Facial paralysis closed-loop repair system and facial paralysis closed-loop repair method

Abstract

The invention relates to a facial paralysis closed-loop repair system and a facial paralysis closed-loop repair method. The facial paralysis closed-loop repair system comprises a neural signal acquisition module, a neural signal decoding module, a stimulation decision module, a stimulation coding module and a stimulation execution module. The neural signal acquisition module is used for acquiring healthy side neural signals, the neural signal decoding module is used for decoding the healthy side neural signals to generate a healthy side movement track, and the stimulation decision module is used for acquiring movement intensity and time interval information corresponding to a paralyzed side movement track from the healthy side movement track. The stimulation coding module is used for generating stimulation configuration information according to the motion intensity and time interval information corresponding to the paralyzed side portion motion trail, and the stimulation execution module controls and stimulates paralyzed side nerves according to the stimulation configuration information. By means of the technical scheme, facial paralysis muscle groups can be effectively controlled, symmetrical movement of the face can be achieved, and prognosis of a facial paralysis patient is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of facial paralysis repair, and in particular to a facial paralysis closed-loop repair system and a facial paralysis closed-loop repair method. Background Art

[0002] Facial paralysis is one of the most common symptoms and signs in neurology patients. The main clinical manifestations of facial paralysis are limited facial movement due to facial muscle weakness and atrophy, incomplete eyelid closure, crooked mouth corners, involuntary drooling, etc. Due to facial muscle weakness or involuntary facial muscle linkage, patients with facial paralysis find it difficult to express their emotions normally. Some patients experience varying degrees of anxiety or depression, which greatly affects their daily social and psychological conditions. Therefore, how to reshape facial muscle activity in patients with facial paralysis and reduce secondary injuries related to facial paralysis is a clinical problem that needs to be solved urgently.

[0003] In the related art, a fully implantable eyelid pacemaker device has been developed for patients with facial paralysis. It effectively records the myoelectricity of the orbicularis oculi muscle on the healthy side, and directly stimulates the orbicularis oculi muscle on the paralyzed side, thereby restoring the blinking function of patients with facial paralysis. However, using muscle signals as the driving signal source for facial activities is insufficient for controlling facial activities of multiple muscle groups. In addition, the stimulation parameters of the device are constant, and the corresponding parameters cannot be selected according to the intensity of the activity. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a facial paralysis closed-loop repair system and a facial paralysis closed-loop repair method. The system can effectively control the facial paralysis muscles and achieve symmetrical movement of the face, thereby improving the prognosis of patients with facial paralysis.

[0005] In a first aspect, the present disclosure provides a closed-loop repair system for facial paralysis, including: a neural signal acquisition module, a neural signal decoding module, a stimulation decision module, a stimulation encoding module, and a stimulation execution module;

[0006] The neural signal acquisition module is connected to the neural signal decoding module, the stimulation decision module is connected to the neural signal decoding module and the stimulation encoding module respectively, and the stimulation encoding module is connected to the stimulation execution module;

[0007] The neural signal acquisition module is used to collect the neural signals of the healthy side, the neural signal decoding module decodes the neural signals of the healthy side to generate the facial motion trajectory of the healthy side, the stimulation decision module is used to obtain the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side from the facial motion trajectory of the healthy side, the stimulation encoding module is used to generate stimulation configuration information according to the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side, and the stimulation execution module controls the stimulation of the paralyzed facial nerve according to the stimulation configuration information.

[0008] Optionally, the neural signal decoding module includes a preprocessing unit and a decoding unit, and the preprocessing unit is connected to the neural signal acquisition module and the decoding unit respectively;

[0009] The preprocessing unit is used to preprocess the healthy side facial nerve signal and send the preprocessed healthy side facial nerve signal to the decoding unit. The decoding unit generates a healthy side facial motion trajectory according to the data change characteristics in the preprocessed healthy side facial nerve signal.

[0010] Optionally, the neural signal acquisition module is connected to the PEDOT:PSS flexible neural electrode via an FPC to acquire neural signals of the healthy side.

