Skeleton three-dimensional positioning adaptive adjustment method and device in combination with big data

Abstract

The invention provides a bone slice three-dimensional positioning adaptive adjustment method and device in combination with big data, and relates to the technical field of positioning adjustment, and the method comprises the steps: building a bone tissue three-dimensional model of a surgical site; calling historical operation case data to perform feature extraction and training, and constructing a bone slice positioning prediction model; inputting the bone tissue three-dimensional model into a bone slice positioning prediction model, and screening out an optimal position and an optimal angle; determining a bone sheet lifting shape design scheme; manufacturing a bone sheet lifting entity according to the bone sheet lifting shape design scheme, and performing implantation simulation in the virtual environment to obtain a bone sheet simulation implantation result; and the space interference state of the bone slice lifting entity is collected in real time and is dynamically adjusted. The technical problem that accurate matching of the bone structure of the patient is further affected due to the fact that changes of the bone form and damage characteristics cannot be effectively handled in the prior art can be solved, and the technical effect of improving the matching accuracy of the bone sheet and the bone structure is achieved.

Description

Technical Field

[0001] This application relates to the field of positioning and adjustment technology, and in particular to a method and device for adaptive adjustment of bone fragment three-dimensional positioning using big data. Background Technology

[0002] With the continuous advancement of medical imaging, existing bone fragment localization and design schemes mainly rely on traditional imaging data and surgical experience. Although these methods can provide some guidance, they have significant shortcomings in terms of accuracy and adaptability.

[0003] Currently, existing technologies still suffer from the inability to monitor and adjust the deviation between the strategies and permissions of game participants in real time. This leads to an inability to effectively respond to dynamic changes in participant strategies during task execution, further impacting system collaboration efficiency and task execution stability. Furthermore, existing technologies fail to effectively integrate the dynamic changes in real-time sensor data and surgical procedure data, resulting in bone fragment localization schemes often being unable to flexibly address various emergencies and the needs of different patients in practical applications.

[0004] In summary, existing technologies suffer from the technical problem that the bone fragment positioning and design methods based on real-time data feedback and dynamic adjustment cannot effectively address changes in bone morphology and injury characteristics, further affecting the accurate matching of patients' bone structures. Summary of the Invention

[0005] The purpose of this application is to provide a method and device for adaptive adjustment of bone fragment three-dimensional positioning based on big data, in order to solve the technical problem that existing bone fragment positioning and design methods based on real-time data feedback and dynamic adjustment cannot effectively cope with changes in bone morphology and injury characteristics, and further affect the accurate matching of the patient's bone structure.

[0006] In view of the above problems, this application provides a method and device for adaptive adjustment of bone fragment three-dimensional positioning by combining big data.

[0007] Firstly, this application provides a bone fragment three-dimensional positioning adaptive adjustment method combining big data, implemented through a bone fragment three-dimensional positioning adaptive adjustment device combining big data, comprising: acquiring three-dimensional image data of the surgical site and establishing a three-dimensional model of bone tissue based on the three-dimensional image data; calling historical surgical case data for feature extraction and training to construct a bone fragment positioning prediction model; inputting the bone tissue three-dimensional model into the bone fragment positioning prediction model, matching similar case data from the historical surgical case data, and selecting the optimal position and optimal angle based on the similar case data; retrieving a material database according to the optimal position and optimal angle to determine a bone fragment support shape design scheme; manufacturing a bone fragment support entity according to the bone fragment support shape design scheme, and performing implantation simulation in a virtual environment to obtain the simulated bone fragment implantation result; and collecting the spatial interference state of the bone fragment support entity in real time, making dynamic adjustments, and recording the iterative optimization for the bone fragment positioning prediction model.

