Condylar fracture operation simulation planning and training system based on patient personalized data

Abstract

The invention relates to the technical field of fracture surgery simulation planning, and discloses a condylar fracture surgery simulation planning and training system based on patient personalized data. Comprising a fracture data rapid scanning module, a personalized model 3D printing module, a training model part replacement module, a multi-scheme simulation evaluation module, a preoperative repeated simulation training module and an operation execution admission judgment module. Replacing relevant parameters of the model with parameters of corresponding parts of the patent training model, reconstructing the model, further generating multiple operation schemes, quantitatively evaluating and screening an optimal scheme, carrying out multiple times of pre-operation simulation training based on the scheme, recording training data in real time, carrying out quantitative analysis, and establishing an operation execution admission judgment mechanism; the operation is allowed to be executed only when the training result meets the preset standard. The precision and safety of the condylar fracture surgery are improved, and scientific support is provided for clinical surgery.

Description

Technical Field

[0001] This invention relates to the field of fracture surgery simulation planning technology, and in particular to a condylar fracture surgery simulation planning and training system based on personalized patient data. Background Technology

[0002] Condylar fractures, a common type of maxillofacial fracture, have complex anatomy and significant individual differences, requiring precise matching of the patient's individual bone morphology and fracture displacement characteristics for surgical treatment. Traditional surgical planning relies on two-dimensional imaging data, which struggles to fully represent the three-dimensional spatial relationship of the fracture area, leading to a high degree of subjectivity in surgical planning. Furthermore, the lack of targeted preoperative simulation training necessitates real-time adjustments to surgical strategies during the operation, increasing surgical risks and the probability of complications. As medical technology advances towards precision and personalization, three-dimensional modeling and simulation training based on real patient data are becoming crucial for improving the surgical outcomes of condylar fractures. An integrated system for rapidly acquiring personalized data and achieving precise simulation and efficient training has become a core technological direction for solving practical clinical problems.

[0003] Existing technologies have two prominent drawbacks: First, the connection between personalized data conversion and model application is insufficient. Although traditional methods can obtain fracture data from some patients, the data scanning efficiency is low, and it is difficult to directly match and replace parameters with the surgical training model after printing the 3D model. This makes it impossible to quickly build a simulation environment that fits the actual situation of the patient, resulting in deviations between the simulation plan and clinical reality. Second, there is a lack of systematicness in surgical simulation evaluation and preoperative training. Most existing simulation systems can only provide simulation analysis of a single plan and lack a multi-plan comparison and screening mechanism. Furthermore, preoperative training has not formed a standardized repetitive training and quantitative access system, making it difficult to ensure that doctors fully grasp the key points of operation before actual surgery and failing to effectively reduce surgical operation errors and uncertainties. Summary of the Invention

[0004] To overcome the shortcomings and deficiencies of existing technologies, this invention provides a surgical simulation planning and training system for condylar fractures based on personalized patient data.

[0005] The technical solution adopted in this invention is a surgical simulation planning and training system for condylar fractures based on personalized patient data, comprising: a rapid fracture data scanning module, a personalized model 3D printing module, a training model component replacement module, a multi-scheme simulation evaluation module, a preoperative repeated simulation training module, and a surgical execution admission determination module. The rapid fracture data scanning module collects three-dimensional spatial coordinate data of the patient's condylar fracture area using a scanning device. The personalized model 3D printing module receives the three-dimensional coordinate data output by the rapid fracture data scanning module, converts it into a printable format file, and then drives a 3D printing device to form a solid fracture model. The training model component replacement module... The module extracts the model feature parameters generated by the personalized model 3D printing module and replaces the parameter information of the corresponding parts in the preset patent training model. The multi-scheme simulation evaluation module calls the training model updated by the training model part replacement module to perform mechanical simulation and surgical path simulation and outputs the evaluation results. The preoperative repeated simulation training module drives the simulation training device to perform multiple repeated surgical operation simulations according to the optimal scheme output by the multi-scheme simulation evaluation module. The surgical execution admission judgment module performs quantitative analysis on the multiple simulation results of the preoperative repeated simulation training module and outputs the surgical execution permission signal. Each module performs real-time bidirectional data transmission and command interaction through the data interface.

[0006] Furthermore, the training model component replacement module includes: a feature parameter extraction unit, a component parameter matching unit, a model parameter update unit, and a replacement validity verification unit. The feature parameter extraction unit extracts geometric dimensions and mechanical properties related parameters of the fracture site from the three-dimensional data of the personalized 3D printed model using an image segmentation algorithm. The component parameter matching unit associates the extracted feature parameters with the parameter types of each component in the patent training model. The model parameter update unit replaces the default parameters of the original components in the training model with the matched personalized parameters and reconstructs the model data. The replacement validity verification unit performs data integrity checks on the training model after parameter replacement and outputs a verification pass signal.

[0007] Furthermore, the multi-scheme simulation evaluation module includes: a simulation scheme generation unit, a mechanical simulation calculation unit, a surgical path simulation unit, and an evaluation result output unit. The simulation scheme generation unit generates multiple surgical simulation schemes with different fracture reduction angles and fixation methods based on the replaced training model. The mechanical simulation calculation unit uses the finite element analysis method to numerically calculate the stress distribution and displacement changes of the fracture site under each simulation scheme. The surgical path simulation unit plans the surgical incision position and operation path according to the mechanical simulation results of each scheme and performs dynamic simulation. The evaluation result output unit comprehensively quantifies and scores the mechanical simulation data and the surgical path simulation results and outputs them in a sorted manner.

[0008] Furthermore, the preoperative repeated simulation training module includes: a training parameter setting unit, a simulation operation execution unit, an operation data recording unit, and a training effect feedback unit. The training parameter setting unit sets the operation force threshold and path deviation allowable range training parameters for the surgical simulation according to the optimal simulation scheme. The simulation operation execution unit drives the robotic arm or virtual operation interface to perform the surgical simulation operation according to the set training parameters. The operation data recording unit collects operation trajectory, force change, and time consumption data in real time during the simulation process. The training effect feedback unit compares the recorded operation data with the standard parameters and outputs deviation feedback information.

[0009] Furthermore, the data correction model used in the rapid fracture data scanning module is as follows: ,in, The corrected z-axis coordinates in three-dimensional space. These are the two-dimensional plane coordinate values. For coordinate correction coefficients, This is the system error compensation value for the scanning equipment.

