A system and method for adaptive tissue state surgical electrode energy dynamic regulation

Abstract

This invention discloses a surgical electrode energy dynamic adjustment technology field, specifically an adaptive tissue state surgical electrode energy dynamic adjustment system and method. First, it collects real-time raw tissue parameters and electrode working condition data from the surgical area to generate a standardized real-time tissue condition dataset. Then, it performs data noise reduction, interference identification, tissue state classification, and state trend prediction, outputting the tissue state prediction result and risk warning level. Next, it matches baseline energy parameters, applies safety threshold constraints, and fine-tunes the parameters, outputting stable energy through a gradual buffering mechanism. Finally, it monitors surgical wound data and compares it with preset standards, iteratively updating the energy matching parameters based on deviation data. Based on this, the invention can achieve precise and differentiated energy adaptation for different types of surgical tissues, effectively avoiding tissue burns due to excessive energy and surgical malfunction due to insufficient energy.

Description

Technical Field

[0001] This invention relates to the field of surgical electrode energy dynamic adjustment technology, specifically to a surgical electrode energy dynamic adjustment system and method that adapts to tissue conditions. Background Technology

[0002] High-frequency surgical electrodes are core instruments in minimally invasive and open surgeries. Utilizing the thermal and cutting effects of high-frequency current, they enable the cutting, ablation, hemostasis, and separation of human tissues. They are widely used in general surgery, orthopedics, gynecology, neurosurgery, and other clinical fields. The energy output precision and tissue compatibility of the surgical electrode directly determine the size of the surgical wound, the hemostatic effect, and the incidence of postoperative complications.

[0003] The human tissues in the surgical area exhibit significant dynamic differences: different tissues (fat, muscle, connective tissue, diseased proliferative tissue, and vascular tissue) show marked differences in impedance, water content, density, and heat resistance threshold. The tissue state changes in real time as the surgery progresses; for example, continuous electrical stimulation-induced tissue dehydration, carbonization, hemorrhage, and tissue compression deformation all alter the electrical and physical properties of the tissue. Existing technologies have attempted to improve control precision through multidimensional signal synergistic analysis. For instance, the published literature CN121489623A proposes a precise control method and system for plasma surgical electrodes based on multidimensional signal mapping. This method achieves predictive adjustment of the plasma surgical electrode through phase space reconstruction, joint recursive graph construction, and extraction of quantitative indicators (joint determinism, joint laminarity, joint recursion rate, and joint entropy). However, this type of method focuses on the dynamic characteristics of multidimensional signals and the prediction of plasma layer stability. The generation of its control parameters depends on the statistical distribution of historical stable intervals and the mapping of complex nonlinear dynamic indicators. It lacks targeted and systematic solutions for core clinical needs such as the differentiated energy adaptation of high-frequency surgical electrodes in different tissue types, real-time tissue state graded response, and intraoperative dynamic gradual buffer output.

[0004] Regarding the clinical energy regulation requirements of high-frequency surgical electrodes, existing technologies still have the following prominent problems:

[0005] 1. Lack of a benchmark energy grading and matching mechanism tailored to the differentiated characteristics of tissues, resulting in insufficient accuracy in energy adaptation: While existing technologies (such as CN121489623A) achieve predictive regulation of energy output through multidimensional signal dynamics analysis, they have not established a dedicated benchmark energy parameter library for different tissue types (fat, muscle, connective tissue, diseased tissue, etc.). They cannot grade tissue states and match differentiated benchmark energies based on biological parameters such as tissue impedance, dielectric constant, and surface temperature. In clinical practice, gynecological myomectomy involves alternating contact between low-density, high-water-content fibroid tissue and high-density, high-impedance pelvic connective tissue. A single or uniform energy output scheme can easily lead to excessive energy in the fibroid tissue, carbonization and thermal burns to the surrounding normal muscle layer, or insufficient energy in the connective tissue, resulting in cutting blockage and incomplete hemostasis, with intraoperative bleeding affecting the surgical field.

