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

Abstract

The invention discloses a rehabilitation training method and system based on transcranial time domain interference electrical stimulation. Comprising a physiological signal acquisition module used for acquiring a multi-modal physiological signal of a user; the software processing module is used for determining a target stimulation target of a user based on the multi-modal physiological signal and generating an electrical stimulation parameter scheme of the target stimulation target; and the electrical stimulation module is used for performing transcranial time domain interference electrical stimulation on the user based on the electrical stimulation parameter scheme. According to the rehabilitation training method and system, the characteristics of the deep nuclei can be accurately regulated and controlled by using the transcranial time domain interference electrical stimulation technology, and the deep focus is accurately stimulated. Meanwhile, a more effective individualized stimulation scheme is provided for the user through the guidance of the multi-modal physiological signals. The system can be applied to dyskinesia rehabilitation in hospitals, communities and homes, and a non-invasive, convenient and efficient solution is provided.

Description

Technical Field

[0001] The present application relates to the field of medical equipment technology, and more specifically, to a rehabilitation training method and system based on transcranial time-domain interferometric electrical stimulation. Background Art

[0002] Diseases such as Parkinson's disease, essential tremor, and sequelae of stroke cause movement disorders, which not only affect patients' physical activity ability, but may also significantly reduce their quality of life and cause serious obstacles to daily activities.

[0003] Studies have shown that transcranial electrical stimulation technology can effectively relieve the symptoms of movement disorders. However, traditional transcranial electrical stimulation methods, such as transcranial direct current stimulation, have limited action areas and insufficient intervention depth, and can only stimulate the superficial cortex, such as the motor cortex. In addition, traditional stimulation methods ignore the user-specific multimodal physiological signal characteristics, so that their symptom relief effects are unsatisfactory, unstable, and not lasting. Summary of the invention

[0004] The embodiments of the present application provide a rehabilitation training method and system based on transcranial time-domain interferometric electrical stimulation, so as to at least solve the technical problems in the related art that the transcranial electrical stimulation intervention depth is insufficient and it is difficult to provide personalized stimulation plans.

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

[0006] A physiological signal acquisition module, used to acquire multimodal physiological signals of the user;

[0007] A software processing module, used to determine the user's target stimulation target based on the multimodal physiological signal, and generate an electrical stimulation parameter scheme for the target stimulation target;

[0008] The electrical stimulation module is used to perform transcranial time-domain interferometric electrical stimulation on the user based on the electrical stimulation parameter scheme.

[0009] In one embodiment, the multimodal physiological signal includes an electroencephalogram signal, an electromyography signal, and a motion acceleration signal.

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

[0011] The target stimulation target determination unit is used to preprocess the multimodal physiological signal; extract the time-frequency feature and the spatial domain feature of the preprocessed EEG signal to obtain the time-frequency feature and the spatial domain feature of the EEG signal;

[0012] Based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked;

[0013] Based on the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain area is traced and located, and the target stimulation target is determined based on the positioning results.

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

[0015] Individualized digital head model generation unit, used to perform brain tissue segmentation on the user's MRI structural image and reconstruct the user's digital head model based on the segmentation result;

[0016] The digital head model is simulated by using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method;

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

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

[0019] A real-time control unit, used to collect multimodal physiological signals of the user during rehabilitation training according to a preset period;

[0020] Inputting the multimodal physiological signal 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;

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

[0022] In one embodiment, it further includes:

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

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

[0025] The optimization unit is used to perform regression analysis on the movement disorder symptom level and the multimodal physiological signal that meet the preset difference before and after the rehabilitation training; and obtain the multimodal physiological signal related to the movement disorder symptom level that meets the preset difference;

[0026] Based on the multimodal physiological signals obtained by regression analysis, the electrical stimulation parameter scheme is optimized.

