Patellofemoral joint prosthesis preparation method and system

Abstract

The invention discloses a patellofemoral joint prosthesis preparation method and system, and the method comprises the steps: carrying out the extraction of the anatomical structure of a patellofemoral joint according to the medical image data of a patient, and reconstructing the three-dimensional geometric models of patella and femur; inputting the three-dimensional geometric model into a mechanical simulation platform to obtain a stress distribution diagram of the patellofemoral joint; generating an initial prosthesis model according to the stress distribution diagram and a patient anatomical model, and obtaining a preliminarily optimized prosthesis design scheme in combination with a topological optimization technology and a multi-objective genetic algorithm; and inputting the preliminarily optimized prosthesis design scheme into additive manufacturing equipment to obtain a final patellofemoral joint prosthesis. By utilizing the embodiment of the invention, the design and manufacturing precision of the patellofemoral joint prosthesis can be improved, and the long-term stability and applicability of the patellofemoral joint prosthesis in a biological environment are improved.

Description

Technical Field

[0001] This invention belongs to the field of prosthesis preparation technology, specifically a method and system for preparing patellofemoral joint prostheses. Background Technology

[0002] The patellofemoral joint, a crucial component of the knee joint, directly impacts human mobility and quality of life. However, with age, sports injuries, or joint diseases such as arthritis, the patellofemoral joint can suffer varying degrees of damage, leading to severe pain and limited mobility. In severe cases, patellofemoral replacement surgery becomes a necessary treatment option. To ensure surgical outcomes and the patient's quality of life, the design and fabrication of the patellofemoral joint prosthesis are paramount. Traditional patellofemoral joint prostheses often rely on generic models, lacking precise consideration of the patient's individual anatomy. In such cases, the prosthesis's fit to the patient's biological structure may be insufficient, thus affecting its performance and lifespan. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for preparing patellofemoral joint prostheses, in order to overcome the shortcomings of the prior art, improve the design and manufacturing precision of patellofemoral joint prostheses, and enhance their long-term stability and applicability in biological environments.

[0004] One embodiment of this application provides a method for preparing a patellofemoral joint prosthesis, the method comprising: Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint was extracted, and a three-dimensional geometric model of the patella and femur was reconstructed using a deep learning-based segmentation network combined with an adaptive morphological algorithm. The three-dimensional geometric model is input into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states, and the stress distribution diagram of the patellofemoral joint is obtained. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, by combining topology optimization technology and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme. The preliminary optimized prosthesis design is input into the additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After manufacturing, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis.

[0005] Optionally, the step of extracting the anatomical structure of the patellofemoral joint based on the patient's medical imaging data, and reconstructing a three-dimensional geometric model of the patella and femur using a deep learning-based segmentation network combined with an adaptive morphological algorithm, includes: Based on the patient's medical image data, an edge computing-based data preprocessing method is used to filter noise and enhance contrast in the image data. An adaptive filtering algorithm is used to eliminate artifacts and noise in the images and generate a processed medical image dataset. For the processed medical image dataset, a deep learning-based segmentation network is used to perform structural segmentation by combining the anatomical features of the patella and femur. Through a multi-scale attention mechanism, anatomical details at different scales are captured to generate preliminary patella and femur segmentation results. For the preliminary patella and femur segmentation results, an optimization method based on adaptive morphology algorithm is adopted. Combining the anatomical features of the patella and femur, the segmentation boundary is smoothed and optimized. Through morphological opening and closing operations and edge enhancement technology, the optimized patella and femur segmentation results are generated. The optimized patella and femur segmentation results were used to construct a three-dimensional geometric model based on a surface reconstruction algorithm. The two-dimensional segmentation results were converted into a three-dimensional geometric model. The model was then smoothed and refined using mesh optimization technology to generate the final three-dimensional geometric model of the patella and femur.

[0006] Optionally, the step of inputting the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain a stress distribution map of the patellofemoral joint includes: Based on the three-dimensional geometric model of the patella and femur, a mesh generation method based on finite element analysis is adopted to discretize the geometric model into a finite element mesh. Through adaptive mesh refinement technology, the high-stress area is locally refined to generate a finite element mesh model. For the finite element mesh model, material parameters are defined based on the material properties of the patella and femur. By using motion capture data, the boundary conditions of the patellofemoral joint under different motion states are simulated to generate a preliminary finite element simulation model. For the preliminary finite element simulation model, a mechanical simulation method based on nonlinear finite element analysis is used to simulate the stress distribution of the patellofemoral joint under different motion states. Through iterative solution algorithm, the stress value of each node is calculated to generate preliminary stress distribution data. For the preliminary stress distribution data, a stress distribution map generation method based on visualization technology is adopted to map the stress values ​​onto a three-dimensional geometric model. Through color gradient mapping and contour line drawing technology, an intuitive patellofemoral joint stress distribution map is generated.

[0007] Optionally, based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, combining topology optimization techniques and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminarily optimized prosthesis design scheme, including: Based on the stress distribution map and the patient's anatomical model, a prosthesis design tool based on generative design algorithm was used to generate an initial prosthesis model by combining the anatomical features and mechanical requirements of the patellofemoral joint. For the initial prosthesis model, a geometry optimization method based on topology optimization technology is adopted. Combined with the high stress area in the stress distribution map, the material distribution of the prosthesis is optimized. Inefficient material areas are removed by density filtering algorithm to generate a preliminary optimized prosthesis geometry. For the initially optimized prosthesis geometry, an optimization method based on a multi-objective genetic algorithm is adopted. Combining the mechanical properties and biocompatibility indicators of the prosthesis, the design parameters of the prosthesis are dynamically adjusted. The adjusted prosthesis design scheme is generated through the Pareto optimal solution search algorithm. For the adjusted prosthesis design, a verification method based on finite element analysis was adopted. Combined with the patient's anatomical model and motion state, the mechanical performance and biocompatibility of the design were verified. Through a feedback correction mechanism, the design parameters were dynamically adjusted to generate the final preliminary optimized prosthesis design.

[0008] Optionally, the preliminary optimized prosthesis design is input into additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After manufacturing, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis, comprising: For the preliminary optimized prosthesis design, an additive manufacturing parameter optimization method based on process simulation software is adopted. Combining the characteristics of selective laser melting technology, the manufacturing parameters of laser power, scanning speed and layer thickness are optimized. Through an adaptive parameter adjustment mechanism, the optimal manufacturing parameter configuration is generated. The optimal manufacturing parameters are input into the additive manufacturing equipment, and selective laser melting technology is used to melt metal powder layer by layer to generate a three-dimensional solid structure of the prosthesis. Through a real-time monitoring system, the accuracy and quality of the manufacturing process are ensured, and a preliminary prosthesis solid is generated. For the initial prosthesis, a surface roughness detection method based on optical scanning technology is used to detect the surface roughness of the prosthesis. The surface of the prosthesis is then preliminarily treated by mechanical polishing technology to produce a prosthesis with a smooth surface. For prostheses with smooth surfaces, a surface treatment technology based on plasma electrolytic oxidation is used to generate a dense oxide film on the surface of the prosthesis. Through electrolyte composition optimization and voltage regulation mechanism, the biocompatibility and wear resistance of the prosthesis are enhanced, resulting in the final patellofemoral joint prosthesis.

[0009] Another embodiment of this application provides a patellofemoral joint prosthesis fabrication system, the system comprising: The reconstruction module is used to extract the anatomical structure of the patellofemoral joint based on the patient's medical imaging data, and to reconstruct the three-dimensional geometric model of the patella and femur using a deep learning-based segmentation network combined with an adaptive morphological algorithm. The simulation module is used to input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint. The generation module is used to generate an initial prosthesis model based on the stress distribution map and the patient's anatomical model using a prosthesis design tool based on a generative design algorithm. It also combines topology optimization technology and a multi-objective genetic algorithm to optimize the geometry, material distribution, and mechanical properties of the initial prosthesis model, thereby obtaining a preliminary optimized prosthesis design scheme. The preparation module is used to input the preliminary optimized prosthesis design into the additive manufacturing equipment, use selective laser melting technology to manufacture the prosthesis, and after the manufacturing is completed, use a surface treatment technology based on plasma electrolytic oxidation to enhance the biocompatibility and wear resistance of the prosthesis to obtain the final patellofemoral joint prosthesis.

[0010] Another embodiment of this application provides a storage medium storing a computer program, wherein the computer program is configured to execute the method described in any of the preceding claims when running.

[0011] Another embodiment of this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the method described in any of the preceding claims.

[0012] Compared with existing technologies, the present invention provides a method for fabricating a patellofemoral joint prosthesis. Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a three-dimensional geometric model of the patella and femur is reconstructed. This three-dimensional geometric model is then input into a mechanical simulation platform to obtain a stress distribution map of the patellofemoral joint. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated. Combining topology optimization technology and a multi-objective genetic algorithm, a preliminary optimized prosthesis design scheme is obtained. This preliminary optimized prosthesis design scheme is then input into additive manufacturing equipment to obtain the final patellofemoral joint prosthesis. This method improves the design and manufacturing precision of the patellofemoral joint prosthesis and enhances its long-term stability and applicability in biological environments. Attached Figure Description

[0013] Figure 1 A hardware structure block diagram of a computer terminal for a patellofemoral joint prosthesis fabrication method provided in an embodiment of the present invention; Figure 2 A schematic flowchart illustrating a method for preparing a patellofemoral joint prosthesis according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a patellofemoral joint prosthesis fabrication system provided in an embodiment of the present invention. Detailed Implementation

[0014] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0015] This invention first provides a method for preparing a patellofemoral joint prosthesis, which can be applied to electronic devices, such as computer terminals, specifically ordinary computers.

[0016] The following detailed explanation uses a computer terminal as an example. Figure 1 This is a hardware structure block diagram of a computer terminal for a patellofemoral joint prosthesis fabrication method provided in an embodiment of the present invention. (See diagram below.) Figure 1 As shown, the computer device includes a processor, memory, and network interface connected via a system bus, wherein the memory may include non-volatile storage media and internal memory.

[0017] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any method for fabricating a patellofemoral joint prosthesis.