[0006] 2. Lack of safety threshold constraints and gradual buffering mechanisms in energy output, resulting in insufficient safety in dynamic response: While existing technologies (such as CN121489623A) can perform time-domain smoothing after the control parameters are generated, their core mapping rules are based on the degree to which the joint recursive quantitative index deviates from the historical stable range to trigger adjustment. This belongs to the "post-event response" or "trend prediction" mode. It does not set real-time safety threshold constraints for the risk level of tissue thermal damage before energy output, nor does it employ a step-by-step gradual buffering mechanism during energy switching to avoid instantaneous energy pulse impacts. For example, in general surgery fat layer dissection, the initial adipose tissue impedance is stable, and the energy output is normal. After continuous cutting for 3-5 seconds, the adipose tissue is heated, dehydrated, and carbonized, causing a significant increase in local impedance. Although existing predictive adjustment can sense the trend, the energy output may still rise and fall abruptly due to the lack of safety threshold locking and gradual transition, leading to electrode adhesion to tissue and eschar accumulation. This not only reduces surgical efficiency but also requires repeated wound dissection, expanding the scope of surgical damage. Summary of the Invention

[0007] To address the aforementioned technical problems of lacking a baseline energy gradation matching mechanism tailored to organizational differences, and lacking safety threshold constraints and gradual buffering mechanisms for energy output, this invention provides the following technical solution:

[0008] A surgical electrode energy dynamic adjustment system that adapts to tissue conditions, comprising:

[0009] The tissue condition full-domain acquisition module collects raw tissue parameters and electrode working condition data in the surgical area in real time, and generates a standardized real-time tissue condition dataset.

[0010] The intelligent organizational status assessment module, based on a standardized real-time organizational condition dataset, performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels.

[0011] The electrode energy dynamic adaptation module includes a reference energy matching unit, an energy threshold constraint unit, a parameter fine-tuning unit, and a gradual buffer output unit.

[0012] The reference energy matching unit, based on the organization status prediction result and risk warning level, retrieves the built-in multi-scenario energy mapping database, matches the reference voltage, reference frequency, and reference output power parameters, and generates an initial energy output scheme.

[0013] The energy threshold constraint unit, based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, defines the upper and lower safety thresholds of real-time energy output and generates an energy prediction scheme with safety constraints.

[0014] The parameter fine-tuning unit, based on an energy prediction scheme with safety constraints, combines real-time tissue temperature fluctuation differences and contact pressure values ​​to fine-tune the baseline energy parameters and output the optimal energy parameters that adapt to the current dynamic state of the tissue.

[0015] The gradual buffer output unit, based on the optimal energy parameters adapted to the current dynamic state of the tissue, adopts a stepped gradual buffer mechanism to output a target energy value within a preset energy range by controlling the pulse width or amplitude of the high-frequency generator, thus outputting stable energy.

[0016] The surgical outcome closed-loop correction module monitors surgical wound data based on stable energy and compares it with preset standards, iteratively updating energy matching parameters based on deviation data.

[0017] As a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment system described in this invention, the tissue condition global acquisition module includes:

[0018] The tissue parameter acquisition unit collects the impedance value, dielectric constant and surface temperature of human tissue in the electrode contact area in real time, and outputs the real-time raw tissue parameter set.

[0019] The working condition data synchronization unit synchronously collects the working condition parameters of the surgical electrodes based on the real-time tissue raw parameter set, and merges them with the real-time tissue raw parameter set to generate a standardized real-time tissue working condition dataset.

[0020] As a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment system described in this invention, the tissue state intelligent judgment module includes:

[0021] The data acquisition and noise reduction unit, based on the standardized real-time organizational condition dataset, uses an adaptive Kalman filter algorithm to remove noisy data, normalizes the effective data, and outputs interference-free standardized operating condition data.

[0022] The intraoperative interference identification unit, based on interference-free standardized working condition data and relying on a pre-set intraoperative interference feature library, identifies interference signals that are not in the tissue body state, marks and isolates invalid interference data, and outputs pure tissue body working condition data.

