An orthopedic surgery robot monitoring system and a monitoring method thereof

Abstract

The application discloses a kind of orthopedic surgery robot monitoring system and monitoring method thereof, it is related to orthopedic surgery robot monitoring technical field, the present application integrates power parameter and position parameter, constructs comprehensive surgical risk assessment system, avoid one-sidedness of single parameter monitoring, based on real-time data calculation power parameter deviation, trajectory deviation and risk coefficient, reflect the dynamic fluctuation of parameter in surgical process, break through the rigidity of traditional static threshold evaluation, reduce the probability of dangerous operation;Risk trend is predicted using model, risk rises, falls or stable state is identified in advance through slope comparison, realize forward-looking early warning, avoid lag response, simultaneously combine risk level dynamic adjustment power parameter and surgical trajectory, improve the risk prevention and control capability in surgical process, reduce the surgical complications caused by risk handling not in time or improper handling, significantly improve the safety and success rate of orthopedic surgery.

Description

Technical Field

[0001] This invention relates to the field of orthopedic surgical robot technology, specifically to an orthopedic surgical robot monitoring system and its monitoring method. Background Technology

[0002] The use of robots is crucial in orthopedic surgery. However, current orthopedic robots face numerous challenges in their operation. Traditional monitoring methods often only acquire single parameters, failing to comprehensively and accurately reflect the robot's operational status. This leads to the inability to promptly detect and address potential risks, such as soft tissue contact, bone thermal injury, and tool overload, thereby increasing the probability of iatrogenic injuries.

[0003] Furthermore, existing robots lack effective and precise control methods, making it difficult to dynamically calibrate motion parameters in conjunction with preoperative planned trajectories. This results in low operational accuracy, susceptibility to errors, and impacts surgical outcomes. Moreover, surgeons frequently need to manually adjust robot parameters during surgery to adapt to different bone conditions, increasing both their workload and the duration of the operation. Therefore, the development of an orthopedic surgical robot monitoring system and its monitoring method is of paramount importance.

[0004] Existing technology, such as the invention patent application with publication number CN112230076B, discloses a method and system for monitoring the motion status of an orthopedic power system. In this system, an electricity meter is installed after a UPS, which is then connected to the orthopedic power system control system and the orthopedic drill. The electricity meter is connected to an industrial control computer via a 485 reader. After the orthopedic drill is started, the industrial control computer collects real-time electrical characteristic data such as voltage, current, power, and power factor monitored by the electricity meter to monitor the drill's status. The electricity meter supports both carrier wave and 485 output, offering stability and convenience. Its electrical characteristics can reflect the drill's operating status in real time, making it a reasonable solution for monitoring drill rotation.

[0005] The existing technology has the following defects, specifically: 1. In the existing technology, only basic parameters are monitored, and there is a lack of dynamic tracking of the three-dimensional position and angle of the surgical tool. The trajectory is adjusted by relying only on experience or single-dimensional data, the risk assessment is not comprehensive, the trajectory control precision is insufficient, which leads to the operation deviating from the preset surgical path and increases the surgical risk.

[0006] 2. In existing technologies, risk assessment is based on pre-set fixed parameters or historical data models. However, it cannot incorporate real-time data that changes dynamically during the operation. It cannot dynamically optimize dynamic parameters and surgical trajectory based on risk level and real-time data. It lacks time series analysis and trend prediction of risk coefficients. It can only judge the risk at the current time point and cannot predict the trend of risk changes, which increases the probability of surgical risks occurring. Summary of the Invention

[0007] The purpose of this invention is to provide an orthopedic surgical robot monitoring system and its monitoring method, which solves the problems existing in the background art.

[0008] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides an orthopedic surgical robot monitoring system, including: a data acquisition module, used to generate reference dynamic parameters and reference surgical trajectory through medical image data processing and three-dimensional reconstruction, and to acquire real-time relevant data of the robot during surgery based on the micro sensors integrated into the orthopedic surgical robot.

[0009] The data processing module is used to calculate the deviation coefficient of the robot's dynamic parameters at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference dynamic parameters. It is also used to calculate the trajectory deviation coefficient of the robot at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference surgical trajectory.

[0010] The early warning module is used to calculate the risk coefficient of each monitoring time point of the operation based on the deviation coefficient of the robot's dynamic parameters and the trajectory deviation coefficient, determine the risk level of each monitoring time point of the operation, and then use time series analysis to predict the trend of risk coefficient changes and generate a graded early warning strategy.