[0018] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0019] Internal memory provides an environment for the execution of computer programs in non-volatile storage media. When executed by a processor, the computer program can enable the processor to perform any method of patellofemoral joint prosthesis fabrication.

[0020] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0021] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0022] See Figure 2 The present invention provides a method for preparing a patellofemoral joint prosthesis, which may include the following steps: S201: Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a deep learning-based segmentation network combined with an adaptive morphological algorithm is used to reconstruct the three-dimensional geometric model of the patella and femur. In this step, the research team extracts the anatomical structure of the patellofemoral joint from the patient's medical imaging data. This process primarily relies on imaging techniques, such as CT or MRI, to generate detailed anatomical images of the patient. First, the team uses edge computing-based data preprocessing methods to filter noise and enhance contrast in the raw images. Adaptive filtering algorithms are applied to remove artifacts and noise from the images, improving the clarity and accuracy of the image information. After this processing, the generated medical imaging dataset will have higher quality, laying the foundation for the subsequent structure extraction process.

[0023] Next, the team will utilize a deep learning-based segmentation network to analyze the processed medical images, achieving automatic segmentation of the patella and femur. By designing a multi-scale attention mechanism, the network can capture anatomical details at different scales, ensuring the accurate extraction of the patellofemoral joint's anatomical features. At this point, the trained deep learning model will be able to effectively distinguish the boundaries between the patella and femur, generating preliminary segmentation results. This process not only improves the segmentation speed but also enhances its accuracy, ultimately forming a clear anatomical structure model.

[0024] Finally, the team will employ an optimization method based on adaptive morphological algorithms to further process the preliminary segmentation results, ensuring smoothness and optimization of the segmentation boundaries. Combining the anatomical features of the patella and femur, morphological opening and closing operations and edge enhancement techniques will be used to generate optimized patellar and femur segmentation results. This optimization step is crucial because it provides an accurate foundation for subsequent 3D geometric model reconstruction, ensuring that the final generated 3D model accurately reflects the patient's anatomical features.

[0025] This step is crucial in the fabrication of patellofemoral joint prostheses. Precise extraction of anatomical structures provides accurate data support for subsequent 3D modeling and prosthesis design, ensuring the prosthesis effectively matches the patient's biological structure. The combination of deep learning and adaptive morphological algorithms not only improves the automation and accuracy of segmentation but also reduces the need for manual intervention, thereby enhancing efficiency and consistency. These improvements have a significant impact on achieving personalized medicine and improving patient suitability and comfort with prostheses.

[0026] Specifically, based on the patient's medical image data, edge computing-based data preprocessing methods can be used to filter noise and enhance contrast in the image data. Adaptive filtering algorithms can be used to eliminate artifacts and noise in the images and generate a processed medical image dataset. In this phase, the research team will perform data preprocessing to improve the quality of medical images. This process utilizes edge computing technology, which distributes data processing tasks to edge devices closer to the data source, thereby accelerating processing and reducing latency. First, the team will use noise filtering algorithms to remove random noise from the images to improve image clarity. For example, the team may apply methods such as mean filtering to smooth the images without losing important edge information.

[0027] Next, after initial denoising, the team will perform contrast enhancement on the images. This process aims to improve the visibility of image details, making the structures of the patella and femur more clearly defined. Assistant image processing techniques, such as histogram equalization, can be used to adjust brightness and contrast, making the distinction between different anatomical structures more obvious. After contrast enhancement, the details in the images should be clearer, providing a good foundation for subsequent segmentation.

[0028] Finally, the team further optimized the processed medical image dataset by applying an adaptive filtering algorithm. Adaptive filtering can dynamically adjust filtering parameters based on image content, helping to eliminate potential artifacts and improve image quality. This processing step ensures that high-value image data is preserved, setting ideal preconditions for subsequent structural segmentation.

[0029] This step underscores the indispensability of image data preprocessing in prosthesis design. By ensuring high-quality images, the team can effectively improve the segmentation accuracy of the patellofemoral joint anatomy, thereby ensuring a more accurate generated 3D geometric model. This accuracy is crucial for personalized medicine, because only by providing accurate patient anatomical information can a prosthesis be designed to suit the patient, thus improving surgical success rates and prosthesis functionality.

[0030] First, the team acquires medical imaging data from patients in the clinic, typically CT or MRI images. Before data preprocessing, the images need to be converted to a different format for subsequent processing. Edge computing technology plays a crucial role at this stage, rapidly preprocessing large-scale image data by performing data processing on edge devices closer to the patient. Once the images are imported into the edge device, the team applies noise filtering algorithms, such as median filtering or Gaussian filtering, to remove noise introduced by imaging equipment or environmental factors. Median filtering is particularly effective at handling impulse noise because it effectively eliminates noise while preserving edge features.

[0031] Next, image enhancement techniques are used to improve the contrast of the images, ensuring that the details of the patella and femur are more clearly defined. For example, the team can use histogram equalization to expand the brightness range of the images, making low-contrast areas (such as soft tissue) easier to identify. After contrast enhancement, the processed images will display more anatomical details, laying the foundation for the application of segmentation algorithms. At this point, the team also uses visualization tools to observe the processing effect, promptly understanding changes in image quality to determine if further adjustments are needed.

[0032] Finally, to eliminate artifacts and residual noise in the images, the research team employed an adaptive filtering algorithm. This algorithm dynamically adjusts filtering parameters based on local image features, ensuring that important image details are preserved as much as possible while denoising. After adaptive filtering, the resulting medical image dataset will possess good clarity and contrast, providing high-quality input data for subsequent deep learning segmentation tasks. This processing method effectively reduces data noise, improves the accuracy of the segmentation algorithm, and further ensures the smooth progress of subsequent work.

[0033] For the processed medical image dataset, a deep learning-based segmentation network is used to perform structural segmentation by combining the anatomical features of the patella and femur. Through a multi-scale attention mechanism, anatomical details at different scales are captured to generate preliminary patella and femur segmentation results. In this phase, the clinical research team will utilize deep learning technology to segment the anatomical structures of the patella and femur on the processed medical image dataset. By designing and training a deep learning-based segmentation network, the team is able to automatically identify and extract complex structures from the images. The first step in this process is to select an appropriate network architecture, such as the U-Net network, which performs exceptionally well in medical image segmentation tasks.

[0034] During the segmentation process, the team combined the anatomical features of the patella and femur with a multi-scale attention mechanism to improve the model's performance. This multi-scale mechanism allows the network to focus on image features at different resolutions, ensuring that subtle details of the patella and femur are not overlooked. The model extracts features at different levels; for example, it captures edge information at lower levels and obtains global information at higher levels, ultimately achieving accurate anatomical detail recognition.

[0035] After obtaining preliminary patellar and femur segmentation results using a deep learning model, the team will conduct an initial evaluation to determine the model's segmentation accuracy. This step typically involves comparing the results with those obtained manually, using statistical metrics such as the Dice coefficient and IoU index to quantify the segmentation effect and ensure the accuracy and reliability of the results.

[0036] This step highlights the superiority of deep learning technology in medical image processing. Through an automated segmentation process, the team not only improved segmentation efficiency but also enabled the high-precision extraction of the anatomical features of the patellofemoral joint. This accurate extraction lays a solid foundation for subsequent 3D model reconstruction and is crucial for the personalization and adaptability of prosthesis design. Furthermore, deep learning segmentation technology reduces manual operation and minimizes errors caused by human factors, making prosthesis design more scientific and standardized.

[0037] After processing the medical image data, the team builds and trains a deep learning-based segmentation network, typically choosing architectures like U-Net or ResNet, optimized for medical image segmentation. First, the team selects an appropriate training dataset to ensure the model can learn the anatomical features of the patella and femur. Data augmentation techniques (such as rotation, scaling, and flipping) increase the diversity of training samples, helping the model improve its generalization ability. Next, the team trains the model using the processed medical image data, applying a cross-entropy loss function and the Adam optimizer to progressively adjust the network weights, thereby improving the model's segmentation accuracy.

[0038] After training, the team will utilize a multi-scale attention mechanism to segment new medical image data. This mechanism allows the model to focus on image features at different scales, effectively capturing the subtle structures of the patellofemoral joint. For example, when capturing the edge features of the patella, the model combines low-level texture information with high-level shape information, ensuring that the boundaries are not only clearly visible but also reflect the actual shape of the anatomical structure. This attention mechanism can significantly improve the accuracy of segmentation results and reduce segmentation errors caused by neglecting local details.

[0039] Finally, after processing by the deep learning model, the team will generate preliminary patellar and femur segmentation results. At this point, the team needs to evaluate the results, comparing them with manual segmentation results and using metrics such as the Dice coefficient and IoU to quantify the model's performance. Through this comparison, the team can determine the accuracy of the model's segmentation and make necessary adjustments. If significant errors are found in the segmentation results, the team can further optimize the model structure or adjust the training parameters to improve model performance. The final preliminary segmentation results will provide the necessary foundational data for subsequent 3D geometric model reconstruction.

[0040] For the preliminary patella and femur segmentation results, an optimization method based on adaptive morphology algorithm is adopted. Combining the anatomical features of the patella and femur, the segmentation boundary is smoothed and optimized. Through morphological opening and closing operations and edge enhancement technology, the optimized patella and femur segmentation results are generated. In this step, the team will further optimize the initial segmentation results to ensure smoother and more accurate segmentation boundaries for the patella and femur. First, using an adaptive morphological algorithm, combined with the anatomical features of the patella and femur, the team will perform morphological processing on the segmentation boundaries. Morphological opening and closing operations are the core of this process; they effectively eliminate subtle noise by performing dilation followed by erosion, while preserving the overall shape and features of the structure.

[0041] The team will then apply edge enhancement techniques to ensure the clarity and accuracy of the patella and femur boundaries. By enhancing the edges of the segmentation results, the team is able to highlight anatomical boundaries, making the structures of the patella and femur more prominent. This optimization step is crucial because it directly affects the accuracy of subsequent 3D model reconstruction.

