Ripple signal detection and identification system based on IED events and time-frequency characteristics

Abstract

The invention provides a ripple signal detection and identification system based on an IED event and time-frequency characteristics, and the system comprises a signal obtaining module which obtains electroencephalogram data of a target object, a preprocessing module which carries out the preprocessing of each channel signal of the electroencephalogram data, the preprocessing comprises power frequency notch and band-pass filtering, the signal is a first frequency band signal at a 25-80Hz frequency band, and the signal is a second frequency band signal at a 70-180Hz frequency band; the IED detection module performs IED signal detection on the first frequency band signal to determine an IED event node; a ripple detection module carries out sliding window analysis on the second frequency band signal, carries out ripple signal detection and determines a ripple event node; and the decision identification module determines the ripple signal category based on the IED event node and the ripple event node. By detecting an IED event and a ripple event, the IED event is introduced into ripple event classification, and automatic detection and identification of physiological ripples and pathological signals are realized in combination with frequency domain features.

Description

Technical Field

[0001] This application relates to the field of electroencephalogram (EEG) signal research technology, and more specifically, to a ripple wave signal detection and recognition system based on IED events and time-frequency characteristics. Background Technology

[0002] In the field of electroencephalography (EEG) neuroscience, ripples and IEDs (Interictal Epileptiform Discharges) are core pathological signals. Ripples are defined as high-frequency oscillations specifically between 80-200 Hz, primarily originating from the hippocampus and temporal cortex. Physiological ripples are defined as those occurring during slow-wave sleep, driving information encoding and storage during memory consolidation; pathological signals are highly correlated with epileptic seizures, and their abnormal enhancement can activate epileptogenic networks, making them key biomarkers for locating epileptogenic foci. Ripple detection requires intracranial electrodes (such as deep brain electrodes or ECoG) and a sampling rate of over 2000 Hz.

[0003] Interictal epileptic discharges (IEDs) refer to characteristic transient EEG waveforms that appear between seizures in epileptic patients. Typical morphologies include spikes (20-70 ms high-amplitude sharp waves), sharp waves, and spike-and-slow-wave complexes (spikes followed by 200-500 ms slow waves). Although these discharges do not directly trigger overt seizures, they reflect abnormal cortical hypersynchronization and are the gold standard for epilepsy diagnosis—their spatial distribution can indicate the location of epileptogenic zone resection surgery, and frequency changes can assess the efficacy of antiepileptic drugs. In clinical practice, scalp EEG has a sensitivity of approximately 30% for superficial IEDs, while precise capture of deep lesions requires stereotactic electroencephalography (SEEG).

[0004] Pathological signals often co-occur with IED events: high-frequency oscillations can attach to the spike components of IED. This coupling phenomenon indicates an increase in the oversynchronization of neuronal clusters and has a sensitivity of up to 90% in predicting epileptic seizures.

[0005] Our previous research (Hippocampal ripples correlate with memory performance in humans, Qing-Tian Duan, Lu Dai, Lu-Kang Wang, Xian-Jun Shi, Xiaowei Chen, Xiang Liao, Chun-Qing Zhang, Hui Yang) showed that in the hippocampal region (CA1-CA4, Subiculum, Presubiculum, DG, where CA1-CA4 represent the angular hippocampus 1-4, Subiculum represents the subventral region, Presubiculum represents the anterior subventral region, and DG represents the dentate gyrus), ripple waves are mainly concentrated in the 70-180Hz range. Physiological ripple waves have a positive effect on memory, while pathological signals and IED events have a negative effect on memory, both showing significant correlations.

[0006] Therefore, developing a signal detection system that can automatically identify physiological ripple waves and pathological signals can provide a powerful aid for the research and assessment of memory disorders. Thus, our team has developed a ripple wave signal detection and recognition system based on IED events and time-frequency characteristics. Summary of the Invention

[0007] The purpose of this application is to provide a ripple wave signal detection and recognition system based on IED events and time-frequency characteristics. By detecting IED events and ripple wave events, IED events are introduced into the ripple wave event classification. At the same time, combined with frequency domain characteristics, the system can automatically detect and recognize physiological ripple waves and pathological signals.

[0008] To achieve the above objectives, the embodiments of this application are implemented in the following manner: In a first aspect, embodiments of this application provide a ripple wave signal detection and recognition system based on IED events and time-frequency characteristics, comprising: a signal acquisition module for acquiring EEG data of a target object, wherein the EEG data includes at least channel signals of each hippocampal subregion, the hippocampal subregions including CA1-CA4, Subiculum, Presubiculum, and DG, CA1-CA4 representing hippocampal horn regions 1-4, Subiculum representing the subventral region, Presubiculum representing the anterior subventral region, and DG representing the dentate gyrus; and a preprocessing module for preprocessing the channel signals of the EEG data, wherein the preprocessing includes power frequency notch filtering and bandpass filtering, the power frequency notch filtering removing 50% of the signal. For power frequency interference, bandpass filtering preserves the 25-80Hz and 70-180Hz frequency bands respectively. The 25-80Hz band is the first frequency band signal, and the 70-180Hz band is the second frequency band signal. An IED detection module is used to detect IED signals in the first frequency band signal and determine IED event nodes, where IED represents interictal epileptiform discharge. A ripple wave detection module is used to perform sliding window analysis on the second frequency band signal to detect ripple wave signals and determine ripple wave event nodes. A decision recognition module is used to determine the ripple wave signal category based on the IED event nodes and ripple wave event nodes, where the ripple wave signal category includes physiological ripple waves and pathological signals.

