Electroencephalogram high-disorder evaluation system, device and storage medium

Abstract

The embodiment of the application discloses a kind of electroencephalogram high dysrhythmia evaluation system, device and storage medium, the system includes processor, the processor is configured to perform the following method: at least two target fragment data are extracted from the EEG signal to be handled;Determine the dynamic functional connectivity matrix corresponding to target fragment data, and the dynamic functional connectivity vector corresponding to dynamic functional connectivity matrix;All dynamic functional connectivity vectors are clustered to obtain at least two functional connectivity state templates, and the time sequence combination is determined by matching the corresponding functional connectivity state template for each dynamic functional connectivity vector;Determine the connection strength level of each functional connectivity state template, and according to the connection strength level of each functional connectivity state template and time sequence combination, determine the evaluation result for representing the high dysrhythmia condition of patient electroencephalogram.The accuracy of the existing brain computer electroencephalogram high dysrhythmia evaluation result is completely dependent on the problem of doctor clinical experience.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of medical signal processing, and in particular to an electroencephalogram high dysrhythmia evaluation system and device and a storage medium. BACKGROUND

[0002] EEG (Electroencephalography) high dysrhythmia is also known as high rhythm disorder or high rhythm disorder, which is manifested as the mixing of spiky waves, sharp waves and multi-spiky waves in the continuous diffuse irregular high-amplitude slow waves. High dysrhythmia is mainly seen in infantile epileptic encephalopathy such as infantile spasms and early myoclonic encephalopathy.

[0003] Infantile spasms is also known as West syndrome, and the interictal EEG shows typical or atypical high dysrhythmia. The EEG clinical evolution process of infantile spasms varies greatly among individuals and is largely dependent on the cause and age of onset. In the EEG of high dysrhythmia, epileptiform discharges are usually more prominent in the posterior head and can persist in wakefulness and sleep, but are often more obvious in sleep and can appear intermittently or completely disappear in wakefulness. The high dysrhythmia in sleep can be intermittent or periodic, and the EEG background immediately after awakening presents a transient "normalization", and then the high dysrhythmia reappears.

[0004] Meta-analysis shows that adrenocorticotropic hormone (ACTH) can relieve seizures in about 76% of children and rapidly normalize EEG in 54% to 89% of children. Long-term follow-up studies have confirmed that about half of the children eventually have near-normal EEG background activity. Early improvement of convulsive seizures and high dysrhythmia helps the children's neurodevelopmental progress, but there is still a lack of sufficient evidence on whether it can improve the long-term prognosis of seizures and intellectual and motor development.

[0005] Although adrenocorticotropic hormone (ACTH) shows strong efficacy in the initial treatment of infantile spasms (IS), nearly half of the patients whose spasms have been suppressed will relapse. The BASED score is an electroencephalogram (EEG) grading scale for infantile spasms. Studies have found that there is a correlation between the BASED score after ACTH treatment and relapse after initial response to ACTH, specifically, the higher the BASED score of electroencephalogram after ACTH treatment, the higher the risk of relapse. However, the BASED score relies on the subjective interpretation of doctors and has limitations in clinical application.

[0006] In summary, the accuracy of existing electroencephalogram high dysrhythmia evaluation results completely depends on the clinical experience of doctors. SUMMARY

[0007] The embodiment of the present application provides a kind of electroencephalogram high dysrhythmia evaluation system, device and storage medium, solve the accuracy of existing electroencephalogram high dysrhythmia evaluation result problem of relying on doctor clinical experience.

[0008] In the first aspect, the embodiment of the present application provides an electroencephalogram high dysrhythmia evaluation system, the system includes processor, the processor is configured to execute the following method:

[0009] At least two target segment data are extracted from the EEG signal to be processed, and the target segment data include epileptiform discharge signals;

[0010] The dynamic functional connectivity matrix corresponding to the target segment data is determined, and the dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix is determined;

[0011] All dynamic functional connectivity vectors are subjected to cluster analysis to obtain at least two functional connectivity state templates, and a time sequence combination reflecting the timing of each functional connectivity state template is determined by matching the corresponding functional connectivity state template for each dynamic functional connectivity vector.

[0012] The connection strength level of each functional connectivity state template is determined, and the evaluation result for indicating the electroencephalogram high dysrhythmia condition of the patient is determined according to the connection strength level of each functional connectivity state template and the time sequence combination.

