Methods, devices, media and equipment for detecting abnormal discharges during the interictal period of epilepsy

Abstract

The disclosed embodiments relate to a method, device, storage medium and electronic device for detecting abnormal discharges between epileptic seizures, and relate to the field of biomedical detection technology. The method comprises: obtaining an electrical signal to be tested from a target user; inputting the electrical signal to be tested into a trained neural network model for processing, and outputting a predicted probability of abnormal discharges in the electrical signal to be tested; the trained neural network model is obtained by training a training set; the training set comprises a plurality of training samples; the training samples comprise electrical signals and corresponding labels of abnormal discharges between seizures of epileptic patients, electrical signals and corresponding labels of no abnormal discharges between seizures of epileptic patients, and electrical signals and corresponding labels of non-epileptic patients; electrical signals of abnormal discharges between seizures of epileptic patients exclude electrical signals of suspected abnormal discharges in electroencephalogram signals caused by electrocardiogram signals and / or electromyogram signals. In this way, the accuracy of positive identification can be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of biomedical detection technology. More specifically, the embodiments of the present disclosure relate to a method for detecting abnormal discharges during epileptic seizures, a device for detecting abnormal discharges during epileptic seizures, a computer-readable storage medium, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] Epilepsy is a chronic neurological disease characterized by sudden abnormal brain reactions and recurrences. It is caused by abnormal activity of brain neurons. This epileptic seizure caused by excessive discharge of neurons is usually accompanied by disorders of movement, sensation, emotion or mental function. Once this sudden neurological disease occurs, the patient's brain will stop working normally, resulting in abnormal reactions such as fainting, body imbalance, convulsions, muscle contractions, loss of consciousness and intuition. For any epilepsy patient, epileptic seizures have a great impact on all aspects of the patient's and his family's life, and may even endanger the patient's life.

[0004] Electroencephalogram (EEG) is a non-invasive signal acquisition method used to clinically record brain-related activities. It has a high temporal resolution and plays an important role in the detection, diagnosis, treatment, efficacy evaluation and pathological research of epilepsy. At present, the diagnosis of epilepsy based on EEG is mainly the detection of epileptic seizures, however, epileptic seizures are not common. In contrast, nearly 80% of epilepsy patients have abnormal neuronal discharges between seizures. These abnormal discharges observable in EEG are called interictal epileptiform discharges (IED). IED is a strong support for epilepsy diagnosis or epileptic seizure risk assessment.

[0005] In the related technologies, most of them collect EEG and determine the interval between epileptic seizures of epileptic patients by observing IED in EEG. Summary of the invention

[0006] However, the IED in the collected EEG may be caused by electrocardiography and / or electromyography. It is not possible to determine that the false positive phenomenon is prone to occur between epileptic seizures in epileptic patients only by observing the IED in the EEG.

[0007] Therefore, an improved method for detecting abnormal discharges between epileptic seizures is highly desirable to exclude the false positive phenomenon to a certain extent.

[0008] In this context, embodiments of the present disclosure are intended to provide a method for detecting abnormal discharges during epileptic seizures, an apparatus for detecting abnormal discharges during epileptic seizures, a computer-readable storage medium, and an electronic device.

[0009] According to a first aspect of the present disclosure, a method for detecting abnormal discharges between epileptic seizures is provided, the method comprising: obtaining an electrical signal to be tested from a target user; the electrical signal to be tested comprises an electroencephalogram (EEG) signal, an electrocardiogram (ECG) signal and an electromyogram (EMG) signal; inputting the electrical signal to be tested into a trained neural network model for processing, and outputting a predicted probability that the electrical signal to be tested has abnormal discharges; the trained neural network model is obtained by training a training set; the training set comprises a plurality of training samples; the training samples comprise electrical signals of epileptic patients with abnormal discharges between seizures and corresponding labels, electrical signals of epileptic patients without abnormal discharges between seizures and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals of epileptic patients with abnormal discharges between seizures are electrical signals excluding suspected abnormal discharges in the electroencephalogram (EEG) signal caused by the electrocardiogram (ECG) signal and / or the electromyogram (EMG) signal.

[0010] In one embodiment, after obtaining the electrical signal to be tested of the target user, the method further includes: performing a short-time Fourier transform on the electrical signal to be tested to obtain time-frequency data of the electrical signal to be tested; correspondingly, inputting the electrical signal to be tested into a trained neural network model for processing includes: inputting the time-frequency data of the electrical signal to be tested into the trained neural network model for processing.

[0011] In one embodiment, the trained neural network model includes three tower layers, and the three tower layers include an EEG signal tower, an EEG signal tower, and an EMG signal tower; the step of inputting the electrical signal to be measured into the trained neural network model for processing includes: inputting the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; inputting the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; inputting the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; and inputting the EMG signal into the EMG signal tower to obtain a feature vector of the EMG signal.

[0012] In one embodiment, the trained neural network model also includes an aggregation layer, and the inputting of the electrical signal to be tested into the trained neural network model for processing includes: inputting the feature vector of the EEG signal, the feature vector of the ECG signal, and the feature vector of the EMG signal output by the three-tower layer into the aggregation layer for splicing to obtain a feature map.

[0013] In one embodiment, the trained neural network model also includes a bottom layer, and the inputting the electrical signal to be measured into the trained neural network model for processing includes: inputting the feature map output by the aggregation layer into the bottom layer for feature extraction and classification, and obtaining the predicted probability that the electrical signal to be measured has abnormal discharge.

[0014] In one embodiment, training the trained neural network model includes: obtaining a training set; the training set includes multiple training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during interictal attacks and corresponding labels, electrical signals of epileptic patients without abnormal discharges during interictal attacks and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; inputting the training set into the neural network model to obtain a predicted classification of the training set; the predicted classification includes positive or negative; the positive indicates that the training sample has abnormal discharges, and the negative indicates that the training sample does not have abnormal discharges; determining the loss value of the neural network model based on the predicted classification of the training set and the label of the training set; and iteratively training the neural network model based on the loss value until a preset convergence condition is reached to obtain the trained neural network model.