[0042] Finally, after optimization and processing, the team generated smoothed and enhanced segmentation results for the patella and femur. This result not only boasts higher accuracy but also prepares the groundwork for generating a three-dimensional geometric model, ensuring that the final model accurately reflects the patient's anatomy. The optimized segmentation results form the basis for the success of subsequent procedures.

[0043] The importance of this step lies in ensuring, through meticulous processing, that the generated anatomical structures reflect realistic biological features and details. The segmentation results, processed with adaptive morphological algorithms and edge enhancement, provide high-quality foundational data for subsequent 3D model reconstruction. This optimization not only improves the accuracy of structural segmentation but also provides reliable anatomical data for prosthesis design, ultimately contributing to improved patient suitability and comfort after surgery.

[0044] After obtaining preliminary patellar and femur segmentation results, the team will apply an adaptive morphological algorithm to optimize the boundaries. First, the team uses morphological opening and closing operations to handle noise and irregular boundaries in the segmentation results. The opening operation, through erosion followed by dilation, effectively eliminates small isolated regions and noise, while the closing operation fills small holes by first dilation and then erosion. This optimization significantly improves the integrity of the segmentation results, making the patellar and femur boundaries smoother and more continuous.

[0045] Next, combining the anatomical features of the patella and femur, the team will apply edge enhancement techniques to improve the clarity of the segmentation boundaries. By using edge detection operators (such as the Sobel operator or Canny edge detection), the team can accurately identify the boundaries of the patella and femur, enhancing the visibility of key anatomical structures. Edge enhancement techniques can highlight those key boundaries and features, making the final segmentation results more realistic and clinically significant. This step ensures the smoothness and realism of the boundaries, which is crucial for subsequent 3D geometric model reconstruction.

[0046] Finally, after adaptive morphological optimization and edge enhancement, the team generates optimized patellar and femur segmentation results. Next, the team uses visualization tools to check the optimization effect, ensuring the segmentation results meet clinical needs. The accuracy and appearance of the optimized segmentation results are verified by comparing them with the original medical images. These optimized segmentation results provide accurate basic data for 3D model reconstruction, a crucial step in ensuring the prosthesis design is suitable for the patient's anatomy. In this way, the team can ensure that the generated model can effectively support the subsequent prosthesis design and manufacturing process.

[0047] The optimized patella and femur segmentation results were used to construct a three-dimensional geometric model based on a surface reconstruction algorithm. The two-dimensional segmentation results were converted into a three-dimensional geometric model. The model was then smoothed and refined using mesh optimization technology to generate the final three-dimensional geometric model of the patella and femur.

[0048] In this phase, the research team will start with the optimized patellar and femur segmentation results and construct a three-dimensional geometric model using surface reconstruction algorithms. First, the team will utilize the segmented two-dimensional image information and apply surface reconstruction algorithms such as Marching Cubes or Dual Contouring to transform this information into a three-dimensional geometric model. These algorithms convert high-dimensional data into a visualized three-dimensional structure by finding isosurfaces in three-dimensional space, providing a foundation for prosthesis design.

[0049] After generating the initial 3D model, the team performs mesh optimization. By using specific mesh simplification and refinement techniques, such as Quadric Error Metrics or Laplacian Smoothing, the team can effectively reduce redundant faces in the model to lower the computational burden while maintaining the realism of the model's shape. This process ensures that the 3D geometric model has a smoother appearance and finer details while preserving important structural features.

[0050] Finally, the generated 3D geometric model will undergo a final evaluation to ensure its accuracy and completeness. The team will verify the model's accuracy by comparing it with the original medical imaging data. Furthermore, if any abnormalities are found, such as uneven boundaries or shape distortion, the team will return to make corresponding adjustments to ensure that the final 3D geometric model of the patella and femur accurately reflects the patient's anatomy and provides reliable data support for subsequent prosthesis design.

[0051] This step is crucial to the entire patellofemoral joint prosthesis fabrication process. By converting the optimized segmentation results into a 3D model, the team is able to provide accurate anatomical data for the personalized design of the prosthesis, which directly impacts the prosthesis's fit, functionality, and comfort. The 3D geometric model not only lays the foundation for subsequent mechanical analysis and prosthesis design but also provides a reference for path planning and material distribution during the manufacturing process. This precise model reconstruction will significantly improve patients' postoperative rehabilitation outcomes, enhance their quality of life, and open up new possibilities for personalized medicine.

[0052] In this phase, the team will utilize the optimized patellar and femur segmentation results to generate a 3D geometric model using surface reconstruction algorithms. First, the team will select a suitable surface reconstruction algorithm, such as Marching Cubes, or in some cases, the Level Set method. The Marching Cubes algorithm transforms the 2D segmentation results into a 3D geometric model by finding isosurfaces. During this process, the algorithm generates point clouds from the segmentation results, converting the boundary information of each segmented region into a computable 3D structure.

[0053] After generating the initial 3D model, the team will implement mesh optimization techniques to improve model quality and computational efficiency. The team will use mesh simplification techniques to reduce the computational burden by decreasing the number of redundant faces while maintaining the realism of the model's shape. For example, Quadric Error Metrics is a commonly used mesh simplification algorithm that calculates the contribution of each face to the overall model error and removes the face with the smallest error. Next, methods such as Laplacian Smoothing are used to smooth the mesh surface, eliminating unsmooth areas in the model caused by the reconstruction process, ensuring the smoothness and detail of the final model.

[0054] Finally, the team conducts a thorough quality assessment, using visualization tools to compare the generated 3D model with the original medical images to ensure accuracy in shape and size. If unreasonable shapes or missing details are found in the model, the team will return for fine-tuning to guarantee high precision. These final 3D geometric models not only provide accurate anatomical data for prosthesis design but also lay a solid foundation for subsequent detailed mechanical simulation analysis. The successful implementation of this process ensures that the personalized design of the prosthesis fully meets the patient's physiological needs, ultimately improving the functionality and comfort of the prosthesis.

[0055] S202, Input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint; In this phase, the research team input the optimized 3D geometric models of the patella and femur into a mechanical simulation platform based on Finite Element Analysis (FEA). First, the team needed to mesh the 3D model, discretizing the geometry into a finite element mesh. This process transforms complex geometries into a series of simple elements, such as tetrahedrons or hexahedrons, facilitating computation. Specifically, the team selected appropriate meshing methods to ensure sufficient mesh density in critical areas of the model (such as the patella-femur contact surface) to accurately capture stress concentration. Adaptive mesh refinement techniques were also used to locally refine high-stress areas, ensuring that details in these areas were not simplified, thereby improving the accuracy of the simulation.

[0056] Next, the team will define corresponding material parameters for the mesh model based on the material properties of the patella and femur. For example, the materials of the patella and femur can be set according to the elastic modulus and Poisson's ratio of actual biological tissues. In the model, the team will also combine motion capture data to simulate the boundary conditions of the patellofemoral joint under different motion states, such as flexion, extension, and rotation. The accurate simulation of these motion states is a key step in ensuring high-quality results, helping to capture the dynamic stress changes of the patellofemoral joint during actual activities.

[0057] Finally, the team will utilize a mechanical simulation method based on nonlinear finite element analysis to calculate the stress value at each node. Iterative solution algorithms will be used to address the stress field at these nodes, enabling efficient numerical calculations and ultimately generating detailed stress distribution data. After the simulation is complete, the team will visualize this data to generate a stress distribution map of the patellofemoral joint. This graphical result clearly demonstrates the stress distribution characteristics of the patellofemoral joint under different movements, thus providing important information for subsequent prosthesis design and optimization.

[0058] This step is of significant clinical importance in the fabrication of patellofemoral joint prostheses. By accurately simulating the stress distribution in the patellofemoral joint, the team can understand the stress changes experienced by the joint under different movement states. This information not only helps in designing the geometry and material distribution of the prosthesis but also lays the foundation for ensuring its mechanical properties and biocompatibility. The resulting stress distribution map will provide scientific data support for prosthesis design, reduce the risk of prosthesis failure, and improve surgical outcomes and long-term rehabilitation quality for patients.

[0059] Specifically, based on the three-dimensional geometric model of the patella and femur, a mesh generation method based on finite element analysis can be used to discretize the geometric model into a finite element mesh. Through adaptive mesh refinement technology, the high-stress area can be locally refined to generate a finite element mesh model. In this step, the team starts with the previously generated 3D geometric models of the patella and femur and applies finite element analysis (FEA) technology to mesh the patella. First, the team selects a suitable meshing method, such as tetrahedral or hexahedral mesh generation techniques. Depending on the model's complexity and computational requirements, the team adjusts the mesh size to ensure sufficient mesh density in critical areas to accurately reflect local shape and stress distribution. For complex biological structures like the patellofemoral joint, an appropriate meshing strategy is crucial as it directly impacts the accuracy and efficiency of subsequent calculations.

[0060] Next, the team will utilize adaptive mesh refinement technology to locally refine the high-stress areas of the patella and femur and their contact surfaces. This strategy ensures that the simulation not only captures the overall stress distribution but also provides in-depth analysis of stress changes in key areas. For example, at the patella-femur contact surface, the direct load during movement may cause a significant increase in local stress. Through local refinement, the calculation results for these areas will be more reliable, providing accurate data support for subsequent analysis and design schemes.

[0061] Finally, after these steps, the team will generate a complete finite element mesh model, preparing it for subsequent analysis. At this point, the team will conduct a mesh quality assessment to ensure that the mesh is free of distortions and duplicate elements, preventing numerical instability during the solution process. A high-quality finite element mesh model provides the necessary foundation for subsequent mechanical simulations, ensuring the reliability and validity of the simulation results.

[0062] Through this mesh generation and refinement process, the team was able to establish a solid foundation for patellofemoral joint biomechanical simulation. The refined finite element mesh model clearly captures the stress distribution characteristics of the joint under different dynamic loads, providing indispensable data support for prosthesis design and optimization. This not only enhances the understanding of joint behavior but also facilitates the subsequent prosthesis design process, ensuring the performance and stability of the prosthesis in clinical applications.