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

[0028] Collect multimodal physiological signals of users;

[0029] Based on the multimodal physiological signal, determining the user's target stimulation target, and generating an electrical stimulation parameter scheme for the target stimulation target;

[0030] Based on the electrical stimulation parameter scheme, transcranial time-domain interferometric electrical stimulation is performed on the user.

[0031] In one embodiment, determining a user's target stimulation point based on the multimodal physiological signal includes:

[0032] Preprocessing the multimodal physiological signal; extracting time-frequency features and spatial features from the preprocessed EEG signal to obtain time-frequency features and spatial features of the EEG signal;

[0033] Based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked;

[0034] Based on the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain area is traced and located, and the target stimulation target is determined based on the positioning results.

[0035] In one embodiment, generating an electrical stimulation parameter scheme for the target stimulation point includes:

[0036] Perform brain tissue segmentation on the user's MRI structural image and reconstruct the user's digital head model based on the segmentation results;

[0037] The digital head model is simulated by using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method;

[0038] Based on the guidance field, an iterative optimization algorithm is used to generate optimal electrical stimulation parameters.

[0039] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0040] This application uses transcranial time-domain interferometric electrical stimulation technology to accurately regulate the characteristics of deep nuclei, combined with multimodal physiological signal characteristics, to guide electrical stimulation programs, so as to achieve more effective relief of movement disorder symptoms. This method solves the limitation that 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 multimodal physiological signals, it provides users with more effective individualized stimulation programs, generates personalized stimulation programs that are more suitable for users, and improves training effects. And the system can be used in hospitals, communities or home environments to achieve non-invasive, convenient and efficient solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 is a flow chart of a rehabilitation training program based on transcranial time-domain interferometric electrical stimulation according to an embodiment of the present application;

[0043] Figure 2 is a flowchart of another rehabilitation training program based on transcranial time-domain interferometric electrical stimulation according to an embodiment of the present application;

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

[0045] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] The following is combined with Figure 3 The rehabilitation training system based on transcranial time domain interferometric electrical stimulation of the embodiment of the present application is introduced in detail. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this regard. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0048] like Figure 3As shown, the system includes: a physiological signal acquisition module, which is used to acquire multimodal physiological signals of the user.

[0049] In an optional implementation, the multimodal physiological signals include EEG signals, EMG signals, motion acceleration signals, etc. Among them, EEG signals are used to evaluate the user's endogenous neural rhythm activity level, such as sensory motor rhythm, etc. EMG signals are used to evaluate the muscle activity level of the user's affected limbs; motion acceleration signals are used to evaluate the movement and control ability of the user's affected limbs, such as the degree of tremor, etc.

[0050] In one embodiment, the physiological signal acquisition module is a physiological signal acquisition device, which includes a plurality of signal acquisition electrodes. During use, it is ensured that the signal acquisition electrodes are correctly placed on the user. This may include electroencephalogram electrodes, electromyogram electrodes, and motion acceleration sensors, etc., which need to be placed in appropriate positions according to specific physiological signal acquisition requirements.

[0051] In the embodiment of the present application, a software processing module is also included, which is used to determine the user's target stimulation target based on the multimodal physiological signal and generate an electrical stimulation parameter scheme for the target stimulation target. The software processing module can be a computer device for implementing data processing.

[0052] In one embodiment, the software processing module includes a target stimulation target point determination unit, which is used to determine the target stimulation target point of the user.

[0053] Specifically, the multimodal physiological signals are preprocessed; the time-frequency features and the spatial domain features are extracted from the preprocessed EEG signals to obtain the time-frequency features and the spatial domain features of the EEG signals.

[0054] The multimodal physiological signal data before rehabilitation training can be fused. First, the physiological signal data of different modalities are downsampled to make their sampling rates consistent; secondly, the physiological signal data of different modalities are spliced ​​in the lead dimension to be fused into a two-dimensional matrix of lead x time. The multimodal physiological signal data includes the user's EEG signals, electromyographic signals, motion acceleration signals, etc. before rehabilitation training.