[0011] Optionally, the neural signal acquisition module transmits the healthy side neural signal to the neural signal decoding module via an air interface based on low-power Bluetooth.

[0012] Optionally, the stimulation encoding module transmits the stimulation configuration information to the stimulation execution module via an air interface based on low-power Bluetooth.

[0013] Optionally, the stimulation execution module comprises a stimulation instruction unpacking unit, a stimulation configuration unit and a stimulation unit, and the stimulation configuration unit is connected to the stimulation instruction unpacking unit and the stimulation unit respectively;

[0014] The stimulation instruction unpacking unit is used to extract the stimulation information in the stimulation configuration information and send the stimulation information to the stimulation configuration unit. The stimulation configuration unit controls the stimulation unit to stimulate the paralyzed facial nerve based on the stimulation information.

[0015] In a second aspect, the present disclosure further provides a closed-loop repair method for facial paralysis, which is applicable to the closed-loop repair system for facial paralysis as described in the first aspect, and comprises:

[0016] Get healthy side nerve signals;

[0017] Decoding the healthy side facial nerve signal to generate a healthy side facial motion trajectory;

[0018] Acquiring the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face according to the movement trajectory of the healthy side face;

[0019] Generate stimulation configuration information according to the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face;

[0020] The paralyzed facial nerve is stimulated according to the stimulation configuration information.

[0021] Optionally, the acquiring, according to the healthy side facial motion trajectory, the motion intensity and time interval information corresponding to the paralyzed side facial motion trajectory includes:

[0022] Extracting motion events from the healthy side facial motion trajectory;

[0023] Build a response model of stimulation parameters and facial motion trajectory on the paralyzed side;

[0024] The motion intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side is obtained according to the response model and the motion event.

[0025] Optionally, generating stimulation configuration information according to the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face includes:

[0026] Extracting at least one of the stimulation amplitude, stimulation pulse width and stimulation frequency from the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face, and encoding it in the form of bytes;

[0027] The bytes are spliced ​​to form stimulation configuration information according to the order in which the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side face occur.

[0028] In a third aspect, the present disclosure further provides a computer-readable storage medium, which stores programs or instructions; the program or instructions enable a computer to execute the steps of the method described in the second aspect.

[0029] In a fourth aspect, the present disclosure further provides an electronic device, comprising: a processor and a memory, wherein the processor executes the steps of the method described in the second aspect by calling a program or instruction stored in the memory.

[0030] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0031] The present disclosure provides a closed-loop repair system for facial paralysis and a closed-loop repair method for facial paralysis. The closed-loop repair system for facial paralysis includes: a neural signal acquisition module, a neural signal decoding module, a stimulation decision module, a stimulation coding module and a stimulation execution module; the neural signal acquisition module is connected to the neural signal decoding module, the stimulation decision module is respectively connected to the neural signal decoding module and the stimulation coding module, and the stimulation coding module is connected to the stimulation execution module; the neural signal acquisition module is used to acquire the neural signal of the healthy side, the neural signal decoding module decodes the neural signal of the healthy side to generate a healthy side facial motion trajectory, the stimulation decision module is used to obtain the motion intensity and time interval information corresponding to the paralyzed side facial motion trajectory from the healthy side facial motion trajectory, the stimulation coding module is used to generate stimulation configuration information according to the motion intensity and time interval information corresponding to the paralyzed side facial motion trajectory, and the stimulation execution module controls the stimulation of the paralyzed facial nerve according to the stimulation configuration information. Therefore, the healthy side nerve signals collected by the present invention can include more specific and diverse information on muscle activity, have a better control effect on the coordinated facial activities of multiple muscle groups, and can control the activities of various parts of the face. The stimulation execution module controls the stimulation of the paralyzed side nerve according to the stimulation configuration information, so that the paralyzed side nerve can be stimulated according to the strength of the healthy side nerve activity. At the same time, responsive electrical stimulation and adaptive electrical stimulation are realized, which can control a variety of facial activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0034] Figure 1 A schematic diagram of the structure of a closed-loop repair system for facial paralysis provided in an embodiment of the present disclosure;