[0009] In conjunction with the first aspect, in the first possible implementation of the first aspect, the IED detection module is specifically used for: for the first frequency band signal of each channel: performing global analysis on the first frequency band signal of the current channel to calculate the baseline voltage of the current channel; using the baseline voltage as a reference, performing peak detection on the first frequency band signal of the current channel and determining candidate nodes that meet the peak condition, wherein the peak condition is: higher than the sum of the baseline voltage and 3 times MAD, where MAD represents the median absolute deviation; for each candidate node, using the candidate node as a reference, determining a 200ms interval forward and a 400ms interval backward to obtain a 600ms time window corresponding to the candidate node, and then performing spike morphology verification, slow wave oscillation verification, and background suppression verification on the signal within the time window, and determining the marked candidate nodes that meet the requirements based on the verification results of spike morphology verification, slow wave oscillation verification, and background suppression verification, and determining the IED event start point and IED event end point based on the marked candidate nodes.

[0010] In conjunction with the first possible implementation of the first aspect, in the second possible implementation of the first aspect, the IED detection module is specifically used for: determining the first valley point after the peak point within the time window based on the peak point corresponding to the candidate node, determining the first 40% valley amplitude point before and after the valley point, calculating the spike morphology symmetry index, and determining the spike morphology verification result; determining the first valley point after the peak point within the time window based on the peak point corresponding to the candidate node, then determining the two valley points after the first valley point, and determining the oscillation attenuation verification result based on the value of each valley point; determining the peak point before the peak point within the time window based on the peak point corresponding to the candidate node, and using the previous peak point as the endpoint, determining the background suppression verification region within the time window, and determining the background suppression verification result.

[0011] In conjunction with the first aspect, in the third possible implementation of the first aspect, the ripple wave detection module is specifically used for: for the second frequency band signal of each channel: performing global analysis on the second frequency band signal of the current channel to calculate the baseline voltage of the current channel; performing sliding window processing on the second frequency band signal of the current channel to obtain several window data, wherein the sliding window size is 100ms and the step size is 20ms; for each window data: performing feature extraction on the window data to determine several feature indices, and judging based on the feature indices to determine candidate ripple wave events, and then determining the start node and end node of each candidate ripple wave event to obtain several ripple wave event nodes.

[0012] In conjunction with the third possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the ripple wave detection module is specifically used for: calculating the energy envelope of the window data to obtain the window energy envelope; counting the number of peaks in the window data; determining whether there are three or more consecutive window data whose window energy envelopes are greater than the sum of the baseline voltage of the front channel and four times the MAD, and the number of peaks in each window data is not less than eight. If so, the consecutive window data are merged as a candidate ripple wave event, where MAD represents the median absolute deviation.

[0013] In conjunction with the fourth possible implementation of the first aspect, in the fifth possible implementation of the first aspect, the ripple wave detection module is specifically used to: calculate the window energy envelope in the following manner: , in, The window energy envelope of the window data. The number of sampling points for the window data. For the first data in the window The sampled voltage values ​​of each data point.

[0014] In conjunction with the fourth possible implementation of the first aspect, in the sixth possible implementation of the first aspect, the ripple wave detection module is specifically used for: for each candidate ripple wave event: determining the time node from the first window data of the candidate ripple wave event when the voltage amplitude first exceeds the sum of the baseline voltage and twice the MAD, as the starting node of the candidate ripple wave event; and determining the time node from the last window data of the candidate ripple wave event when the voltage amplitude last exceeds the sum of the baseline voltage and twice the MAD, as the ending node of the candidate ripple wave event.

[0015] In conjunction with the second possible implementation of the first aspect, in the seventh possible implementation of the first aspect, the decision identification module is specifically used for: For each channel: performing event node matching based on IED event nodes and ripple wave event nodes, determining that ripple wave event nodes whose starting node is located within a target time window are pathological signals, where the target time window represents a 50ms time window starting from the peak point corresponding to the IED event node; For ripple wave event nodes in each channel that are not determined to be pathological signals: performing rapid spectrum analysis and energy concentration analysis on the merged window data where the ripple wave event nodes are located, determining the spectral peak frequency and energy concentration, and then determining whether the ripple wave event nodes are pathological signals based on the spectral peak frequency and energy concentration.

[0016] In conjunction with the seventh possible implementation of the first aspect, in the eighth possible implementation of the first aspect, the decision identification module is specifically used for: performing rapid spectral analysis on the merged window data where the ripple wave event nodes are located, and calculating the spectral peak frequencies. , in, To merge the spectral peak frequencies of the window data, For frequency, Fourier transform of the merged window data; energy concentration analysis of the merged window data containing the ripple wave event nodes, and calculation of energy concentration: , in, To optimize the energy concentration of merged window data, for ~ Energy integral of frequency band, The energy integral is the energy across the entire frequency band from 70 to 180 Hz.

[0017] In conjunction with the seventh possible implementation of the first aspect, in the ninth possible implementation of the first aspect, the decision identification module is specifically used for: if the spectral peak frequency of the merged window data where the ripple wave event node is located is not lower than 140Hz and the energy concentration is not lower than 0.35, determining that the ripple wave event node is a pathological signal; if the spectral peak frequency of the merged window data where the ripple wave event node is located does not exceed 120Hz and the energy concentration does not exceed 0.2, determining that the ripple wave event node is a physiological ripple wave; if the spectral peak frequency of the merged window data where the ripple wave event node is located is within (120, 140) and the energy concentration is within (0.2, 0.35), calculating the probability that the ripple wave event node belongs to a pathological signal based on the spectral peak frequency and energy concentration, and determining whether the ripple wave event node is a pathological signal.