[0015] In one embodiment, inputting the training set into the neural network model to obtain the predicted classification of the training set includes: inputting the training set into the neural network model to obtain the predicted probability of abnormal discharge in the training sample; and determining the predicted classification of the training sample based on the predicted probability of abnormal discharge in the training sample.

[0016] In one embodiment, the neural network model is iteratively trained according to the loss value until a preset convergence condition is reached to obtain the trained neural network model, including: updating model parameters of the neural network model according to the loss value; the model parameters include weights and biases; when the loss value meets the preset convergence condition, the training is terminated to obtain the trained neural network model.

[0017] In one embodiment, the method further includes: preprocessing the electrical signal to be measured; the preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

[0018] According to a second aspect of the present disclosure, there is provided an apparatus for detecting abnormal discharges between epileptic seizures, the apparatus comprising: a data acquisition module, configured to acquire electrical signals to be tested from a target user; the electrical signals to be tested comprise electroencephalogram (EEG) signals, electrocardiogram (ECG) signals and electromyography (EMG) signals; a probability prediction module, configured to input the electrical signals to be tested into a trained neural network model for processing, and output a predicted probability of abnormal discharges in the electrical signals to be tested; the trained neural network model is obtained by training a training set; the training set comprises a plurality of training samples; the training samples comprise electrical signals of epileptic patients with abnormal discharges between seizures and corresponding labels, electrical signals of epileptic patients without abnormal discharges between seizures and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals of epileptic patients with abnormal discharges between seizures are electrical signals excluding suspected abnormal discharges in electroencephalogram (EEG) signals caused by electrocardiogram (ECG) signals and / or electromyography (EMG) signals.

[0019] In one embodiment, the probability prediction module is further configured to: perform short-time Fourier transform on the electrical signal to be tested to obtain time-frequency data of the electrical signal to be tested; and input the time-frequency data of the electrical signal to be tested into the trained neural network model for processing.

[0020] In one embodiment, the trained neural network model includes three tower layers, and the three tower layers include an EEG signal tower, an EEG signal tower, and an EMG signal tower; the probability prediction module is also configured to: input the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; input the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; input the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; input the EMG signal into the EMG signal tower to obtain a feature vector of the EMG signal.

[0021] In one embodiment, the trained neural network model also includes an aggregation layer, and the probability prediction module is further configured to: input the feature vector of the EEG signal, the feature vector of the ECG signal, and the feature vector of the EMG signal output by the three-tower layer into the aggregation layer for splicing to obtain a feature map.

[0022] In one embodiment, the trained neural network model also includes a bottom layer, and the probability prediction module is further configured to: input the feature map output by the aggregation layer into the bottom layer for feature extraction and classification to obtain the predicted probability of abnormal discharge in the electrical signal to be tested.

[0023] In one embodiment, the device also includes a model training module, which is configured to: obtain a training set; the training set includes multiple training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during interictal attacks and corresponding labels, electrical signals of epileptic patients without abnormal discharges during interictal attacks and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; input the training set into a neural network model to obtain a predicted classification of the training set; the predicted classification includes positive or negative; the positive indicates that the training sample has abnormal discharges, and the negative indicates that the training sample does not have abnormal discharges; determine the loss value of the neural network model based on the predicted classification of the training set and the label of the training set; and iteratively train the neural network model based on the loss value until a preset convergence condition is reached to obtain the trained neural network model.

[0024] In one embodiment, the model training module is configured to: input the training set into the neural network model to obtain the predicted probability of abnormal discharge in the training sample; and determine the predicted classification of the training sample based on the predicted probability of abnormal discharge in the training sample.

[0025] In one embodiment, the model training module is configured to: update the model parameters of the neural network model according to the loss value; the model parameters include weights and biases; when the loss value meets a preset convergence condition, end the training to obtain the trained neural network model.

[0026] In one embodiment, the device further includes a data preprocessing module, which is configured to: preprocess the electrical signal to be measured; the preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

[0027] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above methods is implemented.

[0028] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above methods by executing the executable instructions.

[0029] According to the abnormal discharge detection method during epileptic seizures, the abnormal discharge detection device during epileptic seizures, the computer-readable storage medium and the electronic device of the embodiment of the present disclosure, the target user's electrical signal to be tested is obtained; the electrical signal to be tested includes an electroencephalogram signal, an electrocardiogram signal and an electromyogram signal; the electrical signal to be tested is input into the trained neural network model for processing, and the predicted probability of abnormal discharge of the electrical signal to be tested is output; the trained neural network model is obtained by training the training set; the training set includes multiple training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals that exclude suspected abnormal discharges in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal. In this way, by learning the electrocardiogram signal and the electromyogram signal, the model can avoid judging the suspected abnormal discharges in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal as positive; thereby, the accuracy of positive recognition can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0031] Figure 1 A schematic diagram of an abnormal discharge detection process architecture during an epileptic seizure period in an embodiment of the present disclosure is shown;

[0032] Figure 2 A flow chart showing a method for detecting abnormal discharges between epileptic seizures in an embodiment of the present disclosure is shown;

[0033] Figure 3 A structural diagram showing a trained neural network model in a method for detecting abnormal discharges between epileptic seizures in an embodiment of the present disclosure;

[0034] Figure 4 A flowchart showing a neural network model training method in an abnormal discharge detection method between epileptic seizures in an embodiment of the present disclosure is shown;

[0035] Figure 5 A flowchart showing the classification of a training set during the training of a neural network model in a method for detecting abnormal discharges between epileptic seizures in an embodiment of the present disclosure is shown;

[0036] Figure 6 A flowchart showing updating model parameters in the process of training a neural network model in a method for detecting abnormal discharges between epileptic seizures in an embodiment of the present disclosure is shown;

[0037] Figure 7 A schematic diagram showing the structure of an abnormal discharge detection device during epileptic seizures in an embodiment of the present disclosure is shown;

[0038] Figure 8 A schematic structural diagram of an electronic device in an embodiment of the present disclosure is shown.