[0063] In this phase, the research team first needed to convert the three-dimensional geometric models of the patella and femur into mesh models suitable for finite element analysis. The purpose of mesh generation is to discretize the complex geometry into various simple computational elements, thus enabling efficient mechanical analysis. The team chose suitable mesh generation strategies, such as using tetrahedral or hexahedral mesh generation techniques. For the complex shape of the patellofemoral joint, hexahedral meshes are more suitable for large-scale calculations because they provide better accuracy in surface interaction and stress distribution. Therefore, when creating the mesh, the team ensured the use of higher-density hexahedral elements in the critical contact areas of the joint to improve computational accuracy.

[0064] During mesh generation, the team considers mesh quality factors. A high-quality mesh should have a good shape and appropriate size; meshes that are too small or too large can lead to computational errors. The team uses software tools (such as ANSYS or Abaqus) to generate the mesh and then applies mesh quality checking tools to verify indicators such as mesh distortion, fineness, and deformation. If any problems are found, the team will go back and adjust the mesh generation parameters to ensure that the generated mesh meets the requirements and ensures its stability and accuracy in numerical simulations.

[0065] After completing the initial mesh generation, the team will implement adaptive mesh refinement technology. Based on the preliminary stress distribution prediction, the team will identify high-stress areas on and around the patellar contact surface and employ a local refinement strategy to generate more fine elements in these areas. This adaptive optimization strategy can significantly improve the precision of stress analysis for complex geometries, ensuring more accurate stress analysis results in high-stress areas and enhancing the rationality and effectiveness of subsequent designs.

[0066] For the finite element mesh model, material parameters are defined based on the material properties of the patella and femur. By using motion capture data, the boundary conditions of the patellofemoral joint under different motion states are simulated to generate a preliminary finite element simulation model. In this step, the team will assign material properties and define boundary conditions to the meshed finite element model. First, based on the biomechanical characteristics of the patella and femur, the team needs to define corresponding material parameters for each element of the mesh model, such as elastic modulus, Poisson's ratio, and density. These parameters are typically derived from literature or experimental data to ensure that the model accurately reflects the mechanical behavior of biological tissues. For example, the elastic modulus of the patella is usually lower than that of the femur, so the team will input different material parameters into the model to efficiently simulate the different characteristics of the two tissues during load-bearing processes.

[0067] Next, the team will use data obtained from motion capture technology to set the boundary conditions for the joints. This includes different motion states, such as knee flexion, standing, or walking. Motion capture data can provide dynamic boundary conditions related to actual biomechanical behavior, ensuring that the simulation results can realistically reflect the load conditions in daily life. The team will meticulously set these conditions, such as defining the motion trajectory of the patellofemoral joint during knee flexion and the associated external force loads, so that subsequent mechanical analysis can be closer to clinical reality.

[0068] Finally, after defining the material properties and boundary conditions, the team will generate a preliminary finite element simulation model. This model will include all physical characteristics and be ready for mechanical simulation analysis. Using various computational tools, the team will ensure the stability and accuracy of the simulation model under various motion states, creating conditions for the next step of stress analysis. The preliminary finite element simulation model provides a comprehensive foundation for further stress analysis and result verification.

[0069] The importance of this process lies in ensuring the realism and reliability of the finite element simulation model through precise material parameter settings and boundary condition definitions. An accurate model provides effective stress distribution data, helping the research team analyze stress changes in the patellofemoral joint during actual movement. This reliable data not only aids in optimizing prosthesis design but also provides a scientific basis for clinical decision-making, ultimately improving patient treatment outcomes and quality of life.

[0070] In the second step, the team needs to define the corresponding material properties for the generated finite element mesh model. These material properties include elastic modulus, Poisson's ratio, and yield strength, all of which are important parameters for the biomechanical properties of joints. For example, the team can set the elastic modulus of the femur to 17 GPa based on literature data, while setting the elastic modulus of the patella to 3 GPa. These different material parameters reflect the different mechanical responses of biological tissues, helping the simulation model to more realistically assess the performance of the patellofemoral joint. After inputting these parameters into the mesh model, the team will ensure that each element has the relevant material properties to improve the reliability and accuracy of the simulation.

[0071] Next, the team will set boundary conditions for the patellofemoral joint's motion states based on motion capture data. This includes the joint's motion trajectory under different activity states. For example, the research team can capture motion data of patients walking, jumping, and knee flexion to establish corresponding boundary conditions. During the setup, the team will define in detail the range of motion, applied forces, and torques of the patellofemoral joint under each motion state to ensure the model's biological plausibility during simulation. In this way, the model will be able to effectively simulate joint behavior in real-world use, ensuring that the results match reality.

[0072] Finally, by combining material properties and boundary conditions, the team will generate a preliminary finite element simulation model. This model will integrate all biomechanical parameters and motion conditions, laying the foundation for subsequent stress analysis. The team will perform a series of checks to ensure that each parameter is correct and conforms to biomechanical standards. In this way, the preliminary finite element simulation model will have good integrity and reliability, laying a solid foundation for subsequent mechanical analysis, especially when comparing and verifying stress distribution under different motion states.

[0073] For the preliminary finite element simulation model, a mechanical simulation method based on nonlinear finite element analysis is used to simulate the stress distribution of the patellofemoral joint under different motion states. Through iterative solution algorithm, the stress value of each node is calculated to generate preliminary stress distribution data. In this step, the team will use nonlinear finite element analysis to further analyze the generated preliminary simulation model. First, the team will select an appropriate numerical solver to handle nonlinear problems, as the contact and deformation characteristics of the patellofemoral joint during motion are typically nonlinear. By setting suitable algorithms (such as the Newton-Raphson iteration method), the team is able to handle complex contact problems and more accurately simulate force transmission paths. This is particularly important for the patellofemoral joint, as it involves interactions between various shapes and materials.

[0074] Next, the team will calculate the stress value of each node using an iterative solution algorithm. This process involves progressive calculation of the entire model, updating the displacement and stress state of the nodes in each iteration to reach convergence. At this stage, the team needs to develop reasonable convergence criteria to ensure that stress changes are accurately captured during the calculation. For example, the team might set a convergence criterion based on stress changes being less than a certain threshold, thereby ensuring the reliability of the final results.

[0075] Finally, after several iterative calculations, the team will obtain preliminary stress distribution data. This data will provide an important foundation for subsequent stress analysis, revealing the stress changes in the patellofemoral joint under different motion states. Through this data, the team will be able to understand the impact of different motion patterns on the joint, providing intuitive scientific evidence for prosthesis design, with the ultimate goal of optimizing the prosthesis to better meet the needs of patients.

[0076] The significance of this step lies in accurately simulating the stress behavior of the patellofemoral joint through nonlinear finite element analysis, helping the team better understand the joint's performance under dynamic loads. This stress distribution data will provide direct feedback for prosthesis design, enabling the design to precisely match the patient's physiological state. In prosthesis design, reliable stress analysis not only improves the fit of the prosthesis but also reduces the risk of postoperative complications, ultimately improving the patient's quality of life and surgical satisfaction.

[0077] In this step, the team will perform stress analysis using nonlinear finite element analysis on the initially generated finite element simulation model. Nonlinear finite element analysis is an effective method for handling complex material and geometric nonlinear problems, and is suitable for the complex biomechanical characteristics of the patellofemoral joint. The team will first select a suitable solver for nonlinear analysis, which typically involves setting appropriate convergence criteria and a nonlinear material model. Through these settings, the team can ensure the accuracy of stress calculations while avoiding numerical instability caused by nonlinear behavior.

[0078] Next, the team will use an iterative solution algorithm to calculate the stress value of each node during the simulation. This process typically involves repeated iterations of numerical solutions, gradually converging to a solution that meets the convergence criteria. In each iteration, the team will update the displacement, stress state, and external force conditions of each node, gradually approaching the optimal solution calculated by the machine. To improve computational efficiency, the team can utilize parallel computing technology, allowing multiple processing units to compute simultaneously, which can significantly shorten the computation time and improve the real-time analysis capability of the model.

[0079] Ultimately, the team will derive preliminary stress distribution data through iterative calculations. This data will reveal the stress distribution of the patellofemoral joint under different motion states, identifying stress concentration and release areas. The team will analyze the preliminary stress data, comparing it with literature data and clinical observations to ensure the scientific validity and rationality of the simulation results. This preliminary data provides a crucial information foundation for subsequent optimization design and prosthesis adjustments, helping to ensure the effectiveness of the prosthesis in practical applications.

[0080] For the preliminary stress distribution data, a stress distribution map generation method based on visualization technology is adopted to map the stress values ​​onto a three-dimensional geometric model. Through color gradient mapping and contour line drawing technology, an intuitive patellofemoral joint stress distribution map is generated.

[0081] In this phase, the team will visualize the initially generated stress distribution data to more intuitively analyze the stress on the patellofemoral joint under different motion states. First, the team will select suitable visualization software tools, such as ParaView or MATLAB, to import the initial stress distribution data and combine it with a three-dimensional geometric model. By mapping stress values ​​onto the three-dimensional model, the team can transform complex numerical results into visual graphics, making understanding and interpretation simpler and more intuitive. For example, the team can set color gradients, representing low-stress areas with cool colors (such as blue) and high-stress areas with warm colors (such as red), allowing observers to easily identify the parts experiencing greater stress.

[0082] Next, the team will apply contour mapping technology to further refine the stress distribution map. By plotting contour lines on the stress distribution map, the team can clearly present the distribution of different stress levels, allowing observers to more intuitively see the stress change trends in each area. This technology can help the team identify potential weaknesses, especially in prosthesis design, where identifying areas of high stress concentration is crucial, as these areas typically require special attention and design optimization.

[0083] Finally, the generated intuitive stress distribution maps will serve as the basis for reports and presentations. The team will write analytical reports based on the visualizations, linking stress distribution to prosthesis design and providing a scientific basis for design decisions. Simultaneously, these graphical results will also be used to communicate with clinicians, enabling them to better understand potential risks during surgery and provide patients with more personalized treatment plans.

[0084] Visualization technology played a crucial role in this process. By transforming dry digital data into intuitive graphics, the team was able to more effectively analyze and understand the stress distribution in the patellofemoral joint, and also help clinicians and patients easily identify critical areas and potential problems. This information is essential for optimizing subsequent prosthesis design, ensuring that the prosthesis can better distribute and bear the load in practical applications, thereby reducing postoperative complications and improving patients' postoperative recovery and quality of life. Ultimately, this process will help advance personalized medicine, ensuring that every patient receives the best possible treatment outcome.

