Surface-mounted electrode system and method for auxiliary positioning of knee joint nerve treatment

Abstract

The present application relates to the field of medical devices and discloses a system and method for auxiliary positioning of surface-mount electrodes for knee joint nerve treatment, including: a signal acquisition module, a nerve positioning module, an electrode adjustment module, an energy control module, a treatment feedback module, and a treatment evaluation module. It also discloses a method for auxiliary positioning of surface-mount electrodes for knee joint nerve treatment, including the following steps: system initialization, starting the knee joint nerve treatment system, installing surface-mount electrodes, and setting up the energy control module, signal acquisition module, nerve positioning module, treatment feedback module, and electrode adjustment module to prepare for treatment. By introducing real-time physiological feedback, dynamic adjustment of electrode position and radiofrequency energy, and a treatment evaluation module, the present invention achieves more accurate, safe, and personalized knee joint treatment, improves the stability and efficacy of the treatment effect, and reduces the occurrence of side effects.

Description

Technical Field

[0001] The present invention relates to the field of medical devices, and in particular to a surface-mounted electrode system and method for auxiliary positioning of knee joint nerve treatment. Background Art

[0002] In modern society, knee joint disease has become a significant health issue affecting people's quality of life, especially as age or excessive exercise worsens knee joint degeneration and damage. While traditional treatments can alleviate symptoms, they often lack lasting results. Radiofrequency therapy, however, has become a popular treatment option due to its ability to effectively relieve pain and promote tissue repair. Precise electrode positioning and energy control are crucial for radiofrequency treatment of the knee to ensure effective treatment while avoiding unwanted side effects.

[0003] At present, radiofrequency treatment technology mainly relies on fixed-point electrode stimulation, and treatment is usually based on preset treatment parameters. These treatment methods stimulate nerves and regulate temperature through electrodes, aiming to relieve pain and inflammation around the knee joint. Radiofrequency treatment in existing technologies can provide certain therapeutic effects and achieve relatively basic treatment parameter adjustments during the treatment process. Through different current intensities and treatment durations, existing technologies can adjust different parts of the knee joint to a certain extent to cope with different types of pain or injuries. However, most of these technologies lack personalized customization and real-time feedback mechanisms, and rely more on the doctor's experience and traditional treatment standards.

[0004] However, the shortcomings of existing technologies are that they lack adaptability to individual patient differences and cannot be dynamically adjusted according to real-time physiological feedback during treatment. Traditional methods usually use fixed treatment parameters and cannot flexibly respond to electrode position deviations or tissue reactions during treatment. In addition, existing technologies have not established an effective real-time feedback system. Doctors cannot immediately obtain key signals during treatment, and often find it difficult to adjust treatment plans in a timely manner. This lack of a feedback mechanism can easily lead to fluctuations in treatment effects and even bring unnecessary side effects. More importantly, existing technologies do not have a mechanism to comprehensively and systematically evaluate treatment effects and cannot provide doctors with accurate reports and optimization recommendations after treatment. Summary of the Invention

[0005] In response to the deficiencies of the prior art, the present invention provides a surface-mount electrode system and method for auxiliary positioning of knee joint nerve treatment, which solves the problem of lack of personalized adjustment and real-time feedback in the prior art.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a surface-mount electrode system for auxiliary positioning of knee joint nerve treatment, comprising:

[0007] A signal acquisition module, configured to acquire multi-channel signals around the knee joint in real time, the multi-channel signals including impedance data and electrical pulse feedback signals;

[0008] The nerve localization module is connected to the signal acquisition module, determines the location of the target nerve based on the data collected by the signal acquisition module, and generates nerve localization data;

[0009] The electrode adjustment module is connected to the nerve positioning module and is used to adjust the position of the electrode according to the positioning data provided by the nerve positioning module;

[0010] The energy control module is connected to the nerve positioning module and the electrode adjustment module respectively, and controls the energy output of the radiofrequency generator according to the nerve positioning and electrode position data;

[0011] The treatment feedback module is connected to the energy control module and the electrode adjustment module respectively, and is used to monitor the physiological feedback signals during the treatment process in real time and adjust the electrode position and energy output according to the feedback to form a closed-loop control;

[0012] The treatment evaluation module is connected to the treatment feedback module and is used to generate a treatment report after the treatment is completed, evaluate the treatment effect, and provide suggestions on whether to continue treatment and optimization.

[0013] Preferably, the signal acquisition module includes:

[0014] Multi-channel electrode arrays are used to simultaneously detect physiological signals from multiple neural regions, ensuring comprehensiveness and accuracy of the signals;

[0015] A signal preprocessing unit is used to filter, remove noise and enhance the collected signal;

[0016] The data transmission interface is used to transmit the processed signal data to the nerve localization module for further analysis and calculation.

[0017] Preferably, the nerve localization module includes:

[0018] Anatomical model database, which stores standard anatomical structure information of nerves around the knee joint to provide positioning reference;

[0019] Dynamic calibration unit, used to dynamically adjust anatomical model parameters based on individual patient signal characteristics, making nerve localization results more accurate;

[0020] The neural signal matching algorithm is used to analyze the data provided by the signal acquisition module and compare it with the information in the anatomical model database to accurately locate the target nerve.

[0021] Preferably, the electrode adjustment module includes:

[0022] The electrode support unit is used to fix the surface-mount electrodes and can be adjusted according to the patient's anatomical characteristics;

[0023] Positioning fine-tuning unit, used to precisely adjust the position of the electrode after nerve positioning is completed;

[0024] The feedback response unit is connected to the treatment feedback module and dynamically adjusts the electrode position according to the treatment feedback information.

[0025] Preferably, the energy control module includes:

[0026] Energy calculation unit, which calculates appropriate radiofrequency energy parameters based on nerve positioning data, target nerve characteristics and tissue impedance;

[0027] Energy regulation unit, used to dynamically control the output power, action time and frequency of radiofrequency energy to meet individual treatment needs;

[0028] The safety protection unit is used to monitor the output of RF energy in real time and automatically adjust or terminate energy output under abnormal circumstances.