[0011] The display terminal is used to display real-time relevant data of the robot during surgery, including the deviation coefficients of the robot's power parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients and risk levels at each monitoring time point, and the predicted risk coefficients and their changing trends.

[0012] Preferably, the acquisition of real-time relevant data of the robot during surgery includes power parameters, extended parameters, and position parameters, wherein the power parameters include rotational speed, torque, and vibration acceleration, the extended parameters include tool temperature, bone tissue stress distribution, and soft tissue contact state, and the position parameters include three-dimensional coordinate values, direction, and angle.

[0013] Preferably, the method for calculating the deviation coefficient of the robot's dynamic parameters at each monitoring time point is as follows: extracting the dynamic parameters at each monitoring time point during the operation, extracting the reference dynamic parameters, performing numerical fitting processing, inputting them into the robot dynamic parameter deviation coefficient analysis model, and outputting the deviation coefficient of the robot's dynamic parameters at each monitoring time point. The model expression is: ,in Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first The monitoring time point The value of each dynamic parameter, Indicates the robot's first The minimum value of the reference dynamic parameter for each dynamic parameter. Indicates the robot's first The maximum value of the reference dynamic parameter for each dynamic parameter. Number each monitoring time point. , It is any integer greater than 2. These are the numbers for each power parameter. .

[0014] Preferably, the method for calculating the trajectory deviation coefficient of the robot at each monitoring time point is as follows: extracting the position parameters of each monitoring time point during the operation, extracting the reference surgical trajectory, performing numerical fitting processing, calculating the trajectory deviation coefficient and angle deviation coefficient of the robot at each monitoring time point, and then calculating the trajectory deviation coefficient of the robot at each monitoring time point using the following formula: ,in Indicates the robot's first Trajectory deviation coefficient at each monitoring time point Indicates the robot's first Location deviation coefficient at each monitoring time point Indicates the robot's first The angular deviation coefficient at each monitoring time point , These represent the appropriate position deviation coefficient weighting factor and the appropriate angle deviation coefficient weighting factor stored in the database, respectively.

[0015] Preferably, the method for calculating the risk coefficient at each monitoring time point during surgery is as follows: extracting the deviation coefficient of the robot's dynamic parameters at each monitoring time point, extracting the trajectory deviation coefficient of the robot at each monitoring time point, and calculating the risk coefficient at each monitoring time point during surgery. The calculation formula is: ,in Indicates the first surgery Risk coefficient at each monitoring time point Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first Trajectory deviation coefficient at each monitoring time point , These represent the deviation coefficient weighting factor and the suitable trajectory deviation coefficient weighting factor of the appropriate dynamic parameters stored in the database, respectively.

[0016] Preferably, the method for determining the risk level at each monitoring time point of the surgery is as follows: extract the risk coefficient at each monitoring time point of the surgery, and compare it with the risk coefficient range corresponding to each risk level stored in the database. The risk levels are divided into low, medium, and high. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the low risk level, then the risk level of the surgery at that monitoring time point is determined to be low risk. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the medium risk level, then the risk level of the surgery at that monitoring time point is determined to be medium risk. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the high risk level, then the risk level of the surgery at that monitoring time point is determined to be high risk.

[0017] Preferably, the method for predicting the trend of risk coefficient changes using time series analysis is as follows: Risk coefficients are extracted at each monitoring time point during surgery, and a risk coefficient sequence is fitted. This sequence is then input into an autoregressive integral moving average model, which outputs the predicted risk coefficient sequence for the current monitoring time point. The slope of the predicted risk coefficient sequence for the current monitoring time point is calculated and compared with the reference slope of the predicted risk coefficient sequence stored in the database. If the slope of the predicted risk coefficient sequence for the current monitoring time point is higher than the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be upward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is lower than the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be downward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is equal to the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be stable.

[0018] Preferably, the generation of the graded early warning strategy is specifically implemented as follows: extract the trend of the predicted risk coefficient at the current monitoring time point, extract the risk level at the current monitoring time point; if the risk level at the current monitoring time point is low risk, and the trend of the predicted risk coefficient at the current monitoring time point is stabilizing or decreasing, then a first-level early warning signal is generated, while maintaining the current power parameters and surgical trajectory; if the risk level at the current monitoring time point is medium risk, or the trend of the predicted risk coefficient at the current monitoring time point is increasing, then a second-level early warning signal is generated, while dynamically correcting the power parameters and surgical trajectory according to a preset adjustment coefficient; if the risk level at the current monitoring time point is high risk, then a third-level early warning signal is generated, and the robot immediately stops.

