Rehabilitation training method and system based on transcranial time-domain interference electric stimulation

Abstract

The application discloses a rehabilitation training method and system based on transcranial time-domain interference electric stimulation. The method comprises the following steps: a physiological signal acquisition module is used to acquire multi-modal physiological signals of a user; a software processing module is used to determine a target stimulation target point of the user based on the multi-modal physiological signals, and generate an electric stimulation parameter scheme of the target stimulation target point; and an electric stimulation module is used to perform transcranial time-domain interference electric stimulation on the user based on the electric stimulation parameter scheme. According to the rehabilitation training method and system, the characteristics of deep nuclei can be precisely controlled by using the transcranial time-domain interference electric stimulation technology, and the deep lesions can be precisely stimulated. Meanwhile, more effective individualized stimulation schemes can be provided for the user by guiding the multi-modal physiological signals. The system can provide a non-invasive, convenient and efficient solution in the rehabilitation application of movement disorders in hospitals, communities and homes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical equipment, in particular to a rehabilitation training method and system based on transcranial time-domain interference electric stimulation. BACKGROUND

[0002] Diseases such as Parkinson's disease, essential tremor, and post-stroke sequelae cause movement disorders, which not only affect the physical activity ability of patients, but also can significantly reduce their quality of life, making daily activities severely impaired.

[0003] Studies have shown that transcranial electric stimulation technology can effectively alleviate the symptoms of movement disorders. However, traditional transcranial electric stimulation methods, such as transcranial direct current stimulation, have limited action areas, insufficient intervention depth, and can only stimulate the superficial cortex, such as the motor cortex. And the traditional stimulation method ignores the user-specific multi-modal physiological signal features, so that its symptom relief effect is not ideal, unstable and not lasting. SUMMARY

[0004] The embodiments of the present application provide a rehabilitation training method and system based on transcranial time-domain interference electric stimulation, to at least solve the technical problems of insufficient transcranial electric stimulation intervention depth and difficulty in providing personalized stimulation schemes in the related art.

[0005] According to an aspect of an embodiment of the present application, a rehabilitation training system based on transcranial time-domain interference electric stimulation is provided, comprising:

[0006] a physiological signal acquisition module, configured to acquire multi-modal physiological signals of a user;

[0007] a software processing module, configured to determine a target stimulation target point of the user based on the multi-modal physiological signals, and generate an electric stimulation parameter scheme of the target stimulation target point;

[0008] an electric stimulation module, configured to perform transcranial time-domain interference electric stimulation on the user based on the electric stimulation parameter scheme.

[0009] In one embodiment, the multi-modal physiological signals include electroencephalogram signals, electromyogram signals, and motion acceleration signals.

[0010] In one embodiment, the software processing module comprises:

[0011] a target stimulation target point determination unit, configured to preprocess the multi-modal physiological signals; perform time-frequency feature extraction and spatial feature extraction on the preprocessed electroencephalogram signals to obtain time-frequency features and spatial features of the electroencephalogram signals;

[0012] based on the preprocessed electromyogram signals and motion acceleration signals, locate and mark abnormal electroencephalogram data segments and non-abnormal electroencephalogram data segments;

[0013] Based on the labeled abnormal and non-abnormal EEG data segments and the time-frequency features and spatial features of the EEG signals, the abnormal brain region is located, and the target stimulation target point is determined based on the location result.

[0014] In one embodiment, the software processing module comprises:

[0015] The individualized digital head model generation unit is configured to perform brain tissue segmentation on the MRI structural image of the user, and reconstruct a digital head model of the user based on the segmentation result.

[0016] The digital head model is simulated by using the finite element method, the electric field distribution of the transcranial time-domain interference electric stimulation is simulated, and the guide field of the transcranial time-domain interference electric stimulation is calculated based on the simulation method.

[0017] Based on the guide field, an iterative optimization algorithm is used to generate optimal electric stimulation parameters.

[0018] In one embodiment, the software processing module further comprises:

[0019] The real-time regulation unit is configured to collect multi-modal physiological signals during the rehabilitation training of the user according to a preset period.