[0010] Furthermore, the printing accuracy control model adopted by the personalized model 3D printing module is as follows: ,in, These are the dimensional accuracy values ​​for the 3D printed model. For the density of the printing material, For the print head movement speed, For printing ambient temperature, For printing layer thickness, The printhead tilt angle. This is the precision adjustment coefficient.

[0011] Furthermore, the multi-scheme simulation evaluation module adopts the following scheme evaluation model: ,in, This is the comprehensive evaluation value of the scheme. To evaluate the number of indicators, For the first The weighting coefficient of each indicator These are the distribution coefficients for stress, shear force, and displacement, respectively. For the first The stress value corresponding to each index, For the first The shear force value corresponding to each index For the first The displacement value corresponding to the item index, For time weighting coefficients, For the first Items over time The rate of change.

[0012] Furthermore, the training effect evaluation model used in the preoperative repeated simulation training module is as follows: ,in, This represents the average training effect value. To simulate the number of training sessions, For the first Accuracy of operation in each training session. For the first Path deviation value of the training iteration. For the first The force deviation value of each training session For the first The time efficiency coefficient of each training session. For the first The time required to complete the calibration operation during this training session. Standard completion time, This is the time deviation adjustment parameter.

[0013] Furthermore, the admission determination model adopted by the surgical execution admission determination module is as follows: ,in, This is the admission criteria value. The determination coefficient, This represents the average accuracy across multiple training runs. The stability coefficient of the training results. This is the maximum path deviation value. This represents the maximum force deviation value. To calibrate the number of operation items, For the first The number of times the calibration operation is qualified. For the first The total number of training iterations for the item calibration operation.

[0014] The condylar fracture surgery simulation planning and training system based on patient-personalized data also includes an admission decision subsystem, which includes:

[0015] The case operation model construction module transforms the reconstructed training model into a training model for repeatable simulated operations used for endoscopic operation training.

[0016] The critical surgical operation range setting module determines the safe range of critical operations such as repositioning angle, operation path, and operation force under the endoscopic field of vision and operation constraints, based on the optimal endoscopic surgical plan.

[0017] The repetitive simulation operation execution module performs multiple standardized endoscopic surgical simulation operations on the case operation model under the same field of view and instrument path constraints, and collects all operation data.

[0018] The operation consistency assessment module analyzes the convergence and volatility of operation trajectory, force and time parameters in multiple simulated operations to quantitatively assess the operator's operational stability.

[0019] The surgical admission decision module determines the admission criteria for endoscopic condylar fracture surgery and outputs a decision signal based on the evaluation results of the operation consistency assessment module and abnormal operation records.

[0020] Compared with the prior art, this application has at least one of the following beneficial effects:

[0021] This invention proposes a surgical simulation planning and training system for condylar fractures based on personalized patient data. Through rapid fracture data scanning and a personalized model 3D printing module, it efficiently acquires three-dimensional data of the patient's fracture area and creates a physical model, solving the problems of low data acquisition efficiency and the inability of two-dimensional images to represent spatial relationships in traditional methods. This provides precise data support for personalized treatment planning. A training model component replacement module achieves seamless integration between personalized parameters and the patented training model, overcoming the shortcomings of traditional models that are disconnected from the patient's actual condition, making the simulation environment more clinically relevant. A multi-scheme simulation evaluation module generates multiple reduction and fixation schemes and quantifies their scores, overcoming the limitations of existing technologies that lack comparison of single schemes and ensuring the optimality of the surgical plan. A preoperative repeated simulation training module provides standardized repetitive training and real-time data feedback, addressing the problems of insufficient targeting and lack of systematic quantitative evaluation in traditional preoperative training, helping doctors master the key operational points. A surgical execution admission judgment module establishes quantitative admission standards, effectively reducing surgical risks and operational errors. Each module interacts in real time through data interfaces, forming a closed-loop system of "data acquisition - model building - scheme optimization - simulation training - surgical access", which comprehensively improves the accuracy, safety and predictability of condylar fracture surgery. It effectively solves the core pain points of traditional surgical planning being highly subjective and insufficient preoperative preparation, and is especially suitable for surgical types such as endoscopic condylar fracture surgery that have high requirements for operation path dependence and stability.

[0022] This application focuses on the operational characteristics and core admission requirements of endoscopic condylar fracture surgery. It constructs a closed-loop system that extends from the construction of personalized case models, the setting of safety zones for key operations, and the execution of repeated simulated operations, to the quantitative assessment of operational consistency and the scientific decision-making for surgical admission. This system addresses the high surgical risks associated with endoscopic condylar fracture surgery due to limited field of vision, high constraints on the operation path, and stringent requirements for operational stability. Through standardized and quantitative preoperative simulated operation consistency assessment, a precise endoscopic surgical admission determination mechanism is established, further improving the accuracy, safety, and predictability of endoscopic condylar fracture surgery. Attached Figure Description

[0023] Figure 1 This is a diagram showing the system module composition of the present invention;

[0024] Figure 2 This is a flowchart of the system operation steps of the present invention. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] like Figure 1 As shown, the condylar fracture surgery simulation planning and training system based on patient-specific data includes: a rapid fracture data scanning module, a personalized model 3D printing module, a training model component replacement module, a multi-scheme simulation evaluation module, a preoperative repeated simulation training module, and a surgical execution admission determination module.

[0027] The rapid fracture data scanning module acquires three-dimensional spatial coordinate data of the patient's condylar fracture area using technologies such as cone-beam computed tomography (CBCT), multi-slice spiral CT, or magnetic resonance imaging. The personalized model 3D printing module receives the three-dimensional coordinate data output by the rapid fracture data scanning module, converts it into a printable format file, and then drives the 3D printing equipment to form a solid fracture model. The training model component replacement module extracts the model feature parameters generated by the personalized model 3D printing module and replaces the parameter information of the corresponding parts in the preset patented training model. The multi-scheme simulation evaluation module calls the training model updated by the training model component replacement module to perform mechanical simulation and surgical path simulation and outputs the evaluation results. The preoperative repeated simulation training module drives the simulation training equipment to perform multiple repeated surgical operation simulations based on the optimal scheme output by the multi-scheme simulation evaluation module. The surgical execution admission judgment module performs quantitative analysis on the multiple simulation results of the preoperative repeated simulation training module and outputs a surgical execution permission signal. All modules perform real-time bidirectional data transmission and command interaction through a data interface.

