A system and method for monitoring the spinal cord and nerves during transforaminal endoscopic surgery

Abstract

The present invention discloses a system and method for monitoring the spinal cord and nerves during percutaneous endoscopic lumbar disc surgery. In the system, myoelectric electrodes are used to conduct myoelectric signals of a target; angle sensors are used to sense the bending angle signals of corresponding joints when the target is performing limb movements; microphones are used to collect voice information during the operation and convert it into analog electrical signals; collectors are used to synchronously and in real time collect analog electrical signals from the myoelectric electrodes, the angle sensors and the microphones, and convert these analog electrical signals into digital electrical signals, which are then sent to a processor; the processor analyzes and processes the received digital signals, determines whether the target has completed relevant limb movements according to the instructions contained in the voice information, obtains the status information of the spinal cord and nerves, and displays it via the display. The present invention can accurately monitor the status of the spinal cord and nerves in real time and without interruption.

Description

Technical Field

[0001] The present invention relates to the field of electrophysiological detection technology, and more specifically, to a system and method for spinal cord and nerve monitoring in transforaminal endoscopic surgery. Background Art

[0002] Transforaminal endoscopic lumbar discectomy is an effective treatment for spinal cord lesions such as spinal deformity, spinal canal stenosis, and intervertebral disc herniation. Compared with traditional open surgeries such as posterior interbody fusion, transforaminal endoscopic lumbar discectomy has the advantages of less intraoperative bleeding, less trauma, and faster postoperative recovery, and has been increasingly widely used in clinical practice. However, as a minimally invasive surgery, the transforaminal endoscopic lumbar discectomy lacks anatomical landmarks under direct vision, and the operating space is relatively small. When performing spinal canal decompression or pedicle screw placement, it is easy to damage nerves and cause serious complications.

[0003] In order to monitor the status of the spinal cord and nerves in real time during surgery and avoid nerve damage, the main technologies currently used include wake-up tests, somatosensory evoked potentials (SEP), motor evoked potentials (MEP) and intraoperative electromyography (EMG).

[0004] The awakening test determines whether the patient's spinal cord and nerve functions are normal by observing the patient's limb movements. When performing the awakening test, the depth of anesthesia needs to be lowered during the operation. After the patient is awakened, observe whether he can complete the relevant limb movements according to the doctor's instructions. When the autonomous movement is completed, the depth of anesthesia is immediately deepened to complete the operation.

[0005] Somatosensory evoked potentials are time-locked potentials induced by electrical stimulation of peripheral sensory nerves or mixed peripheral nerves. They ascend along the large fiber somatosensory pathway to the sensory cortex of the brain. In clinical applications, electrical stimulation can be applied to peripheral nerves such as the median nerve of the upper limb or the posterior tibial nerve of the lower limb, depending on the spinal cord segment to be monitored and the requirements of the surgery. The corresponding neurophysiological signals are recorded on the nerve trunk and scalp, and the state of the spinal cord and nerves is obtained by analyzing the signal characteristics.

[0006] Motor evoked potentials are motor compound potentials recorded in the spinal cord, peripheral nerves or target muscles by electrically or magnetically stimulating the motor cortex of the brain. The potential waves induced by the motor cortex after being stimulated go down through the internal capsule to the medulla oblongata, and then continue to go down in the corticospinal lateral funiculus to the anterior horn cells of the spinal cord after passing through the pyramidal decussation, activating motor neurons and causing the muscles they control to contract. The corresponding potential changes can be recorded in the epidural space and muscles, and the state of the spinal cord and nerves can be known by analyzing the changes.

[0007] Intraoperative EMG monitoring collects and analyzes the electromyographic signals of specific muscles to identify the status of the relevant spinal cord and nerves. Depending on the way the electromyographic signals are generated, it can be divided into spontaneous and induced EMG monitoring. The former is mainly generated by traction or mechanical stimulation during surgery, which causes nerve root irritation, and records spontaneous electromyographic activity in the muscles innervated by the nerve roots; the latter electrically stimulates surgical instruments or spinal nerve roots, collects and analyzes the neurophysiological feedback signals of the corresponding nerve roots that innervate the muscles, to determine the status of the spinal cord and nerves.

[0008] After analysis, in practical application, the existing technology mainly has the following defects.