[0018] Beneficial effects:

[0019] This solution provides a ripple wave signal detection and recognition system based on IED events and time-frequency characteristics. The system acquires EEG data (including channel signals from various hippocampal subregions, including CA1-CA4, Subiculum, Presubiculum, and DG) from the target subject through a signal acquisition module. A preprocessing module performs power frequency notch filtering and bandpass filtering on the EEG data for each channel. The power frequency notch removes 50Hz power frequency interference, while the bandpass filtering retains the first frequency band signal (25-80Hz) and the second frequency band signal (70-180Hz). An IED detection module detects IED signals in the first frequency band signal to identify IED event nodes. A ripple wave detection module performs sliding window analysis on the second frequency band signal to detect ripple wave signals and identify ripple wave event nodes. Finally, a decision recognition module determines the ripple wave signal type (physiological or pathological) based on the IED event nodes and ripple wave event nodes. This system establishes a spatiotemporal coupling detection foundation through the hippocampal sub-regional acquisition module and the dual-band separation (25-80Hz and 70-180Hz) of the preprocessing module. Using IED events as spatiotemporal anchors for pathological signals (specifically constructing target time windows as the judgment criterion), it assists in the identification and classification of pathological signals. Simultaneously, for non-IED coupled ripple wave events, it analyzes the essential differences in spectral performance between physiological ripple waves and pathological signals, designing a dual-index discrimination based on spectral peak frequency and energy concentration to fundamentally distinguish between pathological signals and physiological ripple waves. This enables effective identification of independently occurring pathological signals, improves the accuracy of ripple wave classification, and reduces the probability of misclassification.

[0020] In the identification of IED events, the waveform morphology at the time of IED occurrence is analyzed to design an IED event detection mechanism. Multiple discrimination criteria are used (based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, determining the first 40% trough amplitude point before and after the trough point, calculating the spike morphology symmetry index, and determining the spike morphology verification result; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, then determining the two trough points after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, then determining the two trough points after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, and then determining the first trough point after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, and then determining the first trough point after the first trough point, and determining the first trough amplitude ... The superposition of the peak point preceding the peak point, and using the preceding peak point as the endpoint, determines the background suppression verification region within the time window, and determines the background suppression verification result. This can effectively address the typical forms of various IED events (including spikes, sharp waves, spike-slow-wave complexes, etc.), improving the accuracy of IED event identification. At the same time, based on the coupling window characteristics of pathological signals and IED events in previous research results, the IED event node is determined as the coupling standard for pathological signals (a 50ms time window starting from the peak point corresponding to the IED event node), improving the accuracy of identifying pathological signals coupled with IED events.

[0021] 3. During ripple wave detection, a global analysis is performed on the second frequency band signal to calculate the baseline voltage. Then, a sliding window process is applied (the sliding window size is 100ms, with a step size of 20ms, which takes into account the short-term characteristics of physiological ripple waves, improving the accuracy of ripple wave event detection and reducing the false negative rate), resulting in several window data points. For each window data point: the energy envelope is calculated; the number of peaks in the window data is counted; it is determined whether there are three or more consecutive window data points whose window energy envelopes are greater than the sum of the baseline voltage of the previous channel and four times the MAD (median absolute deviation), and the number of peaks in each window data point is not less than eight. If so, the consecutive window data points are merged as a single candidate ripple wave event. Furthermore, from the first window of data for candidate ripple wave events, the time point at which the voltage amplitude first exceeds the sum of the baseline voltage and twice the MAD is determined as the starting point of the candidate ripple wave event; from the last window of data for candidate ripple wave events, the time point at which the voltage amplitude last exceeds the sum of the baseline voltage and twice the MAD is determined as the ending point of the candidate ripple wave event. This method can not only effectively detect ripple wave events, but also relatively accurately define the starting range of ripple wave events, thereby improving the accuracy of discrimination and reducing the probability of false positives (i.e., physiological ripple waves being misidentified as pathological signals) in the subsequent IED event coupling discrimination process.

[0022] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the framework of the ripple wave signal detection and recognition system based on IED events and time-frequency characteristics provided in the embodiments of this application.

[0025] Figure 2 This is a signal diagram for the first frequency band, 25-80Hz.

[0026] Figure 3 This is a signal diagram for the second frequency band, 70-180Hz.

[0027] Icons: 10-Ripple wave signal detection and recognition system based on IED event and time-frequency characteristics; 11-Signal acquisition module; 12-Preprocessing module; 13-IED detection module; 14-Ripple wave detection module; 15-Decision recognition module. Detailed Implementation

[0028] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0029] like Figure 1 As shown, Figure 1 A schematic diagram of the framework of the ripple wave signal detection and recognition system 10 based on IED events and time-frequency characteristics provided in the embodiments of this application.

[0030] In this embodiment, the ripple wave signal detection and recognition system 10 based on IED events and time-frequency characteristics may include a signal acquisition module 11, a preprocessing module 12, an IED detection module 13, a ripple wave detection module 14, and a decision recognition module 15.

