Post-stroke rehabilitation system and control method based on brain-computer interface
Patent Information
- Application Number
- CN202610983652.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-02
- Publication Date
- 2026-09-25
AI Technical Summary
目前临床治疗方法（包括手术与非手术疗法）均无法恢复麻痹眼外肌的功能性收缩，亦无法实现双侧眼球的协同、对称运动
本申请提供了一种基于脑机接口的眼运动神经麻痹后修复系统及控制方法，该系统包括：信号采集与解码模块、刺激决策与编码模块和刺激执行模块。信号采集与解码模块能够精准实时捕捉健侧眼外肌的肌电信号，避免无效信号干扰后续处理流程；刺激决策与编码模块可依托健侧眼球实时运动参数结合预设响应模型，快速生成适配患侧眼外肌的个性化电刺激参数，实现刺激方案的精准定制化输出，贴合患侧眼部生理状态与健侧运动同步需求，杜绝通用刺激参数的适配性差问题；刺激执行模块能够严格按照定制化刺激参数生成标准电脉冲并精准施加于患侧眼外肌，保障电刺激的精准执行与稳定输出，让患侧眼外肌跟随健侧眼球同步完成共轭运动，实现双侧眼球运动的精准协同。本系统整体通过信号精准识别解码、个性化刺激参数智能生成、闭环精准刺激执行的全流程协同，可实时驱动患侧眼球与健侧眼球完成同步、对称的眼球运动，有效矫正眼球运动失调问题，大幅提升双眼运动同步精度与刺激控制精准度，同时规避非目标运动的误刺激，兼顾系统运行稳定性与康复干预的安全性、有效性。
Smart Images
Figure CN122805977A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of brain-computer interface technology, and in particular to a brain-computer interface-based eye motor nerve palsy repair system and control method. Background Technology
[0002] Oculomotor nerve palsy leads to denervation of the extraocular muscles on the affected side, causing eye movement disorders, strabismus, and diplopia, severely impacting patients' visual function and quality of life. Current clinical treatments (including surgical and non-surgical methods) cannot restore the functional contraction of the paralyzed extraocular muscles, nor can they achieve coordinated and symmetrical bilateral eye movements. Previous techniques have not established a closed-loop repair system based on brain-computer interfaces and neural prostheses, making it difficult to achieve effective control of the paralyzed extraocular muscles and coordinated reconstruction of bilateral eye movements.
[0003] Eye movements are highly symmetrical. Hering's law of eye movements states that during eye movements, the central nervous system synchronously sends equal amounts of nerve impulses to the extraocular muscles of both eyes, achieving bilateral symmetrical and coordinated eye movements. Accordingly, the electromyography of the extraocular muscles on the healthy side can serve as a signal source to drive the movement of the extraocular muscles on the paralyzed side. This invention is designed based on this principle. Summary of the Invention
[0004] The purpose of this application is to provide a brain-computer interface-based system and control method for repairing oculomotor nerve palsy. This system can drive the paralyzed extraocular muscles on the affected side and their counterparts to move by decoding the electromyographic signals of the extraocular muscles on the healthy side, thereby restoring spontaneous, symmetrical, and coordinated eye movements on both sides after oculomotor nerve palsy.
[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a brain-computer interface-based eye motor nerve palsy recovery system, the system comprising: The signal acquisition and decoding module is used to acquire the electromyographic signals of the healthy extraocular muscles in real time, and decode the electromyographic signals of the healthy extraocular muscles in combination with the eye movement-electromyographic signal relationship model to obtain the real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: motion direction, motion amplitude and motion speed.
[0006] The stimulation decision and encoding module is used to generate personalized stimulation parameters for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball, combined with eyeball motion symmetry and a pre-established electrical stimulation-eyeball motion response model; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration.
[0007] The stimulation execution module is used to generate electrical pulses based on the stimulation parameters and apply electrical stimulation to the extraocular muscles on the affected side.
