Intelligent energy control method and system for an electrosurgical energy platform

Abstract

This invention relates to the field of medical device technology, specifically to an intelligent energy control method and system for an electrosurgical energy platform. The method includes: real-time acquisition of multi-dimensional electrophysiological parameters at the tissue-electrode contact point during electrosurgical procedures, including tissue impedance, voltage, current, and phase difference; inputting the acquired multi-dimensional electrophysiological parameters into a pre-trained tissue type recognition model to identify the currently contacting tissue type and determine its corresponding energy safety threshold; dynamically calculating the optimal energy output parameters based on the identified tissue type and surgical operation mode; and real-time monitoring of tissue state changes, automatically adjusting energy output or triggering a safety protection mechanism when the tissue state reaches a preset critical value. This invention achieves adaptive intelligent control of the electrosurgical energy platform through a combination of multi-parameter fusion sensing and artificial intelligence algorithms, improving surgical safety and accuracy, reducing tissue thermal damage, and lowering the risk of surgical complications.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to an intelligent energy control method and system for an electrosurgical energy platform. Background Technology

[0002] Electrosurgical energy platforms are indispensable equipment in modern surgery. They use high-frequency currents to cut and coagulate human tissues, and are widely used in general surgery, obstetrics and gynecology, urology, cardiothoracic surgery, and many other fields. Electrosurgical procedures have advantages such as less bleeding, shorter operation time, and faster postoperative recovery, but they also carry certain risks.

[0003] Currently, most traditional electrosurgical energy platforms use fixed energy output modes, requiring surgeons to manually adjust energy parameters based on their experience. This approach has several drawbacks: First, the electrophysiological characteristics and thermal tolerance of different human tissues vary greatly, and fixed energy parameters cannot meet the needs of different tissues, easily leading to excessive thermal damage or inadequate hemostasis. Second, tissue states change continuously during surgery, such as transforming from normal tissue to carbonized tissue, and fixed energy output cannot respond to these changes in real time. Third, there is a lack of effective safety protection mechanisms; if arcing or tissue carbonization occurs, the energy output cannot be cut off in time, potentially leading to serious surgical complications. Finally, it requires a high level of surgical experience, and novice surgeons are prone to causing medical accidents due to improper parameter settings.

[0004] Therefore, it is necessary to develop an electrosurgical energy platform control method and system that can identify tissue type in real time, dynamically adjust energy output, and have intelligent safety protection functions to improve the safety and accuracy of surgery. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, this invention provides an intelligent energy control method and system for an electrosurgical energy platform, thereby resolving the technical problems of inaccurate energy control and poor safety in traditional electrosurgical energy platforms.

[0006] This invention is achieved through the following technical solution: A smart energy control method for an electrosurgical energy platform is provided, the method comprising the following steps: Step S10: Real-time acquisition of multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery, including tissue impedance, voltage, current, and phase difference; Step S20: Input the collected multidimensional electrophysiological parameters into the pre-trained tissue type recognition model to identify the current tissue type in real time and determine its corresponding energy safety threshold. Step S30: Based on the identified tissue type and surgical operation mode, dynamically calculate the optimal energy output parameters and control the energy platform output; Step S40: Monitor changes in tissue status in real time. When the tissue status reaches a preset critical value, automatically adjust the energy output or trigger a safety protection mechanism. The sampling frequency of the multidimensional electrophysiological parameters in step S10 is [1kHz, 10kHz]. In step S20, the tissue type identification model adopts a hybrid deep learning model that combines convolutional neural networks and long short-term memory networks, which can identify at least 8 different human tissue types. The preset critical values ​​in step S40 include the critical impedance value for tissue carbonization, the critical temperature value for tissue coagulation, and the critical voltage value for arc discharge.

[0007] Preferably, step S10 involves real-time acquisition of multi-dimensional electrophysiological parameters at the tissue-electrode contact point during electrosurgery, and the steps include: Parameter acquisition preparation: A high-precision impedance measurement module, voltage sensor and current sensor are integrated at the output end of the electrosurgical energy platform. All sensors are calibrated to ensure that the measurement error is within ±2%. Synchronous data acquisition: All sensors are controlled by a microcontroller to start data acquisition synchronously, with data acquisition timestamps accurate to the microsecond level; Data preprocessing: The collected raw data is filtered to remove power frequency interference and high-frequency noise, and the data is smoothed using a moving average algorithm.