[0028] The rapid fracture data scanning module collects key information such as fracture line location, bone fragment displacement distance, and bone surface curvature. The data transmission rate is 100Mbps, and the data is transmitted to subsequent modules in real time via Ethernet interface. At the same time, the CRC32 check algorithm is used to ensure the integrity of data transmission. The data verification time for each frame is no more than 0.005 seconds, which effectively avoids the loss or distortion of coordinate data and provides high-fidelity raw data support for subsequent model construction.

[0029] After receiving the 3D coordinate data output from the fracture data rapid scanning module, the personalized model 3D printing module first converts the original coordinate data into a standard printable file using an STL format conversion algorithm. During the conversion, triangular facet subdivision technology is employed, with facet side lengths controlled between 0.05 and 0.1 mm to ensure a smooth model surface. Subsequently, the module performs layer processing on the STL file, setting the layer thickness to 0.02 mm. Simultaneously, the layer density is dynamically adjusted based on the structural complexity of the fracture site, automatically reducing the layer thickness to 0.01 mm in complex areas. The printing equipment uses fused deposition modeling (FDM) with a 0.4 mm nozzle diameter. Medical-grade polylactic acid (PLA) resin is used, with the material's melting temperature controlled between 180 and 200 degrees Celsius, and the printing platform temperature maintained at 60 degrees Celsius to prevent model deformation due to material cooling and contraction. During printing, the equipment monitors the nozzle movement speed in real time, ranging from 30 to 80 mm / s, dynamically adjusting it according to the model structure. Simultaneously, an infrared thermometer provides real-time feedback on the printing area temperature, automatically adjusting the heating power when the temperature deviation exceeds ±5 degrees Celsius. The printed physical model has a size error of no more than ±0.1 mm, which can accurately reproduce the anatomical structure and displacement of the patient's condylar fracture site.

[0030] The training model component replacement module first extracts key feature parameters from the 3D data of the personalized 3D printed model using an image segmentation algorithm combining edge detection and region growing. These parameters include geometric dimensions such as the length, width, and thickness of the fracture site, as well as mechanical properties such as elastic modulus and Poisson's ratio, achieving an extraction accuracy of 0.001 mm and 0.01 GPa, respectively. Subsequently, a parameter type matching algorithm compares the extracted personalized parameters with a pre-defined component parameter library of the patented training model. This library contains over 1000 different component parameter templates. The matching process employs a cosine similarity algorithm with a similarity threshold of 0.95 to ensure accurate parameter matching. After parameter matching, a model reconstruction algorithm replaces the default parameters of the original components in the training model with personalized parameters. Finite element mesh generation technology is used during reconstruction, with mesh element sizes ranging from 0.1 to 0.5 mm to ensure the accuracy of the model's mechanical property simulation. After the replacement is completed, the module performs a data integrity check on the updated training model. The check indicators include parameter missing rate and mesh quality pass rate. When the parameter missing rate is less than 0.1% and the mesh quality pass rate is higher than 98%, the check is considered to have passed. A check pass signal is generated and transmitted to the next module to ensure that the replaced training model can accurately reflect the patient's personalized fracture characteristics.

[0031] The multi-scheme simulation and evaluation module calls the updated training model from the training model component replacement module. First, based on key parameters such as fracture reduction angle, fixation method, and incision location, a scheme generation algorithm generates 20 to 50 different surgical simulation schemes. The reduction angle is adjusted in 1-degree increments, and fixation methods include various types such as plate fixation and screw fixation. Subsequently, finite element analysis is used to perform mechanical simulation calculations on each scheme. The load range during simulation is set to 0 to 500 N, and the loading rate is 10 N / s. The stress distribution and displacement changes at the fracture site are analyzed, with stress calculation accuracy reaching 0.1 MPa and displacement calculation accuracy reaching 0.001 mm. Simultaneously, a path planning algorithm simulates the surgical operation path for each scheme. The path planning uses the A* algorithm, with a path deviation allowable range of ±0.5 mm, dynamically simulating key operational steps such as surgical incision, bone fragment reduction, and fixation device implantation. After the simulation is completed, a comprehensive evaluation algorithm combining the analytic hierarchy process (AHP) and the entropy weight method is used to quantitatively score each scheme based on 10 evaluation indicators, including mechanical stability, ease of operation, and degree of damage. The scoring range is from 0 to 100 points. Based on the scoring results, all schemes are ranked, the optimal scheme with the highest score is selected, and an evaluation report is output. The evaluation report includes mechanical parameter data, path simulation animation, and comprehensive score ranking for each scheme.

[0032] The preoperative repeated simulation training module sets the training parameters for the surgical simulation based on the optimal scheme output by the multi-scheme simulation evaluation module through parameter configuration algorithms. These parameters include an operational force threshold range of 5 to 50 N, an allowable path deviation range of ±0.3 mm, and an operation duration limit of 30 to 60 minutes. Subsequently, the robotic arm or virtual operating interface is driven to perform the surgical simulation operation. The robotic arm's positioning accuracy reaches 0.01 mm, and its repeatability accuracy reaches 0.005 mm. The virtual operating interface has a display resolution of 1920×1080 pixels and a refresh rate of 60 frames / second. During the simulation operation, displacement sensors, force sensors, and other devices collect data information such as operation trajectory, force changes, and time consumption in real time at a data acquisition frequency of 100 Hz to ensure complete recording of operation details. After the data acquisition is completed, the recorded operation data is compared with preset standard parameters. The standard parameters are derived from a large amount of clinical surgical data. The comparison process uses a mean square error algorithm to calculate the operation deviation. When the deviation exceeds the allowable range, an audible and visual alarm device outputs deviation feedback information to prompt the operator to adjust the operation method. The module supports continuous and repeated simulation training, with the number of training sessions set from 10 to 50. After each training session, a training data report is automatically generated to provide operators with targeted improvement guidance.

[0033] The surgical execution admission judgment module receives multiple simulation training data transmitted from the preoperative repeated simulation training module. First, it standardizes the raw training data using a data preprocessing algorithm to eliminate differences in data units. Then, it uses multivariate statistical analysis to quantitatively analyze the training data, with 15 key indicators including operational accuracy, mean path deviation, force control precision, and operation duration stability. Operational accuracy must reach 95% or higher, mean path deviation must be less than 0.2 mm, force control precision must be ±1N, and the coefficient of variation of operation duration must be less than 5%. During the analysis, a weighted summation algorithm is used to calculate the comprehensive admission evaluation score. The weights of each indicator were determined by 10 senior clinicians based on the Delphi method. The comprehensive score is out of 100 points, and the admission threshold is set at 85 points. When the overall score reaches or exceeds the admission threshold, the training is deemed successful, and the module outputs a surgical execution permission signal through the data interface. The permission signal is transmitted in an encrypted manner to ensure information security. When the overall score is lower than the admission threshold, the training is deemed unsuccessful, and the module outputs a retraining instruction. At the same time, it provides feedback on the specific indicators that were not met and suggestions for improvement until the training results meet the admission requirements, ensuring that doctors have sufficient operational proficiency and accuracy before actual surgery.