[0008] Optionally, the signal acquisition and decoding module includes: an implantable recording electrode, a signal amplifier, an analog-to-digital converter, a microprocessor, and a wireless communication unit.
[0009] The implanted recording electrode has its tail end connected to the input interface of the signal acquisition and decoding module via a flexible lead.
[0010] The signal amplifier, the analog-to-digital converter, the microprocessor, and the wireless communication unit are connected to the implanted recording electrode via a subcutaneous tunnel. The implantable recording electrode is used to collect electromyographic signals of the healthy extraocular muscles in real time.
[0011] The signal amplifier is used to amplify and preprocess the electromyographic signal of the healthy extraocular muscle to obtain preprocessed data.
[0012] The analog-to-digital converter is used to convert the preprocessed data into a digital signal and input it into the microprocessor in the form of a data stream.
[0013] The microprocessor is used to extract time-domain and frequency-domain features from the digital signal to obtain a feature vector, and to decode the real-time motion parameters of the healthy eyeball from the feature vector using an eye movement-electromyography signal relationship model.
[0014] The wireless communication unit is used to send the real-time motion parameters of the healthy eyeball to the stimulus decision and encoding module.
[0015] Optionally, the preprocessing includes: bandpass filtering, power frequency notch filtering, signal segmentation, differential filtering, wavelet transform denoising, and an adaptive denoising algorithm based on noise feature learning.
[0016] Optionally, the expression for the eye movement-electromyography signal relationship model is: [A,V,Dir,latency]=F_EMGEye(Features); Here, Features is the input feature vector, containing time-domain and frequency-domain features extracted from the electromyography (EMG) signal of the healthy extraocular muscles; the time-domain features include root mean square, mean absolute value, waveform length, peak-to-peak value, variance, and slope; the frequency-domain features include median frequency, average power frequency, peak frequency, and band power; F_EMGEye is a mapping function pre-established using a machine learning algorithm; A is the decoded eye movement amplitude; V is the decoded eye movement velocity; Dir is the decoded eye movement direction; and latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect.
[0017] Optionally, the stimulus decision and encoding module includes: a first wireless receiving unit and a central processing unit.
[0018] The first wireless receiving unit is used to receive real-time motion parameters of the healthy eyeball.
[0019] The central processing unit is used to generate personalized stimulation parameters for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball and the electrical stimulation-eye movement response model.
[0020] Optionally, the stimulus decision and encoding module is an externally worn device.
[0021] Optionally, the expression for the electrical stimulation-eye movement response model is: [A_evoked, V_evoked, Dir_evoked, latency]=f_stimeye(Pulse_amp, Pulse_width, Frequency, Duration); Where A_evoked is the amplitude of eye movement induced by electrical stimulation; V_evoked is the velocity of eye movement induced by electrical stimulation; Dir_evoked is the direction of eye movement induced by electrical stimulation; latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect; Pulse_amp is the pulse amplitude of electrical stimulation; Pulse_width is the pulse width of electrical stimulation; Frequency is the frequency of electrical stimulation; Duration is the duration of electrical stimulation; and f_stimeye is the eye movement response function.
[0022] Optionally, the stimulation execution module includes: a second wireless receiving unit, a stimulation source, and an implantable stimulation electrode.
[0023] The second wireless receiving unit is used to receive the stimulation parameters.
[0024] The stimulation source has an input end connected to the second wireless receiving unit and an output end connected to the implantable stimulation electrode via a wire. It is used to generate electrical pulses according to the stimulation parameters and conduct the electrical pulses to the implantable stimulation electrode.
[0025] The implantable stimulation electrode is used to apply electrical stimulation to the extraocular muscles on the affected side according to the electrical pulse.
[0026] Optionally, the input end of the stimulus source is connected to the second wireless receiving unit via SPI, UART, or I2C.
[0027] Secondly, this application provides a control method for a brain-computer interface-based eye motor nerve palsy recovery system, wherein the brain-computer interface-based eye motor nerve palsy recovery system is any of the systems described above, and the control method includes: The electromyographic signals of the healthy extraocular muscles are acquired in real time, and combined with the eye movement-electromyographic signal relationship model, the electromyographic signals of the healthy extraocular muscles are decoded to obtain the real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: motion direction, motion amplitude, and motion speed.
