A lung tissue deformation simulation method and system based on genetic algorithm optimization of flexibility

Abstract

The application discloses a lung tissue deformation simulation method and system based on genetic algorithm optimization flexibility, and the method comprises the steps of: constructing a lung tetrahedral mesh model, adding volume constraints and shear constraints to the lung tetrahedral mesh model; applying a test force simulating the pushing and pulling of a surgical instrument to the lung tetrahedral mesh model; predicting the position of each node in the lung tetrahedral mesh model at the next moment; solving the volume constraints and shear constraints to obtain the volume position deviation and the shear position deviation, correcting the node position at the next moment according to the volume position deviation and the shear position deviation, repeating the correction process of the node position until a set iteration threshold is reached, and then outputting the final lung tetrahedral mesh model at the next moment; and performing graphic rendering and display on the final lung tetrahedral mesh model at the next moment; the application introduces a constraint model more in line with continuum mechanics, so that dynamic simulation with physical realism and real-time performance is realized on a high-resolution lung model.

Description

Technical Field

[0001] This invention belongs to the field of soft tissue simulation technology, specifically relating to a method and system for simulating lung tissue deformation based on genetic algorithm-optimized flexibility. Background Technology

[0002] Dynamic simulation of soft tissue deformation is a core technology for virtual surgical training, preoperative planning, and surgical robot systems. Lung tissue simulation is particularly challenging because it not only possesses highly nonlinear and nearly incompressible material properties, but also exhibits global, large-scale, low-frequency expansion and contraction during respiratory movements. The simulation must simultaneously meet three major requirements: physical realism, real-time performance, and numerical stability.

[0003] Currently, the mainstream simulation methods are divided into two categories: one is the nonlinear finite element method (NFEM) based on continuum mechanics, which simulates deformation by solving nonlinear equilibrium equations. However, it involves a huge amount of computation, relies on iterative solvers, and is prone to convergence difficulties when dealing with fine lung models or large deformations. It requires the use of extremely small time steps, which makes it difficult to meet the requirements of real-time interaction.

[0004] Second, the recently emerging position dynamics and its improved algorithm, Extended Position Dynamics (XPBD), replaces complex mechanical solutions with position-level constraint projection. It has the advantages of simple implementation, high computational efficiency, and strong robustness. It is suitable for real-time interaction and can control material stiffness through flexibility parameters to simulate elastic deformation.

[0005] However, there are two major bottlenecks when applying extended position dynamics to lung tissue simulation: First, it is difficult to calibrate physical parameters. Its flexibility parameters lack accurate analytical mapping with real material properties, relying on manual trial and error to adjust parameters, which is time-consuming and laborious and cannot guarantee physical accuracy. Second, the constraint model is too simple. Commonly used distance and volume constraints cannot accurately capture the complex stress-strain relationship when lung tissue is under stress, and the mechanical response deviates significantly from that of real hyperelastic materials. Summary of the Invention

[0006] This invention provides a method and system for simulating lung tissue deformation based on genetic algorithm-optimized flexibility. It can maintain the efficiency and stability of the XPBD framework, automatically calibrate physical parameters to match real materials, and introduce a constraint model that is more in line with the mechanics of continuum media, thereby achieving dynamic simulation with both physical realism and real-time performance on a high-resolution lung model.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] The first aspect of this invention provides a method for simulating lung tissue deformation based on genetic algorithm-optimized flexibility, comprising:

[0009] Based on the patient's lung scan image data, image segmentation and three-dimensional surface reconstruction calculations are performed to construct a three-dimensional surface mesh model of lung tissue;

[0010] The tetrahedralization algorithm was used to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a lung tetrahedral mesh model. Volume constraints and shear constraints were then added to the lung tetrahedral mesh model.

[0011] Apply simulated surgical instrument pushing and pulling test force to a lung tetrahedral mesh model; predict the position of each node in the lung tetrahedral mesh model at the next time step within each preset time step;

[0012] Based on the preset optimal compliance parameter set and the node position at the next time step, the volume constraint and shear constraint are solved to obtain the volume position deviation and shear position deviation. The node position at the next time step is corrected based on the volume position deviation and shear position deviation. The node position correction process is repeated iteratively until the set iteration threshold is reached, and then the final lung tetrahedral mesh model at the next time step is output. The final lung tetrahedral mesh model at the next time step is then graphically rendered and displayed.