[0034] Preferably, the training model component replacement module includes: a feature parameter extraction unit, a component parameter matching unit, a model parameter update unit, and a replacement validity verification unit. The feature parameter extraction unit extracts geometric dimensions and mechanical properties of the fracture site from the three-dimensional data of the personalized 3D printed model using an image segmentation algorithm. The component parameter matching unit associates the extracted feature parameters with the parameter types of each component in the patented training model. The model parameter update unit replaces the default parameters of the original components in the training model with the matched personalized parameters and reconstructs the model data. The replacement validity verification unit performs data integrity checks on the training model after parameter replacement and outputs a verification pass signal.

[0035] Specifically, the feature parameter extraction unit of the training model component replacement module employs a combination of adaptive threshold edge detection and region growing algorithms to accurately extract key parameters from the 3D point cloud data of the personalized 3D printed model. Geometric parameters include the length, width, and thickness of fracture fragments, as well as the width of the fracture gap, with measurement accuracy controlled to 0.001 mm. Mechanical property parameters include elastic modulus, Poisson's ratio, and shear modulus, with detection accuracy reaching 0.01 GPa. The extraction process utilizes multi-algorithm cross-validation to ensure parameter authenticity. The component parameter matching unit incorporates a standardized parameter type database, including over 50 parameter types across three main categories: geometric, mechanical, and structural. Through a combination of semantic matching and feature vector comparison, the extracted personalized parameters are correlated one-to-one with the parameter types of each component in the patented training model. The matching response time is no more than 0.5 seconds, and the matching accuracy is higher than 99%. The model parameter update unit employs modular data reconstruction technology, replacing the default parameters of the original components in the training model with matched personalized parameters. During the replacement process, the model data is updated synchronously in real time. The reconstructed model data resolution remains at 0.01 mm, and the data transmission latency is less than 10 milliseconds, ensuring that the model parameters are highly consistent with the patient's actual condition. The replacement validity verification unit performs three core checks: data integrity detection, parameter logical consistency verification, and model topology verification. The parameter missing rate must be controlled within 0.1%, the number of parameter logical conflicts must be zero, and the model topology connectivity must reach 100%. Upon successful verification, a verification pass signal is generated, including the verification results and parameter details, providing a reliable model foundation for subsequent simulation evaluations.

[0036] Preferably, the multi-scheme simulation evaluation module includes: a simulation scheme generation unit, a mechanical simulation calculation unit, a surgical path simulation unit, and an evaluation result output unit. The simulation scheme generation unit generates multiple surgical simulation schemes with different fracture reduction angles and fixation methods based on the replaced training model. The mechanical simulation calculation unit uses the finite element analysis method to numerically calculate the stress distribution and displacement changes of the fracture site under each simulation scheme. The surgical path simulation unit plans the surgical incision position and operation path according to the mechanical simulation results of each scheme and performs dynamic simulation. The evaluation result output unit comprehensively quantifies and scores the mechanical simulation data and the surgical path simulation results and outputs them in a sorted order.

[0037] Specifically, the simulation scheme generation unit of the multi-scheme simulation evaluation module is based on the replaced training model. It takes fracture reduction angle, fixation device type, surgical incision location, and operation path planning as core variables. The reduction angle is adjusted in 1-degree increments within the range of -15 degrees to 15 degrees. The fixation device types include more than 20 types such as plates, screws, and intramedullary nails of different specifications. The incision location provides 5 to 8 clinically commonly used alternative areas. Through orthogonal experimental design, 20 to 50 surgical simulation schemes with significant differences are generated. The scheme generation time does not exceed 3 minutes, ensuring that the schemes cover the main clinical possibilities. The mechanical simulation unit employs explicit finite element analysis, dividing the data into tetrahedral mesh elements with a mesh size ranging from 0.1 to 0.5 mm. The mesh quality pass rate exceeds 98%. During the simulation, the applied load simulates the contraction force and biting force of the masticatory muscles, ranging from 0 to 500 N, with a loading rate of 10 N / s. It calculates mechanical parameters such as stress distribution, strain change, and displacement at the fracture site, achieving a stress calculation accuracy of 0.1 MPa and a displacement calculation accuracy of 0.001 mm. Simulation results are output in real-time as contour maps and curves. The surgical path simulation unit uses the A* path planning algorithm combined with dynamic obstacle avoidance technology to plan the paths for key operations such as surgical incision, bone fragment repositioning, fixation device implantation, and postoperative fixation. The allowable path deviation range is set to ±0.5 mm, and the path length optimization rate exceeds 10%. The entire surgical operation process is recreated through three-dimensional dynamic simulation technology, maintaining a simulation frame rate of 30 frames / second, and achieving a visualization level of 0.1 mm for operational details. The evaluation results output unit establishes a comprehensive evaluation system including 10 primary evaluation indicators and 30 secondary evaluation indicators, such as mechanical stability, ease of operation, degree of trauma, and prediction of post-treatment effect. The weights of the indicators are determined by a combination of the analytic hierarchy process (AHP) and the entropy weight method. Each scheme is quantitatively scored, with a score range of 0 to 100. The evaluation results are output in descending order of scores. At the same time, an evaluation report including mechanical data, path animation, and detailed scoring of each scheme is generated to provide data support for the selection of the optimal scheme.

[0038] Preferably, the preoperative repeated simulation training module includes: a training parameter setting unit, a simulation operation execution unit, an operation data recording unit, and a training effect feedback unit. The training parameter setting unit sets the operation force threshold and allowable path deviation range training parameters for the surgical simulation according to the optimal simulation scheme. The simulation operation execution unit drives the robotic arm or virtual operation interface to perform the surgical simulation operation according to the set training parameters. The operation data recording unit collects operation trajectory, force change, and time consumption data in real time during the simulation process. The training effect feedback unit compares the recorded operation data with the standard parameters and outputs deviation feedback information.

