Electroencephalogram signal processing method and device and terminal equipment

Abstract

The invention relates to the technical field of neurology, discloses a neurology disease auxiliary diagnosis method based on electroencephalogram signals, and particularly relates to an electroencephalogram signal processing method and device and terminal equipment. The corresponding target electroencephalogram signals are obtained by segmenting the electroencephalogram signals based on the frequency and the wave band, the target electroencephalogram signals are classified and recognized through the classifier, and finally the classification result of whether epilepsy exists or not is obtained. According to the embodiment, the electroencephalogram signals are automatically recognized, the automatic processing level is improved, the manual film reading cost is reduced, and the recognition accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of neurology, and is an auxiliary diagnosis method for neurological diseases based on electroencephalogram signals, specifically an electroencephalogram signal processing method, apparatus and terminal device. Background Art

[0002] Epilepsy is a common chronic paroxysmal disease of the nervous system, with the common characteristics of paroxysmal, transient, repetitive and stereotyped. There are about 5 million epilepsy patients in the world, with about 2 million new patients each year, and the incidence rate is about 0.7%. Its main characteristics are seizures or abnormal behaviors caused by abnormal neurophysiological activities, accompanied by varying degrees of loss of sensation or consciousness. Unlike other nervous system diseases, epilepsy can be divided into secondary epilepsy caused by other nervous system diseases such as encephalitis and trauma, and primary epilepsy with no external causes and unclear causes; according to the scope of its attack, it can be divided into generalized seizures and focal seizures. Under the secondary classification, it can also be divided into motor seizures and non-motor seizures according to the symptom description. According to more detailed symptom descriptions, it can be divided into generalized tonic-clonic seizures, atonic seizures, absence seizures, automatisms, focal tonic seizures, focal clonic seizures, etc.

[0003] At present, the clinical diagnosis of epilepsy relies on detailed clinical manifestations and electroencephalogram (EEG) examinations. Electroencephalogram (EEG) examinations, including video EEG and dynamic EEG, are important diagnostic bases for epilepsy diagnosis. In current clinical work, EEG examinations require professional physicians to spend a lot of effort to interpret and may lead to misdiagnosis.

[0004] Therefore, with respect to the epilepsy examination methods in the prior art, there is a need for a method for automating epilepsy examinations, thereby reducing the workload of doctors and improving the recognition of the occurrence of epilepsy. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide an electroencephalogram (EEG) signal processing method, apparatus and terminal device, which can realize automatic identification of the occurrence of epilepsy.

[0006] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0007] In a first aspect, a method for processing electroencephalogram (EEG) signals is provided, the method being applied to a patient management device, the patient management device being connected to a data acquisition terminal via a server, the patient management device storing patient information about the patient, including a basic information management module and a target information management module; the data acquisition terminal being used to collect the patient's EEG signals, the EEG signals being stored in the target information management module based on time segments, the basic information management module storing the patient's basic medical information, the patient's basic medical information including but not limited to one or more information of the patient's age, patient's gender, and patient's medical records; the method being applied to the server, the method comprising: retrieving a plurality of corresponding EEG signals from the target information management module according to a target time period, and converting the plurality of EEG signals into a single EEG signal; The EEG signals are integrated based on a graph representation to obtain an initial EEG; multiple EEG signals in the initial EEG are segmented based on a first frequency segment and a second frequency segment to obtain initial frequency EEG signals, and the initial frequency EEG signals are segmented according to an EEG signal fluctuation threshold, and EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold are extracted and integrated to obtain intermediate frequency EEG signals, thereby obtaining an intermediate EEG; a target band is determined based on the patient's age, and the EEG signal corresponding to the target band in the intermediate EEG is extracted to obtain a target EEG; a power spectral density and a time domain mean of the target EEG are extracted, and the power spectral density and the time domain mean are processed based on a classifier to obtain a classification result, wherein the classification result is a probability value of having epilepsy.

[0008] Furthermore, the first frequency segment is 0-80 Hz, and the second frequency segment is 80-500 Hz.

[0009] Furthermore, the segmenting of the plurality of EEG signals in the EEG based on the first frequency segment and the second frequency segment to obtain intermediate frequency EEG signals includes: acquiring EEG signals corresponding to 0-80 Hz in the plurality of EEG signals as the intermediate frequency EEG signals.

[0010] Furthermore, the initial frequency EEG signal is segmented according to the EEG signal fluctuation threshold, including: obtaining the EEG signal fluctuation value corresponding to each band signal in the initial frequency EEG signal, and segmenting each band signal that meets the EEG signal fluctuation threshold.