[0009] 1) As the "gold standard" for intraoperative spinal cord and nerve monitoring, the awakening test can directly obtain the patient's central and peripheral nerve control of limb activities. However, this requires the doctor to observe and judge visually or touch, which is limited by the doctor's clinical experience and may lead to misjudgment. Moreover, this method can only be carried out at a limited time when the patient is awake, and it is impossible to monitor the spinal cord and nerve status in real time and continuously.

[0010] 2) Somatosensory evoked potentials, motor evoked potentials and intraoperative electromyography can achieve real-time uninterrupted monitoring, but these schemes must use weak neuroelectrophysiological signals to determine the state of the spinal cord and nerves. The normal and abnormal relationship between these signals and the integrity and damage of the spinal cord and nerves is not strictly corresponding, and there are false positives and false negatives. In addition, the amplitude of these signals is relatively weak, usually in the range of tens of microvolts to several millivolts, and is easily disturbed by various noises and artifacts during surgery. For example, noise and artifacts include 50Hz power frequency interference, stimulation artifacts, electromagnetic interference of instruments and equipment, and motion artifacts at the electrode and skin interface. The amplitude can reach hundreds of millivolts. Their presence increases the difficulty of neuroelectrophysiological signal waveform recognition and measurement, affecting the accuracy and reliability of spinal cord and nerve monitoring.

[0011] In summary, existing technologies such as wake-up test, somatosensory evoked potential, motor evoked potential, and intraoperative electromyography monitoring used in percutaneous endoscopic lumbar disc surgery have problems such as lack of objective quantitative standards, difficulty in waveform recognition and measurement, and low accuracy and reliability. Summary of the invention

[0012] The purpose of the present invention is to overcome the above-mentioned defects of the prior art and provide a system and method for spinal cord and nerve monitoring during transforaminal endoscopic surgery.

[0013] According to a first aspect of the present invention, a system for monitoring the spinal cord and nerves during transforaminal endoscopic surgery is provided. The system includes electromyographic electrodes, an angle sensor, a microphone, a collector, a processor, and a display, wherein:

[0014] The myoelectric electrodes are used to conduct myoelectric signals of the target;

[0015] The angle sensor is used to sense the bending angle signal of the corresponding joint when the target performs limb activities;

[0016] The microphone is used to collect voice information during the operation and convert it into an analog electrical signal;

[0017] The collector is used to synchronously and real-time collect analog electrical signals from the electromyographic electrodes, the angle sensor and the microphone, and convert these analog electrical signals into digital electrical signals, and then send them to the processor;

[0018] The processor analyzes and processes the received digital signal, determines whether the target completes the relevant limb activities according to the instructions contained in the voice information, obtains the status information of the spinal cord and nerves, and displays it via the display.

[0019] According to a second aspect of the present invention, a method for spinal cord and nerve monitoring during transforaminal endoscopic surgery is provided. The method comprises the following steps:

[0020] Acquire the target's electromyographic signals, the bending angle signals of the corresponding joints when the target performs limb movements, and collect the doctor's voice commands during the operation;

[0021] Determine whether the target completes relevant limb activities according to voice commands, obtain spinal cord and nerve status information, and output display results.

[0022] Compared with the prior art, the advantage of the present invention is that by synchronously collecting the electromyographic signals, joint bending angles and voice data of the patient's limb movements, these data are jointly analyzed and correlated to obtain objective quantitative standards for distinguishing the state of the spinal cord and nerves, and the state of the spinal cord and nerves can be accurately monitored in real time and uninterruptedly.

[0023] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0025] Figure 1 is a block diagram of a spinal cord and nerve monitoring system in transforaminal endoscopic surgery according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of a method for monitoring the spinal cord and nerves during transforaminal endoscopic surgery according to one embodiment of the present invention;

[0027] Figure 3is a schematic diagram of typical body movements according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0029] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0030] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0031] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0032] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0033] The present invention provides a system for spinal cord and nerve monitoring during transforaminal endoscopic surgery, which combines the advantages of existing wake-up tests and intraoperative electromyography monitoring technology. Figure 1 As shown, the system includes electromyographic electrodes, angle sensors, microphones, collectors, processors, displays, etc.

[0034] EMG electrodes are used to conduct myoelectric signals and can be of various types such as implantable electrodes or surface patch electrodes.