[0039] Specifically, the training parameter setting unit of the preoperative repeated simulation training module sets multi-dimensional training parameters based on the optimal scheme output by the multi-scheme simulation evaluation module, combined with clinical surgical operation standards and the surgeon's skill level. The operation force threshold range is 5 to 50N, subdivided into 5N gradients. The allowable path deviation range is ±0.3 mm, the operation time is limited to 30 to 60 minutes, and the deviation in the completion time of key operations does not exceed 30 seconds. Simultaneously, three major assessment indicators are set: operation proficiency, accuracy, and stability. The quantitative standards for these indicators are based on statistical data from over 1000 successful clinical surgeries, ensuring the scientific validity and practicality of the training parameters. The simulation operation execution unit supports both physical robotic arm simulation and virtual simulation modes. The robotic arm uses a six-degree-of-freedom collaborative robot with a positioning accuracy of 0.01 mm and a repeatability of 0.005 mm. The virtual operation interface uses virtual reality technology with a display resolution of 1920×1080 pixels, a refresh rate of 60 frames per second, and an operation force feedback accuracy of 0.1N. The two modes can be seamlessly switched to meet the needs of different training scenarios. The operation data recording unit integrates multiple data acquisition devices such as displacement sensors, force sensors, and time counters, with a data acquisition frequency of 100Hz. It collects data in real time, including operation trajectory coordinates, operation force magnitude, operation time nodes, and completion status of key actions. The data storage format adopts a standardized medical data format, and the data storage volume of a single training process does not exceed 100MB, ensuring data integrity and traceability. The training effect feedback unit uses a mean square error algorithm to calculate the deviation value between the operation data and standard parameters. When the path deviation exceeds ±0.3 mm, the force deviation exceeds ±1N, or the time deviation exceeds 30 seconds, a sound and light alarm device provides real-time feedback. At the same time, it generates a training feedback report including the deviation location, deviation value, and improvement suggestions. The report uses a combination of charts and graphs to visually display training shortcomings, helping operators to adjust their operation methods in a targeted manner and improve training effectiveness.

[0040] Preferably, the data correction model used in the rapid fracture data scanning module is: ,in, The corrected z-axis coordinates in three-dimensional space. These are the two-dimensional plane coordinate values. For coordinate correction coefficients, This is the system error compensation value for the scanning equipment.

[0041] Specifically, the data correction model for the rapid fracture data scanning module is applied to the raw data processing stage of the module. Its function is to correct coordinate deviations caused by environmental interference and mechanical errors in the scanning equipment, ensuring the accuracy of the three-dimensional spatial coordinate data. During implementation, the two-dimensional planar coordinates and initial z-axis coordinates of the patient's condylar fracture area are first acquired using the scanning equipment. The coordinate acquisition range covers the area from 0 to 20 cm on the x-axis and 0 to 15 cm on the y-axis, with a data sampling interval of 0.001 cm. The coordinate correction coefficients in the model are calibrated through 1000 sets of standard model scanning experiments, with values ​​ranging from 0.001 to 0.005 for the first coefficient, 0.002 to 0.006 for the second, 0.1 to 0.3 for the third, 0.5 to 1.2 for the fourth, and 0.3 to 0.8 for the fifth. The system error compensation value is determined based on the factory calibration data of the scanning equipment and actual wear and tear, ranging from 0.0001 to 0.0005 cm. The initial z-axis coordinates are corrected by model calculation. The correction process adopts a point-by-point iterative calculation method. The time for a single coordinate correction is no more than 0.001 seconds. The error of the corrected data is controlled within 0.001 cm, which effectively eliminates the deviation caused by factors such as temperature changes and vibration during the scanning process, and provides high-fidelity coordinate data support for subsequent personalized model 3D printing.

[0042] Preferably, the printing accuracy control model used in the personalized model 3D printing module is: ,in, These are the dimensional accuracy values ​​for the 3D printed model. For the density of the printing material, For the print head movement speed, For printing ambient temperature, For printing layer thickness, The printhead tilt angle. This is the precision adjustment coefficient.

[0043] Specifically, the personalized model 3D printing module printing accuracy control model is used to optimize the printing parameters of the personalized model 3D printing module. By quantifying the correlation between various influencing factors and printing accuracy, the printing parameters are dynamically adjusted to improve the dimensional accuracy of the solid model. During implementation, key parameters such as printing material density, nozzle movement speed, ambient temperature, printing layer thickness, and nozzle tilt angle are collected. The material density measurement accuracy is 0.01 g / cm³, the real-time monitoring range of nozzle movement speed is 30 to 80 mm / s, the ambient temperature is controlled between 20 and 25 degrees Celsius with fluctuations not exceeding ±1 degree Celsius, the printing layer thickness can be adjusted between 0.01 and 0.05 mm, and the nozzle tilt angle is fixed at 0 to 5 degrees. The accuracy adjustment coefficients in the model are determined through multi-factor orthogonal experiments. The first three coefficients range from 0.01 to 0.05, and the latter two coefficients range from 0.8 to 1.5. During the printing process, the model receives real-time monitoring data of various parameters and calculates the current printing accuracy prediction value. When the prediction value exceeds the allowable range of 0.005 to 0.01 mm, the nozzle moving speed and heating power are automatically adjusted with adjustment steps of 1 mm / s and 5 watts, respectively, to ensure that the printed personalized fracture model can accurately reproduce the anatomical structure of the patient's fracture site with a dimensional error of no more than ±0.1 mm.

[0044] Preferably, the multi-scheme simulation evaluation module uses the following scheme evaluation model: ,in, This is the comprehensive evaluation value of the scheme. To evaluate the number of indicators, For the first The weighting coefficient of each indicator These are the distribution coefficients for stress, shear force, and displacement, respectively. For the first The stress value corresponding to each index, For the first The shear force value corresponding to each index For the first The displacement value corresponding to the item index, For time weighting coefficients, For the first Items over time The rate of change.

[0045] Specifically, the multi-scheme simulation evaluation module's scheme evaluation model is applied to the scheme selection stage of the multi-scheme simulation evaluation module. By comprehensively quantifying mechanical properties and surgical operation characteristics, it achieves a scientific ranking of different surgical simulation schemes. During implementation, the number of evaluation indicators is set to 10, including mechanical indicators such as stress, shear force, and displacement, and surgical-related indicators such as operational difficulty and wound area. The weight coefficients of each indicator are determined by five orthopedic experts using the Delphi method, with values ​​ranging from 0.05 to 0.2. The mechanical indicator allocation coefficients are set according to the safety priority of clinical surgery: stress allocation coefficient 0.4 to 0.6, shear force allocation coefficient 0.2 to 0.3, displacement allocation coefficient 0.1 to 0.2, and time weight coefficient set to 0.1 to 0.3 based on the urgency of the surgical operation. During model calculation, the measured values ​​of mechanical parameters and the rate of change data for each scheme are first collected. The measurement accuracy of mechanical parameters is 0.01 MPa, 0.01 MPa, and 0.001 mm, and the sampling interval for the rate of change is 0.1 seconds. Then, the comprehensive evaluation value of each scheme is obtained through weighted summation and integration. The evaluation score ranges from 0 to 100. Schemes with a score higher than 85 are included in the optimal scheme candidate set. The model calculation time is no more than 0.5 seconds per scheme, ensuring efficient completion of multi-scheme comparison and screening.