[0011] Furthermore, extracting and integrating EEG signals from the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals includes: integrating the segmented band signals to obtain the intermediate frequency EEG signals.

[0012] Furthermore, the target band is determined based on the patient's age, and the EEG signal corresponding to the target band in the intermediate EEG is extracted to obtain the target EEG, including: obtaining the patient's age, querying the age-band correspondence relationship based on the patient's age to obtain the target band, extracting the target band in the intermediate frequency EEG signal, and integrating the target band to obtain the target EEG.

[0013] Furthermore, the extracting of the power spectral density of the target electroencephalogram includes: segmenting the EEG signal in the target electroencephalogram based on a target time window to obtain multiple sub-signals; performing a fast Fourier transform on each sub-signal to convert the time domain signal into a frequency domain signal to obtain the power spectral density in each time window, and averaging the power spectral density information in all time windows to obtain the power spectral density of the EEG signal in the target electroencephalogram.

[0014] Furthermore, the classifier is a GBDT classifier.

[0015] In a second aspect, an electroencephalogram (EEG) signal processing device is provided, the device comprising: retrieving a plurality of corresponding electroencephalogram (EEG) signals from a target information management module according to a target time period, and integrating the plurality of the EEG signals based on a graph representation to obtain an initial electroencephalogram (EEG); segmenting the plurality of the EEG signals in the initial electroencephalogram (EEG) based on a first frequency segment and a second frequency segment to obtain initial frequency EEG signals, and segmenting the initial frequency EEG signals according to an EEG signal fluctuation threshold, extracting and integrating the EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtaining an intermediate EEG; determining a target band based on the patient's age, and extracting the EEG signals corresponding to the target band in the intermediate EEG to obtain a target EEG; extracting a power spectral density and a time domain mean of the target EEG, and processing the power spectral density and the time domain mean based on a classifier to obtain a classification result, the classification result being a probability value of having epilepsy.

[0016] In a third aspect, a terminal device is provided, comprising: a memory and a processor coupled to the memory, wherein the processor is configured to execute any one of the above-mentioned EEG signal processing methods based on instructions stored in the memory.

[0017] In the technical solution provided in the embodiment of the present application, the EEG signal is segmented based on frequency and band to obtain the corresponding target EEG signal, and the target EEG signal is classified and identified by a classifier, and finally a classification result of whether the patient has epilepsy is obtained. This embodiment improves the level of automated processing, reduces the cost of manual film reading, and improves the accuracy of identification by automatically identifying EEG signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] The methods, systems and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example numbers represent similar mechanisms in the various views of the accompanying drawings.

[0020] Figure 1 It is a schematic diagram of the structure of the medical management system provided in an embodiment of the present application.

[0021] Figure 2 It is a flowchart of the method for processing EEG signals provided in an embodiment of the present application.

[0022] Figure 3 It is a schematic diagram of a high-lead EEG acquisition endpoint provided in an embodiment of the present application.

[0023] Figure 4 It is a schematic diagram of the structure of the electroencephalogram signal processing device provided in an embodiment of the present application.

[0024] Figure 5 It is a schematic diagram of the terminal device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0026] In the following detailed description, numerous specific details are set forth by way of example in order to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that the present application may be practiced without these details. In other cases, well-known methods, procedures, systems, compositions and / or circuits have been described at a relatively high level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

[0027] Flowcharts are used in the present application to illustrate the execution process performed by the system according to the embodiment of the present application. It should be clearly understood that the execution process of the flowchart may not be performed in order. On the contrary, these execution processes may be performed in reverse order or simultaneously. In addition, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0028] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0029] (1) In response, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0030] (2) Based on is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or have a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0031] At present, the diagnosis of epilepsy is mainly through obtaining the patient's complete medical history of epileptic seizures as much as possible from the patient and his relatives and friends, and then referring for EEG examination. Epileptic seizures are mainly determined based on the patient's clinical manifestations and EEG records. EEG records the electrical activity of the brain, which contains potential pathological information, and is of great significance for the evaluation and diagnosis of epilepsy, lesion localization, dynamic monitoring, treatment plans and effect evaluation. Until now, in clinical practice, EEG examinations are still mainly performed by professional doctors using visual inspection. When doctors are faced with massive amounts of EEG data, visual inspection is time-consuming and inefficient, and the complicated workload will affect the doctor's judgment and the accuracy of the results, resulting in an increase in the misdiagnosis rate. At the same time, due to the interference of clinical experience and subjective factors, different doctors may give different test results for the same EEG data.