[0013] Furthermore, volume constraints and shear constraints are added to the lung tetrahedral mesh model, specifically including:

[0014] ;

[0015] ;

[0016] ;

[0017] ;

[0018] In the formula, tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This represents the edge matrix of the current configuration of the tetrahedral element. This represents the edge matrix of the initial configuration of the tetrahedral unit cell; Let be the strain energy density function. For shear constraint function, For volume constraint functions, For trace function, For matrix transpose, It is a determinant function; and Let be Lamé's constant.

[0019] Furthermore, a test force simulating the pushing and pulling of surgical instruments is applied to the lung tetrahedral mesh model; within each preset time step, the position of each node in the lung tetrahedral mesh model at the next moment is predicted, specifically including:

[0020] ;

[0021] ;

[0022] In the formula, For time steps, Let J be the mass matrix of the j-th node; To simulate the pushing and pulling force of surgical instruments, Let the velocity of the j-th node be the velocity at the current time. Let the velocity of the j-th node be the velocity at the next moment. Let j be the position of the j-th node at the current time. Let j be the position of the j-th node at the next moment.

[0023] Furthermore, the optimal compliance parameter set includes compliance parameters for shear constraints and volume constraints, and the process of obtaining the optimal compliance parameter set includes:

[0024] A tetrahedral mesh model of the lungs of experimental lung samples was constructed, and volume constraints and shear constraints were added to obtain the lung sample model.

[0025] The compliance parameters of shear constraints and volume constraints are initialized; a test force is applied to the lung sample model to perform positional dynamics simulation and obtain the deformation simulation results of each node in the lung sample model.

[0026] The simulation fitness of the lung sample model is calculated based on the deformation simulation results of the nodes and the actual deformation of the lung experimental samples.

[0027] With the goal of minimizing the simulation fitness of the lung sample model, the optimal set of compliance parameters is obtained by solving the compliance parameters of shear constraints and volume constraints using a genetic algorithm.

[0028] Furthermore, the simulation fitness of the lung sample model is calculated based on the deformation simulation results of the nodes and the actual deformation of the lung experimental samples, specifically including:

[0029] ;

[0030] ;

[0031] In the formula, The root mean square error between the deformation simulation results and the actual deformation; The deformation simulation result for the j-th node is shown below. is the true deformation of the j-th node, where j is the node index and N is the number of nodes in the lung experimental sample; For simulation fitness.

[0032] Furthermore, with the goal of minimizing the simulation fitness of the lung sample model, the optimal set of compliance parameters is obtained by solving the compliance parameters of shear constraints and volume constraints using a genetic algorithm, specifically including:

[0033] Randomly generated Using chromosomes as the initial population, chromosomes are used as solutions to the set of flexibility parameters. The simulated fitness of each chromosome in the population is calculated. Based on the simulated fitness of each chromosome, roulette wheel selection or tournament selection is used to select high-quality chromosomes in the current population as parent chromosomes to enter the next generation of population iteration.

[0034] H parent chromosome sets are randomly selected, each containing two parent chromosomes; single-point crossover or arithmetic crossover is performed on each parent chromosome set to form offspring chromosomes; random perturbations are added to the offspring chromosomes according to a preset mutation probability;

[0035] The process involves iteratively solving for the compliance parameters of shear constraints and volume constraints using a genetic algorithm. After generations of evolution, the chromosome with the highest fitness in the population is used as the optimal flexibility parameter to find.

[0036] Furthermore, arithmetic crossover is performed on each parent chromosome set to form offspring chromosomes, specifically including:

[0037] ;

[0038] In the formula, For random weights, and The paternal chromosome set, For offspring chromosomes.

[0039] Furthermore, the shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the node position at the next time step, specifically including:

[0040] The deviation energy of the node position at the next time step is expressed by the following formula:

[0041] ;

[0042] In the formula, This represents the deviation energy of the node position at the next moment. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, For trace function, This is the matrix transpose.