[0023] The tissue status classification unit, based on pure tissue condition data, calls the tissue status recognition model to determine the current tissue type and thermal damage risk level, and outputs the tissue status classification result.

[0024] The status trend prediction unit, based on the tissue status classification results and combined with historical operating data, estimates the future trends of tissue dehydration, carbonization and impedance changes through a time-series prediction algorithm, and outputs tissue status prediction results and risk warning levels.

[0025] As a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment system described in this invention, the surgical effect closed-loop correction module includes:

[0026] The intraoperative effect monitoring unit, based on stable energy, automatically identifies and quantifies the tissue cutting smoothness, carbonized area gray value, and bleeding area percentage of the surgical wound, and outputs surgical effect deviation data after comparing it with the preset standard surgical effect threshold.

[0027] The parameter iterative update unit, based on surgical outcome deviation data, reversely corrects the matching threshold of the energy mapping database and optimizes the energy parameter region corresponding to different tissue states.

[0028] A method for dynamically adjusting the energy of a surgical electrode to adapt to tissue conditions, comprising the following steps:

[0029] S1, Tissue Condition Full-Domain Acquisition: Real-time acquisition of raw tissue parameters and electrode working condition data in the surgical area to generate a standardized real-time tissue condition dataset;

[0030] S2, Intelligent Analysis of Organizational Status: Based on a standardized real-time organizational status dataset, it performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels.

[0031] S3, Dynamic Electrode Energy Adaptation:

[0032] S31, Baseline Energy Matching: Based on the organization status prediction results and risk warning level, the built-in multi-scenario energy mapping database is retrieved to match the baseline voltage, baseline frequency, and baseline output power parameters to generate an initial energy output scheme.

[0033] S32, Energy Threshold Constraint: Based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, define the upper and lower safety thresholds of real-time energy output and generate an energy prediction scheme with safety constraints.

[0034] S33, Precise parameter fine-tuning: Based on an energy prediction scheme with safety constraints, combined with real-time tissue temperature fluctuation differences and contact pressure values, the baseline energy parameters are fine-tuned to output the optimal energy parameters that adapt to the current dynamic state of the tissue.

[0035] S34, Gradual Buffer Output: Based on the optimal energy parameters adapted to the current dynamic state of the tissue, a stepped gradual buffer mechanism is adopted. By controlling the pulse width or amplitude of the high-frequency generator, the target energy value is output within the preset energy range, and the output energy is stable.

[0036] S4, Surgical effect closed-loop correction: Based on stable energy, monitor surgical wound data and compare it with preset standards, and iteratively update energy matching parameters according to deviation data.

[0037] As a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment method of the present invention, the specific steps of S1 are as follows:

[0038] S11, Tissue parameter acquisition: Real-time acquisition of impedance value, dielectric constant and surface temperature of human tissue in the electrode contact area, and output of real-time raw tissue parameter set;

[0039] S12, Synchronization of Operating Condition Data: Based on the real-time tissue raw parameter set, the operating condition parameters of the surgical electrode are synchronously collected and fused with the real-time tissue raw parameter set to generate a standardized real-time tissue operating condition dataset.

[0040] In a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment method of the present invention, the specific steps of S2 are as follows:

[0041] S21, Data noise reduction: Based on the standardized real-time organizational condition dataset, the adaptive Kalman filter algorithm is used to remove noisy data, and the effective data is normalized to output interference-free standardized operating condition data.

[0042] S22, Intraoperative interference identification: Based on interference-free standardized working condition data and relying on the preset intraoperative interference feature library, identify non-tissue body state interference signals, mark and isolate invalid interference data, and output pure tissue body working condition data.

[0043] S23, Tissue Status Classification: Based on pure tissue body working condition data, the tissue status identification model is called to determine the current tissue type and thermal damage risk level, and the tissue status classification result is output.

[0044] S24, Trend Prediction: Based on the tissue state classification results and combined with historical working condition data, the future trends of tissue dehydration, carbonization and impedance changes are estimated through time series prediction algorithms, and the tissue state prediction results and risk warning levels are output.