[0039] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0040] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0041] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0042] According to an embodiment of the present disclosure, a method for detecting abnormal discharges during epileptic seizures, a device for detecting abnormal discharges during epileptic seizures, a computer-readable storage medium, and an electronic device are provided.

[0043] In this document, any number of elements in the drawings is used for illustration rather than limitation, and any naming is used only for distinction and does not have any limiting meaning.

[0044] The principle and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure. SUMMARY OF THE INVENTION

[0046] Epilepsy is a chronic neurological disease characterized by sudden abnormal brain reactions and recurrences. It is caused by abnormal activity of brain neurons. This epileptic seizure caused by excessive discharge of neurons is usually accompanied by disorders of movement, sensation, emotion or mental function. Once this sudden neurological disease occurs, the patient's brain will stop working normally, resulting in abnormal reactions such as fainting, body imbalance, convulsions, muscle contractions, loss of consciousness and intuition. For any epilepsy patient, epileptic seizures have a great impact on all aspects of the patient's and his family's life, and may even endanger the patient's life.

[0047] Electroencephalogram (EEG) is a non-invasive signal acquisition method used to clinically record brain-related activities. It has a high temporal resolution and plays an important role in the detection, diagnosis, treatment, efficacy evaluation and pathological research of epilepsy. At present, the diagnosis of epilepsy based on EEG is mainly the detection of epileptic seizures, however, epileptic seizures are not common. In contrast, nearly 80% of epilepsy patients have abnormal neuronal discharges between seizures. These abnormal discharges observable in EEG are called interictal epileptiform discharges (IEDs). IEDs are a strong support for epilepsy diagnosis or epileptic seizure risk assessment.

[0048] Unlike epileptic seizures, IEDs are more frequent and appear in EEG in various forms, such as spike waves, sharp waves, spike-slow complexes, polyspike-wave complexes, etc. They exist in EEG for different durations (the shortest is only 20-70ms, and the longest lasts more than 1s).

[0049] In the related technologies, most of them collect EEG and determine the interval between epileptic seizures of epileptic patients by observing IED in EEG; however, the IED in the collected EEG may be caused by electrocardiography and / or electromyography, and determining the interval between epileptic seizures of epileptic patients by only observing IED in EEG is prone to false positive phenomenon.

[0050] In view of the above, the present disclosure provides a method for detecting abnormal discharges during epileptic seizures, an abnormal discharge detection device during epileptic seizures, a computer-readable storage medium and an electronic device. First, the target user's electrical signal to be tested is obtained; the electrical signal to be tested includes an electroencephalogram signal, an electrocardiogram signal and an electromyogram signal; secondly, the electrical signal to be tested is input into a trained neural network model for processing, and the predicted probability of abnormal discharge of the electrical signal to be tested is output; the trained neural network model is obtained by training a training set; the training set includes multiple training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals that exclude suspected abnormal discharges in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal. In this way, by learning the electrocardiogram signal and the electromyogram signal, the model can avoid judging the suspected abnormal discharges in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal as positive; thereby, the accuracy of positive recognition can be improved.

[0051] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0052] Application Scenario Overview

[0053] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0054] The present disclosure can be applied to any scenario where it is necessary to identify abnormal discharges between seizures of epileptic patients, such as: obtaining the target user's test signal; the test signal includes an electroencephalogram signal, an electrocardiogram signal and an electromyogram signal; then the test signal is input into a trained neural network model for processing, and the predicted probability of abnormal discharge of the test signal is output; the trained neural network model is obtained by training a training set; the training set includes multiple training samples; the training samples include the electrical signal of abnormal discharge between seizures of epileptic patients and the corresponding label, the electrical signal of no abnormal discharge between seizures of epileptic patients and the corresponding label, the electrical signal of non-epileptic patients and the corresponding label; the electrical signal of abnormal discharge between seizures of epileptic patients is the electrical signal that excludes the suspected abnormal discharge in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal. In this way, by learning the electrocardiogram signal and the electromyogram signal, the model can avoid judging the suspected abnormal discharge in the electroencephalogram signal caused by the electrocardiogram signal and / or the electromyogram signal as positive; thereby, the accuracy of positive identification can be improved.

[0055] Exemplary Methods

[0056] Combine the following Figure 1 The system architecture and application scenarios of the operating environment of this exemplary embodiment are exemplarily described.

[0057] Figure 1A schematic diagram of a system architecture is shown, wherein the system architecture 100 may include an abnormal discharge detection device 110 during epileptic seizures, and the abnormal discharge detection device 110 during epileptic seizures may be a server or a cluster formed by multiple servers; the abnormal discharge detection device 110 during epileptic seizures obtains an electrical signal to be tested from a target user; the electrical signal to be tested includes an electroencephalogram (EEG) signal, an electrocardiogram (ECG) signal, and an electromyogram (EMG) signal; the electrical signal to be tested is then input into a trained neural network model for processing, and a predicted probability of abnormal discharge in the electrical signal to be tested is output; the trained neural network model is obtained by training a training set; the training set includes multiple training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during seizures and corresponding labels, electrical signals of epileptic patients without abnormal discharges during seizures and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; electrical signals of epileptic patients with abnormal discharges during seizures are electrical signals that exclude suspected abnormal discharges in the electroencephalogram (EEG) signal caused by an electrocardiogram (ECG) signal and / or an electromyogram (EMG) signal. In this way, by learning the ECG signals and EMG signals, the model can avoid judging the suspected abnormal discharges in the EEG signals caused by the ECG signals and / or EMG signals as positive; thereby, the accuracy of positive identification can be improved.

[0058] The exemplary embodiment of the present disclosure first provides a method for detecting abnormal discharges between epileptic seizures, which may include:

[0059] Acquire the target user's electrical signals to be tested; the electrical signals to be tested include brain electroencephalogram signals, electrocardiogram signals and myoelectric signals;

[0060] The electrical signal to be tested is input into the trained neural network model for processing, and the predicted probability of abnormal discharge of the electrical signal to be tested is output; the trained neural network model is obtained by training a training set; the training set includes multiple training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals that exclude suspected abnormal discharges in electroencephalogram signals caused by electrocardiogram signals and / or electromyography signals.