[0008] Preferably, the bone fragment three-dimensional localization adaptive adjustment method combining big data further includes: separating the three-dimensional image data to obtain the bone tissue region and the background region; performing three-dimensional reconstruction of the bone tissue region to generate an initial three-dimensional bone tissue model; marking anatomical landmarks on the initial three-dimensional bone tissue model and calculating the spatial positional relationship between the anatomical landmarks; determining the gray value distribution of the bone tissue region and quantifying the density distribution parameter; and constructing the three-dimensional bone tissue model based on the spatial positional relationship and the density distribution parameter.

[0009] Preferably, the bone fragment three-dimensional localization adaptive adjustment method combined with big data further includes: preprocessing the three-dimensional image data to obtain tissue edges, the preprocessing including anisotropic filtering for noise reduction and contrast adaptive enhancement; based on the tissue edges, setting a separation threshold using a grayscale histogram analysis method to separate the background region and tissue region in the three-dimensional image data to obtain initial separated data; using preset high-density feature points of the tissue region in the initial separated data as seed points, expanding to neighboring pixels according to a preset grayscale similarity criterion to extract the bone tissue region; using an edge detection operator to extract the contour features of the bone tissue region, and filling the bone tissue region with morphological opening and closing operations; distinguishing the bone tissue region from the residual soft tissue region using a shape feature analysis algorithm, and removing artifact regions to obtain the separated bone tissue region; and extracting the bone tissue region based on the three-dimensional image data to obtain the background region.

[0010] Preferably, the adaptive adjustment method for three-dimensional bone fragment localization using big data further includes: collecting historical surgical case data, which includes preoperative imaging data, bone fragment design parameters, surgical operation records, and postoperative follow-up evaluation data; extracting bone fragment localization feature vectors and bone fragment localization effect feature vectors from the standardized historical surgical case data, whereby the bone fragment localization feature vectors include anatomical structural features, lesion type features, and biomechanical features; and training the bone fragment localization feature vectors and bone fragment localization effect feature vectors using machine learning algorithms to establish the bone fragment localization prediction model.

[0011] Preferably, the bone fragment three-dimensional localization adaptive adjustment method combining big data further includes: converting the bone tissue three-dimensional model into a feature vector matrix to be matched; inputting the feature vector matrix to be matched into the bone fragment localization prediction model, calculating the distance measure between the feature vector matrix to be matched and the historical surgical case data; filtering out a set of candidate cases within a preset distance threshold based on the distance measure; performing anatomical structure similarity and pathological feature similarity analysis on the set of candidate cases, and outputting the case with the highest similarity score as the similar case data.

[0012] Preferably, the bone fragment three-dimensional positioning adaptive adjustment method combining big data further includes: extracting three-dimensional coordinate data and fixed angle parameters of the bone fragment implantation location from the similar case data; combining the anatomical morphological features of the three-dimensional model of the bone tissue to perform coordinate adaptation on the three-dimensional coordinate data and fixed angle parameters to obtain a candidate adaptation location set and a candidate adaptation angle set; simulating the mechanical conduction performance of the bone fragment based on the candidate adaptation location set and candidate adaptation angle set; and selecting the adaptation location and adaptation angle with a preset stress distribution and a preset stability threshold as the optimal location and optimal angle based on the mechanical conduction performance analysis results.

[0013] Preferably, the bone fragment three-dimensional positioning adaptive adjustment method combining big data further includes: determining the support area to be covered by the bone fragment based on the optimal position and optimal angle; generating an initial geometric shape contour of the bone fragment according to the three-dimensional curved surface morphology of the support area; searching the material database and selecting a list of candidate materials that meet preset biocompatibility and mechanical performance support requirements based on the initial geometric shape contour; determining a target material formula from the candidate material list according to the patient's bone density parameters and expected load requirements; and generating the bone fragment support shape design scheme by combining the initial geometric shape contour and the target material formula.