[0045] In a preferred embodiment of the adaptive tissue state surgical electrode energy dynamic adjustment method described in this invention, the specific steps of S4 are as follows:

[0046] S41, Intraoperative effect monitoring: Based on stable energy, it automatically identifies and quantifies the tissue cutting smoothness, carbonized area gray value, and bleeding area percentage of the surgical wound, and outputs surgical effect deviation data after comparing it with the preset standard surgical effect threshold.

[0047] S42, Parameter Iterative Update: Based on surgical outcome deviation data, the matching threshold of the energy mapping database is corrected in reverse to optimize the energy parameter range corresponding to different tissue states.

[0048] Compared with existing technologies:

[0049] 1. By collecting multi-dimensional tissue biological parameters to classify tissue status, matching exclusive benchmark energy parameters and setting safety threshold constraints, it makes up for the lack of a benchmark energy classification and matching mechanism for the differentiated characteristics of tissues in existing technologies. It can achieve precise differentiated energy adaptation for different types of surgical tissues, effectively avoiding tissue burns due to excessive energy and surgical blockage failure due to insufficient energy.

[0050] 2. By collecting real-time intraoperative dynamic tissue condition data and combining interference identification and state trend prediction technologies, changes such as tissue carbonization and impedance fluctuations can be detected in advance. It is equipped with precise parameter fine-tuning under safety threshold constraints, step-by-step gradual buffer output, and a closed-loop iteration mechanism for surgical effects. This makes up for the lack of pre-safety threshold constraints and gradual buffer mechanisms in the energy output of existing technologies. It can achieve real-time adaptation to the dynamic state of tissue throughout the entire process, significantly improving the stability of surgical operation and wound safety. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the overall framework of the present invention;

[0052] Figure 2 This is a schematic diagram of the framework of the organization condition full-domain acquisition module of the present invention;

[0053] Figure 3 This is a schematic diagram of the organizational state intelligent judgment module framework of the present invention;

[0054] Figure 4 This is a schematic diagram of the electrode energy dynamic adaptation module framework of the present invention;

[0055] Figure 5This is a schematic diagram of the surgical effect closed-loop correction module framework of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0057] This invention provides a surgical electrode energy dynamic adjustment system that adapts to tissue conditions. Please refer to [link / reference]. Figures 1-5 ,include:

[0058] The tissue condition full-domain acquisition module collects raw tissue parameters and electrode working condition data in the surgical area in real time, and generates a standardized real-time tissue condition dataset.

[0059] The tissue parameter acquisition unit, through a high-precision sensing module integrated into the tip of the surgical electrode, collects three core raw biological parameters in real time from the human tissue in the electrode contact area: impedance value, dielectric constant (used to indirectly estimate water content), and surface temperature. These parameters are continuously input into the data terminal at a sampling frequency of 100Hz, and the unit outputs a real-time set of raw tissue parameters. The water content is obtained indirectly through the mapping relationship between the dielectric constant and an empirical model, eliminating the need for direct measurement.

[0060] The operating data synchronization unit, based on a real-time raw tissue parameter set, synchronously collects equipment operating parameters such as the real-time output power of the surgical electrodes, the contact pressure between the electrodes and the tissue, and the continuous working duration. It then integrates biological parameters with equipment operating parameters to generate a standardized real-time tissue operating data set.

[0061] The intelligent organizational status assessment module, based on a standardized real-time organizational condition dataset, performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels.

[0062] The data acquisition and noise reduction unit, based on a standardized real-time tissue condition dataset, uses an adaptive Kalman filter algorithm to remove abnormal noise data caused by intraoperative environmental interference and instantaneous current fluctuations, normalizes the effective data, and outputs interference-free standardized condition data.

[0063] The intraoperative interference identification unit, based on interference-free standardized operating condition data and relying on a pre-set intraoperative interference feature library, identifies non-tissue-specific interference signals such as surgical smoke, transient bleeding, and minor tissue traction, marks and isolates invalid interference data, and outputs pure tissue-specific operating condition data. The interference feature library is generated through machine learning pre-training based on noise data from a large number of clinical surgical samples.