[0019] Preferably, the dynamic correction of the power parameters according to the preset adjustment coefficient is specifically implemented as follows: The risk coefficient at the current monitoring time point is extracted and compared with the risk coefficient threshold stored in the database. If the risk coefficient at the current monitoring time point is lower than the risk coefficient threshold stored in the database, it is determined that the reference power parameters for the next monitoring time point do not need to be adjusted. If the risk coefficient at the current monitoring time point is higher than the risk coefficient threshold stored in the database, it is determined that the reference power parameters for the next monitoring time point need to be adjusted. The formula for calculating the adjustment amount of the reference power parameters is: ,in, Indicates the robot's first The monitoring time point Adjustment amount of each power parameter Indicates the adjustment factor. , Indicates the robot's first The monitoring time point The value of the first dynamic parameter is related to the robot's first... The monitoring time point The difference between the reference dynamic parameters of the first dynamic parameter is used to extract the robot's first dynamic parameter. The monitoring time point The maximum value of the reference dynamic parameter of the first dynamic parameter is subtracted from the dynamic parameter adjustment amount to extract the robot's first dynamic parameter. The monitoring time point The adjusted reference power parameter is obtained by adding the minimum value of the reference power parameter to the power parameter adjustment amount.

[0020] The second aspect of the present invention includes a method for monitoring the dynamics of orthopedic surgery, comprising: step one, data acquisition, which is used to generate reference dynamic parameters and reference surgical trajectory through medical image data processing and three-dimensional reconstruction, and to acquire real-time relevant data of the robot during surgery based on the micro-sensors integrated into the orthopedic surgical robot.

[0021] Step 2: Data processing. Based on the real-time relevant data of the robot during surgery, combined with reference dynamic parameters, the deviation coefficient of the robot's dynamic parameters at each monitoring time point is calculated. Based on the real-time relevant data of the robot during surgery, combined with reference surgical trajectory, the trajectory deviation coefficient of the robot at each monitoring time point is calculated.

[0022] Step 3, Early Warning: Based on the deviation coefficients of the robot's dynamic parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients at each monitoring time point of the surgery are calculated, the risk level at each monitoring time point of the surgery is determined, and then time series analysis is used to predict the trend of risk coefficient changes and generate a graded early warning strategy.

[0023] The beneficial effects of this invention are as follows: 1. In this invention, dynamic parameters and positional parameters are integrated to construct a comprehensive surgical risk assessment system, avoiding the one-sidedness of monitoring a single parameter. Based on real-time data, the deviation of dynamic parameters, trajectory deviation and risk coefficient are calculated to reflect the dynamic fluctuation of parameters during the surgical process, breaking through the rigidity of traditional static threshold assessment and reducing the probability of surgical risks.

[0024] 2. In this invention, the model is used to predict risk trends and the slope comparison is used to identify the risk increase, decrease or stabilization state in advance, so as to realize the forward warning and avoid the delayed response. At the same time, the dynamic parameters and surgical trajectory are dynamically adjusted in combination with the risk level, which improves the risk control capability during the operation, reduces the surgical complications caused by untimely or improper risk handling, and significantly improves the safety and success rate of orthopedic surgery. Attached Figure Description

[0025] 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.

[0026] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0027] Figure 2 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation

[0028] 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.

[0029] Reference Figure 1 As shown, the present invention provides an orthopedic surgical robot monitoring system, including: a data acquisition module, used to generate reference dynamic parameters and reference surgical trajectory through medical image data processing and three-dimensional reconstruction, and to acquire real-time relevant data of the robot during surgery based on the micro sensors integrated into the orthopedic surgical robot.

[0030] It should be noted that the method for generating reference dynamic parameters and reference surgical trajectories through medical image data processing and three-dimensional reconstruction is as follows: anatomical structures are extracted from CT / MRI images, and after noise reduction, segmentation, and three-dimensional modeling, dynamic parameters (such as rotational speed and torque) are set in combination with biomechanical properties such as bone density. Then, a three-dimensional path and operating angle are planned based on anatomical landmarks and obstacle avoidance principles, and finally, a surgical trajectory adapted to the individual is formed and stored in the database.