[0035] Figure 2 A schematic diagram of a closed-loop repair method for facial paralysis provided in an embodiment of the present disclosure;

[0036] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0037] Among them, the correspondence between the figure marks and the structure: 1. Neural signal acquisition module; 2. Neural signal decoding module; 3. Stimulation decision module; 4. Stimulation encoding module; 5. Stimulation execution module; 51. Stimulation instruction unpacking unit; 52. Stimulation configuration unit; 53. Stimulation unit. DETAILED DESCRIPTION

[0038] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0040] In the related art, a fully implantable eyelid pacemaker device has been developed for patients with facial paralysis. It effectively records the myoelectricity of the orbicularis oculi muscle on the healthy side, and directly stimulates the muscles on the paralyzed side, thereby restoring the blinking function of patients with facial paralysis. However, using muscle signals as the driving signal source for facial activities is insufficient for controlling the coordinated activities of multiple muscle groups, and the device can only achieve eyelid function reconstruction, and cannot control the activities of facial positions such as the periorbital area. In addition, the stimulation parameters of the device are constant, and the corresponding parameters cannot be selected according to the intensity of the activity.

[0041] In order to solve the above problems, the embodiments of the present disclosure provide a closed-loop repair system for facial paralysis. Figure 1 A schematic diagram of the structure of a closed-loop repair system for facial paralysis provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the closed-loop repair system for facial paralysis includes: a neural signal acquisition module 1, the neural signal acquisition module 1 is connected to the neural signal decoding module 2, the stimulation decision module 3 is respectively connected to the neural signal decoding module 2 and the stimulation coding module 4, and the stimulation coding module 4 is connected to the stimulation execution module 5; the neural signal acquisition module 1 is used to collect the neural signals of the healthy side, the neural signal decoding module 2 decodes the neural signals of the healthy side to generate the facial motion trajectory of the healthy side, the stimulation decision module 3 is used to obtain the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side from the facial motion trajectory of the healthy side, the stimulation coding module 4 is used to generate stimulation configuration information according to the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side, and the stimulation execution module 5 controls the stimulation of the paralyzed facial nerve according to the stimulation configuration information.

[0042] Specifically, Figure 1As shown, the closed-loop repair system for facial paralysis includes a neural signal acquisition module 1, which is used to collect neural signals of the healthy side. Compared with the prior art of collecting muscle signals as a signal source for driving related facial positions, since one nerve can control multiple muscles, in the motor control pathway, the peripheral nerves are downstream of the central nervous system and upstream of the muscle groups, and the neural signals can include more specific and diverse information about muscle activity. Therefore, the neural signals of the healthy side collected by the embodiment of the present disclosure can include richer information, and the use of the neural signals of the healthy side can better control the coordinated activities of multiple muscle groups.

[0043] Exemplarily, the neural signal acquisition module 1 is implanted in the healthy side nerve, and the neural signal acquisition module 1 continuously acquires the healthy side nerve signals from the healthy side nerve, and temporarily stores these healthy side nerve signals in a buffer of a predetermined length, the length of the buffer is, for example, 16000 (i.e., representing the data of the previous 1s). When the buffer data is accumulated, it enters the neural signal decoding module.

[0044] Exemplarily, the neural signal acquisition module 1 can be connected to the neural signal decoding module via Bluetooth, and the neural signal decoding module 2 decodes the collected healthy side neural signals to generate a healthy side facial motion trajectory. The healthy side facial motion trajectory may include, for example, a perioral motion trajectory, a periorbital motion trajectory, or a motion trajectory of other facial positions, which is not limited in the embodiments of the present disclosure.

[0045] The stimulation decision module 3 obtains the movement intensity and time interval information corresponding to the motion trajectory of the paralyzed side face from the decoded healthy side face motion trajectory, such as the stimulation amplitude, stimulation pulse width and stimulation frequency, etc. The stimulation encoding module 4 receives the movement intensity and time interval information corresponding to the motion trajectory of the paralyzed side face sent by the stimulation decision module 3, and encodes it to form stimulation configuration information and send it to the stimulation execution module 5. The stimulation execution module 5 controls the stimulation of the paralyzed facial nerve according to the information contained in the stimulation configuration information.