[0031] Since this scheme mainly studies various hippocampal subregions (hippocampal subregions include CA1-CA4, Subiculum, Presubiculum, and DG; CA1-CA4 represent hippocampal angles 1-4, Subiculum represents the inferior horn, Presubiculum represents the anterior inferior horn, and DG represents the dentate gyrus), a sampling rate of at least 2000Hz is required. Scalp EEG sampling frequencies are generally 500-2000Hz, intracranial EEG sampling frequencies are generally 2000-5000Hz, and stereotactic EEG is generally 2000-10000Hz, all of which meet the requirements. However, due to differences in acquisition methods, the signal strength of the acquired EEG data for hippocampal subregion localization varies among scalp EEG, intracranial EEG, and stereotactic EEG. The difficulty (or accuracy) of hippocampal subregion localization is scalp EEG > intracranial EEG > stereotactic EEG, while the signal strength is scalp EEG < intracranial EEG < stereotactic EEG. However, scalp EEG does not require intervention in the brain, intracranial EEG requires placing an electrode array directly on the surface of the cerebral cortex, while stereotactic EEG requires vertically implanting deep electrodes into the brain parenchyma using stereotactic techniques. Therefore, in terms of ease of implementation, scalp EEG > intracranial EEG > stereotactic EEG. This embodiment does not limit the specific type of EEG data used; it uses 2000Hz stereotactic EEG as an example for illustration.

[0032] In this embodiment, the signal acquisition module 11 can acquire the EEG data of the target object. The EEG data includes at least the channel signals of each hippocampal subregion (each hippocampal subregion may include channel signals acquired by more than one electrode). The hippocampal subregions include CA1-CA4, Subiculum, Presubiculum, and DG. CA1-CA4 represent hippocampal angles 1-4, Subiculum represents the subluxation, Presubiculum represents the anterior subluxation, and DG represents the dentate gyrus.

[0033] After obtaining the EEG data of the target subject, the preprocessing module 12 can preprocess the signals of each channel of the EEG data. Specifically, the preprocessing may include power frequency notch filtering and bandpass filtering. Power frequency notch filtering removes 50Hz power frequency interference, and bandpass filtering retains the 25-80Hz and 70-180Hz frequency bands respectively. The 25-80Hz frequency band is denoted as the first frequency band signal, and the 70-180Hz frequency band is denoted as the second frequency band signal, such as... Figure 2 and Figure 3 As shown, where, Figure 2 and Figure 3 The horizontal axis represents time (in seconds), and the vertical axis represents voltage (in microvolts).

[0034] After preprocessing the signal of each channel, the first frequency band signal and the second frequency band signal corresponding to each channel can be obtained.

[0035] Accordingly, the IED detection module 13 can perform IED signal detection on the first frequency band signal to determine the IED event node, where IED represents interictal epileptiform discharge.

[0036] In this embodiment, for the first frequency band signal of each channel: the IED detection module 13 can perform a global analysis of the first frequency band signal of the current channel and calculate the baseline voltage of the current channel.

[0037] For example, the IED detection module 13 can use a Hampel filter to remove transient artifacts from the first frequency band signal (window width set to 500ms, threshold set to 3 times the local standard deviation), and then calculate the median as the baseline voltage, thereby eliminating sampling points with abnormal local amplitudes (such as interference from spikes and peaks in IED events). Alternatively, the first frequency band signal after removing transient artifacts can be divided into several segments (e.g., ten segments), the median of each segment can be calculated, and then the mean of the medians of each segment can be used as the baseline voltage; this is not limited here. After determining the baseline voltage, the median absolute deviation (MAD) also needs to be calculated. (1) in, These are Gaussian distribution correction coefficients. This indicates taking the median. The first frequency band signal Voltage values ​​at each sampling point This represents the baseline voltage.

[0038] Subsequently, the IED detection module 13 can perform peak detection on the first frequency band signal of the current channel based on the baseline voltage, and determine candidate nodes that meet the peak condition. The peak condition is that the voltage value at the peak point is higher than the sum of the baseline voltage and three times the median absolute deviation (MAD). This scheme analyzes the characteristics of IED events in stereoscopic EEG data to determine the detection peak as an indicator and identifies sampling points that meet the peak condition as candidate nodes. Although this embodiment does not select the valley point of the spike wave, it could be selected. However, the determination of the subsequent target time window (the time window for determining whether the ripple wave event is coupled with the IED event) would require adjusting the window size accordingly, which needs to be controlled to around 30ms.

[0039] For each candidate node, the IED detection module 13 can use the candidate node as a reference to determine a 200ms interval forward and a 400ms interval backward, thus obtaining a 600ms time window corresponding to the candidate node. Then, the signal within the time window is verified for spike morphology, slow wave oscillation, and background suppression.

[0040] For example, based on the peak point corresponding to the candidate node, the first valley point after the peak point is determined within the time window (in most cases, this valley point is the spike valley point of the IED event), and then the first 40% valley amplitude point before and after the valley point is determined, the spike morphology symmetry index is calculated, and the spike morphology verification result is determined.

[0041] Specifically, the first 40% trough amplitude points before and after the trough point can be determined separately. The first 40% trough amplitude point before the trough point is the point where, based on the baseline voltage, the value decreases to 40% of the amplitude difference between the baseline voltage and the trough point. The first 40% trough amplitude point after the trough point is the point where the voltage rises 60% from the trough point back to the baseline voltage (i.e., the potential difference between the trough point and the baseline voltage is 60% of the potential difference between the trough point and the baseline voltage). Then, the time points of the first 40% trough amplitude point before the trough point, the trough point itself, and the first 40% trough amplitude point after the trough point are determined, and the spike pattern symmetry index is calculated using the following formula: (2) in, The symmetry index of the spike wave pattern. The time point of the valley point, This refers to the time point before the first 40% trough amplitude point. This is the time point of the first 40% trough amplitude after the trough point.