[0008] Preferably, in step S20, the collected multi-dimensional electrophysiological parameters are input into a pre-trained tissue type recognition model to identify the currently contacted tissue type in real time and determine its corresponding energy safety threshold. The steps include: Feature extraction: Time-domain and frequency-domain features were extracted from the preprocessed multi-dimensional electrophysiological parameters, including mean impedance, rate of change of impedance, effective voltage, effective current and power factor. Tissue identification: The extracted time-domain and frequency-domain features are input into a pre-trained tissue type identification model, which outputs the probability distribution of the type of the currently contacted tissue and selects the tissue type with the highest probability as the identification result; Threshold determination: Based on the identified tissue type, query the energy safety threshold corresponding to the tissue from the preset tissue parameter database, including the maximum allowable output power, the longest continuous output time, and the highest output voltage.

[0009] Preferably, in step S30, the optimal energy output parameters are dynamically calculated and the energy platform output is controlled based on the identified tissue type and surgical operation mode. This step includes: Operating mode recognition: By detecting the status of the foot switch on the energy platform and the button on the electrode handle, the current surgical operating mode is identified, including cutting mode, coagulation mode and mixed mode; Energy parameter calculation: Based on tissue type, energy safety threshold and surgical operation mode, the optimal energy output parameters, including output power, output frequency and duty cycle, are calculated using a fuzzy control algorithm. Energy output control: The calculated optimal energy output parameters are sent to the power control module of the energy platform to adjust the energy output in real time.

[0010] Preferably, in step S40, the tissue state changes are monitored in real time. When the tissue state reaches a preset critical value, the energy output is automatically adjusted or a safety protection mechanism is triggered. The steps include: Tissue condition monitoring: Real-time calculation of tissue impedance change rate and power loss, and estimation of tissue temperature through heat conduction model; Critical state judgment: The monitored tissue state parameters are compared with preset critical values ​​to determine whether the tissue is about to reach the carbonization, solidification or arc discharge state. Safety control: When the tissue condition is detected to be close to the critical value, the energy output power is gradually reduced; when the critical value is reached, the energy output is immediately cut off and an audible and visual alarm is issued.

[0011] Preferably, the method further includes an online model update step: During the surgery, the tissue type identification results and corresponding electrophysiological parameters are recorded. When a doctor confirms an error in tissue type identification, the incorrect sample and the correct label are added to the training dataset. During surgical breaks or when equipment is idle, the tissue type identification model is incrementally learned and its parameters are updated.

[0012] Preferably, the step of estimating tissue temperature using a thermal conduction model includes: Establish a one-dimensional heat conduction model that takes into account the thermal conductivity, specific heat capacity and density of the tissue. Calculate the heat absorbed by the tissue based on the energy output power and the duration of action; Based on the one-dimensional heat conduction model, the temperature distribution at different depths of the tissue was obtained, and the surface temperature was taken as the estimation result.

[0013] The present invention also provides an intelligent energy control system for an electrosurgical energy platform, comprising: Multi-parameter acquisition module: Real-time acquisition of multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery, including tissue impedance, voltage, current and phase difference; Tissue type identification module: Input the collected multi-dimensional electrophysiological parameters into the pre-trained tissue type identification model to identify the current tissue type in real time and determine its corresponding energy safety threshold; Intelligent energy calculation module: dynamically calculates the optimal energy output parameters based on the identified tissue type and surgical operation mode; Safety protection and control module: Real-time monitoring of changes in organizational status; when the organizational status reaches a preset critical value, it automatically adjusts energy output or triggers a safety protection mechanism. The sampling frequency of the multi-dimensional electrophysiological parameters in the multi-parameter acquisition module is from 1 kHz to 10 kHz, including 1 kHz and 10 kHz. The tissue type identification module employs a hybrid deep learning model combining convolutional neural networks and long short-term memory networks, which can identify at least eight different human tissue types. The preset critical values ​​in the safety protection control module include the critical impedance value for tissue carbonization, the critical temperature value for tissue solidification, and the critical voltage value for arc discharge.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes an intelligent energy control device for an electrosurgical energy platform. The device includes: a memory, a processor, and a program for intelligent energy control of the electrosurgical energy platform stored in the memory and executable on the processor. The program for intelligent energy control of the electrosurgical energy platform comprises the steps for implementing the intelligent energy control method for an electrosurgical energy platform as described above.