[0013] In the second aspect, the embodiment of the present application also provides an electroencephalogram high dysrhythmia evaluation device, comprising:

[0014] The data determination module is used for extracting at least two target segment data from the EEG signal to be processed, and the target segment data include epileptiform discharge signals;

[0015] The vector determination module is used for determining the dynamic functional connectivity matrix corresponding to the target segment data, and the dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix;

[0016] The time sequence determination module is used for performing cluster analysis on all dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, and a time sequence combination reflecting the timing of each functional connectivity state template is determined by matching the corresponding functional connectivity state template for each dynamic functional connectivity vector.

[0017] The evaluation module is used for determining the connection strength level of each functional connectivity state template, and the evaluation result for indicating the electroencephalogram high dysrhythmia condition of the patient is determined according to the connection strength level of each functional connectivity state template and the time sequence combination.

[0018] In a third aspect, the embodiments of the present application further provide a storage medium containing computer executable instructions for executing the following method when executed by a computer processor:

[0019] extracting at least two target segment data from the EEG signal to be processed, the target segment data including epileptiform discharge signals;

[0020] determining a dynamic functional connectivity matrix corresponding to the target segment data, and a dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix;

[0021] performing cluster analysis on all the dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, and determining a time sequence combination for reflecting the timing of occurrence of each functional connectivity state template by matching each dynamic functional connectivity vector with a corresponding functional connectivity state template;

[0022] determining a connectivity strength level of each functional connectivity state template, and determining an evaluation result for indicating the high dysrhythmia of the patient's EEG according to the connectivity strength level of each functional connectivity state template and the time sequence combination.

[0023] The technical scheme of the EEG high dysrhythmia evaluation system provided by the embodiments of the present application reflects the synchronization degree of each lead EEG signal in the corresponding target segment data through the connectivity strength level of the functional connectivity state template, and reflects the timing of occurrence of each functional connectivity state template through the time sequence combination. Since the connectivity strength level of the functional connectivity state template is combined with the time sequence combination, the synchronization degree between the EEG signals of each lead at any time can be reflected, and thus the evaluation result for reflecting the high dysrhythmia of the patient's EEG can be accurately determined according to the connectivity strength level of the functional connectivity state template combined with the time sequence combination, without relying on the clinical experience of doctors, and at the same time, strong data support can be provided for the clinical diagnosis of doctors. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a structural block diagram of the EEG high dysrhythmia evaluation system provided by the first embodiment of the present application;

[0026] Figure 2 is a flowchart of the EEG high dysrhythmia evaluation method provided by the first embodiment of the present application;

[0027] Figure 3is a schematic diagram of an original EEG signal provided by the embodiment one of the present application;

[0028] Figure 4 is a schematic diagram of a dynamic functional connectivity matrix provided by the embodiment one of the present application;

[0029] Figure 5 is a schematic diagram of a time series combination of a relapse patient provided by the embodiment one of the present application;

[0030] Figure 6 is a schematic diagram of a time series combination of a non-relapse patient provided by the embodiment one of the present application;

[0031] Figure 7 is a flow chart of the EEG hyperdysrhythmia evaluation method provided by the embodiment two of the present application;

[0032] Figure 8 is a schematic diagram of a time series combination of a relapse patient with a BASED score of 2 provided by the embodiment two of the present application;

[0033] Figure 9 is a verification flow chart of the EEG hyperdysrhythmia evaluation method provided by the embodiment three of the present application;

[0034] Figure 10 is a statistical time series diagram of each functional connectivity state template of the non-relapse group and the relapse group provided by the embodiment three of the present application;

[0035] Figure 11 is a structural block diagram of the EEG hyperdysrhythmia evaluation device provided by the embodiment four of the present application. DETAILED DESCRIPTION

[0036] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely by embodiments with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0037] Embodiment one

[0038] Figure 1This is a structural block diagram of the EEG high arrhythmia assessment system provided in Embodiment 1 of the present invention. The system includes a processor 11, a memory 12, and a computer program stored in the memory 12. When the processor 11 executes the computer program, it performs the following EEG high arrhythmia assessment method. Optionally, the system also includes an input device 13 for inputting control commands and an output device 14 for outputting assessment results. The technical solution of this embodiment is applicable to predicting the risk of relapse after recovery in children with spasticity. This method can be executed by the EEG high arrhythmia assessment device provided in this embodiment of the present invention. This device can be implemented in software and / or hardware and configured in the processor of the EEG high arrhythmia assessment system.

[0039] like Figure 2 As shown, the method specifically includes the following steps:

[0040] S110. Extract at least two target segment data from the EEG signal to be processed, the target segment data including epileptiform discharge signals.

[0041] EEG refers to electroencephalography, also known as brain topography (see [link]). Figure 3 Electroencephalography (EEG) is a commonly used auxiliary examination method in neurology. Specifically, electrodes are attached to the scalp to record brain electrical activity; it is an indirect method of detecting brain electrical activity.

