A method and system for simulating and displaying plastic surgery effects based on 3D simulation technology

Abstract

The present invention discloses a method and system for simulating and displaying plastic surgery effects based on 3D simulation technology, which relates to the field of medical information technology. The method includes collecting facial data of a patient and constructing an initial model of a multi-level facial structure; constructing a hybrid deformation model; extracting individualized characteristic parameters of the patient and generating a personalized set of biomechanical parameters through a biomechanical parameter prediction network; applying the personalized set of biomechanical parameters to the hybrid deformation model; receiving operation input parameters of a plastic surgery, and calculating and displaying the deformation results of each layer structure in real time based on a GPU parallel computing framework; constructing a tissue healing and recovery dynamics model, combining the deformation results, and generating appearance prediction data at different time points after the surgery; and performing three-dimensional visualization processing on the appearance prediction data. The present invention creatively integrates CT / MRI, 3D structured light scanning and expression dynamic video sequences, breaks through the limitations of traditional single-modal data modeling, and significantly improves the accuracy of soft tissue boundary recognition.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and particularly to a method and system for simulating and displaying plastic surgery effects based on 3D simulation technology. Background Art

[0002] With the rapid development of medical information technology, 3D simulation technology has been increasingly widely used in predicting the effects of plastic surgery. However, the existing technologies still face significant challenges in practical applications: Firstly, the accuracy of deformation simulation is insufficient. Traditional methods mostly rely on a single mechanical model (such as the finite element or particle spring model), making it difficult to balance computational efficiency and the non-linear deformation characteristics of multi-layer soft tissues, resulting in simulation results deviating from real biomechanical behaviors. Secondly, the lack of personalized adaptation is a problem. Existing models mostly adopt general biomechanical parameters, ignoring individual patient differences and affecting the prediction accuracy. In addition, complex deformation calculations rely on CPU serial processing, making it difficult to achieve real-time feedback for dynamically adjusting surgical parameters and limiting clinical applicability.

[0003] Meanwhile, the existing technologies lack modeling of postoperative dynamic recovery. Traditional methods mostly focus on intraoperative immediate deformation simulation and do not consider long-term morphological evolutions such as tissue healing and scar contraction, making it difficult to display the appearance changes at different postoperative recovery stages. Although some studies have attempted multi-model fusion or parameter optimization, they still have not effectively integrated multi-level modeling, hybrid computing architectures, and dynamic healing prediction, resulting in the difficulty of balancing the precision, personalization, and real-time nature of plastic surgery simulation and restricting its clinical application value. Summary of the Invention

[0004] In view of the problems existing in the existing plastic surgery simulations, such as insufficient accuracy of soft tissue deformation simulation, inadequate consideration of individual differences, and low real-time interaction performance, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to achieve the precision, personalization, and real-time nature of plastic surgery effect simulation through multi-level soft tissue modeling, personalized parameter optimization, and hybrid computing architectures.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for simulating and displaying plastic surgery effects based on 3D simulation technology, which includes collecting facial data of a patient and constructing an initial model of a multi-level facial structure; constructing a hybrid deformation model, where the hybrid deformation model describes the mechanical properties of each layer structure by combining the finite element method and the particle spring model; extracting individualized characteristic parameters of the patient, constructing a biomechanical parameter prediction network, and converting the individualized characteristic parameters into corresponding personalized biomechanical parameter sets; applying the personalized biomechanical parameter sets to the hybrid deformation model to optimize the deformation response characteristics of each layer structure; receiving operation input parameters of the plastic surgery, and calculating and displaying the deformation results of each layer structure in real time based on the GPU parallel computing framework; constructing a tissue healing and recovery dynamics model, and generating appearance prediction data at different time points after the surgery according to the deformation results and the tissue healing and recovery dynamics model; performing three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison display interface.

[0008] As a preferred solution of the method for simulating and displaying plastic surgery effects based on 3D simulation technology according to the present invention, the steps of constructing an initial model of a multi-level facial structure include: collecting facial CT / MRI data and 3D structured light scanning data of the patient, and recording the dynamic video sequence of the patient's facial expressions; applying a deep learning segmentation algorithm to process the CT / MRI data to generate preliminary segmentation masks for five layers of structures including skin, fat, muscle, fascia, and bone; performing spatial registration on the 3D structured light scanning data and the CT / MRI data to correct the outer contour of the skin layer segmentation mask; at the same time, optimizing the segmentation masks of the muscle layer and the fascia layer by constructing a facial muscle movement pattern database; performing boundary smoothing processing on the segmentation masks of each layer structure to generate three-dimensional boundary data; measuring the deformation characteristics of each layer structure based on the dynamic video sequence of the patient's facial expressions, and calculating material property parameters; fusing the three-dimensional boundary data and the material property parameters to generate an initial model of a multi-level facial structure.

[0009] As a preferred solution of the plastic surgery effect simulation and display method based on 3D simulation technology according to the present invention, the steps of constructing a hybrid deformation model include: constructing finite element models of the bone layer and the fascia layer, setting the mesh nodes of the bone layer as rigid fixed boundary conditions, and defining the connection constraint relationship between the fascia layer and the bone layer; constructing a composite deformation model of the muscle layer, applying the non-linear finite element method to the muscle fiber direction area, applying the particle spring model to the muscle connection area, and defining the sliding constraint relationship between the muscle layer and the fascia layer; constructing a particle spring model of the fat layer, setting the spring parameters according to the viscoelastic properties of adipose tissue, and defining the adhesion constraint relationship between the fat layer and the muscle layer; constructing a non-linear finite element model of the skin layer, introducing the hyperelastic material constitutive equation to describe the skin deformation characteristics, and defining the connection constraint relationship between the skin layer and the fat layer; integrating the deformation models of each layer structure to form a hybrid deformation model, applying the material property parameters to the hybrid deformation model, and configuring the corresponding initial model parameters according to the material characteristics of each layer structure.

[0010] As a preferred solution of the plastic surgery effect simulation and display method based on 3D simulation technology according to the present invention, the steps of constructing a biomechanical parameter prediction network include: collecting the basic information of the patient to form a patient individualized characteristic parameter set, and extracting the facial structure feature vectors of the initial models of multi-level facial structures at the same time, and integrating and generating comprehensive feature data; at the same time, constructing a reference database for the biomechanical characteristics of facial tissues; constructing a multi-branch neural network architecture, and establishing independent prediction channels for the skin layer, the fat layer, the muscle layer, the fascia layer, and the bone layer respectively; adopting the multi-branch neural network architecture, pre-training to obtain a general model based on the reference database of the biomechanical characteristics of facial tissues, and training to obtain a biomechanical parameter prediction network through the transfer learning method combined with the comprehensive feature data of historical patients; inputting the comprehensive feature data of the current patient into the biomechanical parameter prediction network, and optimizing it in combination with the patient facial tissue aging degree evaluation index and the data of similar groups in the historical surgery case database to generate a patient individualized biomechanical parameter set.

