Intracranial electroencephalogram epileptic seizure early warning method based on multipath map brain network modeling

Abstract

The invention discloses an intracranial electroencephalogram epileptic seizure early warning method based on multipath map brain network modeling, and belongs to the technical field of electroencephalogram analysis. The method comprises the following steps: providing a multi-path map brain network modeling framework for epileptic seizure prediction; the multi-channel brain map is constructed based on three cross-frequency coupling (CFC) relationships in neuroscience, a frequency band in each channel of the electroencephalogram signal forms nodes of the map, and the three CFC relationships form edges of the map; and designing a multi-path brain map learning network with a joint fusion module to learn modes in the multi-path brain map to form a final representation. According to the method, the iEEG signals can be analyzed, the modes in the iEEG signals can be mined by utilizing the designed multi-channel brain map learning network, uniform characterization is formed, and the accuracy of epileptic seizure prediction is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electroencephalogram (EEG) analysis, and in particular relates to an intracranial EEG epileptic seizure early warning method based on multi-path graph brain network modeling. Background Art

[0002] Epilepsy is a chronic neurological disease. According to the World Health Organization, as of February 2024, approximately 50 million people worldwide are affected by it. Epileptic seizures can impair consciousness and motor function, potentially leading to life-threatening consequences. Predicting epileptic seizures in advance can enable epilepsy patients and medical staff to take preventive measures, effectively reduce the damage caused by epileptic seizures and improve the quality of life of patients. Electroencephalogram (EEG), as an important tool for measuring brain activity, is widely used in epilepsy research and clinical practice. The basic goal of epileptic seizure prediction is to use EEG signals to distinguish the preictal period (the short stage before an epileptic seizure) from the interictal period (the normal stage between two epileptic seizures), which can be regarded as a binary classification problem. Compared with scalp EEG (sEEG), intracranial EEG (iEEG) can directly obtain purer and more accurate signals from deep brain tissue, so iEEG signals have become a more reliable basis for epilepsy research.

[0003] In recent years, with the continuous deepening of epilepsy research, researchers have realized that epilepsy is a network disease, and its prediction performance depends on whether the non-Euclidean structure of brain network connections can be effectively captured. The importance of brain network modeling for epilepsy prediction has become increasingly prominent. To this end, researchers have proposed various graph-based methods, that is, to represent brain networks by constructing brain maps, which are usually constructed based on the relationship between electrode channels, where channels are regarded as nodes and the relationship between channels is regarded as edges. Although these graph-based methods can capture brain network connections and improve the performance of epileptic seizure prediction, their modeling methods are still relatively simple and fail to fully consider the complexity of brain networks. There is still a lot of room for exploration. In order to better use iEEG signals to build brain networks, the following two points need to be considered: First, the brain network is a complex network with multiple relationships. These diverse relationships reflect different aspects of the brain network and form a heterogeneous and complementary structure. In contrast, existing graph learning methods mainly focus on brain network models based on a single relationship and ignore other relationships. Secondly, as mentioned above, iEEG signals can provide more accurate and complete frequency information. However, the existing methods process iEEG signals in a relatively rough way. Instead of extracting signals for each frequency band, all frequency information is encoded together, which results in the rich frequency information and correlation in iEEG signals being masked. Therefore, it is necessary to develop a more effective method to solve the above problems and improve the performance of epileptic seizure prediction. Summary of the invention

[0004] To solve the above technical problems, the present invention provides an intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling, which is used for epileptic seizure prediction, and specifically solves the problems of modeling multiple relationships in brain networks and utilizing iEEG frequency information. A multi-path brain map learning network is designed, and patterns in multi-path brain maps are mined by combining a graph encoder and a joint fusion module.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] An intracranial electroencephalogram epileptic seizure warning method based on multi-path graph brain network modeling, comprising:

[0007] Step 1: Obtain the original iEEG data and perform preprocessing and data enhancement to obtain the final time-frequency diagram;