[0014] Preferably, the bone fragment three-dimensional positioning adaptive adjustment method combining big data further includes: mapping the bone fragment support shape design scheme into layered slice data suitable for additive manufacturing equipment; configuring printing parameters according to the layered slice data, forming the bone fragment support entity through additive manufacturing process; constructing the virtual environment, simulating the implantation of the bone fragment support entity in the virtual environment, detecting the spatial interference state between the bone fragment support entity and surrounding tissues in the virtual environment, and obtaining the simulated bone fragment implantation result if the spatial interference state meets the preset interference standard.

[0015] Preferably, the bone fragment three-dimensional positioning adaptive adjustment method combined with big data further includes: acquiring the spatial interference state of the bone fragment supporting the entity in real time through a pre-embedded bone fragment sensing unit; acquiring the theoretical pressure range corresponding to the current surgical stage and acquiring the theoretical spatial interference state; calculating the state deviation between the spatial interference state and the theoretical spatial interference state, determining whether the state deviation exceeds a preset safety threshold, and generating a comparison analysis result containing deviation details.

[0016] Secondly, this application also provides a bone fragment three-dimensional positioning adaptive adjustment device combining big data, used to execute the bone fragment three-dimensional positioning adaptive adjustment method combining big data as described in the first aspect, including: a bone tissue three-dimensional model establishment module, used to acquire three-dimensional image data of the surgical site and establish a bone tissue three-dimensional model based on the three-dimensional image data; a bone fragment positioning prediction model construction module, used to call historical surgical case data for feature extraction and training to construct a bone fragment positioning prediction model; a screening module, used to input the bone tissue three-dimensional model into the bone fragment positioning prediction model, match similar case data from the historical surgical case data, and screen out the optimal position and optimal angle based on the similar case data; a scheme determination module, used to search a material database according to the optimal position and optimal angle to determine the bone fragment support shape design scheme; a bone fragment simulation implantation result obtaining module, used to manufacture a bone fragment support entity according to the bone fragment support shape design scheme, and perform implantation simulation in a virtual environment to obtain the bone fragment simulation implantation result; and an iterative optimization module, used to collect the spatial interference state of the bone fragment support entity in real time, make dynamic adjustments, and record the iterative optimization for the bone fragment positioning prediction model.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by realizing real-time optimization and dynamic adjustment of bone fragment positioning and design scheme, the technical effect of improving the matching accuracy between bone fragments and skeletal structure is achieved.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the adaptive adjustment method for three-dimensional positioning of bone fragments based on big data, as described in this application.

[0021] Figure 2 This is a schematic diagram of the bone fragment three-dimensional positioning adaptive adjustment device that combines big data according to this application.

[0022] Figure labeling: Module 1 for establishing a 3D model of bone tissue, Module 2 for constructing a bone fragment positioning and prediction model, Module 3 for screening, Module 4 for determining the scheme, Module 5 for obtaining the simulated bone fragment implantation results, and Module 6 for iterative optimization. Detailed Implementation

[0023] This application provides a method and apparatus for adaptive adjustment of bone fragment three-dimensional positioning by combining big data. This solves the technical problem in existing technologies where bone fragment positioning and design methods based on real-time data feedback and dynamic adjustment cannot effectively address changes in bone morphology and injury characteristics, further affecting the accurate matching of bone structures. The method achieves real-time optimization and dynamic adjustment of bone fragment positioning and design schemes, thereby improving the technical accuracy of bone fragment matching with bone structures.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a bone fragment three-dimensional positioning adaptive adjustment method based on big data, which is applied to a bone fragment three-dimensional positioning adaptive adjustment device based on big data, and specifically includes the following steps: Acquire three-dimensional image data of the surgical site, and establish a three-dimensional model of bone tissue based on the three-dimensional image data.

[0026] Furthermore, this application also includes: separating the three-dimensional image data to obtain a skeletal tissue region and a background region; performing three-dimensional reconstruction on the skeletal tissue region to generate an initial three-dimensional model of the skeletal tissue; marking anatomical landmarks on the initial three-dimensional model of the skeletal tissue and calculating the spatial positional relationship between the anatomical landmarks; determining the grayscale value distribution of the skeletal tissue region and quantifying the density distribution parameter; and constructing the three-dimensional model of the skeletal tissue based on the spatial positional relationship and the density distribution parameter.