[0085] In this step, the team will visualize the preliminary stress distribution data to more clearly analyze the stress distribution of the patellofemoral joint under different motion states. First, the team selects suitable visualization software tools, such as MATLAB, ParaView, or ANSYS, to generate stress distribution maps. After importing the calculated stress information into the visualization software, the team can map these numerical data onto a three-dimensional geometric model, using different colors and shapes to reflect stress changes. For example, a color gradient from cool to warm colors indicates a change in stress from low to high, allowing observers to quickly identify high-stress areas.

[0086] Next, the team will apply contour mapping technology to further refine the stress distribution map. By adding contour lines to the stress distribution map, the team can clearly show the trend of stress value changes, thus more intuitively observing the stress concentration in specific areas. This method is particularly effective in identifying high-stress areas that may lead to prosthesis failure, enabling the design team to optimize the design in a targeted manner. For example, stress concentration may occur on the joint contact surface, which requires reinforcement measures in subsequent prosthesis design to ensure the structural stability of the prosthesis.

[0087] Finally, the generated stress distribution maps will be used to write analysis reports and communicate with clinicians. This graphical visualization not only improves the efficiency of information transmission but also makes research results more persuasive, helping clinicians understand the potential risks and design choices of surgery. The team may present the visualization results as meeting material to external experts and the radiology team for more in-depth discussions and feedback. This process is crucial for the final design and optimization of the prosthesis, ensuring that it meets the patient's physiological needs and improves treatment outcomes in practical applications.

[0088] S203, Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, by combining topology optimization technology and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme. Based on the patient's stress distribution map and anatomical model, the research team will use a prosthesis design tool based on a generative design algorithm to generate an initial prosthesis model. This process first combines high-stress areas in the stress distribution map with the patient's anatomical features to ensure the prosthesis design can effectively handle actual loads. For example, if the stress distribution map shows significant stress concentration in a specific area of ​​the patella, indicating that this area bears high pressure during movement, the initial prosthesis model design will prioritize strengthening the structure of this area to ensure the prosthesis can effectively distribute the load and reduce potential damage risks. The generative design tool automates model generation through parametric design, enabling designers to quickly generate multiple design options and accelerate the prosthesis design iteration process.

[0089] This step is crucial for ensuring the biomechanical performance of the patellofemoral joint prosthesis. By combining stress distribution maps and anatomical models of the patient, the team is able to design a prosthesis that better meets the individualized needs of the patient, thereby improving the fit and stability of the prosthesis and reducing the risk of postoperative complications. Simultaneously, the application of generative design technology not only improves design efficiency but also ensures the scientific rigor of the design results, laying a solid foundation for subsequent prosthesis optimization and validation. Furthermore, the optimized prosthesis model will have greater structural strength, helping patients recover faster postoperatively and achieve a better quality of life.

[0090] Specifically, based on stress distribution maps and patient anatomical models, a prosthesis design tool based on generative design algorithms can be used to generate an initial prosthesis model, taking into account the anatomical features and mechanical requirements of the patellofemoral joint. In the first step, the team inputs the actual stress distribution map into a prosthesis design tool based on a generative design algorithm. This tool analyzes the patient's anatomical model and stress distribution data, combined with the specific anatomical features of the patellofemoral joint, to automatically generate a preliminary prosthesis model. The design tool is typically based on parametric design principles, allowing for flexible adjustment of the prosthesis's geometry according to actual biomechanical requirements, such as the shape of the patella and the contact surface of the femur. For example, for areas of stress concentration, the tool will correspondingly increase the material thickness in the design to provide better support and protection. The generated initial prosthesis model typically undergoes multiple iterations and is fine-tuned based on the patient's individual anatomical characteristics to ensure good integration with the surrounding bone tissue after placement.

[0091] The significance of this step lies in enhancing the functionality and fit of the prosthesis through personalized design, thereby reducing the risk of postoperative complications. The application of generative design algorithms not only improves design efficiency but also explores design solutions that better meet patient needs, ensuring the biomechanical stability and durability of the prosthesis during use. By prioritizing high-stress areas, the prosthesis will more effectively distribute and bear the load, fully realizing its function and thus improving the patient's postoperative recovery and quality of life.

[0092] First, the research team imports the patient's medical imaging data and the analyzed stress distribution maps into a prosthesis design tool based on generative design algorithms. This tool typically combines parametric modeling and automated design concepts to identify the geometric and mechanical characteristics that the prosthesis needs to meet. During the setup process, the team determines multiple input parameters, including the patient's specific anatomical data, the physical properties of the prosthesis material, and the expected biomechanical function. For example, researchers might use 3D software tools such as SolidWorks or Fusion 360 to first generate a simple patellofemoral joint model, and then increase the material thickness in specific areas (such as the patellar contact surface) based on stress distribution.

[0093] Secondly, the generative design tool performs a comprehensive analysis of each stress concentration area. The system uses algorithms to simulate the impact of variations in material thickness and shape on the prosthesis's strength and stability. For example, if the stress distribution map shows that a certain segment of the patella is under significant stress, the design tool will consider designing reinforcing ribs in that area to increase the prosthesis's support. This process typically involves multiple iterations, gradually adjusting design parameters to ensure that the generated preliminary prosthesis model meets the patient's specific activity requirements in terms of load-bearing capacity.

[0094] Finally, the team will examine the generated initial prosthesis model to ensure it conforms to the patient's physiological structure and meets medical standards. This stage typically involves multiple communications between engineers and clinicians to ensure the design takes into account individual patient differences. After confirming the model, preparations will begin for the next optimization process to further improve the prosthesis's performance.

[0095] For the initial prosthesis model, a geometry optimization method based on topology optimization technology is adopted. Combined with the high stress area in the stress distribution map, the material distribution of the prosthesis is optimized. Inefficient material areas are removed by density filtering algorithm to generate a preliminary optimized prosthesis geometry. In the second step, the team will perform topology optimization on the initial prosthesis model. Based on the high-stress areas in the stress distribution map, they will adjust the material distribution of the prosthesis using geometric optimization methods. Topology optimization technology dynamically removes unnecessary material from the structure by analyzing the stress distribution within the model, retaining high-stress and critical load-bearing areas. Taking the patellofemoral joint prosthesis as an example, if the analysis results show that a certain area is under high stress, topology optimization will increase the material density in that area, correspondingly reducing the material used in low-stress areas. This approach not only ensures the strength and stability of the prosthesis but also reduces its weight without affecting function, improving patient comfort.

[0096] The topology-optimized prosthesis model significantly improves the mechanical performance of the prosthesis, making it more flexible and efficient during movement. By precisely removing redundant material, the prosthesis design becomes more biomechanically compliant, reducing the risk of fatigue failure during use and ensuring a better experience for patients. This process also provides effective data support for subsequent prosthesis validation and improvement, ensuring that the final product meets higher standards.

[0097] In the second step, the team will perform topology optimization on the initially generated prosthetic model. This process first involves stress analysis of the prosthetic model using finite element analysis to identify high-stress areas. Researchers will use software such as ANSYS or COMSOL Multiphysics to calculate the stress distribution of the prosthetic under various operating conditions. Through this analysis, the team can clearly identify which areas bear high stress and which areas are redundant and have low load-bearing capacity.

[0098] Next, combining the stress distribution map, the team will apply density-filtered topology optimization techniques. For example, if certain areas are identified as low-stress regions in the stress distribution map, density filtering algorithms can be used to reduce the material density in these areas or directly remove unnecessary material, thus reducing the weight of the prosthesis and improving patient comfort. Simultaneously, the team may employ a thickening strategy to add material in high-stress areas to ensure the structural strength of the prosthesis. This optimization not only focuses on the aesthetics of the prosthesis but also emphasizes its functionality, utilizing materials in the most effective way.

[0099] Finally, after multiple iterations and optimizations, a preliminary optimized prosthesis geometry was generated. The team then conducted mechanical simulations on the optimized model in various scenarios to confirm its safety and effectiveness in practical use. This process helps the team ensure the biomechanical rationality of the design before final manufacturing, thus laying the foundation for subsequent processing and verification.

[0100] For the initially optimized prosthesis geometry, an optimization method based on a multi-objective genetic algorithm is adopted. Combining the mechanical properties and biocompatibility indicators of the prosthesis, the design parameters of the prosthesis are dynamically adjusted. The adjusted prosthesis design scheme is generated through the Pareto optimal solution search algorithm. In the third step, the team will further refine the initially optimized prosthesis geometry using a multi-objective genetic algorithm. This stage focuses not only on the prosthesis's mechanical properties but also on other factors such as biocompatibility to ensure the design's comprehensiveness and stability. Specifically, the genetic algorithm will simulate biological evolution, iteratively optimizing multiple candidate designs through selection, crossover, and mutation operations. The team will set multiple objective functions, such as minimizing prosthesis weight, increasing structural strength, and enhancing biocompatibility, to find the optimal design using a Pareto optimal solution search algorithm.

[0101] The application of multi-objective genetic algorithms can effectively solve the problem of conflicting multi-dimensional objectives in prosthesis design. This design optimization method not only improves the mechanical properties of the prosthesis but also ensures higher standards in biocompatibility, reducing the risk of postoperative complications due to inappropriate material selection. By dynamically adjusting design parameters, the team can obtain the optimal solution, providing a more scientific and reasonable design basis for the final product and improving the overall quality and performance of the prosthesis.

[0102] In the third step, the team will further optimize the preliminary optimization model using a multi-objective genetic algorithm. First, the researchers will define several optimization objectives related to the prosthesis's performance, such as its strength, stiffness, fatigue life, and biocompatibility. This typically involves setting a series of indicators, such as the prosthesis's load-bearing capacity and its compatibility with surrounding tissues, and quantifying them through mathematical models to ensure they can be effectively evaluated during the optimization process.