[0011] As a preferred solution of the plastic surgery effect simulation and display method based on 3D simulation technology of the present invention, wherein: applying the personalized biomechanical parameter set to the hybrid deformation model includes the following steps: updating the material property parameters of the hybrid deformation model according to the personalized biomechanical parameter set, and mapping the updated parameters to the mesh nodes and element properties of the hybrid deformation model; performing a comprehensive deformation test, including a loading-unloading cycle test to verify the deformation trajectory and recovery characteristics of each layer structure, and a local deformation test to calculate the displacement field and stress distribution of the facial area, and recording the deformation response characteristic curve; comparing the deformation response characteristic curve with the standard curve of the similar patient group in the historical data of the historical surgery case database, calculating the deviation value, and generating a parameter fine-tuning guidance; optimizing the biomechanical parameters of each layer structure according to the parameter fine-tuning guidance, and repeatedly performing parameter mapping and comprehensive deformation test until the deformation response accuracy reaches the preset accuracy threshold, and outputting the optimized hybrid deformation model.

[0012] As a preferred solution of the plastic surgery effect simulation and display method based on 3D simulation technology of the present invention, wherein: real-time calculating and displaying the deformation results of each layer structure based on the GPU parallel computing framework includes the following steps: receiving the plastic surgery parameters input by the doctor, and converting the plastic surgery parameters into the mechanical constraint conditions and load distribution parameters of the hybrid deformation model, and constructing a digital mapping model of the surgical operation; configuring the GPU parallel computing framework, dividing the calculation sub-domains according to the spatial distribution of the surgical area, and applying the asynchronous adaptive mesh refinement technology to perform mesh encryption on the directly affected area of the surgery; constructing a heterogeneous parallel solver, allocating the sparse matrix solving task of the finite element model to the GPU tensor core, and allocating the particle calculation of the particle spring model to the CUDA multi-threaded block, and synchronizing the inter-layer force data through the shared memory; performing real-time calculation of tissue deformation, and outputting the displacement field, stress field and strain field; asynchronously transmitting the displacement field data to the visualization module through the GPU-CPU heterogeneous pipeline to generate the deformation result data of each layer structure.

[0013] As a preferred solution of the plastic surgery effect simulation and display method based on 3D simulation technology of the present invention, wherein: generating the appearance prediction data at different time points after the surgery includes the following steps: constructing a tissue healing and recovery dynamics model, including an acute phase sub-model, an edema regression sub-model, a tissue fibrosis sub-model, a scar formation sub-model, and defining the state variable transfer rules between the sub-models; importing the deformation result data as the initial state after the surgery, and constructing a time series model; sequentially performing the acute phase, edema regression, tissue fibrosis, and scar formation stages in the time series model, and using the output state of the previous stage as the input for each stage, and generating the facial tissue state prediction data at the corresponding time point through the corresponding sub-model; integrating the output data of each stage through the time series model to generate the full-cycle appearance prediction data of the postoperative recovery process.

[0014] In the second aspect, an embodiment of the present invention provides a plastic surgery effect simulation display system based on 3D simulation technology, which includes a facial structure initialization module, which is used to collect patient facial data, build a multi-level facial structure initial model, and obtain three-dimensional boundary data and material property parameters of each layer structure; a hybrid deformation modeling module, which is used to build a hybrid deformation model, which uses a finite element method and a mass spring model to describe the mechanical properties of each layer structure; a parameter personalization module, which is used to extract the patient's individualized characteristic parameters, build a biomechanical parameter prediction network, and convert the individualized characteristic parameters into corresponding personalized biomechanical parameter sets; a model parameter optimization module, which is used to apply the personalized biomechanical parameter set to the hybrid deformation model to optimize the deformation response characteristics of each layer structure; a real-time deformation calculation module, which is used to receive the operation input parameters of the plastic surgery, and calculate and display the deformation results of each layer structure in real time based on the GPU parallel computing framework; a postoperative recovery prediction module, which is used to build a tissue healing and recovery dynamics model, and generate appearance prediction data at different time points after surgery according to the deformation results and the tissue healing and recovery dynamics model; a visualization display module, which is used to perform three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison display interface.

[0015] The beneficial effects of the present invention are as follows: the present invention creatively integrates CT / MRI, 3D structured light scanning and expression dynamic video sequences, breaks through the limitations of traditional single-modal data modeling, and significantly improves the accuracy of soft tissue boundary recognition; it pioneers the "finite element + particle spring" hybrid deformation model architecture, and performs differentiated modeling for different tissue characteristics, while innovatively designing the interlayer sliding and adhesion constraint relationship, which not only improves the computational efficiency but also maintains a high degree of biomechanical fidelity; it realizes personalized biomechanical parameter prediction through a multi-branch neural network architecture, and converts the individual characteristics of patients into precise simulation parameters, realizing truly personalized and precise modeling; it constructs a complete tissue healing and recovery dynamics model from the acute phase to scar formation, and for the first time realizes the prediction of appearance changes at different time points after surgery, providing doctors and patients with a comprehensive postoperative recovery assessment tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a framework flow chart of the plastic surgery effect simulation display method based on 3D simulation technology.

[0018] Figure 2It is a flow chart for constructing a hybrid deformation model of a plastic surgery effect simulation display method based on 3D simulation technology.

[0019] Figure 3 It is a flow chart for obtaining a patient's personalized biomechanical parameter set of a plastic surgery effect simulation display method based on 3D simulation technology. Specific embodiments

[0020] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0021] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0022] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is separate or selectively exclusive of other embodiments.

[0023] Example 1, referring to Figures 1 to 3 , which is the first embodiment of the present invention. This embodiment provides a plastic surgery effect simulation display method based on 3D simulation technology, and the framework flow chart is as Figure 1 shown, including,

[0024] S1: Collect the facial data of the patient, construct an initial model of the multi-level facial structure, and obtain the three-dimensional boundary data and material property parameters of each layer structure.

[0025] Specifically, collect the patient's facial CT / MRI data, 3D structured light scanning data, and the patient's facial expression dynamic video sequence (i.e., the video sequence of performing preset expression actions); apply the deep learning segmentation algorithm to process the CT / MRI data to generate a preliminary segmentation mask of the five layers of skin, fat, muscle, fascia, and bone; perform spatial registration on the 3D structured light scanning data and the CT / MRI data to correct the outer contour of the skin layer segmentation mask; extract the feature point movement trajectories in the facial expression dynamic video sequence, construct a facial muscle movement pattern database, and optimize the segmentation masks of the muscle layer and the fascia layer based on the facial muscle movement pattern database. It should be noted that when the deep learning segmentation algorithm processes the CT / MRI data, if the confidence level of the segmentation mask is lower than the preset confidence threshold (such as <90%), start the interactive correction module, allow the doctor to manually mark the key anatomical landmark points, and iteratively optimize the segmentation mask through semi-supervised learning.

[0026] Furthermore, perform boundary smoothing processing on the segmentation masks of each layer structure to generate three-dimensional boundary data; extract the image eigenvalue of each layer structure, and establish the mapping relationship between the image eigenvalue and the material property parameters; at the same time, measure the deformation characteristics of each layer structure based on the facial expression dynamic video sequence, and calculate the material property parameters; fuse the three-dimensional boundary data and the material property parameters to generate an initial multi-level facial structure model.

[0027] It should be noted that the preference of the initial multi-level facial structure model being divided into five layer structures of skin, fat, muscle, fascia, and bone lies in that it not only conforms to the real composition of the facial anatomical structure but also can accurately reflect the unique biomechanical characteristics of each layer (such as the elasticity of the skin, the contractility of the muscle, and the rigid support of the bone); at the same time, these five layers are exactly the main target tissues of most facial plastic surgeries and can accurately simulate the interlayer deformation transfer relationship and surgical influence.