[0008] Step 2: extract amplitude and phase information from the final time-frequency diagram, divide it by frequency band and project it into amplitude and phase features;

[0009] Step 3, semantically encode the amplitude and phase features to obtain multi-path graph node features, construct multi-path graph edge features based on the similarity between the amplitude and phase features, and construct a multi-path brain map based on the multi-path graph node features and the multi-path graph edge features, wherein the multi-path brain map includes an amplitude-amplitude coupling subgraph, a phase-phase coupling subgraph, and a phase-amplitude coupling subgraph;

[0010] Step 4: Use a graph convolutional network to learn the relationship patterns within and between sub-graphs of multiple brain maps, and perform feature fusion through a cross-attention mechanism to obtain the final representation, which is then sent to a classification head for binary classification of pre-ictal and interictal periods.

[0011] On the other hand, the present invention provides an intracranial electroencephalogram epilepsy attack warning device based on multi-channel brain network modeling, including: a data acquisition and preparation module, a multi-channel brain map preparation module, a multi-channel brain map construction module and a multi-channel brain map learning module, wherein:

[0012] The data acquisition and preparation module is used to acquire the original iEEG data and perform preprocessing and data enhancement on it to obtain the final time-frequency diagram;

[0013] The multi-channel brain map preparation module is used to extract amplitude and phase information from the final time-frequency map, and divide and project it into amplitude and phase features according to frequency bands;

[0014] The multi-path brain map construction module is used to perform semantic encoding on amplitude and phase features to obtain multi-path graph node features, construct multi-path graph edge features based on the similarity between amplitude and phase features, and construct a multi-path brain map based on the multi-path graph node features and the multi-path graph edge features, wherein the multi-path brain map includes an amplitude-amplitude coupling subgraph, a phase-phase coupling subgraph, and a phase-amplitude coupling subgraph;

[0015] The multi-path brain map learning module is used to learn the relationship patterns within and between multi-path brain map sub-maps, and perform feature fusion through a cross-attention mechanism to obtain a final representation, and the final representation is sent to a classification head for binary classification of pre-ictal and interictal periods to obtain a classification result.

[0016] In a third aspect, the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the aforementioned intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling.

[0018] The beneficial effects of the present invention are:

[0019] The present invention proposes a multi-path brain network modeling framework for epileptic seizure prediction and warning, which can better represent various relationships in the brain network and make full use of the frequency information in iEEG; designs a multi-path brain map construction process, which can construct a semantically rich multi-path brain map based on three CFC relationships; proposes a multi-path brain map learning network, which can mine the relationship patterns within and between sub-maps of the multi-path brain map and integrate them into a unified final representation, thereby improving the accuracy of epileptic seizure prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of the intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling of the present invention;

[0021] Figure 2 This is a network structure diagram of the intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0023] In order to overcome the limitations of existing methods, the present invention proposes an epileptic seizure prediction and warning method based on multi-channel brain network modeling, which includes: multi-channel brain map preparation, multi-channel brain map construction and multi-channel brain map learning. Among them, the multi-channel brain map preparation link extracts amplitude and phase representations from iEEG signals to prepare for the construction of the map. The multi-channel brain map construction link constructs three sub-maps based on CFC to capture different brain network connections. Finally, the multi-channel brain map learning link reveals the patterns within and between sub-maps and integrates them into a unified representation.