[0061] Figure 2 The exemplary process of the abnormal discharge detection method between epileptic seizures is shown below. Figure 2 Each step in the procedure is described in detail.

[0062] refer to Figure 2 In step S210, the electrical signal to be tested of the target user is obtained.

[0063] The electrical signals to be measured include electroencephalogram signals, electrocardiogram signals and electromyography signals.

[0064] The electrical signal to be tested is an electrical signal collected from the object to be tested. The electrical signal is an active signal spontaneously generated by the physiological process of the living body, which can more accurately reflect the physiological state or physical state of the person, so that the electrical signal can be used to determine whether the living body is abnormal. Exemplarily, the above-mentioned biomedical signals may include any one or more of the following: EEG signals, ECG signals, and EMG signals.

[0065] EEG signals can be electroencephalograms (EEGs) collected by multi-channel brain machines. EEGs are graphs obtained by amplifying and recording the spontaneous biopotentials of the cerebral cortex from the scalp using sophisticated instruments. They are spontaneous, rhythmic electrical activities of brain cell groups recorded by electrodes. This type of electrical activity is a plane diagram of the relationship between the potential and time, with the potential as the vertical axis and time as the horizontal axis. The frequency (period), amplitude, and phase of brain waves constitute the basic characteristics of EEGs.

[0066] The ECG signal can be an electrocardiogram collected by a multi-lead electrocardiogram machine. An electrocardiogram (ECG) refers to a graph of various potential changes drawn from the body surface by an electrocardiograph, with the pacemaker, atrium, and ventricle being excited successively in each cardiac cycle, accompanied by changes in the electrocardiogram bioelectricity. The electrocardiogram is an objective indicator of the occurrence, propagation, and recovery process of cardiac excitement.

[0067] Electromyography (EMG) is the superposition of action potentials of motor units in numerous muscle fibers in time and control, which can be obtained by sticking electromyography sensors on the skin.

[0068] Continue to refer Figure 2 In step S220, the electrical signal to be tested is input into the trained neural network model for processing, and the predicted probability of abnormal discharge in the electrical signal to be tested is output.

[0069] Among them, the training set includes multiple training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals that exclude suspected abnormal discharges in the EEG signals caused by ECG signals and / or EMG signals.

[0070] Exemplarily, the neural network model may include an input layer (INPUT), three tower layers (eeg block+ecg block+emg block), an aggregation layer (aggregate), a bottom block (bottom block), and an output layer (OUTPUT); wherein the input layer is used to obtain the electrical signal to be tested in this step; the three tower layers are used to perform feature extraction on the EEG signal, ECG signal, and EMG signal in the electrical signal to be tested obtained by the input layer, respectively, to obtain respective feature vectors; the aggregation layer is used to concatenate the feature vectors output by the three tower layers to obtain a feature map; the bottom block is used to perform feature extraction and classification on the feature map output by the aggregation layer, to obtain the predicted probability of abnormal discharge in the electrical signal to be tested and the predicted probability of no abnormal discharge in the electrical signal to be tested; the output layer is used to output the predicted probability of abnormal discharge in the electrical signal to be tested. Exemplarily, the neural network model may be trained to obtain the above-mentioned trained neural network model. Exemplarily, refer to Figure 3 , the structure of the trained neural network model is consistent with that of the neural network model.

[0071] The electrical signals and corresponding labels of abnormal discharges in the interictal period of epileptic patients can be regarded as positive samples, and the electrical signals and corresponding labels of no abnormal discharges in the interictal period of epileptic patients and the electrical signals and corresponding labels of non-epileptic patients can be regarded as negative samples; illustratively, the electrical signals and corresponding labels of abnormal discharges in the interictal period of epileptic patients are obtained by professional staff through identification and labeling of EEG signals, ECG signals, and EMG signals collected in the same period of time based on professional knowledge. In this way, electrical signals suspected of abnormal discharges in EEG signals caused by ECG signals and / or EMG signals can be excluded, and then the electrical signals and corresponding labels of abnormal discharges in the interictal period of epileptic patients are obtained.

[0072] In one embodiment, different electrical signals included in the electrical signal to be tested need to be processed separately; specifically, the trained neural network model includes a three-tower structure, and the three towers include an electroencephalogram signal tower, an electrocardiogram signal tower, and an electromyography signal tower. The "inputting the electrical signal to be tested into the trained neural network model for processing" in the above step S220 may further include the following steps:

[0073] The EEG signal is input into the EEG signal tower to obtain the feature vector of the EEG signal.

[0074] The EEG signal tower is used to extract features from the EEG signal to obtain a feature vector of the EEG signal; further, when the EEG signal is a multi-channel EEG signal, the EEG signals of multiple channels can be sequentially input into the EEG signal tower, and the features of the EEG signals of multiple channels can be sequentially extracted to obtain feature vectors of the EEG signals of multiple channels. Figure 3, eeg block is the above-mentioned EEG signal tower. Input n_eeg channels in eeg into eeg block in sequence to obtain n_eeg feature vectors.

[0075] Input the ECG signal into the ECG signal tower to obtain the feature vector of the ECG signal.

[0076] Among them, the ECG signal tower is used to extract features from the ECG signal to obtain a feature vector of the ECG signal; further, when the ECG signal is a multi-channel ECG signal, the ECG signals of multiple channels can be sequentially input into the ECG signal tower, and the features of the ECG signals of multiple channels are sequentially extracted to obtain feature vectors of the ECG signals of multiple channels. For example, reference Figure 3 , ecg block is the above-mentioned ECG signal tower. Input n_ecg channels in ecg into ecg block in sequence to obtain n_ecg feature vectors.

[0077] The electromyographic signal is input into the electromyographic signal tower to obtain the characteristic vector of the electromyographic signal.