[0028] Preferably, the present invention creatively integrates CT / MRI, 3D structured light scanning, and facial expression dynamic video sequences, breaking through the limitations of traditional single-modal data modeling; through deep learning segmentation and semi-supervised correction mechanism (triggered by confidence threshold), it organically combines the anatomical accuracy of medical images with the biomechanical characteristics of dynamic videos, significantly improving the accuracy of soft tissue boundary recognition, realizing the precise modeling of the five layer structures of skin, fat, muscle, fascia, and bone, and greatly reducing the need for manual intervention in the modeling process.

[0029] S2: Construct a hybrid deformation model based on the three-dimensional boundary data and the material property parameters. The hybrid deformation model uses a combination of the finite element method and the particle spring model to describe the mechanical characteristics of each layer structure.

[0030] Specifically, the flow chart for constructing the hybrid deformation model is as Figure 2 shown and includes the following steps:

[0031] S2.1: Import the three-dimensional boundary data, perform tetrahedral mesh division on the boundaries of each layer structure, and generate a discrete mesh structure with topological connection relationships.

[0032] S2.2: Construct a finite element model of the bone layer. Based on the rigid characteristics of the bone, set the mesh nodes of the bone layer as rigid fixed boundary conditions to simulate its supporting role in facial deformation.

[0033] Specifically, import the discrete grid structure of the bone layer, identify the bone boundaries based on the bone layer segmentation mask, and generate a high-precision bone surface mesh; apply the tetrahedral mesh generation technology to mesh the bone surface to ensure mesh quality and computational efficiency; define the material property parameters of the bone layer, set the local elastic modulus and Poisson's ratio parameters according to the bone structure characteristics to reflect the mechanical properties of the bone; set the fixed boundary conditions, identify the key anatomical structure points, and use them as fixed constraint points to provide a stable deformation reference benchmark; assemble the stiffness matrix to establish the overall mechanical properties of the bone layer as the supporting structure for the deformation of other tissue layers.

[0034] Furthermore, establish special boundary conditions for the bone connection areas, set the degrees of freedom of movement at the movable joints such as the temporomandibular joint to allow relative movement in specific directions; transfer the bone force and deformation information to the connection layer, and calculate the displacement and force boundary conditions at the bone-fascia interface through the interpolation algorithm as the input conditions for the fascia layer deformation.

[0035] S2.3: Construct the finite element model of the fascia layer, define the connection constraint relationship between the fascia layer and the bone layer, and establish the correlation equation between the fascia deformation and the bone fixed points.

[0036] Specifically, import the discrete grid structure of the fascia layer, use the fascia layer segmentation mask to generate a mesh representing the fascia anatomical features; apply the nonlinear elastic material method to define the constitutive equation of the fascia material to reflect its mechanical properties in the tensile and compressive states; construct the fascia-bone connection constraint, identify the attachment points of the fascia and the bone based on their respective segmentation masks, establish the node correspondence relationship, and define the displacement constraint conditions; design a variable stiffness connection scheme, set different connection stiffnesses for different anatomical regions to simulate the tight and loose connections between the fascia and the bone; assemble the stiffness matrix based on the tetrahedral mesh, integrate the connection constraints, and establish the overall mechanical analysis framework.

[0037] Furthermore, define the load transfer mechanism, establish the transfer path of the fascia force and deformation information to the muscle layer, and calculate the displacement and force boundary conditions at the fascia-muscle interface; use the implicit integration format to calculate the deformation response of the fascia under external forces and capture its mechanical behavior characteristics.

[0038] S2.4: Construct the composite deformation model of the muscle layer, apply the nonlinear finite element method to the muscle fiber direction area, apply the particle spring model to the muscle connection area, and define the sliding constraint relationship between the muscle layer and the fascia layer.

[0039] Specifically, the muscle region is divided, the muscle fiber orientation is identified based on CT / MRI data, and the muscle tissue is divided into fiber direction regions and connection regions; a finite element model of the fiber direction region is constructed, the anisotropic nonlinear finite element method is adopted, the active-passive coupling constitutive equation is defined, the Hill model is introduced to describe the dynamic mechanical properties of muscle contraction, and the activation factor parameter is set to simulate the muscle response under nerve drive; a particle spring model of the connection region is constructed, and a dual-stiffness spring is designed to distinguish the mechanical behavior of the tendon in different deformation states; a transition zone is constructed, and a weighting function is applied at the region junction to smoothly fuse the mechanical responses of the two models and ensure the continuity of deformation.

[0040] Furthermore, the sliding constraint relationship between the muscle layer and the fascia layer is defined, the normal impenetrability condition and the tangential Coulomb friction are applied, and the constraint force is calculated to simulate the physiological sliding characteristics; the hybrid deformation model is solved, the hybrid stiffness matrix is assembled, and the implicit integration format is used to solve the dynamic equation to calculate the deformation response of the muscle layer in different activation states.

[0041] Preferably, through multi-scale modeling and physical-driven parameter calibration, the problem of difficult to balance accuracy and efficiency in traditional muscle modeling is solved, providing innovative technical support for the precise planning and effect prediction of plastic surgery.

[0042] S2.5: Construct a particle spring model of the fat layer, set the spring parameters according to the viscoelastic properties of the adipose tissue, and define the adhesion constraint relationship between the fat layer and the muscle layer.

[0043] Specifically, the discrete grid structure of the fat layer is imported, the fat distribution region is identified based on the fat layer segmentation mask, the surface fat distribution is corrected by combining 3D structured light scanning data, and a grid expressing the distribution characteristics of the adipose tissue is generated; a multi-resolution particle system is constructed, different densities of particle distributions are set according to the requirements of local anatomical details, and the calculation accuracy and efficiency are balanced; a viscoelastic spring network is designed, the connection relationship between particles is established, and the spring constant and damping coefficient are defined according to the viscoelastic properties of the adipose tissue; the Maxwell-Kelvin structure is applied, the spring viscoelastic parameters are set, and the hysteretic response characteristics of the adipose tissue during loading and unloading are simulated; the fat density change region is defined, and different particle densities and spring parameters are set for different facial regions to reflect the local adipose tissue distribution characteristics.

[0044] Furthermore, a fat-muscle adhesion constraint is constructed, the contact region between the fat layer and the muscle layer is identified based on their respective segmentation masks, the node correspondence relationship is established, the adhesion force function is defined, and the interaction between the two tissue layers is simulated; a multi-layer sliding mechanism is designed to allow the fat layer to slide limitedly on the surface of the muscle layer while maintaining the overall connectivity, reflecting the actual physiological characteristics; the Verlet integration method is used to calculate the evolution of the particle position over time to simulate the deformation response of the fat layer under external forces.

[0045] S2.6: Construct a nonlinear finite element model of the skin layer, introduce the hyperelastic material constitutive equation to describe the skin deformation characteristics, and define the connection constraint relationship between the skin layer and the fat layer.

[0046] Specifically, a hyperelastic constitutive equation is defined, a hyperelastic material model is used to describe the nonlinear mechanical properties of the skin, and the material property parameters are initialized based on the image eigenvalues; a finite element model of the skin layer is constructed, the stiffness matrix is ​​assembled based on the tetrahedral mesh, and boundary conditions are applied to constrain the deformation behavior; the connection constraint relationship between the skin layer and the fat layer is defined, contact node pairs are constructed, normal adhesion force and tangential friction force are applied to simulate the mechanical interaction between the two layers; the nonlinear dynamic equations are solved, and the deformation response of the skin layer is calculated.