[0024] Specifically, CFC is defined as the interaction between neural oscillations in different frequency bands. Since amplitude and phase are basic properties of frequency, CFC mainly includes amplitude-amplitude coupling (AAC), phase-phase coupling (PPC), and phase-amplitude coupling (PAC). In the multi-channel brain map, the frequency band of each channel is regarded as a node of the graph, and the three types of CFC relationships are regarded as three types of edges of the graph. Therefore, the multi-channel brain map consists of three sub-graphs, each representing a CFC relationship. In order to construct the multi-channel brain map, the amplitude and phase are first extracted from the iEEG signal using the short-time Fourier transform (STFT), and encoded to obtain semantic representation, further forming node features, while different CFC relationships are calculated accordingly and threshold filtering is performed to form edges. After completing the construction of the multi-path brain map, a multi-path brain map learning network was introduced for graph representation learning. It uses a graph convolutional network (GCN) encoder to learn the relationship patterns within and between sub-graphs, and fuses them through a joint fusion module with a cross-attention mechanism to obtain the final representation, which is then sent to the classification head for binary classification of pre-ictal and inter-ictal periods.

[0025] like Figure 1 As shown, it is a flow chart of the intracranial EEG epilepsy attack warning method based on multi-path graph brain network modeling of the present invention, including:

[0026] Step 1: Prepare iEEG epilepsy data as input and perform data preprocessing and data augmentation; here we take the public Kaggle dataset (https: / / kaggle.com / competitions / seizure-prediction) as an example.

[0027] For data preprocessing, the original signal data is downsampled to 256 Hz, the data is divided into non-overlapping segments of length 5s using a sliding window, and the time-frequency diagram is generated using STFT as a training sample. channels and timestamped iEEG segments , STFT will fragment No. channels, i.e. , converted to have time windows and Channel time-frequency diagram of frequency components , which is a complex matrix:

[0028]

[0029] in, is the time offset, represents the Fourier transform, is the window function, The representative frequency is The complex exponential function of is a natural constant, is pi, is an imaginary unit, Indicates time. The time-frequency diagrams of all channels are combined into segments The corresponding time-frequency diagram , the collection of time-frequency graphs of all segments is taken as the sample set.

[0030] For the data augmentation operation, the samples were augmented to balance the number of samples in the interictal and preictal periods. Specifically, two samples were randomly selected from the preictal sample set after the preprocessing operation, and the augmented samples were created by concatenating the low-frequency part of the first sample with the high-frequency part of the second sample. The boundary frequency of the low and high frequencies was set to 20 Hz because brain activity mainly occurs in the frequency range below 30 Hz. This augmentation process was repeated times, among which represents the number of preictal samples after preprocessing operations, is the enhancement factor. By adjusting , the balance between interictal and preictal samples can be controlled. Therefore, for each patient or each experimental dog, It is set individually according to the original ratio of interictal and preictal samples. The samples in the enhanced sample set are the final time-frequency diagram .

[0031] Step 2: Multi-channel mind map preparation. Figure 2 As shown, the present invention first extracts amplitude and phase information from the iEEG signal processed according to step 1, and then divides and projects it into amplitude and phase features according to frequency bands to prepare for the construction of multi-channel brain maps.

[0032] Step 2-1: Amplitude and phase extraction. Amplitude The final time-frequency diagram The modulus is obtained, and the phase Corresponding to the final time-frequency diagram The main angle of the two can be calculated as follows:

[0033]

[0034]

[0035] in, and represent the real part and imaginary part of the complex number respectively. In addition, in order to improve the training stability and speed up the convergence, and z-score normalization was applied.

[0036] Step 2-2: Divide by frequency band and project. According to the frequency band division in the EEG signal, the normalized amplitude and Phase Decomposition along the frequency dimension: (1-4 Hz), (4-8 Hz), (8-12 Hz), (12-30Hz) and (>30 Hz). This decomposition produces amplitudes of specific frequency bands and Phase ,in represents the frequency band index, represents the total number of frequency bands, Indicates The bandwidth of the frequency band. (1-4 Hz), (4-8 Hz), (8-12 Hz), (12-30 Hz) and The bandwidths of these five frequency bands (>30 Hz) are different, and the amplitude and phase information of different frequency bands are different in dimension. Therefore, the amplitude and phase information of each frequency band are projected to a dimension of The unified feature space of :

[0037]

[0038]

[0039] in, represents stacking along the second dimension, It means flattening the last two dimensions, that is , are the learnable weights for the amplitude and phase projections of each frequency band, respectively. So far, the amplitude and phase features are expressed as and , which laid the foundation for the subsequent construction of multi-channel mind maps.