[0027] Furthermore, this application also includes: preprocessing the three-dimensional image data to obtain tissue edges, the preprocessing including anisotropic filtering for noise reduction and adaptive contrast enhancement; based on the tissue edges, setting a separation threshold using a grayscale histogram analysis method to separate the background region and tissue region in the three-dimensional image data to obtain initial separated data; using preset high-density feature points of the tissue region in the initial separated data as seed points, expanding to neighboring pixels according to a preset grayscale similarity criterion to extract the skeletal tissue region; using an edge detection operator to extract the contour features of the skeletal tissue region, and combining morphological opening and closing operations to fill the skeletal tissue region; using a shape feature analysis algorithm to distinguish the skeletal tissue region from the residual soft tissue region, and removing artifact regions to obtain the separated skeletal tissue region; and extracting the skeletal tissue region based on the three-dimensional image data to obtain the background region.

[0028] Specifically, preprocessing 3D image data aims to optimize image quality through specific image processing techniques, thereby improving the accuracy of subsequent analysis. The preprocessing process includes anisotropic filtering denoising, which effectively removes noise from the image while preserving edge information. Adaptive contrast enhancement helps to improve the contrast of different regions in the image, making tissue edges more prominent, improving image visibility, and laying the foundation for subsequent region separation and analysis.

[0029] Based on tissue edges, a separation threshold is set using gray-level histogram analysis to further separate background and tissue regions in the 3D image data. Gray-level histogram analysis analyzes the distribution of gray values ​​in the image to determine a reasonable threshold. Using this threshold as a standard, tissue regions are distinguished from background regions, thus obtaining preliminary separation data. This step provides the basic framework for subsequent precise tissue region extraction.

[0030] For the tissue regions in the initial separated data, high-density feature points are preset as seed points. Based on the gray-level similarity criterion, these seed points are expanded to neighboring pixels to extract the skeletal tissue regions. The selection of high-density feature points is based on the density differences of the tissue regions. By selecting pixels with similar gray levels around the seed points, a more precise skeletal tissue region is expanded. This process ensures that the skeletal regions can be accurately extracted from the image.

[0031] An edge detection operator is used to extract the contour features of the skeletal tissue region, and morphological opening and closing operations are combined to fill the skeletal tissue region. The edge detection operator can identify the edges of the skeletal region, providing contour information of the skeleton. The morphological opening and closing operations further process the extracted contour, filling in gaps and details in the contour, resulting in a more complete and accurate skeletal tissue region.

[0032] Shape feature analysis algorithms can effectively distinguish between skeletal tissue regions and residual soft tissue regions, and eliminate artifact areas. Based on the geometric characteristics of the region, the shape feature analysis algorithm identifies the differences between bone and soft tissue, and removes non-biological tissues or noise appearing in the image, ensuring that the extracted skeletal region is accurate.

[0033] Based on 3D image data, the skeletal tissue region is extracted, and the background region is obtained. By inputting the processed data into the extraction algorithm, the precise skeletal tissue region can be extracted, while the background region is separated, ensuring the accuracy and effectiveness of the entire image processing process.

[0034] Three-dimensional reconstruction of the skeletal tissue region involves using computer algorithms to map two-dimensional data of the skeletal tissue region into three-dimensional space, generating a preliminary three-dimensional model of the skeleton. The reconstruction process, based on the extracted skeletal tissue region and combined with pixel information from the image, establishes the three-dimensional structure of the skeleton, ensuring that its shape matches the actual skeletal structure as closely as possible.

[0035] Anatomical landmarks were marked on the initial 3D model of the skeletal tissue, and the spatial relationships between these landmarks were calculated. The landmarks were marked according to medical anatomical standards to ensure the precise location of their corresponding key parts within the bone. By calculating the spatial relationships between the landmarks, the geometric features of the skeletal tissue could be obtained, laying the foundation for subsequent precise localization and analysis.