[0047] S2.7: Integrate the deformation models of each layer structure, establish the interlayer force transfer equations, and form a mixed deformation model.

[0048] S2.8: Apply material property parameters to the mixed deformation model and configure corresponding initial model parameters according to the material properties of each layer structure.

[0049] The material property parameters include but are not limited to elastic modulus, Poisson's ratio, density, viscosity parameter, hyperelastic parameter and anisotropy parameter. In addition, the material property parameters are initialized through the mapping relationship between the image feature value and the material property parameter.

[0050] S2.9: Perform preset deformation tests to verify the accuracy of the deformation response of each layer of the mixed deformation model under different forces, adjust the interlayer sliding constraint parameters and adhesion constraint parameters, and optimize the interlayer sliding and adhesion effects.

[0051] Preferably, the present invention has pioneered the design of a hybrid model framework of "finite element + mass spring" to perform differentiated modeling for different tissue characteristics. Compared with the traditional single physical model, this multi-scale hybrid modeling method improves computational efficiency while maintaining high precision, and balances the problem of accuracy and efficiency in traditional methods. At the same time, the innovative introduction of sliding constraints and adhesion constraints to simulate the interaction between tissue layers solves the deformation and distortion problem caused by traditional fixed constraints, which is more in line with actual physiological characteristics.

[0052] S3: Extract the patient's individual characteristic parameters, construct a biomechanical parameter prediction network, and convert the individual characteristic parameters into the corresponding personalized biomechanical parameter set.

[0053] Specifically, the flowchart for obtaining the patient's personalized biomechanical parameter set is as follows: Figure 3 As shown, the following steps are included:

[0054] S3.1: Collect the patient's basic information to form a set of individualized characteristic parameters for the patient.

[0055] Among them, the patient's basic information includes but is not limited to the patient's age, gender, race, BMI index, etc.

[0056] In addition, collecting the patient's basic information requires the consent or authorization of the patient.

[0057] S3.2: Based on clinical trial data and literature research, construct a reference database of facial tissue biomechanical properties including different ages, genders, and races.

[0058] S3.3: Design a feature extraction neural network to automatically identify the positions of key anatomical landmark points on the initial model of the multi-level facial structure and extract facial structure feature vectors.

[0059] Specifically, design a feature extraction architecture based on a convolutional neural network, including an input layer, a feature extraction layer, a landmark detection layer, and a feature vector generation layer. Through training, the network can automatically identify the key anatomical landmark points on the face and generate vectors representing the facial structure features.

[0060] S3.4: Integrate the set of individualized characteristic parameters of the patient and the facial structure feature vectors to generate comprehensive feature data.

[0061] S3.5: Construct a multi-branch neural network architecture and establish independent prediction channels for the skin layer, fat layer, muscle layer, fascia layer, and bone layer respectively.

[0062] Specifically, a shared feature extraction backbone network of the multi-branch neural network is defined. The cross-sectional feature map of facial tissues is extracted by cascading convolutional layers and a spatial pyramid pooling module to generate a feature vector encoding the patient's anatomical structure. A skin layer prediction channel is constructed, using a sequence of fully connected layers and a parameter regularization constraint layer to output a set of material property parameters applicable to the finite element model of the skin layer. A fat layer prediction channel is constructed, combining a temporal memory unit and a residual connection structure, for the set of material property parameters applicable to the particle spring model of the fat layer. A muscle layer prediction channel is constructed, designing a parallel dual-channel network, with one channel processing the muscle fiber direction tensor field and the other channel processing the topological structure of the connection region, and fusing through an attention mechanism to output a set of material property parameters applicable to the mixed deformation model of the muscle layer. A fascia layer prediction channel is constructed, using a graph convolutional unit to process the fascia-bone connection point distribution data and cascading fully connected layers to process the fascia material properties, and outputting a set of material property parameters applicable to the finite element model of the fascia layer. A bone layer prediction channel is constructed, converting the bone structure into a three-dimensional feature volume through voxelization and extracting the density distribution features through three-dimensional convolutional layers, for the set of parameters applicable to the boundary conditions of the bone layer. A layer-to-layer force transfer learning module is constructed, establishing an inter-layer connection matrix based on the anatomical position relationship and learning the layer-to-layer force transfer rules through a graph neural network to ensure the consistency of the prediction parameters of each layer.

[0063] S3.6: Adopt a multi-branch neural network architecture, pre-train a general model based on the reference database of facial tissue biomechanical characteristics, and train a biomechanical parameter prediction network through transfer learning combined with the comprehensive feature data of historical patients.

[0064] Specifically, data samples are extracted from the reference database of facial tissue biomechanical characteristics, and the data sample set is divided into a training subset, a validation subset, and a test subset according to a preset ratio (7:2:1). The data in the training subset is normalized and data-augmented. A phased training strategy is adopted. First, the dedicated prediction channels are fixed, and only the shared feature extraction backbone network is trained to optimize the feature representation ability. Then, the dedicated prediction channels are unfrozen, and the multi-branch neural network is trained using the mini-batch gradient descent method, and a weighted loss function is used to balance the prediction accuracy of each layer. Based on the performance evaluation of the validation subset, a learning rate decay strategy and an early stopping mechanism are adopted to prevent the model from overfitting, and a pre-trained general model is obtained.

[0065] Furthermore, the comprehensive feature data of historical patients is imported, the underlying parameters of the shared feature extraction backbone network are frozen, and transfer learning technology is applied to fine-tune the parameters of the high-level network. A loss function adapted to domain transfer is designed to balance the retention of general knowledge and the adaptation to the characteristics of the target patient group, and a biomechanical parameter prediction network for the target patient group is trained. The performance of the biomechanical parameter prediction network is evaluated using the test subset, the prediction errors of the material property parameters of each layer are calculated, and a model performance report is generated.

[0066] S3.7: Input the comprehensive characteristic data of the current patient into the biomechanical parameter prediction network to generate a set of patient-specific biomechanical parameters.

[0067] S3.8: Based on the evaluation index of the aging degree of the patient's facial tissue, adjust the elastic parameter and viscous parameter in the set of patient-specific characteristic parameters.

[0068] Among them, the evaluation index of the aging degree includes the measured value of skin elasticity, the depth data of facial wrinkles, and the measured data of facial bone density; calculate the comprehensive aging coefficient based on these measurement data, and according to the preset biomechanical rules, correspondingly adjust the reduction ratio of the elastic parameter and the increase ratio of the viscous parameter to accurately simulate the tissue aging characteristics.

[0069] Among them, the comprehensive aging coefficient is calculated by weighted summation, and the adjustment rules of the elastic parameter E and the viscous parameter are respectively: , , where is the comprehensive aging coefficient, and are adjustment coefficients (respectively controlling the change ratio of the elastic parameter and the viscous parameter with the aging degree), are the elastic parameter and viscous parameter before adjustment, are the elastic parameter and viscous parameter after adjustment.

[0070] S3.9: Optimize the deformation response parameters according to the data of similar groups in the historical surgical case database to generate the final set of patient-specific biomechanical parameters.