[0029] Preferably, the treatment feedback module includes:

[0030] A physiological signal monitoring unit, used to monitor in real time the physiological responses of nerves during treatment, including muscle contraction, temperature change, and impedance change;

[0031] Adaptive regulation unit, based on monitored feedback data, automatically adjusts energy output parameters to optimize treatment effects;

[0032] Intelligent learning unit, used to record feedback data from multiple treatment processes and optimize subsequent treatment plans through machine learning methods.

[0033] Preferably, the treatment assessment module includes:

[0034] A treatment effect analysis unit, used to evaluate the patient's response to radiofrequency treatment based on treatment feedback data;

[0035] Personalized report generation unit, used to generate personalized treatment reports, provide efficacy analysis, and make optimization suggestions for subsequent treatment plans;

[0036] The clinical database comparison unit is used to compare patient treatment data with historical data in the clinical database to evaluate treatment success rates and adjust future treatment strategies.

[0037] Preferably, the feedback response unit includes:

[0038] A signal analysis unit is used to receive real-time physiological signals provided by the treatment feedback module and analyze muscle reactions, electrophysiological changes, and local temperature fluctuations to evaluate neural response;

[0039] The position calibration unit adjusts the angle and contact pressure of the electrode support unit based on the analyzed feedback data to optimize the electrode fit and nerve action area;

[0040] The dynamic adaptation unit uses the patient's individual anatomical characteristics and real-time treatment feedback data to adaptively adjust the electrode micro-displacement so that the treatment area always remains in the optimal target position.

[0041] Preferably, the energy calculation unit includes:

[0042] A biological characteristic analysis unit is used to collect tissue impedance, blood flow characteristics, and physiological response data of the target nerve to provide a basis for personalized energy calculation;

[0043] The dose control unit calculates the appropriate RF energy intensity based on the analysis results and adjusts the pulse width and frequency to match the neurological treatment needs;

[0044] The real-time correction unit uses feedback information obtained during the treatment process to dynamically fine-tune the energy output.

[0045] The present invention also provides a method for auxiliary positioning of surface electrodes for treating knee joint nerves, comprising the following steps:

[0046] System initialization: Start the knee joint nerve treatment system, install the surface-mount electrodes, and set up the energy control module, signal acquisition module, nerve positioning module, treatment feedback module, and electrode adjustment module to prepare for treatment.

[0047] Signal acquisition: The multi-channel electrode array in the signal acquisition module simultaneously collects physiological signals around the knee joint, including impedance data and electrical pulse feedback signals, and performs filtering, denoising, and enhancement processing through the signal preprocessing unit;

[0048] Nerve localization: Based on the data provided by the signal acquisition module, the nerve localization module analyzes and compares the standard nerve positions in the anatomical model database, combines the patient's individual signal characteristics, and dynamically calibrates and determines the location of the target nerve;

[0049] Electrode adjustment: Based on the positioning data provided by the nerve positioning module, the electrode adjustment module adjusts the position of the surface-mounted electrode and ensures that the electrode is accurately aligned with the target nerve through the electrode support unit and positioning fine-tuning unit;

[0050] Energy control: Based on the nerve positioning data and electrode position data, the energy control module calculates the appropriate RF energy parameters and controls the output power, frequency and duration of the RF generator;

[0051] Treatment process monitoring and feedback adjustment: During treatment, the treatment feedback module monitors the physiological response of the target nerve in real time, uses the physiological signal monitoring unit to obtain muscle response and temperature change information, and adjusts the electrode position and radiofrequency energy output based on the feedback data;

[0052] Treatment evaluation and report generation: After the treatment is completed, the treatment evaluation module analyzes the treatment feedback data and generates a personalized treatment report to evaluate the patient's treatment effect and provide recommendations on whether to continue treatment and optimization;

[0053] Treatment optimization and termination: Based on the results of treatment effect analysis, determine whether the treatment plan needs to be adjusted and whether treatment should continue.

[0054] The present invention provides a surface-mount electrode system and method for auxiliary positioning of knee joint nerve treatment. It has the following beneficial effects:

[0055] 1. This invention utilizes a multi-parameter feedback-based neurotherapy assistance system. By monitoring tissue impedance, neural responses, and temperature changes in real time, it dynamically adjusts radiofrequency energy and electrode placement, achieving precise, personalized treatment outcomes. Compared to existing, simple, fixed-value radiofrequency treatments, this invention effectively addresses individual differences, avoids overheating or overstimulation, and significantly improves treatment safety and effectiveness.

[0056] 2. The present invention forms a closed-loop control mechanism through the close collaboration of the treatment feedback module, the energy control module, and the nerve localization module. This mechanism automatically adjusts the treatment plan based on real-time physiological feedback, ensuring treatment stability. Compared with traditional treatment methods, the present invention avoids the lag of manual intervention, reduces human error during the treatment process, and achieves more intelligent and precise treatment.

[0057] 3. This invention uses a treatment assessment module to generate personalized treatment reports and provide recommendations for continuing treatment and optimizing the treatment plan. This comprehensive assessment method can help doctors better judge treatment progress and effectiveness. Compared with existing methods that rely solely on cursory observation during treatment, it significantly improves the transparency and adjustability of treatment results and reduces treatment blindness.