[0040] Step 3: Multi-path mind map construction. Figure 2 As shown, the multi-path mind map constructed by the present invention inherits the core idea of ​​the multi-path map, and its characteristic is that there are various relationships between nodes. It can be expressed as:

[0041]

[0042] in, is the initial node feature, , , is the adjacency matrix corresponding to the three CFC relationships. In addition, to ensure that different edges are supported by different types of node information, the initial node features Decompose and construct fine-grained features. Specifically, the extracted amplitude and phase features and As the input of multi-way brain map construction, the multi-way brain map construction includes node construction, edge construction and the final multi-way brain map construction for brain network modeling.

[0043] Step 3-1: Semantic feature extraction. Amplitude and phase features and They are just preliminary representations, and they need to be encoded by Transformer. Transformer uses multi-head self-attention mechanism and feedforward network to model the interdependence between features. This process generates semantic amplitude and phase embeddings , which can be expressed as:

[0044]

[0045]

[0046] Among them, the flattened amplitude and phase characteristics , Here It means to flatten the first two dimensions, that is, (in ). It consists of multiple Transformer layers, and its embedding dimension is same.

[0047] Step 3-2: Node feature construction. Based on the extracted semantic amplitude and phase embedding, node features are customized for each subgraph to correspond to three different CFC relationships. Therefore, these node features are Specifically, since AAC captures the relationship between amplitudes and PPC captures the relationship between phases, the node features of the AAC and PPC subgraphs are defined as and For the PAC subgraph representing the interaction between phase and amplitude, a PAC gate is used to combine the amplitude and phase embeddings. The gate value is calculated by applying a linear transformation to the concatenation of the amplitude and phase embeddings. :

[0048]

[0049] in, Indicates splicing along the node feature dimension, is the learnable weight of the PAC gate, and the superscript T indicates transposition. Then, the node features of the PAC subgraph It is derived as a weighted sum of semantically defined amplitude and phase embeddings:

[0050]

[0051] in, is element-wise multiplication.

[0052] Step 3-3: Edge construction,The edges in the multi-path brain map are constructed based on the similarity between the amplitude and phase features.,According to the definition of the three CFC relationships, the,adjacency matrix is initialized as a similarity matrix. Specifically, Originated from the similarity between amplitude features, Originated from the similarity between phase features, Derived from the similarity between phase and amplitude features:

[0053]

[0054]

[0055]

[0056] in, represents the cosine similarity. Threshold filtering is then applied to the adjacency matrix to eliminate spurious relationships and ensure the sparsity of the subgraph, which can be expressed as:

[0057]

[0058] in, yes Middle Line The elements of the column, is the threshold, set to 0.5. In addition, a cross-frequency mask is applied to the adjacency matrix to ensure that the edges appear between different frequency bands, and the positions of the same frequency band are set to zero. Thus, the final adjacency matrix represents the edges in the corresponding subgraph, where non-zero positions indicate the presence of edges and their weights are the corresponding values, and zero positions indicate the absence of edges.

[0059] Step 3-4: Multi-channel brain map construction. To construct this special multi-channel brain map, three sub-graphs are defined, representing the three relationships of AAC, PPC and PAC. Since the iEEG signals from the same channel and frequency band are regarded as one node, these sub-graphs share the same node set, but different node features and edge sets. According to the settings of nodes and edges, the multi-channel brain map The build is as follows:

[0060]

[0061] in, , , is a subgraph constructed using the corresponding node features and adjacency matrix:

[0062]

[0063]

[0064] .