[0071] Among them, the matching criteria for the data of similar groups include age, gender, race, and BMI index, and the final set of patient-specific biomechanical parameters includes the elastic parameter, viscous parameter, hyperelastic parameter, anisotropic parameter, and interlayer coupling parameter corresponding to each layer structure.

[0072] It should be noted that the deformation response parameter is an intermediate optimization parameter obtained through the analysis of historical surgical case data, and its optimization result is used to adjust the elastic parameter, viscous parameter, hyperelastic parameter, anisotropic parameter, and interlayer coupling parameter in the final parameter set to improve the accuracy of facial soft tissue deformation prediction. In addition, the optimization methods of the deformation response parameter include but are not limited to regression analysis, machine learning models (such as random forest, support vector machine), or deep learning models (such as neural network), and are fitted and predicted based on the biomechanical response characteristics of similar group data.

[0073] S4: Apply the set of personalized biomechanical parameters to the hybrid deformation model to optimize the deformation response characteristics of each layer structure.

[0074] Specifically, parse the personalized biomechanical parameter set, extract the elastic parameters, viscous parameters, hyperelastic parameters, anisotropic parameters, and interlayer coupling parameters corresponding to each layer structure; update the material property parameters of the hybrid deformation model according to the personalized biomechanical parameter set, including updating the elastic parameters of each layer structure, configuring the viscous parameters of each layer structure in the hybrid deformation model, modifying the hyperelastic parameters of the skin layer, adjusting the anisotropic parameters of the muscle layer, and updating the interlayer coupling parameters between adjacent tissue layers in the hybrid deformation model; perform model parameter mapping to map the updated material property parameters to the grid nodes and element properties of the hybrid deformation model.

[0075] Furthermore, perform a loading-unloading cycle test to verify the deformation trajectory and recovery characteristics of each layer structure during the loading and unloading processes, and detect the deformation response accuracy of the hybrid deformation model after the parameters are applied; perform a local deformation test to calculate the displacement field and stress distribution of at least two facial regions under a preset force, and record the deformation response characteristic curve; compare the deformation response characteristic curve with the standard curve of the similar patient group in the historical data of the historical surgery case database, calculate the deviation value, and generate a parameter fine-tuning guidance; optimize the biomechanical parameters of each layer structure according to the parameter fine-tuning guidance, and repeat the execution of model parameter mapping, loading-unloading cycle test, and local deformation test until the deformation response accuracy reaches the preset accuracy threshold; generate an optimized hybrid deformation model, including the updated material property parameters and interlayer interaction parameters of each layer structure.

[0076] It should be noted that the deviation value is calculated by the mean square error, and the parameter fine-tuning guidance includes the proportion of increase / decrease of the elastic parameters; the preset accuracy threshold is that the relative error is less than 5%; the model parameter mapping adopts the weighted average method, considering the grid density and element type.

[0077] Preferably, traditional plastic surgery simulations rely on general parameters, cannot reflect the individual differences of patients, and only focus on static deformation characteristics, resulting in a large deviation between the simulation results and the actual surgical effects. By applying the personalized biomechanical parameter set to the hybrid deformation model, the present invention realizes individualized precise modeling and significantly improves the simulation accuracy; independent prediction channels are designed for different tissue layers, and the graph neural network is combined to process the interlayer force transmission, breaking through the limitations of the traditional general parameter model; the loading-unloading cycle test and the local deformation test are combined to comprehensively evaluate the dynamic response and local deformation characteristics of the model, making the simulation results more consistent with the mechanical behavior in actual surgery, and providing reliable support for the precise planning and effect prediction of plastic surgery.

[0078] S5: Receive the operation input parameters of the plastic surgery, and calculate and display the deformation results of each layer structure in real time based on the GPU parallel computing framework.

[0079] Specifically, it receives plastic surgery parameters input by a doctor, including the type of surgery, the area of action, the operating force, the properties of implants, and the scope of tissue resection; converts the plastic surgery parameters into mechanical constraint conditions and load distribution parameters of a hybrid deformation model, and constructs a digital mapping model of the surgical operation, including the following steps: parsing the input surgical type parameters, matching the preset biomechanical constraint rule library, and activating the corresponding tissue deformation calculation mode; generating a dynamic mechanical load distribution acting on the target area according to the operating force parameters and the geometric characteristics of the surgical tool; constructing the initial boundary conditions of the implant-tissue contact surface and the constraint equations of the tissue defect area based on the implant parameters and the scope of tissue resection; integrating the spatial action range and biomechanical characteristics of the surgical area to generate the global distribution matrix of the hybrid deformation model; performing validity verification and dynamic adjustment of the plastic surgery parameters to ensure the numerical stability of the boundary conditions and the distribution matrix.

[0080] Furthermore, configure a GPU parallel computing framework, divide the calculation sub-domains according to the spatial distribution of the surgical area, pre-allocate the GPU memory pool and set a dynamic expansion strategy, where the dynamic expansion strategy refers to using CUDA's unified memory management or memory pool technology to automatically allocate additional memory blocks when more memory is detected and release them when not needed; apply asynchronous adaptive mesh refinement technology to perform mesh encryption on the directly affected surgical area in an independent CUDA stream and synchronize the encrypted mesh to the main calculation thread in real time; construct a heterogeneous parallel solver, allocate the sparse matrix solution task of the finite element model to the GPU tensor core, and allocate the particle calculation of the particle spring model to the CUDA multi-thread block, and synchronize the inter-layer force data through shared memory; perform real-time calculation of tissue deformation, monitor the GPU utilization rate and calculation latency, dynamically adjust the mesh density of non-critical areas, and output the displacement field, stress field, and strain field, where the non-critical area refers to the area that is not directly affected by the surgery and the biomechanical influence is negligible; asynchronously transmit the displacement field data to the rendering module through the GPU-CPU heterogeneous pipeline to generate the deformation result data of each layer structure.

[0081] Preferably, the present invention realizes the digital mapping of surgical operations by automatically converting plastic surgery parameters into mechanical constraint conditions and load distribution parameters of a hybrid deformation model; designs a GPU computing architecture specifically for soft tissue deformation, especially realizes the adaptive mesh refinement of the surgical area and the dynamic mesh simplification of non-critical areas, and balances accuracy and performance; at the same time, based on the GPU parallel computing framework, adopts dynamic memory management, asynchronous adaptive mesh refinement, and heterogeneous parallel solvers, significantly improving the computing efficiency; in addition, by dynamically adjusting the mesh density of non-critical areas and the GPU-CPU heterogeneous pipeline, it optimizes the allocation of computing resources and provides intuitive preoperative planning support for doctors.

[0082] S6: Construct a tissue healing and recovery kinetics model. Based on the deformation results and the tissue healing and recovery kinetics model, generate appearance prediction data at different postoperative time points.

[0083] Specifically, constructing a tissue healing and recovery kinetics model includes an acute-phase sub-model, an edema regression sub-model, a tissue fibrosis sub-model, and a scar formation sub-model, and defining the state variable transfer rules between the sub-models, including the following steps: Construct an acute-phase sub-model, use the constitutive equation of non-linear elastic materials to describe the characteristics of edematous tissues, use the concentration gradient equation of inflammatory factors to simulate the diffusion of edema, and establish a mathematical mapping relationship between surgical trauma parameters and the intensity of inflammatory response; construct an edema regression sub-model, use an exponential decay function to characterize the process of body fluid reabsorption, calculate the liquid flow rate in combination with the tissue permeability matrix, and integrate the stress-strain recovery equation to simulate the tissue morphology recovery; construct a tissue fibrosis sub-model, use the collagen fiber directional deposition algorithm to describe the fibrosis process, characterize the change in tissue hardness through the anisotropic material stiffness tensor, and apply the local stress field as a fibrosis process regulator; construct a scar formation sub-model, use the contraction-stress coupling equation to describe the evolution of scar tissues, simulate the plastic deformation of tissues through the von Mises yield criterion, and integrate the optical property change matrix to generate scar appearance characteristics.