[0046] The healthy side nerve signals collected by the embodiments of the present disclosure can include more specific and diverse information on muscle activity, have a better control effect on the coordinated activities of multiple muscle groups, and can control the activities of various parts of the face. The stimulation execution module 5 controls the stimulation of the paralyzed side nerve according to the stimulation configuration information, so that the paralyzed side nerve can be stimulated according to the strength of the healthy side nerve activity. At the same time, responsive electrical stimulation and adaptive electrical stimulation are realized, and various facial activities can be controlled.

[0047] Optionally, the neural signal decoding module 2 includes a preprocessing unit and a decoding unit, and the preprocessing unit is connected to the neural signal acquisition module 1 and the decoding unit respectively; the preprocessing unit is used to preprocess the healthy side neural signal, and send the preprocessed healthy side neural signal to the decoding unit, and the decoding unit generates a healthy side facial movement trajectory based on the data change characteristics in the preprocessed healthy side neural signal.

[0048] Specifically, the preprocessing unit is used to preprocess the healthy side nerve signal, for example, filtering, gain and digitization processing can be performed on the healthy side nerve signal.

[0049] The decoding unit may include, for example, a facial nerve electrical signal decoding neural network (WhiskerNet), which consists of an encoding part for feature extraction and a decoding part for signal decoding. The encoding part includes a manually extracted feature network and a CNN feature extraction network, as well as respective LSTM networks, which encode the neural electrical signal into a potential information vector. The decoding part consists of a fully connected layer and a self-attention module to decode the information vector and generate the whisker motion position of the corresponding time node. In the encoding part, the manually extracted features represent the signal feature extraction driven by expert knowledge, which can extract biologically meaningful signal features from the neural electrical signal. The CNN feature extraction network represents a professional form of machine intelligence, which can automatically learn deep and multi-scale signal features to more comprehensively capture the information in the neural electrical signal. The two feature extraction methods complement each other, so that the encoding part can more effectively extract the feature information of the neural electrical signal. In the decoding part, the fully connected layer is responsible for fusing the features extracted by the encoding part for subsequent decoding operations. The role of the self-attention module is to capture and learn the temporal dependency between the neural signal-motion of different individuals, and to perform individualized signal feature fusion, thereby ensuring accurate decoding of the signals of different individuals. This individualized decoding method can better adapt to the differences between different individuals and improve the accuracy and reliability of decoding. Therefore, the feature-fused facial nerve electrical signal neural network decoding architecture built by the embodiment of the present disclosure adopts parameter sharing and adaptive training strategies to achieve high-precision and robust signal decoding in multiple individuals.

[0050] Optionally, the neural signal acquisition module 1 is connected to the PEDOT:PSS flexible neural electrode via an FPC to acquire neural signals of the healthy side.

[0051] Specifically, PEDOT:PSS, i.e. poly(3,4-ethylenedioxythiophene):polystyrene sulfonic acid, is an aqueous solution of a high molecular polymer. The disclosed embodiment uses a low-impedance, soft, and electrochemically good polymer electrode, the healthy lateral nerve is connected to the PEDOT:PSS flexible nerve, and the neural signal acquisition module 1 is connected to the PEDOT:PSS flexible neural electrode via an FPC (Flexible Printed Circuit). The PEDOT:PSS flexible neural electrode has a low elastic modulus and good bioadhesion, can fit tightly to the peripheral nerve, form a stable neural-electrode interface, adapt to the dynamic changes of the neural in the awake state, and achieve continuous and stable recording of high-quality neural electrical signals, such as healthy lateral neural signals.

[0052] Optionally, the neural signal acquisition module 1 transmits the healthy side neural signal to the neural signal decoding module 2 via an air interface based on low-power Bluetooth.

