An electrical stimulation control system

Abstract

The present application discloses an electrical stimulation control system, which includes four parts: an information acquisition module, an information analysis module, an electrical stimulation control module, and a multi-channel electrical stimulator. The information acquisition module includes an image collector, an electromyographic signal collector, and a neural signal collector. The information analysis module includes an image analysis unit and an electrical signal analysis unit. The electrical stimulation control module includes an error analysis module and an adaptive algorithm controller. The information acquisition module acquires motion information such as images, electromyographic signals, and neural potential signals of the affected and healthy sides of the face. The information analysis module performs facial symmetry analysis based on the motion information and determines the symmetry coefficient between the affected and healthy sides. The electrical stimulation control module uses symmetry coefficient error analysis and iterative learning rules to control the output electrical stimulation parameters, thereby adaptively adjusting the electrical stimulation signal intensity output by the multi-channel electrical stimulator, so that the movement state of the muscles on the affected side is consistent with that on the healthy side, effectively repairing facial symmetry.

Description

Technical Field

[0001] The present application relates to the field of medical rehabilitation technology, and more specifically, to an electrical stimulation control system. Background Art

[0002] In rehabilitation diagnosis and treatment, electrical stimulation therapy is a method that uses electrical stimulation to restore limb motor function. By stimulating the patient's muscle tissue with a small electric current, causing muscle contraction, this method restores lost or impaired motor function. Therefore, electrical stimulation therapy is widely used in the field of medical rehabilitation.

[0003] In the field of medical rehabilitation, facial paralysis is a disease characterized by motor dysfunction of the facial expression muscles, also known as facial nerve paralysis. It is often manifested as numbness of the facial muscles on the affected side, deviation of the mouth and eyes, and inability to make movements such as frowning, frowning, closing the eyes, puffing up, and pursing the lips, resulting in uncoordinated facial expressions on both sides of the face. Therefore, in the rehabilitation treatment of facial paralysis, electrical stimulation can be used to restore the coordination function of the patient's facial muscles. In 1978, Tobey and Sutton formally proposed that unilateral peripheral facial paralysis could be repaired through electrical stimulation. They severed one side of the rabbit's facial nerve, then implanted electrodes near the facial muscles on the healthy side to record their electrical activity. The electrical activity of the facial muscles on the healthy side triggered the electrical stimulator, stimulating the corresponding muscles on the affected side and causing them to contract, thereby keeping the movement state of the affected side consistent with that of the healthy side, in order to achieve the purpose of repairing facial paralysis.

[0004] The above-mentioned method of treating facial paralysis using electrical stimulation achieves the adjustment of the movement state of the muscles on the affected side of the face. However, since the electrical stimulation parameters are pre-set fixed values, the output intensity of the electrical stimulation remains unchanged during the treatment process. Therefore, the stimulated facial muscles will always be in the same degree of contraction state, causing facial muscle fatigue, resulting in poor coordination between the two sides of the face and poor treatment effect. Summary of the Invention

[0005] In view of this, the present application provides an electrical stimulation control system for solving the problem that the intensity of electrical stimulation output in the existing electrical stimulation therapy for facial paralysis remains unchanged, resulting in poor treatment effect.

[0006] In order to achieve the above objectives, the following solutions are proposed:

[0007] An electrical stimulation control system, comprising:

[0008] Information acquisition module, information analysis module, electrical stimulation control module and multi-channel electrical stimulator;

[0009] The information acquisition module is used to respectively acquire movement information of the affected side and the healthy side of the patient's face when the patient performs a target facial movement, wherein the movement information is an image and an electrical signal used to represent the facial movement state, and transmit the movement information to the information analysis module;

[0010] The information analysis module determines a symmetry coefficient between the affected side and the healthy side based on the input motion information of the affected side and the healthy side, wherein the symmetry coefficient is used to represent the difference between the motion information of the affected side and the healthy side, and inputs the symmetry coefficient into the electrical stimulation control module;