[0043] The shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the deviation energy of the node position at the next moment. The formula is as follows:

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] ;

[0049] In the formula, This refers to the time-normalized compliance parameter in the shear constraint. This represents the optimal compliance parameter in the shear constraint. For time steps, Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the generalized inverse mass in shear constraints. The current time step in the shear constraint is represented by the Lagrange multiplier, which is initially set to 0. This represents the current time-increment of the Lagrange multipliers in the shear constraint; This refers to the shear position deviation; For the next time step Lagrange multiplier in the shear constraint, the updated Lagrange multiplier Used to calculate the shear position deviation at the next moment.

[0050] Furthermore, based on the preset optimal compliance parameter set and the node position at the next time step, the volume position deviation is obtained by solving the volume constraint, specifically including:

[0051] ;

[0052] ;

[0053] ;

[0054] ;

[0055] ;

[0056] ;

[0057] In the formula, The static water energy at the node position at the next moment. It is a determinant function. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This refers to the generalized inverse mass within volume constraints. Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the time-normalized compliance parameter in the volume constraint. This is the optimal compliance parameter in the volume constraint. For time steps, For the current Lagrange multiplier in the volume constraint, For the current time step, the Lagrange multiplier increment in the volume constraint. This is due to volume position deviation. For the next time step Lagrange multiplier in volume constraints, the updated Lagrange multiplier Used to calculate the volume position deviation at the next moment.

[0058] A second aspect of the present invention provides a lung tissue deformation simulation system based on genetic algorithm-optimized flexibility, comprising:

[0059] The data acquisition module is used to perform image segmentation and three-dimensional surface reconstruction operations based on the patient's lung scan image data to construct a three-dimensional surface mesh model of lung tissue;

[0060] The model building module uses a tetrahedralization algorithm to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a lung tetrahedral mesh model, and adds volume constraints and shear constraints to the lung tetrahedral mesh model.

[0061] The surgical simulation module applies a simulated surgical instrument pushing and pulling test force to the lung tetrahedral mesh model; within each preset time step, it predicts the position of each node in the lung tetrahedral mesh model at the next moment.

[0062] The position correction module is used to solve the volume constraints and shear constraints according to the preset optimal compliance parameter set and the node position at the next time step to obtain the volume position deviation and shear position deviation. Based on the volume position deviation and shear position deviation, the node position at the next time step is corrected. The node position correction process is repeated iteratively until the set iteration threshold is reached, and then the final lung tetrahedral mesh model at the next time step is output.

[0063] The display rendering module is used to graphically render and display the final tetrahedral mesh model of the lungs at the next moment.

[0064] A third aspect of the present invention provides an electronic terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the lung tissue deformation simulation method of the first aspect.

[0065] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0066] This invention constructs a three-dimensional surface mesh model of lung tissue by combining image segmentation processing with three-dimensional surface reconstruction calculations, which can achieve high-precision and realistic three-dimensional reconstruction of the morphology of the patient's lung tissue. On this basis, a tetrahedralization algorithm is used to mesh the three-dimensional surface mesh model to obtain a lung tetrahedral mesh model with regular structure and excellent quality, which effectively improves the computational adaptability and physical simulation accuracy of the mesh model. Furthermore, volume constraints and shear constraints are applied to the lung tetrahedral mesh model, which can effectively suppress non-physical expansion or contraction of the model volume and unreasonable shear deformation during physical simulation, thereby significantly enhancing the geometric stability and physical realism of the three-dimensional lung tissue model.

[0067] This invention sequentially predicts the spatial positions of all nodes in the model at each preset time step, and simultaneously performs volume constraint and shear constraint solving operations based on the optimized set of flexibility parameters. It calculates the volume position deviation and shear position deviation at the corresponding time step, and uses the two types of deviation results to correct the preliminary predicted node positions in real time. Through iterative node position correction process, until the preset iteration convergence threshold is met, a high-precision tetrahedral mesh model of the lung at the next time step that conforms to the mechanical properties of lung tissue is finally output. This effectively takes into account the volume preservation characteristics of soft tissue and the shear deformation law, improves the accuracy, stability and physical realism of lung deformation prediction during surgical simulation, and reduces mesh distortion and deformation distortion problems. Attached Figure Description