[0020] The multi-modal physiological signals are input into a pre-trained classification and prediction model to obtain the activity state of the user; the activity state includes an abnormal activity state and a normal activity state.

[0021] When the user is in an abnormal activity state, the electric stimulation parameters are dynamically adjusted based on the real-time multi-modal physiological signals.

[0022] In one embodiment, the software processing module further comprises:

[0023] The evaluation module is configured to collect and evaluate the movement disorder symptom level before and after the rehabilitation training of the user.

[0024] In one embodiment, the software processing module further comprises:

[0025] The optimization unit is configured to perform regression analysis on the movement disorder symptom level and the multi-modal physiological signals that meet the preset difference before and after the rehabilitation training, and obtain the multi-modal physiological signals related to the movement disorder symptom level that meets the preset difference.

[0026] Based on the multi-modal physiological signals obtained by the regression analysis, the electric stimulation parameter scheme is optimized.

[0027] According to another aspect of the embodiments of the present application, a rehabilitation training method based on transcranial time-domain interference electric stimulation is provided, comprising:

[0028] collecting multi-modal physiological signals of a user;

[0029] determining a target stimulation target point of the user based on the multi-modal physiological signals, and generating an electrical stimulation parameter scheme of the target stimulation target point;

[0030] performing transcranial time-domain interference electrical stimulation on the user based on the electrical stimulation parameter scheme.

[0031] In one embodiment, determining the target stimulation target point of the user based on the multi-modal physiological signals comprises:

[0032] preprocessing the multi-modal physiological signals; performing time-frequency feature extraction and spatial feature extraction on the preprocessed electroencephalogram signals to obtain time-frequency features and spatial features of the electroencephalogram signals;

[0033] locating and labeling abnormal electroencephalogram data segments and non-abnormal electroencephalogram data segments based on the preprocessed electromyogram signals and motion acceleration signals;

[0034] locating abnormal brain regions based on the labeled abnormal and non-abnormal electroencephalogram data segments and the time-frequency features and spatial features of the electroencephalogram signals, and determining the target stimulation target point based on the locating result.

[0035] In one embodiment, generating the electrical stimulation parameter scheme of the target stimulation target point comprises:

[0036] segmenting brain tissues of an MRI structural image of the user, and reconstructing a digital head model of the user based on the segmentation result;

[0037] simulating the digital head model by using a finite element method, simulating electric field distribution of transcranial time-domain interference electrical stimulation, and calculating a guide field of the transcranial time-domain interference electrical stimulation based on the simulation method;

[0038] generating optimal electrical stimulation parameters by using an iterative optimization algorithm based on the guide field.

[0039] The technical scheme provided by the embodiments of the present application can include the following beneficial effects:

[0040] The transcranial time-domain interference electrical stimulation technology can accurately regulate the characteristics of deep nuclei, and the multi-modal physiological signal characteristics can guide the electrical stimulation scheme, so as to more effectively relieve the symptoms of movement disorders. The method solves the limitation that the traditional transcranial electrical stimulation technology cannot accurately stimulate deep lesions (such as thalamus, globus pallidus and hippocampus, etc.); at the same time, through the guidance of multi-modal physiological signals, a more effective individualized stimulation scheme is provided for the user, a more suitable personalized stimulation scheme is generated for the user, and the training effect is improved. The system can be applied in hospitals, communities or home environments to realize a non-invasive, convenient and efficient solution. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0042] Figure 1 is a flow chart of a rehabilitation training scheme based on transcranial time-domain interference electric stimulation according to an embodiment of the application;

[0043] Figure 2 is another flow chart of a rehabilitation training scheme based on transcranial time-domain interference electric stimulation according to an embodiment of the application;

[0044] Figure 3 is a schematic diagram of a rehabilitation training system based on transcranial time-domain interference electric stimulation according to an embodiment of the application. DETAILED DESCRIPTION

[0045] In order to enable persons skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0046] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0047] The following will be described in detail with reference to the accompanying drawings Figure 3 The rehabilitation training system based on transcranial time-domain interference electric stimulation according to the embodiments of the present application will be described in detail. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0048] As shown in FIG. 1, the rehabilitation training system based on transcranial time-domain interference electric stimulation according to the embodiments of the present application includes a transcranial time-domain interference electric stimulation device 100, a rehabilitation training device 200, and a control device 300. Figure 3As shown, the system comprises: a physiological signal acquisition module, configured to acquire multi-modal physiological signals of a user.

