Electromyographic signal acquisition method, system and equipment for pain assessment and medium

Abstract

The invention discloses an electromyographic signal acquisition system and device for standard pose pain assessment and discrimination, and relates to the field of electromyographic acquisition, and the system comprises a pose detection module which is used for discriminating whether the pose of a person to be acquired is a specific standard pose; the electromyographic signal acquisition module is used for selecting a proper acquisition channel to perform signal acquisition according to the pose of the acquired person; according to the electromyographic signal acquisition system and device for standard pose pain assessment and discrimination, the pose of a person to be acquired is detected in real time by using an external camera and a wearable gyroscope sensor array, and is compared with specific standard pose model data in a pose comparison system; whether the posture of the collected person is a specific standard posture or not is judged through a clear and efficient method; the specific standard pose is designed according to a pain principle and a scientific experimental scheme, so that the electromyographic signal corresponding to the specific standard pose of the collected person can be used as an important index for pain assessment and treatment effect judgment.

Description

[0001] This application is a divisional application. The original application invention title is an electromyogram signal acquisition system and device for standard pose pain assessment and discrimination, the application number is 202410301539.4, and the application date is March 16, 2024. Technical Field

[0002] The present invention relates to electromyogram acquisition technology, and specifically relates to an electromyogram signal acquisition system and device for standard pose pain assessment and discrimination. Background Art

[0003] Electromyogram signal acquisition based on specific poses has been widely used in the field of pain assessment to enhance the in-depth understanding of the human physiological condition. Capturing the weak bioelectric signals generated in the muscle area under specific poses provides a novel and non-invasive approach for pain assessment. Electromyogram signal acquisition provides objective biofeedback information for medical professionals, helping to more accurately evaluate the pain condition and treatment effect of patients. This information can assist in formulating personalized treatment plans, improving treatment effects, and can be used to monitor the rehabilitation progress of patients. Electromyogram (EMG) is the superposition of motor unit action potentials (MUAP) of numerous muscle fibers in time and space. Among them, surface electromyogram signal (SEMG) is the comprehensive effect of superficial muscle EMG and the electrical activity on the nerve trunk on the skin surface, which can reflect the activity of the neuromuscular system to a certain extent and is an important bioinformation carrier for evaluating the motor function of the neuromuscular system. Electromyogram signal acquisition is a technology for measuring human muscle activity and has been widely used in fields such as research on motor control, diagnosis of muscle diseases, rehabilitation treatment, medical research, and clinical diagnosis.

[0004] [[ID=

[0005] First, existing methods lack a pose detection device. Users simply imitate the exercise instructions played in the video to perform limb movements, which may lead to deviations between the subject's pose and the set standard pose. Therefore, the obtained target electromyographic signals may not necessarily be generated by a specific standard pose. Second, the pose used in this method is not designed for pain assessment. Therefore, the acquired electromyographic signals cannot be used as indicators for pain assessment and treatment effect discrimination. Thus, a standard pose pain assessment and discrimination electromyographic signal acquisition system and device were developed. Summary of the Invention

[0006] The purpose of this invention is to provide an electromyography signal acquisition system and device for standard posture pain assessment and discrimination, so as to overcome the above-mentioned shortcomings in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an electromyographic signal acquisition system for standard posture pain assessment and discrimination, including a posture detection module for determining whether the posture of the subject being acquired is a specific standard posture;

[0008] The electromyography (EMG) signal acquisition module selects the appropriate acquisition channel for signal acquisition based on the subject's posture.

[0009] The electromyography (EMG) signal central processing unit is connected to the EMG signal acquisition module. It converts the EMG signals acquired by the EMG signal acquisition module into digital signals through an analog-to-digital converter (ADC). The ADC chip data is then sent to the host computer for visualization and data signal storage for subsequent signal data processing.

[0010] As a further optimization of the present invention, the pose detection module uses an external camera to optically capture the pose information of the subject based on the subject's movements, and then compares and judges it with the pose database in the system.

[0011] As a further optimization of the present invention, the pose detection module uses convolutional neural networks (CNN) and recurrent neural networks (RNN) to perform pose detection and action analysis, thereby improving the accuracy and robustness of signal judgment and detection.

[0012] As a further optimization of the present invention, the electromyography signal acquisition module is responsible for acquiring electromyography signals and performing amplification and filtering processing.

[0013] As a further optimization of the present invention, the electromyographic signal central processing unit performs signal conversion on the electromyographic signal acquired by the electromyographic signal acquisition module, converts the original signal into a digital signal, and sends it to the electromyographic signal storage device in the host computer for signal storage.

[0014] An electromyographic signal device for standard posture pain assessment and discrimination includes at least one processor;

[0015] And, a memory communicatively connected to the at least one processor;

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform an electromyographic signal acquisition system for standard posture pain assessment and discrimination as described in any of the above.