[0058] 4. By combining advanced algorithms such as fuzzy control and machine learning, this invention not only adjusts treatment parameters based on real-time data but also learns from historical treatment data and adaptively optimizes treatment plans. Compared to traditional single-step adjustment strategies, this invention can more intelligently address complex treatment environments and patient differences, significantly improving treatment outcomes and patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of the system construction of the present invention;

[0060] Figure 2 This is a framework diagram of the signal acquisition module of the present invention;

[0061] Figure 3 This is a framework diagram of the nerve localization module of the present invention;

[0062] Figure 4 This is a framework diagram of the electrode adjustment module of the present invention;

[0063] Figure 5 This is a framework diagram of the energy control module of the present invention;

[0064] Figure 6 This is a framework diagram of the treatment feedback module of the present invention;

[0065] Figure 7 This is a framework diagram of the treatment evaluation module of the present invention;

[0066] Figure 8 Schematic diagram of the method flow of the present invention;

[0067] Figure 9 Schematic diagram of the surface-mount electrode of the present invention;

[0068] Figure 10 This is a schematic diagram of a surface-mount electrode with a puncture needle according to the present invention;

[0069] Figure 11 This is a schematic diagram of the radiofrequency electrode of the present invention being connected to the puncture needle;

[0070] Figure 12 A schematic diagram of a movable positioning hole according to the present invention;

[0071] Figure 13 Schematic diagram of the adhesion positioning layer of the present invention;

[0072] Figure 14 Schematic diagram of the superior medial geniculate nerve of the present invention.

[0073] Among them, 1. Surface mount electrode; 2. Movable positioning hole; 3. Motor surface layer; 4. Electrical layer; 5. Adhesion positioning layer; 6. Superior lateral geniculate nerve; 7. Superior medial geniculate nerve; 8. Inferior medial geniculate nerve. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0075] Please see the attached Figure 1 -Attached Figure 7 The embodiment of the present invention provides a surface-mount electrode system for auxiliary positioning of knee joint nerve treatment, comprising:

[0076] A signal acquisition module, configured to acquire multi-channel signals around the knee joint in real time, the multi-channel signals including impedance data and electrical pulse feedback signals;

[0077] The signal acquisition module is used to collect multi-channel physiological signals around the knee joint in real time, providing data support for subsequent nerve localization, electrode adjustment, and energy control. To ensure data accuracy and comprehensiveness, the signal acquisition module can simultaneously acquire multiple different types of signal information and optimize data quality through signal processing. Generally, the signals collected by this module include tissue impedance data and electrical pulse feedback signals, which are used to characterize the physiological state of neural tissue and its response to external stimuli.

[0078] In this embodiment, the signal acquisition module uses a multi-channel electrode array for data acquisition. The multi-channel electrode array is composed of multiple independent electrode units, and the electrode units can act on different nerve areas respectively to improve the spatial resolution of the signal. Specifically, each electrode unit includes a signal input terminal and a reference electrode. The input terminal is used to detect changes in electrical signals in local tissues, while the reference electrode is used to provide a reference potential for differential amplification to improve signal stability. In some embodiments, the spacing between the electrode units can be adjusted according to the patient's anatomical structure to optimize the signal acquisition effect.

[0079] In one possible implementation, the signal acquisition module also includes a signal preprocessing unit. The signal preprocessing unit is used to filter, denoise, amplify, and perform other processing on the collected original signal to enhance the signal quality. Generally, the acquisition of impedance data requires the use of low-frequency AC signals for measurement, and the common frequency range is between 1kHz and 100kHz. On this basis, more abundant tissue characteristic information can be obtained by measuring the impedance changes at different frequencies. For example, in some embodiments, the impedance It can be calculated by the following formula:

[0080] ;

[0081] in, is the applied AC voltage, is the measured response current, is tissue impedance.

[0082] Alternatively, the signal preprocessing unit can use a bandpass filter to remove high-frequency noise and combine it with an adaptive noise suppression algorithm to reduce interference. Specifically, Kalman filtering or wavelet transform methods can be used to optimize the collected signal, thereby enhancing the effective signal and effectively suppressing interference components.

[0083] In another possible implementation, the signal acquisition module also includes a data transmission interface for transmitting processed signal data to the nerve localization module. Data transmission can be done via wired or wireless means. For wired transmission, low-noise shielded cables can be used to reduce electromagnetic interference. For wireless transmission, Bluetooth Low Energy (BLE) or Wi-Fi is typically used to ensure real-time and stable signals.

[0084] In some embodiments, the signal acquisition module can also be combined with an electrical pulse feedback signal to assess the excitability and functional status of the nerve. The electrical pulse feedback signal refers to the response signal generated by the nerve tissue after external electrical stimulation. Generally, the strength, duration, and frequency of this signal can reflect the health of the nerve. For example, the conduction capacity of the nerve can be assessed by measuring its compound action potential (CAP), which is calculated as follows:

[0085] ;

[0086] in, is the neural potential signal, and are the start and end time of the integration, Dimension represents the cumulative effect of the neural potential signal, is a small time increment.

[0087] Specifically, the electrical pulse feedback signal can be collected using a high-impedance input amplifier to reduce signal attenuation. Simultaneously, the collected signal can be subjected to feature extraction, such as calculating peak amplitude, rise time, duration, and spectral characteristics, to provide richer diagnostic information.

[0088] In one possible implementation, to further improve signal acquisition stability, the signal acquisition module can employ an active servo circuit to adjust the contact impedance between the electrode and the skin in real time, maintaining optimal signal acquisition quality. For example, an automatic gain control (AGC) algorithm based on negative feedback can be employed to ensure that the signal amplitude remains within an appropriate dynamic range.

[0089] In some embodiments, the signal acquisition module can also work in conjunction with the treatment feedback module to achieve closed-loop control. Specifically, during treatment, the system can monitor changes in tissue impedance in real time and adjust the RF energy output to optimize the treatment effect. For example, if elevated tissue impedance is detected, this may indicate increased tissue temperature or decreased moisture. In this case, the RF energy can be appropriately reduced to prevent tissue damage.

[0090] The nerve localization module is connected to the signal acquisition module, determines the location of the target nerve based on the data collected by the signal acquisition module, and generates nerve localization data;

[0091] As one of the core components of the system, the nerve localization module works closely with the signal acquisition module. Its main function is to analyze and determine the position of the target nerves around the knee joint based on the collected multi-channel physiological signals, and generate nerve localization data for electrode adjustment and energy control. In general, the accuracy of nerve localization directly determines the effectiveness of subsequent treatment. Therefore, this module needs to have high-precision computing capabilities and be able to adapt to the individual anatomical differences of different patients. In order to achieve this goal, the present invention combines an anatomical model database, a dynamic calibration unit, and a neural signal matching algorithm to achieve accurate identification of target nerves on the basis of multi-channel signal acquisition.