[0015] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as intelligent energy control of an electrosurgical energy platform. When the intelligent energy control program of the electrosurgical energy platform is executed by a processor, it implements an intelligent energy control method for an electrosurgical energy platform as described above.

[0016] The beneficial effects of this invention are as follows: 1. This invention collects multi-dimensional electrophysiological parameters at the contact point between tissue and electrode in real time, including impedance, voltage, current and phase difference, and uses a hybrid deep learning model based on convolutional neural network and long short-term memory network to identify tissue type in real time. It can accurately distinguish at least 8 different human tissue types, providing accurate tissue characteristic input for subsequent intelligent energy control. This fundamentally changes the traditional mode of relying on doctors' vision and experience to judge tissue type, and improves the objectivity and accuracy of energy control. 2. This invention dynamically calculates and outputs optimal energy parameters based on the identified tissue type, preset energy safety threshold, and real-time identified surgical operation modes, such as cutting and coagulation, achieving intelligent matching of energy output with specific tissues and surgical intentions. Simultaneously, by real-time monitoring of tissue impedance changes and estimation of tissue temperature and other state parameters, and comparing them with preset critical values ​​for carbonization, coagulation, and arc discharge, it achieves closed-loop monitoring and safety protection of the tissue state. It can automatically adjust or cut off energy output when the tissue is about to reach a dangerous state, effectively preventing excessive tissue damage and unexpected complications, and significantly improving the overall safety and controllability of electrosurgery. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of an intelligent energy control method for an electrosurgical energy platform according to the present invention.

[0019] Figure 2 This is a schematic diagram of the intelligent energy control system structure of an electrosurgical energy platform according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, in one embodiment of the present invention, an intelligent energy control method for an electrosurgical energy platform includes the following steps: Step S10: Real-time acquisition of multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery, including tissue impedance, voltage, current, and phase difference; Specifically, the "multidimensional electrophysiological parameters" in this step refer to several key physical quantities that reflect the electrical properties of the tissue, synchronously acquired from the interface between the electrosurgical energy platform output and the biological tissue. These include: tissue impedance (reflecting the tissue's resistance to current), voltage (potential difference across the electrodes), current (current intensity flowing through the tissue), and phase difference (phase shift between the voltage and current waveforms, reflecting the capacitive or inductive component of the tissue). These parameters are acquired in real time at a high sampling frequency of 1kHz to 10kHz (including values ​​at both ends), ensuring data timeliness and high resolution, and capturing rapid dynamic changes in the tissue under energy. The acquired raw multidimensional parameter sequences form the data foundation for subsequent tissue identification and state analysis.

[0022] Specifically, this step serves as the data input for the entire intelligent energy control process. Its technical advantage lies in providing the system with real-time, high-precision raw tissue electrophysiological information. By synchronously acquiring four key parameters—impedance, voltage, current, and phase difference—at high frequency, the instantaneous electrical characteristics of the tissue at the current electrode contact point can be comprehensively and three-dimensionally characterized. This avoids the potential limitations of a single parameter and provides reliable and abundant data support for accurate analysis and decision-making in subsequent steps.

[0023] Specifically, compared to traditional electrosurgical equipment that may only monitor a single parameter such as output power or current, or whose sampling frequency is too low to capture rapid transients, this step, through high-frequency (1-10kHz) synchronous acquisition of multi-dimensional parameters, can more sensitively and comprehensively perceive the microscopic response of tissue under energy. This is equivalent to equipping the energy platform with a high-precision "sensory system," enabling it to "sense" subtle changes in the electrical properties of tissue, laying the data foundation for achieving true adaptive control, and breaking through the bottleneck of insufficient information perception in traditional open-loop control.