[0032] In order to solve the technical problems in the prior art, the present application provides an EEG signal processing method for realizing automatic diagnosis of epilepsy. Figure 1, applied in a medical management system 100, the system includes a patient management device 110, a data acquisition terminal 120, a display terminal 130 and a server 140, wherein the patient management device stores patient information about the patient, the data terminal is used to collect the patient's electroencephalogram signal, and the collected electroencephalogram signal is stored in the patient management device based on a time segmentation method. Among them, the patient management device includes a basic information management module and a target information management module, wherein the basic information management module stores the patient's basic medical information, and the target information management module is used to store the electroencephalogram signal collected by the data acquisition terminal, and stores it in a time segmentation method. Among them, the display terminal 130 is used to display the collected electroencephalogram signal.

[0033] Specifically, the basic medical information in the embodiment of the present application includes but is not limited to the patient's age, the patient's gender, and one or more information in the patient's medical record. Among them, for this application, the basic medical information is mainly the patient's age information.

[0034] In this embodiment, the data acquisition end is a high-lead device, and the EEG signal collected by the high-lead EEG cap is a high-lead EEG. Figure 3 The high-lead EEG used in this embodiment is a 128-lead EEG.

[0035] The collected EEG signals can be used to automatically detect epilepsy. Figure 2 The EEG signal processing method shown in the figure is executed, and the execution of the EEG signal processing method includes the following steps:

[0036] Step S210. Retrieve a plurality of corresponding EEG signals from the target information management module according to the target time period, and integrate the plurality of EEG signals based on a graphical representation to obtain an initial EEG.

[0037] In the embodiment of the present application, the target time period is a collection time set according to the collection cycle and the detection cycle. It is set according to the patient and clinical conditions, and this collection mechanism will not be described in detail in this embodiment.

[0038] The electroencephalogram (EEG) signal is also commonly used in neurology and will not be described in detail in this embodiment.

[0039] Step S220. Segment the multiple EEG signals in the initial EEG based on the first frequency segmentation and the second frequency segmentation to obtain initial frequency EEG signals, and segment the initial frequency EEG signals according to the EEG signal fluctuation threshold, extract and integrate the EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtain an intermediate EEG.

[0040] The first frequency and the second frequency in the embodiment of the present application are low frequency and high frequency according to the frequency distribution, wherein the first frequency is a frequency of 0-80 Hz segment, and the second frequency is a frequency of 80-500 Hz segment. In the concentration, the segmentation of the initial frequency EEG signal is to select the EEG signal in the 0-80 Hz segment from multiple EEG signals as the initial frequency EEG signal.

[0041] The initial frequency EEG signal after segmentation is clinically a low-frequency segmented EEG wave, and the EEG signal is clinically classified into two categories: task state and resting state. In the embodiment of the present application, different EEG wave bands have different effects on the diagnosis of epilepsy, such as high-frequency oscillations are mostly used to locate epileptic foci, and the increase or decrease of each low-frequency band is related to the frequency of seizures, brain network function, etc.; the task state EEG signal refers to the EEG when the brain function is active, thinking or nervous, which can induce abnormal brain waves and increase the positive rate of EEG detection; the resting state EEG is the brain wave collected when the subject closes his eyes and rests; in this embodiment, the low-frequency resting state EEG signal is selected as the intermediate frequency EEG signal. Among them, the screening of low and high frequency EEG signals is carried out through frequency distribution, while the screening for task state and resting state is carried out through EEG signal fluctuation threshold. Specifically, by setting the threshold range corresponding to the EEG signal fluctuations in resting state and task state, that is, the EEG signal fluctuation value corresponding to each band signal in the screened low-frequency EEG signal that meets the EEG signal fluctuation threshold is screened out, and the screened band signals are integrated to obtain the intermediate frequency EEG signal.

[0042] Among them, the screened intermediate frequency EEG signal is the low-frequency resting-state EEG.

[0043] Step S230: Determine the target band based on the patient's age, and extract the EEG signal corresponding to the target band in the intermediate EEG to obtain the target EEG.