[0068] Figure 1 This is an overall flowchart of the lung tissue deformation simulation method based on genetic algorithm optimization of flexibility provided in Embodiment 1 of the present invention;

[0069] Figure 2 This is a structural diagram of the lung tetrahedral mesh provided in Embodiment 1 of the present invention. Detailed Implementation

[0070] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0071] Example 1

[0072] like Figure 1 As shown, this embodiment provides a lung tissue deformation simulation method based on genetic algorithm to optimize flexibility, including:

[0073] Deformation simulation results were obtained by simulating lung experimental samples. The optimal set of compliance parameters was determined by comparing the deformation simulation results with the actual deformation of the lung experimental samples, specifically including:

[0074] A tetrahedral mesh model of the lungs of experimental lung samples was constructed, and volume constraints and shear constraints were added to obtain the lung sample model.

[0075] The optimal compliance parameter set includes compliance parameters for shear constraints and volume constraints. The compliance parameters for shear constraints and volume constraints are initialized. A test force is applied to the lung sample model to perform position dynamics simulation, and the deformation simulation results of each node in the lung sample model are obtained.

[0076] The simulation fitness of the lung sample model is calculated based on the deformation simulation results of the nodes and the actual deformation of the lung experimental sample, specifically including:

[0077] ;

[0078] ;

[0079] In the formula, The root mean square error between the deformation simulation results and the actual deformation; The deformation simulation result for the j-th node is shown below. is the true deformation of the j-th node, where j is the node index and N is the number of nodes in the lung experimental sample; For simulation fitness.

[0080] With the goal of minimizing the simulation fitness of the lung sample model, the optimal set of compliance parameters is obtained by solving for the compliance parameters of shear constraints and volume constraints using a genetic algorithm. Specifically, this set includes:

[0081] Randomly generated Using chromosomes as the initial population, chromosomes are used as solutions to the set of flexibility parameters. The simulated fitness of each chromosome in the population is calculated. Based on the simulated fitness of each chromosome, roulette wheel selection or tournament selection is used to select high-quality chromosomes in the current population as parent chromosomes to enter the next generation of population iteration.

[0082] H parent chromosome sets are randomly selected, each containing two parent chromosomes; single-point crossover or arithmetic crossover is performed on each parent chromosome set to form offspring chromosomes; random perturbations are added to the offspring chromosomes according to a preset mutation probability; the formula for arithmetic crossover of each parent chromosome set to form offspring chromosomes is as follows:

[0083] ;

[0084] In the formula, For random weights, and The paternal chromosome set, For offspring chromosomes.

[0085] The process involves iteratively solving for the compliance parameters of shear constraints and volume constraints using a genetic algorithm. After generations of evolution, the chromosome with the highest fitness in the population is used as the optimal flexibility parameter to find.

[0086] By minimizing the simulation fitness of the lung sample model as the optimization objective, a genetic algorithm is used to globally optimize the compliance parameters under both shear and volume constraints. This effectively overcomes the shortcomings of traditional trial-and-error methods, which rely on experience and have low convergence efficiency. It quickly obtains the optimal set of compliance parameters that makes the model simulation response highly consistent with the actual mechanical behavior of the lung. This method not only significantly improves the accuracy and automation of parameter calibration and reduces the uncertainty caused by human intervention, but also takes into account the shear and volume deformation characteristics of the material, so that the optimized compliance parameters have better mechanical fidelity under physiological load conditions.

[0087] like Figure 2 As shown, a three-dimensional surface mesh model of lung tissue is constructed by performing image segmentation and three-dimensional surface reconstruction operations based on the patient's lung scan image data; a tetrahedralization algorithm is used to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a tetrahedral mesh model of lung tissue.

[0088] Add volume constraints and shear constraints to the lung tetrahedral mesh model, specifically including:

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] In the formula, tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This represents the edge matrix of the current configuration of the tetrahedral element. This represents the edge matrix of the initial configuration of the tetrahedral unit cell; Let be the strain energy density function. For shear constraint function, For volume constraint functions, For trace function, For matrix transpose, It is a determinant function; and Let be Lamé's constant.