[0031] In one specific embodiment, the acquisition of real-time relevant data of the robot during surgery includes power parameters, extended parameters, and position parameters. The power parameters include rotational speed, torque, and vibration acceleration. The extended parameters include tool temperature, bone tissue stress distribution, and soft tissue contact state. The position parameters include three-dimensional coordinates, direction, and angle.

[0032] It should be noted that the rotational speed, torque, and vibration acceleration are obtained through a rotational speed sensor, a torque sensor, and a vibration acceleration sensor, respectively. The tool temperature, bone tissue stress distribution, and soft tissue contact state are obtained through a tool temperature sensor, a bone tissue stress sensor, and a soft tissue contact sensor, respectively. The three-dimensional coordinate values, direction, and angle are obtained through a three-dimensional positioning sensor. All sensors are located inside or on the surface of the robot.

[0033] The data processing module is used to calculate the deviation coefficient of the robot's dynamic parameters at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference dynamic parameters. It is also used to calculate the trajectory deviation coefficient of the robot at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference surgical trajectory.

[0034] In one specific embodiment, the method for calculating the deviation coefficient of the robot's dynamic parameters at each monitoring time point is as follows: extracting the dynamic parameters at each monitoring time point during the operation, extracting reference dynamic parameters, performing numerical fitting processing, inputting them into the robot dynamic parameter deviation coefficient analysis model, and outputting the deviation coefficient of the robot's dynamic parameters at each monitoring time point. The model expression is: ,in Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first The monitoring time point The value of each dynamic parameter, Indicates the robot's first The minimum value of the reference dynamic parameter for each dynamic parameter. Indicates the robot's first The maximum value of the reference dynamic parameter for each dynamic parameter. Number each monitoring time point. , It is any integer greater than 2. These are the numbers for each power parameter. .

[0035] In one specific embodiment, the method for calculating the trajectory deviation coefficient of the robot at each monitoring time point is as follows: Position parameters of each monitoring time point during the surgery are extracted, a reference surgical trajectory is extracted, and after numerical fitting processing, the trajectory deviation coefficient and angle deviation coefficient of the robot at each monitoring time point are calculated. Then, the trajectory deviation coefficient of the robot at each monitoring time point is calculated using the following formula: ,in Indicates the robot's first Trajectory deviation coefficient at each monitoring time point Indicates the robot's first Location deviation coefficient at each monitoring time point Indicates the robot's first The angular deviation coefficient at each monitoring time point , These represent the appropriate position deviation coefficient weighting factor and the appropriate angle deviation coefficient weighting factor stored in the database, respectively.

[0036] In this invention, dynamic parameters and positional parameters are integrated to construct a comprehensive surgical risk assessment system, avoiding the one-sidedness of monitoring a single parameter. Based on real-time data, the deviation of dynamic parameters, trajectory deviation, and risk coefficient are calculated to reflect the dynamic fluctuations of parameters during the surgical process. This breaks through the rigidity of traditional static threshold assessment and reduces the probability of surgical complications.

[0037] It should be noted that the position deviation coefficient is calculated using the following formula: ,in , , They represent the robot's number 1 and 2. Each monitoring time point axis coordinate values axis coordinate values axis coordinate values, , , They represent the robot's number 1 and 2. Each monitoring time point is referenced from the surgical trajectory. axis coordinate values axis coordinate values axis coordinate values, This represents the position deviation threshold stored in the database; the angle deviation coefficient is analyzed as follows: extracting the robot's... Each monitoring time point axis coordinate values axis coordinate values The axis coordinate values ​​are fitted into a tangent vector. Referring to the tangent vector of the surgical trajectory at the same time point Then, the angular deviation coefficient is calculated, and the calculation formula is: , This represents the angular deviation threshold stored in the database. It should also be noted that the database stores appropriate position deviation coefficient weighting factors and appropriate angular deviation coefficient weighting factors. The real-time trajectory and reference trajectory of the robot during historical surgeries are extracted, the position deviation coefficient and angular deviation coefficient at each time point are calculated, the data is normalized, and principal component analysis (PCA) is used to determine the contribution of position and angle to the surgical outcome, thus obtaining appropriate position deviation coefficient weighting factors and appropriate angular deviation coefficient weighting factors.