[0044] In the embodiment of the present application, the frequency of common brain waves can be divided into five frequency bands according to the frequency range, namely α (8-13Hz), β (14-30Hz), θ (4-7Hz), δ (1-3Hz), and γ (31-80Hz). Among them, α wave is the most important brain wave in the electroencephalogram, and is the basic rhythm of normal human brain waves. It is most obvious when the eyes are closed and quiet, and can be subdivided into fast, medium, and slow. The frequency of slow α wave is 8-9Hz, and slow α wave mainly appears in the stage of blurred consciousness before falling asleep quietly; the frequency of medium α wave is 9-12Hz, which mainly appears when calm and relaxed and focused; the frequency of fast α wave is 12-13Hz, which mainly appears in an alert state. Alpha wave was first discovered and named by Berger. An α wave activity consists of one or several continuous α waves, which is manifested as a regular and rhythmic continuous appearance of α waveform with a roughly constant frequency. Beta waves mainly appear when one is nervous, excited or excited. When awakened by a nightmare, the brain waves will change from slow wave rhythm to beta wave rhythm. Theta waves are "subconscious" waveforms in adults, and are mainly seen in frustrated or depressed states and in patients with mental illness. They mainly appear in adults when they are extremely tired, drowsy or anesthetized. This waveform can also be collected in the temporal and occipital lobes of infants or adults with immature intellectual development. Gamma waves mainly involve higher processing tasks and cognitive learning, and are closely related to human learning, memory and information processing.

[0045] According to the characteristics of the above different bands in the low-frequency EEG waves, the EEG signals of the corresponding sub-segments should be selected for different patients, and in this embodiment, the selection of sub-segmented EEG signals is screened by the age of the patient. Among them, the screening of age is based on the basic information in the basic information management module. The sub-segmented EEG signals corresponding to age are mainly screened in α waves and δ waves. Specifically, the sub-segmented EEG signals corresponding to patients in the younger age group, i.e., the age group of 0-12 years old, are δ waves, and the sub-segmented EEG signals for patients over 12 years old are α waves. In this embodiment of the application, the EEG signals are segmented according to age and clinical manifestations, and the corresponding sub-segmented EEG signals are selected by age as the target EEG signals for epilepsy identification.

[0046] Step S240: extract the power spectrum density of the target EEG in the frequency domain and the multi-scale entropy in the time domain, and process the power spectrum density and the multi-scale entropy based on the classifier to obtain a classification result.

[0047] For epilepsy identification of the target EEG composed of the target EEG signals screened in step S230, it is necessary to extract the feature values ​​corresponding to the EEG signals and classify them based on the feature values. The classification result is the probability of illness, that is, the probability value of illness calculated by the final classifier. When the probability value of illness is greater than the preset standard value, it is determined to be epilepsy, and when it is lower than the preset standard value, it is determined to be non-epilepsy.

[0048] Among them, the features for epilepsy identification of EEG signals include frequency domain and time domain, wherein the feature corresponding to the frequency domain is power spectral density, and the feature corresponding to the time domain is multi-scale entropy.

[0049] Specifically, the acquisition process of the above two features is described in detail. Among them, the power spectral density is calculated by dividing the EEG signal based on the target time window to obtain multiple sub-signals; each sub-signal is subjected to a fast Fourier transform to convert the time domain signal into a frequency domain signal to obtain the power spectral density in each time window, and the power spectral density information in all time windows is averaged to obtain the power spectral density of the EEG signal in the target EEG. For the calculation of multi-scale entropy, first for the EEG signal {X(i), i=1,2,…,N}, different scale factors are selected, and a coarse-grained time series is constructed by averaging the continuously increasing data points in a non-overlapping window with the scale factor as the window length, as shown in the following formula: in, represents the coarse-grained time series, τ represents the scale factor, and the length of each coarse-grained time series is L = int(N / τ). When τ = 1, the time series is the original time series. Construct an m-dimensional vector for: Calculating vectors and The distance between ij : Based on the preset threshold r (r>0), the statistics d ij The total number of ≤r is recorded as p m , where p m is the number of template matches, and its ratio to the total distance is calculated. m : Calculate C m The average For m=m+1, repeat the above steps to calculate C m+1 : Calculate C m+1 The mean At this time, when L is a finite value, the above result is the SampEn value of the sequence length L. Repeat the above steps to obtain the SampEn estimation value at different scales. The multi-scale entropy value of the time series is defined as:

[0050] In an embodiment of the present application, when the classifier is a GBDT classifier, the power spectral density and the multi-scale entropy are obtained through the above processing, and the power spectral density and the multi-scale entropy are input into the GBDT classifier to obtain the final classification result.