[0011] The electrical stimulation control module determines a target electrical stimulation parameter corresponding to the symmetry coefficient based on the symmetry coefficient error and the electrical stimulation parameter corresponding to the last target facial action, wherein the symmetry coefficient error is the difference between the symmetry coefficient and the target symmetry coefficient, and the target symmetry coefficient is the symmetry coefficient corresponding to when the action information of the affected side and the healthy side are consistent, and sends the target electrical stimulation parameter to the multi-channel electrical stimulator;

[0012] The multi-channel electrical stimulator outputs an electrical stimulation signal corresponding to the target electrical stimulation parameter.

[0013] Preferably, the information acquisition module includes:

[0014] Image collector, electromyographic signal collector and neural signal collector;

[0015] The image collector is used to simultaneously acquire images of the affected side and the healthy side of the face under the target facial action;

[0016] The electromyographic signal collector is used to simultaneously acquire electromyographic signals of the affected side and the healthy side of the face under the target facial movement, wherein the electromyographic signals are electrical signals generated by the contraction of facial muscles;

[0017] The neural signal collector is used to obtain nerve impulse signals at the same position on the affected and healthy sides by simultaneously stimulating the facial nerves on the affected and healthy sides under the target facial movement. The nerve impulse signals are electrical signals conducted along the facial nerve fibers.

[0018] Preferably, the information analysis module includes an image analysis unit and an electrical signal analysis unit;

[0019] The image analysis unit is used to obtain facial feature data of the affected side and the healthy side from the images of the affected side and the healthy side of the face respectively;

[0020] The electrical signal analysis unit is used to obtain electrical signal characteristic parameters of the electromyographic signals and the nerve impulse signals on the affected side and the healthy side of the face.

[0021] Preferably, the information analysis module is specifically used to obtain affected-side data and healthy-side data, wherein the affected-side data is composed of the facial feature data and the electrical signal characteristic parameters of the affected side, and the healthy-side data is composed of the facial feature data and the electrical signal characteristic parameters of the healthy side;

[0022] The symmetry coefficient is determined by a pre-established symmetry equation, which is a three-variable linear equation containing only three unknowns: the symmetry coefficient, the affected-side data, and the healthy-side data.

[0023] Preferably, the electrical stimulation control module includes an error analysis module and an adaptive algorithm controller;

[0024] The error analysis module is specifically configured to determine the symmetry coefficient error based on the symmetry coefficient and the target symmetry coefficient;

[0025] The adaptive algorithm controller is specifically used to establish an iterative learning model between the symmetry coefficient error and the target electrical stimulation parameters using iterative learning rules. The iterative learning model corrects the target electrical stimulation coefficient corresponding to the k-1th target facial action by using the symmetry coefficient error corresponding to the kth target facial action, completes iterative learning, and determines the target electrical stimulation parameters output when the kth target facial action is performed.

[0026] Preferably, the image collector includes a camera.

[0027] Preferably, the electromyographic signal collector includes an electromyographic signal electrode sheet, and the neural signal collector includes a neural signal electrode sheet.

[0028] Preferably, the system further comprises a display, which is connected to the electromyographic signal electrode sheet and the nerve signal electrode sheet and is used to display the electromyographic signal and the nerve impulse signal.

[0029] Preferably, the multi-channel electrical stimulation module is specifically configured to output a voltage or current of corresponding frequency and magnitude according to the target electrical stimulation parameters.

[0030] Preferably, it also includes:

[0031] The electrical stimulation signal is output through the electrode sheet.