[0092] In this embodiment, the nerve localization module uses the standard nerve structure information provided by the anatomical model database as a preliminary reference, and combines it with the real-time data transmitted by the signal acquisition module to perform multi-level comparative analysis. The anatomical model database stores a large amount of knee joint nerve anatomical characteristics based on clinical data, including nerve distribution area, nerve diameter, relative position of nerves and adjacent tissues, conductivity parameters, and impedance characteristics. In specific applications, the nerve localization module first extracts an anatomical model from the database that matches the patient's basic information and performs a preliminary nerve region division based on this.

[0093] In some embodiments, the dynamic calibration unit of the nerve localization module is used to adjust the information in the anatomical model database based on the specific physiological parameters of the individual patient. Specifically, the unit can modify the anatomical model based on the patient's knee joint physiological signal characteristics, such as the measured basic tissue impedance, nerve excitation threshold, tissue conductivity distribution, etc., to improve the matching accuracy. For example, during the impedance measurement process, the following calculation formula can be used to characterize the conductive properties of different tissues:

[0094] ;

[0095] in, is tissue impedance, is the DC resistance of the tissue, For inductive reactance, is the signal angular frequency, is the dielectric relaxation time constant of the tissue, Is an imaginary unit.

[0096] Alternatively, the dynamic calibration unit can incorporate the patient's historical treatment data, comparing the current signal with previous data to make adaptive corrections. This personalized data-based model optimization method can effectively improve the accuracy of nerve localization and reduce the impact of individual differences.

[0097] In one possible implementation, the neural signal matching algorithm of the nerve localization module uses a multi-parameter analysis method to extract features from the collected impedance data and electric pulse feedback signals, and compare them with the standard signals in the database to determine the location of the target nerve. Specifically, the algorithm can extract parameters such as nerve discharge frequency, action potential waveform characteristics, impedance change rate, etc. based on time domain, frequency domain, and time-frequency domain analysis, and calculate the similarity with the standard data. The similarity calculation can be calculated using the following formula:

[0098] ;

[0099] in, is the deviation of neural matching, is the measured signal characteristic value, is the standard signal characteristic value in the database, is the weight factor, is the number of characteristic parameters.

[0100] Typically, after the matching algorithm completes its calculations, it will generate an optimal prediction of the target nerve's location and send this data to the electrode adjustment module to guide the adjustment of the surface-mounted electrodes. In some embodiments, the nerve localization module can also generate a nerve localization confidence interval, which gives the possible location range of the target nerve, and continuously optimize the localization accuracy through a subsequent dynamic feedback mechanism.

[0101] In another possible implementation, to improve the robustness of nerve localization, the nerve localization module can combine multiple repeated measurements, that is, repeatedly collecting nerve signals at different time points and under various electrical stimulation intensities, and using statistical methods to perform comprehensive calculations. For example, the weighted average method can be used to calculate the final nerve location:

[0102] ;

[0103] in, To finally determine the location of the nerve, For the The position value obtained by the measurement, is the confidence weight of the measurement, is the number of measurements.

[0104] In some embodiments, the nerve localization module can also interact with the treatment feedback module to adjust the nerve localization results based on real-time feedback during treatment. For example, if the system detects an abnormal nerve response after electrode stimulation, it may indicate that the nerve location is not accurately matched. In this case, the relocalization mechanism can be automatically triggered to recalculate the target nerve location and guide electrode adjustment.

[0105] Alternatively, the nerve localization module can employ machine learning algorithms to optimize nerve localization accuracy. By training models based on artificial neural networks (ANNs), support vector machines (SVMs), or random forests (RFs), the module can adaptively adjust nerve matching parameters after multiple measurements, improving computational efficiency and accuracy. For example, an ANN model can be used to predict nerve location, as mathematically expressed as follows:

[0106] ;

[0107] in, The results of nerve localization are is the input signal feature vector, is the weight matrix, is the bias term, is the activation function.

[0108] The electrode adjustment module is connected to the nerve positioning module and is used to adjust the position of the electrode according to the positioning data provided by the nerve positioning module;

[0109] Please see the attached Figure 9 -Attached Figure 14 ,The energy control module is respectively connected with the nerve positioning module and the electrode adjustment module to control the energy output of the RF generator according to the nerve positioning and electrode position data;

[0110] The energy control module achieves precise transmission and regulation of radio frequency energy by working in coordination with the surface-mount electrodes 1, the movable positioning holes 2, the motor surface layer 3, the electrical layer 4 and the adhesive positioning layer 5.

[0111] Surface-mount electrode 1: The energy control module is connected to the electrical layer 4 of the surface-mount electrode. By regulating the current and voltage on the electrode, the transmission of radiofrequency energy is more accurate and effective, ensuring effective coupling between the electrode and the target nerve.

[0112] Mobile positioning hole 2: By adjusting the position of mobile positioning hole 2 in real time, the energy control module can accurately control the contact point of the electrode, thereby ensuring that the radiofrequency energy is focused on the target nerve area and avoiding energy leakage or over-concentration;

[0113] Motor Surface 3: Motor Surface 3 ensures precise control of electrode position through mechanical adjustment. The interaction between the Energy Control Module and Motor Surface 3 enables automatic adjustment of RF energy output to the optimal power to account for any slight changes in electrode position during treatment.

[0114] Electrical layer 4: Electrical layer 4 provides electrical contact between the electrode and the tissue. The energy control module controls the distribution of RF energy by adjusting the current intensity in electrical layer 4, thereby ensuring the best match between the electrode and the target nerve;

[0115] Adhesion Positioning Layer 5: This layer ensures the fixation and stability of the electrodes to the skin surface, preventing electrode position shifting during treatment. The energy control module adjusts the adhesion positioning layer 5 to ensure the electrodes maintain optimal contact position, achieving the best RF treatment effect.