[0051] Among them, for the GBDT classifier, which is a classifier that is trained to converge, its structure can adopt the structure in the prior art. The training convergence and classification process is implemented using the existing GBDT classifier structure and will not be repeated in this embodiment.

[0052] With respect to the EEG signal processing method adopted in step S210-step S240, the EEG signal is segmented based on frequency and band to obtain the corresponding target EEG signal, and the target EEG signal is classified and identified by a classifier, and finally a classification result of whether the patient has epilepsy is obtained. This embodiment improves the level of automatic processing, reduces the cost of manual film reading, and improves the accuracy of identification by automatically identifying EEG signals.

[0053] See also Figure 4 Based on step S210-step S230, a virtual device for execution is also provided, which is an EEG signal processing device 400. This device can be configured in any software product to execute the process of step S210-step S230. This device can be a separate plug-in module or a complete computer product. This device includes:

[0054] The initial EEG processing module 410 is used to retrieve a plurality of corresponding EEG signals from the target information management module according to the target time period, and integrate the plurality of EEG signals based on a graph representation to obtain an initial EEG;

[0055] The intermediate EEG processing module 420 is used to segment the multiple EEG signals in the initial EEG based on the first frequency segmentation and the second frequency segmentation to obtain initial frequency EEG signals, and segment the initial frequency EEG signals according to the EEG signal fluctuation threshold, extract and integrate the EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtain the intermediate EEG;

[0056] A target EEG processing module 430 is used to determine a target band based on the patient's age, and extract an EEG signal corresponding to the target band in the intermediate EEG to obtain a target EEG;

[0057] The identification module 440 is used to extract the power spectrum density and the time domain mean of the target electroencephalogram, and process the power spectrum density and the time domain mean based on the classifier to obtain a classification result, and the classification result is a probability value of suffering from epilepsy.

[0058] A method for processing EEG signals provided in an embodiment of the present application collects EEG signals.

[0059] See also Figure 5 , the above method can also be integrated into the provided terminal device 500, and the device may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and memory 502, and the memory 502 may store one or more storage applications or data. Among them, the memory 502 can be a temporary storage or a permanent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the terminal device. Furthermore, the processor 501 can be configured to communicate with the memory 502, and the terminal device executes a series of computer executable instructions in the memory 502. The terminal device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input or output interfaces 505, one or more keyboards 506, etc.

[0060] In a specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the terminal device, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following:

[0061] Retrieving a plurality of corresponding electroencephalogram signals from the target information management module according to a target time period, and integrating the plurality of electroencephalogram signals based on a graph representation to obtain an initial electroencephalogram;

[0062] Segmenting the plurality of EEG signals in the initial EEG based on the first frequency segmentation and the second frequency segmentation to obtain initial frequency EEG signals, segmenting the initial frequency EEG signals according to an EEG signal fluctuation threshold, extracting and integrating EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtaining an intermediate EEG;

[0063] Determine a target band based on the patient's age, and extract an electroencephalogram signal corresponding to the target band in the intermediate electroencephalogram to obtain a target electroencephalogram;

[0064] The power spectrum density in the frequency domain and the multi-scale entropy in the time domain of the target electroencephalogram are extracted, and the power spectrum density and the multi-scale entropy are processed based on a classifier to obtain a classification result.

[0065] The following is a detailed introduction to the various components of the processor:

[0066] In this embodiment, the processor is an application specific integrated circuit (ASIC), or is configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processor, DSP), or one or more field programmable gate arrays (field programmable gate array, FPGA).

[0067] Optionally, the processor may execute various functions by running or executing a software program stored in the memory and calling data stored in the memory, such as executing the above-mentioned Figure 2 The method shown.

[0068] In a specific implementation, as an embodiment, the processor may include one or more microprocessors.

[0069] Among them, the memory is used to store the software program that executes the solution of the present application, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0070] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processing unit through the interface circuit of the processor, and the embodiments of the present application do not specifically limit this.

[0071] It should be noted that the structure of the processor shown in this embodiment does not constitute a limitation on the device, and the actual device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0072] In addition, the technical effects of the processor can refer to the technical effects of the method described in the above method embodiment, which will not be repeated here.