[0038] The early warning module is used to calculate the risk coefficient of each monitoring time point of the operation based on the deviation coefficient of the robot's dynamic parameters and the trajectory deviation coefficient, determine the risk level of each monitoring time point of the operation, and then use time series analysis to predict the trend of risk coefficient changes and generate a graded early warning strategy.

[0039] In one specific embodiment, the method for calculating the risk coefficient at each monitoring time point of the surgery is as follows: extracting the deviation coefficient of the robot's dynamic parameters at each monitoring time point, extracting the trajectory deviation coefficient of the robot at each monitoring time point, and calculating the risk coefficient at each monitoring time point of the surgery. The calculation formula is as follows: ,in Indicates the first surgery Risk coefficient at each monitoring time point Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first Trajectory deviation coefficient at each monitoring time point , These represent the deviation coefficient weighting factor and the suitable trajectory deviation coefficient weighting factor of the appropriate dynamic parameters stored in the database, respectively.

[0040] It should be noted that the appropriate deviation coefficient weighting factors for dynamic parameters and the appropriate trajectory deviation coefficient weighting factors stored in the database are set by professionals.

[0041] In one specific embodiment, the method for determining the risk level at each monitoring time point of the surgery is as follows: extract the risk coefficient at each monitoring time point of the surgery, and compare it with the risk coefficient range corresponding to each risk level stored in the database. The risk levels are divided into low, medium, and high. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the low risk level, then the risk level of the surgery at that monitoring time point is determined to be low risk. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the medium risk level, then the risk level of the surgery at that monitoring time point is determined to be medium risk. If the risk coefficient at a certain monitoring time point of the surgery is within the risk coefficient range corresponding to the high risk level, then the risk level of the surgery at that monitoring time point is determined to be high risk.

[0042] It should be noted that the risk coefficient ranges corresponding to each risk level stored in the database are quantified using historical data, such as percentiles, mean ± standard deviation, and ROC curves, and are set by professionals.

[0043] In one specific embodiment, the method for predicting the trend of risk coefficient changes using time series analysis is as follows: extract the risk coefficients at each monitoring time point of the surgery, fit a risk coefficient sequence, input it into an autoregressive integral moving average model, output the predicted risk coefficient sequence for the current monitoring time point, and then calculate the slope of the predicted risk coefficient sequence for the current monitoring time point. Compare the slope of the predicted risk coefficient sequence for the current monitoring time point with the reference slope of the predicted risk coefficient sequence stored in the database. If the slope of the predicted risk coefficient sequence for the current monitoring time point is higher than the reference slope of the predicted risk coefficient sequence stored in the database, the trend of the risk coefficient change for the current monitoring time point is determined to be upward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is lower than the reference slope of the predicted risk coefficient sequence stored in the database, the trend of the risk coefficient change for the current monitoring time point is determined to be downward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is equal to the reference slope of the predicted risk coefficient sequence stored in the database, the trend of the risk coefficient change for the current monitoring time point is determined to be stable.

[0044] In this invention, a model is used to predict risk trends, and the rising, falling or stable state of risk is identified in advance by comparing slopes, so as to achieve forward-looking early warning and avoid delayed response. At the same time, dynamic parameters and surgical trajectory are dynamically adjusted in combination with risk level, which improves the risk control capability during the operation, reduces surgical complications caused by untimely or improper risk management, and significantly improves the safety and success rate of orthopedic surgery.

[0045] It should be noted that the autoregressive integral moving average model is existing technology and will not be elaborated on here. The calculation of the slope of the predicted risk coefficient sequence is specifically as follows: the predicted risk coefficient sequence is fitted into a linear regression equation, and then the slope is calculated. The reference slope of the predicted risk coefficient sequence stored in the database is used to calculate its slope distribution based on a large number of historical surgical risk coefficient sequences. The reference slope is set by professionals.

[0046] Risk coefficient sequences {R(1), R(2), ...} at each monitoring time point during surgery An autoregressive integral moving average (ARIMA) model is established for R(j)} to predict the risk coefficients {R(i+1), R(i+2),} for the next n monitoring time points. The expression for the ARIMA model is: Φ(B)(1-B)dR(t)=θ(B)}, R(i+n)}. θ(t), where Φ(B) is the autoregressive polynomial, B is the shift operator, d is the difference order, and θ(B) is the moving average polynomial. (t) is a white noise sequence.