[0028] Based on the real-time motion parameters of the healthy eyeball, combined with the eyeball motion symmetry and the pre-established electrical stimulation-eyeball motion response model, personalized stimulation parameters for the extraocular muscles of the affected side are generated; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration.
[0029] An electrical pulse is generated based on the stimulation parameters; the electrical pulse is used to apply electrical stimulation to the extraocular muscles on the affected side.
[0030] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a brain-computer interface-based system and control method for the repair of oculomotor nerve palsy. The system includes a signal acquisition and decoding module, a stimulation decision and encoding module, and a stimulation execution module. The signal acquisition and decoding module can accurately capture the electromyographic signals of the healthy extraocular muscles in real time, avoiding interference from invalid signals in subsequent processing. The stimulation decision and encoding module can quickly generate personalized electrical stimulation parameters adapted to the affected extraocular muscles based on the real-time motion parameters of the healthy eyeball and a preset response model, achieving precise and customized output of the stimulation plan, conforming to the physiological state of the affected eye and the synchronous movement needs of the healthy eyeball, and eliminating the problem of poor adaptability of general stimulation parameters. The stimulation execution module can strictly generate standard electrical pulses according to the customized stimulation parameters and accurately apply them to the affected extraocular muscles, ensuring accurate execution and stable output of electrical stimulation, allowing the affected extraocular muscles to complete conjugate movements synchronously with the healthy eyeball, achieving precise coordination of bilateral eyeball movements. This system, through precise signal recognition and decoding, intelligent generation of personalized stimulation parameters, and closed-loop precise stimulation execution, enables real-time synchronous and symmetrical eye movements between the affected and healthy eyes. It effectively corrects eye movement disorder, significantly improves the synchronization accuracy of binocular movements and the precision of stimulation control, while avoiding false stimulation of non-target movements, thus ensuring both system stability and the safety and effectiveness of rehabilitation intervention. Attached Figure Description
[0031] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0032] Figure 1 A structural block diagram of a brain-computer interface-based eye motor nerve palsy repair system provided in one embodiment of this application; Figure 2 A flowchart illustrating a control method for a brain-computer interface-based eye motor nerve palsy recovery system according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0034] This application relates to a closed-loop neural prosthesis system driven by physiological signals, used to repair the loss of oculomotor coordination function after oculomotor nerve palsy, which is fundamentally different from existing neuromodulation techniques (such as deep brain stimulation for Parkinson's disease). Deep brain stimulation for Parkinson's disease usually relies on preset parameters or the detection of abnormal discharge signals in the deep brain (such as beta waves) to trigger stimulation. Its control objective is to inhibit the pathological discharge of the basal ganglia circuit, which belongs to the negative feedback regulation mechanism.
[0035] This application employs a "healthy side drives the affected side" positive-phase following accommodation strategy. The driving signal originates from the physiological electromyographic signal of the extraocular muscles on the healthy side, which accurately reflects the patient's eye movement intention. The system decodes the movement intention on the healthy side in real time and drives the conjugate muscles on the affected side to contract synchronously according to the Hering rule of bilateral eye movement, thereby reconstructing the natural coordinated movement of both eyes. In short, Parkinson's DBS works by "detecting abnormalities → inhibiting abnormalities," while this application works by "detecting the intention on the healthy side → driving the affected side to follow," representing a fundamental difference in signal source, control target, and physiological basis.