[0042] Epileptiform discharge is a descriptive term in EEG diagnostic results, referring to abnormal waveforms on the EEG that suggest the possible presence of epilepsy. These waveforms may include sharp waves, spikes, sharp-slow-wave complexes, spike-slow-wave complexes, or polyspike-slow-wave complexes. However, the presence of epileptiform discharge does not necessarily mean that the patient has epilepsy. Epileptiform discharge can also occur in normal individuals, with 1.1% to 6.8% of normal individuals exhibiting this phenomenon.

[0043] In one embodiment, a medical EEG acquisition device is used to acquire the patient's EEG signal, with a sampling rate ranging from 200 to 1000 Hz, a channel number ranging from 16 to 32 channels, and a sampling time greater than or equal to two hours. Unnecessary channel information is removed from the original EEG signal to obtain the channel-deleted EEG signal, such as electromyography (EMG) channel signals and bilateral mastoid point channel signals. Figure 3C3 and C4 channels) and the like; a 50 Hz notch filter is used to eliminate power frequency noise interference in the channel-deleted electroencephalogram signal to obtain an electroencephalogram signal after removing power frequency noise; the electroencephalogram signal after removing power frequency noise is subtracted from the reference data to obtain an electroencephalogram signal after re-referencing; the electroencephalogram signal after re-referencing is subjected to high-pass filtering at 0.1 Hz to obtain an electroencephalogram signal after removing base drift; wherein the re-referencing includes a single electrode re-reference, a bipolar re-reference, a Laplacian re-reference, or a global re-reference, and the like. The embodiment preferably uses global re-reference, i.e., the mean value of all data in the whole brain is used as the reference data.

[0044] For the EEG signal of a patient with epilepsy, some time periods contain continuous epileptiform discharges, some time periods contain no epileptiform discharges, and the probability of epileptiform discharges during sleep is greater than that during non-sleep. Therefore, in one embodiment, time segments during sleep are extracted from the patient's EEG signal to obtain a sleep EEG signal, so as to reduce the data operation amount of extracting the EEG signal containing the epileptiform discharge signal.

[0045] In one embodiment, time segments containing preset body motion artifacts are removed from the sleep EEG signal to update the sleep EEG signal, so as to further reduce the data operation amount of extracting the EEG signal containing the epileptiform discharge signal, and improve the data quality of extracting the EEG signal containing the epileptiform discharge signal. The embodiment does not limit the amplitude of the preset body motion artifact, and the actual use can be flexibly set according to the specific situation.

[0046] A time segment containing an epileptiform discharge is extracted from the updated sleep EEG signal to obtain a to-be-processed EEG signal. The time segment is greater than or equal to a preset time threshold.

[0047] At least two target segment data are extracted from the to-be-processed EEG signal. Specifically, the to-be-processed EEG signal is divided into a series of target segments (t0, t0…t L ) by using a sliding time window method. The total number of target segments is (L+1), the time range of the time window length is 0.5-10 seconds, the minimum value of the step length of the sliding time window is 0.5s, and the maximum value is T0.

[0048] S120, determining a dynamic functional connectivity matrix corresponding to the target segment data, and a dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix.

[0049] The phase locking value (PLV) can quantify the degree of synchronization of two EEG signals in a specific frequency band and time region. In this embodiment, the PLV is used to determine the dynamic functional connectivity matrix corresponding to the target segment data. Specifically, the Hilbert transform is performed on the target segment data x(t) using formula (1):

[0050]

[0051] wherein, is the complex number of x(t), is the imaginary part of x(t), is the phase.

[0052] The PLV of two leads is calculated using formula (2), and is normalized so that the value is between 0 and 1, to obtain the dynamic functional connectivity matrix of each target segment, as shown in formula (3). Figure 4 The closer the PLV is to 1, the more synchronized the signals of the two leads are.

[0053]

[0054] wherein, T is the length of the time window.

[0055] As can be seen from formula (4), Figure 4 for each patient's dynamic functional connectivity matrix, it includes the PLV value of any lead and other leads, so the entire dynamic functional connectivity matrix is symmetric along a diagonal line. In other words, for any dynamic functional connectivity matrix, the upper triangular part above the symmetry line (diagonal line) and the lower triangular part below the symmetry line (diagonal line) both contain dynamic functional connectivity information between all leads. Therefore, this embodiment extracts the upper triangular part or the lower triangular part of each dynamic functional connectivity matrix, and then stretches the upper triangular part or the lower triangular part into a vector to obtain the dynamic functional connectivity vector (v0, v1…v L ) corresponding to each target segment data.