[0024] For example, when cutting a mixed tissue containing muscle and fat, the type of tissue in contact with the electrode can change within milliseconds as the electrode moves. This step continuously acquires parameters such as impedance at frequencies up to 10 kHz, enabling immediate detection of impedance jumps as the electrode moves from muscle (relatively low impedance) to fat (relatively high impedance), along with accompanying changes in voltage and current waveforms. This rapid, multi-dimensional data acquisition capability allows the system to promptly perceive changes in the tissue interface, paving the way for accurate tissue type identification in subsequent steps.

[0025] Step S20: Input the collected multidimensional electrophysiological parameters into the pre-trained tissue type recognition model to identify the current tissue type in real time and determine its corresponding energy safety threshold. Specifically, the "tissue type identification model" in this step is a hybrid deep learning model pre-trained using a large amount of labeled tissue electrophysiological parameter data. Its architecture combines convolutional neural networks (CNNs) and long short-term memory networks (LSTMs). CNNs excel at extracting spatial features from local data, while LSTMs excel at handling long-term dependencies in time-series data. The model input is the multi-dimensional electrophysiological parameter time series collected and preprocessed in step S10, and the output is the probability distribution of the currently contacted tissue belonging to a predefined category (such as skin, muscle, fat, blood vessels, nerves, fascia, bone, tumor tissue, etc., at least 8 types). After identifying the tissue type, the system queries and retrieves the corresponding "energy safety threshold" from a pre-set "tissue parameter database." These thresholds include, but are not limited to, the maximum allowable output power, the longest safe action time, and the highest tolerated voltage, setting safety boundaries for the next step of energy calculation.

[0026] Specifically, the technical effect of this step lies in transforming the raw electrophysiological data stream into tissue type labels with clear medical significance and their safety constraints. It acts as the system's "intelligent recognition brain," achieving automated and real-time identification of the contacted tissue type through sophisticated pattern recognition capabilities, and associating it with the corresponding energy safety upper limit. This allows energy control decisions to be based on accurate tissue identification and safety regulations.

[0027] Specifically, compared to the traditional method of relying entirely on the surgeon's visual observation and tactile experience to determine tissue type, this step achieves objective, quantitative, and rapid automatic identification through an artificial intelligence model. This not only reduces over-reliance on the surgeon's personal experience and minimizes the possibility of subjective misjudgment, but more importantly, its identification speed (real-time) and the number of identifiable tissue types (at least 8) far exceed the instantaneous judgment ability of humans. Especially in minimally invasive surgeries where the field of vision is limited or tissues have similar appearances, this identification method based on electrophysiological characteristics provides a new and reliable dimension for judgment, which is a key prerequisite for achieving precise energy delivery.

[0028] For example, during laparoscopic partial hepatectomy, electrodes may sequentially contact the liver parenchyma, intrahepatic small blood vessels, and peribiliary tissue. These tissues may be visually difficult to distinguish. The identification model in this step, by analyzing real-time impedance change patterns and voltage-current phase relationships, can quickly determine that the currently contacted tissue is highly vascularized (with specific impedance pulsation characteristics). It then immediately applies the lower energy safety threshold corresponding to the vascular tissue (to prevent vascular rupture and bleeding), instead of using the higher threshold for the liver parenchyma. This real-time identification and threshold matching ensures safe operation.

[0029] Step S30: Based on the identified tissue type and surgical operation mode, dynamically calculate the optimal energy output parameters and control the energy platform output; Specifically, the "surgical operation mode" in this step refers to the surgical function that the doctor intends to perform through input devices such as foot switches and handle buttons. This mainly includes a cutting mode (primarily for tissue vaporization and separation), a coagulation mode (primarily for protein heating and vascular closure), and a mixed mode (balancing cutting and coagulation). The system identifies the current mode by detecting the status of these input devices. "Dynamically calculating the optimal energy output parameters" means that, within the tissue type and safety threshold framework determined in step S20, and in conjunction with the requirements of the currently identified surgical mode, intelligent algorithms such as fuzzy control are used to calculate in real time the most suitable combination of energy output parameters for the current situation. This mainly includes output power (determining energy intensity), output frequency (affecting cutting fineness), and duty cycle (pulse operation mode, affecting heat diffusion). The calculated parameters are sent in real time to the power control module of the energy platform, driving the power generator to adjust the output.