[0078] The EMG signal tower is used to extract features from the EMG signal to obtain a feature vector of the EMG signal; further, when the EMG signal is a multi-channel EMG signal, the EMG signals of multiple channels can be sequentially input into the EMG signal tower, and feature extraction is performed on the EMG signals of multiple channels in sequence to obtain feature vectors of the EMG signals of multiple channels. Figure 3 , emg block is the above-mentioned electromyographic signal tower. Input n_emg channels in emg into emg block in sequence to obtain n_emg feature vectors.

[0079] It should be noted that the EEG signal tower, ECG signal tower and EMG signal tower are three parallel feature extraction networks, which are independent of each other and do not affect each other; these three signal layers are obtained by learning the features of EEG signals, ECG signals and EMG signals.

[0080] In one embodiment, the trained neural network model further includes an aggregation layer; specifically, the “inputting the electrical signal to be tested into the trained neural network model for processing” in the above step S220 may further include the following steps:

[0081] The feature vectors of the EEG signal, the EKG signal and the EMG signal output by the three-tower layer are input into the aggregation layer for splicing to obtain a feature map.

[0082] Vector concatenation, that is, connecting two or more vectors in a certain order to form a longer vector, can be done horizontally or vertically. For example, there are two vectors A = [1, 2, 3] and B = [4, 5, 6]. If they are concatenated horizontally, the result is C = [1, 2, 3, 4, 5, 6]. If they are concatenated vertically, the result is

[0083] Exemplary, reference Figure 3 , aggregate is the above aggregation layer, which concatenates the n_eeg, n_ecg and n_emg feature vectors output by the three tower layers to obtain the feature map.

[0084] In one embodiment, the trained neural network model further includes a bottom layer; specifically, the “inputting the electrical signal to be tested into the trained neural network model for processing” in the above step S220 may further include the following steps:

[0085] The feature map output by the aggregation layer is input into the bottom layer, and the bottom layer is used to extract and classify the feature map to obtain the predicted probability of the positive electrical signal to be tested.

[0086] Among them, the bottom layer may include a convolutional layer, a pooling layer, a fully connected layer, and a classification layer; among them, the pooling layer may include an average pooling layer or a maximum pooling layer.

[0087] The abnormal discharge detection method during epileptic seizures in the embodiment of the present invention is used to predict the probability of abnormal discharge in the electrical signal to be tested. Therefore, the classification layer in the trained neural network model can be a binary classifier; specifically, the electrical signal with abnormal discharge during the interictal period of epileptic patients is a positive sample, and its label is "positive"; the electrical signal without abnormal discharge during the interictal period of epileptic patients and the electrical signal of non-epileptic patients are negative samples, and their labels are all "negative"; that is, there are two labels (two categories), and the number of nodes of the classification layer softmax is 2. During the training process, the classification layer softmax can map the feature data output by the fully connected layer to the probability of belonging to these two categories.

[0088] Exemplary, reference Figure 3 , bottom block is the bottom layer mentioned above, the feature map output by aggregate is input into the bottom block, the feature map is extracted and classified, and the predicted probability of the tested electrical signal being positive and the predicted probability of being negative are obtained.

[0089] In one implementation, the electrical signal to be measured may be processed for ease of analysis; specifically, refer to Figure 3 After the above step S210, the method for detecting abnormal discharges during epileptic seizures may further include the following steps:

[0090] Perform short-time Fourier transform on the electrical signal to be measured to obtain time-frequency data of the electrical signal to be measured.

[0091] Among them, the short-time Fourier transform (STFT) is a time-frequency analysis method that decomposes the signal in time and frequency and can analyze the short-time changes of the signal. Compared with the Fourier transform, the short-time Fourier transform can capture the local characteristics of the signal in time and frequency. Therefore, the short-time Fourier transform is more suitable for analyzing non-stationary signals.

[0092] When performing short-time Fourier transform, you first need to select a suitable window function to segment the signal. Commonly used window functions include Hanning window, rectangular window, Gaussian window, etc. The choice of window function should be determined according to the actual application scenario and characteristics to maximize the retention of the signal's spectral information.

[0093] Then, the window function is applied to each time period of the signal, and the signal within each window is Fourier transformed. In this way, the spectrum information of each time period can be obtained. Usually, in order to reduce the amount of calculation, you can choose to use the fast Fourier transform algorithm for calculation.

[0094] The obtained spectrum information can be represented as a two-dimensional matrix, where the horizontal axis represents time and the vertical axis represents frequency. Each element in the matrix represents the signal energy at the corresponding time and frequency. By visualizing this matrix, the changes of the signal in time and frequency can be observed more intuitively.

[0095] Correspondingly, the “inputting the electrical signal to be tested into the trained neural network model for processing” in the above step S220 may further include the following steps:

[0096] The time-frequency data of the electrical signal to be measured is input into the trained neural network model for processing.

[0097] The video data of the electrical signal to be tested is input into the trained neural network model for processing, so as to facilitate the analysis of the electrical signal to be tested. The specific processing process is consistent with the processing process of the trained neural network model, and will not be repeated here.

[0098] In one implementation, the neural network model is trained to obtain a trained neural network model; specifically, refer to Figure 4 , training the trained neural network model may further include the following steps S410 to 440:

[0099] Step S410: Obtain a training set.

[0100] The training set includes multiple training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during the interictal period and corresponding labels, electrical signals of epileptic patients without abnormal discharges during the interictal period and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels.

[0101] A training set can be obtained from an open source dataset. When there is no corresponding open source dataset for the electrical signal to be tested, manual labeling can be performed. Specifically, a certain number of electrical signals can be randomly selected from the obtained electrical signals as sample signals, and then the category corresponding to each sample signal can be labeled to generate sample signals and corresponding labels, thereby obtaining a training set.

[0102] Generally speaking, the more sample signals there are, the more accurate the model training results will be; but at the same time, the training time will be longer. Therefore, users can determine the appropriate number of sample signals according to their needs.