[0032] It can be seen from the above technical solution that an electrical stimulation control system provided by an embodiment of the present application obtains motion information that can characterize the movement state of the affected side and the healthy side of the patient's face, analyzes the symmetry between the affected side and the healthy side, determines the symmetry coefficient representing the difference in motion information between the affected side and the healthy side, and then obtains the symmetry coefficient error of the symmetry coefficient relative to the target symmetry coefficient. The target symmetry coefficient is the symmetry coefficient obtained when the motion information of the affected side and the healthy side are completely consistent. The target electrical stimulation parameters corresponding to the symmetry coefficient are determined according to the symmetry coefficient error and the electrical stimulation parameters corresponding to the last target facial movement. The corresponding electrical stimulation signal is output according to the target electrical stimulation parameters to realize adaptive adjustment of the output electrical stimulation, so that the target electrical stimulation parameters corresponding to the current symmetry coefficient can stimulate the contraction degree of the affected side muscles to be consistent with that of the healthy side muscles, effectively restore the coordination function of the patient's facial muscles, realize the repair of the patient's facial symmetry, and enhance the rehabilitation treatment effect of patients with facial paralysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0034] Figure 1 A schematic diagram of the structure of an electrical stimulation control system provided in an embodiment of the present application;

[0035] Figure 2 A flowchart of a method of performing rehabilitation training using the electrical stimulation control system provided in an embodiment of the present application;

[0036] Figure 3 This is a schematic diagram of an algorithm for an electrical stimulation control module provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0038] The investigation found that the clinical manifestations of patients with facial paralysis are usually obvious asymmetry on both sides of the face. The specific reason is that the movement time and amplitude of the muscles on the affected side are shorter than those on the healthy side. Therefore, facial symmetry is an important feature of facial paralysis rehabilitation.

[0039] However, the inventors have found that when using the existing electrical stimulation therapy to repair facial paralysis in patients, the repair effect cannot meet expectations. Further research has found that the existing systems all control the output electrical stimulation intensity according to pre-set electrical stimulation parameters. However, since patients will inevitably have some facial muscle movements, such as blinking, during the repair process, once this happens, the state of the facial muscles will also change. If the stimulation is still performed with a fixed electrical stimulation intensity at this time, the degree of contraction of the facial muscles on the affected side will be inconsistent with that on the healthy side, and the coordination and symmetry of the two sides of the face will be low, resulting in poor facial paralysis repair effect and failure to meet expectations.

[0040] In view of this, the inventors proposed an electrical stimulation control system. Figure 1 This is a system architecture diagram of an electrical stimulation control system provided in an embodiment of the present application, such as Figure 1 As shown, the system may include an information acquisition module 10, an information analysis module 11, an electrical stimulation control module 12, and a multi-channel electrical stimulator 13. The information acquisition module 10 includes an image collector 100, an electromyographic signal collector 101, and a neural signal collector 102; the information analysis module 11 includes an image analysis module 110 and an electrical signal analysis module 111; and the electrical stimulation control module 12 includes an error analysis module 120 and an adaptive algorithm controller 121.

[0041] Among them, the image collector 100 can be a device that can support image acquisition function, such as a high-speed infrared data acquisition camera; the electromyography signal collector 101 can be a device or system that can collect facial electromyography signals, such as a surface electromyograph or a needle electromyograph; the nerve signal collector 102 can be a device or system that can collect facial nerve information, such as a nerve conduction recorder; the image analysis module 110 can be a face recognition system.

[0042] In this embodiment, using Figure 1 The system shown realizes adaptive adjustment of electrical stimulation. The information of the affected side and the healthy side of the patient's face is collected through the information collection module 10. The collected information is analyzed in the information analysis module 11 to complete the symmetry analysis between the affected side and the healthy side. The data obtained from the symmetry analysis is input into the electrical stimulation control module 12, and the error analysis is performed on the data. The electrical stimulation output is controlled by the error so that the degree of muscle contraction on the stimulated affected side is consistent with that on the healthy side, thereby achieving coordinated repair of the two sides of the face and completing the rehabilitation treatment of facial paralysis.