[0056] Since the EEG signal is disturbed by the surrounding noise during the collection process, in an embodiment, a band-pass filter is used to filter the target segment data before the Hilbert transform is performed on the target segment data, to update the target segment data, and then the Hilbert transform is performed on the updated target segment data. In this embodiment, the filtering range of the band-pass filter can be selected as 4-40 Hz.

[0057] S130, cluster analysis is performed on all dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, and a time sequence combination reflecting the timing of the occurrence of each functional connectivity state template is determined by matching each dynamic functional connectivity vector to the corresponding functional connectivity state template.

[0058] The preset clustering algorithm is used to perform clustering analysis on all dynamic functional connectivity vectors to obtain K functional connectivity state templates. The clustering analysis can classify the dynamic functional connectivity vectors according to similarity (distance) to make the similarity between the dynamic functional connectivity vectors in the same class stronger than the similarity between the dynamic functional connectivity vectors in other classes. Therefore, different functional connectivity state templates correspond to different functional connectivity states.

[0059] Optionally, the K value is determined according to a silhouette coefficient, for example, a value corresponding to a silhouette coefficient that exceeds a preset coefficient threshold is taken as the K value. The preset clustering algorithm is an existing clustering algorithm, for example, k-means clustering, density clustering, spectral clustering, and the like.

[0060] In one embodiment, since each class corresponds to a functional connectivity state template after clustering analysis, after the K functional connectivity state templates are determined, each dynamic functional connectivity vector is directly matched with the functional connectivity state template corresponding to the class in which the dynamic functional connectivity vector is located, to obtain a time sequence diagram for reflecting arrangement of the functional connectivity state templates along a time axis of the electroencephalogram signal, that is, a time sequence combination of all functional connectivity state templates.

[0061] In one embodiment, after the K functional connectivity state templates are determined, the distance between each dynamic functional connectivity vector and each functional connectivity state template is determined, and each dynamic functional connectivity vector is matched with the functional connectivity state template corresponding to the minimum distance, to obtain the time sequence combination of all functional connectivity state templates. Matching the dynamic functional connectivity vector with the functional connectivity state template according to the minimum distance can improve the accuracy of functional connectivity state template matching and avoid the problem of poor repeatability of clustering analysis.

[0062] Figure 5 The time sequence combination of the patient with electroencephalogram hyperdysrhythmia provided by the embodiment of the present application is provided. The abscissa of the time sequence combination is a time window identifier, the ordinate is a connection strength level of the functional connectivity state template, and the width of the line represents the time span of the corresponding functional connectivity state template.

[0063] S140, determining a connection strength level of each functional connectivity state template, and determining an evaluation result for indicating the electroencephalogram hyperdysrhythmia condition of the patient according to the connection strength level of each functional connectivity state template and the time sequence combination.

[0064] After all the functional connectivity state templates are obtained, the mean of all the functional connectivity state templates is calculated, and all the functional connectivity state templates are sorted in ascending order of the mean. The sorting result can be represented as (State0, State1…State K). From the functional connectivity state template State0 to the functional connectivity state template State K The higher the synchronization of the EEG signals between the leads in the corresponding target segment data is.

[0065] In one embodiment, preset evaluation index data of each functional connectivity state template is determined according to the time series combination, and an evaluation result for indicating the high arrhythmicity of the patient's EEG is determined according to the connection strength level of each functional connectivity state template and the preset evaluation index data. Specifically, the evaluation result for indicating the high arrhythmicity of the patient's EEG is determined according to the preset evaluation index data of the target functional connectivity state template.

[0066] The preset evaluation index includes one or more of the occurrence frequency, the coverage rate and the average duration. The occurrence frequency refers to the number of occurrences of each functional connectivity state template in the time series combination; the coverage rate refers to the ratio of the number of occurrences of each functional connectivity state template in the time series combination to the total number of occurrences of all functional connectivity state templates in the time series combination; and the average duration refers to the continuous occurrence time of each functional connectivity state template.

[0067] The target functional connectivity state template is a functional connectivity state template with a connection strength level exceeding a preset level threshold. For example, there are five functional connectivity state templates in total, and the evaluation result for indicating the high arrhythmicity of the patient's EEG is determined according to the preset evaluation index data of the two functional connectivity state templates with the highest connection strength levels.