[0036] Compared with conventional brain-computer interface (BCI) technologies (such as BCI systems for limb movement disorders), this application represents a significant breakthrough in both technical approach and implementation path. Conventional BCIs typically rely on decoding motor intentions from the central nervous system (such as motor cortical EEG and neuronal firing) to control external prostheses or stimulate paralyzed muscles. The technical challenges lie in the acquisition of central signals (often requiring intracranial electrode implantation), high-precision decoding, and complex human-computer interaction algorithms. In contrast, this application proposes a "healthy-side-driven-affected-side" strategy based on peripheral electromyography (EMG) signals, specifically addressing the unique physiological basis of oculomotor nerve palsy. This strategy requires only the implantation of recording electrodes in the healthy extraocular muscles, which then drive the contraction of the conjugate muscles on the affected side in real time, without involving complex central signal decoding. This design fully utilizes the inherent bilateral synergistic mechanism of eye movement (Hering's rule), where the conjugate muscles of both eyes always receive equal amounts of nerve impulses simultaneously. Therefore, the EMG signals from the healthy side can directly serve as the "command template" for movement on the affected side, avoiding the uncertainty and high computational requirements of central decoding. The technical solution of this application has been experimentally verified in a rabbit animal model of abducens nerve palsy constructed by our team. The closed-loop system constructed in this application can effectively induce the paralyzed eyeball to produce symmetrical abducens movement that is synchronous with the adduction movement of the healthy eyeball, successfully realizing the symmetrical reconstruction of bilateral eyeball movement, and verifying the technical feasibility and effectiveness of this application.
[0037] Furthermore, compared to conventional brain-computer interfaces used in limb function reconstruction, this system is more in line with the anatomical and physiological characteristics of small extraocular muscles and highly coordinated conjugate muscles, realizing a paradigm shift from "central drive" to "peripheral follow-up" and providing a new technical path for the repair of oculomotor nerve palsy.
[0038] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0039] In one exemplary embodiment, such as Figure 1 As shown, a brain-computer interface-based eye motor nerve palsy repair system is provided, the system comprising: The signal acquisition and decoding module is used to acquire the electromyographic signals of the healthy extraocular muscles in real time, and decode the electromyographic signals of the healthy extraocular muscles in combination with the eye movement-electromyographic signal relationship model to obtain the real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: motion direction, motion amplitude and motion speed.
[0040] The stimulation decision and encoding module is used to generate personalized stimulation parameters for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball, combined with eyeball motion symmetry and a pre-established electrical stimulation-eyeball motion response model; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration.
[0041] The stimulation execution module is used to generate electrical pulses based on the stimulation parameters and apply electrical stimulation to the extraocular muscles on the affected side.
[0042] This application proposes a novel paradigm for oculomotor repair: "healthy side drives affected side." Based on the bilateral synergistic mechanism of oculomotor movement, it is the first to apply brain-computer interface and neural prosthesis technology to the repair of oculomotor nerve palsy. By recording and decoding the electromyographic signals of the healthy side's extraocular muscles, it provides a physiological basis for dynamic stimulation of the paralyzed side. Simultaneously, it constructs a closed-loop neural prosthesis system integrating signal acquisition, decoding, stimulation decision-making, and execution, possessing real-time control capabilities and demonstrating clinical translational potential.
[0043] As an optional implementation, the signal acquisition and decoding module includes: an implantable recording electrode, a motion type recognition unit, a signal amplifier, an analog-to-digital converter, a microprocessor, and a wireless communication unit.
[0044] The implanted recording electrode has its tail end connected to the input interface of the signal acquisition and decoding module via a flexible lead.
[0045] The signal amplifier, the analog-to-digital converter, the microprocessor, and the wireless communication unit are connected to the implanted recording electrode via a subcutaneous tunnel.
[0046] The implantable recording electrode is used to collect electromyographic signals of the healthy extraocular muscles in real time.
[0047] The signal amplifier is used to amplify and preprocess the electromyographic signal of the healthy extraocular muscle to obtain preprocessed data. The preprocessing includes: bandpass filtering, power frequency notch filtering, signal segmentation, differential filtering, wavelet transform denoising, and an adaptive denoising algorithm based on noise feature learning.
[0048] The analog-to-digital converter is used to convert the preprocessed data into a digital signal and input it into the microprocessor in the form of a data stream.