[0094] A tetrahedralization algorithm was used to mesh the 3D surface mesh model, resulting in a well-structured and high-quality tetrahedral mesh model of the lungs. This effectively improved the computational adaptability and physical simulation accuracy of the mesh model. Furthermore, volume constraints and shear constraints were applied to the lung tetrahedral mesh model, which effectively suppressed non-physical expansion or contraction of the model volume and unreasonable shear deformation during the physical simulation process, thereby significantly enhancing the geometric stability and physical realism of the 3D lung tissue model.

[0095] A simulated surgical instrument pushing and pulling force is applied to a lung tetrahedral mesh model; within each preset time step, the positions of each node in the lung tetrahedral mesh model at the next moment are predicted, specifically including:

[0096] ;

[0097] ;

[0098] In the formula, This is the time step; in this embodiment, the time step is 0. Let J be the mass matrix of the j-th node; To simulate the pushing and pulling force of surgical instruments, Let $j$ be the velocity of the j-th node at the current time, with the node's initial velocity being 0. Let the velocity of the j-th node be the velocity at the next moment. Let j be the position of the j-th node at the current time. Let j be the position of the j-th node at the next moment.

[0099] The shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the node position at the next time step, specifically including:

[0100] The deviation energy of the node position at the next time step is expressed by the following formula:

[0101] ;

[0102] In the formula, This represents the deviation energy of the node position at the next moment. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, For trace function, This is the matrix transpose.

[0103] The shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the deviation energy of the node position at the next moment. The formula is as follows:

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] ;

[0109] In the formula, This refers to the time-normalized compliance parameter in the shear constraint. This represents the optimal compliance parameter in the shear constraint. For time steps, Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the generalized inverse mass in shear constraints. The current time step in the shear constraint is represented by the Lagrange multiplier, which is initially set to 0. This represents the current time-increment of the Lagrange multipliers in the shear constraint; This refers to the shear position deviation; For the next time step Lagrange multiplier in the shear constraint, the updated Lagrange multiplier Used to calculate the shear position deviation at the next moment.

[0110] The volume position deviation is obtained by solving the volume constraint based on the preset optimal compliance parameter set and the node position at the next time step, specifically including:

[0111] ;

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] ;

[0117] In the formula, The static water energy at the node position at the next moment. It is a determinant function. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This refers to the generalized inverse mass within volume constraints. Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the time-normalized compliance parameter in the volume constraint. This is the optimal compliance parameter in the volume constraint. For time steps, For the current Lagrange multiplier in the volume constraint, For the current time step, the Lagrange multiplier increment in the volume constraint. This is due to volume position deviation. For the next time step Lagrange multiplier in volume constraints, the updated Lagrange multiplier Used to calculate the volume position deviation at the next moment.

[0118] The node position at the next moment is corrected based on the volume position deviation and the shear position deviation, expressed by the following formula:

[0119] ;

[0120] In the formula, Let j be the position of the j-th node at the current time. This refers to volumetric positional deviation; Let j be the corrected position of the j-th node at the next time step. This represents the shear position deviation.

[0121] The process of correcting the node positions is repeated until the set iteration threshold is reached, and then the final tetrahedral mesh model of the lung at the next time step is output; the final tetrahedral mesh model of the lung at the next time step is then rendered and displayed graphically.

[0122] This embodiment effectively balances the characteristics of soft tissue volume preservation and shear deformation, improving the accuracy, stability, and physical realism of lung deformation prediction during surgical simulation, and reducing mesh distortion and deformation distortion problems.

[0123] Example 2

[0124] This embodiment provides a lung tissue deformation simulation system based on a genetic algorithm to optimize flexibility. The lung tissue deformation simulation system is used to execute the lung tissue deformation simulation method described in Embodiment 1. The lung tissue deformation simulation system includes:

[0125] The data acquisition module is used to perform image segmentation and three-dimensional surface reconstruction operations based on the patient's lung scan image data to construct a three-dimensional surface mesh model of lung tissue;

[0126] The model building module uses a tetrahedralization algorithm to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a lung tetrahedral mesh model, and adds volume constraints and shear constraints to the lung tetrahedral mesh model.