[0116] Superior lateral geniculate nerve 6: The superior lateral geniculate nerve 6 is responsible for transmitting sensory information in the knee joint area, such as pain, temperature, and proprioception. During radiofrequency treatment, precise positioning of this nerve is crucial to ensure that the radiofrequency energy can accurately act on the nerve to relieve pain caused by knee joint inflammation or degeneration. The energy control module adjusts the output of radiofrequency energy to avoid excessive energy concentration or leakage, ensuring that energy is delivered to the nerve, helping to relieve pain and promote tissue repair.

[0117] Superior medial geniculate nerve 7: The superior medial geniculate nerve 7 is involved in the sensory and motor functions of the knee joint, affecting the stability and movement of the knee joint. By precisely applying radiofrequency energy to this nerve, symptoms such as knee stiffness and limited mobility caused by nerve dysfunction can be effectively alleviated. The goal of radiofrequency treatment is to reduce pain or dysfunction caused by excessive nerve activation by regulating the excitability of the nerve. The energy control system continuously adjusts the radiofrequency power during treatment to ensure that the energy acts precisely on the target nerve.

[0118] Inferior Medial Geniculate Nerve 8: The inferior medial geniculate nerve 8 is closely associated with sensory transmission and reflex activity in the knee joint. Radiofrequency treatment of this nerve can alleviate chronic pain caused by nerve inflammation or injury and improve knee joint function. During treatment, the energy control module precisely adjusts the radiofrequency energy output based on real-time data provided by the nerve localization module to maximize the treatment effect while avoiding thermal damage to other tissues.

[0119] The energy control module is a key component in the radiofrequency treatment process. Its main function is to dynamically adjust the energy output of the radiofrequency generator based on the target nerve position and electrode arrangement data provided by the nerve positioning module and the electrode adjustment module to ensure that the radiofrequency signal can accurately act on the target nerve area. In general, energy control needs to comprehensively consider the impedance characteristics of nerve tissue, the transmission efficiency of radiofrequency energy, the treatment time and safety parameters, so as to achieve refined energy management. The energy control module of the present invention adopts an energy calculation unit, an energy regulation unit and a safety protection unit to ensure that the risk of thermal damage to the tissue is minimized while meeting the treatment needs.

[0120] In this embodiment, the energy calculation unit of the energy control module is used to determine the optimal RF energy parameters. Generally, the effectiveness of RF treatment depends on the relative position of the electrode and the target nerve, the tissue impedance characteristics, and the energy distribution pattern. To optimize the RF energy setting, the energy calculation unit can calculate the RF power using the following formula:

[0121] ;

[0122] in, is the RF power, is the measured response current, is the impedance of the target tissue. Calculated from the data provided by the nerve localization module, it can be expressed by the following formula:

[0123] ;

[0124] in, is the applied AC voltage, is the measured response current, is the impedance of the target tissue.

[0125] As an option, the energy calculation unit can further optimize the energy delivery strategy based on the heat capacity and thermal conductivity of the tissue to prevent excessive temperature rise in the tissue. The temperature change of the tissue can be expressed by the following heat conduction equation:

[0126] ;

[0127] in, is the tissue temperature, For time, is the thermal diffusivity of the tissue, is the RF heating power density, is the tissue density, is the specific heat capacity, is the Laplace operator of temperature.

[0128] In one possible implementation, the energy calculation unit dynamically calculates the radiofrequency dose in the treatment area and adjusts the radiofrequency frequency according to the physiological state of the target nerve. The optimization of can be determined by the following formula:

[0129] ;

[0130] in, is the inductance in the circuit, This calculation ensures that the RF signal is in the optimal bio-effect range. is the frequency of the circuit, indicating the oscillation frequency of the circuit.

[0131] In some embodiments, the energy control module's energy regulation unit is used to dynamically control the RF generator's power output, signal frequency, and duration of action. Specifically, when the target nerve location provided by the nerve localization module shifts, or when the electrode adjustment module reports a change in electrode position, the energy regulation unit automatically adjusts the RF signal to match the latest treatment needs. For example, if the distance between the electrode and the nerve is detected to have increased, the system can automatically increase the RF power to ensure sufficient energy is delivered to the neural tissue.

[0132] In another possible implementation, the energy regulation unit adopts an adaptive regulation strategy to adjust the RF energy output according to the physiological signal feedback during the treatment process. For example, when the tissue temperature gradually rises, the system can prevent overheating by reducing the RF power or shortening the pulse width. The calculation can be expressed by the following formula:

[0133] ;

[0134] in, is the frequency of the RF modulation signal, is the dielectric relaxation time constant of the tissue.

[0135] Alternatively, the energy conditioning unit can employ a closed-loop control strategy, automatically adjusting RF parameters by monitoring changes in tissue impedance in real time. For example, if a sudden increase in tissue impedance is detected during treatment, potentially indicating tissue dehydration or overheating, the system can trigger an automatic power reduction mode to protect tissue from damage.

[0136] In this embodiment, the safety protection unit is used to monitor the safety of RF energy output and take protective measures when an abnormality is detected. Generally, the safety protection unit can monitor the following parameters in real time:

[0137] Tissue impedance change trend;

[0138] target tissue temperature;

[0139] The contact status between the electrode and the tissue;

[0140] Physiological signal feedback during treatment, such as muscle response and changes in pain threshold.

[0141] In some embodiments, the safety protection unit can determine whether to reduce the RF energy based on tissue temperature and impedance data. For example, when the system detects that the tissue temperature reaches a set threshold Energy output automatically decreases when:

[0142] ;

[0143] in, is the adjusted RF power, is the original set power, For real-time tissue temperature, is the target temperature, It is the maximum temperature, indicating the maximum safe temperature during treatment.

[0144] As an option, the safety protection unit can provide an abnormality detection mechanism, which automatically interrupts the treatment and triggers a warning when it detects that the tissue impedance exceeds the normal range or the energy output is abnormal. For example, when the tissue impedance changes beyond the preset range When the system triggers the following protection measures:

[0145] ;

[0146] in, is the resistance change, which indicates the difference between the current resistance and the reference resistance. is the current resistance value, indicating the resistance of the current tissue, It is the reference resistance value, which indicates the resistance of the tissue in its initial or normal state.