[0065] As the names imply, these three subgraphs correspond to three types of CFC relationships. represents the coupling between the amplitudes, represents the coupling between phases, Represents the coupling between amplitude and phase. A variety of coupling types are covered overall to summarize the diverse relationships inherent in brain networks.

[0066] Step 4: Multi-path mind map learning. Figure 2 As shown in Figure 2, the constructed multi-way brain map clearly represents the relationship between nodes in the brain network, and multi-way brain map learning aims to reveal the underlying relationship patterns through model-based learning. Multi-way brain map learning mainly consists of two parts: graph encoding and feature fusion.

[0067] Step 4-1: Graph encoding. The present invention uses GCN as a graph encoder. For a given node feature And the corresponding adjacency matrix , the GCN layer is defined as follows:

[0068]

[0069] in, is the layer index, is the degree matrix of the graph, It is layer GCN layer, It is The input node features of the layer, and , It is The learnable weights of the layers, is the ReLU activation function. The present invention uses three independent two-layer GCN encoders to encode the sub-graph embeddings respectively. ,in is the output dimension of the entire GCN encoder:

[0070]

[0071]

[0072]

[0073] The output dimensions of these two layers are set to twice and half of the feature dimension, respectively. The subgraph embedding contains the encoded CFC relations, reflecting the three aspects of the brain network.

[0074] Step 4-2: Feature fusion. After graph encoding, the three different subgraph embeddings have effectively learned the coupling relationship contained in their respective subgraphs. To this end, the present invention designs a joint fusion module based on the cross-attention mechanism to make full use of the information from all three subgraphs and integrate these embeddings into a unified final representation. First, the joint representation is obtained by summing the subgraph embeddings. , as the initial result of the fusion process:

[0075] ,

[0076] Then, the subgraph embeddings are refined using a criss-cross attention mechanism. In this process, As a query (query), and the subgraph is embedded As a key (key) and value (value). This can be expressed mathematically as:

[0077]

[0078]

[0079] in, are learnable weights, Represents the cross attention mechanism. By combining cross attention, residual connection and layer normalization, we get the refined embedding :

[0080]

[0081]

[0082]

[0083] in, The representation layer is normalized. The final representation is recorded as , which is obtained by additively aggregating the refinement embeddings:

[0084] .

[0085] Step 4-3: Output classification. The final representation is input into a fully connected layer classification head to distinguish between interictal and preictal segments. If the output is interictal, it means that the patient is in a normal state and no intervention is required; if the output is preictal, it means that the patient is about to have an attack and an early warning is needed so that epileptic patients and medical staff can prepare.

[0086] Preferably, cross entropy loss is used as the loss function, and back propagation is used to update model parameters until convergence; hyperparameters such as learning rate, number of training rounds, feature dimension of the model, number of layers and heads of the Transformer encoder are adjusted to optimize model performance.

[0087] Preferably, the test set is used for evaluation. The evaluation adopts the leave-one-out cross validation (LOOCV) for seizures as the evaluation strategy. One seizure data is left out as the test set and the remaining data is used as the training set in each round. This is repeated for each seizure, and the final performance is the average of these rounds. The evaluation indicators used in the evaluation include AUC, sensitivity (Sn), false positive rate per hour (FPR / h) and p-value. Among them, AUC reflects the classification performance of interictal and preictal periods; Sn refers to the ratio of successfully predicted epileptic seizures to the total number of epileptic seizures; FPR / h refers to the number of wrong predictions per hour; p-value indicates the statistical improvement of the model relative to the random predictor. If the p-value is less than 0.001, it means that the model is statistically superior to the random predictor at a confidence level of at least 99.9%.

[0088] When the model output is converted into the actual output of the epilepsy warning system, in order to improve stability and avoid the impact of model output fluctuations, the warning system can only be used continuously. There are at least Only when the model determines that the patient is in the pre-ictal stage will an early warning be issued. and Adjust according to actual situation.