[0055] Furthermore, the signal fusion data matrix of the EEG signal, the EMG signal, and the motion acceleration signal is preprocessed, including low-pass filtering, power frequency notching, and removal of baseline drift, to obtain preprocessed data.

[0056] Furthermore, the preprocessed EEG data is subjected to time-frequency feature extraction, for example, by using filtering, fast Fourier transform (FFT), wavelet transform and other methods to extract time-frequency features, thereby obtaining the time-frequency features of the EEG signal.

[0057] The spatial features of the preprocessed EEG data are extracted, for example, by using methods such as common spatial pattern (CSP), principal component analysis (PCA), independent component analysis (ICA) and cluster statistical analysis (Maximum cluster-level mass) to extract spatial features and obtain the spatial features of the EEG signal.

[0058] Furthermore, based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked.

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

[0060] Through this step, based on whether there are abnormalities in the electromyographic signals and motion acceleration signals, the abnormal EEG data segments are located and marked, thereby achieving labeling of the EEG data.

[0061] Furthermore, based on the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain areas are traced and located, and the target stimulation targets are determined based on the positioning results.

[0062] In one embodiment, based on the existing target positioning navigation analysis model software, the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signal can be input, and the abnormal brain area that produces the abnormal EEG data segment can be output. Based on the positioning results, the target stimulation target is determined.

[0063] Using the target positioning navigation analysis model software, input the preprocessed EEG data, which includes EEG signal segments marked as abnormal and non-abnormal. At the same time, input the time-frequency features and spatial features of these signals, which may include time-frequency features such as power spectral density, coherence, phase locking value extracted from the EEG signal, and spatial features obtained from independent component analysis (ICA) or principal component analysis (PCA). Based on the input data, locate the abnormal brain area that produces abnormal EEG data segments. Perform statistical tests on the located abnormal brain areas, and cluster the areas with the most significant statistical results as the target stimulation targets.

[0064] In one embodiment, the software processing module further includes: an individualized digital head model generating unit, which is used to generate electrical stimulation parameters during the training process.

[0065] Specifically, brain tissue segmentation is performed on the user's MRI structural image, and the user's digital head model is reconstructed based on the segmentation result.

[0066] Use software to segment the user's personalized MRI structural images into brain tissue. This process 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 a personalized digital head model, ensuring the precise positioning of subsequent electrical stimulation. Based on the segmentation results, a personalized digital head model is reconstructed.

[0067] Furthermore, the digital head model is simulated using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method.

[0068] The digital head model is simulated using the finite element method (FEM) to calculate the electric field distribution during transcranial time-domain interferometric electrical stimulation (tTIS). The finite element method provides great freedom in the choice of discreteness, and smaller units can be used in areas with large electric field gradients to improve the accuracy of the simulation. The electric field distribution calculated by the finite element method can determine the guiding field of the electrical stimulation, that is, the propagation path and distribution of the electrical stimulation in the brain tissue.

[0069] Based on the guidance field, an iterative optimization algorithm was used to generate the optimal electrical stimulation parameters.

[0070] In the generated guidance field, iterative optimization algorithms, such as gradient descent, evolutionary algorithm and genetic algorithm, are used to reversely derive the optimal electrical stimulation parameter scheme for the target stimulation target.

[0071] Reverse engineering: These algorithms optimize electrical 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 method and iterative optimization algorithm to provide users with personalized interventional electrical stimulation rehabilitation training programs in order to achieve the best results. By precisely controlling the electrical stimulation parameters, the program's pertinence and effectiveness can be improved while reducing possible side effects.

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

[0074] Specifically, the real-time control unit is used to collect multimodal physiological signals of the user during rehabilitation training according to a preset period; the multimodal physiological signals are input into a pre-trained classification prediction model to obtain the user's activity state; 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 the real-time multimodal physiological signals.

