, and peak angle. Furthermore, the recall rate can be set according to different needs, or a machine learning method can be used to obtain the set value of the recall rate; this disclosure does not impose any limitations.

[0063] Step 103 above also includes:

[0064] Step 1031: Based on the original EEG signal, acquire the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal, wherein the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal together form the lead combination signal.

[0065] In step 1031, the bipolar reference EEG signal, the earlobe reference EEG signal, and the averaged reference EEG signal are obtained from the bipolar reference lead, the earlobe reference lead, and the averaged reference lead, respectively.

[0066] In this setup, the bipolar reference lead is recorded by a pair of probing electrodes. No common electrode is connected to any of the bipolar leads. Bipolar lead groups are mostly configured in a chain-like manner, meaning that along adjacent electrodes in the same arrangement, one electrode is shared and connected to the input of one amplifier and the input of another amplifier, serving as the reference. Figure 1 As shown, patterns such as the frontal-central region (e.g., the area enclosed by FZ-CZ) and the central-parietal region (e.g., the area enclosed by CZ-PZ) can avoid pattern distortion caused by reference electrode activation. Moreover, during focal discharges, a special EEG pattern—phase inversion—can be formed.

[0067] The ear-pole reference lead uses both earlobes as reference electrodes, also known as a unipolar lead. The reference electrode is a common electrode for multiple leads. All recording electrodes are connected to the negative terminal of the amplifier, and the reference electrode is connected to the positive terminal. The averaging reference lead connects each recording electrode on the scalp (only each electrode placed) in series with a 1-2 MΩ resistor, and then connects them in parallel. After this process, the potential at each point on the scalp is significantly reduced and averaged, theoretically approaching zero.

[0068] The embodiments provided in this disclosure can improve the interpretation ability and accuracy of electroencephalograms (EEGs). By using combined lead waveforms and comprehensively analyzing the different manifestations of these waveforms in different lead conditions, and detecting discharges based on discharge activation logic rules, the false alarm rate is significantly reduced, and the accuracy of epilepsy detection is improved.

[0069] Step 1032: Determine the number of detectors based on the number of EEG signals contained in the lead combination signal. The number of detectors corresponds one-to-one with the number of EEG signals contained in the lead combination signal.

[0070] Step 1033: Use multiple detectors to detect discharges at the locations corresponding to the predicted discharge locations in the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal.

[0071] The detector is a single-channel, multi-type waveform classifier for the corresponding lead data. The waveform classifier categorizes EEG fragments into four main types: epileptiform discharges, slow waves, artifacts, and others. When calculating the discharge probability map, the probability of artifact appearance is first calculated, and some artifacts are filtered out. Then, the probability locations of artifact appearances are compared with the discharge locations in the hyperpolarization probability map, further filtering out artifacts to improve detection accuracy.

[0072] The embodiments provided in this disclosure further filter out artifacts by exploiting the difference between the artifact occurrence logic and the discharge occurrence logic when calculating the discharge probability map, thus solving the problem of low accuracy caused by errors in the interpretation of the detection equipment.

[0073] This disclosure also provides a device for detecting abnormal brainwave discharges, such as... Figure 3 As shown, the device includes an acquisition module 201, which is configured to:

[0074] Obtain raw EEG signals.

[0075] The device further includes a processing module 202, which is configured to:

[0076] Each channel of the raw EEG signal is filtered to obtain lead data; the lead data is superimposed to obtain a superimposed waveform; hyperpolarization detection is performed on the superimposed waveform to obtain a hyperpolarization probability map; and the predicted discharge location is determined based on the hyperpolarization probability map.

[0077] The device also includes a detection module 203, which is configured to:

[0078] Based on the raw EEG signals, bipolar reference EEG signals, auricular reference EEG signals, and average reference EEG signals are acquired. These signals together form a lead combination signal. The number of detectors is determined based on the number of EEG signals contained in the lead combination signal, with each detector corresponding to a specific number of EEG signals in the lead combination signal. Multiple detectors are used to detect discharges at the locations corresponding to the predicted discharge locations in the bipolar reference EEG signal, auricular reference EEG signal, and average reference EEG signal.

[0079] The device further includes a generation module 204, which is configured to:

[0080] Generate a discharge probability map that includes discharge location information and discharge probability information.

[0081] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0082] This disclosure also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0083] The present disclosure discloses a method, apparatus, medium, and device for detecting abnormal brainwave discharges, which can achieve the following:

[0084] Beneficial effects:

[0085] The embodiments disclosed herein can save doctors valuable time in locating epileptiform discharges, enabling fully automated detection of epileptiform discharges. By using a hyperpolarization probability map to determine the selection of candidate locations for abnormal discharges, the overall computational complexity is greatly reduced, resulting in significantly lower computation time and savings in labor costs.

[0086] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, apparatus (devices), or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data), including but not limited to RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and can include any information delivery medium.

[0087] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising…” does not exclude the presence of additional identical elements in the article or device that includes said element.

[0091] Although preferred embodiments of this disclosure have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this disclosure.

[0092] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, then the intent of this disclosure also includes these modifications and variations.