[0049] The microprocessor is used to extract time-domain and frequency-domain features from the digital signal to obtain a feature vector, and to decode the real-time motion parameters (direction of motion, amplitude of motion, and speed of motion) of the healthy eyeball from the feature vector using an eye movement-electromyography signal relationship model.
[0050] The wireless communication unit is used to send the real-time motion parameters of the healthy eyeball to the stimulus decision and encoding module.
[0051] Specifically, the eye movement-electromyography signal relationship model is established based on the eye movement decoding database. It is a machine learning regression model that takes the time domain characteristics (root mean square, mean absolute value, waveform length, peak-to-peak value, variance and slope, etc.) and frequency domain characteristics (median frequency, average power frequency, peak frequency, band power, etc.) of the electromyography signal of the healthy extraocular muscles as input and the decoded eye movement amplitude, velocity and direction as output.
[0052] The expression for the eye movement-electromyographic signal relationship model is as follows: [A,V,Dir,latency]=F_EMGEye(Features); Here, Features is the input feature vector, containing time-domain and frequency-domain features extracted from the electromyography (EMG) signal of the healthy extraocular muscles; the time-domain features include root mean square, mean absolute value, waveform length, peak-to-peak value, variance, and slope; the frequency-domain features include median frequency, average power frequency, peak frequency, and band power; F_EMGEye is a mapping function pre-established using a machine learning algorithm; A is the decoded eye movement amplitude; V is the decoded eye movement velocity; Dir is the decoded eye movement direction; and latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect.
[0053] As an optional implementation, the stimulus decision and encoding module includes a first wireless receiving unit and a central processing unit. The stimulus decision and encoding module is externally wearable.
[0054] The first wireless receiving unit is used to receive the decoded real-time motion parameters (motion direction, motion amplitude, and motion speed) of the healthy eyeball via Bluetooth.
[0055] The central processing unit is used to generate personalized stimulation parameters (pulse amplitude, pulse width, frequency, and stimulation duration) for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball and the electrical stimulation-eye movement response model.
[0056] The electrical stimulation-ocular motion response model is pre-established and stored in the central processing unit. It describes the quantitative relationship between the electrical stimulation parameters applied to the extraocular muscles on the affected side and the induced ocular motion response.
[0057] The expression for the electrical stimulation-eye movement response model is: [A_evoked, V_evoked, Dir_evoked, latency]=f_stimeye(Pulse_amp, Pulse_width, Frequency, Duration); Where A_evoked is the amplitude of eye movement induced by electrical stimulation; V_evoked is the velocity of eye movement induced by electrical stimulation; Dir_evoked is the direction of eye movement induced by electrical stimulation; latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect; Pulse_amp is the pulse amplitude of electrical stimulation; Pulse_width is the pulse width of electrical stimulation; Frequency is the frequency of electrical stimulation; Duration is the duration of electrical stimulation; and f_stimeye is the eye movement response function.
[0058] The model takes as input the desired eye movement parameters (direction, amplitude, and velocity) and outputs as stimulation parameters (pulse amplitude, pulse width, frequency, and duration). The model is obtained through individualized stimulation experiments and stored in the form of lookup tables or polynomial fitting coefficients.
[0059] As an optional implementation, the stimulation execution module includes: a second wireless receiving unit, a stimulation source, and an implantable stimulation electrode.
[0060] The second wireless receiving unit is used to receive the stimulation parameters.
[0061] The stimulation source has an input end connected to the second wireless receiving unit and an output end connected to the implantable stimulation electrode via a wire. It is used to generate electrical pulses according to the stimulation parameters and conduct the electrical pulses to the implantable stimulation electrode.
[0062] Specifically, the input end of the stimulus source is connected to the second wireless receiving unit via SPI, UART (TTL) or I2C.
[0063] The implanted stimulation electrode is used to apply electrical stimulation to the extraocular muscles on the affected side according to the electrical pulse, thereby inducing muscle contraction.
[0064] In summary, this application has the following effects: 1. Functional recovery: For the first time, functional electrical stimulation control of denervated extraocular muscles is achieved, restoring the contractile ability of the extraocular muscles on the affected side (paralyzed side), overcoming the limitation of existing therapies that cannot restore muscle motor function.
