Method and apparatus for detecting tissue denaturation point during sealing, and electrosurgical instrument

Abstract

The application discloses a method and device for detecting a denaturation point of tissue in a sealing process and an electrosurgical instrument. The method comprises the following steps: acquiring a real-time electrical signal fed back by tissue based on electrode input energy at a current moment; and determining whether the tissue reaches a denaturation point according to the real-time electrical signal and a historical period electrical signal. The set period before the current moment is regarded as the historical period, and the electrical signal fed back by the tissue based on the electrode input energy in the historical period is the historical period electrical signal. The detection result of the denaturation point of the tissue obtained in the scheme can reduce the detection result error caused by the signal value jump of the tissue due to accidental factors. Compared with the single-point comparison scheme in the prior art, the scheme has higher precision.

Description

Technical Field

[0001] This application relates to the field of electrosurgical instrument technology, and in particular to a method, device and electrosurgical instrument for detecting tissue degeneration points during the sealing process. Background Technology

[0002] The electrosurgical instrument comprises a handle assembly, a rotating head assembly, an elongated body assembly, and an end effector assembly connected sequentially from proximal to distal. The handle assembly is connected to a main unit capable of outputting high-frequency, high-voltage current. The elongated body assembly extends distally from the rotating head assembly, and the user can rotate the elongated body assembly and the end effector assembly together about the longitudinal axis of the elongated body assembly by manipulating the rotating head assembly. The end effector assembly is operatively mounted distal to the elongated body assembly for manipulating tissue to perform specific surgical procedures.

[0003] The end effector is designed as a clamping structure. This clamping structure includes two cooperating clamping arms, at least one of which has an electrode (depending on whether it is a monopolar or bipolar type). During operation, once the two clamping arms clamp and seal the tissue, the handle assembly controls the electrodes to be energized and emit a high-frequency alternating current signal. This signal passes through the tissue and heats it; this process is called preheating. During heating, the tissue's properties change, thus altering the electrical signal. The tissue transmits this signal value to the host unit, which determines whether a change in tissue properties has occurred (hereinafter referred to as the tissue denaturation point) based on the signal change. When the tissue reaches the denaturation point, hemostasis and sealing are achieved. The host unit then changes the output electrical signal, thereby altering the electrode's output energy to complete the tissue sealing. Based on the above description, accurately identifying whether the tissue has reached the denaturation point is crucial.

[0004] In some existing methods, a baseline curve is pre-defined to show the ideal impedance value of tissue during heating, changing over time. The node corresponding to the minimum impedance value on this baseline curve is taken as the tissue denaturation point. During actual tissue sealing, the real-time calculated impedance value is compared with the impedance value recorded on the baseline curve. If the calculated impedance value matches the defined minimum impedance point, the tissue is considered to have reached the denaturation point. However, for electrosurgical instruments, it is difficult to guarantee that the impedance value will change according to the pattern defined by the baseline curve during tissue sealing. Furthermore, the actual detected impedance value is prone to jumps. Determining whether the tissue has reached the denaturation point solely based on comparing the impedance value detected at a certain moment with the minimum impedance value after curing can easily lead to misjudgment. Therefore, the existing methods for determining the tissue denaturation point contain a certain degree of error. Summary of the Invention

[0005] The technical problem this application aims to solve is the poor accuracy of existing electrosurgical instruments in detecting whether tissue has reached the denaturation point during the tissue sealing process. To address this, this application proposes a method, device, and electrosurgical instrument for detecting tissue denaturation points during the sealing process.

[0006] To address the aforementioned technical problems, this application provides the following technical solution:

[0007] Firstly, the technical solution of this application provides a method for detecting tissue denaturation points during the sealing process, including:

[0008] Acquire the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment;

[0009] The determination of whether the tissue has reached the denaturation point is based on the real-time electrical signal and the historical period electrical signal; wherein, the set period before the current time is taken as the historical period, and the electrical signal obtained by the tissue based on the electrode input energy within the historical period is the historical period electrical signal.

[0010] Secondly, the technical solution of this application provides a device for detecting tissue denaturation points during the sealing process, comprising:

[0011] The sampling module is configured to acquire the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment;

[0012] The denaturation point determination module is configured to determine whether the tissue has reached the denaturation point based on the real-time electrical signal and the historical time period electrical signal; wherein, a set time period before the current time is taken as the historical time period, and the electrical signal fed back by the tissue based on the electrode input energy obtained within the historical time period is the historical time period electrical signal.

[0013] Thirdly, the present application provides a computer-readable storage medium storing program information, wherein a computer retrieves the program instructions and executes the tissue denaturation point detection method during the sealing process described in the first aspect.

[0014] Fourthly, the present application provides an electronic device, which includes at least one processor and at least one memory, wherein at least one memory stores program information, and at least one processor retrieves the program instructions and executes the tissue denaturation point detection method during the sealing process described in the first aspect.

[0015] Fifthly, the present application provides an electrosurgical instrument, wherein the main unit of the electrosurgical instrument is equipped with the tissue denaturation point detection device during the sealing process described in the second aspect, or the computer-readable storage medium described in the third aspect, or the electronic device described in the fourth aspect.

[0016] The technical solution of this application has the following technical advantages over the prior art:

[0017] This application provides a method, device, and electrosurgical instrument for detecting tissue denaturation points during the sealing process. During tissue sealing, the real-time electrical signal of the tissue, fed back by electrode input energy, is continuously monitored. Unlike existing methods that simply compare the real-time electrical signal (a single-point value) with a fixed value, this method combines historical electrical signals and performs a holistic logical judgment to determine whether the tissue has reached a denaturation point. Therefore, the tissue denaturation point detection results obtained in this solution reduce errors caused by accidental factors such as signal jumps. Compared to existing single-point comparison methods, this solution offers higher accuracy and more realistically reflects the actual characteristics or changing patterns of the tissue's electrical signals. Attached Figure Description

[0018] The preferred embodiments of this application will be described in detail below with reference to the accompanying drawings, which will help to understand the purpose and advantages of this application, wherein:

[0019] Figure 1 This is a schematic diagram of the electrosurgical device involved in this application.

[0020] Figure 2 This is a flowchart of a method for detecting tissue denaturation points during the sealing process according to one embodiment of this application;

[0021] Figure 3 This is a flowchart of a method for detecting tissue denaturation points during the sealing process according to another embodiment of this application;

[0022] Figure 4 This is a flowchart of a method for detecting tissue denaturation points during the sealing process, as described in yet another embodiment of this application.

[0023] Figure 5 This is a schematic diagram of the structure of a neuron in a multilayer perceptron according to one embodiment of this application;

[0024] Figure 6 This is a structural block diagram of a tissue denaturation point detection device during the sealing process according to one embodiment of this application;

[0025] Figure 7 This is a schematic diagram of the hardware connections of an electronic device used in the tissue denaturation point detection method during the sealing process, as described in one embodiment of this application. Detailed Implementation

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

[0027] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0028] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0029] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0030] This application generally relates to a scheme for detecting tissue degeneration points during tissue sealing using a medical device, and particularly to a method, device, and electrosurgical instrument for detecting tissue degeneration points during sealing. Figure 1 The electrosurgical instrument 100 shown can be used to cut, coagulate (cauterize and seal) tissue, and / or clamp tissue during surgical procedures. The electrosurgical instrument 100 can operatively transmit electrosurgical energy to an end effector 30 to act on tissue, achieving cutting, coagulation (cauterization and sealing) of tissue. The electrosurgical instrument 100 can also be used to clamp and manipulate tissue when no electrosurgical energy is supplied to the end effector 30. The clamping structure of the end effector 30 can selectively open or close, thereby allowing the end effector 30 to clamp tissue and apply electrosurgical energy to the tissue.