[0049] In an optional implementation, the multi-modal physiological signals include electroencephalogram signals, electromyogram signals, motion acceleration signals, etc. The electroencephalogram signals are used to evaluate the endogenous neural rhythm activity level of the user, such as the sensorimotor rhythm, etc. The electromyogram signals are used to evaluate the muscle activity level of the affected limb of the user; and the motion acceleration signals are used to evaluate the movement and control ability of the affected limb of the user, such as the tremor degree, etc.

[0050] In an implementation, the physiological signal acquisition module is a physiological signal acquisition device, which comprises a plurality of signal acquisition electrodes, and in use, the signal acquisition electrodes are ensured to be correctly placed on the user. This can include electroencephalogram electrodes, electromyogram electrodes, motion acceleration sensors, etc., which need to be placed at appropriate positions according to specific physiological signal acquisition requirements.

[0051] In the embodiments of the present application, a software processing module is further included, configured to determine a target stimulation target point of the user based on the multi-modal physiological signals, and generate an electrical stimulation parameter scheme of the target stimulation target point. The software processing module can be a computer device, configured to realize data processing.

[0052] In an implementation, the software processing module comprises a target stimulation target point determination unit, configured to determine the target stimulation target point of the user.

[0053] Specifically, the multi-modal physiological signals are preprocessed; the electroencephalogram signals after preprocessing are subjected to time-frequency feature extraction and spatial domain feature extraction, to obtain time-frequency features and spatial domain features of the electroencephalogram signals.

[0054] The multi-modal physiological signal data before rehabilitation training can be subjected to data fusion. First, the physiological signal data of different modalities are subjected to down-sampling, so as to make the sampling rates consistent; second, the physiological signal data of different modalities are subjected to data splicing in the dimension of leads, so as to be fused into a two-dimensional matrix of lead X time. The multi-modal physiological signal data includes electroencephalogram signals, electromyogram signals, motion acceleration signals, etc. of the user before rehabilitation training.

[0055] Further, the multi-modal signal fusion data matrix of the electroencephalogram signals, electromyogram signals and motion acceleration signals is preprocessed, including low-pass filtering, power frequency notch filtering and removing baseline drift, etc., to obtain the data after preprocessing.

[0056] Further, the electroencephalogram data after preprocessing is subjected to time-frequency feature extraction, for example, using filtering, fast Fourier transform (FFT) and wavelet transform, etc. to extract time-frequency features. The time-frequency features of the electroencephalogram signals are obtained.

[0057] The pre-processed electroencephalogram data is subjected to spatial feature extraction, for example, using common spatial pattern (CSP), principal component analysis (PCA), independent component analysis (ICA) and cluster statistical analysis (Maximum cluster-level mass) to extract spatial features of the electroencephalogram signal.

[0058] Further, based on the pre-processed electromyogram signal and motion acceleration signal, abnormal electroencephalogram data segments and non-abnormal electroencephalogram data segments are located and labeled.

[0059] It can be understood that, by analyzing the pre-processed electromyogram signal and motion acceleration signal, abnormal electromyogram signals and abnormal motion acceleration signals can be obtained, for example, abnormal limb movement and abnormal muscle activity of the user at a certain time. Through the abnormal motion acceleration signal and electromyogram signal, the abnormal electroencephalogram data segment corresponding to the abnormal time can be located.

[0060] Through this step, based on whether the electromyogram signal and motion acceleration signal are abnormal, the abnormal electroencephalogram data segment is located and labeled, and the electroencephalogram data is labeled.