[0017] Compared with existing technologies, the present invention provides an electromyography signal acquisition system and device for standard posture pain assessment and discrimination. It uses an external camera and a wearable gyroscope sensor array to detect the posture of the subject in real time and compares it with the specific standard posture model data in the posture comparison system. It has a clear and efficient method to determine whether the posture of the subject is a specific standard posture.

[0018] The specific standard posture is designed based on the principles of pain and scientific experimental protocols. Therefore, the electromyographic signals corresponding to the specific standard posture of the subject can serve as an important indicator for pain assessment and treatment effect evaluation. Attached Figure Description

[0019] 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 recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0020] Figure 1 This is a schematic diagram illustrating a specific application of electromyography (EMG) signal acquisition according to an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of an electromyography signal acquisition system provided in an embodiment of the present invention;

[0022] Figure 3 A first schematic diagram of the structure of the human body for applying the electromyography signal acquisition device provided by the present invention;

[0023] Figure 4 The second schematic diagram shows the structure of the human body to which the electromyography signal acquisition device provided by the present invention is applied.

[0024] Explanation of reference numerals in the attached figures

[0025] 1. Camera; 2. Host computer algorithm diagnosis and information display system; 3. Wearable electromyography acquisition device; 4. Gyroscope sensor. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. The terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, unless otherwise explicitly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0028] Example 1:

[0029] Please see Figures 1-4 An electromyography signal acquisition system for standard posture pain assessment and discrimination includes a posture detection module for determining whether the subject's posture is a specific standard posture.

[0030] The pose detection module uses an external camera 1 for optical capture, obtains the position and pose information of the subject based on the subject's movements, and compares and judges it with the pose database in the system.

[0031] The pose detection module uses convolutional neural networks (CNN) and recurrent neural networks (RNN) for pose detection and motion analysis, which improves the accuracy and robustness of signal judgment and detection.

[0032] In this scheme, a gyroscope sensor 4 is also used to measure the angular velocity of the device, the position and orientation of the subject, and the changes in attitude. Based on the law of conservation of angular momentum, when the subject rotates around a specific axis and performs corresponding actions, a torque will be generated in the direction perpendicular to the rotation axis. The attitude angle and attitude change of the subject are calculated by numerical integration, and the attitude information is converted into Euler angles. This angle information is compared with the preset angles in the system database to determine whether it meets the position and attitude angle standard.

[0033] The electromyography (EMG) signal acquisition module selects the appropriate acquisition channel for signal acquisition based on the subject's posture.

[0034] The electromyography (EMG) signal acquisition module is responsible for acquiring EMG signals and performing amplification and filtering.

[0035] Specifically, the wearable electromyography (EMG) acquisition device 3 is first correctly worn on the skin (near the muscle where the EMG signal needs to be acquired), ensuring good contact and stable signal transmission. The received signal is filtered through a 50Hz power frequency filter to remove noise introduced by power frequency interference from the power system.

[0036] Since the electromyographic signals received by the electrode pads are weak potential changes, differential amplification is required to amplify the signals. Considering that the DC component may not contribute or may even introduce errors, high-pass and low-pass filters can be used to process signals with different frequency components.

[0037] First, a high-pass filter is used to remove the DC component from the signal, allowing only signal components with frequencies above a certain threshold to pass through, thereby improving signal quality and reliability. Second, a low-pass filter is used to smooth the signal, removing high-frequency noise and reducing fluctuations and rapid changes in the electromyography (EMG) signal, further improving signal quality. After high-pass and low-pass filtering, the noise components of the signal are suppressed, and then an amplifier is used to amplify the signal for observation and analysis. Finally, signal rectification further enhances the signal characteristics, reflecting the signal's changing trends.

[0038] The electromyography (EMG) signal central processing unit is connected to the EMG signal acquisition module. It converts the EMG signals acquired by the EMG signal acquisition module into digital signals through an analog-to-digital converter (ADC). The ADC chip data is then sent to the host computer for visualization and data signal storage for subsequent signal data processing.

[0039] The central processing unit for electromyography (EMG) signals performs signal conversion on the EMG signals acquired by the EMG signal acquisition module, converting the raw signals into digital signals and sending them to the EMG signal storage device in the host computer for signal storage.

[0040] Specifically, the system comprises three subsystems: an electromyography (EMG) signal storage system, a pose comparison system, and a valid EMG signal storage system. The EMG signal storage system stores the EMG data signals sent from the ADC chip to the host computer. The pose comparison system compares the subject's posture information acquired by the pose detection module with the system's standard pose data model to ensure the standardization and normalization of the subject's posture, and feeds the comparison results back to the EMG signal storage system. The EMG signal storage system then selects valid EMG signals based on the comparison results and sends them to the valid EMG signal storage system for storage.

[0041] The pose detection module can acquire more comprehensive behavioral information of the subject through a dual-modal integrated data acquisition method, and send this information to the pose comparison system in the host computer for pose comparison.