[0053] Optionally, the stimulation encoding module 4 transmits the stimulation configuration information to the stimulation execution module 5 via an air interface based on low-power Bluetooth.

[0054] In the related art, the signal transmission method in the partial facial paralysis repair device is wired signal transmission. Although the wired transmission signal has good stability, the surgical implantation process is complicated, the destructive damage is large, and it may affect the facial appearance. The neural signal acquisition module 1 of the disclosed embodiment transmits the healthy side neural signal to the neural signal decoding module 2 through the air interface based on low-power Bluetooth, and the stimulation encoding module 4 transmits the stimulation configuration information to the stimulation execution module 5 through the air interface based on low-power Bluetooth, which can achieve minimally invasive and efficient signal transmission and reduce the difficulty of surgical implantation.

[0055] Alternatively, if Figure 1 As shown, the stimulation execution module 5 includes a stimulation instruction unpacking unit 51, a stimulation configuration unit 52 and a stimulation unit 53, and the stimulation configuration unit 52 is connected to the stimulation instruction unpacking unit 51 and the stimulation unit 53 respectively; the stimulation instruction unpacking unit 51 is used to extract the stimulation information in the stimulation configuration information, and send the stimulation information to the stimulation configuration unit 52, and the stimulation configuration unit 52 controls the stimulation unit 53 to stimulate the paralyzed facial nerve based on the stimulation information.

[0056] Specifically, the stimulation execution module 5 can be, for example, an MCU (Microcontroller Unit), the stimulation instruction unpacking unit 51 can be, for example, a numerical control stimulation pattern generator, the stimulation instruction unpacking unit 51 receives the stimulation configuration information sent by the stimulation coding module 4, and extracts the stimulation information in the stimulation configuration information, such as stimulation amplitude, stimulation pulse width and stimulation frequency, and combines the stimulation parameters including the stimulation amplitude, stimulation pulse width and stimulation frequency as a group of stimulation information. The stimulation configuration unit 52 can be, for example, a digital control configuration stimulator, and the stimulation configuration unit 52 controls the stimulation unit 53 to start multi-pulse stimulation to the paralyzed lateral nerve based on the stimulation information, and simultaneously starts a timer of a specified duration to ensure that the stimulation to the paralyzed lateral nerve meets the requirement of the stimulation time in the stimulation information. Once the timer is finished, the stimulation configuration unit 52 will read the next group of stimulation information and control the stimulation unit 53 to continue to stimulate the paralyzed lateral nerve. Repeat the above process until the number of stimulation pulses in the stimulation information is completed.

[0057] When the stimulation execution module 5 and the stimulation encoding module 4 are connected via wireless communication, such as Bluetooth, the stimulation execution module 5 can receive Bluetooth data packets at a time interval of 1 s, and complete the required electrical stimulation of the paralyzed facial nerve in sequence, thereby realizing closed-loop control of facial paralysis.

[0058] Exemplarily, the stimulation configuration unit 52 can be connected to the paralyzed facial nerve via the stimulation unit 53, the stimulation unit 53 is connected to the PEDOT:PSS flexible nerve electrode via the FPC, and the PEDOT:PSS flexible nerve electrode is connected to the paralyzed facial nerve. The PEDOT:PSS flexible nerve electrode can be regulated at the neural level, for example, to achieve overall regulation of the facial paralysis muscle group, which is more in line with actual clinical needs.

[0059] The closed-loop repair system for facial paralysis provided by the embodiments of the present disclosure can collect healthy side nerve signals that include more specific and diverse information on muscle activity, and has a better control effect on the coordinated activities of multiple muscle groups. The stimulation execution module controls the stimulation of the paralyzed side nerve according to the stimulation configuration information, so that the paralyzed side nerve can be stimulated according to the strength of the healthy side nerve activity. At the same time, responsive electrical stimulation and adaptive electrical stimulation are realized, and various facial activities can be controlled.