[0031] like Figure 1As shown, the electrosurgical instrument 100 provided in this application is typically connected to a host device that outputs electrosurgical energy. It is understood that the same electrosurgical instrument 100 can be used with various different host devices via an external cable 40. The electrosurgical instrument 100 includes a handle assembly 10, an elongated body assembly 20, and an end effector assembly 30 connected sequentially from proximal to distal. The proximal end of the handle assembly 10 is provided with a power supply connection for electrical connection to the host device. The power supply connection is shaped like a socket or plug and configured for easy connection to the output terminal or output connector of the host device. The power supply connection may also be configured as an electrical slip ring to provide a reliable electrical connection when the actuating component rotates. The end effector assembly 30 is used to manipulate tissue to perform specific surgical operations, such as clamping, coagulating, or cutting tissue.

[0032] Reference Figure 1 As shown, the end effector 30 includes a first clamping portion 31 and a second clamping portion 32 pivotally connected. The first clamping portion 31 and the second clamping portion 32 pivot towards each other to clamp tissue, and pivot away from each other to release tissue. Alternatively, in an alternative embodiment, the first clamping portion 31 of the end effector 30 can be operatively pivoted toward the second clamping portion 32 until the jaws of the end effector 30 are closed to clamp tissue; the first clamping portion 31 pivots away from the second clamping portion 32 until the jaws of the end effector 30 are opened to release tissue, and vice versa. Further, at least one of the first clamping portion 31 and the second clamping portion 32 is provided with an electrode in contact with tissue to transfer electrosurgical energy to the tissue, achieving a sealing operation.

[0033] like Figure 1 As shown, at least a portion of the handle assembly 10 is held by the user, facilitating operator control of the surgical instrument. The handle assembly 10 operably provides a driving force, such as a closing driving force and a cutting driving force, to the end effector 30. The handle assembly 10 includes a gripping body 11 that can be gripped by the user and a closing trigger 12 pivotally connected to the gripping body 11. The user operates the end effector 30 to perform closing or opening actions by operating the closing trigger 12. The gripping body 11 is generally T-shaped, with an internal cavity for accommodating the drive mechanism and actuation circuitry, etc.

[0034] The elongated body assembly 20 includes a plurality of longitudinal members that operatively connect the end actuation assembly 30 to a plurality of actuators housed in the handle assembly 10. The elongated body assembly 20 includes an outer sleeve that defines the outer surface of the elongated body and accommodates other components moving through it. For example, the outer sleeve is shaped to move longitudinally relative to an inner actuating member axially received within the outer sleeve. The inner actuating member can be a rod, shaft, stamped metal, or other suitable metal component.

[0035] Reference Figure 1 As shown, the closed trigger 12 is operably fitted onto the proximal portion of the elongated body assembly 20. The handle assembly 10 also includes a cutting trigger 13 pivotally connected to the grip body 11. The user operates the cutting trigger 13 to operate the blade actuation member within the end effector assembly 30 to perform a cutting action. A cable for delivering electrosurgical energy is also disposed within the outer sleeve of the elongated body assembly 20. The distal end of the cable is connected to the first clamping portion 31 and / or the second clamping portion 32 of the end effector assembly 30, respectively, to transmit high-frequency electrosurgical energy to the electrodes on the first clamping portion 31 and / or the second clamping portion 32.

[0036] A knob 50 is also provided at the distal end of the handle assembly 10. The user can rotate the knob 50 to allow the elongated body assembly 20 and the end effector assembly 30 to rotate as a whole around the longitudinal axis. The closing trigger 12 extends from the side away from the elongated body assembly 20 to the main body of the grip body 11. The grip portion of the grip body 11 has an opening 110 on the side opposite to the closing trigger 12. The closing trigger 12 can slide along the opening 110 to partially slide into or partially out of the receiving cavity. As the area of ​​the closing trigger 12 entering the receiving cavity increases, the angle between the first clamping portion 31 and / or the second clamping portion 32 of the end effector assembly 30 gradually decreases until the closing trigger 12 pivots to the closed position, at which point the end effector assembly 30 is in a closed state. As the closed trigger 12 is further operated to pivot towards the gripping body 11, the area where the closed trigger 12 enters the receiving cavity further increases. When the closed trigger 12 pivots to the activated position, the activation circuit is turned on, and electrosurgical energy is provided to the end effector 30. When the closed trigger 12 is operated to pivot from the closed position to the activated position, the operator can distinguish between the closed operation and the activated operation based on the different grip feel.

[0037] After the activation operation is completed, when the closing trigger 12 is pivoted away from the gripping body 11, the area of ​​the closing trigger 12 entering the receiving cavity gradually decreases, the angle between the first clamping portion 31 and / or the second clamping portion 32 of the end effector 30 gradually increases, and the end effector 30 gradually opens until the closing trigger 12 is pivoted to the open position, at which point the end effector 30 is in its maximum open state. In some embodiments, when the closing trigger 12 is pivoted to the open position, at least a portion of the closing trigger 12 is located within the receiving cavity. It is understood that the user can also choose to switch between closing and opening operations to achieve clamping and opening of the target tissue without performing the activation circuit process.

[0038] Based on the above description, when the closed trigger 12 pivots to the excitation position, the excitation circuit is switched to the on state. The electrosurgical energy output by the host is output via the power supply connection to the end-effector 30 (i.e., the electrosurgical energy is transmitted to the electrodes of the first clamping part 31 and / or the second clamping part 32) to apply electrosurgical energy to the tissue on the end-effector 30 to achieve tissue sealing. During the tissue sealing process, the temperature of the tissue increases due to the injection of electrosurgical energy, thereby affecting the impedance value of the tissue. The current value flowing through the tissue and the electrode voltage acting on the tissue will change, and therefore the current value or voltage value reflected in the end-effector 30 will change accordingly. This change can be fed back to the host via the external cable 40, allowing the host to detect the temperature of the tissue or whether the tissue has reached the denaturation point. Generally, when the tissue reaches the denaturation point, it can be considered that the tissue has completed the preheating process or that the tissue fluid has reached the boiling point. At this time, the tissue heating operation can be ended, and the host can change the output electrosurgical energy to continue to complete the subsequent tissue sealing process. Based on the above process, determining whether the tissue has reached its denaturation point is crucial. If the heating operation ends too early and subsequent processes begin, the sealing effect may be affected because the tissue's properties do not meet the sealing requirements. Conversely, continuing heating after the tissue has reached its denaturation point may result in severe tissue damage under high temperatures, or even prevent complete sealing. The tissue denaturation point detection method provided in this application can be applied to the main unit of the aforementioned electrosurgical instrument to accurately determine whether the tissue has reached its denaturation point.

[0039] This application provides a method for detecting tissue degeneration points during the sealing process, such as... Figure 2 As shown, the method includes the following steps:

[0040] S10: Obtain the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment.