[0061] Further, based on the labeled abnormal and non-abnormal electroencephalogram data segments and the time-frequency features and spatial features of the electroencephalogram signal, the abnormal brain region is traced and located, and the target stimulation target point is determined based on the location result.

[0062] In an embodiment, based on an existing target point positioning navigation analysis model software, the labeled abnormal and non-abnormal electroencephalogram data segments and the time-frequency features and spatial features of the electroencephalogram signal are input, and the located abnormal brain region that produces the abnormal electroencephalogram data segment is output. Based on the location result, the target stimulation target point is determined.

[0063] Using the target point positioning navigation analysis model software, the pre-processed electroencephalogram data is input, which includes the labeled abnormal and non-abnormal electroencephalogram signal segments. At the same time, the time-frequency features and spatial features of these signals are input, which can include the power spectral density, coherence, phase locking value and other time-frequency features extracted from the electroencephalogram signal, and the spatial features obtained from independent component analysis (ICA) or principal component analysis (PCA). Based on the input data, the abnormal brain region that produces the abnormal electroencephalogram data segment is located. The located abnormal brain region is subjected to statistical test, and the region with the most significant statistical result is clustered as the target stimulation target point.

[0064] In an embodiment, the software processing module further comprises: an individualized digital head model generation unit. Used to generate the electrical stimulation parameters in the training process.

[0065] Specifically, the user's MRI structural image is segmented into brain tissues, and a digital head model of the user is reconstructed based on the segmentation results.

[0066] The individualized MRI structural image of the user is segmented by software, which can use tools such as FSL-FAST or SPM, which can automatically segment the 3D image of the brain into different tissue types, including gray matter, white matter, and cerebrospinal fluid. This step is the basis for building an individualized digital head model, ensuring accurate positioning of subsequent electrical stimulation. Based on the segmentation results, an individualized digital head model is reconstructed.

[0067] Further, the digital head model is simulated using the finite element method, and the electric field distribution of transcranial time-domain interference electric stimulation is simulated, and the guide field of transcranial time-domain interference electric stimulation is calculated based on the simulation method.

[0068] The digital head model is simulated using the finite element method (FEM), and the electric field distribution during transcranial time-domain interference electric stimulation (tTIS) is calculated. The finite element method provides great freedom in the choice of discretization, allowing smaller elements to be used in areas with high electric field gradients to improve the accuracy of the simulation. The electric field distribution calculated by the finite element method can determine the guide field of the electric stimulation, i.e. the propagation path and distribution of the electric stimulation in the brain tissue.

[0069] Based on the guide field, an iterative optimization algorithm is used to generate the optimal electric stimulation parameters.

[0070] In the generated guide field, an iterative optimization algorithm such as gradient descent, evolutionary algorithm, and genetic algorithm is used to inversely deduce the optimal electric stimulation parameter scheme for the target stimulation target.

[0071] Inverse deduction: These algorithms optimize the electric stimulation parameters (such as current intensity, stimulation duration, electrode position, etc.) through an iterative process to achieve the best stimulation effect on the target brain area.

[0072] This method combines individualized MRI images, finite element methods, and iterative optimization algorithms to provide personalized transcranial time-domain interference electric stimulation rehabilitation training programs for users to achieve the best results. By precisely controlling the electric stimulation parameters, the program can be more targeted and effective, while reducing potential side effects.

[0073] In one embodiment, the software processing module further includes a real-time control unit.

[0074] Specifically, the real-time regulation unit is configured to collect the multi-modal physiological signals of the user during the rehabilitation training process according to a preset period; input the multi-modal physiological signals into a pre-trained classification prediction model to obtain an activity state of the user; the activity state includes an abnormal activity state and a normal activity state; and dynamically adjust the electrical stimulation parameters based on the real-time multi-modal physiological signals when the user is in the abnormal activity state.

[0075] In an embodiment, a classification prediction model is trained in advance. A plurality of physiological signal data is obtained, and the physiological signal data is labeled into physiological signal data corresponding to a normal activity state and physiological signal data corresponding to an abnormal activity state. A training set is obtained based on the labeled data. The classification prediction model is trained based on the training set. The classification prediction model can be a model structure in the form of a convolutional neural network, a multilayer perceptron, etc., which is not limited in the present application.