[0060] The disclosed embodiment also provides a closed-loop repair method for facial paralysis. Figure 2 This is a flow chart of a closed-loop repair method for facial paralysis provided by an embodiment of the present disclosure. This method can be executed by a closed-loop repair system for facial paralysis provided by an embodiment of the present disclosure, and can be applied in scenarios where facial paralysis needs to be repaired. Figure 2 As shown, the method comprises the following steps:

[0061] S101. Obtain nerve signals of the healthy side.

[0062] Specifically, the neural signal module fits the healthy side nerves and continuously collects healthy side nerve signals.

[0063] S102, decoding the healthy side facial nerve signal to generate a healthy side facial motion trajectory.

[0064] Specifically, the neural signal decoding module filters, amplifies, digitally processes and decodes the neural signal of the healthy side, thereby generating the facial motion trajectory of the healthy side. The specific processing method can refer to the description of the above embodiment, and the embodiment of the present disclosure will not be repeated here.

[0065] S103, obtaining the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face according to the movement trajectory of the healthy side face.

[0066] Optionally, obtaining the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side face according to the motion trajectory of the healthy side face includes: extracting motion events from the motion trajectory of the healthy side face; establishing a response model of the paralyzed side stimulation parameters and the motion trajectory of the paralyzed side face; and obtaining the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side face according to the response model and the motion events.

[0067] Specifically, the motion trajectory of the healthy side face includes, for example, a maximum point, which represents a motion event of the motion trajectory of the healthy side face, for example, a coordinate point of a stimulation occurrence position in the motion trajectory of the healthy side face. The time position of each maximum point is used as the specific moment of the stimulation, and the intensity of the maximum value guides the target intensity of the stimulation.

[0068] A response model of the stimulation parameters and the facial motion trajectory of the paralyzed side is constructed. For example, the response model of the stimulation parameters and the facial motion trajectory can be a linear time-invariant (LTI) model related to the electrical stimulation pulse. The facial motion trajectory of the healthy side is substituted into the response model of the stimulation parameters and the facial motion trajectory, thereby obtaining the motion intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side, so as to solve the stimulation parameters of the paralyzed side. In the embodiment of the present disclosure, in order to simplify the model, the stimulation pulse width is fixed to 200 μs.

[0069] S104, generating stimulation configuration information according to the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face.

[0070] Optionally, stimulation configuration information is generated according to the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side of the face, including: extracting at least one of the stimulation amplitude, stimulation pulse width and stimulation frequency from the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side of the face, and encoding it in the form of bytes; splicing the bytes according to the order in which the stimulation information occurs to form the stimulation configuration information.

[0071] Exemplarily, taking the stimulation information including stimulation amplitude, stimulation pulse width and stimulation frequency as an example, the stimulation amplitude, stimulation pulse width and stimulation frequency are respectively encoded into one byte, that is, the stimulation information required to complete one electrical stimulation is encoded with three bytes. The stimulation amplitude is quantized at intervals of 10μA, the stimulation pulse width is quantized at intervals of 10μs, and the stimulation frequency is quantized at intervals of 8ms. Each group of stimulation information is encoded with three bytes according to the combination of stimulation amplitude, stimulation pulse width and stimulation frequency, and then these three-byte codes are spliced ​​in the order in which the stimulation occurs. The splicing result is the effective stimulation information that needs to be transmitted, which is used as the stimulation configuration information. In addition, the number of stimulation pulses can be obtained when the three-byte codes are spliced.

[0072] Exemplarily, the stimulation configuration information can be transmitted by Bluetooth communication. The first two bytes of the Bluetooth data packet are the packet header, the third byte indicates the number of stimulation pulses required in the stimulation configuration information, and the remaining bytes are the effective stimulation information obtained by the above encoding. The stimulation configuration information is then packaged and transmitted to the stimulation execution module via Bluetooth.

[0073] Therefore, the paralyzed facial nerve is stimulated by utilizing the stimulation configuration information. Compared with the prior art which can only realize responsive electrical stimulation with constant and stable stimulation parameters, the present application can realize both responsive electrical stimulation and adaptive electrical stimulation. Different stimulation parameters are selected according to the strength of the stimulation activity of the healthy facial nerve, so as to control various facial activities.