[0043] Combine Figure 1 The electrical stimulation control system structure shown in FIG. Figure 2 This embodiment of the present application provides a method for utilizing Figure 1Flow chart of rehabilitation training based on the electrical stimulation control system, refer to Figure 2 , the process may include:

[0044] Step S20 : ​​When the patient performs the target facial movement, the information acquisition module 10 acquires movement information of the affected side and the healthy side of the patient's face.

[0045] Target facial movements can include resting, raising eyebrows, frowning, closing eyes, smiling, pouting, and other movements. Movement information can include facial images and various electrical signals, such as electromyographic signals and neural potential signals. This movement information can characterize the movement of the patient's facial muscles during specific target facial movements, such as the amplitude of the movement, the degree of facial muscle contraction, and the position of the facial features.

[0046] Specifically, when the patient performs the target facial movement, the image collector 100 simultaneously acquires images of the affected side and the healthy side of the face.

[0047] In combination with the above embodiment, the image collector 100 can be a high-speed infrared data acquisition camera. In this embodiment, the patient looks at the acquisition camera and performs corresponding target facial movements according to the prompts. The camera can be photographed by the operator or automatically by setting a countdown.

[0048] Furthermore, when the patient performs the target facial movement, the myoelectric signal collector 101 simultaneously obtains the myoelectric signals of the affected side and the healthy side of the face.

[0049] In this embodiment, the electromyographic signal can be an electrical signal generated by the contraction of facial expression muscles. The patient's skin is first degreased to enhance conductivity, and then an electrode is placed on each facial feature. The facial feature parts may include the upper part of the eyebrow arch, the outer side of the outer canthus, the nasolabial groove, the outer side of the corner of the mouth, and the front of the helix. Finally, the patient follows the prompts of the action animation demonstrated by the system and performs target facial movements such as calming, raising eyebrows, frowning, closing eyes, showing teeth, and pouting. Under the target facial movements, the electrode sheet can collect the electromyographic signals generated by the muscle contraction of the facial muscles at the electrode placement sites on the affected side and the healthy side. The preamplifier can enhance the signal and transmit the signal, and the electromyographic signal is stored in the server, which can be observed using a display. The display can be connected to the above-mentioned electrode placement locations through the electrode sheet to display the collected facial electromyographic signals.

[0050] Furthermore, when the patient performs the target facial movement, the neural signal collector 102 simultaneously obtains the facial neural signals of the affected side and the healthy side of the face.

[0051] The facial nerve signal may be a conduction signal of the facial nerve and its branches. In an embodiment, the facial nerve signal may be a nerve impulse signal induced by the facial nerve of the patient, and the nerve impulse signal is an electrical signal conducted along the facial nerve fibers.

[0052] First, the patient's skin is defatted to enhance conductivity. Then, electrodes are placed at the facial nerve and facial nerve branch locations at the characteristic facial parts of the affected and healthy sides, respectively. The facial characteristic parts may include the upper part of the eyebrow arch, the outer side of the outer canthus, the nasolabial groove and the outer side of the corner of the mouth. Furthermore, in order to extract the nerve impulse signals of the affected and healthy sides, stimulation electrodes are placed in front of the main trunk of the facial nerve on the affected and healthy sides, respectively. When the patient performs the above-mentioned target facial movements, stimulation is given at the same time to induce nerve potentials. Finally, the nerve impulse signals at the electrodes on the affected and healthy sides are collected respectively, and the nerve impulse signals are facial nerve potential signals. The signal can be enhanced and transmitted by a preamplifier, and the nerve impulse signals are stored in a server, which can be observed using a display. The display can be connected to the above-mentioned electrode placement positions through electrode sheets to display the collected facial nerve potential signals.

[0053] The information acquisition module 10 in the electrical stimulation control system provided in this embodiment acquires motion information that can characterize the facial movement state by collecting the patient's facial image and facial electromyographic signals, neural potential signals and other electrical signals. The motion information constructs a multimodal data set of the patient's facial appearance features, electromyographic signals and neural potential signals, so as to reduce calculation errors when the following information analysis module 11 performs information analysis.