[0046] Preferably, the training effect evaluation model used in the preoperative repeated simulation training module is: ,in, This represents the average training effect value. To simulate the number of training sessions, For the first Accuracy of operation in each training session. For the first Path deviation value of the training iteration. For the first The force deviation value of each training session For the first The time efficiency coefficient of each training session. For the first The time required to complete the calibration operation during this training session. Standard completion time, This is the time deviation adjustment parameter.

[0047] Specifically, the preoperative repeated simulation training module training effect evaluation model is used to quantitatively evaluate the training effect of the preoperative repeated simulation training module. By comprehensively analyzing the operational data from multiple training sessions, it objectively reflects the surgeon's proficiency. During implementation, the number of simulation training sessions is set to 10 to 50. After each training session, data such as operational accuracy, path deviation, force deviation, time efficiency coefficient, and completion time of key operations are collected. The statistical precision for operational accuracy is 0.1%, the measurement precision for path and force deviation is 0.01 mm and 0.1 N, respectively, and the time efficiency coefficient is determined based on the ratio of operation time to standard time, ranging from 0.8 to 1.2. The standard completion time of key operations is set based on the average operation time of clinically skilled physicians, ranging from 5 to 15 minutes. The time deviation adjustment parameter in the model is set to 2 to 5. The average training effect value is calculated by averaging the data from multiple training sessions, with the effect value ranging from 0 to 100 points. A score of 80 or above is considered a passing grade. The model calculation process uses a weighted average and exponential compensation algorithm to highlight the weight of later training data, effectively reflecting the surgeon's skill improvement trend and providing a quantitative basis for preoperative training effect evaluation.

[0048] Preferably, the admission determination model adopted by the surgical execution admission determination module is: ,in, This is the admission criteria value. The determination coefficient, This represents the average accuracy across multiple training runs. The stability coefficient of the training results. This is the maximum path deviation value. This represents the maximum force deviation value. To calibrate the number of operation items, For the first The number of times the calibration operation is qualified. For the first The total number of training iterations for the item calibration operation.

[0049] Specifically, the surgical execution admission judgment module's admission judgment model is used for the admission qualification review of the surgical execution admission judgment module. It generates objective admission judgment results by integrating key indicator data from multiple simulation training sessions. During implementation, the mean accuracy and stability coefficient of multiple training sessions are first calculated. The mean accuracy is the arithmetic mean of the accuracy of all training operations, and the stability coefficient is obtained by calculating the standard deviation of the accuracy of each training session, requiring it to be below 5%. The maximum path deviation and maximum force deviation are taken as the extreme values ​​of all training data, and must be controlled within 0.3 mm and 1 N, respectively. The number of key operation items is set to 8 to 12, including core steps such as incision positioning, bone block repositioning, and fixation implantation. The number of qualified attempts for each key operation and the total number of training sessions are statistically analyzed in real time. The judgment coefficients in the model are calibrated using clinical surgical risk assessment data; the first two coefficients are set to 0.3 to 0.5, and the third coefficient is set to 0.8 to 1.2. The admission criteria calculated by the model range from 0 to 100 points, and the threshold is set at 85 points. When the criteria value reaches or exceeds the threshold, a surgical execution permission signal is output; otherwise, a retraining instruction is returned to ensure that actual surgery can only be performed when the training effect meets the standard.

[0050] like Figure 2 As shown, the condylar fracture surgery simulation planning and training system based on personalized patient data operates in the following steps: First, a rapid fracture data scanning module performs a comprehensive scan of the patient's condylar fracture area, collecting 3D raw data including fracture line location and bone fragment displacement, and transmitting it to a data processing terminal. Second, a personalized model 3D printing module performs format conversion and layer processing on the received 3D raw data, generating slice files that meet the requirements of 3D printing equipment, driving the printing equipment to print a personalized fracture entity model using biocompatible materials. Third, a training model component replacement module obtains the calibration structural parameters of the 3D printed model through a parameter extraction algorithm, compares and matches them with the component parameter library of the patented training model, and replaces the incorrectly matched personalized parameters in the training model. The first step involves reconstructing the model based on the original parameters of the components. The second step involves a multi-scheme simulation evaluation module that, based on the reconstructed training model, sets different reset parameters and fixed schemes, performs mechanical performance analysis and surgical procedure simulation through simulation algorithms, and quantifies and scores each scheme according to preset evaluation indicators to select the optimal scheme. The third step involves a preoperative repeated simulation training module that loads the parameter configuration of the optimal scheme, drives the simulation training platform to perform multiple surgical simulation operations, records the path trajectory, force control, and operation time data of each operation in real time, and generates a training report. The fourth step involves a surgical execution admission judgment module that compares the data analysis results of multiple simulation trainings with preset admission standards. When all indicators meet the requirements, a surgical execution permission signal is output. If any indicators are not met, the process returns to the fourth step to regenerate the simulation scheme.

[0051] This condylar fracture surgery simulation planning and training system, based on personalized patient data, features several key components. The rapid fracture data scanning module efficiently collects three-dimensional spatial data of the patient's condylar fracture area, providing a more comprehensive and accurate representation of the fracture line location and bone fragment displacement characteristics compared to traditional two-dimensional imaging. The personalized model 3D printing module directly converts the scanned data into a physical model, providing an intuitive physical medium for subsequent simulation and training. The training model component replacement module precisely connects personalized parameters with the patented training model, ensuring the simulation environment perfectly matches the patient's actual condition. The multi-scheme simulation evaluation module generates multiple surgical plans and performs quantitative evaluations, ensuring the scientific validity and optimality of each plan. The preoperative repeated simulation training module provides standardized and repeatable training scenarios, helping doctors master key operational points. The surgical execution access determination module constructs an access mechanism through quantitative analysis, providing dual protection for surgical safety.