[0030] Specifically, the technical effect of this step lies in achieving intelligent decision-making and real-time control of energy output. As the system's "control center," it integrates two key inputs: tissue identity information (type and safety threshold) and the doctor's operational intent (surgical mode). Through algorithmic fusion, it outputs personalized optimal energy parameters and directly drives hardware execution. This makes energy output no longer fixed or manually adjustable, but adaptable to the two core variables: "which tissue is being treated" and "what operation is being performed."

[0031] Specifically, compared to existing technologies where doctors need to repeatedly try and switch between multiple energy levels and modes based on experience, this step achieves a shift from "human adapting to machine" to "machine adapting to human and tissue." The system automatically completes a complex parameter optimization process, outputting a "customized" energy solution tailored to the specific scenario. This not only reduces the cognitive and operational burden on doctors, allowing them to focus more on the surgery itself, but more importantly, it ensures that the energy output at any given moment matches the tissue characteristics and surgical goals, thus theoretically achieving the best surgical outcome (such as smooth cutting and reliable hemostasis) and minimal collateral damage.

[0032] For example, when the system identifies the current tissue as "muscle tissue" and the doctor presses the foot switch to enter "fine cutting mode," this step dynamically calculates a set of parameters with relatively low power, high frequency, and appropriate duty cycle, based on the safety threshold of muscle tissue and the high requirements for thermal damage control during fine cutting. This controls the energy platform to output a current that effectively separates muscle fibers while minimizing surrounding thermal damage. If the doctor switches to "coagulation mode" to treat a small bleeding point, the system immediately recalculates and outputs a set of energy parameters suitable for coagulation (usually requiring lower frequency and different waveforms). The entire process requires no manual adjustment of the energy knob by the doctor.

[0033] Step S40: Real-time monitoring of tissue state changes; when the tissue state reaches a preset critical value, automatic adjustment of energy output or triggering of a safety protection mechanism; the sampling frequency of the multi-dimensional electrophysiological parameters in step S10 is 1kHz to 10kHz, including 1kHz and 10kHz; the tissue type identification model in step S20 adopts a hybrid deep learning model combining convolutional neural networks and long short-term memory networks, which can identify at least 8 different human tissue types; the preset critical values ​​in step S40 include the critical impedance value of tissue carbonization, the critical temperature value of tissue coagulation, and the critical voltage value of arc discharge.

[0034] Specifically, the "tissue state changes" in this step mainly refer to the physicochemical changes that occur in tissues under continuous energy exposure, which are reflected in electrophysiological parameters. Monitoring includes real-time calculation of the "tissue impedance change rate" (the rate of change of impedance over time; a rapid increase often indicates carbonization) and "power loss" (the difference between the actual input power and tissue absorption), and estimation of the temperature of the tissue surface and deeper layers by establishing a simplified "heat conduction model" (considering tissue thermal conductivity, specific heat capacity, density, combined with output power and exposure time). "Preset critical values" are safety thresholds determined experimentally in advance, including: the critical impedance value for tissue carbonization (impedance rising to a certain value indicates tissue carbonization), the critical temperature value for tissue coagulation (such as the temperature threshold for protein denaturation, approximately 60-70℃), and the critical voltage value for arc discharge (excessive voltage may break down the air, generating an arc and causing non-contact damage). When any parameter monitored in real-time reaches or approaches its corresponding critical value, the system triggers a response.

[0035] Specifically, the technical effect of this step is to provide a real-time safety monitoring and protection mechanism for the entire intelligent energy control system, forming the final "safety gate" of closed-loop control. It continuously assesses the effects of energy action and potential risks, and once it detects that the tissue state is approaching a dangerous situation (such as imminent carbonization, excessive solidification, or the possibility of electric arcing), it automatically intervenes, either by adjusting the energy to avoid risks or by directly cutting off the output and issuing an alarm to prevent the damage from escalating.