[0075] In one embodiment, a classification prediction model is trained in advance. A variety of physiological signal data are obtained, and the physiological signal data are labeled to be divided into physiological signal data corresponding to normal activity states and physiological signal data corresponding to abnormal activity states. A training set is obtained based on the labeled data. A 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 specifically limited in this application.

[0076] Furthermore, when the user turns on the rehabilitation training equipment, the user's multimodal physiological signals are collected at preset intervals, and the specific intervals can be set according to actual needs. The multimodal physiological signals are input into the pre-trained classification prediction model to obtain the identified activity state of the user; based on the real-time multimodal physiological signals, it can be predicted that the current user is in an abnormal activity state, at which time electrical stimulation is required, or in a normal activity state, at which time electrical stimulation is not required.

[0077] Furthermore, when the user is in an abnormal activity state, the electrical stimulation parameters are dynamically adjusted based on real-time multimodal physiological signals to achieve adaptive electrical stimulation rehabilitation training.

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

[0079] The present application also includes an electrical stimulation module for performing transcranial time-domain interferometric electrical stimulation on the user based on the electrical stimulation parameter scheme. The electrical stimulation module includes stimulation electrodes for transcranial time-domain interferometric electrical stimulation, which need to be worn on the user's head.

[0080] In one implementation scenario, the user correctly wears the signal acquisition electrodes of the multimodal physiological signal acquisition device and the stimulation electrodes of the transcranial time-domain interferometry electrical stimulation, and the user is electrically stimulated based on the initially generated electrical stimulation parameter plan.

[0081] When the device is turned on for rehabilitation training, the user's multimodal physiological signals are collected at preset intervals, and the specific intervals can be set according to actual needs. The multimodal physiological signals are input into the pre-trained classification prediction model to obtain the identified activity status of the user; based on the real-time multimodal physiological signals, it can be predicted that the current user is in an abnormal activity state, at which time electrical stimulation is required, or in a normal activity state, at which time electrical stimulation is not required. When the user is in an abnormal activity state, the electrical stimulation parameters are dynamically adjusted based on the real-time multimodal physiological signals. Adaptive electrical stimulation rehabilitation training is achieved.

[0082] The entire rehabilitation training process is characterized by its adaptability and real-time nature. By monitoring and analyzing the user's physiological signals in real time, the system is able to dynamically adjust the electrical stimulation parameters to adapt to the user's changing physiological state and rehabilitation needs. This approach not only improves the treatment effect, but also has the potential to reduce unwanted side effects because it only provides electrical stimulation when the user needs it.

[0083] In one embodiment, the system further comprises: an evaluation module for collecting and evaluating the movement disorder symptom level of the user before and after rehabilitation training.

[0084] Specifically, a movement disorder clinical assessment scale is used to collect and assess the movement disorder symptom level of the user before and after rehabilitation training, and the clinical assessment scale includes a motor function assessment scale, a motor ability assessment scale, a tremor assessment scale, a clinical tremor assessment scale, etc. This application does not make specific limitations.

[0085] In an optional implementation, the movement disorder symptom level of the user before and after rehabilitation training may also be evaluated based on the collected multimodal physiological signals.

[0086] In one embodiment, after the rehabilitation training is completed, the optimization unit of the software processing module can also be used to perform regression analysis on the movement disorder symptom levels and multimodal physiological signals that meet preset differences before and after the rehabilitation training; obtain multimodal physiological signals related to the movement disorder symptom levels that meet the preset differences; and optimize the electrical stimulation parameter scheme based on the multimodal physiological signals obtained by the regression analysis.

[0087] Specifically, statistical tests are used to compare clinical assessment results and multimodal physiological signal characteristics before and after rehabilitation training to identify the significant differences. This step is an important part of evaluating treatment effects and identifying key physiological changes. Statistical tests can help determine which changes are significant, thus providing a basis for subsequent analysis.