[0068] Taking the preset evaluation index as the coverage rate, in one embodiment, when the coverage rate of at least one of the two functional connectivity state templates with the highest connection strength levels is greater than 10%, the evaluation result for indicating the high arrhythmicity of the EEG is output; otherwise, when the coverage rates of the two functional connectivity state templates with the highest connection strength levels are both less than 10%, the evaluation result for indicating no high arrhythmicity of the EEG is output. For example, Figure 6 A time series combination of a non-recurrent patient is provided for the embodiment of the present application. As can be seen from the figure, the coverage rate of the functional connectivity state template with a connection strength level of 4 is less than 10%, and the coverage rate of the functional connectivity state template with a connection strength level of 3 is also less than 10%, so Figure 6 The corresponding evaluation result is no high arrhythmicity of the EEG. This no high arrhythmicity evaluation result is the clinical evaluation result that the non-recurrent patient should have. From Figure 6 It can be obviously seen that the coverage rate of the functional connectivity state template with a connection strength level of 4 is less than 10%, and the coverage rate of the functional connectivity state template with a connection strength level of 3 is greater than 10%, so Figure 6 The corresponding evaluation result is high arrhythmicity of the EEG. The high arrhythmicity of the EEG is the clinical evaluation result that the recurrent patient should have.

[0069] The technical scheme of the electroencephalogram high dysrhythmia evaluation system provided by the embodiment of the present application reflects the synchronization degree of each lead EEG signal in the corresponding target segment data through the connection strength level of the functional connection state template, and reflects the occurrence timing of each functional connection state template through the time sequence combination. Since the connection strength level of the functional connection state template is combined with the time sequence combination, the synchronization degree between the EEG signals of each lead at any moment can be reflected. Therefore, the evaluation result for reflecting the electroencephalogram high dysrhythmia of the patient can be accurately determined according to the connection strength level of the functional connection state template combined with the time sequence combination, without relying on the clinical experience of doctors, and at the same time, strong data support can be provided for the clinical diagnosis of doctors.

[0070] Embodiment two

[0071] Figure 7 is a flowchart of the electroencephalogram high dysrhythmia evaluation method provided by the second embodiment of the present application. The embodiment of the present application adds the step of determining the evaluation result for representing the electroencephalogram high dysrhythmia condition of the patient in combination with the BSAED score on the basis of the above-mentioned embodiment.

[0072] Correspondingly, the method of the embodiment comprises:

[0073] S210, extracting at least two target segment data from the EEG signal to be processed, the target segment data comprising an epileptiform discharge signal.

[0074] S220, determining a dynamic functional connection matrix corresponding to the target segment data, and a dynamic functional connection vector corresponding to the dynamic functional connection matrix.

[0075] S230, performing cluster analysis on all dynamic functional connection vectors to obtain at least two functional connection state templates, and determining a time sequence combination for reflecting the occurrence timing of each functional connection state template by matching each dynamic functional connection vector with the corresponding functional connection state template.

[0076] S240, determining the evaluation result for representing the electroencephalogram high dysrhythmia condition of the patient according to the BASED score and the connection strength level of each functional connection state template and the preset evaluation index data.

[0077] The BASED score is an index for clinically evaluating electroencephalogram high dysrhythmia. Generally, more than or equal to 4 points is defined as electroencephalogram high dysrhythmia, and less than or equal to 3 points is defined as no electroencephalogram high dysrhythmia.

[0078] The preliminary evaluation result of the patient is determined according to the connection strength level of each functional connection state template of the patient and preset evaluation index data. Specifically, the preliminary evaluation result of the patient is determined according to preset evaluation index data of a target functional connection state template. The target functional connection state template is a functional connection state template whose connection strength level exceeds a preset level threshold, such as the two functional connection state templates with the highest connection strength levels.

[0079] If the evaluation result corresponding to the BASED score is consistent with the preliminary evaluation result, the preliminary evaluation result is taken as the evaluation result of the patient; if the evaluation result corresponding to the BASED score is inconsistent with the preliminary evaluation result, prompt information is output to remind the user to re-evaluate the electroencephalogram hyperdysrhythmia of the patient.

[0080] Specifically, if the BASED score result is greater than or equal to 4 points and the preliminary evaluation result is electroencephalogram hyperdysrhythmia, the evaluation result of the patient is electroencephalogram hyperdysrhythmia; if the BASED score result is less than or equal to 3 points and the preliminary evaluation result is no electroencephalogram hyperdysrhythmia, the evaluation result of the patient is no electroencephalogram hyperdysrhythmia; if the BASED score result is greater than or equal to 4 points and the preliminary evaluation result is no electroencephalogram hyperdysrhythmia, re-evaluation prompt is output.

[0081] Exemplarily, the preset evaluation index is coverage. Figure 5 The coverage of the functional connection state template with the connection strength level of 3 is greater than 10%, and therefore the preliminary evaluation result of the patient is electroencephalogram hyperdysrhythmia. The BASED score given by the doctor is 4 points. Since the preliminary evaluation result is consistent with the evaluation result corresponding to the BASED score, the preliminary evaluation result, i.e., electroencephalogram hyperdysrhythmia, is taken as the final evaluation result of the patient.