[0035] The angle sensor is used to sense the bending angle of the corresponding joint when the target patient performs limb movements under the doctor's instruction. For example, the angle sensor can be obtained by a displacement sensor composed of a potentiometer through displacement-angle conversion. Or if it is inconvenient to install and fix the angle sensor, an inertial measurement unit (IMU) is used instead.

[0036] The microphone is used to collect voice information during the operation and convert it into electrical signals. Through the voice command, it can be determined whether the collected patient's electromyographic signal or joint angle signal is related to the action command issued by the doctor to the patient. If not, it may be noise interference or spontaneous electromyographic signal. The microphone can use an existing commercial microphone.

[0037] The collector is used to synchronously and real-time collect analog electrical signals from the electromyographic electrodes, angle sensors and microphones, convert these analog electrical signals into digital electrical signals, and then send them to the processor.

[0038] The processor receives and processes data sent by the collector, including electromyographic signals, joint angle signals, voice information, etc., and performs digital filtering, feature extraction, electromyographic-joint angle relationship measurement, voice recognition, linear discriminant analysis, data storage and other analysis and processing on these data to determine whether the patient can complete relevant limb activities according to the doctor's instructions, and obtain the status information of the spinal cord and nerves. The processor can be a computer, a system on chip (System On Chip, SOC), a digital signal processor (Digital Signal Processor, DSP) and other devices that can realize specific logical functions through user programming.

[0039] The display shows the analysis and processing results of the processor. The status information of the spinal cord and nerves obtained by the processor analysis can be obtained from the display to prompt the doctor whether to continue the operation.

[0040] The system provided can be used to collect and analyze data such as the patient's electromyography, joint bending angle, and limb movement instructions given by the doctor to the patient during surgery, whether or not a wake-up test is performed, to achieve spinal cord and nerve monitoring. Figure 2 As shown, the method for monitoring the spinal cord and nerves includes the following steps.

[0041] Step S201, pasting electrodes, installing angle sensors and microphones.

[0042] First, before the operation, electromyography electrodes are attached to the patient, angle sensors are installed, and microphones are placed to collect the doctor's voice commands.

[0043] Depending on the depth of the monitored muscle, the myoelectric electrodes can be either implantable electrodes such as needle electrodes or surface patch electrodes such as silver / silver chloride gel electrodes. Surface patch electrodes are used to collect surface myoelectric signals, while implantable electrodes are used to collect deep myoelectric signals. The myoelectric electrodes are pasted on the muscles that control limb movement or the corresponding skin of the spinal cord or nerves that need to be monitored, and the pasting positions on both sides of the limbs are symmetrical. For example, if the L3 / L4 segment of the spine needs to be monitored, it can be placed on the vastus lateralis muscles of both legs; if the L4 / L5 segment of the spine needs to be monitored, it can be placed on the tibialis anterior muscles of both legs.

[0044] The angle sensor is installed at the active joint corresponding to the patient's limb movements to measure the angle of joint bending. The installation positions on both sides of the limbs are symmetrical.

[0045] In step S202, the patient completes preset intraoperative monitoring limb movements at different joint bending angles, and collects corresponding myoelectric and joint angle data.

[0046] After the sensors are attached and installed, the patient is instructed to complete the preset intraoperative monitoring limb movements at different joint bending angles, and the corresponding electromyographic signals and joint angle data are collected synchronously. Figure 3 As shown, you can also use actions such as lifting your legs and toes, and the actions you take correspond to the spinal nerves that need to be monitored. The myoelectric signals will be different with different joint bending angles. You can record multiple (such as 3 to 5) different myoelectric data at different bending angles, but they should all include the myoelectric data at the maximum angle.

[0047] Step S203, analyzing the electromyographic data, extracting features, and establishing a model for predicting joint angles using electromyographic data.

[0048] Filter the EMG data. For example, use digital filters such as high-pass filtering and power frequency notch filtering to filter out interference such as zero drift and power frequency noise. For the filtered EMG data, extract the time-frequency domain data features related to the joint angle, such as root mean square value, integral value, absolute average value, average power frequency, etc. Use common models such as linear discriminant analysis and back propagation neural network, take the time-frequency domain features corresponding to the EMG signal as input, and the joint bending angle as output to establish a model for predicting joint angles (or EMG prediction joint angle model). Use the collected EMG and joint angle sample data to train the model and obtain model parameters, such as weights and biases.