[0088] For clinical assessment results and multimodal physiological signal features with significant differences identified in statistical tests, regression analysis is performed. Regression analysis is a statistical method used to evaluate the strength and direction of the relationship between two or more variables. Through regression analysis, multimodal physiological signal features associated with clinical assessment results with significant changes can be obtained.

[0089] The multimodal physiological signal features obtained by regression analysis are used as the model features of the online analysis algorithm of transcranial time-domain interferometric electrical stimulation guided by multimodal physiological signals in the next treatment course, thereby guiding the adjustment of electrical stimulation parameters.

[0090] This application uses transcranial time-domain interferometric electrical stimulation technology to accurately regulate the characteristics of deep nuclei, and combines clinical evaluation with multimodal physiological signal characteristics to guide and optimize stimulation schemes, thereby achieving more effective, more stable and more lasting relief of movement disorder symptoms. This method solves the limitation that traditional transcranial electrical stimulation technology cannot accurately stimulate deep lesions (such as thalamus, globus pallidus and hippocampus); at the same time, through the guidance of multimodal physiological signals, it provides users with more effective individualized stimulation schemes. This method combines multimodal physiological signal acquisition equipment with transcranial time-domain interferometric electrical stimulation software and hardware equipment to provide non-invasive, convenient and efficient solutions in movement disorder rehabilitation applications in hospitals, communities and homes.

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

[0092] S101 collects multimodal physiological signals of the user;

[0093] S102 determines the user's target stimulation target based on the multimodal physiological signal, and generates an electrical stimulation parameter scheme for the target stimulation target;

[0094] S103 performs transcranial time-domain interferometric electrical stimulation on the user based on the electrical stimulation parameter plan.

[0095] In one embodiment, determining a user's target stimulation point based on a multimodal physiological signal includes:

[0096] Preprocess the multimodal physiological signals; extract the time-frequency features and the spatial domain features of the preprocessed EEG signals to obtain the time-frequency features and the spatial domain features of the EEG signals;

[0097] Based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked;

[0098] Based on the marked abnormal and non-abnormal EEG data fragments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain areas are traced and located, and the target stimulation targets are determined based on the positioning results.

[0099] In one embodiment, generating an electrical stimulation parameter scheme for a target stimulation point includes:

[0100] Perform brain tissue segmentation on the user's MRI structural image and reconstruct the user's digital head model based on the segmentation results;

[0101] The digital head model is simulated by using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method;

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

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

[0104] In one embodiment, it also includes: collecting and evaluating the movement disorder symptom level of the user before and after rehabilitation training.

[0105] In one embodiment, it also includes: performing regression analysis on movement disorder symptom levels and multimodal physiological signals that meet preset differences before and after rehabilitation training; obtaining multimodal physiological signals related to movement disorder symptom levels that meet preset differences; and optimizing electrical stimulation parameter schemes based on the multimodal physiological signals obtained through regression analysis.

[0106] In order to facilitate understanding of the rehabilitation training method based on transcranial time-domain interferometric electrical stimulation in the embodiment of the present application, the following is a Figure 2 Further description.

[0107] like Figure 2 As shown, it includes: first, the clinical assessment scale is used to collect and evaluate the level of movement disorder symptoms before training; multimodal physiological signals are collected and evaluated before training; target stimulation target is traced and located; stimulation parameter scheme is analyzed; rehabilitation training is carried out using transcranial time domain interferometric electrical stimulation guided by multimodal physiological signals; the clinical assessment scale is used to collect and evaluate the level of movement disorder symptoms after training; multimodal physiological signals are collected and evaluated after training; statistical analysis is performed before and after training and the scheme is optimized.