[0076] Further, during the process in which the user starts the rehabilitation training device, the multi-modal physiological signals of the user are collected every preset period. Specifically, the interval period can be set according to actual needs. The multi-modal physiological signals are input into the pre-trained classification prediction model to obtain an identified activity state of the user. The current user can be predicted to be in an abnormal activity state based on real-time multi-modal physiological signals, in which case electrical stimulation is needed, or in a normal activity state, in which case electrical stimulation is not needed.

[0077] Further, when the user is in an abnormal activity state, the electrical stimulation parameters are dynamically adjusted based on real-time multi-modal physiological signals. Self-adaptive electrical stimulation rehabilitation training is achieved.

[0078] In an optional embodiment, when the user is in an abnormal activity state, real-time multi-modal physiological signals can be obtained by a signal acquisition device. Based on the real-time multi-modal physiological signals, an electrical stimulation parameter generation unit in a software processing module is used to adjust the electrical stimulation parameters in real time through an iterative optimization algorithm. For example, the current size is adjusted.

[0079] The present application also includes an electrical stimulation module for transcranial time-domain interference electrical stimulation of the user based on an electrical stimulation parameter scheme. The electrical stimulation module includes a stimulation electrode for transcranial time-domain interference electrical stimulation, which needs to be worn on the head of the user.

[0080] In an implementation scenario, the user correctly wears the signal acquisition electrodes of the multi-modal physiological signal acquisition device and correctly wears the stimulation electrodes for transcranial time-domain interference electrical stimulation, and electrical stimulation is performed on the user based on the initially generated electrical stimulation parameter scheme.

[0081] In the process of starting the device for rehabilitation training, the multi-modal physiological signals of the user are collected every interval of a preset period. Specifically, the interval period can be set according to actual needs. The multi-modal physiological signals are input into a pre-trained classification and prediction model to obtain the recognized activity state of the user. Based on the real-time multi-modal physiological signals, it can be predicted that the current user is in an abnormal activity state, in which case electrical stimulation is needed, or in a normal activity state, in which case electrical stimulation is not needed. When the user is in an abnormal activity state, the electrical stimulation parameters are dynamically adjusted based on real-time multi-modal physiological signals. Self-adaptive electrical stimulation rehabilitation training is achieved.

[0082] The whole rehabilitation training process is characterized by its adaptability and real-time nature. By real-time monitoring and analysis of the user's physiological signals, the system can dynamically adjust the electrical stimulation parameters to adapt to the user's changing physiological state and rehabilitation needs. This method not only improves the treatment effect, but also may reduce unnecessary side effects, as it only provides electrical stimulation when the user needs it.

[0083] In one embodiment, it further comprises an evaluation module. For collecting and evaluating the motor disorder symptom level before and after rehabilitation training of the user.

[0084] Specifically, the motor disorder symptom level before and after rehabilitation training of the user is collected and evaluated using a motor disorder clinical evaluation scale, which includes a motor function evaluation scale, a motor ability evaluation scale, a tremor evaluation scale, a clinical tremor rating scale, etc. The present application is not limited in detail.

[0085] In an optional implementation, the motor disorder symptom level before and after rehabilitation training of the user can also be evaluated according to the collected multi-modal physiological signals.

[0086] In one embodiment, after the rehabilitation training is completed, an optimization unit of a software processing module can also be used to perform regression analysis on the motor disorder symptom level and multi-modal physiological signals that meet the preset difference before and after rehabilitation training; obtain the multi-modal physiological signals related to the motor disorder symptom level that meets the preset difference; and optimize the electrical stimulation parameter scheme based on the multi-modal physiological signals obtained by regression analysis.

[0087] Specifically, through statistical testing, the clinical evaluation results and multi-modal physiological signal features before and after rehabilitation training are compared to identify the parts with significant differences. This step is an important part of evaluating treatment effect and identifying key physiological changes. Statistical testing can help determine which changes are significant, thereby providing a basis for subsequent analysis.