[0052] This system combines rapid scanning with 3D printing technology to solve the problems of low data acquisition efficiency and unintuitive spatial relationship presentation in traditional methods, laying a solid data foundation for personalized treatment planning. The component replacement function of the training model compensates for the disconnect between traditional training models and actual patient conditions, making simulation results more clinically valuable. The multi-plan simulation evaluation mechanism overcomes the limitations of single-plan comparisons, using quantitative scoring to select the optimal plan and improve the scientific rigor of surgical planning. Standardized preoperative repeated training and effect feedback address the shortcomings of traditional preoperative training, such as weak targeting and lack of systematic evaluation, effectively reducing surgical errors. The surgical execution admission judgment module uses quantitative indicators to control the surgical entry threshold, effectively reducing the risks caused by insufficient preoperative preparation in traditional surgery and comprehensively improving the precision and safety of condylar fracture surgery.

[0053] The condylar fracture surgery simulation planning and training system based on patient-personally-owned data in this application also includes an admission decision subsystem. This subsystem assists in determining whether the operator meets the requirements for entering the actual surgical stage, rather than replacing the final decision of the clinician. It includes a case operation model construction module, a surgical critical operation range setting module, a repeated simulation operation execution module, an operation consistency assessment module, and a surgical execution admission decision module, wherein:

[0054] The case operation model construction module receives personalized 3D coordinate data of patient fractures from the original module, along with reconstructed training model data. It integrates refined scanning data of the condylar anatomy specific to endoscopic surgery, and adapts the basic model to the endoscopic field of view and operating instruments. This constructs a virtual training model suitable for minimally invasive endoscopic procedures, resolving the mismatch between the original basic model and the endoscopic surgical scenario. The model accurately reproduces the anatomical field of view and operational constraints of condylar fractures under endoscopy, achieving a model fidelity of over 99%, with visualization accuracy of operational details down to 0.1 mm. This module standardizes the geometric structure, field of view parameters, and instrument movement paths of the modified model, ensuring parameter consistency during multiple calls and repeated simulations. This provides a highly accurate and consistent standardized training platform for subsequent repetitive simulations, completing model repeatability calibration. Parameter deviations across multiple calls do not exceed ±0.01 mm, ensuring data comparability and result validity in subsequent repetitive simulations and avoiding training and evaluation distortions caused by model deviations. Simultaneously generate a visual model of the fracture site under endoscopic vision, a kinematic model of endoscopic instruments, and a collision detection model of the collaborative operation of two instruments (holding the endoscope and operating), thus recreating the real operation scenario of limited vision and instrument coordination in endoscopic surgery.

[0055] The critical surgical operation range setting module, based on the optimal endoscopic surgical plan selected by the original multi-scheme simulation and evaluation module, accurately extracts the core critical operations of endoscopic condylar fracture surgery, including fracture fragment reduction angle, endoscopic instrument movement path, bone fragment reduction operation force, and fixation device implantation force / angle. Combining the endoscopic field of view, instrument operation space limitations (narrow space at the posterior border of the mandibular ramus), and obstacle avoidance requirements for important anatomical structures such as blood vessels / nerves around the condyle, the module calculates the upper and lower safety thresholds of each critical operation through finite element analysis and A* path planning algorithm, forming quantitative constraint standards. The safety range parameters of each critical operation are associated and stored with the case operation model, supporting dynamic threshold adjustment according to endoscope model, instrument specifications, and patient fracture classification to adapt to personalized surgical needs.

[0056] The repetitive simulation operation execution module loads the repeatable simulation operation training model generated by the case operation model construction module, fixing endoscopic field parameters, instrument path constraint parameters, and force feedback accuracy of the operating equipment to ensure that the environment for multiple simulation operations is completely consistent. Based on the optimal endoscopic surgical plan, it performs 10-50 standardized and repeatable endoscopic condylar fracture surgery simulation operations, closely matching the entire clinical surgical process. Using a high-frequency acquisition frequency of over 100Hz, it records quantitative data such as the operation trajectory, reduction angle, operation force, and time consumption of each step in real time for each simulation operation. If key parameters exceed the safe range in a single operation, an audible and visual alarm is immediately issued and the operation is marked as abnormal, recording the abnormal parameters and the occurrence point. The real-time abnormal marking function can promptly remind the operator of operational deviations, helping the operator quickly identify their own operational problems, improving the pertinence and efficiency of preoperative simulation training, and retaining abnormal operation records for subsequent admission decisions. The repetitive simulation operation execution module ensures that multiple simulation operations are performed in a completely consistent environment, eliminating the interference of environmental variables on the operation data, ensuring that the collected operation data sets are highly comparable, and providing an effective data foundation for subsequent operation consistency assessment.

[0057] The operation consistency assessment module receives multiple sets of operation data collected by the repeated simulation operation execution module, performs standardized preprocessing to eliminate differences in data units, remove extreme abnormal data caused by non-model / equipment issues, and retains valid data for consistency analysis. It analyzes the convergence (the degree to which parameters converge towards the optimal value across multiple operations) and volatility (the degree of dispersion of parameters across multiple operations) of parameters across four dimensions: operation trajectory, operation force, reset angle, and operation time, generating quantitative assessment indicators for each dimension. Then, it uses the analytic hierarchy process (AHP) to determine the weight of each assessment dimension, performs a quantitative comprehensive score for the compliance of each dimension, and determines whether the operation consistency meets the standards. Simultaneously, it generates an operation consistency assessment report, including quantitative data for each dimension, a comprehensive score, the compliance determination, and details of abnormal operations.

[0058] The surgical execution admission decision module receives the comprehensive score and evaluation report output by the operation consistency assessment module, as well as the abnormal operation data recorded by the repeated simulation operation execution module, and integrates them to form a complete admission decision basis. It implements a dual judgment standard, neither of which can be missing: ① The comprehensive operation consistency score is ≥85 points and all dimensions meet the standard; ② In all repeated simulation operations, no key operation parameters exceed the safety range. Even if the overall consistency meets the standard, a single abnormality will not grant admission.

[0059] Based on the aforementioned dual-standard judgment results, an endoscopic surgery execution permission signal or admission rejection signal is output. If rejected, the reason for non-compliance is clearly explained, such as insufficient consistency score or abnormal operation. Operators are then guided to conduct targeted intensive training, forming a closed loop of training-assessment-feedback-retraining. This replaces the traditional surgical admission judgment based on subjective experience, achieving quantitative and standardized decision-making for endoscopic surgery admission, ensuring that only physicians with satisfactory operational stability and no operational risks can perform actual surgeries. This minimizes the risks of endoscopic surgery: satisfactory operational consistency ensures that physicians possess stable endoscopic operation capabilities, and the absence of abnormal operations ensures that physicians strictly adhere to operational safety constraints. This dual protection effectively reduces the probability of intraoperative operational errors and improves the safety and success rate of endoscopic condylar fracture surgery.