[0082] Exemplarily, the preset evaluation index is coverage. Figure 8 The coverage of the functional connection state template with the connection strength level of 3 and the functional connection state template with the connection strength level of 4 are both greater than 10%, and therefore the preliminary evaluation result of the patient is electroencephalogram hyperdysrhythmia. The BASED score given by the doctor is 2 points, which corresponds to no electroencephalogram hyperdysrhythmia. Since the preliminary evaluation result is inconsistent with the evaluation result corresponding to the BASED score, re-evaluation prompt is output to remind the doctor to re-evaluate whether the patient has electroencephalogram hyperdysrhythmia.

[0083] The technical scheme provided by the embodiment of the application determines the final evaluation result of the patient according to the evaluation result corresponding to the BASED score and the preliminary evaluation result, which can guarantee the accuracy of the evaluation result on the one hand, and can also verify the accuracy of the evaluation result corresponding to the BASED score through the preliminary evaluation result on the other hand.

[0084] Embodiment three

[0085] Figure 9 FIG. 8 is a flowchart of a verification process of the electroencephalogram high desynchronization evaluation method provided by an embodiment of the present application. The embodiment is used to provide experimental data support for the foregoing embodiments. The total number of samples of the embodiment is 20, including 8 relapse samples and 12 non-relapse samples.

[0086] Correspondingly, the method of the embodiment includes:

[0087] S310, for each patient, extracting at least two target segment data from the to-be-processed EEG signal, the target segment data including an epileptiform discharge signal.

[0088] S320, determining a dynamic functional connectivity matrix corresponding to the target segment data, and a dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix.

[0089] S330, performing clustering analysis on all the dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, and determining a time sequence combination for reflecting the timing of the occurrence of each functional connectivity state template by matching each dynamic functional connectivity vector with a corresponding functional connectivity state template.

[0090] S340, extracting coordinate information of each functional connectivity state template from the time sequence combination, and determining a time sequence of each functional connectivity state template according to the coordinate information of each functional connectivity state template.

[0091] It can be understood that the time sequence of each functional connectivity state template is used to reflect the timing and frequency of occurrence of the corresponding functional connectivity state template.

[0092] S350, when it is detected that the time sequences of all the functional connectivity state templates of all the samples are generated, determining the occurrence rate of each functional connectivity state template in each time in the relapse group to obtain a statistical time sequence of each functional connectivity state template in the relapse group, and determining the occurrence rate of each functional connectivity state template in each time in the non-relapse group to obtain a statistical time sequence of each functional connectivity state template in the non-relapse group.

[0093] For each time, the total number of occurrences of each functional connectivity state template in the relapse group is determined, and the ratio of the total number to the total number of samples in the relapse group is taken as the occurrence rate of the corresponding functional connectivity state template, thereby obtaining the statistical time sequence of each functional connectivity state template in the relapse group; and the total number of occurrences of each functional connectivity state template in the non-relapse group is determined, and the ratio of the total number to the total number of samples in the non-relapse group is taken as the occurrence rate of the corresponding functional connectivity state template, thereby obtaining the statistical time sequence of each functional connectivity state template in the non-relapse group.

[0094] It can be understood that the horizontal coordinate of the statistical time series is the time window, and the vertical coordinate is the incidence, see Figure 10 . Figure 10 State0, State1, State2, State3 and State4 in FIG. 6 are the identifiers of the functional connection state templates, and the numbers in the identifiers represent the functional connection strength levels.

[0095] S360, according to the statistical time series of each functional connection state template in the recurrence group and the statistical time series of each functional connection state template in the non-recurrence group, verifying the evaluation result.

[0096] Figure 10 The first column in FIG. 6 shows the statistical time series of each functional connection state template in the non-recurrence group, Figure 10 The second column in FIG. 6 shows the statistical time series of each functional connection state template in the recurrence group. It can be seen from the figure that the incidence of the third functional connection state template and the fourth functional connection state template in the recurrence group on the entire time axis is significantly higher than that of the third functional connection state template and the fourth functional connection state template in the non-recurrence group on the entire time axis. Specifically, the average incidence of the third functional connection state template and the fourth functional connection state template in the recurrence group on the entire time axis is greater than 10%.

[0097] In summary, the embodiment verifies that according to the combination of the connection strength level and the time series of each functional connection state template, the evaluation result for representing the high disrhythmia of the patient's EEG can be determined. Specifically, the evaluation result for representing the high disrhythmia of the patient's EEG is determined according to the preset evaluation index data of the target functional connection state template. The preset evaluation index can be one or more of the incidence, coverage rate and average duration.