[0127] The surgical simulation module applies a simulated surgical instrument pushing and pulling test force to the lung tetrahedral mesh model; within each preset time step, it predicts the position of each node in the lung tetrahedral mesh model at the next moment.

[0128] The position correction module is used to solve the volume constraints and shear constraints according to the preset optimal compliance parameter set and the node position at the next time step to obtain the volume position deviation and shear position deviation. Based on the volume position deviation and shear position deviation, the node position at the next time step is corrected. The node position correction process is repeated iteratively until the set iteration threshold is reached, and then the final lung tetrahedral mesh model at the next time step is output.

[0129] The display rendering module is used to graphically render and display the final tetrahedral mesh model of the lungs at the next moment.

[0130] Example 3

[0131] This embodiment provides an electronic terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the lung tissue deformation simulation method described in Embodiment 1.

[0132] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for simulating lung tissue deformation based on genetic algorithm for optimizing flexibility, characterized in that, include: Based on the patient's lung scan data, image segmentation and three-dimensional surface reconstruction calculations are performed to construct a three-dimensional surface mesh model of lung tissue; The tetrahedralization algorithm was used to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a lung tetrahedral mesh model. Volume constraints and shear constraints were then added to the lung tetrahedral mesh model. Test forces simulating the pushing and pulling of surgical instruments were applied to a tetrahedral mesh model of the lung; Within each preset time step, predict the position of each node in the lung tetrahedral mesh model at the next moment; Based on the preset optimal compliance parameter set and the node position at the next time step, the volume constraint and shear constraint are solved to obtain the volume position deviation and shear position deviation. The node position at the next time step is corrected based on the volume position deviation and shear position deviation. The node position correction process is repeated iteratively until the set iteration threshold is reached, and then the final lung tetrahedral mesh model at the next time step is output. The final lung tetrahedral mesh model at the next time step is then rendered and displayed graphically.

2. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 1, characterized in that, Add volume constraints and shear constraints to the lung tetrahedral mesh model, specifically including: ； ； ； ； In the formula, tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This represents the edge matrix of the current configuration of the tetrahedral element. This represents the edge matrix of the initial configuration of the tetrahedral unit cell; Let be the strain energy density function. For shear constraint function, For volume constraint functions, For trace function, For matrix transpose, It is a determinant function; and Let be Lamé's constant.

3. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 1, characterized in that, Test forces simulating the pushing and pulling of surgical instruments were applied to a tetrahedral mesh model of the lung; Within each preset time step, predict the positions of each node in the lung tetrahedral mesh model at the next time step, specifically including: ； ； In the formula, For time steps, Let J be the mass matrix of the j-th node; To simulate the pushing and pulling force of surgical instruments, Let the velocity of the j-th node be the velocity at the current time. Let the velocity of the j-th node be the velocity at the next moment. Let j be the position of the j-th node at the current time. Let j be the position of the j-th node at the next moment.

4. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 1, characterized in that, The optimal compliance parameter set includes compliance parameters for shear constraints and volume constraints. The process of obtaining the optimal compliance parameter set includes: A tetrahedral mesh model of the lungs of experimental lung samples was constructed, and volume constraints and shear constraints were added to obtain the lung sample model. The compliance parameters of shear constraints and volume constraints are initialized; a test force is applied to the lung sample model to perform positional dynamics simulation and obtain the deformation simulation results of each node in the lung sample model. The simulation fitness of the lung sample model is calculated based on the deformation simulation results of the nodes and the actual deformation of the lung experimental samples. With the goal of minimizing the simulation fitness of the lung sample model, the optimal set of compliance parameters is obtained by solving the compliance parameters of shear constraints and volume constraints using a genetic algorithm.

5. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 4, characterized in that, The simulation fitness of the lung sample model is calculated based on the deformation simulation results of the nodes and the actual deformation of the lung experimental sample, specifically including: ； ； In the formula, The root mean square error between the deformation simulation results and the actual deformation; The deformation simulation result for the j-th node is shown below. is the actual deformation of the j-th node, where j is the node index and N is the number of nodes in the lung experimental sample; For simulation fitness.

6. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 4, characterized in that, With the goal of minimizing the simulation fitness of the lung sample model, the optimal set of compliance parameters is obtained by solving for the compliance parameters of shear constraints and volume constraints using a genetic algorithm. Specifically, this set includes: Randomly generated Using chromosomes as the initial population, chromosomes are used as solutions to the set of flexibility parameters. The simulated fitness of each chromosome in the population is calculated. Based on the simulated fitness of each chromosome, roulette wheel selection or tournament selection is used to select high-quality chromosomes in the current population as parent chromosomes to enter the next generation of population iteration. H parent chromosome sets are randomly selected, each containing two parent chromosomes; single-point crossover or arithmetic crossover is performed on each parent chromosome set to form offspring chromosomes; random perturbations are added to the offspring chromosomes according to a preset mutation probability; The process involves iteratively solving for the compliance parameters of shear constraints and volume constraints using a genetic algorithm. After generations of evolution, the chromosome with the highest fitness in the population is used as the optimal flexibility parameter to find.

7. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 4, characterized in that, The shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the node position at the next time step, specifically including: The deviation energy of the node position at the next time step is expressed by the following formula: ； In the formula, This represents the deviation energy of the node position at the next moment. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, For trace function, This is the matrix transpose. The shear position deviation is obtained by solving the shear constraint based on the preset optimal compliance parameter set and the deviation energy of the node position at the next moment. The formula is as follows: ； ； ； ； ； In the formula, This refers to the time-normalized compliance parameter in the shear constraint. This represents the optimal compliance parameter in the shear constraint. For time steps, Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the generalized inverse mass in shear constraints. The current time step in the shear constraint represents the Lagrange multiplier, with an initial value of 0. This represents the current time-increment of the Lagrange multipliers in the shear constraint; This refers to the shear position deviation; For the next time step Lagrange multiplier in the shear constraint, the updated Lagrange multiplier Used to calculate the shear position deviation at the next moment.

8. The lung tissue deformation simulation method based on genetic algorithm optimization of flexibility according to claim 4, characterized in that, The volume position deviation is obtained by solving the volume constraint based on the preset optimal compliance parameter set and the node position at the next time step, specifically including: ； ； ； ； ； ； In the formula, The static water energy at the node position at the next moment. It is a determinant function. tetrahedral elements in the tetrahedral mesh model of the lung Deformation gradient, This refers to the generalized inverse mass within volume constraints. Let be the mass of the j-th node; j is the node index; e is the tetrahedral element. This refers to the time-normalized compliance parameter in the volume constraint. This is the optimal compliance parameter in the volume constraint. For time steps, For the current Lagrange multiplier in the volume constraint, For the current time step, the Lagrange multiplier increment in the volume constraint. This is due to volume position deviation. For the next time step Lagrange multiplier in volume constraints, the updated Lagrange multiplier Used to calculate the volume position deviation at the next moment.

9. A lung tissue deformation simulation system based on genetic algorithm for optimizing flexibility, characterized in that, include: The data acquisition module is used to perform image segmentation and three-dimensional surface reconstruction operations based on the patient's lung scan image data to construct a three-dimensional surface mesh model of lung tissue; The model building module uses a tetrahedralization algorithm to perform mesh subdivision processing on the three-dimensional surface mesh model of lung tissue to obtain a lung tetrahedral mesh model, and adds volume constraints and shear constraints to the lung tetrahedral mesh model. The surgical simulation module applies simulated surgical instrument pushing and pulling test forces to a tetrahedral mesh model of the lung. Within each preset time step, predict the position of each node in the lung tetrahedral mesh model at the next moment; The position correction module is used to solve the volume constraints and shear constraints according to the preset optimal compliance parameter set and the node position at the next time step to obtain the volume position deviation and shear position deviation. Based on the volume position deviation and shear position deviation, the node position at the next time step is corrected. The node position correction process is repeated iteratively until the set iteration threshold is reached, and then the final lung tetrahedral mesh model at the next time step is output. The display rendering module is used to graphically render and display the final tetrahedral mesh model of the lungs at the next moment.

10. An electronic terminal, comprising a processor and a storage medium; the storage medium being used to store instructions; characterized in that, The processor is configured to operate according to the instructions to perform the steps of the lung tissue deformation simulation method according to any one of claims 1 to 8.

Images