[0103] Next, the team will use a genetic algorithm to iteratively refine the initially optimized prosthesis. The basic idea of ​​a genetic algorithm is to find the optimal solution among multiple design candidates by simulating the natural selection process. The team will generate an initial population containing prosthesis models with different design parameters, and gradually approximate the optimal solution through processes such as crossover, mutation, and selection. Each generation of candidate models will undergo finite element analysis to evaluate their performance in terms of mechanical properties and biocompatibility. For example, if a candidate model can reduce weight and improve biocompatibility while maintaining strength, then that model will receive a higher evaluation score and be retained in the next generation.

[0104] Finally, after multiple iterations, the team will arrive at a prosthesis design optimized for multiple objectives. This design will not only achieve the expected goals in terms of mechanical performance but also ensure that biocompatibility meets clinical requirements. The research team will conduct thorough evaluations and discussions at this stage to ensure that the final design can best suit the patient's life and reduce postoperative complications.

[0105] For the adjusted prosthesis design, a verification method based on finite element analysis was adopted. Combined with the patient's anatomical model and motion state, the mechanical performance and biocompatibility of the design were verified. Through a feedback correction mechanism, the design parameters were dynamically adjusted to generate the final preliminary optimized prosthesis design.

[0106] In the final step, the team will conduct a comprehensive validation of the adjusted prosthesis design to ensure its performance in real-world biological environments. Using finite element analysis (FEM) methods, combined with patient anatomical models and motion patterns, the research team can simulate the prosthesis's response under various dynamic loads. This process involves not only testing the prosthesis's mechanical properties but also rigorously evaluating its biocompatibility. The team will design experimental scenarios to simulate real-life patient movements and observe the prosthesis's performance under stress to ensure its safety and effectiveness in practical applications.

[0107] The purpose of this step is to ensure that the use of the prosthesis in the patient's body will not have negative effects and to reduce the risk of postoperative complications. Through validation, the team can identify potential problems in the design and adjust the design parameters in a timely manner, thereby improving the safety and suitability of the final prosthesis. This feedback mechanism not only improves the accuracy of the design but also ensures that the prosthesis meets the needs of individual patients, improving postoperative recovery and the patient's quality of life.

[0108] In the final step, the team will conduct a comprehensive validation of the adjusted prosthesis design to ensure its performance in real-world biological environments. First, researchers will create a finite element model of the prosthesis, combining anatomical models of patients with actual motion patterns. Using finite element analysis software, the team will simulate the prosthesis's behavior under various working conditions, including static and dynamic loads. This stage emphasizes stress analysis, stiffness testing, and fatigue experiments to ensure the prosthesis can withstand the corresponding biomechanical loads in actual clinical applications.

[0109] Secondly, the team will focus on verifying the biocompatibility of the design. This typically involves cell culture experiments under in vitro conditions to observe the cell attachment, proliferation, and differentiation of the prosthetic material. Through collaboration with biomaterials experts, the team will confirm that the selected materials will not induce an immune response and are safely compatible with human tissues. Feedback from this process will directly influence the selection of prosthetic materials and the fine-tuning of design parameters.

[0110] Finally, if design deficiencies are discovered during validation, the team will dynamically adjust the design parameters through a feedback correction mechanism. This may include changing the prosthesis's geometry, material distribution, or even readjusting the optimization objectives. Through systematic iterative feedback, the team can ultimately obtain a prosthesis design that meets all requirements, laying a solid foundation for subsequent manufacturing and clinical application. This stage ensures that the prosthesis achieves ideal performance in both mechanical and biocompatibility aspects, improving patients' postoperative recovery and quality of life.

[0111] S204, the preliminary optimized prosthesis design is input into the additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After the manufacturing is completed, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis.

[0112] In this step, the research team inputs the preliminarily optimized prosthesis design into the additive manufacturing equipment and uses selective laser melting (SLM) technology to manufacture the prosthesis. SLM is a high-precision additive manufacturing process that uses a high-energy laser to melt metal powder layer by layer to form complex three-dimensional structures. The team first needs to set relevant parameters on the additive manufacturing equipment, such as laser power, scanning speed, and layer thickness. These parameters directly affect the final quality and performance of the prosthesis. For example, appropriately increasing the laser power can accelerate the melting speed, but setting it too high may lead to overheating and deformation of the material; therefore, optimization through prior experiments is necessary. During the manufacturing process, a real-time monitoring system monitors each step of the laser melting process to ensure the accuracy and quality of the entire process.

[0113] Manufacturing using selective laser melting (SLM) technology significantly enhances the complexity and precision of prosthesis design. This process allows designers to create prostheses with highly detailed and complex geometries to meet the individualized physiological needs of patients. Furthermore, the metallic materials used in additive manufacturing (such as titanium alloys) possess excellent biocompatibility and mechanical properties, enabling better integration of the prosthesis with the patient's biological tissues. Ultimately, this efficient and precise manufacturing process not only improves the performance and durability of patellofemoral joint prostheses but also shortens production cycles and accelerates the time to clinical application.

[0114] Specifically, for the preliminary optimized prosthesis design, an additive manufacturing parameter optimization method based on process simulation software can be used. Combining the characteristics of selective laser melting technology, the manufacturing parameters such as laser power, scanning speed, and layer thickness can be optimized. Through an adaptive parameter adjustment mechanism, the optimal manufacturing parameter configuration can be generated. In the first step, the team used process simulation software to optimize additive manufacturing parameters to ensure the quality and performance of the prosthesis during production. This process first involves a comprehensive understanding of selective laser melting technology, including the impact of key parameters such as laser power, scanning speed, and layer thickness. The team uses computer simulations to predict melting behavior under different parameter combinations to determine the optimal parameter range. For example, in some cases, increasing laser power can accelerate the manufacturing process, but if the speed is too fast, it may lead to uneven melting, which in turn affects the internal structure of the prosthesis.

[0115] To address this, the team employs an adaptive parameter adjustment mechanism to monitor the manufacturing process in real time. When the monitoring system detects that a parameter configuration does not meet preset standards, it automatically adjusts the parameters, optimizing laser power and scanning speed. By continuously collecting process data and feedback, the team can flexibly respond to various manufacturing challenges, ensuring that the final manufacturing parameter settings produce high-quality prostheses.

[0116] The significance of using process simulation software to optimize additive manufacturing parameters lies in providing a scientific basis and systematic support for the prosthesis production process. By precisely adjusting each parameter, the manufacturing quality of the prosthesis can be significantly improved, material waste reduced, and production costs lowered. Simultaneously, this method also provides reliable assurance for the creation of complex, layered structures, ensuring that the prosthesis meets biomechanical and biocompatibility requirements, thereby improving the patient's surgical success rate and recovery outcome.

[0117] First, the team uses process simulation software to optimize additive manufacturing parameters. This software has the ability to simulate how different manufacturing conditions affect the quality of the final product. The team sets parameter ranges, including key factors such as laser power, scanning speed, and layer thickness, which directly affect the melting and solidification of materials in selective laser melting (SLM). For example, excessively high laser power may lead to over-melting of the material, while too low power may lead to insufficient melting, affecting the strength and density of the prosthesis.

[0118] Next, the team will conduct multiple simulation experiments to model the impact of different parameter combinations on the final prosthesis. By analyzing the simulation results for each parameter combination, the team can identify the optimal parameter configuration, such as finding a combination of laser power and scanning speed that allows the prosthesis to melt and solidify uniformly during heat treatment, avoiding localized stress concentration. The results of each simulation will be recorded in detail to facilitate subsequent parameter adjustments and optimizations.

[0119] Finally, thanks to an adaptive parameter adjustment mechanism, the team can monitor the manufacturing process in real time and adjust parameters accordingly. This mechanism monitors variables such as temperature and speed during laser melting in real time while the equipment is running, ensuring the production quality of each layer. For example, if the monitoring system detects an anomaly in the melting of a certain layer, the team can immediately adjust the laser power or scanning speed to maintain product quality stability. Through this process, the final configuration of manufacturing parameters maximizes the performance and applicability of the prosthesis.

[0120] The optimal manufacturing parameters are input into the additive manufacturing equipment, and selective laser melting technology is used to melt metal powder layer by layer to generate a three-dimensional solid structure of the prosthesis. Through a real-time monitoring system, the accuracy and quality of the manufacturing process are ensured, and a preliminary prosthesis solid is generated. In the second step, the team applied the optimized manufacturing parameters to the additive manufacturing equipment, officially entering the prosthesis manufacturing stage. Using selective laser melting technology, the equipment melts metal powder layer by layer according to the set parameters, gradually building the three-dimensional solid structure of the prosthesis. During the actual manufacturing process, the equipment's laser beam moves precisely according to the instructions of the design model, spraying metal powder and melting it through laser heating.

[0121] This process requires careful attention not only to the laser's intensity and speed but also to close monitoring of the melting process of each layer. The team uses a real-time monitoring system to record temperature changes and powder flow during melting, allowing for the timely detection of any anomalies, such as porosity or incomplete fusion. This enables the team to adjust machine parameters as needed, ensuring reliable adhesion of each layer of the prosthesis and maintaining good structural consistency.

[0122] The layered additive manufacturing process ensures the prosthesis's advantages in complex structures, such as the precision and geometric complexity that traditional manufacturing methods struggle to achieve. By rigorously controlling every step of the manufacturing process, the team can guarantee the quality and strength of the final product, reducing the need for subsequent processing. Furthermore, the metallic materials used in selective laser melting technology not only possess strong mechanical properties but also excellent biocompatibility, laying the foundation for the safe use of the prosthesis within the human body.

[0123] At this stage, the team inputs the optimized manufacturing parameters into the additive manufacturing equipment, officially initiating the prosthesis manufacturing process. The additive manufacturing equipment melts metal powder layer by layer according to the set parameters, constructing the three-dimensional entity of the prosthesis. Selective laser melting (SLM) technology uses a laser to heat metal powder to its melting point at specific locations, thus forming a solid material. Once one layer is melted, the equipment automatically lays down a new layer of metal powder, and the laser processes the next layer, repeating this process until the prosthesis is completely constructed.