[0098] Embodiment four

[0099] Figure 11 is a structural block diagram of the EEG high disrhythmia evaluation device provided by the embodiment of the application. The device is used to execute the EEG high disrhythmia evaluation method provided by any of the above embodiments, and can be realized by software or hardware. The device comprises:

[0100] The data determination module 41 is configured to extract at least two target segment data from the to-be-processed EEG signal, and the target segment data comprises an epileptiform discharge signal.

[0101] The vector determination module 42 is configured to determine a dynamic functional connection matrix corresponding to the target segment data, and a dynamic functional connection vector corresponding to the dynamic functional connection matrix.

[0102] The time sequence determination module 43 is configured to perform cluster analysis on all dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, and determine a time sequence combination reflecting the time sequence of occurrence of each functional connectivity state template by matching each dynamic functional connectivity vector to a corresponding functional connectivity state template.

[0103] The evaluation module 44 is configured to determine the connectivity strength level of each functional connectivity state template, and determine an evaluation result representing the high arrhythmicity of the patient's EEG according to the connectivity strength level of each functional connectivity state template and the time sequence combination.

[0104] Optionally, the data determination module 41 is further configured to extract a time segment in a sleep stage from the patient's EEG signal to obtain a sleep stage EEG signal, remove a time segment containing a preset body motion artifact from the sleep stage EEG signal to update the sleep stage EEG signal, and extract a time segment containing a preset continuous time threshold of epileptiform discharge from the updated sleep stage EEG signal to obtain the EEG signal to be processed.

[0105] Optionally, the vector determination module 42 is configured to determine a dynamic functional connectivity matrix corresponding to the target segment data based on the phase-locked value.

[0106] Optionally, the time sequence determination module 43 is configured to calculate the distance between each dynamic functional connectivity vector and each functional connectivity state template, and match each dynamic functional connectivity vector to a functional connectivity state template corresponding to the minimum distance to obtain the time sequence combination reflecting the time sequence of occurrence of each functional connectivity state template.

[0107] Optionally, the evaluation module 44 is configured to determine the mean value of the phase-locked value of each functional connectivity state template, sort all mean values, and determine the connectivity strength level of each functional connectivity state according to the sorting result.

[0108] Optionally, the evaluation module 44 is configured to determine a preset evaluation index data of each functional connectivity state template according to the time sequence, the preset evaluation index including one or more of occurrence frequency, coverage rate and average duration, and determine the evaluation result representing the high arrhythmicity of the patient's EEG according to the connectivity strength level of each functional connectivity state template and the preset evaluation index data.

[0109] Optionally, the evaluation module 44 is configured to determine the evaluation result representing the high arrhythmicity of the patient's EEG according to the preset evaluation index data of the target functional connectivity state template, wherein the target functional connectivity state template is a functional connectivity state template whose connectivity strength level exceeds a preset level threshold.

[0110] Optionally, the evaluation module 44 is further configured to acquire a BASED score of the patient; and determine a preliminary evaluation result of the patient according to the connection strength level of each functional connectivity state template and the preset evaluation index data; and determine an evaluation result for indicating the high disorganization of the patient's EEG according to the evaluation result corresponding to the BASED score and the preliminary evaluation result.

[0111] The EEG high disorganization evaluation device provided by the embodiment of the present application reflects the synchronization degree of each lead EEG signal in the corresponding target segment data through the connection strength level of the functional connectivity state template, reflects the occurrence timing of each functional connectivity state template through the time sequence combination, and according to the connection strength level of the functional connectivity state template and the time sequence combination, the synchronization degree of each lead EEG signal at any moment can be determined, so that the evaluation result for reflecting the high disorganization of the patient's EEG can be accurately determined, without relying on the clinical experience of doctors, and at the same time, strong data support can be provided for the clinical diagnosis of doctors.

[0112] The EEG high disorganization evaluation device provided by the embodiment of the present application can execute the EEG high disorganization evaluation method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0113] Embodiment five

[0114] The embodiment of the present application further provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute a storage medium containing computer executable instructions, and the method comprises:

[0115] Extracting at least two target segment data from the to-be-processed EEG signal, the target segment data comprising an epileptiform discharge signal;

[0116] Determining a dynamic functional connectivity matrix corresponding to the target segment data, and a dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix;

[0117] Performing cluster analysis on all dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, determining a time sequence combination for reflecting the occurrence timing of each functional connectivity state template by matching each dynamic functional connectivity vector with a corresponding functional connectivity state template;

[0118] Determining a connection strength level of each functional connectivity state template, and determining an evaluation result for indicating the high disorganization of the patient's EEG according to the connection strength level of each functional connectivity state template and the time sequence combination.