[0074] S105. Stimulate the paralyzed facial nerve according to the stimulation configuration information.

[0075] The specific stimulation method can be referred to the above embodiment and will not be described in detail here.

[0076] The closed-loop repair system and method for facial paralysis provided by the embodiments of the present disclosure provide a new paradigm for the closed-loop repair of facial paralysis based on a neural prosthesis, whether it is based on a low-impedance, soft and electrochemically good polymer electrode as a bidirectional neural regulation interface, or the introduction of a deep learning neural network model for real-time signal decoding, or a precise regulation model of electrical stimulation parameters (stimulation amplitude, stimulation pulse width and stimulation frequency) and facial movement trajectory, and a closed-loop repair system for facial paralysis that integrates the above tasks. The embodiments of the present disclosure provide a new idea for the symmetrical repair of facial paralysis, reconstruction of facial appearance, and improvement of the long-term prognosis of facial paralysis. More importantly, for other motor nerve injuries with symmetrical activities, such as the abducens nerve, the motor branch of the trigeminal nerve or the hypoglossal nerve, the neural function can be reconstructed through the new paradigm of neural closed-loop repair based on a neural prosthesis proposed by the embodiments of the present disclosure. In addition, the closed-loop repair system for facial paralysis constructed by the embodiments of the present disclosure realizes individualization in two key links-decoding of the healthy side neural signals and the response model of the stimulation parameters and the facial movement trajectory. Individualized closed-loop repair of facial paralysis is achieved through a short-term and fast signal decoding module and stimulation model parameter update. This not only suggests the prospect of rapidly promoting the system in multiple individuals while maintaining a high degree of robustness, but also provides an important preliminary experimental basis for the system calibration method and effect after long-term implantation of the facial paralysis neural prosthesis in vivo.

[0077] Based on the above implementation, the present disclosure also provides an electronic device, Figure 3 The structure diagram of an electronic device provided by the embodiment of the present disclosure is shown in FIG. Figure 3 As shown, the electronic device includes a processor 301 and a memory 302. The processor 301 executes the steps of the methods of the above embodiments by calling the program or instructions stored in the memory 302, so it has the beneficial effects of the above embodiments, which will not be repeated here.

[0078] Specifically, Figure 3 As shown, the electronic device may include at least one processor 301, at least one memory 302, and at least one communication interface 303. The various components in the electronic device are coupled together via a bus system 304. The communication interface 303 is used to transmit information with external devices. It is understood that the bus system 304 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 304 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 304 is not described in detail. Figure 3 Various buses are labeled as bus system 304 .

[0079] It is understood that the memory 302 in this embodiment may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. In some implementations, the memory 302 stores the following elements: executable units or data structures, or their subsets, or their extended set operating systems and applications. In the disclosed embodiment, the processor 301 executes the steps of each embodiment of the method provided in the disclosed embodiment by calling the program or instruction stored in the memory 302.

[0080] The method provided in the embodiment of the present disclosure can be applied to the processor 301, or implemented by the processor 301. The processor 301 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 301 or an instruction in the form of software. The above-mentioned processor 301 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0081] The steps of the method provided in the embodiment of the present disclosure can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software units in the decoding processor. The software unit can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 302, and the processor 301 reads the information in the memory 302 and completes the steps of the method in combination with its hardware.

[0082] The electronic device may also include one physical component, or multiple physical components, according to the instructions generated by the processor 301 when executing the method provided in the embodiment of the present disclosure. Different physical components can be set inside the electronic device, or outside the electronic device, such as a cloud server, etc. Each physical component cooperates with the processor 301 and the memory 302 to realize the functions of the electronic device in this embodiment.

[0083] The embodiments of the present disclosure further provide a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of any one of the methods provided in the above embodiments.

[0084] In some embodiments, the computer executable instructions, when executed by a computer processor, can also be used to execute the technical solution of any of the above methods provided in the embodiments of the present disclosure to achieve corresponding beneficial effects.

[0085] Through the above description of the implementation methods, the technical personnel in the relevant field can clearly understand that the present disclosure can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer's floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present disclosure.