[0047] In one specific embodiment, the generation of the graded early warning strategy is implemented as follows: extract the trend of the predicted risk coefficient at the current monitoring time point, extract the risk level at the current monitoring time point; if the risk level at the current monitoring time point is low risk, and the trend of the predicted risk coefficient at the current monitoring time point is stabilizing or decreasing, then a first-level early warning signal is generated, while maintaining the current power parameters and surgical trajectory; if the risk level at the current monitoring time point is medium risk, or the trend of the predicted risk coefficient at the current monitoring time point is increasing, then a second-level early warning signal is generated, while dynamically correcting the power parameters and surgical trajectory according to a preset adjustment coefficient; if the risk level at the current monitoring time point is high risk, then a third-level early warning signal is generated, and the robot stops urgently.

[0048] It should be noted that the first-level warning signal is indicated by a yellow warning light accompanied by a gentle beep; the second-level warning signal is indicated by an orange warning light accompanied by a buzzer alarm, and the specific deviation parameters, such as torque exceeding the limit, are indicated; the third-level warning signal is indicated by a red warning light accompanied by a sharp alarm.

[0049] In one specific embodiment, the dynamic correction of the power parameters according to a preset adjustment coefficient is implemented as follows: The risk coefficient at the current monitoring time point is extracted and compared with a risk coefficient threshold stored in the database. If the risk coefficient at the current monitoring time point is lower than the risk coefficient threshold stored in the database, it is determined that the reference power parameters for the next monitoring time point do not need adjustment. If the risk coefficient at the current monitoring time point is higher than the risk coefficient threshold stored in the database, it is determined that the reference power parameters for the next monitoring time point need adjustment. The formula for calculating the adjustment amount of the reference power parameters is: ,in, Indicates the robot's first The monitoring time point Adjustment amount of each power parameter Indicates the adjustment factor. , Indicates the robot's first The monitoring time point The value of the first dynamic parameter is related to the robot's first... The monitoring time point The difference between the reference dynamic parameters of the first dynamic parameter is used to extract the robot's first dynamic parameter. The monitoring time point The maximum value of the reference dynamic parameter of the first dynamic parameter is subtracted from the dynamic parameter adjustment amount to extract the robot's first dynamic parameter. The monitoring time point The adjusted reference power parameter is obtained by adding the minimum value of the reference power parameter to the power parameter adjustment amount.

[0050] It should be noted that the risk coefficient thresholds stored in the database are set by professionals. The adjustment coefficient, used to quantify the adjustment intensity of the dynamic parameters when the risk exceeds the standard, is also set by professionals. It should also be noted that the analysis method for the dynamic correction of the surgical trajectory is the same as that for the dynamic correction of the dynamic parameters, and will not be elaborated on here.

[0051] The display terminal is used to display real-time relevant data of the robot during surgery, including the deviation coefficients of the robot's power parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients and risk levels at each monitoring time point, and the predicted risk coefficients and their changing trends.

[0052] It should be noted that it also includes a database, specifically including appropriate position deviation coefficient weighting factors, appropriate angle deviation coefficient weighting factors, position deviation thresholds, angle deviation thresholds, appropriate dynamic parameter deviation coefficient weighting factors, appropriate trajectory deviation coefficient weighting factors, reference slopes of the predicted risk coefficient sequence, risk coefficient ranges corresponding to each risk level, appropriate risk coefficient thresholds, and adjustment coefficients.

[0053] It should be noted that the data acquisition module is connected to the data processing module, the data processing module is connected to the early warning module, and the data acquisition module, data processing module, and early warning module are all connected to the display terminal and the database.

[0054] refer to Figure 2 A method for monitoring the dynamics of orthopedic surgery includes: Step 1, data acquisition, which generates reference dynamic parameters and reference surgical trajectory through medical image data processing and three-dimensional reconstruction, and acquires real-time relevant data of the robot during surgery based on the micro-sensors integrated into the orthopedic surgical robot.

[0055] Step 2: Data processing. Based on the real-time relevant data of the robot during surgery, combined with reference dynamic parameters, the deviation coefficient of the robot's dynamic parameters at each monitoring time point is calculated. Based on the real-time relevant data of the robot during surgery, combined with reference surgical trajectory, the trajectory deviation coefficient of the robot at each monitoring time point is calculated.

[0056] Step 3, Early Warning: Based on the deviation coefficients of the robot's dynamic parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients at each monitoring time point of the surgery are calculated, the risk level at each monitoring time point of the surgery is determined, and then time series analysis is used to predict the trend of risk coefficient changes and generate a graded early warning strategy.