[0119] Of course, the storage medium provided by the embodiment of the present application includes computer executable instructions, and the computer executable instructions are not limited to the method operations described above, but can also perform related operations in the electroencephalogram high disrhythmia evaluation method provided by any embodiment of the present application.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk or an optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the electroencephalogram high disrhythmia evaluation method described in various embodiments of the present application.

[0121] It is worth noting that in the above embodiment of the electroencephalogram high disrhythmia evaluation device, each unit and module included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding function can be realized; in addition, the specific name of each functional unit is only for easy mutual distinction, and does not limit the protection scope of the present application.

[0122] Note that the above is only the preferred embodiment of the present application and the technical principle applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. An electroencephalographic hyperdysrhythmia assessment system, comprising: comprises a processor configured to perform the following method: extracting at least two target segment data from the EEG signal to be processed, the target segment data comprising epileptiform discharge signals; determining a dynamic functional connectivity matrix corresponding to the target segment data, and a dynamic functional connectivity vector corresponding to the dynamic functional connectivity matrix; performing cluster analysis on all dynamic functional connectivity vectors to obtain at least two functional connectivity state templates, determining a time series combination reflecting the timing of the occurrence of each functional connectivity state template by matching each dynamic functional connectivity vector to a corresponding functional connectivity state template, the horizontal coordinate of the time series combination being a time window identifier, the vertical coordinate being a connection strength level of the functional connectivity state template, and the time span of the corresponding functional connectivity state template being represented by the width of the line; determining the connection strength level of each functional connectivity state template, and determining an evaluation result for indicating the high dysrhythmia condition of the patient's EEG according to the connection strength level of each functional connectivity state template and the time series combination; wherein the determination of the evaluation result for indicating the high dysrhythmia condition of the patient's EEG according to the connection strength level of each functional connectivity state template and the time series combination comprises: determining the evaluation result for indicating the high dysrhythmia condition of the patient's EEG according to the preset evaluation index data of the target functional connectivity state template, wherein the target functional connectivity state template is a functional connectivity state template whose connection strength level exceeds a preset level threshold, and the preset evaluation index comprises one or more of occurrence frequency, coverage rate and average duration.

2. The system of claim 1, wherein, Before the extraction of the at least two target segment data from the EEG signal to be processed, the method further comprises: extracting a time segment in a sleep period from the patient's EEG signal to obtain a sleep period EEG signal; removing a time segment containing a preset body motion artifact from the sleep period EEG signal to update the sleep period EEG signal; extracting a time segment containing epileptiform discharges of a preset continuous time threshold from the updated sleep period EEG signal to obtain the EEG signal to be processed.

3. The system of claim 1, wherein, The determination of the dynamic functional connectivity matrix corresponding to the target segment data comprises: determining the dynamic functional connectivity matrix corresponding to the target segment data based on the phase-locked value.

4. The system of claim 1, wherein, The determination of the time series combination reflecting the timing of the occurrence of each functional connectivity state template by matching each dynamic functional connectivity vector to a corresponding functional connectivity state template comprises: calculating the distance between each dynamic functional connectivity vector and each functional connectivity state template; matching each dynamic functional connectivity vector to the functional connectivity state template corresponding to the minimum distance to obtain the time series combination reflecting the timing of the occurrence of each functional connectivity state template.

5. The system of claim 1, wherein, The determination of the connection strength level of each functional connectivity state template comprises: determining the mean value of the phase-locked value of each functional connectivity state template; sorting all mean values and determining the connection strength level of each functional connectivity state according to the sorting result.

6. The system of any of claims 1-5, wherein, The method further comprises: obtaining the BASED score of the patient; The evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time sequence combination, and the evaluation result for indicating the high dysrhythmia condition of the patient's EEG is determined according to the connection strength level of each functional connection state template and the time ​ ​ 7. An electroencephalogram high desynchronization evaluation device characterized by comprising: ​ ​ ​ ​ ​ ​ ​ 8. A storage medium containing computer-executable instructions, wherein: ​ ​ ​ ​ determine a connection strength level of each functional connection state template, and determine an evaluation result for representing the high dysrhythmia condition of the patient's brain electricity according to the combination of the connection strength level of each functional connection state template and the time sequence; The method comprises the following steps: According to the preset evaluation index data of the target functional connection state template, the evaluation result for representing the high dysrhythmia condition of the patient's brain electricity is determined, wherein the target functional connection state template is a functional connection state template with a connection strength level exceeding a preset level threshold, and the preset evaluation index includes one or more of the occurrence frequency, the coverage rate and the average duration.

Images