[0086] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0087] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those 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 disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A closed-loop repair system for facial paralysis, characterized in that: include: Neural signal acquisition module, neural signal decoding module, stimulation decision module, stimulation encoding module and stimulation execution module; The neural signal acquisition module is connected to the neural signal decoding module, the stimulation decision module is connected to the neural signal decoding module and the stimulation encoding module respectively, and the stimulation encoding module is connected to the stimulation execution module; The neural signal acquisition module is used to collect the neural signals of the healthy side, the neural signal decoding module decodes the neural signals of the healthy side to generate the facial motion trajectory of the healthy side, the stimulation decision module is used to obtain the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side from the facial motion trajectory of the healthy side, the stimulation encoding module is used to generate stimulation configuration information according to the movement intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side, and the stimulation execution module controls the stimulation of the paralyzed facial nerve according to the stimulation configuration information.

2. The facial paralysis closed-loop repair system according to claim 1, characterized in that: The neural signal decoding module includes a preprocessing unit and a decoding unit, and the preprocessing unit is connected to the neural signal acquisition module and the decoding unit respectively; The preprocessing unit is used to preprocess the healthy side facial nerve signal and send the preprocessed healthy side facial nerve signal to the decoding unit. The decoding unit generates a healthy side facial motion trajectory according to the data change characteristics in the preprocessed healthy side facial nerve signal.

3. The closed-loop repair system for facial paralysis according to claim 1, characterized in that: The neural signal acquisition module is connected to the PEDOT:PSS flexible neural electrode through FPC to collect the neural signals of the healthy side.

4. The facial paralysis closed-loop repair system according to claim 1, characterized in that: The neural signal acquisition module transmits the healthy side neural signal to the neural signal decoding module via an air interface based on low-power Bluetooth.

5. The facial paralysis closed-loop repair system according to claim 1, characterized in that: The stimulation encoding module transmits the stimulation configuration information to the stimulation execution module via an air interface based on low-power Bluetooth.

6. The facial paralysis closed-loop repair system according to claim 1, characterized in that: The stimulation execution module comprises a stimulation instruction unpacking unit, a stimulation configuration unit and a stimulation unit, wherein the stimulation configuration unit is connected to the stimulation instruction unpacking unit and the stimulation unit respectively; The stimulation instruction unpacking unit is used to extract the stimulation information in the stimulation configuration information and send the stimulation information to the stimulation configuration unit. The stimulation configuration unit controls the stimulation unit to stimulate the paralyzed facial nerve based on the stimulation information.

7. A closed-loop repair method for facial paralysis, characterized in that: Applicable to the facial paralysis closed-loop repair system according to any one of claims 1 to 6, the method comprising: Get healthy side nerve signals; Decoding the healthy side facial nerve signal to generate a healthy side facial motion trajectory; Acquiring the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face according to the movement trajectory of the healthy side face; Generate stimulation configuration information according to the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face; The paralyzed facial nerve is stimulated according to the stimulation configuration information.

8. The closed-loop repair method for facial paralysis according to claim 7, characterized in that: The step of obtaining the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face according to the movement trajectory of the healthy side face includes: Extracting motion events from the healthy side facial motion trajectory; Establish a response model between the stimulation parameters of the paralyzed side and the facial motion trajectory of the paralyzed side; The motion intensity and time interval information corresponding to the facial motion trajectory of the paralyzed side is obtained according to the response model and the motion event.

9. The closed-loop repair method for facial paralysis according to claim 7, characterized in that: Generating stimulation configuration information according to the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side face includes: Extracting at least one of the stimulation amplitude, stimulation pulse width and stimulation frequency from the movement intensity and time interval information corresponding to the movement trajectory of the paralyzed side face, and encoding it in the form of bytes; The bytes are spliced ​​to form stimulation configuration information according to the order in which the motion intensity and time interval information corresponding to the motion trajectory of the paralyzed side face occur.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions; the programs or instructions enable a computer to execute the steps of the method according to any one of claims 7 to 9.

Images