[0147] like > , the RF output will be automatically stopped and the user will be prompted to check the electrode position or tissue status.

[0148] In another possible implementation, the safety protection unit could incorporate intelligent data analysis to learn treatment patterns across different patients and optimize RF energy delivery strategies accordingly. For example, the system could store multiple treatment histories and use machine learning models to predict optimal energy parameters, further enhancing personalized treatment outcomes.

[0149] The treatment feedback module is connected to the energy control module and the electrode adjustment module respectively, and is used to monitor the physiological feedback signals during the treatment process in real time and adjust the electrode position and energy output according to the feedback to form a closed-loop control;

[0150] The treatment feedback module is responsible for real-time monitoring, data analysis and adaptive adjustment throughout the treatment process. Its main function is to monitor physiological feedback data based on the signals provided by the electrode adjustment module and the energy control module, and to optimize and adjust the electrode position and radiofrequency energy during the treatment process. In general, the treatment feedback module needs to be able to identify key parameters such as tissue impedance changes, electromyographic signal (EMG) fluctuations, nerve response delays, tissue temperature gradients, and form a closed-loop control based on this to ensure the safety and accuracy of the treatment. The treatment feedback module of the present invention includes a physiological signal acquisition unit, a feedback analysis unit and an adaptive adjustment unit, which can perform multi-level regulation during the treatment process to ensure the stability and controllability of radiofrequency treatment.

[0151] In this embodiment, the physiological signal acquisition unit of the treatment feedback module is responsible for real-time monitoring of the physiological feedback signals of the target area, including impedance changes, action potential characteristics, local tissue temperature, and nerve discharges after radiofrequency stimulation. Generally, the physiological signal acquisition unit needs to have high temporal resolution and high spatial resolution to ensure the accuracy of the feedback data. For example, during the radiofrequency application process, the physiological signal acquisition unit can measure the dynamic changes in impedance in the following ways:

[0152] ;

[0153] in, represents the impedance change, is the most recently measured tissue impedance, is the initial impedance baseline value.

[0154] As an option, the physiological signal acquisition unit can use multi-frequency impedance measurement technology to obtain the complex impedance characteristics of the tissue by applying AC signals of different frequencies and calculate the impedance spectrum curve. Specifically, the impedance characteristics at different frequencies can be expressed as:

[0155] ;

[0156] in, is the complex impedance, is the real part (resistance component), is the imaginary part (reactance component).

[0157] In one possible implementation, the feedback analysis unit of the treatment feedback module is used to analyze tissue status based on the collected physiological signal data and determine whether electrode position or RF energy needs to be adjusted. Specifically, the feedback analysis unit can use time series analysis methods to calculate the dynamic trend of neural responses. For example, during RF stimulation, if the peak amplitude of the nerve action potential is detected to decrease, it may indicate a decrease in nerve excitability. The system can automatically increase the RF power or adjust the electrode position to optimize the treatment effect.

[0158] In some embodiments, the feedback analysis unit uses nonlinear data modeling to calculate the dynamic change trend of the neural response. For example, a polynomial fitting model is used to estimate the change trend of the neural response:

[0159] ;

[0160] in, represents the amplitude of the nerve action potential, For time, , , ,…, is the fitting parameter. Through this method, the system can predict the future trend of the neural state and adjust the RF parameters in advance. is the highest power of the polynomial, indicating the fitting order of the neural signal.

[0161] In this embodiment, the adaptive adjustment unit of the treatment feedback module is used to adjust the electrode position and RF energy output when an abnormal physiological signal is detected. Generally, when the feedback analysis unit detects that the impedance change exceeds the normal range or the nerve response signal is abnormal, the adaptive adjustment unit will send instructions to the electrode adjustment module to adjust the electrode position, or send instructions to the energy control module to change the RF power and modulation parameters. For example, when the distance between the electrode and the target nerve increases, the RF power can be optimized in the following ways:

[0162] ;

[0163] in, is the adjusted RF power, is the original set power, is the electrode offset, The optimal electrode-nerve distance is set.

[0164] In another possible implementation, the adaptive regulation unit can be combined with a feedback control algorithm to achieve closed-loop regulation. For example, a fuzzy control method can be used to divide physiological signal feedback data into different state levels and set corresponding regulation strategies. Specifically, the fuzzy control rules can be set based on the impedance change rate, neural response amplitude, and tissue temperature change:

[0165] If the impedance change is small and the neural response is stable, maintain the current RF power.

[0166] If the impedance changes significantly but the nerve response is still within the normal range, the RF power should be appropriately reduced.

[0167] If the neural response is weakened and the impedance increases, adjust the electrode position and reduce the RF power.

[0168] If the tissue temperature exceeds the set threshold, the RF output will be stopped and a warning will be issued.

[0169] Alternatively, the adaptive adjustment unit can combine historical data analysis with machine learning algorithms to optimize electrode adjustment and energy control strategies. For example, a support vector machine (SVM) can be used to classify different treatment states and automatically recommend the optimal parameter adjustment strategy. The decision function of the support vector machine can be expressed as:

[0170] ;

[0171] in, is the classification function, is the weight vector, is the input physiological signal feature vector, This method can improve the intelligent adjustment capability of the system and make the treatment feedback more accurate.

[0172] In some embodiments, the treatment feedback module can also be linked with the safety protection mechanism to immediately terminate the radiofrequency treatment when a high-risk signal is detected. For example, if the tissue temperature is detected to exceed the set threshold , the system will automatically stop the RF output and send out an alarm signal to avoid thermal damage to the tissue.