[0036] The grayscale distribution of bone tissue regions is determined, and density distribution parameters are quantified. The grayscale distribution reflects the density differences of bone tissue in images, thus revealing the structural characteristics of different regions. The quantification of density distribution parameters helps to accurately describe the density characteristics of bone tissue, providing a basis for subsequent mechanical analysis and design.

[0037] A three-dimensional model of the skeletal tissue is constructed based on spatial relationships and density distribution parameters. Combining the previously annotated anatomical relationships and density distribution data, computer modeling techniques are used to generate the final three-dimensional model of the skeletal tissue. This model can more accurately reflect the geometric morphology and internal density characteristics of the bone, providing precise data support for subsequent bone fragment localization and personalized design.

[0038] By using historical surgical case data for feature extraction and training, a bone fragment localization prediction model is constructed.

[0039] Furthermore, this application also includes: collecting the historical surgical case data, which includes preoperative imaging data, bone fragment design parameters, surgical operation records, and postoperative follow-up effect evaluation data; extracting bone fragment positioning feature vectors and bone fragment positioning effect feature vectors from the standardized historical surgical case data, whereby the bone fragment positioning feature vectors include anatomical structural features, lesion type features, and biomechanical features; and training the bone fragment positioning feature vectors and bone fragment positioning effect feature vectors using a machine learning algorithm to establish the bone fragment positioning prediction model.

[0040] Specifically, collecting historical surgical case data aims to obtain relevant clinical data from multiple sources for subsequent analysis and prediction. This data includes preoperative imaging data, bone fragment design parameters, surgical procedure records, and postoperative follow-up evaluation data. Preoperative imaging data provides information on the patient's skeletal morphology obtained through imaging techniques before surgery. Bone fragment design parameters involve details of the bone fragment design, such as size and shape. Surgical procedure records detail the actual steps and techniques performed during the surgery. Postoperative follow-up evaluation data reflects the postoperative treatment effect and the patient's recovery.

[0041] Bone fragment localization feature vectors and bone fragment localization effect feature vectors are extracted from standardized historical surgical case data, further transforming the data into a form that the model can process. The bone fragment localization feature vectors include anatomical structural features, lesion type features, and biomechanical features. Anatomical structural features describe the specific structure and morphology of the patient's bones, lesion type features involve the specific type of fracture or other bone problems, and biomechanical features reflect the impact of bone fragment localization on the mechanical properties of the patient's bones.

[0042] The bone fragment localization feature vector and bone fragment localization effect feature vector are trained using machine learning algorithms. The aim is to learn patterns from historical data and build a predictive model based on these patterns. Machine learning algorithms can extract patterns and relationships from large amounts of historical data and optimize the model through training, enabling it to make accurate localization predictions when faced with new cases. Through this training process, the bone fragment localization prediction model can predict the most suitable bone fragment localization scheme based on the input new case data.

[0043] The three-dimensional model of the bone tissue is input into the bone fragment localization prediction model. Similar case data is matched from the historical surgical case data. Based on the similar case data, the optimal position and optimal angle are selected.

[0044] Furthermore, this application also includes: converting the three-dimensional model of the bone tissue into a feature vector matrix to be matched; inputting the feature vector matrix to be matched into the bone fragment localization prediction model, and calculating the distance measure between the feature vector matrix to be matched and the historical surgical case data; filtering out a set of candidate cases within a preset distance threshold based on the distance measure; performing anatomical structure similarity and pathological feature similarity analysis on the set of candidate cases, and outputting the case with the highest similarity score as the similar case data.