[0089] Through the above steps, the present invention can analyze iEEG signals, construct multi-channel brain maps to express various relationships in complex brain networks and make full use of the frequency information in iEEG, and then use the designed multi-channel brain map learning network to mine the patterns and form a unified representation, thereby improving the accuracy of epileptic seizure prediction.

[0090] On the other hand, the present invention provides an intracranial electroencephalogram epileptic seizure warning device based on multi-channel brain network modeling, which includes various modules that can implement various steps of the aforementioned method, specifically, including a data acquisition and preparation module, a multi-channel brain map preparation module, a multi-channel brain map construction module and a multi-channel brain map learning module, wherein:

[0091] The data acquisition and preparation module is used to acquire the original iEEG data and perform preprocessing and data enhancement on it to obtain the final time-frequency diagram;

[0092] The multi-channel brain map preparation module is used to extract amplitude and phase information from the final time-frequency map, and then divide it into frequency bands and project it into amplitude and phase features;

[0093] The multi-path brain map construction module is used to perform semantic encoding on amplitude and phase features to obtain multi-path graph node features, construct multi-path graph edge features based on the similarity between amplitude and phase features, and construct a multi-path brain map based on the multi-path graph node features and the multi-path graph edge features, wherein the multi-path brain map includes an amplitude-amplitude coupling subgraph, a phase-phase coupling subgraph, and a phase-amplitude coupling subgraph;

[0094] The multi-path brain map learning module is used to learn the relationship patterns within and between multi-path brain map sub-maps, and perform feature fusion through a cross-attention mechanism to obtain a final representation, and the final representation is sent to a classification head for binary classification of pre-ictal and interictal periods to obtain a classification result.

[0095] In a third aspect, the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling.

[0096] In a fourth aspect, the present invention provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the aforementioned intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling.

[0097] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for early warning of intracranial electroencephalogram epileptic seizures based on multi-path graph-brain network modeling, characterized in that: include: Step 1: Obtain the original iEEG data and perform preprocessing and data enhancement to obtain the final time-frequency diagram; Step 2: extract amplitude and phase information from the final time-frequency diagram, divide it by frequency band and project it into amplitude and phase features; Step 3, semantically encode the amplitude and phase features to obtain multi-path graph node features, construct multi-path graph edge features based on the similarity between the amplitude and phase features, and construct a multi-path brain map based on the multi-path graph node features and the multi-path graph edge features, wherein the multi-path brain map includes an amplitude-amplitude coupling subgraph, a phase-phase coupling subgraph, and a phase-amplitude coupling subgraph; Step 4: Use a graph convolutional network to learn the relationship patterns within and between sub-graphs of multiple brain maps, and perform feature fusion through a cross-attention mechanism to obtain the final representation, which is then sent to a classification head for binary classification of pre-ictal and interictal periods.

2. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 1 is characterized in that: The step 1 includes collecting and downsampling iEEG data, dividing the data into non-overlapping segments using a sliding window, generating a time-frequency diagram using STFT and performing data enhancement, and obtaining a final time-frequency diagram as a training sample.

3. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 1 is characterized in that: The step 2 comprises: Step 2-1, extracting amplitude and phase based on the final time-frequency graph, wherein the amplitude is obtained by the modulus of the final time-frequency graph, the phase corresponds to the main argument of the final time-frequency graph, and the amplitude and phase are normalized; Step 2-2: According to the frequency band division in the EEG signal, the normalized amplitude and phase are decomposed along the frequency dimension, and the amplitude and phase information of each frequency band is projected into a unified feature space through linear transformation to obtain amplitude and phase features.

4. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 1 is characterized in that: The step 3 comprises: Step 3-1: Transformer uses a multi-head self-attention mechanism and a feedforward network to model and encode the interdependencies between features and extract semantic amplitude and phase embeddings; Step 3-2: based on the extracted semantic amplitude and phase embeddings, customize the node features for each subgraph so that it corresponds to the amplitude-amplitude coupling subgraph, the phase-phase coupling subgraph, and the phase-amplitude coupling subgraph; Step 3-3, constructing a multi-path graph edge feature based on the similarity between the amplitude and phase features, using an adjacency matrix to characterize the similarity, applying a threshold filter to the adjacency matrix, wherein a non-zero position in the adjacency matrix indicates the existence of an edge, and its weight is a corresponding value; Step 3-4: Define iEEG signals from the same channel and frequency band as one node, and the subgraphs share the same node set, but with different node features and edge sets. Construct a multi-path brain map based on the node and edge settings. : in, , , The amplitude-amplitude coupling subgraph, phase-phase coupling subgraph, and phase-amplitude coupling subgraph are constructed using the corresponding node features and adjacency matrix: In the formula, , , They represent the node features of the amplitude-amplitude coupling subgraph, the phase-phase coupling subgraph, and the phase-amplitude coupling subgraph, respectively. , , They represent the adjacency matrices of the amplitude-amplitude coupling subgraph, the phase-phase coupling subgraph, and the phase-amplitude coupling subgraph respectively.

5. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 4 is characterized in that: In step 3-2, the node features of the amplitude-amplitude coupling subgraph are defined as semantic amplitude embedding, the phase-phase coupling subgraph is defined as semantic phase embedding, and the phase-amplitude coupling subgraph is defined as the weighted sum of semantic amplitude and phase embeddings.

6. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 1, characterized in that: The step 4 comprises: Step 4-1: For a given node feature and the corresponding adjacency matrix, three independent two-layer GCN encoders are used to encode the amplitude-amplitude coupling subgraph, the phase-phase coupling subgraph, and the phase-amplitude coupling subgraph embedding respectively; Step 4-2: Use a joint fusion module based on a cross-attention mechanism to integrate the sub-graph embeddings into a unified final representation; Step 4-3: The final representation is input into a fully connected layer classification head to distinguish between interictal and preictal segments.

7. The intracranial EEG epilepsy attack early warning method based on multi-path graph brain network modeling according to claim 6 is characterized in that: The step 4-2 comprises: The amplitude-amplitude coupling subgraph, phase-phase coupling subgraph, and phase-amplitude coupling subgraph are embedded and summed to obtain a joint representation; The subgraph embeddings are refined using the cross-attention mechanism to obtain refined embeddings, which are then added and aggregated to obtain the final representation.

8. An intracranial EEG epilepsy attack warning device based on multi-path graph-brain network modeling, characterized in that: include: Data acquisition and preparation module, multi-channel brain map preparation module, multi-channel brain map construction module and multi-channel brain map learning module, where: The data acquisition and preparation module is used to acquire the original iEEG data and perform preprocessing and data enhancement on it to obtain the final time-frequency diagram; The multi-channel brain map preparation module is used to extract amplitude and phase information from the final time-frequency map, and divide and project it into amplitude and phase features according to frequency bands; The multi-path brain map construction module is used to perform semantic encoding on amplitude and phase features to obtain multi-path graph node features, construct multi-path graph edge features based on the similarity between amplitude and phase features, and construct a multi-path brain map based on the multi-path graph node features and the multi-path graph edge features, wherein the multi-path brain map includes an amplitude-amplitude coupling subgraph, a phase-phase coupling subgraph, and a phase-amplitude coupling subgraph; The multi-path brain map learning module is used to learn the relationship patterns within and between multi-path brain map sub-maps, and perform feature fusion through a cross-attention mechanism to obtain a final representation, and the final representation is sent to a classification head for binary classification of pre-ictal and interictal periods to obtain a classification result.

9. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; Wherein, when one or more programs are executed by the one or more processors, the one or more processors implement the intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: Executable instructions are stored thereon, which, when executed by a processor, enable the processor to implement the intracranial EEG epileptic seizure warning method based on multi-path graph brain network modeling as described in any one of claims 1-7.

Images