[0041] Combination Figure 1The electrosurgical instrument shown, when used to perform tissue sealing, clamps the tissue with the first clamping part 31 and the second clamping part 32 of the end-effector 30. The electrodes on the first clamping part 31 and / or the second clamping part 32 are in direct contact with the tissue, and the electrodes inject the electrosurgical energy output from the host into the tissue to heat it. When the temperature of the tissue changes, its impedance value also changes, that is, the impedance value between the first clamping part 31 and the second clamping part 32 changes, so the current or voltage of the electrodes on the first clamping part 31 and / or the second clamping part 32 will change. The electrodes feed back the real-time changing current or voltage to the host through an external cable 40. In this step, the host uses the value of the current or voltage transmitted by the external cable 40 as the real-time electrical signal. Alternatively, the host uses an analog-to-digital converter to convert the analog current or voltage into a digital signal as the real-time electrical signal. It is understood that in subsequent solutions of this application, the form of the electrical signal can be set or selected manually, as long as the electrical signals used throughout the detection process have the same form (e.g., all analog signals or all digital signals).

[0042] S20: Determine whether the tissue has reached the denaturation point based on the real-time electrical signal and the historical period electrical signal; wherein, the set period before the current time is taken as the historical period, and the electrical signal fed back by the tissue based on the electrode input energy obtained within the historical period is the historical period electrical signal.

[0043] The selection of the set time period can be determined by comprehensively considering the host's signal processing efficiency and detection cycle. The higher the host's signal processing efficiency, the larger the amount of data the host can process. In practical applications, the amount of data that can be processed within the detection cycle can be taken as the amount of data to be processed within the detection cycle. The amount of data to be processed within the detection cycle includes real-time electrical signals and historical period electrical signals. This allows us to determine the signal quantity of historical period electrical signals, and thus determine the length of the set time period.

[0044] The host computer can pre-store judgment logic methods. This pre-defined judgment logic can be a pre-completed application program, which can be called and executed after being placed in the host computer. The pre-defined judgment logic can use historical time period electrical signals and real-time electrical signals to determine whether the tissue has reached the denaturation point.

[0045] In this scheme, the determination of whether tissue has reached the denaturation point is based on a combination of real-time electrical signals and historical time-period electrical signals using preset judgment logic. This differs from existing methods that simply compare the real-time electrical signal (a single point value) with a fixed value. Instead, this scheme combines historical time-period electrical signals and uses preset judgment logic to perform a comprehensive logical judgment on both the real-time and historical signals before obtaining the result. Therefore, the tissue denaturation point detection results obtained in this scheme reduce the detection error caused by accidental factors such as abrupt changes in tissue signal values ​​and better highlight the characteristics of the tissue electrical signals. Compared to existing single-point comparison schemes, this scheme has higher accuracy.

[0046] like Figure 3 As shown, the preset judgment logic in some solutions includes:

[0047] S21: Obtain the real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical time period electrical signal.

[0048] In this step, the real-time feature value is obtained by combining the real-time electrical signal at the current moment with the electrical signal at a historical time period. The purpose is to use the electrical signal at a historical time period to smooth, sharpen, edge-mudge, and Gaussian blur the real-time electrical signal at the current moment, so as to avoid the impact on the detection accuracy when there are jumps in the real-time electrical signal. Therefore, this scheme can better highlight the characteristics of the tissue electrical signal.

[0049] S22: Obtain a baseline feature value based on the real-time feature value and the historical feature value. The historical feature value is determined based on the electrical signal deviation corresponding to the tissue reaching the denaturation point during the historical sealing process.

[0050] Specifically, the historical sealing process can be the tissue sealing process performed by this host computer during animal experiments or historical clinical trials. The host computer can record data from each sealing process to form a historical data set. In this solution, data with the same attributes as the real-time feature value can be directly retrieved from the historical data set. The historical feature value can be regarded as data for deviation adjustment of the baseline feature value. That is, when the baseline feature value initially set by the host computer is inaccurate during the historical sealing process, it will be adjusted by the operator. The amount of each adjustment is the "electrical signal deviation". If it needs to be increased, it can be indicated by "+"; if it needs to be decreased, it can be indicated by "-".

[0051] S23: Determine whether the real-time electrical signal is greater than or equal to the reference characteristic value. If yes, proceed to step S24; otherwise, return to step S10.

[0052] In this scheme, the magnitude relationship between the real-time electrical signal and the reference characteristic value calculated in step S22 can be determined directly.

[0053] S24: Determine that the tissue has reached the denaturation point.

[0054] In this scheme, the baseline feature value is determined based on historical feature values ​​and combined with real-time feature values. This allows the baseline feature value to not only possess the regularity verified by history, but also to be adjusted based on the actual feedback of electrical signal detection results from the tissue during the current sealing process. This ensures that the baseline feature value meets the changing requirements of the actual scenario in the current sealing process and ensures the accuracy of the detection results when the tissue reaches the denaturation point.

[0055] If the real-time characteristic value is less than the reference characteristic value, the process returns to step S10, which involves obtaining the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment. That is, if the tissue has not reached the denaturation point, the host continues to perform the preheating operation on the tissue while cyclically detecting whether the tissue has reached the denaturation point until the real-time characteristic value is greater than or equal to the reference characteristic value, thus satisfying the judgment condition that the tissue has reached the denaturation point.

[0056] In step S21 above, the real-time electrical signal and the historical period electrical signal can be processed in various ways to obtain the real-time feature value corresponding to the real-time electrical signal. In this application embodiment, three implementation schemes are provided. In the three schemes, the real-time electrical signal and the historical period electrical signal are illustrated using the impedance value of tissue feedback as an example. It can be understood that in actual applications, it is not necessary to be limited to the following three specific schemes provided in this embodiment.

[0057] Option 1: Obtain the average electrical signal of the real-time electrical signal and the historical period electrical signal at each moment; use the minimum average electrical signal as the real-time feature value at the current moment.

[0058] In this scheme, the electrical signal is the impedance value fed back by the organization. The average electrical signal refers to the average value of the impedance value Z over a continuous time period. This continuous time period includes both real-time impedance values ​​and historical impedance values. Specifically, taking the current moment as the moment corresponding to the Tth sampling period as an example, the host acquires the impedance values ​​detected over a total of T consecutive sampling periods, including the impedance value at the current moment and impedance values ​​from (T-1) historical periods. The process of obtaining the real-time feature value in this scheme is as follows:

[0059] Initially, the host first stores a very large average value M of minimum impedance. min In the process of real-time electrical signal detection, a new average impedance value M is calculated for each real-time impedance value obtained. t If M t <M min Then, using the new impedance value average value M tAs the new minimum impedance value, the average value, i.e., M min M t Refresh. The frequency of the real-time electrical signal detected by the tissue feedback can be preset, so the sampling period is a known quantity.

[0060] During the sealing process, the host can calculate a new average impedance value M in each sampling period. t Whenever a smaller average impedance value appears, it is used to refresh the previously obtained average impedance value and taken as the real-time feature value corresponding to the current sampling period. Therefore, the smallest average value is always used as the real-time feature value, and its formula is expressed as:

[0061] M t =mean(Z) t Z t-T ).

[0062] Among them, Z t This represents the impedance value corresponding to the t-th sampling period.