[0042] like If the spike pattern verification is successful, then the spike pattern verification is successful; otherwise, the spike pattern verification is unsuccessful.

[0043] For example, the IED detection module 13 can determine the first valley point after the peak point within the time window based on the peak point corresponding to the candidate node, and then determine the two valley points after the first valley point, and determine the oscillation decay verification result based on the value of each valley point.

[0044] Specifically, the IED detection module 13 can determine the first valley point after the peak point within the time window (in most cases, this valley point is the spike valley point of the IED event), and then determine two more valley points. It then judges whether the voltage value of the subsequent valley point is greater than the voltage value of the preceding valley point (i.e., the voltage value of the first valley point after the peak point, the voltage value of the first valley point after the first valley point after the peak point, and the voltage value of the second valley point after the first valley point after the peak point). If this condition is met, the oscillation attenuation verification can be determined to be passed; otherwise, the oscillation attenuation verification fails.

[0045] For example, the IED detection module 13 can determine the previous peak point within the time window based on the peak point corresponding to the candidate node, and use the previous peak point as the endpoint to determine the background suppression verification region within the time window (with the start of the time window as the start of the background suppression verification region and the previous peak point corresponding to the candidate node as the endpoint of the background suppression verification region), and then determine whether there are sampling points within the background suppression verification region that meet the following conditions: (3) in, Represents any sampling point in the background suppression verification region. voltage value, Baseline voltage, This represents the voltage value of the peak point preceding the peak point corresponding to the candidate node.

[0046] If there are no sampling points within the background suppression verification area that meet the condition (Formula (3)), the background suppression verification is deemed successful. Otherwise, the background suppression verification is deemed unsuccessful.

[0047] After completing spike morphology verification, slow wave oscillation verification, and background suppression verification, the IED detection module 13 can determine the candidate nodes that meet the requirements based on the verification results (whether the verification is passed). In this embodiment, if any two of the spike morphology verification, slow wave oscillation verification, and background suppression verification are passed, the candidate node can be determined as a candidate node for labeling (because the typical waveform of an IED event generally meets 2-3 conditions, while atypical waveforms that are more difficult to detect, such as multi-spiked slow wave clusters, generally also meet two conditions, thereby realizing the detection of IED events).

[0048] After identifying the candidate nodes, the start and end points of the IED event need to be determined. The IED detection module 13 can use the peak point corresponding to the candidate node to determine the first sampling point reaching the baseline voltage, which serves as the start point of the IED event. Furthermore, the IED detection module 13 can use the second valley point after the first valley point following the peak point corresponding to the candidate node as the starting point, and search backwards within a 200ms interval for the first consecutive 80ms interval where the voltage value is continuously less than the sum of the baseline voltage and twice the MAD. If such an interval exists, the start point of the target interval is taken as the end point of the IED event; otherwise, the end point is the position 80ms prior to the end point of the time window containing the candidate node.

[0049] After determining the IED event start and end points corresponding to each candidate node, integration can be performed. This involves integrating IED events where there is overlap between the IED event start and end points. This allows multiple IED events that actually belong to the same multi-spiky slow wave cluster but are identified as different IED events to be integrated into a single IED event node, improving the accuracy of IED event detection. Based on this, the IED detection module 13 can determine all IED event nodes corresponding to the first frequency band signal of each channel.

[0050] At the same time, the ripple wave detection module 14 can perform sliding window analysis on the second frequency band signal to detect ripple wave signals and determine the ripple wave event nodes.

[0051] In this embodiment, for the second frequency band signal of each channel: the ripple wave detection module 14 can perform a global analysis of the second frequency band signal of the current channel and calculate the baseline voltage of the current channel. The calculation of the baseline voltage and the MAD can be found in the previous description of the relevant processing process of the first frequency band signal, and will not be repeated here.

[0052] Subsequently, the ripple wave detection module 14 can perform sliding window processing on the second frequency band signal of the current channel to obtain several window data, wherein the sliding window size is 100ms and the step size is 20ms. The sliding window size of 100ms and the step size of 20ms here are mainly designed to take into account the short time course characteristics of physiological ripple waves.

[0053] For each window of data: the ripple wave detection module 14 can extract features from the window data and determine several feature indices.

[0054] For example, the ripple wave detection module 14 can perform energy envelope calculation on the window data to obtain the window energy envelope.

[0055] Specifically, the window energy envelope is calculated using the following method: (4) in, The window energy envelope of the window data. The number of sampling points for the window data. For the first data in the window The sampled voltage values ​​of each data point.

[0056] Additionally, the ripple wave detection module 14 can count the number of peaks in the window data to obtain the number of peaks in each window data.

[0057] Then, the ripple wave detection module 14 can determine whether there are three or more consecutive window energy envelopes that are greater than the sum of the baseline voltage of the front channel and four times the MAD, and the number of peaks in each window data is not less than eight.

[0058] If at least three consecutive windows of data exist, the consecutive windows are merged into a single candidate ripple event. Based on this, the ripple detection module 14 can further determine the start and end nodes of each candidate ripple event.