[0042] The electromyography (EMG) signal central processing module performs signal conversion on the EMG signals acquired by the EMG signal acquisition module, transforming the raw signals into digital signals and sending them to the EMG signal storage system in the host computer for signal storage, thus providing a high-quality data foundation for subsequent analysis.

[0043] The host computer algorithm diagnosis and information display system 2 filters the electromyographic signals in its other subsystem, the electromyographic signal storage system, based on the comparison results obtained from its pose comparison system, to obtain valid electromyographic signals. This surface electromyographic signal acquisition system not only improves the accuracy of pose detection but also provides strong support for subsequent data processing and analysis.

[0044] The external camera 1 captures the subject's movements and compares them in real time with standard poses in the pose database. The gyroscope sensor 4 measures the device's angular velocity, the subject's position and orientation, and posture changes, converting the posture information into Euler angles. This angle information is then compared with preset angles in the system database. This process ensures accurate and reliable data support for pose detection and motion analysis, providing effective electromyographic signals for pose detection.

[0045] The frequency of surface electromyography (SEMG) signals ranges from 20Hz to 500Hz, with the effective frequency concentrated in the range of 50Hz to 150Hz. Unavoidable noise interference is frequently present in SEMG signals, necessitating noise reduction to analyze more realistic signals. This paper selects the Extended Kalman Filter (EKF) method for SEMG signal noise reduction. Kalman filtering is an optimal estimation algorithm, essentially a Bayesian model. It does not require the entire time series data but instead uses optimization methods to estimate the state at the previous time step and combines this with the measured signal value at the current time step to estimate the current state. However, traditional Kalman filtering is only effective for linear systems; for nonlinear signals like SEMG, the filtering effect is not ideal. Therefore, this paper discusses the Extended Kalman Filter (EKF), which performs a nonlinear transformation of the linear function in Kalman filtering to achieve nonlinear signal analysis.

[0046] In calculations, a nonlinear model can be set up, which is approximated as follows:

[0047] X k =A Xk-1 +B Uk +W k Z k =C Xk +v k

[0048] Calculate the autocorrelation matrix of the noise:

[0049]

[0050] The main calculation steps of the filtering algorithm are as follows: State prediction equation: Prediction error covariance:

[0051]

[0052] State update, Kalman gain:

[0053]

[0054] Update the state equation:

[0055]

[0056] Update covariance:

[0057]

[0058] The meanings of the variables in the formula are shown in the figure.

[0059]

[0060] This shows that after the original surface electromyography (EMG) signal containing a lot of noise is processed by the extended Kalman filter, the high-frequency signal is effectively filtered out, while more of the low-frequency part of the EMG signal is retained, providing a cleaner initial signal for feature extraction of the EMG signal.

[0061] Example 2:

[0062] An electromyographic signal device for standard posture pain assessment and discrimination includes at least one processor;

[0063] And, a memory communicatively connected to the at least one processor;

[0064] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform an electromyographic signal acquisition system for standard posture pain assessment and discrimination as described in any of the above.

[0065] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for acquiring electromyographic signals for pain assessment, characterized in that, include: The pose data of the subject is collected by an external camera and a wearable gyroscope sensor array. The pose data is then determined by an algorithm that combines convolutional neural networks (CNN) and recurrent neural networks (RNN) to determine whether the pose data conforms to a specific standard pose designed based on the principle of pain induction. When the posture conforms to a specific standard posture, the corresponding pain assessment acquisition channel is selected to acquire electromyographic signals, and then amplified and filtered. The acquired electromyographic signals are converted into digital signals using an analog-to-digital converter (ADC). The extended Kalman filter algorithm was used to extract the low-frequency electromyographic components related to pain from the digital signal, and the extracted data was sent to the host computer for visualization and storage.

2. The method according to claim 1, characterized in that, The device captures the subject's movements using an external camera and compares them in real time with standard poses in a pose database. It also measures the device's angular velocity, the subject's position and orientation, and posture changes using a wearable gyroscope sensor array. The posture changes are then converted into Euler angles, which are compared with preset angles to ensure that the pose data conforms to a specific standard pose.

3. A standard posture electromyography signal acquisition system for pain assessment, characterized in that, include: The pose detection module is used to collect the pose data of the subject through an external camera and a wearable gyroscope sensor array. By using an algorithm that combines convolutional neural networks (CNN) and recurrent neural networks (RNN), it determines whether the pose data conforms to a specific standard pose designed based on the principle of pain induction. The electromyography (EMG) signal acquisition module is used to select the corresponding pain assessment acquisition channel to acquire EMG signals when the posture conforms to a specific standard posture, and then amplify and filter the signals. The central processing unit for electromyography (EMG) signals is used to convert the acquired EMG signals into digital signals via analog-to-digital converter (ADC). The extended Kalman filter algorithm was used to extract the low-frequency electromyographic components related to pain from the digital signal, and the extracted data was sent to the host computer for visualization and storage.

4. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform an electromyography signal acquisition method for pain assessment according to any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements an electromyography signal acquisition method for pain assessment as described in any one of claims 1-2.

Images