[0063] The method of calculating the average impedance value can not only filter out unstable impedance detection results and reduce noise in the signal detection process, but also ensures that the host's memory only needs to store a minimum average impedance value M. min The solution requires only T consecutive impedance values, so the host computer only needs to perform a very small amount of calculation and provide very little storage space.

[0064] Option 2: Obtain the weighted sum of the real-time electrical signal and the historical period electrical signal at each moment according to the preset weight value; take the minimum weighted sum as the real-time feature value at the current moment.

[0065] In this scheme, the real-time characteristic value is obtained by calculating the weighted sum of the impedance values ​​Z detected over T consecutive sampling periods. The process of obtaining the real-time characteristic value in this scheme is as follows:

[0066] Each impedance value Z detected within T sampling periods is multiplied by its pre-set weight value, and the sum of the results of multiplying each impedance value by its weight value yields a weighted sum B. t This scheme processes the real-time impedance values ​​using methods such as weight smoothing, sharpening, edge detection, and Gaussian blurring to obtain new real-time characteristic values. Taking T consecutive impedance values ​​as an example, there are also T preset weight values. When T = 3, the mathematical expression for the weighted sum is:

[0067] B t =W -1 Z t-1 +W0Z t +W1Z t-1 ;

[0068] Where W is the preset weight value, and impedance values ​​with the same subscript correspond to the weight values, which are multiplied during calculation. The preset weight value can be determined by the electrical signal at the initial stage of different automatic organization types, or it can be manually preset by the operator according to needs. The preset weight value is determined based on the kernel type selected by the operator. For example, applying a sharpening kernel weight factor can increase the difference between impedance values. Applying an average kernel weight factor will average T consecutive impedance values. Here, if all the average kernel weight factors are... The result will then be the same as the calculation result of Scheme 1. In the above process, the result obtained by multiplying the detected impedance value and the preset weight value and then adding them is stored in the host. The real-time feature value can be selected by weighting value B. t The minimum value.

[0069] It is understandable that the real-time feature value obtained will change after the preset weight value in the above scheme is changed, and the corresponding benchmark feature value will also change. Therefore, multiple methods for obtaining benchmark feature values ​​can be achieved by adjusting the preset weight value to meet the needs of different scenarios.

[0070] Option 3: Obtain the predicted value of the electrical signal at the current moment based on the electrical signal variation pattern of the historical period; if the difference between the real-time electrical signal and the predicted value is less than a difference threshold, then the real-time electrical signal is used as the real-time feature value; otherwise, the predicted value is used as the real-time feature value. The smaller the difference threshold, the more accurate the corresponding real-time feature value. In the following embodiments, the difference threshold is directly set to zero, meaning that ideally, the real-time electrical signal should equal the predicted value.

[0071] Taking the historical period electrical signal as an example, which refers to the impedance value obtained within a set period, there is more than one impedance value. Based on these multiple impedance values, the impedance value change pattern can be deduced, thus enabling the prediction of the impedance value corresponding to the next sampling period. Specifically, the first derivative of the impedance values ​​obtained in T consecutive sampling periods is used to obtain the predicted impedance value: among the T impedance values, according to the order of their acquisition time, the impedance value Z of the next sampling period is used... t Subtract the impedance value Z from the previous sampling period t-1 The signal differences between them are then obtained, so T impedance values ​​can yield (T-1) signal differences; the average of these (T-1) signal differences is obtained by summing them and dividing by (T-1), and this average is used as the historical signal average; the historical signal average is then added to the most recently obtained impedance value Z. t The predicted impedance value A can be obtained from the above. t That is, the impedance value Z t+1 Its formula can be expressed as:

[0072]

[0073] This scheme primarily predicts the current impedance value by analyzing historical impedance values ​​and their trends. It smooths out impedance fluctuations over T sampling periods and more effectively utilizes historical impedance trends to predict the current impedance value. This scheme is particularly suitable for scenarios where impedance values ​​are continuously decreasing or increasing. During the tissue preheating phase of the sealing process, the tissue impedance value exhibits a stable trend. For example, five consecutively detected impedance values ​​might be: [6, 5.5, 4, 3, 2]. In this sequence, 5.5 is a fluctuating value, and 2 is the most recently acquired impedance value. Using first-order differentiation, the next impedance value can be directly predicted as: 2 - (1 + 1 + 1.5 + 0.5) / 4 = 1. However, if the actual detected next impedance value is 1.5, the difference between the actual and predicted impedance values ​​is too large. In this case, the predicted value of 1 is used to replace the actual impedance value as the sixth impedance value.

[0074] Using the above method, the host only needs to store a minimum historical signal average value A. min The impedance values ​​detected over T consecutive sampling periods are sufficient. Similar to Scheme 1, at the initial moment, the minimum historical signal average value A... min It is set to a very large value, so that a new historical signal average value A can be obtained for each new impedance value detected during subsequent detection. t If A t <A min Then A min Will be A t refresh.

[0075] The above scheme predicts the next electrical signal by utilizing the changing patterns of electrical signals over historical periods. In practical applications, the impedance value may not be continuously decreasing or increasing. In such cases, the predicted electrical signal value can be obtained through the following modification: An electrical signal curve is obtained by fitting the acquired electrical signals from the historical period, with time as the x-axis and the electrical signal value as the y-axis. The y-axis corresponding to the current moment on the electrical signal curve is then used as the predicted electrical signal value. In practical applications, after obtaining the impedance values ​​for T consecutive sampling periods, the existing curve fitting method can be used to obtain the impedance value change curve. The x-axis of the change curve is selected as time, and the y-axis is selected as the electrical signal value. Using the change curve, the impedance value at any future time point can be predicted. This scheme can accurately predict the impedance value even in scenarios where the impedance value does not follow a continuously decreasing or increasing pattern.

[0076] In the above scheme, the reference feature value can be obtained based on the real-time feature value and the historical feature value. Preferably, the reference feature value is determined as follows: Reference feature value = Real-time feature value + Historical feature value. In this scheme, the historical feature value is obtained based on the deviation of the electrical signal when the tissue reaches the denaturation point during the historical sealing process. As mentioned above, the deviation can be positive or negative, so the historical feature value may be negative, and the reference feature value may be larger than the real-time feature value or smaller than the implemented feature value.

[0077] The above-mentioned scheme provided in this application takes into account both the deviation of the baseline characteristic value in the historical sealing process and the real-time characteristic value obtained in the current sealing process, and truly obtains a judgment benchmark that conforms to the current sealing process, thereby making the judgment on whether the tissue has reached the denaturation point more accurate.

[0078] In some embodiments, such as Figure 4 As shown, the above method includes the following steps before step S10:

[0079] S00: Acquire the tissue electrical signal during the initial stage of the historical sealing process and the tissue electrical signal range corresponding to the denaturation point; the tissue electrical signal is the electrical signal fed back by the tissue based on the electrode input energy during the initial stage.

[0080] In this step, the model is trained using data from the initial phase of historical closure procedures based on clinical experience. The initial phase refers to a relatively short period after the closure begins. Multiple tissue electrical signals are collected within this phase to capture a series of changing electrical signals. The duration of the initial phase can be determined through calibration experiments.