[0036] Specifically, compared to traditional electrosurgical equipment which lacks effective real-time intraoperative tissue status feedback and automatic protection functions, this step represents a qualitative leap from open-loop control to closed-loop safety monitoring. Traditionally, doctors rely primarily on indirect and delayed phenomena such as tissue color and smoke emission to make judgments, easily missing the optimal intervention window. This step, by quantitatively monitoring impedance change rate and estimating temperature, can provide earlier and more objective risk warnings (e.g., an abnormal impedance change rate can provide an early warning before visible carbonization) and automatically take action. This shifts the initiative for safety protection from entirely relying on the doctor's vigilance to the system's automatic monitoring capabilities, greatly enhancing the safety of the surgical procedure, especially beneficial for inexperienced doctors or those performing lengthy and complex surgeries.

[0037] For example, coagulating the severed end of a large blood vessel requires sufficient energy and time. This step continuously monitors the tissue impedance and estimates the temperature at that location. If the impedance begins to rise abnormally rapidly due to local tissue dehydration (approaching the carbonization critical impedance value), the system will determine that there is a risk of carbonization and automatically execute a "gradual reduction of energy output power" operation to attempt to achieve coagulation while avoiding carbonization. If the impedance value spikes instantaneously above the critical value, or the estimated temperature exceeds the coagulation critical temperature value by a significant margin, the system will determine that a danger has occurred, "immediately cut off energy output," and trigger an audible and visual alarm to alert the doctor for examination and treatment, thereby preventing postoperative rebleeding due to the shedding of the carbonized scab.

[0038] In addition, such as Figure 2 As shown, in one embodiment of the present invention, an intelligent energy control system for an electrosurgical energy platform is proposed. The intelligent energy control system for the electrosurgical energy platform includes: Multi-parameter acquisition module: Real-time acquisition of multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery, including tissue impedance, voltage, current and phase difference; Tissue type identification module: Input the collected multi-dimensional electrophysiological parameters into the pre-trained tissue type identification model to identify the current tissue type in real time and determine its corresponding energy safety threshold; Intelligent energy calculation module: dynamically calculates the optimal energy output parameters based on the identified tissue type and surgical operation mode; Safety protection and control module: Real-time monitoring of changes in organizational status; when the organizational status reaches a preset critical value, it automatically adjusts energy output or triggers a safety protection mechanism. The sampling frequency of the multi-dimensional electrophysiological parameters in the multi-parameter acquisition module is from 1 kHz to 10 kHz, including 1 kHz and 10 kHz. The tissue type identification module employs a hybrid deep learning model combining convolutional neural networks and long short-term memory networks, which can identify at least eight different human tissue types. The preset critical values ​​in the safety protection control module include the critical impedance value for tissue carbonization, the critical temperature value for tissue solidification, and the critical voltage value for arc discharge.

[0039] This application provides an intelligent energy control system for an electrosurgical energy platform, employing the intelligent energy control method for an electrosurgical energy platform described in the above embodiments. This system solves the technical problems of inaccurate energy control and poor safety in traditional electrosurgical energy platforms. Compared with the prior art, the beneficial effects of the intelligent energy control system for an electrosurgical energy platform provided in this application are the same as those of the intelligent energy control method for an electrosurgical energy platform provided in the above embodiments. Furthermore, other technical features of the intelligent energy control system for an electrosurgical energy platform are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0040] This application provides an intelligent energy control device for an electrosurgical energy platform. The intelligent energy control device for the electrosurgical energy platform includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the intelligent energy control method for an electrosurgical energy platform as described in Embodiment 1 above.