[0049] Step S204, start the surgery, collect electromyography, joint angle and voice data in real time and synchronously, and recognize the limb movement instructions issued by the doctor.

[0050] After the model training is completed, the transforaminal endoscopic surgery begins. General or local anesthesia can be performed according to the needs of the operation, but appropriate anesthetic drugs should be selected to avoid affecting the electromyographic signals of the muscles controlled by the monitored nerves. Figure 1 The system collects myoelectric, joint angle and voice data synchronously and continuously in real time, and performs pre-processing such as filtering on the data. Depending on the progress of the operation and the need for monitoring, the doctor chooses to wake up (general anesthesia) or not wake up (local anesthesia) the patient, and instructs the patient to complete the preset intraoperative monitoring limb movements. In order to accurately monitor the spinal cord and nerve status, the patient should be instructed to complete the movement instructions with the maximum bending angle or maximum force.

[0051] Step S205, determining whether a body movement instruction has been issued.

[0052] Perform real-time online recognition of voice data to analyze whether there are any action instructions given by doctors to patients.

[0053] Step S206, analyze and calculate the myoelectric characteristics and joint angle data after issuance, and calculate the difference with the corresponding data of the patient before the operation.

[0054] If it is detected that the doctor has issued relevant instructions, the electromyographic signal characteristics and maximum joint bending angle after the instructions are issued are analyzed and calculated, and the difference between the electromyographic signal characteristics or the maximum joint bending angle and the corresponding data of the patient before the operation is calculated. At the same time, the electromyographic data after the instructions are issued are used together with the electromyographic-joint angle prediction model established before the operation to predict the joint bending angle and calculate the difference with the actual value.

[0055] The obtained difference may include the difference of electromyographic signal characteristics, the difference between the maximum joint angle before and after the operation, or the excess value between the acquired joint bending angle and the joint bending angle predicted based on the model. The subsequent judgment using those differences can be set according to actual needs.

[0056] Step 207, determining whether the difference exceeds a set threshold.

[0057] If the above differences are all within the preset threshold range (S211), it means that the patient's spinal cord and nerve functions are normal, and the corresponding results are given on the display screen, prompting the doctor to perform the operation normally (step S212).

[0058] If the above differences all exceed the preset threshold range, it means that the patient has spinal cord or nerve damage, and an alarm is issued on the display screen to prompt the doctor to stop the operation (step S208); if only part of the data exceeds the threshold, the joint angle is analyzed based on the result of electromyography prediction. If the difference between the predicted angle and the actual angle is within the allowable error of the model (such as 5°), it means that the patient's spinal cord and nerve function are normal, and the maximum bending angle may not be reached due to anesthesia and other reasons. The patient can try to rest for a period of time before continuing to complete the action. Otherwise, it means that the patient's spinal cord and nerve function are abnormal.

[0059] During the operation, even if the limb movement command issued by the doctor is not detected (step S209), the electromyographic and joint bending angle data are still collected in real time and continuously. Detect whether the electromyographic data characteristics or joint angles exceed the preset threshold (for example, the root mean square value of the electromyography in the 200ms time window exceeds 20% of the corresponding value at the maximum bending angle, or the joint bending angle is greater than 15°). If so, after excluding interference from the patient's autonomous activities, external noise, etc., if the data abnormality still does not disappear, it indicates that there may be traction or mechanical stimulation of the nerve roots during the operation. At this time, the doctor should stop the operation and issue intraoperative monitoring limb movement instructions to the patient (step S210), and collect, analyze and judge the relevant data after the instructions are issued.

[0060] Store and analyze normal and abnormal data before and during surgery, optimize and improve threshold judgment criteria based on electromyographic data characteristics, big data analysis, doctor's judgment and other results, and continuously improve the accuracy and reliability of spinal cord and nerve monitoring (step S213).

[0061] In summary, compared with the prior art, the present invention has the following advantages:

[0062] 1) As an improvement on the existing "gold standard" of intraoperative spinal cord and nerve monitoring - awakening test, the present invention provides an objective quantitative standard for distinguishing the state of the spinal cord and nerves through real-time synchronous collection of electromyography, joint bending angle, voice and other data, and online analysis and correlation judgment, avoiding misjudgment caused by inaccurate visual or tactile judgment, insufficient clinical experience of doctors, etc., and improving the accuracy and reliability of intraoperative monitoring. In addition, it solves the problem that the existing awakening test cannot monitor the state of the spinal cord and nerves in real time and uninterruptedly.