[0064] The tissue state grading unit, based on pure tissue ontology working condition data, calls a pre-trained tissue state recognition model, compares the impedance, temperature, and dielectric constant threshold ranges of different tissues, determines the current tissue type (fat, muscle, connective tissue, diseased tissue) and thermal damage risk level, and outputs the tissue state grading results.

[0065] The tissue condition trend prediction unit, based on the tissue condition classification results and combined with three consecutive frames of historical operating condition data, estimates the trends of tissue dehydration, carbonization, and impedance changes within the next 1-2 seconds using a time-series prediction algorithm (such as a long short-term memory network or Kalman filter trend fitting). It then outputs the tissue condition prediction result and risk warning level. Here, "prediction" is based on trend extrapolation from a limited number of frames of data, rather than precise deduction.

[0066] The electrode energy dynamic adaptation module matches the baseline energy parameters based on the tissue state prediction results and risk warning level, applies safety threshold constraints and performs parameter fine-tuning, and outputs stable energy through a gradual buffering mechanism.

[0067] The reference energy matching unit, based on the organization status prediction results and risk warning level, retrieves the built-in multi-scenario energy mapping database, matches the reference voltage, reference frequency, and reference output power parameters corresponding to the organization type, risk level, and status change trend, and generates an initial energy output scheme.

[0068] The energy threshold constraint unit, based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, defines the upper and lower safety thresholds of real-time energy output, locks the dangerous energy range, and generates an energy prediction scheme with safety constraints.

[0069] The parameter fine-tuning unit, based on an energy prediction scheme with safety constraints, combines real-time tissue temperature fluctuation differences and contact pressure values ​​to perform millisecond-level fine-tuning of the baseline energy parameters, correct energy output deviations, and output optimal energy parameters that adapt to the current dynamic state of the tissue.

[0070] The gradual buffer output unit, based on optimal energy parameters adapted to the current dynamic state of the tissue, replaces the instantaneous switching mode with a stepped gradual buffer mechanism. By controlling the pulse width or amplitude of the high-frequency generator, it gradually adjusts to the target energy value within 2-5 energy output cycles, achieving a smooth power transition, avoiding instantaneous energy pulse impacts, and ultimately executing stable energy output.

[0071] The surgical outcome closed-loop correction module, based on stable energy, monitors surgical wound data and compares it with preset standards, and iteratively updates energy matching parameters according to deviation data.

[0072] The intraoperative outcome monitoring unit, based on stable energy, automatically identifies and quantifies the tissue cut smoothness, grayscale value of carbonized areas, and percentage of bleeding area of ​​the surgical wound through a vision module (such as a miniature camera) or ultrasound probe integrated into the surgical electrodes. It compares these data with preset standard surgical outcome thresholds and outputs surgical outcome deviation data. The vision module can acquire wound images in real time, evaluate the smoothness of the cut edges through edge detection algorithms, and identify carbonized and bleeding areas through color analysis.

[0073] The parameter iteration and update unit, based on surgical outcome deviation data, reversely corrects the matching threshold of the energy mapping database, optimizes the energy parameter range corresponding to different tissue states, completes the adaptive parameter iteration for this surgery, and achieves dynamic closed-loop adjustment throughout the entire process.

[0074] A method for dynamically adjusting the energy of a surgical electrode to adapt to tissue conditions, comprising the following steps:

[0075] S1, Tissue Condition Full-Domain Acquisition: Real-time acquisition of raw tissue parameters and electrode working condition data in the surgical area to generate a standardized real-time tissue condition dataset;

[0076] S11, Tissue Parameter Acquisition: A high-precision sensing module integrated into the tip of the surgical electrode collects three core biological parameters in real time from the human tissue in the electrode contact area: impedance, dielectric constant (used to indirectly estimate water content), and surface temperature. These parameters are continuously entered into the data terminal at a sampling frequency of 100Hz, outputting a real-time set of raw tissue parameters. The water content is obtained indirectly through the mapping relationship between the dielectric constant and an empirical model, eliminating the need for direct measurement.