[0073] It should be understood that the processor in the embodiments of the present application may be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0074] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0075] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0076] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0077] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0078] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0083] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0084] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing electroencephalogram signals, characterized in that: The method is applied to a patient management device, which is connected to a data acquisition terminal through a server, and stores patient information about the patient, including a basic information management module and a target information management module; the data acquisition terminal is used to collect the patient's electroencephalogram signal, and the electroencephalogram signal is stored in the target information management module based on a time segmentation method, and the basic information management module stores the patient's basic medical information, which includes but is not limited to one or more information of the patient's age, the patient's gender, and the patient's medical record; The method is applied in the server, and the method includes: Retrieving a plurality of corresponding electroencephalogram signals from the target information management module according to a target time period, and integrating the plurality of electroencephalogram signals based on a graph representation to obtain an initial electroencephalogram; Segmenting the plurality of EEG signals in the initial EEG based on the first frequency segmentation and the second frequency segmentation to obtain initial frequency EEG signals, segmenting the initial frequency EEG signals according to an EEG signal fluctuation threshold, extracting and integrating EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtaining an intermediate EEG; Determine a target band based on the patient's age, and extract an electroencephalogram signal corresponding to the target band in the intermediate electroencephalogram to obtain a target electroencephalogram; The power spectrum density in the frequency domain and the multi-scale entropy in the time domain of the target electroencephalogram are extracted, and the power spectrum density and the multi-scale entropy are processed based on a classifier to obtain a classification result, wherein the classification result is a probability value of having epilepsy.

2. The method for processing electroencephalogram signals according to claim 1, characterized in that: The first frequency segment is 0-80 Hz, and the second frequency segment is 80-500 Hz.

3. The method for processing electroencephalogram signals according to claim 2, characterized in that: The segmenting of the plurality of EEG signals in the EEG based on the first frequency segment and the second frequency segment to obtain the initial frequency EEG signal includes: acquiring the EEG signal corresponding to 0-80 Hz in the plurality of EEG signals as the initial frequency EEG signal.

4. The method for processing electroencephalogram signals according to claim 3, characterized in that: The initial frequency EEG signal is segmented according to the EEG signal fluctuation threshold, including: obtaining the EEG signal fluctuation value corresponding to each band signal in the initial frequency EEG signal, and segmenting each band signal that meets the EEG signal fluctuation threshold.

5. The method for processing electroencephalogram signals according to claim 4, characterized in that: The step of extracting and integrating the EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain the intermediate frequency EEG signals includes: integrating the segmented band signals to obtain the intermediate frequency EEG signals.

6. The method for processing electroencephalogram signals according to claim 5, characterized in that: The method of determining a target band based on the patient's age and extracting an EEG signal corresponding to the target band in the intermediate EEG to obtain a target EEG includes: obtaining the patient's age, querying the age-band correspondence relationship based on the patient's age to obtain the target band, extracting the target band in the intermediate frequency EEG signal, and integrating the target band to obtain the target EEG.

7. The method for processing electroencephalogram signals according to claim 6, characterized in that: The extracting of the power spectral density of the target electroencephalogram frequency domain includes: segmenting the electroencephalogram signal in the target electroencephalogram based on a target time window to obtain a plurality of sub-signals; performing a fast Fourier transform on each sub-signal to convert the time domain signal into a frequency domain signal to obtain the power spectral density in each time window, and averaging the power spectral density information in all time windows to obtain the power spectral density of the electroencephalogram signal in the target electroencephalogram.

8. The method for processing electroencephalogram signals according to claim 1, characterized in that: The classifier is a GBDT classifier.

9. An electroencephalogram signal processing device, characterized in that: The device comprises: An initial EEG processing module, used to retrieve a plurality of corresponding EEG signals from a target information management module according to a target time period, and integrate the plurality of EEG signals based on a graph representation to obtain an initial EEG; An intermediate EEG processing module is used to segment the multiple EEG signals in the initial EEG based on the first frequency segmentation and the second frequency segmentation to obtain initial frequency EEG signals, and segment the initial frequency EEG signals according to the EEG signal fluctuation threshold, extract and integrate the EEG signals in the initial frequency EEG signals corresponding to the EEG signal fluctuation threshold to obtain intermediate frequency EEG signals, and obtain an intermediate EEG; A target EEG processing module, used to determine a target band based on the patient's age, and extract an EEG signal corresponding to the target band in the intermediate EEG to obtain a target EEG; The identification module is used to extract the power spectrum density and the time domain mean of the target electroencephalogram, and process the power spectrum density and the time domain mean based on the classifier to obtain a classification result, wherein the classification result is a probability value of suffering from epilepsy.

10. A terminal device, comprising: A memory and a processor coupled to the memory, wherein the processor is configured to execute the EEG signal processing method according to any one of claims 1 to 8 based on instructions stored in the memory.

Images