[0041] In one embodiment of the present invention, an intelligent energy control device for an electrosurgical energy platform may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The described intelligent energy control device for an electrosurgical energy platform is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0042] The intelligent energy control device of an electrosurgical energy platform may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a machine-readable storage medium (RAM). The RAM also stores various programs and data required for the operation of the intelligent energy control device of the electrosurgical energy platform. The processor, ROM, and machine-readable storage medium are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus. Typically, the following systems can be connected to the I / O interface: input devices including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices including, for example, magnetic tapes, hard disks, etc.; and a communication unit. The communication unit allows the intelligent energy control device of the electrosurgical energy platform to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an intelligent energy control device for an electrosurgical energy platform with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0043] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication unit, or installed from a storage device, or installed from a read-only memory. When the computer program is executed by a processor, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0044] This application provides an intelligent energy control device for an electrosurgical energy platform, employing the intelligent energy control method for an electrosurgical energy platform described in the above embodiments. This method solves the technical problems of inaccurate energy control and poor safety in traditional electrosurgical energy platforms. Compared with the prior art, the beneficial effects of the intelligent energy control device for an electrosurgical energy platform provided in this application are the same as those of the intelligent energy control method for an electrosurgical energy platform described in the above embodiments. Furthermore, other technical features of this intelligent energy control device for an electrosurgical energy platform are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0045] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0046] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intelligent energy control method for an electrosurgical energy platform as described above.

[0047] The computer program product provided in this application can solve the technical problems of inaccurate energy control and poor safety in traditional electrosurgical energy platforms. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the intelligent energy control method for an electrosurgical energy platform provided in the above embodiments, and will not be repeated here.

[0048] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for intelligent energy control of an electrosurgical energy platform, characterized in that, The method includes the following steps: Step S10: Real-time acquisition of multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery, including tissue impedance, voltage, current, and phase difference; Step S20: Input the collected multidimensional electrophysiological parameters into the pre-trained tissue type recognition model to identify the current tissue type in real time and determine its corresponding energy safety threshold. Step S30: Based on the identified tissue type and surgical operation mode, dynamically calculate the optimal energy output parameters and control the energy platform output; Step S40: Monitor changes in tissue status in real time. When the tissue status reaches a preset critical value, automatically adjust the energy output or trigger a safety protection mechanism. The sampling frequency of the multidimensional electrophysiological parameters in step S10 is [1kHz, 10kHz]. In step S20, the tissue type identification model adopts a hybrid deep learning model that combines convolutional neural networks and long short-term memory networks, which can identify at least 8 different human tissue types. The preset critical values ​​in step S40 include the critical impedance value for tissue carbonization, the critical temperature value for tissue coagulation, and the critical voltage value for arc discharge.

2. The intelligent energy control method for an electrosurgical energy platform according to claim 1, characterized in that, Step S10 involves real-time acquisition of multi-dimensional electrophysiological parameters at the tissue-electrode contact point during electrosurgery. The steps include: Parameter acquisition preparation: A high-precision impedance measurement module, voltage sensor, and current sensor are integrated at the output end of the electrosurgical energy platform, and all sensors are calibrated; Synchronous data acquisition: The microcontroller controls all sensors to start acquiring data synchronously. Data preprocessing: The collected raw data is filtered to remove power frequency interference and high-frequency noise, and the data is smoothed using a moving average algorithm.

3. The intelligent energy control method for an electrosurgical energy platform according to claim 1, characterized in that, In step S20, the collected multidimensional electrophysiological parameters are input into a pre-trained tissue type recognition model to identify the currently contacted tissue type in real time and determine its corresponding energy safety threshold. The steps include: Feature extraction: Time-domain and frequency-domain features were extracted from the preprocessed multi-dimensional electrophysiological parameters, including mean impedance, rate of change of impedance, effective voltage, effective current and power factor. Tissue identification: The extracted time-domain and frequency-domain features are input into a pre-trained tissue type identification model, which outputs the probability distribution of the type of the currently contacted tissue and selects the tissue type with the highest probability as the identification result; Threshold determination: Based on the identified tissue type, query the energy safety threshold corresponding to the tissue from the preset tissue parameter database, including the maximum allowable output power, the longest continuous output time, and the highest output voltage.