[0081] When tissue reaches a denaturation point, it corresponds to a value of the tissue's electrical signal. To ensure the accuracy of the denaturation point detection results and avoid misjudgments caused by occasional jumps, this scheme can obtain a tissue electrical signal range by adding or reducing a certain error range based on the value. For example, if the allowable error is 0.1%, and the tissue electrical signal corresponding to the denaturation point is R, then the tissue electrical signal range can be [0.99×R, 1.01×R]. It can be understood that the electrical signal can be selected as voltage, current, impedance, energy, etc.

[0082] S01: The learning algorithm is trained using the tissue electrical signal of the initial stage in the historical sealing process as the input sample and the tissue electrical signal interval as the output sample. The trained learning algorithm is used as the tissue degeneration point prediction model.

[0083] In this solution, existing learning algorithms, such as deep learning algorithms, can be selected. Different input and output samples will result in different judgment benchmark feature values ​​obtained during training. This application embodiment can provide training methods with different input and output samples as follows: input samples are voltage and current values, or voltage, current, and tissue size values; output samples are a voltage range and a current range, or a two-dimensional matrix obtained from a voltage sequence and a current sequence, or a tissue impedance range, or a tissue impedance sequence. Accordingly, the tissue electrical signal, the real-time electrical signal, and the historical time period electrical signal are: continuous, corresponding voltage and current values ​​fed back by the tissue based on the electrode input energy within a set time period; or, continuous, corresponding voltage, current, and tissue size values ​​fed back by the tissue based on the electrode input energy within a set time period; the tissue electrical signal interval is: the voltage and current value interval corresponding to when the tissue reaches the denaturation point; or, a two-dimensional matrix obtained based on the voltage and current value sequences corresponding to when the tissue reaches the denaturation point; or, the tissue impedance value interval corresponding to when the tissue reaches the denaturation point, or the tissue impedance sequence corresponding to when the tissue reaches the denaturation point. In practical applications, it is necessary to ensure that the input samples and output samples selected during training are consistent with the input signals and output results selected during actual detection.

[0084] Step S20 includes:

[0085] S2A: The current time is defined as the end time of the initial stage in the current sealing process, and the initial stage in the current sealing process is defined as the set time period. The real-time electrical signal and the historical time period electrical signal are input signals to the tissue degeneration point prediction model, and the output of the tissue degeneration point prediction model is used as the predicted electrical signal interval of the tissue degeneration point.

[0086] The initial stage in this step is the same as the initial stage in step S00. After the electrosurgical instrument applies a portion of the initial electrosurgical energy to the tissue, real-time measured tissue electrical signals will be obtained for T consecutive sampling cycles in the initial stage. These T consecutive sampling cycles of real-time measured tissue electrical signals are then input into the tissue degeneration point prediction model trained in step S01. The tissue degeneration point prediction model has been trained with experiments related to tissue degeneration points and outputs the possible tissue electrical signal range when the tissue reaches the degeneration point. Therefore, the output of the tissue degeneration point prediction model should be the predicted electrical signal range corresponding to the current T tissue electrical signals.

[0087] S2B: Determine the real-time electrical signal interval corresponding to the tissue denaturation point during the current sealing process based on the predicted electrical signal interval. The method for determining the real-time electrical signal interval using the predicted electrical signal interval varies depending on the type of tissue electrical signal.

[0088] Specifically, if the tissue electrical signal interval is the voltage and current value interval corresponding to the tissue reaching the denaturation point, then the voltage or current value interval is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is a two-dimensional matrix obtained based on the voltage and current value sequences corresponding to the tissue reaching the denaturation point, then the average voltage value interval obtained by combining the average voltage value obtained from the voltage value sequence with the error range, or the average current value interval obtained by combining the average current value obtained from the current value sequence with the error range, is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is the tissue impedance value interval corresponding to the tissue reaching the denaturation point, then the tissue impedance value interval is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is the tissue impedance sequence corresponding to the tissue reaching the denaturation point, then the average impedance value interval obtained by combining the average impedance value obtained from the tissue impedance sequence with the error range is taken as the real-time electrical signal interval segment.

[0089] The tissue size value described above is a parameter used to represent the size of the tissue, determined by the acquired voltage and current. In practical scenarios, since the host computer can detect changes in electrical signals such as current and voltage due to changes in tissue properties, the tissue size can be obtained using conventional derivation algorithms. Impedance values ​​and other parameters are also discussed. The sequence described above is a finite-length series of values, containing multiple values. The average value can be used to calculate the actual electrical signal value to be obtained. For example, an impedance value sequence is a finite-length series of impedance values. By using the average value of all impedance values ​​in the sequence as the corresponding actual impedance value, and using a predefined error range, the impedance value range can be obtained, thus yielding the real-time electrical signal range.

[0090] S2C: Determine whether the real-time electrical signal is located within the real-time electrical signal interval. If yes, proceed to step S2D; otherwise, return to step S10.

[0091] In subsequent testing, it is only necessary to determine whether the real-time electrical signal falls within the real-time electrical signal interval to determine whether the tissue has reached the denaturation point.

[0092] S2D: Determines when the tissue has reached the denaturation point.

[0093] This scheme enables the prediction of real-time electrical signal intervals during the initial stage of the sealing process. Subsequent real-time monitoring of the tissue's feedback electrical signals allows for the determination of a denaturation point if the real-time electrical signal falls within the aforementioned interval. By employing a training-based learning algorithm, the data detection and computation process, along with the real-time tracking of electrical signals, is simplified, resulting in faster denaturation point identification. Earlier identification of tissue denaturation facilitates better coordination with the control electrode system, reducing the likelihood of losing track of and controlling tissue properties. Furthermore, the training-based model approach yields more accurate results in determining denaturation points.

[0094] In some schemes, the learning algorithm is a multilayer perceptron algorithm, in which the function of the i-th layer perceptron is represented as: y i =f(w i-1 x i-1 +b).

[0095] Where, if i > 1, then x i-1 Let x be the output of the (i-1)th layer perceptron. If i = 1, then x i-1 To acquire tissue electrical signals; w i-1 is a weight matrix composed of preset weight factors in the perceptron, b is a preset bias in the perceptron, and f() is a preset nonlinear function.

[0096] like Figure 5 The diagram shows a neuron in a perceptron. Each layer of the perceptron contains a finite number of parallel neurons, each with its own learnable weights and biases, all using the same input. The outputs of these neurons form the inputs of the neurons in the next layer. To reduce hardware overhead, the number of neurons in each layer varies, with the neurons in the last layer outputting electrical signals.

[0097] This scheme employs a multilayer perceptron algorithm. When using sample data for training, the sample data can be selected as needed. Obviously, different input and output samples will result in different weight values ​​and biases after training. As mentioned earlier, the input data selected during actual detection should be consistent with the input samples used during training.

[0098] In addition, in the above scheme, the input samples can be pre-sorted according to their importance, or for example, the weights of input samples with high importance can be increased. This is equivalent to pre-configuring the weight values ​​of each input sample before it enters the learning algorithm, so that input samples with higher weight values ​​have a greater impact on the output results.

[0099] In the embodiments described above, the incorporation of a learning and training approach enhances the accuracy of tissue degeneration point assessment, further highlighting the characteristics of tissue electrical signals. Furthermore, this solution only requires inputting the electrical signal from the initial stage of the sealing process into the tissue degeneration point prediction model. This allows for direct determination of the real-time electrical signal range during tissue degeneration, leading to a rapid conclusion regarding the tissue degeneration status. Earlier assessment of tissue degeneration and more accurate coordination with the electrode control unit prevents loss of tracking and control over the tissue.