[0124] During manufacturing, the team uses a real-time monitoring system to continuously track the melting process. This system can monitor multiple parameters, including laser position, power, speed, and temperature of each layer. If the monitoring system detects any anomalies, such as excessively high temperatures or incomplete melting of the material, it will immediately issue an alarm and adjust the laser parameters to ensure the quality of the melt and the consistency of the finished product.

[0125] Once manufacturing is complete, the team inspects the initial prototype of the prosthesis to ensure its shape and dimensions meet design requirements. This initial quality check may involve visual inspection and preliminary measurements to verify surface smoothness and geometric accuracy. This process ensures the prosthesis meets the required quality standards before formal application, laying the foundation for subsequent post-processing and surface treatment.

[0126] For the initial prosthesis, a surface roughness detection method based on optical scanning technology is used to detect the surface roughness of the prosthesis. The surface of the prosthesis is then preliminarily treated by mechanical polishing technology to produce a prosthesis with a smooth surface. In the third step, the team employed a surface roughness detection method based on optical scanning technology to conduct a comprehensive surface analysis of the initially manufactured prosthesis. Using a high-precision optical scanner, the team was able to perform high-resolution detection of the prosthesis surface, obtaining detailed data on surface roughness. This step is particularly important for the functionality and biocompatibility of the prosthesis, as the smoothness and uniformity of the surface directly affect the contact and adhesion between the prosthesis and surrounding tissues.

[0127] Meanwhile, the team will analyze surface defects based on the test results, such as tiny pits, scratches, or uneven coatings. If left untreated, these defects could become potential breeding grounds for bacteria, affecting the long-term performance and safety of the prosthesis. To further improve the surface quality of the prosthesis, the team will employ mechanical polishing technology to perform preliminary surface treatment, achieving the desired surface roughness standard.

[0128] Through meticulous surface roughness testing, the team ensured that the prosthesis met the required biocompatibility standards, thereby improving its safety for use in the human body. A smooth surface effectively reduces postoperative complications and the risk of infection, while also promoting rapid tissue healing. Furthermore, mechanical polishing not only improves the prosthesis's appearance but also significantly enhances its mechanical properties, ensuring its stability and durability in biological environments.

[0129] At this stage, the team will inspect the surface roughness of the initially manufactured prosthesis to ensure it meets clinical application standards. The team will use high-precision optical scanning technology to comprehensively scan every surface of the prosthesis. This technology can capture minute changes on the surface, generating a high-resolution 3D model, which facilitates the analysis of surface roughness and defects. Using this data, the team can identify any unevenness, scratches, or other defects on the surface.

[0130] Next, the team will assess whether mechanical polishing is necessary based on the test results. Mechanical polishing can significantly improve the smoothness of the prosthesis surface and reduce the impact of surface defects on biocompatibility. If the surface roughness of the prosthesis is found to be higher than the predetermined standard during the scan, the team will use specialized polishing equipment to apply mechanical force evenly to remove micro-protrusions and smooth rough areas on the prosthesis surface. This process typically involves using polishing materials of different particle sizes to gradually increase surface smoothness.

[0131] Finally, after mechanical polishing, the team will conduct a final inspection of the prosthesis surface to ensure that the surface quality meets standards. This inspection process may include reusing optical scanning technology and other surface inspection instruments to ensure that all surfaces meet the designed biocompatibility requirements. Through this series of steps, the team is able to provide a smooth, implantable prosthesis, preparing it for the next step of surface treatment.

[0132] For prostheses with smooth surfaces, a surface treatment technology based on plasma electrolytic oxidation is used to generate a dense oxide film on the surface of the prosthesis. Through electrolyte composition optimization and voltage regulation mechanism, the biocompatibility and wear resistance of the prosthesis are enhanced, resulting in the final patellofemoral joint prosthesis.

[0133] In the final step, the team will perform a surface treatment based on plasma electrolytic oxidation on the mechanically polished prosthesis. This technology can form a dense oxide film on the prosthesis surface, further improving the overall performance of the prosthesis by enhancing the biocompatibility and wear resistance of the material. Specifically, plasma electrolytic oxidation can be performed at lower temperatures, avoiding thermal damage to the prosthesis structure, while the resulting oxide film is uniform and dense, which helps improve the prosthesis's corrosion resistance and biocompatibility in biological environments.

[0134] In implementing this technology, the team optimizes the electrolyte composition and adjusts the voltage and current density to ensure the generated oxide film has good structural properties. For example, adding compounds containing elements such as calcium and phosphorus helps improve the biocompatibility of the membrane. By adjusting the voltage, the electrochemical reaction rate can be controlled, thereby ensuring the integrity and density of the membrane.

[0135] The dense oxide film generated on the prosthesis surface by plasma electrolytic oxidation technology significantly enhances the prosthesis's biocompatibility, helps improve its adhesion to surrounding tissues, and reduces the risk of postoperative infection. Simultaneously, the enhanced wear resistance effectively extends the prosthesis's lifespan and improves its reliability during daily activities. This step ensures excellent prosthesis performance in clinical use, further improving overall treatment outcomes and patients' quality of life.

[0136] In the final step, the team will perform a plasma-electrolytic oxidation-based surface treatment on the polished prosthesis. The core of this technology lies in generating a dense oxide film on the prosthesis surface through an electrochemical reaction. This oxide film not only improves the prosthesis's biocompatibility but also enhances its wear resistance, thereby increasing its lifespan within the body. The team will select a suitable electrolyte and optimize its composition based on the material type to ensure that the oxide film's properties meet expectations.

[0137] Before electrolytic oxidation, the team adjusts the voltage and current to ensure reaction stability and film consistency. For example, when processing titanium alloys, the team sets a specific current density to ensure uniform oxide film thickness while avoiding damage to the material from excessive current. Furthermore, the team monitors the reaction process in real time to ensure that oxide film formation meets design standards.

[0138] After processing, the team will test the thickness and bonding strength of the oxide film to ensure it meets clinical requirements. Through these steps, the team will ultimately produce a patellofemoral joint prosthesis that meets the expected performance standards, possesses good biocompatibility and wear resistance, and can effectively meet the needs of patients. This series of processes ensures the long-term stability of the prosthesis after implantation, providing a solid foundation for the patient's rehabilitation.

[0139] As can be seen, based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a three-dimensional geometric model of the patella and femur is reconstructed. The three-dimensional geometric model is then input into a mechanical simulation platform to obtain a stress distribution map of the patellofemoral joint. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated. Combining topology optimization technology and a multi-objective genetic algorithm, a preliminary optimized prosthesis design scheme is obtained. The preliminary optimized prosthesis design scheme is then input into additive manufacturing equipment to obtain the final patellofemoral joint prosthesis. This process can improve the design and manufacturing accuracy of the patellofemoral joint prosthesis and enhance its long-term stability and applicability in a biological environment.

[0140] Another embodiment of the present invention provides a patellofemoral joint prosthesis fabrication system, see [link to documentation]. Figure 3 The system may include: The reconstruction module 301 is used to extract the anatomical structure of the patellofemoral joint based on the patient's medical imaging data, and to reconstruct the three-dimensional geometric model of the patella and femur using a deep learning-based segmentation network combined with an adaptive morphological algorithm. The simulation module 302 is used to input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint. The generation module 303 is used to generate an initial prosthesis model based on the stress distribution map and the patient's anatomical model using a prosthesis design tool based on a generative design algorithm, and to optimize the geometry, material distribution and mechanical properties of the initial prosthesis model by combining topology optimization technology and a multi-objective genetic algorithm to obtain a preliminary optimized prosthesis design scheme. The preparation module 304 is used to input the preliminary optimized prosthesis design into the additive manufacturing equipment, use selective laser melting technology to manufacture the prosthesis, and after the manufacturing is completed, use a surface treatment technology based on plasma electrolytic oxidation to enhance the biocompatibility and wear resistance of the prosthesis to obtain the final patellofemoral joint prosthesis.

[0141] As can be seen, based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a three-dimensional geometric model of the patella and femur is reconstructed. The three-dimensional geometric model is then input into a mechanical simulation platform to obtain a stress distribution map of the patellofemoral joint. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated. Combining topology optimization technology and a multi-objective genetic algorithm, a preliminary optimized prosthesis design scheme is obtained. The preliminary optimized prosthesis design scheme is then input into additive manufacturing equipment to obtain the final patellofemoral joint prosthesis. This process can improve the design and manufacturing accuracy of the patellofemoral joint prosthesis and enhance its long-term stability and applicability in a biological environment.

[0142] This invention also provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0143] Specifically, in this embodiment, the storage medium can be configured to store a computer program for performing the following steps: S201: Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a deep learning-based segmentation network combined with an adaptive morphological algorithm is used to reconstruct the three-dimensional geometric model of the patella and femur. S202, Input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint; S203, Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, by combining topology optimization technology and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme. S204, the preliminary optimized prosthesis design is input into the additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After the manufacturing is completed, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis.

[0144] As can be seen, based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a three-dimensional geometric model of the patella and femur is reconstructed. The three-dimensional geometric model is then input into a mechanical simulation platform to obtain a stress distribution map of the patellofemoral joint. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated. Combining topology optimization technology and a multi-objective genetic algorithm, a preliminary optimized prosthesis design scheme is obtained. The preliminary optimized prosthesis design scheme is then input into additive manufacturing equipment to obtain the final patellofemoral joint prosthesis. This process can improve the design and manufacturing accuracy of the patellofemoral joint prosthesis and enhance its long-term stability and applicability in a biological environment.

[0145] This invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0146] Specifically, the aforementioned electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the aforementioned processor, and the input / output device is connected to the aforementioned processor.

[0147] Specifically, in this embodiment, the processor can be configured to perform the following steps via a computer program: S201: Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a deep learning-based segmentation network combined with an adaptive morphological algorithm is used to reconstruct the three-dimensional geometric model of the patella and femur. S202, Input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint; S203, Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, by combining topology optimization technology and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme. S204, the preliminary optimized prosthesis design is input into the additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After the manufacturing is completed, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis.