[0059] For example, for each candidate ripple wave event: the ripple wave detection module 14 can determine the time node from the first window data of the candidate ripple wave event when the voltage amplitude first exceeds the sum of the baseline voltage and twice the MAD, as the starting node of the candidate ripple wave event; and determine the time node from the last window data of the candidate ripple wave event when the voltage amplitude last exceeds the sum of the baseline voltage and twice the MAD, as the ending node of the candidate ripple wave event.

[0060] In this way, the ripple wave detection module 14 can obtain several ripple wave event nodes with determined start and end nodes. By processing the second frequency band signal of each channel in this manner, the ripple wave event nodes in the second frequency band signal of each channel can be obtained.

[0061] The decision recognition module 15 needs to determine the ripple wave signal category based on the IED event node and the ripple wave event node. The ripple wave signal category includes physiological ripple waves and pathological signals.

[0062] In this embodiment, the decision recognition module 15 can use a multi-level discrimination method to distinguish between physiological ripple waves and pathological signals.

[0063] First, for each channel: the decision recognition module 15 can perform event node matching based on the IED event node and the ripple wave event node, and determine that the ripple wave event node whose starting node is located within the target time window is a pathological signal. The target time window refers to a 50ms time window starting from the peak point corresponding to the IED event node (if the spike valley point is used as the reference, then the 30ms time window after that is determined as the target time window).

[0064] For the remaining ripple wave event nodes that are not identified as pathological signals, the decision identification module 15 can perform rapid spectrum analysis and energy concentration analysis on the merged window data where the ripple wave event nodes are located (after analyzing the frequency domain characteristics of physiological ripple waves and pathological signals, we found that the peak frequency of physiological ripple waves is mainly distributed in 70-120Hz, while the peak frequency of pathological signals is mainly distributed in 140-180Hz; in terms of energy concentration, physiological ripple waves are generally lower than 0.2, while pathological signals are usually not lower than 0.35. Both of these indicators have strong distinguishability, so they are selected), determine the peak frequency and energy concentration, and then determine whether the ripple wave event node is a pathological signal based on the peak frequency and energy concentration.

[0065] For example, the decision recognition module 15 can perform rapid spectrum analysis on the merged window data where the ripple wave event nodes are located.

[0066] First, the merged window data can be preprocessed by adding a Hanning window to suppress spectral leakage: (5) in, For the first time after adding a window The value of each sampling point, For the merged window data, the first The value of each sampling point, , This represents the number of sampling points in the merged window data.

[0067] Then, a Fast Fourier Transform (FFT) is used to expand the number of sampling points in the merged window data after adding the Hanning window to the nearest power of 2 (e.g., expanding 2000 sampling points to 2048 sampling points), i.e., m data points. Then perform spectrum calculation: (6) in, For the Fourier transform of merged window data, For frequency, The imaginary unit, The number of sampling points after the merged window data is expanded.

[0068] Based on this, the decision identification module 15 can calculate the spectral peak frequency: (7) in, To merge the spectral peak frequencies of the window data, For frequency, This is a Fourier transform for merging window data.

[0069] Furthermore, the decision identification module 15 can perform energy concentration analysis on the merged window data where the ripple wave event nodes are located, and calculate the energy concentration: (8) in, To optimize the energy concentration of merged window data, for ~ Energy integral of frequency band, The energy integral is the energy across the entire frequency band from 70 to 180 Hz.

[0070] After calculating the spectral peak frequency and energy concentration of the merged window data, the decision identification module 15 can determine whether the spectral peak frequency of the merged window data where the ripple wave event node is located is not lower than 140Hz and whether the energy concentration is not lower than 0.35.

[0071] If the spectral peak frequency of the merged window data where the ripple wave event node is located is not lower than 140Hz and the energy concentration is not lower than 0.35, the decision identification module 15 can determine that the ripple wave event node is a pathological signal.

[0072] Then, the decision recognition module 15 can determine whether the spectral peak frequency of the merged window data where the ripple wave event node is located does not exceed 120Hz and the energy concentration does not exceed 0.2.

[0073] If the spectral peak frequency of the merged window data where the ripple wave event node is located does not exceed 120Hz and the energy concentration does not exceed 0.2, the decision identification module 15 can determine that the ripple wave event node is a physiological ripple wave.

[0074] If the spectral peak frequency of the merged window data containing the ripple wave event node is within (120, 140) and the energy concentration is within (0.2, 0.35), such ripple wave event nodes are relatively few. A fallback approach can be used to distinguish between physiological ripple waves and pathological signals: calculate the probability that the ripple wave event node belongs to a pathological signal based on the spectral peak frequency and energy concentration, and determine whether the ripple wave event node is a pathological signal.

[0075] For example, the probability that a ripple wave event node belongs to a pathological signal can be calculated based on the deviation of the spectral peak frequency and energy concentration from the judgment criteria: (9) in, This represents the probability that a ripple wave event node belongs to a pathological signal. and All are weighted indices, and For example, in this embodiment... and Taking 0.5 each as an example, The spectral peak frequencies of the ripple wave event nodes are denoted as . The energy concentration of the ripple wave event node.

[0076] If the probability that a ripple wave event node is a pathological signal If the value is not less than 0.5, the ripple wave event node is determined to be a pathological signal, and the ripple wave event is classified and identified accordingly.

[0077] For each channel: Event node matching is performed based on IED event nodes and ripple wave event nodes. Ripple wave event nodes whose starting nodes are located within a specified time window are identified as pathological signals. The specified time window is a 50ms time window starting from the peak point corresponding to the IED event node. For ripple wave event nodes in each channel that are not identified as pathological signals: rapid spectrum analysis and energy concentration analysis are performed on the merged window data where the ripple wave event nodes are located to determine the peak frequency and energy concentration. Based on the peak frequency and energy concentration, it is then determined whether the ripple wave event node is a pathological signal.