[0108] It should be noted that the rehabilitation training system based on transcranial time-domain interferometric electrical stimulation provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when executing the rehabilitation training method based on transcranial time-domain interferometric electrical stimulation. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, 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 interferometric electrical stimulation provided in the above embodiment belongs to the same concept as the rehabilitation training method embodiment based on transcranial time-domain interferometric electrical stimulation. The implementation process is detailed in the system embodiment, which will not be repeated here.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A rehabilitation training system based on transcranial time-domain interferometric electrical stimulation, characterized in that: include: A physiological signal acquisition module, used to acquire multimodal physiological signals of the user; A software processing module, used to determine the user's target stimulation target based on the multimodal physiological signal, and generate an electrical stimulation parameter scheme for the target stimulation target; The electrical stimulation module is used to perform transcranial time-domain interferometric electrical stimulation on the user based on the electrical stimulation parameter scheme.

2. The system according to claim 1, characterized in that The multimodal physiological signals include electroencephalogram signals, electromyography signals, and motion acceleration signals.

3. The system according to claim 1, characterized in that The software processing module comprises: The target stimulation target determination unit is used to preprocess the multimodal physiological signal; extract the time-frequency feature and the spatial domain feature of the preprocessed EEG signal to obtain the time-frequency feature and the spatial domain feature of the EEG signal; Based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked; Based on the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain area is traced and located, and the target stimulation target is determined based on the positioning results.

4. The system according to claim 1, characterized in that The software processing module comprises: Individualized digital head model generation unit, used to perform brain tissue segmentation on the user's MRI structural image and reconstruct the user's digital head model based on the segmentation result; The digital head model is simulated by using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method; Based on the guidance field, an iterative optimization algorithm is used to generate optimal electrical stimulation parameters.

5. The system according to claim 1, characterized in that The software processing module further includes: A real-time control unit, used to collect multimodal physiological signals of the user during rehabilitation training according to a preset period; Inputting the multimodal physiological signal 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 multimodal physiological signals.

6. The system according to claim 1, characterized in that Also includes: The evaluation module is used to collect and evaluate the user's movement disorder symptom level before and after rehabilitation training.

7. The system according to claim 6, characterized in that The software processing module further includes: The optimization unit is used to perform regression analysis on the movement disorder symptom level and the multimodal physiological signal that meet the preset difference before and after the rehabilitation training; and obtain the multimodal physiological signal related to the movement disorder symptom level that meets the preset difference; Based on the multimodal physiological signals obtained by regression analysis, the electrical stimulation parameter scheme is optimized.

8. A rehabilitation training method based on transcranial time-domain interferometric electrical stimulation, characterized in that: include: Collect multimodal physiological signals of users; Based on the multimodal physiological signal, determining the user's target stimulation target, and generating an electrical stimulation parameter scheme for the target stimulation target; Based on the electrical stimulation parameter scheme, transcranial time-domain interferometric electrical stimulation is performed on the user.

9. The method according to claim 8, characterized in that Determining a target stimulation point of a user based on the multimodal physiological signal includes: Preprocessing the multimodal physiological signal; extracting time-frequency features and spatial features from the preprocessed EEG signal to obtain time-frequency features and spatial features of the EEG signal; Based on the preprocessed electromyographic signals and motion acceleration signals, abnormal EEG data segments and non-abnormal EEG data segments are located and marked; Based on the marked abnormal and non-abnormal EEG data segments and the time-frequency characteristics and spatial characteristics of the EEG signals, the abnormal brain area is traced and located, and the target stimulation target is determined based on the positioning results.

10. The method according to claim 8, characterized in that Generating an electrical stimulation parameter scheme for the target stimulation point includes: Perform brain tissue segmentation on the user's MRI structural image and reconstruct the user's digital head model based on the segmentation results; The digital head model is simulated by using the finite element method to simulate the electric field distribution of transcranial time-domain interferometric electrical stimulation, and the guiding field of transcranial time-domain interferometric electrical stimulation is calculated based on the simulation method; Based on the guidance field, an iterative optimization algorithm is used to generate optimal electrical stimulation parameters.

Images