[0077] S12, Synchronization of Operating Condition Data: Based on the real-time raw tissue parameter set, synchronously collect equipment operating condition parameters such as the real-time output power of the surgical electrode, the contact pressure between the electrode and the tissue, and the continuous working duration. Integrate biological parameters with equipment operating condition parameters to generate a standardized real-time tissue operating condition dataset.

[0078] S2, Intelligent Analysis of Organizational Status: Based on a standardized real-time organizational status dataset, it performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels.

[0079] S21, Data Noise Reduction: Based on a standardized real-time tissue condition dataset, an adaptive Kalman filter algorithm is used to remove abnormal noise data caused by intraoperative environmental interference and instantaneous current fluctuations. The effective data is normalized to output interference-free standardized condition data.

[0080] S22, Intraoperative Interference Identification: Based on interference-free standardized operating condition data and relying on a pre-set intraoperative interference feature library, this method identifies non-tissue-specific interference signals such as surgical smoke, transient bleeding, and minor tissue traction, marks and isolates invalid interference data, and outputs pure tissue-specific operating condition data. The interference feature library is generated through machine learning pre-training based on noise data from a large number of clinical surgical samples.

[0081] S23, Tissue State Grading: Based on pure tissue ontology working condition data, the pre-trained tissue state recognition model is called, and the current tissue type (fat, muscle, connective tissue, diseased tissue) and thermal damage risk level are determined by comparing the impedance, temperature, and dielectric constant threshold ranges of different tissues, and the tissue state grading results are output.

[0082] S24, Trend Prediction: Based on the tissue state classification results and combined with three consecutive frames of historical operating data, the dehydration, carbonization, and impedance change trends of the tissue within the next 1-2 seconds are estimated using a time-series prediction algorithm (such as a long short-term memory network or Kalman filter trend fitting). The tissue state prediction result and risk warning level are output. Here, "prediction" is based on trend extrapolation from a limited number of frames of data, rather than precise deduction.

[0083] S3, Dynamic adaptation of electrode energy: Based on the tissue state prediction results and risk warning level, the baseline energy parameters are matched, a safety threshold constraint is applied and the parameters are fine-tuned, and a stable energy is output through a gradual buffering mechanism.

[0084] S31, Baseline Energy Matching: Based on the organizational state prediction results and risk warning level, the built-in multi-scenario energy mapping database is retrieved to match the baseline voltage, baseline frequency, and baseline output power parameters corresponding to the organizational type, risk level, and state change trend, and an initial energy output scheme is generated.

[0085] S32, Energy Threshold Constraint: Based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, define the upper and lower safety thresholds of real-time energy output, lock the dangerous energy range, and generate an energy prediction scheme with safety constraints.

[0086] S33, Precise Parameter Fine-Tuning: Based on an energy prediction scheme with safety constraints, combined with real-time tissue temperature fluctuation differences and contact pressure values, the baseline energy parameters are finely tuned at the millisecond level to correct energy output deviations and output optimal energy parameters that adapt to the current dynamic state of the tissue.

[0087] S34, Gradual Buffer Output: Based on the optimal energy parameters adapted to the current dynamic state of the tissue, a stepped gradual buffer mechanism is used to replace the instantaneous switching mode. By controlling the pulse width or amplitude of the high-frequency generator, the output is gradually adjusted to the target energy value within 2-5 energy output cycles, achieving a smooth power transition, avoiding instantaneous energy pulse impacts, and ultimately executing stable energy output.

[0088] S4, Surgical effect closed-loop correction: Based on stable energy, monitor surgical wound data and compare it with preset standards, and iteratively update energy matching parameters according to deviation data;

[0089] S41, Intraoperative Outcome Monitoring: Based on stable energy, the system automatically identifies and quantifies the tissue cut smoothness, grayscale value of carbonized areas, and percentage of bleeding area of ​​the surgical wound through a vision module (such as a miniature camera) or ultrasound probe integrated into the surgical electrodes. This data is compared with preset standard surgical outcome thresholds, and the system outputs surgical outcome deviation data. The vision module can acquire wound images in real time, evaluate the smoothness of the cut edges through edge detection algorithms, and identify carbonized and bleeding areas through color analysis.