[0103] Exemplarily, the electrical signals and corresponding labels of abnormal discharges during the interictal period of epileptic patients are taken as positive samples, and the electrical signals and corresponding labels of no abnormal discharges during the interictal period of epileptic patients, and the electrical signals and corresponding labels of non-epileptic patients are taken as negative samples; wherein, the electrical signals and corresponding labels of abnormal discharges during the interictal period of epileptic patients are obtained by professional staff through identification and labeling of EEG signals, ECG signals, and EMG signals collected within the same period of time based on professional knowledge. In this way, electrical signals suspected of abnormal discharges in EEG signals caused by ECG signals and / or EMG signals can be excluded, and then, the electrical signals and corresponding labels of abnormal discharges during the interictal period of epileptic patients are obtained.

[0104] Step S420: input the training set into the neural network model to obtain the predicted classification of the training set.

[0105] Among them, the prediction classification includes positive or negative; positive means that the training sample has abnormal discharge, and negative means that the training sample does not have abnormal discharge.

[0106] Exemplarily, the neural network model may include an input layer, a three-tower layer, an aggregation layer, a bottom layer, and an output layer; specifically, the three-tower layer may include an EEG signal tower, an ECG signal tower, and an EMG signal tower; wherein the EEG signal tower is used to extract features from EEG signals, the ECG signal tower is used to extract features from ECG signals, and the EMG signal tower is used to extract features from EMG signals to obtain respective feature vectors; the aggregation layer is used to concatenate the feature vectors output by the three-tower layer to obtain a feature map; the bottom layer is used to extract and classify the feature map output by the aggregation layer to obtain the predicted classification results of the training set; the output layer is used to output the predicted classification results of the training set.

[0107] Exemplarily, the electrical signals of epileptic patients with abnormal discharges during the interictal period and the corresponding labels are used as positive samples, and the electrical signals of epileptic patients without abnormal discharges during the interictal period and the corresponding labels, and the electrical signals of non-epileptic patients and the corresponding labels are used as negative samples to train the neural network model, that is, the classifier in the neural network model is a binary classifier, and then, a positive prediction result or a negative prediction result is output.

[0108] Step S430: Determine the loss value of the neural network model according to the predicted classification of the training set and the label of the training set.

[0109] Among them, the prediction accuracy of the training set can be determined according to the prediction results of the training set and the label of the training set, and then the prediction accuracy of the training set can be subtracted from 1 to obtain the loss value of the neural network model; the loss value of the neural network model can also be determined based on the model output results and the label of the training set by using a loss function. For example, the loss of each iterative training can be calculated according to the cross entropy loss function.

[0110] Step S440: Iteratively train the neural network model according to the loss value until a preset convergence condition is reached to obtain a trained neural network model.

[0111] Among them, the preset convergence condition is an iteration number threshold or a loss value threshold set according to historical data or experience; then, when the iteration number threshold or the loss value threshold is reached, the iterative training is ended to obtain a trained neural network model.

[0112] In one embodiment, the above-mentioned prediction classification result is obtained based on the prediction probability; specifically, refer to Figure 5 , the above step 420 may further include the following steps S510 and S520:

[0113] Step S510: input the training set into the neural network model to obtain the predicted probability of abnormal discharge in the training sample.

[0114] Among them, the bottom layer may include a convolutional layer, a pooling layer, a fully connected layer, and a classification layer; among them, the pooling layer may include an average pooling layer or a maximum pooling layer.

[0115] As before, the training samples include the electrical signals of epileptic patients with abnormal discharges during the interictal period and the corresponding labels, the electrical signals of epileptic patients without abnormal discharges during the interictal period and the corresponding labels, and the electrical signals of non-epileptic patients and the corresponding labels; among them, the electrical signals of epileptic patients with abnormal discharges during the interictal period are positive samples, and their labels are "positive"; the electrical signals of epileptic patients without abnormal discharges during the interictal period and the electrical signals of non-epileptic patients are negative samples, and their labels are all "negative"; that is, there are two labels (two categories), and the number of nodes of the classification layer softmax is 2. During the training process, the classification layer softmax can map the feature data output by the fully connected layer to the probability of belonging to these two categories.

[0116] Step S520: Determine the predicted classification of the training sample according to the predicted probability of abnormal discharge in the training sample.

[0117] As before, after the classification layer softmax maps the feature data output by the fully connected layer into probabilities of belonging to positive and negative, the output layer output can select the category with the highest probability as the predicted category of the input training sample.

[0118] In one embodiment, the trained neural network model is obtained by continuously adjusting the parameters of the model; specifically, refer to Figure 6 , the above step S440 may further include the following steps S610 and S620:

[0119] Step S610: Update the model parameters of the neural network model according to the loss value.

[0120] Among them, model parameters include weights and biases.

[0121] Specifically, the weights and biases of the neural network can be updated using a back-propagation algorithm based on the loss value.

[0122] Step S620: When the loss value meets the preset convergence condition, the training is terminated to obtain a trained neural network model.

[0123] Among them, the preset convergence condition is an iteration number threshold or a loss value threshold set according to historical data or experience; then, when the iteration number threshold or the loss value threshold is reached, the iterative training is ended to obtain a trained neural network model.

[0124] In actual operation, the test data can also be used to further test the neural network model trained by the training set. After the test passes, the neural network model that passes the test is used as a trained neural network model.

[0125] In one embodiment, in order to improve the accuracy of data analysis, the data may be preprocessed; specifically, the above-mentioned abnormal discharge detection method during epileptic seizures may further include the following steps:

[0126] Preprocess the electrical signal to be measured.

[0127] The preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

[0128] Resampling refers to repeatedly drawing samples from the training set; these samples are then used to refit a specific model to retrieve more information about the fitted model. The goal is to collect more information about the samples, improve accuracy, and estimate uncertainty.

[0129] Filtering is to filter out a specific frequency point or frequencies outside the frequency point to obtain a power signal with a specific frequency, or to eliminate a power signal with a specific frequency.