[0054] Step S21 : The information analysis module 11 determines the symmetry coefficient between the affected side and the healthy side based on the motion information of the affected side and the healthy side.

[0055] Specifically, the image analysis unit 110 in the information analysis module 11 performs image analysis on the patient's facial image collected by the image collector 100, and the electrical signal analysis unit 111 in the information analysis module 11 performs electrical signal analysis on the facial electromyographic signals collected by the electromyographic signal collector 101 and the facial neural potential signals collected by the neural signal collector 102.

[0056] Optionally, the image analysis unit 110 can utilize facial feature recognition algorithms or face recognition technology to obtain facial feature data for both the affected and unaffected sides of the facial image and reduce redundant background. Facial feature data may include eyebrow elevation, eye closure, and mouth corner position. The electrical signal analysis unit 111 can display various electrical signal parameters, such as pulse width, amplitude, and frequency, on an oscilloscope to obtain characteristic electrical signal parameters for the electromyographic and neural potential signals.

[0057] Further optionally, the symmetry equation is used to process the data of the affected side and the healthy side obtained through the above information analysis to determine the symmetry coefficient between the affected side and the healthy side.

[0058] Among them, the affected side data may include the above-mentioned facial feature data of the affected side and the electrical signal characteristic parameters of the electromyographic signals and nerve potential signals collected on the affected side, and the healthy side data may include the above-mentioned facial feature data of the healthy side and the electrical signal characteristic parameters of the electromyographic signals and nerve potential signals collected on the healthy side. The symmetry coefficient can represent the difference in data values ​​between the affected side data and the healthy side data.

[0059] The symmetry equation can be a three-variable linear equation containing only three unknowns: the symmetry coefficient, the affected-side data, and the healthy-side data. Specifically, the affected-side data and the healthy-side data obtained at the same facial feature positions corresponding to the affected and healthy sides are substituted into the pre-established symmetry equation to calculate the symmetry coefficient for the corresponding facial feature positions. This embodiment provides the following optional symmetry coefficient calculation formulas, and the corresponding symmetry equations are shown in Formula 1:

[0060]

[0061] The four symmetry equations in formula 1 above can all be used to calculate the symmetry coefficient, where A paretic Indicates the data of the patient's affected side, A non-paretic Represents the data of the healthy side of the patient. The above-mentioned affected side data and healthy side data can be the facial feature data obtained by the above-mentioned image analysis unit 110, and can also be the electrical signal feature parameters obtained by the above-mentioned electrical signal analysis unit 111. In particular, the affected side data and the healthy side data substituted into the above-mentioned symmetry equation to calculate the symmetry coefficient should correspond one to one. For example, the affected side data substituted into is the numerical value of the eyebrow raising height of the affected side, and the corresponding healthy side data substituted into should be the numerical value of the eyebrow raising height of the healthy side. For another example, the affected side data substituted into is the amplitude of the electromyographic signal collected from the orbicularis oculi muscle on the affected side, then the corresponding healthy side data substituted into should be the amplitude of the electromyographic signal collected from the orbicularis oculi muscle on the healthy side.

[0062] Step S22: The error analysis module 120 obtains the symmetry coefficient error.

[0063] Alternatively, the symmetry coefficient error may be the difference between the symmetry coefficient obtained by the information analysis unit 11 and the target symmetry coefficient. The target symmetry coefficient is a standard value that can be determined by the symmetry equation. Specifically, the target symmetry coefficient is obtained by substituting the affected-side data into the healthy-side data and setting the value obtained by substituting the data into the symmetry equation.

[0064] Step S23 , the electrical stimulation control module 12 determines the target electrical stimulation parameters corresponding to the symmetry coefficient based on the symmetry coefficient error and the electrical stimulation parameters output by the adaptive algorithm controller 121 when the target facial action was last performed.