[0090] S42, Parameter Iteration Update: Based on surgical outcome deviation data, the matching threshold of the energy mapping database is corrected in reverse, the energy parameter range corresponding to different tissue states is optimized, and the adaptive parameter iteration of this surgery is completed, realizing dynamic closed-loop adjustment throughout the entire process.

[0091] Although the present invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the disclosed embodiments can be combined with each other in any manner. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A surgical electrode energy dynamic adjustment system that adapts to tissue conditions, characterized in that, include: The tissue condition full-domain acquisition module collects raw tissue parameters and electrode working condition data in the surgical area in real time, and generates a standardized real-time tissue condition dataset. The intelligent organizational status assessment module, based on a standardized real-time organizational condition dataset, performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels. The electrode energy dynamic adaptation module includes a reference energy matching unit, an energy threshold constraint unit, a parameter fine-tuning unit, and a gradual buffer output unit. The reference energy matching unit, based on the organization status prediction result and risk warning level, retrieves the built-in multi-scenario energy mapping database, matches the reference voltage, reference frequency, and reference output power parameters, and generates an initial energy output scheme. The energy threshold constraint unit, based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, defines the upper and lower safety thresholds of real-time energy output and generates an energy prediction scheme with safety constraints. The parameter fine-tuning unit, based on an energy prediction scheme with safety constraints, combines real-time tissue temperature fluctuation differences and contact pressure values ​​to fine-tune the baseline energy parameters and output the optimal energy parameters that adapt to the current dynamic state of the tissue. The gradual buffer output unit, based on the optimal energy parameters adapted to the current dynamic state of the tissue, adopts a stepped gradual buffer mechanism to output a target energy value within a preset energy range by controlling the pulse width or amplitude of the high-frequency generator, thus outputting stable energy. The surgical outcome closed-loop correction module monitors surgical wound data based on stable energy and compares it with preset standards, iteratively updating energy matching parameters based on deviation data.

2. The adaptive tissue state-based surgical electrode energy dynamic adjustment system according to claim 1, characterized in that, The tissue condition global data acquisition module includes: The tissue parameter acquisition unit collects the impedance value, dielectric constant and surface temperature of human tissue in the electrode contact area in real time, and outputs the real-time raw tissue parameter set. The working condition data synchronization unit synchronously collects the working condition parameters of the surgical electrodes based on the real-time tissue raw parameter set, and merges them with the real-time tissue raw parameter set to generate a standardized real-time tissue working condition dataset.

3. The self-adapting tissue state surgical electrode energy dynamic adjustment system of claim 1, wherein, The intelligent organizational status assessment module includes: The data acquisition and noise reduction unit, based on the standardized real-time organizational condition dataset, uses an adaptive Kalman filter algorithm to remove noisy data, normalizes the effective data, and outputs interference-free standardized operating condition data. The intraoperative interference identification unit, based on interference-free standardized working condition data and relying on a pre-set intraoperative interference feature library, identifies interference signals that are not in the tissue body state, marks and isolates invalid interference data, and outputs pure tissue body working condition data. The tissue status classification unit, based on pure tissue condition data, calls the tissue status recognition model to determine the current tissue type and thermal damage risk level, and outputs the tissue status classification result. The status trend prediction unit, based on the tissue status classification results and combined with historical operating data, estimates the future trends of tissue dehydration, carbonization and impedance changes through a time-series prediction algorithm, and outputs tissue status prediction results and risk warning levels.