[0130] Denoising refers to removing noise from a signal; it can be done by moving average, median filtering, wavelet transform, and adaptive filtering.

[0131] Numerical standardization refers to the conversion of original data into dimensionless indicator evaluation values ​​through certain mathematical transformations. That is, all indicator values ​​are at the same quantitative level, which is conducive to comprehensive analysis and comparison. Numerical standardization can be carried out by standardization, normalization, centralization and other methods.

[0132] Segmentation refers to segmenting the electrical signals collected within a period of time according to certain time intervals to obtain more sample data or electrical signals to be tested.

[0133] Exemplary Devices

[0134] After introducing the abnormal discharge detection method between epileptic seizures according to the exemplary embodiment of the present disclosure, next, referring to Figure 7 An apparatus for detecting abnormal discharges between epileptic seizures according to an exemplary embodiment of the present disclosure will be described.

[0135] refer to Figure 7As shown, an abnormal discharge detection device 700 during epileptic seizures includes: a data acquisition module 710, configured to acquire the target user's electrical signals to be tested; the electrical signals to be tested include electroencephalogram signals, electrocardiogram signals and electromyogram signals; a probability prediction module 720, configured to input the electrical signals to be tested into a trained neural network model for processing, and output a predicted probability of abnormal discharge in the electrical signals to be tested; the trained neural network model is obtained by training a training set; the training set includes a plurality of training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during the seizures and corresponding labels, electrical signals of epileptic patients without abnormal discharges during the seizures and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; electrical signals of epileptic patients with abnormal discharges during the seizures are electrical signals excluding suspected abnormal discharges in the electroencephalogram signals caused by electrocardiogram signals and / or electromyogram signals.

[0136] In one embodiment, the probability prediction module 720 is further configured to: perform short-time Fourier transform on the electrical signal to be tested to obtain time-frequency data of the electrical signal to be tested; and input the time-frequency data of the electrical signal to be tested into the trained neural network model for processing.

[0137] In one embodiment, the trained neural network model includes three tower layers, which include an EEG signal tower, an ECG signal tower, and an EMG signal tower; the probability prediction module 720 is also configured to: input the EEG signal into the EEG signal tower to obtain a feature vector of the EEG signal; input the ECG signal into the ECG signal tower to obtain a feature vector of the ECG signal; input the EMG signal into the EMG signal tower to obtain a feature vector of the EMG signal.

[0138] In one embodiment, the trained neural network model also includes an aggregation layer, and the probability prediction module 720 is further configured to: input the feature vectors of the EEG signal, the feature vectors of the ECG signal, and the feature vectors of the EMG signal output by the three tower layers into the aggregation layer for splicing to obtain a feature map.

[0139] In one embodiment, the trained neural network model also includes a bottom layer, and the probability prediction module 720 is further configured to: input the feature map output by the aggregation layer into the bottom layer for feature extraction and classification to obtain the predicted probability of abnormal discharge in the electrical signal to be tested.

[0140] In one embodiment, the device also includes a model training module, which is configured to: obtain a training set; the training set includes multiple training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during interictal attacks and corresponding labels, electrical signals of epileptic patients without abnormal discharges during interictal attacks and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; input the training set into the neural network model to obtain a predicted classification of the training set; the predicted classification includes positive or negative; positive indicates that the training sample has abnormal discharges, and negative indicates that the training sample does not have abnormal discharges; determine the loss value of the neural network model based on the predicted classification of the training set and the label of the training set; based on the loss value, iteratively train the neural network model until a preset convergence condition is reached to obtain a trained neural network model.

[0141] In one embodiment, the model training module is configured to: input the training set into the neural network model to obtain the predicted probability of abnormal discharge in the training sample; and determine the predicted classification of the training sample based on the predicted probability of abnormal discharge in the training sample.

[0142] In one embodiment, the model training module is configured to: update the model parameters of the neural network model according to the loss value; the model parameters include weights and biases; when the loss value meets the preset convergence conditions, end the training and obtain a trained neural network model.

[0143] In one embodiment, the device further includes a data preprocessing module, which is configured to: preprocess the electrical signal to be measured; the preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

[0144] Exemplary Storage Media

[0145] The storage medium according to the exemplary embodiment of the present disclosure is described below.

[0146] In this exemplary embodiment, the above method can be implemented by a program product, such as a portable compact disk read-only memory (CD-ROM) and including program code, and can be run on a device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus, or a device.

[0147] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0148] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0149] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RE, etc., or any suitable combination of the foregoing.

[0150] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0151] Exemplary Electronic Devices

[0152] refer to Figure 8 An electronic device according to an exemplary embodiment of the present disclosure is described.

[0153] Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0154] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0155] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 1 The method steps shown, etc.

[0156] The storage unit 820 may include a volatile storage unit, such as a random access storage unit (RAM) 821 and / or a cache storage unit 822 , and may further include a read-only storage unit (ROM) 823 .

[0157] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, such program modules 825 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0158] The bus 830 may include a data bus, an address bus, and a control bus.

[0159] The electronic device 800 can also communicate with one or more external devices 2000 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), and this communication can be performed through an input / output (I / O) interface 850. The electronic device 800 also includes a display unit 840, which is connected to the input / output (I / O) interface 850 for display. In addition, the electronic device 800 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter 860. As shown in the figure, the network adapter 860 communicates with other modules of the electronic device 800 through a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0160] It should be noted that, although several modules or submodules of the device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0161] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0162] Although the spirit and principle of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A method for detecting abnormal discharges between epileptic seizures, characterized in that: The method comprises: Acquire the target user's electrical signal to be tested; the electrical signal to be tested includes an electroencephalogram signal, an electrocardiogram signal, and an electromyography signal; The electrical signal to be tested is input into a trained neural network model for processing, and a predicted probability of abnormal discharge in the electrical signal to be tested is output; the trained neural network model is obtained by training a training set; the training set includes a plurality of training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals excluding the suspected abnormal discharges in the EEG signals caused by the EEG signals and / or the EMG signals; The trained neural network model includes three tower layers, including an EEG signal tower, an EKG signal tower and an EMG signal tower; the EEG signal tower is used to obtain a feature vector of the EEG signal according to the input EEG signal; the EKG signal tower is used to obtain a feature vector of the EKG signal according to the input EKG signal; the EMG signal tower is used to obtain a feature vector of the EMG signal according to the input EMG signal; and the EMG signal tower is used to obtain a feature vector of the EMG signal according to the input EMG signal. The trained neural network model further includes an aggregation layer, which is used to concatenate the input feature vectors of the EEG signal, the EKG signal, and the EMG signal to obtain a feature map; The trained neural network model also includes a bottom layer, which is used to extract and classify the input feature map to obtain a predicted probability of abnormal discharge in the electrical signal to be tested.