[0093] Industrial applicability

[0094] The embodiments of this disclosure provide a method, apparatus, medium, and device for detecting abnormal brainwave discharges, which can solve the problems of existing technologies that consume a lot of doctors' valuable time in locating epileptiform discharges, and that the interpretation ability of primary care physicians is low, resulting in low accuracy. Furthermore, by using a probability maximization method to detect abnormal brainwave discharges, the location of abnormal brainwave discharges can be accurately determined, while also reducing manpower burden, saving time, and improving the quality of medical services.

Claims

1. A method for detecting abnormal brainwave discharges, characterized in that, Acquire raw EEG signals; Hyperpolarization detection is performed on the raw EEG signal to obtain the predicted discharge location; The lead combination signal is obtained from the raw EEG signal, and the discharge detection is performed on the lead combination signal according to the predicted discharge location; Generate a discharge probability map that includes discharge location information and discharge probability information; The step of performing hyperpolarization detection on the raw EEG signal to obtain the predicted discharge location includes: The lead data in the raw EEG signal are superimposed to obtain a superimposed waveform; Hyperpolarization detection is performed on the superimposed waveform to obtain a hyperpolarization probability map; The predicted discharge location is determined based on the hyperpolarization probability diagram; The step of performing hyperpolarization detection on the superimposed waveform to obtain a hyperpolarization probability map includes: Select waveform positions whose recall rate exceeds 0.99 based on the feature parameters of the superimposed waveform; The waveform positions are combined; Obtain the hyperpolarization probability map; The characteristic parameters include the waveform height, peak rise time, peak fall time, and peak angle.

2. The method for detecting abnormal brainwave discharges according to claim 1, characterized in that, The process of superimposing the lead data from the raw EEG signal to obtain the superimposed waveform includes: The data from each channel of the raw EEG signal is filtered to obtain the lead data; The lead data are superimposed to obtain the superimposed waveform.

3. The method for detecting abnormal brainwave discharges according to claim 1, characterized in that, The step of obtaining lead combination signals from the raw EEG signals and detecting discharges in the lead combination signals based on the predicted discharge locations includes: Based on the original EEG signal, a bipolar reference EEG signal, an auricular reference EEG signal, and an average reference EEG signal are obtained, wherein the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal together form the lead combination signal; Discharge detection is performed on the position in the lead combination signal that corresponds to the predicted discharge position.

4. The method for detecting abnormal brainwave discharges according to claim 3, characterized in that, The step of detecting discharge at the position corresponding to the predicted discharge position in the lead combination signal includes: The number of detectors is determined based on the number of EEG signals contained in the lead combination signal, and the number of detectors corresponds one-to-one with the number of EEG signals contained in the lead combination signal. The detectors are used to detect discharges at the positions corresponding to the predicted discharge positions in the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal, respectively.

5. The method for detecting abnormal brainwave discharges according to claim 1, characterized in that, The raw EEG signal is discrete sampled data at a preset frequency; and / or, The raw EEG signal is data collected by an EEG instrument through reference electrodes.

6. A device for detecting abnormal brainwave discharges, characterized in that, The acquisition module is used to acquire raw EEG signals; The processing module is used to perform hyperpolarization detection on the raw EEG signal to obtain the predicted discharge location; The detection module is used to obtain the lead combination signal from the raw EEG signal and to perform discharge detection on the lead combination signal according to the predicted discharge location. The generation module is used to generate a discharge probability map that includes discharge location information and discharge probability information. The processing module is specifically used for: The lead data in the raw EEG signal are superimposed to obtain a superimposed waveform; Hyperpolarization detection is performed on the superimposed waveform to obtain a hyperpolarization probability map; The predicted discharge location is determined based on the hyperpolarization probability diagram; The processing module is specifically used for: Select waveform positions whose recall rate exceeds 0.99 based on the feature parameters of the superimposed waveform; The waveform positions are combined; Obtain the hyperpolarization probability map; The characteristic parameters include the waveform height, peak rise time, peak fall time, and peak angle.

7. The brainwave abnormal discharge detection device according to claim 6, characterized in that, The processing module is specifically used for: The data from each channel of the raw EEG signal is filtered to obtain the lead data; The lead data are superimposed to obtain the superimposed waveform.

8. The brainwave abnormal discharge detection device according to claim 6, characterized in that, The detection module is specifically used for: Based on the original EEG signal, a bipolar reference EEG signal, an auricular reference EEG signal, and an average reference EEG signal are obtained, wherein the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal together form the lead combination signal; Discharge detection is performed on the position in the lead combination signal that corresponds to the predicted discharge position.

9. The brainwave abnormal discharge detection device according to claim 8, characterized in that, The detection module is specifically used for: The number of detectors is determined based on the number of EEG signals contained in the lead combination signal, and the number of detectors corresponds one-to-one with the number of EEG signals contained in the lead combination signal. The detectors are used to detect discharges at the positions corresponding to the predicted discharge positions in the bipolar reference EEG signal, the auricular reference EEG signal, and the average reference EEG signal, respectively.

10. The brainwave abnormal discharge detection device according to claim 6, characterized in that, The raw EEG signal is discrete sampled data at a preset frequency; and / or, The raw EEG signal is data collected by an EEG instrument through reference electrodes.

11. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

12. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method of any one of claims 1 to 5.

Images