[0078] In summary, this application provides a ripple wave signal detection and recognition system 10 based on IED events and time-frequency characteristics. The system acquires EEG data (including channel signals from various hippocampal subregions, including CA1-CA4, Subiculum, Presubiculum, and DG) from the target object via a signal acquisition module 11. A preprocessing module 12 performs power frequency notch filtering and bandpass filtering on the EEG data for each channel signal. The power frequency notch removes 50Hz power frequency interference, and the bandpass filtering retains the first frequency band signal (25-80Hz) and the second frequency band signal (70-180Hz). An IED detection module 13 detects IED signals in the first frequency band signal to identify IED event nodes. A ripple wave detection module 14 performs sliding window analysis on the second frequency band signal to detect ripple wave signals and identify ripple wave event nodes. Finally, a decision recognition module 15 determines the ripple wave signal category (physiological ripple wave or pathological signal) based on the IED event nodes and ripple wave event nodes. This system establishes a spatiotemporal coupling detection foundation through the hippocampal sub-regional acquisition module 11 and the dual-band separation (25-80Hz and 70-180Hz) of the preprocessing module 12. Using IED events as spatiotemporal anchors for pathological signals (specifically constructing target time windows as the judgment criterion), it assists in the identification and classification of pathological signals. Simultaneously, for non-IED coupled ripple wave events, it analyzes the essential differences in spectral performance between physiological ripple waves and pathological signals, designing a dual-index discrimination based on spectral peak frequency and energy concentration to fundamentally distinguish between pathological signals and physiological ripple waves. This enables effective identification of independently occurring pathological signals, improves the accuracy of ripple wave classification, and reduces the probability of misclassification.

[0079] In the identification of IED events, the waveform morphology at the time of IED occurrence is analyzed to design an IED event detection mechanism. Multiple discrimination criteria are used (based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, determining the first 40% trough amplitude point before and after the trough point, calculating the spike morphology symmetry index, and determining the spike morphology verification result; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, then determining the two trough points after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, then determining the two trough points after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, and then determining the first trough point after the first trough point, and determining the oscillation decay verification result based on the value of each trough point; based on the peak point corresponding to the candidate node, determining the first trough point after the peak point within a time window, and then determining the first trough point after the first trough point, and determining the first trough amplitude ... The superposition of the peak point preceding the peak point, and using the preceding peak point as the endpoint, determines the background suppression verification region within the time window, and determines the background suppression verification result. This can effectively address the typical forms of various IED events (including spikes, sharp waves, spike-slow-wave complexes, etc.), improving the accuracy of IED event identification. At the same time, based on the coupling window characteristics of pathological signals and IED events in previous research results, the IED event node is determined as the coupling standard for pathological signals (a 50ms time window starting from the peak point corresponding to the IED event node), improving the accuracy of identifying pathological signals coupled with IED events.

[0080] During ripple wave detection, a global analysis of the second frequency band signal is performed to calculate the baseline voltage. Then, a sliding window process is applied (the sliding window size is 100ms, with a step size of 20ms, which takes into account the short-term characteristics of physiological ripple waves, improving the accuracy of ripple wave event detection and reducing the false negative rate), resulting in several window data points. For each window data point: the energy envelope is calculated to obtain the window energy envelope; the number of peaks in the window data is counted; it is determined whether there are three or more consecutive window data points whose window energy envelopes are greater than the sum of the baseline voltage of the previous channel and four times the MAD (median absolute deviation), and the number of peaks in each window data point is not less than eight. If so, the consecutive window data points are merged as a candidate ripple wave event. Furthermore, from the first window of data for candidate ripple wave events, the time point at which the voltage amplitude first exceeds the sum of the baseline voltage and twice the MAD is determined as the starting point of the candidate ripple wave event; from the last window of data for candidate ripple wave events, the time point at which the voltage amplitude last exceeds the sum of the baseline voltage and twice the MAD is determined as the ending point of the candidate ripple wave event. This method can not only effectively detect ripple wave events, but also relatively accurately define the starting range of ripple wave events, thereby improving the accuracy of discrimination and reducing the probability of false positives (i.e., physiological ripple waves being misidentified as pathological signals) in the subsequent IED event coupling discrimination process.

[0081] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A ripple wave signal detection and recognition system based on IED events and time-frequency characteristics, characterized in that, include: The signal acquisition module is used to acquire the EEG data of the target object. The EEG data contains at least the channel signals of each hippocampal subregion, which includes CA1-CA4, Subiculum, Presubiculum, and DG. CA1-CA4 represent hippocampal horn regions 1-4, Subiculum represents the inferior horn, Presubiculum represents the anterior inferior horn, and DG represents the dentate gyrus. The preprocessing module is used to preprocess the signals of each channel of the EEG data. The preprocessing includes power frequency notch filtering and bandpass filtering. Power frequency notch filtering removes 50Hz power frequency interference, and bandpass filtering retains the 25-80Hz frequency band and the 70-180Hz frequency band respectively. The 25-80Hz frequency band is the first frequency band signal, and the 70-180Hz frequency band is the second frequency band signal. The IED detection module is used to detect IED signals in the first frequency band signal and determine the IED event node, where IED represents interictal epileptiform discharge. The ripple wave detection module is used to perform sliding window analysis on the second frequency band signal, detect ripple wave signals, and determine ripple wave event nodes. The decision recognition module is used to determine the ripple wave signal category based on the IED event node and the ripple wave event node. The ripple wave signal category includes physiological ripple waves and pathological signals.

2. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 1, characterized in that, The IED detection module is specifically used for: For the first frequency band signal of each channel: Perform a global analysis on the first frequency band signal of the current channel to calculate the baseline voltage of the current channel; Using the baseline voltage as a reference, peak detection is performed on the first frequency band signal of the current channel, and candidate nodes that meet the peak condition are identified. The peak condition is: higher than the sum of the baseline voltage and 3 times MAD, where MAD represents the median absolute deviation. For each candidate node, a 200ms interval is determined forward and a 400ms interval is determined backward, resulting in a 600ms time window for the candidate node. Then, spike morphology verification, slow wave oscillation verification, and background suppression verification are performed on the signal within the time window. Based on the verification results of spike morphology verification, slow wave oscillation verification, and background suppression verification, the marked candidate nodes that meet the requirements are determined. Based on the marked candidate nodes, the IED event start point and IED event end point are determined.

3. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 2, characterized in that, The IED detection module is specifically used for: Based on the peak points corresponding to the candidate nodes, the first valley point after the peak point is determined within the time window, the first 40% valley amplitude point before and after the valley point is determined, the spike morphology symmetry index is calculated, and the spike morphology verification result is determined. Based on the peak points corresponding to the candidate nodes, the first valley point after the peak point is determined within the time window, and then the two valley points after the first valley point are determined. The oscillation decay verification result is determined based on the value of each valley point. Based on the peak point corresponding to the candidate node, the previous peak point is determined within the time window, and the background suppression verification region is determined within the time window with the previous peak point as the endpoint, thus determining the background suppression verification result.

4. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 1, characterized in that, The ripple wave detection module is specifically used for: For the second frequency band signal of each channel: Perform a global analysis on the second frequency band signal of the current channel to calculate the baseline voltage of the current channel; The second frequency band signal of the current channel is processed by sliding window to obtain several window data, wherein the sliding window size is 100ms and the step size is 20ms; For each window of data: feature extraction is performed on the window data to determine several feature indices. Based on the feature indices, candidate ripple events are determined. Then, the start and end nodes of each candidate ripple event are determined to obtain several ripple event nodes.

5. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 4, characterized in that, The ripple wave detection module is specifically used for: The energy envelope of the window is obtained by performing energy envelope calculation on the window data; Count the number of peaks in the window data; Determine if there are three or more consecutive window energy envelopes that are greater than the sum of the baseline voltage of the front channel and four times the MAD, and if each window data has at least eight peaks. If so, merge the consecutive window data as a candidate ripple wave event, where MAD represents the median absolute deviation.

6. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 5, characterized in that, The ripple wave detection module is specifically used for: The window energy envelope is calculated using the following method: ， in, The window energy envelope of the window data. The number of sampling points for the window data. For the first data in the window The sampled voltage values ​​of each data point.

7. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 5, characterized in that, The ripple wave detection module is specifically used for: For each candidate ripple wave event: From the first window of data of the candidate ripple wave event, the time point at which the voltage amplitude first exceeds the sum of the baseline voltage and twice the MAD is determined as the starting point of the candidate ripple wave event; From the last window of data of the candidate ripple wave event, the time point at which the voltage amplitude last exceeds the sum of the baseline voltage and twice the MAD is determined as the termination point of the candidate ripple wave event.

8. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 3, characterized in that, The decision recognition module is specifically used for: For each channel: Event node matching is performed based on IED event nodes and ripple wave event nodes. Ripple wave event nodes whose starting node is located within the target time window are identified as pathological signals. The target time window is a 50ms time window starting from the peak point corresponding to the IED event node. For ripple wave event nodes in each channel that are not identified as pathological signals: perform rapid spectrum analysis and energy concentration analysis on the merged window data where the ripple wave event node is located to determine the peak frequency and energy concentration, and then determine whether the ripple wave event node is a pathological signal based on the peak frequency and energy concentration.

9. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 8, characterized in that, The decision recognition module is specifically used for: Perform fast spectral analysis on the merged window data containing the ripple wave event nodes to calculate the spectral peak frequencies: ， in, To merge the spectral peak frequencies of the window data, For frequency, Fourier transform for merging window data; Energy concentration analysis is performed on the merged window data containing the ripple wave event nodes, and the energy concentration is calculated: ， in, To optimize the energy concentration of merged window data, for ~ Energy integral of frequency band, The energy integral is the energy across the entire frequency band from 70 to 180 Hz.

10. The ripple wave signal detection and recognition system based on IED events and time-frequency characteristics according to claim 8, characterized in that, The decision recognition module is specifically used for: If the spectral peak frequency of the merged window data where the ripple wave event node is located is not lower than 140Hz and the energy concentration is not lower than 0.35, the ripple wave event node is determined to be a pathological signal. If the spectral peak frequency of the merged window data where the ripple wave event node is located does not exceed 120Hz and the energy concentration does not exceed 0.2, the ripple wave event node is determined to be a physiological ripple wave. If the spectral peak frequency of the merged window data where the ripple wave event node is located is within (120, 140) and the energy concentration is within (0.2, 0.35), calculate the probability that the ripple wave event node belongs to a pathological signal based on the spectral peak frequency and energy concentration, and determine whether the ripple wave event node is a pathological signal.

Images