[0057] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications or additions should fall within the protection scope of the present invention.

Claims

1. A monitoring system for an orthopedic surgical robot, characterized in that, include: The data acquisition module is used to generate reference dynamic parameters and reference surgical trajectory through medical image data processing and 3D reconstruction, and to acquire real-time relevant data of the robot during surgery based on the micro sensors integrated into the orthopedic surgical robot. The data processing module is used to calculate the deviation coefficient of the robot's power parameters at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference power parameters. It is also used to calculate the trajectory deviation coefficient of the robot at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference surgical trajectory. The early warning module is used to calculate the risk coefficient of each monitoring time point of the operation based on the deviation coefficient of the robot's dynamic parameters and the trajectory deviation coefficient, determine the risk level of each monitoring time point of the operation, and then use time series analysis to predict the trend of risk coefficient changes and generate a graded early warning strategy. The display terminal is used to display real-time relevant data of the robot during surgery, including the deviation coefficients of the robot's power parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients and risk levels at each monitoring time point, and the predicted risk coefficients and their changing trends.

2. The orthopedic surgical robot monitoring system according to claim 1, characterized in that, The acquisition of real-time relevant data of the robot during surgery includes power parameters, extended parameters, and position parameters. The power parameters include rotational speed, torque, and vibration acceleration. The extended parameters include tool temperature, bone tissue stress distribution, and soft tissue contact state. The position parameters include three-dimensional coordinates, direction, and angle.

3. The orthopedic surgical robot monitoring system according to claim 2, characterized in that, The specific method for calculating the deviation coefficient of the robot's dynamic parameters at each monitoring time point is as follows: The dynamic parameters at each monitoring time point during the operation are extracted, and reference dynamic parameters are extracted. After numerical fitting, these parameters are input into the robot dynamic parameter deviation coefficient analysis model, which outputs the deviation coefficients of the robot's dynamic parameters at each monitoring time point. The model expression is as follows: ,in Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first The monitoring time point The value of each dynamic parameter, Indicates the robot's first The minimum value of the reference dynamic parameter for each dynamic parameter. Indicates the robot's first The maximum value of the reference dynamic parameter for each dynamic parameter. Number each monitoring time point. , It is any integer greater than 2. These are the numbers for each power parameter. .

4. The orthopedic surgical robot monitoring system according to claim 3, characterized in that, The specific implementation method for calculating the trajectory deviation coefficient of the robot at each monitoring time point is as follows: Positional parameters at each monitoring time point during the surgery are extracted, and a reference surgical trajectory is extracted. After numerical fitting, the trajectory deviation coefficient and angle deviation coefficient of the robot at each monitoring time point are calculated. The trajectory deviation coefficient of the robot at each monitoring time point is then calculated using the following formula: ,in Indicates the robot's first Trajectory deviation coefficient at each monitoring time point Indicates the robot's first Location deviation coefficient at each monitoring time point Indicates the robot's first The angular deviation coefficient at each monitoring time point , These represent the appropriate position deviation coefficient weighting factor and the appropriate angle deviation coefficient weighting factor stored in the database, respectively.

5. The orthopedic surgical robot monitoring system according to claim 4, characterized in that, The specific method for calculating the risk coefficient at each monitoring time point during surgery is as follows: The deviation coefficients of the robot's dynamic parameters and trajectory deviation coefficients at each monitoring time point are extracted. The risk coefficients at each monitoring time point of the surgery are then calculated using the following formula: ,in Indicates the first surgery Risk coefficient at each monitoring time point Indicates the robot's first Deviation coefficient of dynamic parameters at each monitoring time point, Indicates the robot's first Trajectory deviation coefficient at each monitoring time point , These represent the deviation coefficient weighting factor and the suitable trajectory deviation coefficient weighting factor of the appropriate dynamic parameters stored in the database, respectively.

6. The orthopedic surgical robot monitoring system according to claim 5, characterized in that, The specific method for determining the risk level at each monitoring time point during surgery is as follows: The risk coefficients at each monitoring time point during the surgery are extracted and compared with the risk coefficient ranges corresponding to each risk level stored in the database. The risk levels are divided into low, medium, and high. If the risk coefficient at a certain monitoring time point during the surgery is within the risk coefficient range corresponding to the low risk level, the risk level of the surgery at that monitoring time point is determined to be low risk. If the risk coefficient at a certain monitoring time point during the surgery is within the risk coefficient range corresponding to the medium risk level, the risk level of the surgery at that monitoring time point is determined to be medium risk. If the risk coefficient at a certain monitoring time point during the surgery is within the risk coefficient range corresponding to the high risk level, the risk level of the surgery at that monitoring time point is determined to be high risk.