[0084] Furthermore, define the state variable transfer rules between the sub-models, establish transfer matrices for displacement fields, stress fields, tissue density, and material parameters, formulate a data format conversion protocol, and design a method for maintaining the consistency of state parameters between different models; integrate the time series state transition algorithm, use piecewise continuous functions to describe the stage characteristics of the recovery process, establish a parametric correspondence between the surgical type and the duration of the recovery stage, and construct a complete tissue healing and recovery kinetics model.

[0085] Furthermore, import the deformation result data as the postoperative initial state and construct a time series model, where the time series model performs the following operations: Set the postoperative recovery time axis, divide the effective time intervals of each sub-model, including the acute phase, the edema regression phase, the tissue fibrosis phase, and the scar formation phase; establish the triggering conditions for stage switching; define the data interfaces between the sub-models, and use the output state of the previous stage as the input of the next stage.

[0086] Furthermore, when the time series model progresses to the acute phase, the initial postoperative state is input into the acute phase sub-model to generate predicted data on the facial tissue state at the first postoperative time point, including the spatial distribution of edema volume, tissue displacement field, and surface short-term deformation; when the time series model progresses to the edema regression phase, the output state of the acute phase sub-model is input into the edema regression sub-model to generate predicted data on the facial tissue state at the second postoperative time point, including the location of the residual edema area, tissue retraction amount, and surface smoothness; when the time series model progresses to the tissue fibrosis phase, the output state of the edema regression sub-model is input into the tissue fibrosis sub-model to generate predicted data on the facial tissue state at the third postoperative time point, including the distribution of deep elastic modulus, morphological offset, and dynamic stability parameters; when the time series model progresses to the scar formation phase, the output state of the tissue fibrosis sub-model is input into the scar formation sub-model to generate predicted data on the facial tissue state at the fourth postoperative time point, including the scar shrinkage amount, final displacement field, and morphological confidence interval; the output data of each phase are integrated through the time series model to generate full-cycle appearance prediction data for the postoperative recovery process.

[0087] In addition, the first, second, third, and fourth time points are 7 days, 30 days, 180 days, and 365 days respectively. The preference of these time points is reflected in the turning cycles of key biological processes: 7 days corresponds to the peak of acute inflammation (maximum spread of edema), 30 days covers the mid-term of the decay of the body fluid index (70%-80% of edema regression), 180 days matches the stable period of collagen remodeling (fibrosis hardness tends to be stable), and 365 days corresponds to the end point of scar maturation (shrinkage rate <5%). Its design not only conforms to the biological time constants of tissue healing (such as the macrophage activity cycle of 28 days and the collagen half-life of 90-120 days), but also fits the clinical follow-up nodes, balancing the observational requirements of short-term drastic changes and long-term progressive processes through an exponential time span.

[0088] Preferably, traditional plastic surgery simulations usually only focus on the immediate surgical effects and ignore the important impact of the postoperative tissue healing and recovery process on the final appearance, resulting in patients lacking an accurate expectation of the changes at different postoperative stages. By constructing a complete kinetic model of tissue healing and recovery, the present invention realizes the full-cycle simulation from the acute postoperative phase to scar formation, provides a comprehensive postoperative recovery assessment tool for doctors, and enables patients to form a reasonable expectation of the postoperative appearance changes, significantly improving the clinical value of plastic surgery effect prediction and patient satisfaction.

[0089] S7: Perform three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison display interface with multiple perspectives and multiple time points.

[0090] Furthermore, this embodiment also provides a plastic surgery effect simulation and display system based on 3D simulation technology, including a facial structure initialization module for collecting patient facial data, constructing an initial multi-level facial structure model, and obtaining three-dimensional boundary data and material property parameters of each layer structure; a hybrid deformation modeling module for constructing a hybrid deformation model, which describes the mechanical properties of each layer structure by combining the finite element method and the particle spring model; a parameter personalization module for extracting patient individual characteristic parameters, constructing a biomechanical parameter prediction network, and converting the individual characteristic parameters into corresponding personalized biomechanical parameter sets; a model parameter optimization module for applying the personalized biomechanical parameter sets to the hybrid deformation model to optimize the deformation response characteristics of each layer structure; a real-time deformation calculation module for receiving the operation input parameters of plastic surgery and calculating and displaying the deformation results of each layer structure in real time based on the GPU parallel computing framework; a postoperative recovery prediction module for constructing a tissue healing and recovery dynamics model, and generating appearance prediction data at different postoperative time points according to the deformation results and the tissue healing and recovery dynamics model; and a visualization display module for performing three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison and display interface.

[0091] In summary, the present invention creatively integrates CT / MRI, 3D structured light scanning, and expression dynamic video sequences, breaks through the limitations of traditional single-modal data modeling, and significantly improves the soft tissue boundary recognition accuracy; it first creates a "finite element + particle spring" hybrid deformation model architecture, performs differential modeling for different tissue characteristics, and innovatively designs the interlayer sliding and adhesion constraint relationships, which not only improves the calculation efficiency but also maintains a high biomechanical fidelity; it realizes the prediction of personalized biomechanical parameters through a multi-branch neural network architecture, converts the individual characteristics of patients into accurate simulation parameters, and achieves truly individualized and accurate modeling; it constructs a complete tissue healing and recovery dynamics model from the acute phase to scar formation, and for the first time realizes the prediction of appearance changes at different postoperative time points, providing a comprehensive postoperative recovery evaluation tool for doctors and patients.

[0092] Example 2, referring to Figures 1 to 3 , is the second embodiment of the present invention. This embodiment provides a plastic surgery effect simulation and display method based on 3D simulation technology. To verify the beneficial effects of the present invention, scientific demonstrations are carried out through economic benefit calculations and simulation experiments.

[0093] In real-world applications, the plastic surgery effect simulation and display method based on 3D simulation technology first collected facial data from a 55-year-old female patient. The patient faced facial relaxation problems and hoped to improve her appearance through a facelift. The acquisition team used a Siemens SOMATOM CT scanner to obtain the patient's facial CT scan data with a resolution of 0.5 mm; the facial surface morphology data was collected by an Artec Eva 3D structured light scanner with an accuracy of 0.1 mm; at the same time, a high-definition video sequence of the patient performing 7 preset facial expression actions such as smiling and frowning was recorded. The nnU-Net deep learning segmentation framework was applied to process the CT data. The initial segmentation mask confidence was 87.3%, lower than the 90% threshold, and then the interactive correction module was activated. Professional physicians marked 42 key anatomical landmark points. After 10 iterations of semi-supervised learning, the segmentation mask confidence increased to 95.7%. After boundary smoothing processing and material property parameter extraction, an accurate initial facial model with five layers of skin, fat, muscle, fascia, and bone was successfully constructed. Compared with traditional single-modal data modeling, the anatomical boundary recognition accuracy increased by 28.3%, and the manual intervention time decreased by 64.5%.