[0045] Furthermore, this application also includes: extracting three-dimensional coordinate data and fixed angle parameters of the bone fragment implantation location from the similar case data; combining the anatomical morphological features of the three-dimensional model of the bone tissue, performing coordinate adaptation on the three-dimensional coordinate data and fixed angle parameters to obtain a candidate adaptation location set and a candidate adaptation angle set; simulating the mechanical conduction performance of the bone fragment based on the candidate adaptation location set and candidate adaptation angle set; and selecting the adaptation location and adaptation angle with a preset stress distribution and a preset stability threshold as the optimal location and optimal angle based on the mechanical conduction performance analysis results.

[0046] Specifically, the purpose of converting a 3D model of skeletal tissue into a feature vector matrix to be matched is to transform complex 3D data into a form suitable for predictive model processing. The 3D model contains information about the location, shape, and structure of various parts of the skeleton in space, while the feature vector matrix is ​​a vector representation that extracts key information from the 3D model to form a multi-dimensional data matrix, enabling the model to further process and analyze this data.

[0047] After inputting the feature vector matrix to be matched into the bone fragment localization prediction model, the distance measure between the feature vector matrix and historical surgical case data is calculated. The distance measure evaluates the similarity or difference between the feature vector to be matched and historical case data in a multidimensional feature space using a mathematical algorithm. This measure can employ methods such as Euclidean distance and Manhattan distance, aiming to quantify the gap between the data to be matched and historical cases, thereby providing a basis for screening similar cases.

[0048] Based on distance metrics, a set of candidate cases within a preset distance threshold is selected. This selection process extracts cases from all historical cases that are similar to the data to be matched by setting a predetermined distance threshold. The preset distance threshold can be determined based on experience or statistical analysis, with the aim of ensuring that the selected case set has a high degree of correlation in similarity, thus ensuring the effectiveness of subsequent analysis.

[0049] Anatomical structure similarity analysis and pathological feature similarity analysis were performed on the candidate case set data. Anatomical structure similarity analysis assessed the degree of matching between candidate cases and the data to be matched by comparing the similarity in skeletal morphology, structural layout, etc. Pathological feature similarity analysis evaluated the similarity between candidate cases and the data to be matched in terms of disease type, degree of bone injury, etc. The cases with the highest similarity scores were selected and output as similar case data for subsequent localization and treatment plan design.

[0050] The purpose of extracting three-dimensional coordinate data and fixed angle parameters of bone fragment implantation sites from similar case data is to obtain bone fragment implantation site and angle information similar to the current case from historical cases. Three-dimensional coordinate data refers to the specific position of the bone fragment in three-dimensional space obtained through imaging technology, while fixed angle parameters refer to the fixed angles set by the bone fragment relative to the bone structure. This data is used to provide a reference for bone fragment localization in the current case.

[0051] By combining the anatomical morphological features of a 3D model of bone tissue, coordinate adaptation is performed on the 3D coordinate data and fixed angle parameters to obtain a set of candidate adaptation positions and angles. Anatomical morphological features reflect the spatial distribution and shape of the bone structure. Adaptation with 3D coordinate data and fixed angle parameters ensures that the bone fragments can better conform to the bone structure in the new 3D space. This process generates candidate adaptation position and angle sets by calculating different adapted coordinate positions and angles, providing multiple options for the final selection.

[0052] The mechanical conduction properties of bone fragments are simulated based on a candidate set of fitting positions and angles. Mechanical conduction performance analysis involves calculating and simulating the mechanical response of the bone fragment at different fitting positions and angles, including the pressure and stress distribution experienced by the bone fragment in contact with the bone. Based on the analysis results, the optimal positions and angles are selected under preset stress distributions and preset stability thresholds. This selection process ensures that the chosen positions and angles not only maximize the restoration of bone function but also guarantee mechanical stability and long-term effectiveness.

[0053] Based on the optimal position and angle, the material database is searched to determine the bone plate support shape design scheme.

[0054] Furthermore, this application also includes: determining the support area to be covered by the bone fragment based on the optimal position and optimal angle; generating an initial geometric shape profile of the bone fragment according to the three-dimensional curved surface morphology of the support area; searching the material database and selecting a list of candidate materials that meet preset biocompatibility and mechanical performance support requirements based on the initial geometric shape profile; determining a target material formula from the list of candidate materials according to the patient's bone density parameters and expected load requirements; and generating the bone fragment support shape design scheme by combining the initial geometric shape profile and the target material formula.