2. The method according to claim 1, characterized in that After obtaining the electrical signal to be tested from the target user, the method further includes: Performing short-time Fourier transform on the electrical signal to be measured to obtain time-frequency data of the electrical signal to be measured; Correspondingly, the step of inputting the electrical signal to be tested into the trained neural network model for processing includes: The time-frequency data of the electrical signal to be measured is input into the trained neural network model for processing.

3. The method according to claim 1, characterized in that Training the trained neural network model includes: Acquire a training set; the training set includes a plurality of training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during the interictal period and corresponding labels, electrical signals of epileptic patients without abnormal discharges during the interictal period and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; Inputting the training set into a neural network model to obtain a predicted classification of the training set; the predicted classification includes positive or negative; the positive indicates that the training sample has abnormal discharge, and the negative indicates that the training sample does not have abnormal discharge; Determining a loss value of the neural network model according to the predicted classification of the training set and the label of the training set; According to the loss value, the neural network model is iteratively trained until a preset convergence condition is reached to obtain the trained neural network model.

4. The method according to claim 3, characterized in that The step of inputting the training set into a neural network model to obtain a predicted classification of the training set includes: Inputting the training set into the neural network model to obtain a predicted probability of abnormal discharge in the training sample; The predicted classification of the training sample is determined according to the predicted probability that the training sample has abnormal discharge.

5. The method according to claim 3, characterized in that: The iterative training of the neural network model according to the loss value until a preset convergence condition is reached to obtain the trained neural network model includes: According to the loss value, updating the model parameters of the neural network model; the model parameters include weights and biases; When the loss value meets the preset convergence condition, the training is terminated to obtain the trained neural network model.

6. The method according to claim 1, characterized in that The method further comprises: The electrical signal to be tested is preprocessed; the preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

7. A device for detecting abnormal discharges between epileptic seizures, characterized in that: The device comprises: A data acquisition module is configured to acquire the target user's electrical signals to be tested; the electrical signals to be tested include brain electroencephalogram signals, electrocardiogram signals and myoelectric signals; The probability prediction module is configured to input the electrical signal to be tested into a trained neural network model for processing, and output a predicted probability that the electrical signal to be tested has abnormal discharge; the trained neural network model is obtained by training a training set; the training set includes a plurality of training samples; the training samples include electrical signals with abnormal discharges during the interictal period of epileptic patients and corresponding labels, electrical signals without abnormal discharges during the interictal period of epileptic patients and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; the electrical signals with abnormal discharges during the interictal period of epileptic patients are electrical signals that exclude suspected abnormal discharges in the EEG signals caused by the EEG signals and / or the EMG signals; The trained neural network model includes three tower layers, including an EEG signal tower, an EKG signal tower and an EMG signal tower; the EEG signal tower is used to obtain a feature vector of the EEG signal according to the input EEG signal; the EKG signal tower is used to obtain a feature vector of the EKG signal according to the input EKG signal; the EMG signal tower is used to obtain a feature vector of the EMG signal according to the input EMG signal; and the EMG signal tower is used to obtain a feature vector of the EMG signal according to the input EMG signal. The trained neural network model further includes an aggregation layer, which is used to concatenate the input feature vectors of the EEG signal, the EKG signal, and the EMG signal to obtain a feature map; The trained neural network model also includes a bottom layer, which is used to extract and classify the input feature map to obtain a predicted probability of abnormal discharge in the electrical signal to be tested.

8. The device according to claim 7, characterized in that The probability prediction module is further configured to: Performing short-time Fourier transform on the electrical signal to be measured to obtain time-frequency data of the electrical signal to be measured; The time-frequency data of the electrical signal to be measured is input into the trained neural network model for processing.

9. The device according to claim 7, characterized in that The device also includes a model training module, which is configured to: Acquire a training set; the training set includes a plurality of training samples; the training samples include electrical signals of epileptic patients with abnormal discharges during the interictal period and corresponding labels, electrical signals of epileptic patients without abnormal discharges during the interictal period and corresponding labels, and electrical signals of non-epileptic patients and corresponding labels; Inputting the training set into a neural network model to obtain a predicted classification of the training set; the predicted classification includes positive or negative; the positive indicates that the training sample has abnormal discharge, and the negative indicates that the training sample does not have abnormal discharge; Determining a loss value of the neural network model according to the predicted classification of the training set and the label of the training set; According to the loss value, the neural network model is iteratively trained until a preset convergence condition is reached to obtain the trained neural network model.

10. The device according to claim 9, characterized in that The model training module is configured as follows: Inputting the training set into the neural network model to obtain a predicted probability of abnormal discharge in the training sample; The predicted classification of the training sample is determined according to the predicted probability that the training sample has abnormal discharge.

11. The device according to claim 9, characterized in that The model training module is configured as follows: According to the loss value, updating the model parameters of the neural network model; the model parameters include weights and biases; When the loss value meets the preset convergence condition, the training is terminated to obtain the trained neural network model.

12. The device according to claim 7, characterized in that The device also includes a data preprocessing module, which is configured to: The electrical signal to be tested is preprocessed; the preprocessing includes at least one of resampling, filtering, denoising, numerical standardization, and segmentation.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

14. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 6 by executing the executable instructions.

Images