[0065] 2. Bilateral synergistic movement reconstruction: Based on the electromyographic signal of the healthy side driving the contraction of the concomitant muscle on the affected side, symmetrical movement of the bilateral eyeballs is achieved, which significantly improves clinical symptoms such as diplopia in all directions and enhances the patient's visual function and quality of life.
[0066] 3. System closed-loop intelligent control: Construct a complete closed-loop system from signal acquisition, decoding, decision-making to stimulus execution, with adaptive adjustment capabilities to improve the system's cross-individual performance.
[0067] In one exemplary embodiment, such as Figure 2 As shown, a control method for a brain-computer interface-based eye motor nerve palsy recovery system is provided. The brain-computer interface-based eye motor nerve palsy recovery system is the system described above. The control method includes: S1: Real-time acquisition of electromyographic signals of the healthy extraocular muscles, combined with an eye movement-electromyographic signal relationship model, decodes the electromyographic signals of the healthy extraocular muscles to obtain real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: direction of movement, amplitude of movement, and speed of movement.
[0068] S2: Based on the real-time motion parameters of the healthy eyeball, combined with the eyeball motion symmetry and the pre-established electrical stimulation-eyeball motion response model, generate personalized stimulation parameters for the extraocular muscles of the affected side; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration.
[0069] S3: Generate an electrical pulse according to the stimulation parameters; the electrical pulse is used to apply electrical stimulation to the extraocular muscles on the affected side.
[0070] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores electromyographic signals of the bilateral extraocular muscles. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a control method for a brain-computer interface-based oculomotor nerve palsy repair system.
[0071] Figure 3The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0072] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0073] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0074] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations and be authorized by the owner of the corresponding device.
[0075] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0076] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0077] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0078] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A brain-computer interface-based eye motor nerve palsy repair system, characterized in that, The system includes: The signal acquisition and decoding module is used to acquire the electromyographic signals of the healthy extraocular muscles in real time, and decode the electromyographic signals of the healthy extraocular muscles in combination with the eye movement-electromyographic signal relationship model to obtain the real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: motion direction, motion amplitude and motion speed. The stimulation decision and encoding module is used to generate personalized stimulation parameters for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball, combined with eyeball motion symmetry and a pre-established electrical stimulation-eyeball motion response model; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration; The stimulation execution module is used to generate electrical pulses based on the stimulation parameters and apply electrical stimulation to the extraocular muscles on the affected side.
2. The eye motor nerve palsy repair system based on brain-computer interface according to claim 1, characterized in that, The signal acquisition and decoding module includes: an implantable recording electrode, a signal amplifier, an analog-to-digital converter, a microprocessor, and a wireless communication unit; The implantable recording electrode has its tail end connected to the input interface of the signal acquisition and decoding module via a flexible lead. The signal amplifier, the analog-to-digital converter, the microprocessor, and the wireless communication unit are connected to the implanted recording electrode via a subcutaneous tunnel. The implantable recording electrode is used to collect electromyographic signals of the contralateral extraocular muscles in real time. The signal amplifier is used to amplify and preprocess the electromyographic signal of the healthy extraocular muscle to obtain preprocessed data. The analog-to-digital converter is used to convert the preprocessed data into a digital signal and input it into the microprocessor in the form of a data stream; The microprocessor is used to extract time-domain and frequency-domain features from the digital signal to obtain a feature vector, and to decode the real-time motion parameters of the healthy eyeball from the feature vector using an eye movement-electromyography signal relationship model. The wireless communication unit is used to send the real-time motion parameters of the healthy eyeball to the stimulus decision and encoding module.
3. The brain-computer interface-based eye motor nerve palsy repair system according to claim 2, characterized in that, The preprocessing includes: bandpass filtering, power frequency notch filtering, signal segmentation, differential filtering, wavelet transform denoising, and an adaptive denoising algorithm based on noise feature learning.