[0065] Optionally, the adaptive algorithm controller 121 obtains the symmetry coefficient error output by the error analysis module 120 and the electrical stimulation parameters output by the adaptive algorithm controller 121 when the target facial action was performed last time, and can determine the target electrical stimulation parameters corresponding to the symmetry coefficient determined in the above step S21 through a pre-established iterative learning model.

[0066] The iterative learning model may be an iterative learning model between the symmetry coefficient error and the target electrical stimulation parameter established using an iterative learning rule. Specifically, the iterative learning rule is shown in Formula 2:

[0067] U k (n) = U k-1 (n)+(f p +f i ∑δn+f d Δ)e k (n) (Formula 2)

[0068] Among them, the input value e k (n) is an n-dimensional vector where e=[e(1),e(2),…,e(n)] T ∈R n The kth vector of can be referred to as the symmetry coefficient error, that is, the difference between the symmetry coefficient and the target symmetry coefficient, and the output value U k-1 (n) and U k (n) is an n-dimensional vector U = [U(1), U(2), …, U(n)] T ∈R n The k-1th and kth vectors in the adaptive algorithm controller 121 can be referred to as the electrical stimulation parameters and target electrical stimulation parameters output by the adaptive algorithm controller 121, f p 、f i and f d are the proportional, integral and differential learning factor matrices respectively.

[0069] Step S24: The multi-channel electrical stimulator 13 outputs an electrical stimulation signal corresponding to the target electrical stimulation parameters.

[0070] Optionally, the multi-channel electrical stimulator 13 obtains the target electrical stimulation parameter U output by the electrical stimulation control module 12. out , output voltage or current of corresponding frequency and magnitude according to the parameters.

[0071] The multi-channel electrical stimulator 13 can transmit the output electrical stimulation to the target action position on the affected side of the patient's face through the electrode sheet, stimulating the muscles at that position to contract.

[0072] The method for rehabilitation training using an electrical stimulation control system provided in this embodiment obtains facial images, electromyographic signals and neural potential signals of the affected and healthy sides of the patient's face through the information acquisition module 10, and establishes a multimodal data set. After data analysis in the information analysis module 11, the data diversity can be enhanced, thereby reducing the calculation error of the symmetry coefficient. The symmetry coefficient calculated by the symmetry equation is input into the electrical stimulation control module 12, and the symmetry coefficient error is determined by the error analysis module 120. The adaptive algorithm controller 121 uses iterative learning rules to pre-establish an iterative learning model between the symmetry coefficient error and the target electrical stimulation parameters. When using the system for rehabilitation training, the iterative learning model can be directly called, and the determined symmetry coefficient error is used to adjust the output target electrical stimulation parameters, and then the electrical stimulation corresponding to the target electrical stimulation parameters is output by the multi-channel electrical stimulator to achieve adaptive adjustment of the output electrical stimulation.

[0073] Further integration Figure 3 , Figure 3 The schematic diagram of the algorithm of an electric stimulation control module provided in the embodiment of the present application is shown. The structure of the electric stimulation control module 12 has been introduced in the above embodiment, and can include an error analysis module 120 and an adaptive algorithm controller 121. Figure 3 As shown, the algorithm flow of this module may include:

[0074] S0. The error analysis module 120 obtains the symmetry coefficient and determines the symmetry coefficient error in combination with the target symmetry coefficient.

[0075] Alternatively, the calculation formula for the symmetry coefficient error is shown in Formula 3:

[0076] e k =I k -I s (Formula 3)

[0077] Among them, I k is the symmetry coefficient when the target facial action is performed for the kth time, I s is the target symmetry coefficient. According to the above symmetry equation provided in this embodiment, the target symmetry coefficient I s The result of calculation is 0 or 1, e k is the symmetry coefficient error when performing the target facial action for the kth time.