[0060] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" 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 mechanical connection or an electrical 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 will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0061] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A surgical simulation planning and training system for condylar fractures based on personalized patient data, characterized in that: include: The module includes rapid fracture data scanning, personalized model 3D printing, training model component replacement, multi-scheme simulation evaluation, preoperative repeated simulation training, and surgical execution admission determination. The rapid fracture data scanning module collects three-dimensional spatial coordinate data of the patient's condylar fracture area through a scanning device. The personalized model 3D printing module receives the three-dimensional coordinate data output by the rapid fracture data scanning module, converts it into a printable format file, and then drives the 3D printing device to form a solid fracture model. The training model component replacement module extracts the model feature parameters generated by the personalized model 3D printing module and replaces the parameter information of the corresponding parts in the preset patented training model. The multi-scheme simulation evaluation module calls the training model updated by the training model component replacement module to perform mechanical simulation and surgical path simulation and outputs the evaluation results. The preoperative repeated simulation training module drives the simulation training device to perform multiple repeated surgical operation simulations according to the optimal scheme output by the multi-scheme simulation evaluation module. The surgical execution admission judgment module performs quantitative analysis on the multiple simulation results of the preoperative repeated simulation training module and outputs a surgical execution permission signal. All modules perform real-time bidirectional data transmission and command interaction through a data interface.

2. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The training model component replacement module includes: a feature parameter extraction unit, a component parameter matching unit, a model parameter update unit, and a replacement validity verification unit; The feature parameter extraction unit extracts geometric dimensions and mechanical properties of fracture sites from the three-dimensional data of the personalized 3D printed model using an image segmentation algorithm. The component parameter matching unit associates the extracted feature parameters with the parameter types of each component in the patent training model. The model parameter update unit replaces the default parameters of the original components in the training model with the matched personalized parameters and reconstructs the model data. The replacement validity verification unit performs data integrity detection on the training model after parameter replacement and outputs a verification pass signal.

3. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The multi-scheme simulation and evaluation module includes: a simulation scheme generation unit, a mechanical simulation calculation unit, a surgical path simulation unit, and an evaluation result output unit; The simulation scheme generation unit generates various surgical simulation schemes with different fracture reduction angles and fixation methods based on the replaced training model. The mechanical simulation calculation unit uses the finite element analysis method to numerically calculate the stress distribution and displacement changes of the fracture site under each simulation scheme. The surgical path simulation unit plans the surgical incision position and operation path according to the mechanical simulation results of each scheme and performs dynamic simulation. The evaluation result output unit comprehensively quantifies and scores the mechanical simulation data and the surgical path simulation results and outputs them in a sorted manner.

4. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The preoperative repeated simulation training module includes: a training parameter setting unit, a simulation operation execution unit, an operation data recording unit, and a training effect feedback unit; The training parameter setting unit sets the operation force threshold and path deviation allowable range training parameters for surgical simulation according to the optimal simulation scheme. The simulation operation execution unit drives the robotic arm or virtual operation interface to perform surgical simulation operations according to the set training parameters. The operation data recording unit collects operation trajectory, force change, and time consumption data in real time during the simulation process. The training effect feedback unit compares the recorded operation data with the standard parameters and outputs deviation feedback information.

5. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The data correction model used in the rapid fracture data scanning module is as follows: ， in, The corrected z-axis coordinates in three-dimensional space. These are the two-dimensional plane coordinate values. For coordinate correction coefficients, This is the system error compensation value for the scanning equipment.

6. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The personalized model 3D printing module uses the following printing accuracy control model: ， in, These are the dimensional accuracy values ​​for the 3D printed model. For the density of the printing material, For the print head movement speed, For printing ambient temperature, For printing layer thickness, The printhead tilt angle. This is the precision adjustment coefficient.

7. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The multi-scheme simulation and evaluation module uses the following scheme evaluation model: ， in, This is the comprehensive evaluation value of the scheme. To evaluate the number of indicators, For the first The weighting coefficient of each indicator These are the distribution coefficients for stress, shear force, and displacement, respectively. For the first The stress value corresponding to each index, For the first The shear force value corresponding to each index For the first The displacement value corresponding to the item index, For time weighting coefficients, For the first Indicators over time The rate of change.

8. The condylar fracture surgical simulation planning and training system based on personalized patient data according to claim 1, characterized in that, The training effect evaluation model used in the preoperative repeated simulation training module is as follows: ， in, This represents the average training effect value. To simulate the number of training sessions, For the first Accuracy of operation in each training session. For the first Path deviation value of the training iteration. For the first The force deviation value of each training session For the first The time efficiency coefficient of each training session. For the first The time required to complete the calibration operation during this training session. Standard completion time, This is the time deviation adjustment parameter.

9. The surgical simulation planning and training system for condylar fractures based on personalized patient data according to claim 1, characterized in that, The admission determination model used by the surgical execution admission determination module is as follows: ， in, This is the admission criteria value. The determination coefficient, This represents the average accuracy across multiple training runs. The stability coefficient of the training results. This is the maximum path deviation value. This represents the maximum force deviation value. To calibrate the number of operation items, For the first The number of times the calibration operation is qualified. For the first The total number of training iterations for the item calibration operation.

10. The surgical simulation planning and training system for condylar fractures based on personalized patient data according to any one of claims 1-9, characterized in that, It also includes an access decision subsystem, which includes: The case operation model construction module transforms the reconstructed training model into a training model for repeatable simulated operations used for endoscopic operation training. The critical surgical operation range setting module determines the safe range of critical operations such as repositioning angle, operation path, and operation force under the endoscopic field of vision and operation constraints, based on the optimal endoscopic surgical plan. The repetitive simulation operation execution module performs multiple standardized endoscopic surgical simulation operations on the case operation model under the same field of view and instrument path constraints, and collects all operation data. The operation consistency assessment module analyzes the convergence and volatility of operation trajectory, force and time parameters in multiple simulated operations to quantitatively assess the operator's operational stability. The surgical admission decision module determines the admission criteria for endoscopic condylar fracture surgery and outputs a decision signal based on the evaluation results of the operation consistency assessment module and abnormal operation records.

Images