[0063] 2) The present invention improves the anti-interference ability of the intraoperative monitoring system by collecting and analyzing multimodal physiological data such as electromyography, joint angles, and voice, avoiding the problems of waveform recognition and measurement difficulties and poor anti-interference ability caused by the existing somatosensory evoked potential, motor evoked potential, and intraoperative electromyography technologies that simply collect weak neural or electromyographic signals.

[0064] 3) The present invention collects patient data before surgery, establishes a model for predicting joint bending angles using electromyography, and applies it to the estimation of joint bending angles during surgery, thereby judging the state of the spinal cord and nerves and reducing the false positive rate of the judgment results.

[0065] 4) The present invention can continuously improve the accuracy and reliability of spinal cord and nerve monitoring by storing and analyzing normal and abnormal data before and during surgery, optimizing and improving the threshold judgment standard based on the characteristics of electromyographic data, big data analysis, doctor's judgment and other results. Through sufficient simulation test verification, the present invention can meet clinical needs and give more accurate clinical instructions.

[0066] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0067] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0068] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0069] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, Python, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0070] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0071] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0072] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0073] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0074] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A system for monitoring the spinal cord and nerves during transforaminal endoscopic surgery, comprising an electromyographic electrode, an angle sensor, a microphone, a collector, a processor and a display, wherein: The myoelectric electrodes are used to conduct myoelectric signals of the target; The angle sensor is used to sense the bending angle signal of the corresponding joint when the target performs limb activities; The microphone is used to collect voice information during the operation and convert it into an analog electrical signal; The collector is used to synchronously and real-time collect analog electrical signals from the electromyographic electrodes, the angle sensor and the microphone, and convert these analog electrical signals into digital electrical signals, and then send them to the processor; The processor analyzes and processes the received digital signal, determines whether the target completes the relevant limb movement according to the instruction contained in the voice information, obtains the state information of the spinal cord and nerves, and displays it via the display; The processor obtains the state information of the spinal cord and nerves according to the following steps: If it is detected according to the voice information that the doctor has issued a relevant instruction, the myoelectric characteristics and joint bending angle after the instruction is issued are collected; The electromyographic characteristics after the command is issued are input into the trained joint angle prediction model to predict the joint bending angle, and the difference between the predicted joint bending angle and the actual joint bending angle collected is calculated; If the corresponding differences under all instructions are within the set threshold range, the display prompts the doctor to perform the operation normally; If the corresponding differences under all instructions exceed the threshold range, the doctor is prompted to stop the operation via the display; If some of the differences corresponding to all the instructions exceed the threshold range, the prediction result of the joint angle prediction model is analyzed, and if the difference between the predicted joint bending angle and the actual joint bending angle is within the set allowable error range, the display prompts to continue to complete the action after a period of time; The joint angle prediction model is trained according to the following steps: Collect electromyographic signals during various limb activities and filter them to remove interference; For the filtered electromyographic signal, the time-frequency domain features related to the joint angle are extracted to construct a sample data set. Each sample reflects the corresponding relationship between the time-frequency domain features of the electromyographic signal and the joint bending angle. A joint angle prediction model is established, with the time-frequency domain features corresponding to the electromyographic signal as input and the bending angle of the joint as output, and the sample data set is used for training to obtain model parameters.

2. The system according to claim 1, characterized in that The myoelectric electrodes are implantable electrodes or surface patch electrodes.

3. The system according to claim 1, characterized in that The angle sensor is obtained by a displacement sensor composed of a potentiometer through displacement-angle conversion, or an inertial measurement unit is used.

4. The system according to claim 1, characterized in that The processor is a computer, a system-on-chip chip or a digital signal processor.

5. The system according to claim 1, characterized in that The joint angle prediction model is a linear discriminant analysis model or a neural network model.

6. The system according to claim 1, characterized in that During the procedure, the processor also performs the following steps: In the case where no voice information is detected, detect whether the data characteristics of the electromyographic signal or the joint bending angle exceeds the set threshold to determine whether an abnormality occurs; When it is determined that an abnormal situation has occurred, after eliminating the interference of the target's autonomous activities or external noise, if the abnormal situation still does not disappear, the doctor is prompted to stop the operation via the display.

Images