[0173] The treatment evaluation module is connected to the treatment feedback module and is used to generate a treatment report after the treatment is completed, evaluate the treatment effect, and provide suggestions on whether to continue treatment and optimization;

[0174] The treatment evaluation module is used to conduct a comprehensive evaluation of the treatment process after the treatment is completed and generate a detailed treatment report. This module can not only evaluate the treatment effect, but also provide recommendations on whether to continue treatment and how to optimize the treatment plan based on the physiological signal data provided by the treatment feedback module. Generally, the treatment evaluation module evaluates the effectiveness and safety of the treatment by conducting in-depth analysis of key parameters such as physiological feedback data, nerve responses, tissue temperature changes, impedance characteristics, etc. during the treatment process. On this basis, the evaluation module can provide personalized treatment optimization recommendations to help doctors decide whether to continue treatment and adjust the treatment plan. The core components of the treatment evaluation module include the effect evaluation unit, the report generation unit, and the recommendation generation unit, and through close connection with the treatment feedback module, it ensures the real-time and accuracy of the evaluation process.

[0175] In this embodiment, the effect evaluation unit of the treatment evaluation module analyzes various physiological signals during the treatment process based on the feedback data provided by the treatment feedback module to evaluate the treatment effect. For example, the effect evaluation unit calculates a comprehensive score of the treatment effect based on the improvement of the neural response, the change in tissue temperature, and the stability of the impedance. In general, the evaluation of the treatment effect depends on the combination of multiple indicators. The evaluation process can use a weighted average method to generate a final treatment effect score based on the contribution of each physiological signal. For example, the treatment effect can be evaluated according to the following criteria:

[0176] The degree of improvement of nerve response: The degree of nerve recovery is assessed through data such as the amplitude of change in action potential and nerve conduction velocity.

[0177] Tissue temperature stability: Analyze whether there is a risk of overheating or insufficient cooling based on temperature changes during treatment.

[0178] Smoothness of impedance changes: Significant fluctuations in impedance may indicate poor electrode-tissue contact or abnormalities in the treatment process.

[0179] Alternatively, the effect evaluation unit can employ a multidimensional data fusion algorithm to weightedly fuse feedback signals from different sources, thereby more accurately assessing treatment effectiveness. For example, principal component analysis (PCA) can be used to extract the principal components of physiological signals, reducing redundant data and improving evaluation efficiency.

[0180] Specifically, the scoring formula for treatment effect can be calculated based on the weighted calculation of different physiological signals measured during treatment. For example, if the contribution weights of nerve response, tissue temperature and impedance are , , , the comprehensive effect score It can be expressed as:

[0181] ;

[0182] in, 、 、 Represent the scores of nerve response, tissue temperature and impedance, , , , are their respective weight coefficients, It is a comprehensive evaluation score, which represents the comprehensive score of treatment effect.

[0183] In one possible implementation, the report generation unit of the treatment evaluation module generates a detailed treatment report based on the treatment score provided by the effect evaluation unit. The report contains key data from the treatment process, evaluation results, and visual charts to help doctors understand the progress and effectiveness of the treatment. For example, the report can display neural response graphs before and after treatment, tissue temperature change curves, and impedance change trend graphs. Doctors can use this data to determine whether the treatment has achieved the desired effect. Based on the evaluation results, the report also makes recommendations on whether to continue treatment and provides further optimization plans.

[0184] As an option, the report generation unit can generate personalized treatment recommendations based on historical treatment data, recommending the optimal treatment plan and possible optimization measures. For example, if the treatment feedback module detects abnormal tissue temperature, the report will alert the physician to the risk of overheating and recommend adjustments to the RF power or electrode position. Furthermore, the report can include post-treatment recovery period recommendations and a follow-up monitoring plan.

[0185] In this embodiment, the recommendation generation unit of the treatment evaluation module makes a recommendation on whether to continue treatment based on the treatment effect score of the effect evaluation unit. Specifically, the recommendation generation unit determines whether the treatment has achieved the desired effect based on the comprehensive score and treatment progress. If the treatment effect is poor, the recommendation generation unit may recommend extending the treatment time, adjusting the treatment intensity, or changing the electrode position. If the evaluation results show a good treatment effect, the recommendation generation unit may recommend ending treatment and continue to observe the patient's recovery.

[0186] Optionally, the recommendation generation unit can also provide targeted optimization suggestions based on feedback signals during treatment. For example, if a decrease in neural response is detected, the recommendation generation unit can recommend increasing the RF power or, based on changes in electrode position, adjusting the optimal distance between the electrode and the target nerve. Furthermore, the recommendation generation unit can combine the patient's historical treatment data to propose personalized treatment adjustment plans.

[0187] In some embodiments, the treatment evaluation module can incorporate machine learning algorithms to optimize the treatment efficacy assessment and recommendation generation process by learning from and modeling historical treatment data. For example, a support vector machine (SVM) can be used to classify treatment efficacy and generate more precise optimization recommendations based on patient responses and treatment history. Through machine learning models, the treatment evaluation module can automatically adjust evaluation criteria and recommendation content based on the unique characteristics of each patient.

[0188] The knee joint nerve treatment auxiliary positioning surface electrode method described below and the knee joint nerve treatment auxiliary positioning surface electrode system described above can be referenced to each other.

[0189] Please see the attached Figure 8 The present invention also provides a method for auxiliary positioning of surface electrodes for knee joint nerve treatment, comprising the following steps:

[0190] S1. System initialization: Start the knee joint nerve treatment system, install the surface-mount electrodes, and set up the energy control module, signal acquisition module, nerve positioning module, treatment feedback module, and electrode adjustment module to prepare for treatment.