[0148] As can be seen, based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint is extracted, and a three-dimensional geometric model of the patella and femur is reconstructed. The three-dimensional geometric model is then input into a mechanical simulation platform to obtain a stress distribution map of the patellofemoral joint. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated. Combining topology optimization technology and a multi-objective genetic algorithm, a preliminary optimized prosthesis design scheme is obtained. The preliminary optimized prosthesis design scheme is then input into additive manufacturing equipment to obtain the final patellofemoral joint prosthesis. This process can improve the design and manufacturing accuracy of the patellofemoral joint prosthesis and enhance its long-term stability and applicability in a biological environment.

[0149] The above description, based on the embodiments shown in the figures, details the structure, features, and effects of the present invention. The above description is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the figures. Any changes made in accordance with the concept of the present invention, or equivalent embodiments modified to have equivalent changes, that do not exceed the spirit covered by the specification and figures, should be within the protection scope of the present invention.

Claims

1. A method for preparing a patellofemoral joint prosthesis, characterized in that, The method includes: Based on the patient's medical imaging data, the anatomical structure of the patellofemoral joint was extracted, and a three-dimensional geometric model of the patella and femur was reconstructed using a deep learning-based segmentation network combined with an adaptive morphological algorithm. The three-dimensional geometric model is input into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states, and the stress distribution diagram of the patellofemoral joint is obtained. Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, by combining topology optimization technology and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme. The preliminary optimized prosthesis design is input into the additive manufacturing equipment, and the prosthesis is manufactured using selective laser melting technology. After manufacturing, a surface treatment technology based on plasma electrolytic oxidation is used to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis.

2. The method according to claim 1, characterized in that, The process involves extracting the anatomical structure of the patellofemoral joint based on the patient's medical imaging data, and then reconstructing a three-dimensional geometric model of the patella and femur using a deep learning-based segmentation network combined with an adaptive morphological algorithm. Based on the patient's medical image data, an edge computing-based data preprocessing method is used to filter noise and enhance contrast in the image data. An adaptive filtering algorithm is used to eliminate artifacts and noise in the images and generate a processed medical image dataset. For the processed medical image dataset, a deep learning-based segmentation network is used to perform structural segmentation by combining the anatomical features of the patella and femur. Through a multi-scale attention mechanism, anatomical details at different scales are captured to generate preliminary patella and femur segmentation results. For the preliminary patella and femur segmentation results, an optimization method based on adaptive morphology algorithm is adopted. Combining the anatomical features of the patella and femur, the segmentation boundary is smoothed and optimized. Through morphological opening and closing operations and edge enhancement technology, the optimized patella and femur segmentation results are generated. The optimized patella and femur segmentation results were used to construct a three-dimensional geometric model based on a surface reconstruction algorithm. The two-dimensional segmentation results were converted into a three-dimensional geometric model. The model was then smoothed and refined using mesh optimization technology to generate the final three-dimensional geometric model of the patella and femur.

3. The method according to claim 2, characterized in that, The process of inputting the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtaining a stress distribution map of the patellofemoral joint includes: Based on the three-dimensional geometric model of the patella and femur, a mesh generation method based on finite element analysis is adopted to discretize the geometric model into a finite element mesh. Through adaptive mesh refinement technology, the high-stress area is locally refined to generate a finite element mesh model. For the finite element mesh model, material parameters are defined based on the material properties of the patella and femur. By using motion capture data, the boundary conditions of the patellofemoral joint under different motion states are simulated to generate a preliminary finite element simulation model. For the preliminary finite element simulation model, a mechanical simulation method based on nonlinear finite element analysis is used to simulate the stress distribution of the patellofemoral joint under different motion states. Through iterative solution algorithm, the stress value of each node is calculated to generate preliminary stress distribution data. For the preliminary stress distribution data, a stress distribution map generation method based on visualization technology is adopted to map the stress values ​​onto a three-dimensional geometric model. Through color gradient mapping and contour line drawing technology, an intuitive patellofemoral joint stress distribution map is generated.

4. The method according to claim 3, characterized in that, Based on the stress distribution map and the patient's anatomical model, an initial prosthesis model is generated using a prosthesis design tool based on a generative design algorithm. Then, combining topology optimization techniques and a multi-objective genetic algorithm, the geometry, material distribution, and mechanical properties of the initial prosthesis model are optimized to obtain a preliminary optimized prosthesis design scheme, including: Based on the stress distribution map and the patient's anatomical model, a prosthesis design tool based on generative design algorithm was used to generate an initial prosthesis model by combining the anatomical features and mechanical requirements of the patellofemoral joint. For the initial prosthesis model, a geometry optimization method based on topology optimization technology is adopted. Combined with the high stress area in the stress distribution map, the material distribution of the prosthesis is optimized. Inefficient material areas are removed by density filtering algorithm to generate a preliminary optimized prosthesis geometry. For the initially optimized prosthesis geometry, an optimization method based on a multi-objective genetic algorithm is adopted. Combining the mechanical properties and biocompatibility indicators of the prosthesis, the design parameters of the prosthesis are dynamically adjusted. The adjusted prosthesis design scheme is generated through the Pareto optimal solution search algorithm. For the adjusted prosthesis design, a verification method based on finite element analysis was adopted. Combined with the patient's anatomical model and motion state, the mechanical performance and biocompatibility of the design were verified. Through a feedback correction mechanism, the design parameters were dynamically adjusted to generate the final preliminary optimized prosthesis design.

5. The method according to claim 4, characterized in that, The process involves inputting the preliminarily optimized prosthesis design into additive manufacturing equipment, using selective laser melting technology to manufacture the prosthesis, and then employing a plasma electrolytic oxidation-based surface treatment technology to enhance the biocompatibility and wear resistance of the prosthesis, resulting in the final patellofemoral joint prosthesis, comprising: For the preliminary optimized prosthesis design, an additive manufacturing parameter optimization method based on process simulation software is adopted. Combining the characteristics of selective laser melting technology, the manufacturing parameters of laser power, scanning speed and layer thickness are optimized. Through an adaptive parameter adjustment mechanism, the optimal manufacturing parameter configuration is generated. The optimal manufacturing parameters are input into the additive manufacturing equipment, and selective laser melting technology is used to melt metal powder layer by layer to generate a three-dimensional solid structure of the prosthesis. Through a real-time monitoring system, the accuracy and quality of the manufacturing process are ensured, and a preliminary prosthesis solid is generated. For the initial prosthesis, a surface roughness detection method based on optical scanning technology is used to detect the surface roughness of the prosthesis. The surface of the prosthesis is then preliminarily treated by mechanical polishing technology to produce a prosthesis with a smooth surface. For prostheses with smooth surfaces, a surface treatment technology based on plasma electrolytic oxidation is used to generate a dense oxide film on the surface of the prosthesis. Through electrolyte composition optimization and voltage regulation mechanism, the biocompatibility and wear resistance of the prosthesis are enhanced, resulting in the final patellofemoral joint prosthesis.

6. A patellofemoral joint prosthesis fabrication system, characterized in that, The system includes: The reconstruction module is used to extract the anatomical structure of the patellofemoral joint based on the patient's medical imaging data, and to reconstruct the three-dimensional geometric model of the patella and femur using a deep learning-based segmentation network combined with an adaptive morphological algorithm. The simulation module is used to input the three-dimensional geometric model into a mechanical simulation platform based on finite element analysis to simulate the stress distribution of the patellofemoral joint under different motion states and obtain the stress distribution diagram of the patellofemoral joint. The generation module is used to generate an initial prosthesis model based on the stress distribution map and the patient's anatomical model using a prosthesis design tool based on a generative design algorithm. It also combines topology optimization technology and a multi-objective genetic algorithm to optimize the geometry, material distribution, and mechanical properties of the initial prosthesis model, thereby obtaining a preliminary optimized prosthesis design scheme. The preparation module is used to input the preliminary optimized prosthesis design into the additive manufacturing equipment, use selective laser melting technology to manufacture the prosthesis, and after the manufacturing is completed, use a surface treatment technology based on plasma electrolytic oxidation to enhance the biocompatibility and wear resistance of the prosthesis to obtain the final patellofemoral joint prosthesis.

7. The system according to claim 6, characterized in that, The reconstruction module is specifically used for: Based on the patient's medical image data, an edge computing-based data preprocessing method is used to filter noise and enhance contrast in the image data. An adaptive filtering algorithm is used to eliminate artifacts and noise in the images and generate a processed medical image dataset. For the processed medical image dataset, a deep learning-based segmentation network is used to perform structural segmentation by combining the anatomical features of the patella and femur. Through a multi-scale attention mechanism, anatomical details at different scales are captured to generate preliminary patella and femur segmentation results. For the preliminary patella and femur segmentation results, an optimization method based on adaptive morphology algorithm is adopted. Combining the anatomical features of the patella and femur, the segmentation boundary is smoothed and optimized. Through morphological opening and closing operations and edge enhancement technology, the optimized patella and femur segmentation results are generated. The optimized patella and femur segmentation results were used to construct a three-dimensional geometric model based on a surface reconstruction algorithm. The two-dimensional segmentation results were converted into a three-dimensional geometric model. The model was then smoothed and refined using mesh optimization technology to generate the final three-dimensional geometric model of the patella and femur.

8. The method according to claim 7, characterized in that, The simulation module is specifically used for: Based on the three-dimensional geometric model of the patella and femur, a mesh generation method based on finite element analysis is adopted to discretize the geometric model into a finite element mesh. Through adaptive mesh refinement technology, the high-stress area is locally refined to generate a finite element mesh model. For the finite element mesh model, material parameters are defined based on the material properties of the patella and femur. By using motion capture data, the boundary conditions of the patellofemoral joint under different motion states are simulated to generate a preliminary finite element simulation model. For the preliminary finite element simulation model, a mechanical simulation method based on nonlinear finite element analysis is used to simulate the stress distribution of the patellofemoral joint under different motion states. Through iterative solution algorithm, the stress value of each node is calculated to generate preliminary stress distribution data. For the preliminary stress distribution data, a stress distribution map generation method based on visualization technology is adopted to map the stress values ​​onto a three-dimensional geometric model. Through color gradient mapping and contour line drawing technology, an intuitive patellofemoral joint stress distribution map is generated.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method of any one of claims 1-5 when it is run.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1-5.

Images