4. The intelligent energy control method for an electrosurgical energy platform according to claim 1, characterized in that, In step S30, the optimal energy output parameters are dynamically calculated and the energy platform output is controlled based on the identified tissue type and surgical operation mode. The steps include: Operating mode recognition: By detecting the status of the foot switch on the energy platform and the button on the electrode handle, the current surgical operating mode is identified, including cutting mode, coagulation mode and mixed mode; Energy parameter calculation: Based on tissue type, energy safety threshold and surgical operation mode, the optimal energy output parameters, including output power, output frequency and duty cycle, are calculated using a fuzzy control algorithm. Energy output control: The calculated optimal energy output parameters are sent to the power control module of the energy platform to adjust the energy output in real time.

5. The intelligent energy control method for an electrosurgical energy platform according to claim 1, characterized in that, In step S40, the tissue state changes are monitored in real time. When the tissue state reaches a preset critical value, the energy output is automatically adjusted or a safety protection mechanism is triggered. The steps include: Tissue condition monitoring: Real-time calculation of tissue impedance change rate and power loss, and estimation of tissue temperature through heat conduction model; Critical state judgment: The monitored tissue state parameters are compared with preset critical values ​​to determine whether the tissue is about to reach the carbonization, solidification or arc discharge state. Safety control: When the tissue condition is detected to be close to the critical value, the energy output power is gradually reduced; when the critical value is reached, the energy output is immediately cut off and an audible and visual alarm is issued.

6. The intelligent energy control method for an electrosurgical energy platform according to claim 5, characterized in that, The steps for estimating tissue temperature using a heat conduction model in the tissue condition monitoring include: Establish a one-dimensional heat conduction model that takes into account the thermal conductivity, specific heat capacity and density of the tissue. Calculate the heat absorbed by the tissue based on the energy output power and the duration of action; Based on the one-dimensional heat conduction model, the temperature distribution at different depths of the tissue was obtained, and the surface temperature was taken as the estimation result.

7. The intelligent energy control method for an electrosurgical energy platform according to claim 1, characterized in that, The method also includes an online model update step: During the surgery, the tissue type identification results and corresponding electrophysiological parameters are recorded. When a doctor confirms an error in tissue type identification, the incorrect sample and the correct label are added to the training dataset. During surgical breaks or when equipment is idle, the tissue type identification model is incrementally learned and its parameters are updated.

8. An intelligent energy control system for an electrosurgical energy platform, characterized in that, The system executes the intelligent energy control method for an electrosurgical energy platform as described in claim 1, comprising: Multi-parameter acquisition module: used to acquire multi-dimensional electrophysiological parameters at the contact point between tissue and electrode during electrosurgery in real time, including tissue impedance, voltage, current and phase difference; Tissue type identification module: This module is used to input the collected multi-dimensional electrophysiological parameters into a pre-trained tissue type identification model, identify the currently contacted tissue type in real time, and determine its corresponding energy safety threshold. Intelligent energy calculation module: used to dynamically calculate the optimal energy output parameters based on the identified tissue type and surgical operation mode; Safety protection control module: used to monitor changes in the organization's state in real time. When the organization's state is detected to reach a preset critical value, it automatically adjusts the energy output or triggers the safety protection mechanism. The sampling frequency of the multi-dimensional electrophysiological parameters in the multi-parameter acquisition module is from 1 kHz to 10 kHz, including 1 kHz and 10 kHz. The tissue type identification module employs a hybrid deep learning model combining convolutional neural networks and long short-term memory networks, which can identify at least eight different human tissue types. The preset critical values ​​in the safety protection control module include the critical impedance value for tissue carbonization, the critical temperature value for tissue solidification, and the critical voltage value for arc discharge.

9. An intelligent energy control device for an electrosurgical energy platform, characterized in that, include: The present invention includes a memory, a processor, and an intelligent energy control program for an electrosurgical energy platform stored in the memory and executable on the processor, wherein the intelligent energy control program for the electrosurgical energy platform, when executed by the processor, implements an intelligent energy control method for an electrosurgical energy platform as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes an intelligent energy control program for an electrosurgical energy platform, which, when executed by a processor, implements an intelligent energy control method for an electrosurgical energy platform as described in any one of claims 1 to 7.

Images