[0088] For the clinical evaluation results and multi-modal physiological signal features with significant differences identified in the statistical test, regression analysis is performed. Regression analysis is a statistical method for assessing the strength and direction of the relationship between two or more variables. Through regression analysis, multi-modal physiological signal features related to clinical evaluation results with significant changes can be obtained.

[0089] The multi-modal physiological signal features obtained by regression analysis are used as model features of the online analysis algorithm of the transcranial time-domain interference electric stimulation guided by multi-modal physiological signals in the next course of treatment. Thus, the electric stimulation parameter adjustment is guided.

[0090] The application utilizes the characteristics of transcranial time-domain interference electric stimulation technology to precisely regulate deep nuclei, combines clinical evaluation and multi-modal physiological signal features, guides and optimizes the stimulation scheme, thereby achieving more effective, stable and lasting relief of symptoms of movement disorders. This method solves the limitation of traditional transcranial electric stimulation technology that cannot precisely stimulate deep lesions (such as thalamus, globus pallidus and hippocampus, etc.); at the same time, through the guidance of multi-modal physiological signals, a more effective individualized stimulation scheme is provided for users. This method can provide a non-invasive, convenient and efficient solution in the rehabilitation of movement disorders in hospitals, communities and homes by combining multi-modal physiological signal acquisition devices with transcranial time-domain interference electric stimulation software and hardware devices.

[0091] According to another aspect of the embodiments of the application, a rehabilitation training method based on transcranial time-domain interference electric stimulation is also provided. As shown in Figure 1 the method includes:

[0092] S101 acquiring multi-modal physiological signals of a user;

[0093] S102 determining a target stimulation target point of the user based on the multi-modal physiological signals, and generating an electric stimulation parameter scheme of the target stimulation target point;

[0094] S103 performing transcranial time-domain interference electric stimulation on the user based on the electric stimulation parameter scheme.

[0095] In one embodiment, determining the target stimulation target point of the user based on the multi-modal physiological signals includes:

[0096] preprocessing the multi-modal physiological signals; performing time-frequency feature extraction and spatial feature extraction on the preprocessed electroencephalogram signals to obtain time-frequency features and spatial features of the electroencephalogram signals;

[0097] locating and labeling abnormal electroencephalogram data segments and non-abnormal electroencephalogram data segments based on the preprocessed electromyogram signals and motion acceleration signals;

[0098] Based on the marked abnormal and non-abnormal EEG data segments and the time-frequency features and spatial features of the EEG signals, the abnormal brain region is traced and located, and the target stimulation target point is determined based on the location result.

[0099] In one embodiment, an electrical stimulation parameter scheme of the target stimulation target point is generated, including:

[0100] The MRI structural image of the user is segmented for brain tissue, and a digital head model of the user is reconstructed based on the segmentation result;

[0101] The digital head model is simulated by using a finite element method, the electric field distribution of transcranial time domain interference electric stimulation is simulated, and the guide field of transcranial time domain interference electric stimulation is calculated based on the simulation method;

[0102] Based on the guide field, an iterative optimization algorithm is used to generate the optimal electrical stimulation parameters.

[0103] In one embodiment, further comprising: collecting multi-modal physiological signals of the user during rehabilitation training according to a preset period; inputting the multi-modal physiological signals into a pre-trained classification prediction model to obtain the activity state of the user; the activity state includes an abnormal activity state and a normal activity state; when the user is in an abnormal activity state, the electrical stimulation parameters are dynamically adjusted based on real-time multi-modal physiological signals.

[0104] In one embodiment, further comprising: collecting and evaluating the movement disorder symptom level before and after rehabilitation training.

[0105] In one embodiment, further comprising: performing regression analysis on the movement disorder symptom level and the multi-modal physiological signals that meet the preset difference before and after rehabilitation training; obtaining the multi-modal physiological signals related to the movement disorder symptom level that meets the preset difference; and optimizing the electrical stimulation parameter scheme based on the multi-modal physiological signals obtained by the regression analysis.