[0078] S1. The adaptive algorithm controller 121 obtains the symmetry coefficient error and determines the output target electrical stimulation parameters through a pre-established iterative learning model.

[0079] Further optionally, according to the iterative learning rule introduced in the above embodiment, the symmetry coefficient error e can be established. k The target electrical stimulation parameter U output by the adaptive algorithm controller 121 out The iterative learning model between is shown in Formula 4:

[0080] U out =H k =T(H k-1 +E k ) (Formula 4)

[0081] Among them, H k The parameter U representing the kth output electrical stimulation out ;H k-1 The parameter U representing the k-1th output electrical stimulation out0 ;E k represents the error parameter, as shown in Formula 5:

[0082] E k =Le k (Formula 5)

[0083] Where L is the learning parameter, which can be calculated based on the ratio between the symmetry coefficient obtained from the experiment on people without facial paralysis and the actual output electrical stimulation parameter. The symmetry coefficient error e k Multiply by the word writing parameter L to get the error parameter E k ;

[0084] In the iterative learning model shown in Formula 4, T is a constraint function that ensures that the output parameter H is always within an acceptable range. The constraint function is shown in Formula 6:

[0085]

[0086] in, is the maximum electrical stimulation intensity that the patient can accept, and the constraint function T ensures that the output parameter H will never exceed the maximum electrical stimulation intensity that the patient can accept, so as to ensure absolute safety; where u is the minimum electrical stimulation intensity, that is, because the electrical stimulation output intensity cannot be negative, when the target electrical stimulation parameter U out When the calculated value is negative, the constraint function T is set to 0 to avoid output errors.

[0087] According to an iterative learning model provided by this embodiment, when performing the same target facial action, the adaptive algorithm controller 121 uses the symmetry coefficient error e determined by the error analysis module 120 for the kth time. k The electrical stimulation coefficient U for the k-1th output out0 Correction is performed to determine the target electrical stimulation parameter U output for the kth time out , where the target electrical stimulation parameter U output for the kth time is out This is the corrected result.

[0088] When the patient's facial movements change, the symmetry coefficient obtained through information analysis may be different, thus causing the symmetry coefficient error to change. The iterative learning model provided in this embodiment can perform iterative learning based on the change in the symmetry coefficient error and adaptively adjust the output target electrical stimulation parameters.

[0089] An embodiment of the present application provides an electrical stimulation control system, in which an information acquisition module 10 acquires motion information such as images, electromyographic signals, and neural potential signals of the affected and healthy sides of a patient's face, transmits the above motion information to an information analysis module 11 for data analysis, extracts the patient's facial feature data and electrical signal feature parameters of the electromyographic signals and neural potential signals, constructs a multimodal data set, and uses the data of the affected and healthy sides in the multimodal data set to determine the symmetry coefficient between the affected and healthy sides. Furthermore, the electrical stimulation control module 12 acquires the symmetry coefficient, obtains the symmetry coefficient error through symmetry coefficient error analysis, determines the output target electrical stimulation parameters through an iterative learning model between the pre-established symmetry coefficient error and the target electrical stimulation parameters, and adaptively adjusts the electrical stimulation parameters using the change in the symmetry coefficient, thereby controlling the intensity of the electrical stimulation signal output by the multi-channel electrical stimulator 13, so that the degree of muscle contraction on the affected side of the patient's face caused by the electrical stimulation signal is consistent with the degree of muscle contraction at the corresponding position on the healthy side, thereby achieving facial symmetry repair and restoring the facial coordination function of patients with facial paralysis, effectively improving the rehabilitation treatment effect.