[0100] This application provides a device for detecting tissue degeneration points during the sealing process, such as... Figure 6 As shown, the system includes: a sampling module 610, configured to acquire the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment; and a denaturation point determination module 620, configured to determine whether the tissue has reached a denaturation point based on the real-time electrical signal and historical time period electrical signals; wherein, a set time period prior to the current moment is taken as the historical time period, and the electrical signal fed back by the tissue based on the electrode input energy acquired within the historical time period is the historical time period electrical signal. The selection of the set time period can be determined based on a comprehensive consideration of the host's signal processing efficiency and detection cycle. In this solution, the determination of whether the tissue has reached a denaturation point is based on a combination of the real-time electrical signal and the historical time period electrical signal with preset judgment logic. This differs from the existing method of simply comparing the real-time electrical signal (a single-point value) with a certain "fixed value." Instead, it combines the historical time period electrical signal and uses preset judgment logic to perform a holistic logical judgment on both the real-time and historical time period electrical signals before obtaining the judgment result. Therefore, the tissue denaturation point detection result obtained in this solution can reduce the detection result error caused by accidental factors such as jumps in the tissue signal value, and this solution has higher accuracy.

[0101] In some solutions, the denaturation point determination module 620 is further used to obtain a real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical period electrical signal; and to obtain a reference feature value based on the real-time feature value and the historical feature value. The historical feature value is determined based on the electrical signal deviation corresponding to when the tissue reaches the denaturation point during the historical sealing process; it is determined whether the real-time electrical signal is greater than or equal to the reference feature value, and if so, it is determined that the tissue has reached the denaturation point. In this solution, the real-time feature value is obtained by combining the real-time electrical signal at the current moment and the historical period electrical signal. The purpose is to use the historical period electrical signal to smooth, sharpen, edge-divide, and Gaussian blur the real-time electrical signal at the current moment, so as to avoid the impact on the detection accuracy when the real-time electrical signal jumps. Therefore, this solution can better highlight the characteristics of the tissue electrical signal. The historical sealing process can be the tissue sealing process involved in animal experiments or historical clinical trials performed by this host. The historical feature value can be regarded as data for deviation adjustment of the reference feature value. In this scheme, the baseline feature value is determined based on historical feature values ​​and combined with real-time feature values. This allows the baseline feature value to not only possess the regularity verified by history, but also to be adjusted based on the actual feedback of electrical signal detection results from the tissue during the current sealing process. This ensures that the baseline feature value meets the changing requirements of the actual scenario in the current sealing process and ensures the accuracy of the detection results when the tissue reaches the denaturation point.

[0102] In the above scheme, the denaturation point determination module 620 is further configured to return to the sampling module 610 when the real-time feature value is less than the reference feature value. That is, if the tissue has not reached the denaturation point, the host continues to perform the preheating operation on the tissue, while cyclically detecting whether the tissue has reached the denaturation point until the real-time feature value is greater than or equal to the reference feature value, which satisfies the determination condition that the tissue has reached the denaturation point.

[0103] Furthermore, the mutation point determination module 620 is used to process the real-time electrical signal and the historical period electrical signal in various ways to obtain the real-time feature value corresponding to the real-time electrical signal. This application embodiment provides three implementation schemes. In all three schemes, the real-time electrical signal and the historical period electrical signal are illustrated using the impedance value of tissue feedback as an example. Specifically:

[0104] The variable point determination module 620 is used to acquire the average electrical signal of the real-time electrical signal and the historical period electrical signal at each moment; and to use the minimum average electrical signal as the real-time feature value at the current moment. In this scheme, the method of calculating the average impedance value can not only filter out unstable impedance value detection results and reduce noise in the signal detection process, but also, since the host's memory only needs to store a minimum average impedance value M, minThe solution requires only T consecutive impedance values, so the host computer only needs to perform a very small amount of calculation and provide very little storage space.

[0105] Alternatively, the variable point determination module 620 is used to obtain the weighted sum of the real-time electrical signal and the historical period electrical signal at each moment according to a preset weight value; and to take the minimum weighted sum as the real-time feature value at the current moment. In this scheme, the real-time feature value is obtained by calculating the weighted sum of the impedance values ​​Z detected within T consecutive sampling periods. In this scheme, multiple methods for obtaining reference feature values ​​can be achieved by adjusting the preset weight value to meet the needs of different scenarios.

[0106] Alternatively, the variable point determination module 620 is used to obtain the predicted value of the electrical signal at the current moment based on the electrical signal variation pattern of the historical period; if the difference between the real-time electrical signal and the predicted electrical signal is less than a difference threshold, then the real-time electrical signal is used as the real-time feature value; otherwise, the predicted electrical signal is used as the real-time feature value. This scheme smooths the fluctuation of the impedance value over T sampling periods and more effectively uses the historical impedance value variation trend to predict the impedance value at the current moment. This scheme is particularly suitable for scenarios where the impedance value is continuously decreasing or continuously increasing.

[0107] In some solutions, the variable point determination module 620 is used to fit an electrical signal curve based on the acquired electrical signals from the historical time period. The electrical signal curve has time as the horizontal axis and electrical signal value as the vertical axis. The vertical axis corresponding to the current time point on the electrical signal curve is used as the predicted electrical signal value. This solution can predict the impedance value at any future time point using the change curve, and can accurately predict the impedance value even in scenarios where the impedance value does not continuously decrease or continuously increase.

[0108] In some solutions, the benchmark feature value in the denaturation point determination module 620 is determined as follows: benchmark feature value = real-time feature value + historical feature value. The solution provided in this application considers both the benchmark feature value deviation during the historical sealing process and the real-time feature value obtained during the current sealing process, thus obtaining a judgment benchmark that truly conforms to the current sealing process. This results in higher accuracy in determining whether the tissue has reached the denaturation point.

[0109] In some embodiments, the device further includes:

[0110] The sample acquisition module is configured to acquire the tissue electrical signals during the initial stage of a historical sealing process and the corresponding tissue electrical signal interval when the tissue reaches the denaturation point. The tissue electrical signals are the electrical signals fed back by the tissue based on electrode input energy during the initial stage. The model is trained using data from the initial stage of a historical sealing process based on clinical experience. The initial stage refers to a relatively short period after the sealing begins. Multiple tissue electrical signals are collected within a selected stage. The point at which the tissue reaches the denaturation point corresponds to a single point value of the tissue electrical signal. To ensure the accuracy of the denaturation point detection results and avoid misjudgments caused by occasional jumps, this scheme can increase or decrease the error range based on the point value to obtain the tissue electrical signal interval.