[0106] In order to facilitate understanding of the rehabilitation training method based on transcranial time domain interference electric stimulation of the embodiments of the present application, the following will be described in conjunction with the accompanying Figure 2 further description.

[0107] As Figure 2 shown, including: first, the pre-training clinical evaluation scale collects and evaluates the movement disorder symptom level; the pre-training multi-modal physiological signal is collected and evaluated; the target stimulation target point is traced and located; the stimulation parameter scheme is analyzed; the transcranial time domain interference electric stimulation guided by the multi-modal physiological signal is used for rehabilitation training; the post-training clinical evaluation scale collects and evaluates the movement disorder symptom level; the post-training multi-modal physiological signal is collected and evaluated; the pre-training and post-training statistical analysis and optimization scheme are performed.

[0108] It should be noted that the rehabilitation training system based on transcranial time-domain interference electric stimulation provided in the above embodiment is only used for illustrating the division of the above functional modules when the rehabilitation training method based on transcranial time-domain interference electric stimulation is performed, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the rehabilitation training system based on transcranial time-domain interference electric stimulation and the rehabilitation training method based on transcranial time-domain interference electric stimulation provided in the above embodiment belong to the same concept, and the implementation process is described in detail in the system embodiment, which will not be described here.

[0109] The technical features of the above embodiments can be combined arbitrarily, and in order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0110] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

Claims

1. A transcranial time-domain interferential electric stimulation based rehabilitation training system, characterized in that, The method comprises the following steps: physiological signal acquisition module for collecting multi-modal physiological signals of the user; The multi-modal physiological signals include electroencephalogram signals, electromyogram signals and motion acceleration signals; The software processing module is used to determine the target stimulation target point of the user based on the multi-modal physiological signals, and generate the electric stimulation parameter scheme of the target stimulation target point; The software processing module comprises a target stimulation target point determination unit for preprocessing the multi-modal physiological signals; time-frequency feature extraction and spatial feature extraction are performed on the preprocessed electroencephalogram signals to obtain time-frequency features and spatial features of the electroencephalogram signals; based on the preprocessed electromyogram signals and motion acceleration signals, abnormal electroencephalogram data segments and non-abnormal electroencephalogram data segments are located and labeled; based on the labeled abnormal and non-abnormal electroencephalogram data segments and the time-frequency features and spatial features of the electroencephalogram signals, the abnormal brain region is located and traced, and the target stimulation target point is determined based on the location result; The electric stimulation module is used to perform transcranial time domain interference electric stimulation on the user based on the electric stimulation parameter scheme.

2. The system of claim 1, wherein, The software processing module comprises: An individualized digital head model generation unit is used to segment the brain tissue of the MRI structural image of the user, and reconstruct a digital head model of the user based on the segmentation result; The digital head model is simulated by using the finite element method, the electric field distribution of the transcranial time domain interference electric stimulation is simulated, and the guide field of the transcranial time domain interference electric stimulation is calculated based on the simulation method; Based on the guide field, an iterative optimization algorithm is used to generate the optimal electric stimulation parameters.

3. The system of claim 1, wherein, The software processing module further comprises: A real-time regulation unit is used to collect the multi-modal physiological signals of the user during the rehabilitation training process according to a preset period; The multi-modal physiological signals are input into a pre-trained classification prediction model to obtain the activity state of the user; the activity state includes an abnormal activity state and a normal activity state; When the user is in an abnormal activity state, the electric stimulation parameters are dynamically adjusted based on the real-time multi-modal physiological signals.

4. The system of claim 1, wherein, Further comprising: An evaluation module is used to collect and evaluate the movement disorder symptom levels of the user before and after rehabilitation training.

5. The system of claim 4, wherein, The software processing module further comprises: An optimization unit is used to perform regression analysis on the movement disorder symptom levels and multi-modal physiological signals that meet the preset difference before and after rehabilitation training; and obtain the multi-modal physiological signals related to the movement disorder symptom levels that meet the preset difference; Based on the multi-modal physiological signals obtained by regression analysis, the electric stimulation parameter scheme is optimized.

Images