[0094] Based on the obtained three-dimensional boundary data and material property parameters, the research team constructed a hybrid deformation model. First, tetrahedral mesh generation was performed on each layer structure to generate a discrete structure containing 283,564 mesh elements. The bone layer was set with a rigid fixed boundary condition and an elastic modulus of 13,700 MPa; a connection constraint relationship was established between the fascia layer and the bone layer with an elastic modulus of 80 MPa; the muscle layer adopted a hybrid modeling method, where the fiber direction region used the nonlinear finite element method, the connection region used the particle spring model, and the active contraction region was described by the Hill model, with an elastic modulus set to 32.8 MPa and an activation factor range of 0 - 1.0; a sliding constraint relationship was defined between the muscle layer and the fascia layer, and the normal non-penetration condition and the tangential Coulomb friction coefficient were set to 0.28; the fat layer used the particle spring model with a spring stiffness of 4.3 kPa and a damping coefficient of 0.32; the skin layer adopted the Ogden hyperelastic model with a shear modulus of 23.1 kPa and a bulk modulus of 0.4 MPa. To optimize the interlayer interaction, 10 groups of preset deformation tests were performed, and the interlayer sliding constraint parameters and adhesion constraint parameters were adjusted, so that the deformation response error of each layer structure under different loads was controlled within 4.2%. The computational efficiency was increased by 65.3% compared with the traditional single physical model, while maintaining an accuracy level of not less than 94%.

[0095] For the patient's personalized biomechanical characteristics, the system collected the patient's basic information (55 years old, female, Asian race, BMI index of 24.2) as an individualized feature parameter set, and obtaining the patient's consent or authorization was required for collecting the patient's basic information. Combining the biomechanical parameter data of 2,376 facial tissue cases in the clinical trial database, a multi-branch neural network architecture was constructed. The network contains 5 independent prediction channels, respectively for the skin layer, fat layer, muscle layer, fascia layer, and bone layer. The shared feature extraction backbone network extracts features through the spatial pyramid pooling module. The skin layer prediction channel uses 3 fully connected layers, and parameter regularization constraints are set at the end; the fat layer prediction channel combines LSTM units and residual connections; the muscle layer prediction channel designs a parallel dual-channel structure to process the muscle fiber direction and connection area respectively; the fascia layer prediction channel uses graph convolutional units to process the distribution of connection points; the bone layer prediction channel extracts density distribution features through 3D convolution. The multi-branch network was trained based on a 75% / 15% / 10% training / validation / test set division, using the Adam optimizer with an initial learning rate of 0.0002, decaying by 10% every 10 epochs. The final model prediction error was less than 7.3%, and the generated patient's personalized biomechanical parameter set includes the elastic, viscous, hyperelastic, and anisotropic parameters of each tissue layer. Based on the measured skin elasticity (0.62 mm / N), the average facial wrinkle depth (1.8 mm), and bone density assessment, the comprehensive aging coefficient was calculated to be 0.78, and the reduction ratio of the elastic parameter (-22.3%) and the increase ratio of the viscous parameter (+35.1%) were adjusted accordingly.

[0096] After applying the personalized biomechanical parameter set to the hybrid deformation model, the system performed a simulation calculation of a facelift operation. The surgical parameters input by the doctor included: SMAS facelift, traction in the zygomatic region, and the operation force of 2.8 N / cm 2, without implants, and the width of the temporal incision is 4.2 cm. These parameters are converted into load distributions through a biomechanical constraint rule base, and the mesh density in the surgical area is increased to three times the original density, reaching approximately 850,000 elements. Real-time calculations are performed using the NVIDIA RTX 3090 GPU parallel computing framework. The computational domain is divided into 32 subdomains, and each subdomain is assigned to a separate CUDA thread block. The system applies asynchronous adaptive mesh refinement technology to encrypt the mesh in the directly affected area of the surgery, while the non-critical areas are dynamically adjusted to 65% of the original density. The sparse matrix solution task of the finite element model is assigned to the GPU tensor core, and the particle calculations of the particle spring model are assigned to the CUDA multi-threaded block. The inter-layer force data is synchronized through shared memory. The final computational performance reaches a real-time rendering rate of 24 frames per second, with a simulation calculation delay of less than 42 milliseconds, a 28.4-fold speedup compared to traditional CPU calculations, while maintaining the deformation accuracy at the 95.2% level. The surgical deformation results show that the maximum displacement of the SMAS layer reaches 7.2 mm, the stress concentration area is located at the edge of the temporal incision, and the maximum stress value is 0.58 MPa.

[0097] Based on the surgical deformation results, the system applies a tissue healing and recovery dynamics model to predict the appearance changes at different time points after surgery. The acute-phase submodel (7 days after surgery) predicts the facial edema volume distribution, with a maximum edema thickness of 5.3 mm, concentrated in the zygomatic area and the mandibular line; the edema regression submodel (30 days after surgery) shows that the residual edema drops to 18.2% of the initial value, and the tissue retraction amount is 1.3 mm; the tissue fibrosis submodel (180 days after surgery) calculates that the deep elastic modulus increases by 27.4%, and the morphological deviation is 17.5% of the original traction amount; the scar formation submodel (365 days after surgery) predicts a scar contraction amount of 0.8 mm, and the final displacement field retracts by 10.3% compared to the immediate surgical effect. The system generates a three-dimensional visualization interface for each time point, showing the complete appearance change process of the patient from pre-operation, acute post-operation, edema regression, fibrosis to the final effect. Through calculation and comparison, the comparison between the predicted final appearance at 365 days after surgery and the three-dimensional scan data taken during the actual follow-up shows that the average deviation is only 1.8 mm, and the position matching rate reaches 93.5%, far superior to traditional simulation methods. As shown in Table 1, the present invention has significant advantages compared with the prior art.

[0098] Table 1 Performance Comparison between the Present Invention and the Prior Art

[0099]

[0100] As can be seen from Table 1, the method for simulating and displaying plastic surgery effects based on 3D simulation technology proposed by the present invention is superior to the prior art in terms of multiple performance indicators. This method constructs a high-precision facial structure model through multi-modal data fusion, adopts a hybrid deformation model to balance calculation accuracy and efficiency, introduces a personalized biomechanical parameter prediction network to achieve patient-specific modeling, uses a GPU parallel computing framework to achieve real-time simulation calculation, and constructs a tissue healing and recovery dynamics model to predict the appearance changes during the entire postoperative period. These innovative points together constitute a complete plastic surgery effect prediction system, providing clinicians with accurate surgical planning tools, while helping patients form reasonable postoperative recovery expectations, and significantly improving the safety and patient satisfaction of plastic surgery.