[0191] S2. Signal acquisition: The multi-channel electrode array in the signal acquisition module simultaneously collects physiological signals around the knee joint, including impedance data and electrical pulse feedback signals, and performs filtering, denoising, and enhancement processing through the signal preprocessing unit;

[0192] S3. Nerve localization: Based on the data provided by the signal acquisition module, the nerve localization module analyzes and compares the standard nerve positions in the anatomical model database, combines the patient's individual signal characteristics, and dynamically calibrates and determines the position of the target nerve;

[0193] S4. Electrode adjustment: Based on the positioning data provided by the nerve positioning module, the electrode adjustment module adjusts the position of the surface-mounted electrode and ensures that the electrode is accurately aligned with the target nerve through the electrode support unit and the positioning fine-tuning unit;

[0194] S5. Energy control: Based on the nerve positioning data and electrode position data, the energy control module calculates the appropriate radiofrequency energy parameters and controls the output power, frequency and duration of the radiofrequency generator;

[0195] S6. Treatment process monitoring and feedback adjustment: During treatment, the treatment feedback module monitors the physiological response of the target nerve in real time, uses the physiological signal monitoring unit to obtain muscle response and temperature change information, and adjusts the electrode position and radiofrequency energy output based on the feedback data;

[0196] S7. Treatment evaluation and report generation: After the treatment is completed, the treatment evaluation module analyzes the treatment feedback data and generates a personalized treatment report to evaluate the patient's treatment effect and provide recommendations on whether to continue treatment and optimization;

[0197] S8. Treatment optimization and termination: Based on the results of the treatment effect analysis, determine whether the treatment plan needs to be adjusted and whether treatment should continue.

[0198] The method of this embodiment can be used to execute the above system embodiment. Its principles and technical effects are similar and will not be described in detail here.

[0199] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A surface-mount electrode system for auxiliary positioning of knee joint nerve treatment, characterized by: include: A signal acquisition module, configured to acquire multi-channel signals around the knee joint in real time, the multi-channel signals including impedance data and electrical pulse feedback signals; The nerve localization module is connected to the signal acquisition module, determines the location of the target nerve based on the data collected by the signal acquisition module, and generates nerve localization data; The electrode adjustment module is connected to the nerve positioning module and is used to adjust the position of the electrode according to the positioning data provided by the nerve positioning module; The energy control module is connected to the nerve positioning module and the electrode adjustment module respectively, and controls the energy output of the radiofrequency generator according to the nerve positioning and electrode position data; The treatment feedback module is connected to the energy control module and the electrode adjustment module respectively, and is used to monitor the physiological feedback signals during the treatment process in real time and adjust the electrode position and energy output according to the feedback to form a closed-loop control; The treatment evaluation module is connected to the treatment feedback module and is used to generate a treatment report after the treatment is completed, evaluate the treatment effect, and provide suggestions on whether to continue treatment and optimization; The electrode adjustment module includes: The electrode support unit is used to fix the surface-mount electrodes and can be adjusted according to the patient's anatomical characteristics; Positioning fine-tuning unit, used to precisely adjust the position of the electrode after nerve positioning is completed; A feedback response unit is connected to the treatment feedback module and dynamically adjusts the electrode position according to the treatment feedback information; The feedback response unit includes: A signal analysis unit is used to receive real-time physiological signals provided by the treatment feedback module and analyze muscle reactions, electrophysiological changes, and local temperature fluctuations to evaluate neural response; The position calibration unit adjusts the angle and contact pressure of the electrode support unit based on the analyzed feedback data to optimize the electrode fit and nerve action area; The dynamic adaptation unit uses the patient's individual anatomical characteristics and real-time treatment feedback data to adaptively adjust the electrode micro-displacement so that the treatment area always remains in the optimal target position.

2. The knee joint nerve treatment auxiliary positioning surface electrode system according to claim 1, characterized in that: The signal acquisition module includes: Multi-channel electrode arrays are used to simultaneously detect physiological signals from multiple neural regions, ensuring comprehensiveness and accuracy of the signals; A signal preprocessing unit is used to filter, remove noise and enhance the collected signal; The data transmission interface is used to transmit the processed signal data to the nerve localization module for further analysis and calculation.

3. The surface-mount electrode system for auxiliary positioning of knee joint nerve treatment according to claim 1, characterized in that: The neural localization module includes: Anatomical model database, which stores standard anatomical structure information of nerves around the knee joint to provide positioning reference; Dynamic calibration unit, used to dynamically adjust anatomical model parameters based on individual patient signal characteristics, making nerve localization results more accurate; The neural signal matching algorithm is used to analyze the data provided by the signal acquisition module and compare it with the information in the anatomical model database to accurately locate the target nerve.

4. The surface-mount electrode system for auxiliary positioning of knee joint nerve treatment according to claim 1, characterized in that: The energy control module includes: Energy calculation unit, which calculates appropriate radiofrequency energy parameters based on nerve positioning data, target nerve characteristics and tissue impedance; Energy regulation unit, used to dynamically control the output power, action time and frequency of radiofrequency energy to meet individual treatment needs; The safety protection unit is used to monitor the output of RF energy in real time and automatically adjust or terminate energy output under abnormal circumstances.

5. The surface-mount electrode system for auxiliary positioning of knee joint nerve treatment according to claim 1, characterized in that: The treatment feedback module includes: A physiological signal monitoring unit, used to monitor in real time the physiological responses of nerves during treatment, including muscle contraction, temperature change, and impedance change; Adaptive regulation unit, based on monitored feedback data, automatically adjusts energy output parameters to optimize treatment effects; Intelligent learning unit, used to record feedback data from multiple treatment processes and optimize subsequent treatment plans through machine learning methods.

6. The surface-mount electrode system for auxiliary positioning of knee joint nerve treatment according to claim 1, characterized in that: The treatment assessment module includes: A treatment effect analysis unit, used to evaluate the patient's response to radiofrequency treatment based on treatment feedback data; Personalized report generation unit, used to generate personalized treatment reports, provide efficacy analysis, and make optimization suggestions for subsequent treatment plans; The clinical database comparison unit is used to compare patient treatment data with historical data in the clinical database to evaluate treatment success rates and adjust future treatment strategies.

7. The surface-mount electrode system for auxiliary positioning of knee joint nerve treatment according to claim 4, characterized in that: The energy calculation unit includes: A biological characteristic analysis unit is used to collect tissue impedance, blood flow characteristics, and physiological response data of the target nerve to provide a basis for personalized energy calculation; The dose control unit calculates the appropriate RF energy intensity based on the analysis results and adjusts the pulse width and frequency to match the neurological treatment needs; The real-time correction unit uses feedback information obtained during the treatment process to dynamically fine-tune the energy output.

Images