[0090] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0091] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0092] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An electrical stimulation control system, characterized in that: include: Information acquisition module, information analysis module, electrical stimulation control module and multi-channel electrical stimulator; The information acquisition module is used to respectively acquire movement information of the affected side and the healthy side of the patient's face when the patient performs a target facial movement, wherein the movement information is an image and an electrical signal used to represent the facial movement state, and transmit the movement information to the information analysis module; The information analysis module determines a symmetry coefficient between the affected side and the healthy side based on the input motion information of the affected side and the healthy side, wherein the symmetry coefficient is used to represent the difference between the motion information of the affected side and the healthy side, and inputs the symmetry coefficient into the electrical stimulation control module; The electrical stimulation control module determines a target electrical stimulation parameter corresponding to the symmetry coefficient based on the symmetry coefficient error and the electrical stimulation parameter corresponding to the last target facial action, wherein the symmetry coefficient error is the difference between the symmetry coefficient and the target symmetry coefficient, and the target symmetry coefficient is the symmetry coefficient corresponding to when the action information of the affected side and the healthy side are consistent, and sends the target electrical stimulation parameter to the multi-channel electrical stimulator; The multi-channel electrical stimulator outputs an electrical stimulation signal corresponding to the target electrical stimulation parameter; The information acquisition module includes: Image collector, electromyographic signal collector and neural signal collector; The image collector is used to simultaneously acquire images of the affected side and the healthy side of the face under the target facial action; the image collector is a high-speed infrared data acquisition camera; The electromyographic signal collector is used to simultaneously obtain electromyographic signals of the affected side and the healthy side of the face under the target facial movement, wherein the electromyographic signals are electrical signals generated by the contraction of facial muscles; the electromyographic signal collector is a surface electromyograph or a needle electromyograph; The neural signal collector is used to obtain nerve impulse signals at the same position on the affected and healthy sides by simultaneously stimulating the facial nerves on the affected and healthy sides under the target facial movement. The nerve impulse signals are electrical signals conducted along the facial nerve fibers; the neural signal collector is a nerve conduction recorder.

2. The system according to claim 1, wherein: The information analysis module includes an image analysis unit and an electrical signal analysis unit; The image analysis unit is used to obtain facial feature data of the affected side and the healthy side from the images of the affected side and the healthy side of the face respectively; The electrical signal analysis unit is used to obtain electrical signal characteristic parameters of the electromyographic signals and the nerve impulse signals on the affected side and the healthy side of the face.

3. The system according to claim 2, characterized in that The information analysis module is specifically used to obtain affected-side data and healthy-side data, wherein the affected-side data is composed of the facial feature data and the electrical signal characteristic parameters of the affected side, and the healthy-side data is composed of the facial feature data and the electrical signal characteristic parameters of the healthy side; The symmetry coefficient is determined by a pre-established symmetry equation, which is a three-variable linear equation containing only three unknowns: the symmetry coefficient, the affected-side data, and the healthy-side data.

4. The system according to claim 1, wherein: The electrical stimulation control module includes an error analysis module and an adaptive algorithm controller; The error analysis module is specifically configured to determine the symmetry coefficient error based on the symmetry coefficient and the target symmetry coefficient; The adaptive algorithm controller is specifically used to establish an iterative learning model between the symmetry coefficient error and the target electrical stimulation parameters using an iterative learning rule. The iterative learning model corrects the target electrical stimulation parameters corresponding to the k-1th target facial action using the symmetry coefficient error corresponding to the kth target facial action, completes iterative learning, and determines the target electrical stimulation parameters output when the kth target facial action is performed.

5. The system according to claim 1, wherein: The electromyographic signal collector includes an electromyographic signal electrode sheet, and the neural signal collector includes a neural signal electrode sheet.

6. The system according to claim 5, characterized in that The system further comprises a display, which is connected to the electromyographic signal electrode sheet and the nerve signal electrode sheet and is used for displaying the electromyographic signal and the nerve impulse signal.

7. The system according to claim 1, wherein: The multi-channel electrical stimulator is specifically used to output a voltage or current of corresponding frequency and magnitude according to the target electrical stimulation parameters.

8. The system according to claim 1, wherein: Also includes: The electrical stimulation signal is output through the electrode sheet.

Images