[0111] The model training module uses the tissue electrical signals from the initial stage of the historical sealing process as input samples and the tissue electrical signal intervals as output samples to train the learning algorithm. The trained learning algorithm serves as the tissue degeneration point prediction model. Existing learning algorithms, such as deep learning algorithms, can be selected. Different input and output samples will result in different judgment benchmark feature values ​​obtained during training. Embodiments of this application can provide training methods with different input and output samples: input samples are voltage and current values, or voltage, current, and tissue size values; output samples are voltage and current value intervals, or a two-dimensional matrix obtained from voltage and current value sequences, or tissue impedance value intervals, or tissue impedance sequences. Accordingly, the tissue electrical signal, the real-time electrical signal, and the historical time period electrical signal are: continuous, corresponding voltage and current values ​​fed back by the tissue based on the electrode input energy within a set time period; or, continuous, corresponding voltage, current, and tissue size values ​​fed back by the tissue based on the electrode input energy within a set time period; the tissue electrical signal interval is: the voltage and current value interval corresponding to when the tissue reaches the denaturation point; or, a two-dimensional matrix obtained based on the voltage and current value sequences corresponding to when the tissue reaches the denaturation point; or, the tissue impedance value interval corresponding to when the tissue reaches the denaturation point, or the tissue impedance sequence corresponding to when the tissue reaches the denaturation point. In practical applications, it is necessary to ensure that the input samples and output samples selected during training are consistent with the input signals and output results selected during actual detection.

[0112] The denaturation point determination module 620 is further configured to use the end time of the initial stage in the current sealing process as the current time, and the initial stage in the current sealing process as the set time period. The real-time electrical signal and the historical time period electrical signal are input signals to the tissue denaturation point prediction model, and the output of the tissue denaturation point prediction model is used as the predicted electrical signal interval for the tissue denaturation point. Based on the predicted electrical signal interval, the real-time electrical signal interval corresponding to the tissue denaturation point in the current sealing process is determined. It is then determined whether the real-time electrical signal is located within the real-time electrical signal interval; if so, the tissue has reached the denaturation point. In the above scheme, if the tissue electrical signal interval is the voltage and current value interval corresponding to the tissue reaching the denaturation point, then the voltage or current value interval is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is a two-dimensional matrix obtained based on the voltage and current value sequences corresponding to the tissue reaching the denaturation point, then the average voltage value interval obtained by combining the average voltage value obtained from the voltage value sequence with the error range, or the average current value interval obtained by combining the average current value obtained from the current value sequence with the error range, is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is the tissue impedance value interval corresponding to the tissue reaching the denaturation point, then the tissue impedance value interval is taken as the real-time electrical signal interval segment; if the tissue electrical signal interval is the tissue impedance sequence corresponding to the tissue reaching the denaturation point, then the average impedance value interval obtained by combining the average impedance value obtained from the tissue impedance sequence with the error range is taken as the real-time electrical signal interval segment.

[0113] This scheme enables the prediction of real-time electrical signal intervals during the initial stage of the sealing process. Subsequent real-time monitoring of the tissue's feedback electrical signals allows for the determination of a denaturation point if the real-time electrical signal falls within the aforementioned interval. By employing a training-based learning algorithm, the data detection and computation process, along with the real-time tracking of electrical signals, is simplified, resulting in faster denaturation point identification. Earlier identification of tissue denaturation facilitates better coordination with the control electrode system, reducing the likelihood of losing track of and controlling tissue properties. Furthermore, the training-based model approach yields more accurate results in determining denaturation points.

[0114] In some schemes, the learning algorithm in the model training module is a multilayer perceptron algorithm, where the function of the i-th layer perceptron is represented as: y i =f(w i-1 x i-1 +b). Where, if i > 1, then x i-1 Let x be the output of the (i-1)th layer perceptron. If i = 1, then x i-1 To acquire tissue electrical signals; wi-1 Let b be the weight matrix composed of preset weight factors in the perceptron, b be the preset bias in the perceptron, and f() be the preset nonlinear function. This scheme employs a multilayer perceptron algorithm. When using sample data for training, the sample data can be selected as needed. Different input and output samples will result in different weight values ​​and biases after training. As mentioned earlier, the input data selected during actual detection should be consistent with the input samples used during training. Due to the combination of learning and training methods, the judgment results of tissue degeneration points can achieve higher accuracy and better highlight the characteristics of tissue electrical signals. Furthermore, this scheme only needs to input the electrical signal of the initial stage of the sealing process into the tissue degeneration point prediction model to directly determine the real-time electrical signal range during tissue degeneration prediction, thereby quickly drawing conclusions about the tissue degeneration situation. Earlier judgment of tissue degeneration can also more accurately coordinate with the electrode control host, preventing loss of tracking and control of the tissue situation.

[0115] This application also provides a computer-readable storage medium storing program information. After a computer retrieves the program instructions, it executes the tissue denaturation point detection method during the sealing process described in any of the above method embodiments.

[0116] This application also provides an electronic device, such as... Figure 7The electronic device includes at least one processor 710 and at least one memory 720. The at least one memory 720 stores program information. After reading the program information, the at least one processor 710 executes the tissue denaturation point detection method during the sealing process as described in any of the above method embodiments. The device may further include an input device 730 and an output device 740. The processor 710, memory 720, input device 730, and output device 740 are communicatively connected. The memory 720, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 710 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 720, thereby implementing the tissue denaturation point detection method during the sealing process provided in any of the above embodiments. The memory 720 may include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the tissue denaturation point detection method during the sealing process. Furthermore, memory 720 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 720 may optionally include memory remotely located relative to processor 710, and these remote memories may be connected via a network to means of performing the tissue denaturation point detection method during the sealing process. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. Input device 730 may receive user clicks and generate signal inputs related to user settings and function control of the tissue denaturation point detection method during the sealing process. Output device 740 may include a display device such as a display screen. When the one or more modules are stored in memory 720 and are run by the one or more processors 710, the tissue denaturation point detection method during the sealing process in any of the above method embodiments is executed.

[0117] This application also provides an electrosurgical instrument, wherein the main unit of the electrosurgical instrument is equipped with a tissue degeneration point detection device, a computer-readable storage medium, or an electronic device during the sealing process as described in the above embodiments.

[0118] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this application.

Claims

1. A method for detecting tissue degeneration points during sealing, characterized in that, include: The real-time electrical signal at the current moment is acquired, the real-time electrical signal being determined based on the temperature change of the tissue based on the energy input from the electrodes, and fed back via the electrodes; Determining whether the tissue has reached the denaturation point based on the real-time electrical signal and the historical period electrical signal includes: obtaining a real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical period electrical signal; obtaining a reference feature value based on the real-time feature value and the historical feature value; the historical feature value is determined based on the electrical signal deviation corresponding to when the tissue reached the denaturation point during the historical sealing process; if the real-time electrical signal is greater than or equal to the reference feature value, it is determined that the tissue has reached the denaturation point. Specifically, a set period of time prior to the current moment is taken as the historical period, and the electrical signal obtained by the tissue based on the electrode input energy within the historical period is the historical period electrical signal.

2. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that, The reference feature value is obtained based on the real-time feature value and the historical feature value: The sum of the real-time feature value and the historical feature value is used as the baseline feature value.

3. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that, The step of determining whether the tissue has reached the denaturation point based on the real-time electrical signal and the historical time period electrical signal further includes: If the real-time electrical signal is less than the reference characteristic value, then return to the step of obtaining the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment.

4. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that, The step of obtaining the real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical time period electrical signal includes: Obtain the average electrical signal of the real-time electrical signal and the historical period electrical signal at each moment; The minimum average electrical signal is used as the real-time feature value at the current moment.

5. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that, The step of obtaining the real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical time period electrical signal includes: The weighted sum of the real-time electrical signal and the historical period electrical signal at each moment is obtained according to the preset weight value; The minimum weighted sum is taken as the real-time feature value at the current moment.

6. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that, The step of obtaining the real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical time period electrical signal includes: The predicted value of the electrical signal at the current moment is obtained based on the electrical signal variation pattern of the historical period. If the difference between the real-time electrical signal and the predicted value of the electrical signal is less than the difference threshold, then the real-time electrical signal is used as the real-time feature value; otherwise, the predicted value of the electrical signal is used as the real-time feature value.

7. The method for detecting tissue degeneration points during the sealing process according to claim 6, characterized in that, The step of obtaining the predicted electrical signal value at the current moment based on the electrical signal variation pattern of the historical period includes: Obtain the signal difference between every two adjacent acquired electrical signals in the historical time period; The average of all signal differences is used as the historical signal average. The sum of the latest acquired electrical signal and the average value of the historical signals in the historical period is used as the predicted value of the electrical signal.

8. The method for detecting tissue degeneration points during the sealing process according to claim 6, characterized in that, The step of obtaining the predicted electrical signal value at the current moment based on the electrical signal variation pattern of the historical period includes: An electrical signal curve is obtained by fitting the acquired electrical signals from the historical period, with time as the horizontal axis and electrical signal value as the vertical axis. The vertical coordinate corresponding to the current moment on the horizontal axis of the electrical signal curve is taken as the predicted value of the electrical signal.

9. The method for detecting tissue degeneration points during the sealing process according to any one of claims 1-8, characterized in that: The electrical signal fed back by the tissue based on the energy input from the electrodes is the tissue impedance value.

10. The method for detecting tissue degeneration points during the sealing process according to claim 1, characterized in that: Before acquiring the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment, the method further includes: Acquire the tissue electrical signal during the initial stage of the historical sealing process and the corresponding tissue electrical signal range when the tissue reaches the denaturation point; the tissue electrical signal is the electrical signal fed back by the tissue based on the electrode input energy during the initial stage; The learning algorithm is trained using the tissue electrical signal in the initial stage of the historical sealing process as the input sample and the tissue electrical signal interval as the output sample. The trained learning algorithm is then used as a tissue degeneration point prediction model. The step of determining whether the tissue has reached the denaturation point based on the real-time electrical signal and the historical time period electrical signal includes: The current time is defined as the end time of the initial stage in the current sealing process, and the set time period is defined as the initial stage in the current sealing process. The real-time electrical signal of the initial stage and the electrical signal of the historical period are input to the tissue degeneration point prediction model, and the output of the tissue degeneration point prediction model is used as the predicted electrical signal interval of the tissue degeneration point. Based on the predicted electrical signal interval, the real-time electrical signal interval corresponding to the tissue denaturation point during the current sealing process is determined; If the real-time electrical signal is within the real-time electrical signal interval, it is determined that the tissue has reached the denaturation point; otherwise, the process returns to the step of obtaining the real-time electrical signal fed back by the tissue based on the electrode input energy at the current moment.

11. The method for detecting tissue degeneration points during the sealing process according to claim 10, characterized in that: The tissue electrical signal, the real-time electrical signal, and the historical time period electrical signal are: continuous voltage and current values ​​with corresponding relationships fed back by the tissue based on the energy input from the electrode within a set time period; Alternatively, within a set time period, the tissue provides continuous, corresponding voltage, current, and tissue size values ​​based on the energy input from the electrodes. The tissue electrical signal range is: the voltage and current range corresponding to when the tissue reaches the denaturation point; Alternatively, a two-dimensional matrix obtained based on the voltage and current value sequences corresponding to the point when the tissue reaches the denaturation point; or, the tissue impedance value range corresponding to the point when the tissue reaches the denaturation point, or the tissue impedance sequence corresponding to the point when the tissue reaches the denaturation point.

12. The method for detecting tissue degeneration points during the sealing process according to claim 11, characterized in that, Determining the real-time electrical signal interval corresponding to the tissue degeneration point during the current sealing process based on the predicted electrical signal interval includes: If the tissue electrical signal interval is the voltage and current value interval corresponding to when the tissue reaches the denaturation point, then the voltage or current value interval is taken as the real-time electrical signal interval segment. If the tissue electrical signal interval is a two-dimensional matrix obtained based on the voltage value sequence and the current value sequence when the tissue reaches the denaturation point, then the average voltage value interval obtained by combining the average voltage value obtained by the voltage value sequence with the error range or the average current value interval obtained by combining the average current value obtained by the current value sequence with the error range shall be used as the real-time electrical signal interval segment. If the tissue electrical signal interval is the tissue impedance value interval corresponding to when the tissue reaches the denaturation point, then the tissue impedance value interval is taken as the real-time electrical signal interval segment; If the tissue electrical signal interval is the tissue impedance sequence corresponding to the point when the tissue reaches the denaturation point, then the average impedance value interval obtained by combining the average impedance value obtained from the tissue impedance sequence with the error range shall be used as the real-time electrical signal interval segment.

13. The method for detecting tissue degeneration points during the sealing process according to claim 10, characterized in that, The learning algorithm is trained using the tissue electrical signal from the initial stage of the historical sealing process as input samples and the tissue electrical signal interval as output samples. The trained learning algorithm is then used in the tissue degeneration point prediction model. The learning algorithm is a multilayer perceptron algorithm; in the multilayer perceptron algorithm, the first... i The functional representation of a layer perceptron is: ； Among them, if i＞1 ,but For the ( i-1 The output of the layer perceptron, if i=1 ,but To obtain the tissue electrical signals; The weight matrix is ​​composed of preset weight factors in the perceptron. b This is a preset deviation in the sensor; f（） This is a preset nonlinear function.

14. A device for detecting tissue denaturation points during sealing, characterized in that, include: The sampling module is configured to acquire a real-time electrical signal at the current moment, the real-time electrical signal being determined based on the temperature change of the tissue based on the energy input from the electrodes, and fed back via the electrodes; A denaturation point determination module is configured to determine whether the tissue has reached a denaturation point based on the real-time electrical signal and the historical time period electrical signal; including: obtaining a real-time feature value corresponding to the real-time electrical signal based on the real-time electrical signal and the historical time period electrical signal; obtaining a reference feature value based on the real-time feature value and the historical feature value; the historical feature value is determined based on the electrical signal deviation corresponding to when the tissue reached the denaturation point during the historical sealing process; if the real-time electrical signal is greater than or equal to the reference feature value, it is determined that the tissue has reached the denaturation point; wherein, a set time period before the current time is taken as the historical time period, and the electrical signal fed back by the tissue based on the electrode input energy obtained within the historical time period is the historical time period electrical signal.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program information, and after the computer retrieves the program information, it executes the method for detecting tissue degeneration points during the sealing process as described in any one of claims 1-13.

16. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory, wherein at least one memory stores program information, and at least one processor retrieves the program information and executes the tissue denaturation point detection method during the sealing process as described in any one of claims 1-13.

17. An electrosurgical instrument, characterized in that, The main unit of the electrosurgical instrument is equipped with the tissue degeneration point detection device during the sealing process as described in claim 14, or the computer-readable storage medium as described in claim 15, or the electronic device as described in claim 16.

Images