[0101] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for simulating and displaying plastic surgery effects based on 3D simulation technology, characterized in that: include, Collect patient facial data and build a multi-level initial facial structure model; Constructing a hybrid deformation model, wherein the hybrid deformation model uses a finite element method and a mass-spring model to describe the mechanical properties of each layer structure; Extracting individualized characteristic parameters of patients, constructing a biomechanical parameter prediction network, and converting the individualized characteristic parameters into corresponding personalized biomechanical parameter sets; Applying the personalized biomechanical parameter set to the hybrid deformation model to optimize the deformation response characteristics of each layer structure; Receive the input parameters of plastic surgery operations, calculate and display the deformation results of each layer structure in real time based on the GPU parallel computing framework; Constructing a tissue healing and recovery kinetic model, and generating appearance prediction data at different time points after surgery according to the deformation results and the tissue healing and recovery kinetic model; Performing three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison display interface; The construction of the blended deformation model comprises the following steps: Construct finite element models of the bone layer and fascia layer, set the mesh nodes of the bone layer as rigid fixed boundary conditions, and define the connection constraint relationship between the fascia layer and the bone layer; Construct a composite deformation model of the muscle layer, apply the nonlinear finite element method to the muscle fiber direction area, apply the mass-spring model to the muscle connection area, and define the sliding constraint relationship between the muscle layer and the fascia layer; Construct a mass spring model of the fat layer, set the spring parameters according to the viscoelastic properties of the fat tissue, and define the adhesion constraint relationship between the fat layer and the muscle layer; A nonlinear finite element model of the skin layer is constructed, the hyperelastic material constitutive equation is introduced to describe the skin deformation characteristics, and the connection constraint relationship between the skin layer and the fat layer is defined; The deformation models of each layer structure are integrated to form a mixed deformation model, material property parameters are applied to the mixed deformation model, and corresponding initial model parameters are configured according to the material properties of each layer structure.

2. The method for simulating and displaying plastic surgery effects based on 3D simulation technology according to claim 1, characterized in that: The construction of the multi-level facial structure initial model comprises the following steps: Collect the patient's facial CT / MRI data and 3D structured light scanning data, and record the patient's facial expression dynamic video sequence; Applying a deep learning segmentation algorithm to process the CT / MRI data to generate a preliminary segmentation mask of the five-layer structure of skin, fat, muscle, fascia, and bone; The 3D structured light scanning data and the CT / MRI data are spatially registered to correct the outer contour of the skin layer segmentation mask; at the same time, the segmentation masks of the muscle layer and the fascia layer are optimized by constructing a facial muscle movement pattern database; Perform boundary smoothing processing on the segmentation mask of each layer structure to generate three-dimensional boundary data; Based on the patient's facial expression dynamic video sequence, the deformation characteristics of each layer structure are measured to calculate material property parameters; The three-dimensional boundary data and material property parameters are integrated to generate a multi-level facial structure initial model.

3. The method for simulating and displaying plastic surgery effects based on 3D simulation technology according to claim 1, characterized in that: The construction of the biomechanical parameter prediction network comprises the following steps: Collect the basic information of the patient to form the patient's individualized feature parameter set, extract the facial structure feature vector of the multi-level facial structure initial model, and integrate it to generate comprehensive feature data; at the same time, build a reference database of facial tissue biomechanical properties; Construct a multi-branch neural network architecture and establish independent prediction channels for the skin layer, fat layer, muscle layer, fascia layer, and bone layer; The multi-branch neural network architecture is adopted to obtain a general model based on the reference database of facial tissue biomechanical properties through pre-training, and a biomechanical parameter prediction network is obtained through training by combining the comprehensive feature data of historical patients through a transfer learning method; The comprehensive characteristic data of the current patient is input into the biomechanical parameter prediction network, and is optimized by combining the patient's facial tissue aging assessment indicators and similar group data in the historical surgical case database to generate a personalized biomechanical parameter set for the patient.

4. The method for simulating and displaying plastic surgery effects based on 3D simulation technology according to claim 1, characterized in that: Applying the personalized biomechanical parameter set to the blended deformation model comprises the following steps: updating material property parameters of the hybrid deformation model according to the personalized biomechanical parameter set, and mapping the updated parameters to mesh node and unit properties of the hybrid deformation model; Perform comprehensive deformation tests, including loading-unloading cycle tests to verify the deformation trajectory and recovery characteristics of each layer structure, and local deformation tests to calculate the displacement field and stress distribution in the facial area and record the deformation response characteristic curve; Compare the deformation response characteristic curve with the standard curve of similar patient groups in the historical data of the historical surgical case database, calculate the deviation value, and generate parameter fine-tuning guidance; The biomechanical parameters of each layer structure are optimized according to the parameter fine-tuning guidance, and the parameter mapping and comprehensive deformation test are repeated until the deformation response accuracy reaches the preset accuracy threshold, and the optimized hybrid deformation model is output.

5. The method for simulating and displaying plastic surgery effects based on 3D simulation technology according to claim 1, characterized in that: The real-time calculation and display of the deformation results of each layer structure based on the GPU parallel computing framework includes the following steps: Receive the plastic surgery parameters input by the doctor, and convert the plastic surgery parameters into mechanical constraints and load distribution parameters of the hybrid deformation model to build a digital mapping model of the surgical operation; Configure the GPU parallel computing framework, divide the computing subdomains according to the spatial distribution of the surgical area, and apply asynchronous adaptive mesh refinement technology to perform mesh encryption on the direct surgical area; Build a heterogeneous parallel solver to assign the sparse matrix solving task of the finite element model to the GPU tensor core, assign the mass calculation of the mass-spring model to the CUDA multi-threaded block, and synchronize the inter-layer force data through shared memory; Perform real-time calculation of tissue deformation and output displacement field, stress field and strain field; The displacement field data is asynchronously transmitted to the visualization module through the GPU-CPU heterogeneous pipeline to generate the deformation result data of each layer structure.

6. The method for simulating and displaying plastic surgery effects based on 3D simulation technology according to claim 1, characterized in that: The generating of appearance prediction data at different time points after surgery comprises the following steps: Construct a tissue healing and recovery dynamics model, including an acute phase sub-model, an edema resolution sub-model, a tissue fibrosis sub-model, and a scar formation sub-model, and define the state variable transfer rules between the sub-models; Import the deformation result data as the initial state after surgery and construct a time series model; The acute phase, edema regression, tissue fibrosis, and scar formation phases in the time series model are executed in sequence. Each phase uses the output state of the previous phase as input and generates the predicted data of the facial tissue state at the corresponding time point through the corresponding sub-model. The output data of each stage are integrated through the time series model to generate the appearance prediction data of the whole cycle of the postoperative recovery process.

7. A plastic surgery effect simulation display system based on 3D simulation technology, based on the plastic surgery effect simulation display method based on 3D simulation technology according to any one of claims 1 to 6, characterized in that: Also includes, The facial structure initialization module is used to collect the patient's facial data and build a multi-level facial structure initial model; A hybrid deformation modeling module is used to construct a hybrid deformation model, wherein the hybrid deformation model uses a finite element method and a mass spring model to describe the mechanical characteristics of each layer structure; A parameter personalization module is used to extract individualized characteristic parameters of patients, construct a biomechanical parameter prediction network, and convert the individualized characteristic parameters into corresponding personalized biomechanical parameter sets; A model parameter optimization module, used for applying the personalized biomechanical parameter set to the hybrid deformation model to optimize the deformation response characteristics of each layer structure; The real-time deformation calculation module is used to receive the operation input parameters of the plastic surgery, and calculate and display the deformation results of each layer structure in real time based on the GPU parallel computing framework; A postoperative recovery prediction module is used to construct a tissue healing and recovery dynamics model, and generate appearance prediction data at different time points after surgery based on the deformation results and the tissue healing and recovery dynamics model; The visualization display module is used to perform three-dimensional visualization processing on the appearance prediction data to form a plastic surgery effect comparison display interface.

Images