4. The eye motor nerve palsy repair system based on brain-computer interface according to claim 1, characterized in that, The expression for the eye movement-electromyographic signal relationship model is as follows: [A,V,Dir,latency]=F_EMGEye(Features); Here, Features is the input feature vector, containing time-domain and frequency-domain features extracted from the electromyography (EMG) signal of the healthy extraocular muscles; the time-domain features include root mean square, mean absolute value, waveform length, peak-to-peak value, variance, and slope; the frequency-domain features include median frequency, average power frequency, peak frequency, and band power; F_EMGEye is a mapping function pre-established using a machine learning algorithm; A is the decoded eye movement amplitude; V is the decoded eye movement velocity; Dir is the decoded eye movement direction; and latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect.
5. The eye motor nerve palsy repair system based on brain-computer interface according to claim 1, characterized in that, The stimulus decision and encoding module includes: a first wireless receiving unit and a central processing unit; The first wireless receiving unit is used to receive the real-time motion parameters of the healthy eyeball; The central processing unit is used to generate personalized stimulation parameters for the extraocular muscles on the affected side based on the real-time motion parameters of the healthy eyeball and the electrical stimulation-eye movement response model.
6. The eye motor nerve palsy repair system based on brain-computer interface according to claim 1, characterized in that, The stimulus decision and coding module is an externally worn device.
7. The eye motor nerve palsy repair system based on brain-computer interface according to claim 1, characterized in that, The expression for the electrical stimulation-eye movement response model is: [A_evoked, V_evoked, Dir_evoked, latency]=f_stimeye(Pulse_amp, Pulse_width, Frequency, Duration); Where A_evoked is the amplitude of eye movement induced by electrical stimulation; V_evoked is the velocity of eye movement induced by electrical stimulation; Dir_evoked is the direction of eye movement induced by electrical stimulation; latency is the latency of eye movement, i.e., the time from impulse transmission to the generation of a motor effect; Pulse_amp is the pulse amplitude of electrical stimulation; Pulse_width is the pulse width of electrical stimulation; Frequency is the frequency of electrical stimulation; Duration is the duration of electrical stimulation; and f_stimeye is the eye movement response function.
8. The brain-computer interface-based eye motor nerve palsy repair system according to claim 1, characterized in that, The stimulation execution module includes: a second wireless receiving unit, a stimulation source, and an implantable stimulation electrode; The second wireless receiving unit is used to receive the stimulation parameters; The stimulation source has an input end connected to the second wireless receiving unit and an output end connected to the implantable stimulation electrode via a wire, used to generate electrical pulses according to the stimulation parameters and conduct the electrical pulses to the implantable stimulation electrode; The implantable stimulation electrode is used to apply electrical stimulation to the extraocular muscles on the affected side according to the electrical pulse.
9. The brain-computer interface-based eye motor nerve palsy repair system according to claim 8, characterized in that, The input end of the stimulus source is connected to the second wireless receiving unit via SPI, UART or I2C.
10. A control method for a brain-computer interface-based eye motor nerve post-paralysis repair system, wherein the brain-computer interface-based eye motor nerve post-paralysis repair system is the system described in any one of claims 1-9, characterized in that, The control method includes: The electromyographic signals of the healthy extraocular muscles are acquired in real time, and combined with the eye movement-electromyographic signal relationship model, the electromyographic signals of the healthy extraocular muscles are decoded to obtain the real-time motion parameters of the healthy eyeball; the real-time motion parameters of the healthy eyeball include: motion direction, motion amplitude, and motion speed. Based on the real-time motion parameters of the healthy eyeball, combined with the symmetry of eyeball motion and the pre-established electrical stimulation-eyeball motion response model, personalized stimulation parameters for the extraocular muscles of the affected side are generated; the stimulation parameters include: pulse amplitude, pulse width, frequency and stimulation duration; An electrical pulse is generated based on the stimulation parameters; the electrical pulse is used to apply electrical stimulation to the extraocular muscles on the affected side.