7. The orthopedic surgical robot monitoring system according to claim 6, characterized in that, The specific method for predicting the trend of risk coefficient changes using time series analysis is as follows: Risk coefficients are extracted at each monitoring time point during surgery, and a risk coefficient sequence is fitted. This sequence is then input into an autoregressive integral moving average model, which outputs the predicted risk coefficient sequence for the current monitoring time point. The slope of the predicted risk coefficient sequence for the current monitoring time point is calculated and compared with the reference slope of the predicted risk coefficient sequence stored in the database. If the slope of the predicted risk coefficient sequence for the current monitoring time point is higher than the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be upward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is lower than the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be downward. If the slope of the predicted risk coefficient sequence for the current monitoring time point is equal to the reference slope stored in the database, the risk coefficient trend for the current monitoring time point is determined to be stable.

8. The orthopedic surgical robot monitoring system according to claim 7, characterized in that, The specific implementation method of the generation of hierarchical early warning strategy is as follows: Extract the trend of the predicted risk coefficient at the current monitoring time point and the risk level at the current monitoring time point. If the risk level at the current monitoring time point is low and the trend of the predicted risk coefficient at the current monitoring time point is stabilizing or decreasing, a first-level warning signal is generated, while maintaining the current power parameters and surgical trajectory. If the risk level at the current monitoring time point is medium, or the trend of the predicted risk coefficient at the current monitoring time point is increasing, a second-level warning signal is generated, while dynamically correcting the power parameters and surgical trajectory according to the preset adjustment coefficient. If the risk level at the current monitoring time point is high, a third-level warning signal is generated, and the robot stops immediately.

9. The orthopedic surgical robot monitoring system according to claim 8, characterized in that, The specific method for dynamically correcting the power parameters according to the preset adjustment coefficient is as follows: Extract the risk coefficient for the current monitoring time point and compare it with the risk coefficient threshold stored in the database. If the risk coefficient for the current monitoring time point is lower than the risk coefficient threshold stored in the database, it is determined that the reference dynamic parameter for the next monitoring time point does not need to be adjusted. If the risk coefficient for the current monitoring time point is higher than the risk coefficient threshold stored in the database, it is determined that the reference dynamic parameter for the next monitoring time point needs to be adjusted. The formula for calculating the adjustment amount of the reference dynamic parameter is as follows: ,in, Indicates the robot's first The monitoring time point Adjustment amount of each power parameter Indicates the adjustment factor. , Indicates the robot's first The monitoring time point The value of the first dynamic parameter is related to the robot's first... The monitoring time point The difference between the reference dynamic parameters of the first dynamic parameter is used to extract the robot's first dynamic parameter. The monitoring time point The maximum value of the reference dynamic parameter of the first dynamic parameter is subtracted from the dynamic parameter adjustment amount to extract the robot's first dynamic parameter. The monitoring time point The adjusted reference power parameter is obtained by adding the minimum value of the reference power parameter to the power parameter adjustment amount.

10. A method for performing the orthopedic surgical dynamic monitoring system according to any one of claims 1 to 9, characterized in that, include: Step 1, Data Acquisition, is used to generate reference dynamic parameters and reference surgical trajectory through medical image data processing and 3D reconstruction. Based on the micro sensors integrated into the orthopedic surgical robot, real-time relevant data of the robot during surgery is acquired. Step 2, data processing, is used to calculate the deviation coefficient of the robot's dynamic parameters at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference dynamic parameters. It is also used to calculate the trajectory deviation coefficient of the robot at each monitoring time point based on the real-time relevant data of the robot during surgery and in combination with the reference surgical trajectory. Step 3, Early Warning: Based on the deviation coefficients of the robot's dynamic parameters and trajectory deviation coefficients at each monitoring time point, the risk coefficients at each monitoring time point of the surgery are calculated, the risk level at each monitoring time point of the surgery is determined, and then time series analysis is used to predict the trend of risk coefficient changes and generate a graded early warning strategy.

Images