4. The self-adapting tissue state surgical electrode energy dynamic adjustment system of claim 1, wherein, The surgical outcome closed-loop correction module includes: The intraoperative effect monitoring unit, based on stable energy, automatically identifies and quantifies the tissue cutting smoothness, carbonized area gray value, and bleeding area percentage of the surgical wound, and outputs surgical effect deviation data after comparing it with the preset standard surgical effect threshold. The parameter iterative update unit, based on surgical outcome deviation data, reversely corrects the matching threshold of the energy mapping database and optimizes the energy parameter region corresponding to different tissue states.

5. A method for adaptive tissue state electrode energy dynamic adjustment, comprising: Includes the following steps: S1, Tissue Condition Full-Domain Acquisition: Real-time acquisition of raw tissue parameters and electrode working condition data in the surgical area to generate a standardized real-time tissue condition dataset; S2, Intelligent Analysis of Organizational Status: Based on a standardized real-time organizational status dataset, it performs data noise reduction, interference identification, organizational status classification, and status trend prediction, and outputs organizational status prediction results and risk warning levels. S3, Dynamic Electrode Energy Adaptation: S31, Baseline Energy Matching: Based on the organization status prediction results and risk warning level, the built-in multi-scenario energy mapping database is retrieved to match the baseline voltage, baseline frequency, and baseline output power parameters to generate an initial energy output scheme. S32, Energy Threshold Constraint: Based on the initial energy output scheme and combined with the current tissue thermal damage risk warning level, define the upper and lower safety thresholds of real-time energy output and generate an energy prediction scheme with safety constraints. S33, Precise parameter fine-tuning: Based on an energy prediction scheme with safety constraints, combined with real-time tissue temperature fluctuation difference and contact pressure value, the baseline energy parameters are fine-tuned to output the optimal energy parameters that adapt to the current tissue dynamic state. S34, Gradual Buffer Output: Based on the optimal energy parameters adapted to the current dynamic state of the tissue, a stepped gradual buffer mechanism is adopted. By controlling the pulse width or amplitude of the high-frequency generator, the target energy value is output within the preset energy range, and the output energy is stable. S4, Surgical effect closed-loop correction: Based on stable energy, monitor surgical wound data and compare it with preset standards, and iteratively update energy matching parameters according to deviation data.

6. The method of claim 5, wherein the method further comprises: The specific steps of S1 are as follows: S11, Tissue parameter acquisition: Real-time acquisition of impedance value, dielectric constant and surface temperature of human tissue in the electrode contact area, and output of real-time raw tissue parameter set; S12, Synchronization of Operating Condition Data: Based on the real-time tissue raw parameter set, the operating condition parameters of the surgical electrode are synchronously collected and fused with the real-time tissue raw parameter set to generate a standardized real-time tissue operating condition dataset.

7. The method of claim 5, wherein the method further comprises: The specific steps of S2 are as follows: S21, Data noise reduction: Based on the standardized real-time organizational condition dataset, the adaptive Kalman filter algorithm is used to remove noisy data, and the effective data is normalized to output interference-free standardized operating condition data. S22, Intraoperative interference identification: Based on interference-free standardized working condition data and relying on the preset intraoperative interference feature library, identify interference signals that are not in the tissue body state, mark and isolate invalid interference data, and output pure tissue body working condition data. S23, Tissue Status Classification: Based on pure tissue body working condition data, the tissue status identification model is called to determine the current tissue type and thermal damage risk level, and the tissue status classification result is output. S24, Trend Prediction: Based on the tissue state classification results and combined with historical working condition data, the future trends of tissue dehydration, carbonization and impedance changes are estimated through time series prediction algorithms, and the tissue state prediction results and risk warning levels are output.

8. The method of claim 5, wherein the method further comprises: The specific steps of S4 are as follows: S41, Intraoperative effect monitoring: Based on stable energy, it automatically identifies and quantifies the tissue cutting smoothness, carbonized area gray value, and bleeding area percentage of the surgical wound, and outputs surgical effect deviation data after comparing it with the preset standard surgical effect threshold. S42, Parameter Iterative Update: Based on surgical outcome deviation data, the matching threshold of the energy mapping database is corrected in reverse to optimize the energy parameter range corresponding to different tissue states.

Images