[0055] Specifically, determining the support area to be covered by the bone graft based on the optimal position and angle means that after determining the final position and angle of the bone graft, the required support area is further calculated. The support area refers to the region where the bone graft contacts the bone and provides support; its size and shape determine the degree of contact and fixation effect between the bone graft and the bone. This step ensures that the bone graft receives stable support within the bone, thereby achieving the best implantation result.

[0056] Generating the initial geometric outline of the bone fragment based on the three-dimensional surface morphology of the support region refers to designing the preliminary shape of the bone fragment according to the three-dimensional structural shape of the support region. The three-dimensional surface morphology of the support region can provide contact surface information between the bone fragment and the bone, thereby generating an initial geometric outline that meets anatomical requirements. This ensures that the bone fragment can accurately fit the bone structure and provide sufficient support and stability during use.

[0057] The process involves searching materials databases and, based on initial geometric contours, selecting a list of candidate materials that meet predefined biocompatibility and mechanical performance requirements. The aim is to identify suitable bone graft materials from these databases. Biocompatibility requires the material to integrate well with human tissue without causing immune rejection or other side effects. Mechanical performance requirements dictate that the material can withstand the mechanical loads applied to the bone graft during and after surgery. This process uses the material properties in the database to select a list of suitable candidate materials.

[0058] Determining the target material formulation from a candidate material list based on the patient's bone density parameters and expected load requirements means selecting an appropriate material formulation according to the patient's specific bone density and the load requirements the bone will need to withstand postoperatively. The patient's bone density parameters reflect the quality and strength of their bone, while the expected load requirements relate to the mechanical load the bone graft will need to withstand postoperatively. By combining these parameters, the most suitable material formulation is selected from the candidate materials to ensure that the bone graft meets the patient's individualized needs.

[0059] Combining the initial geometric shape and target material formulation to generate a bone plate support shape design scheme refers to completing the final design of the bone plate support shape based on the known geometry of the bone plate and the selected material. This design scheme not only requires the shape of the bone plate to match the bone support area, but also requires the selection of materials to meet mechanical requirements, ensuring the long-term stability and support capacity of the bone plate in the bone.

[0060] A bone support entity is manufactured according to the bone support shape design scheme, and implantation simulation is performed in a virtual environment to obtain the bone support simulation implantation result.

[0061] Furthermore, this application also includes: mapping the bone fragment support shape design scheme to layered slicing data suitable for additive manufacturing equipment; configuring printing parameters according to the layered slicing data, forming the bone fragment support entity through additive manufacturing process; constructing the virtual environment, simulating the implantation of the bone fragment support entity in the virtual environment, detecting the spatial interference state between the bone fragment support entity and surrounding tissues in the virtual environment, and obtaining the simulated implantation result of the bone fragment if the spatial interference state meets the preset interference standard.

[0062] Specifically, mapping the bone-supporting shape design to layered slicing data suitable for additive manufacturing equipment transforms the design into a format that the equipment can understand and execute. Additive manufacturing equipment typically requires input of layered slicing data, which converts the design into layers of two-dimensional information. The shape and dimensions of each layer guide the equipment in printing layer by layer. During this process, the three-dimensional form of the design is divided into multiple horizontal layers to ensure accurate printing of each layer during manufacturing.

[0063] Configuring printing parameters based on layered slicing data and forming the bone-supported entity through additive manufacturing means setting appropriate printing parameters based on the generated layered slicing data. These parameters, including printing speed, temperature, and material supply, determine the accuracy and quality during the printing process. The additive manufacturing process combines these parameters with the slicing data, stacking material layer by layer to precisely manufacture the bone-supported entity of the required shape, ensuring that the final product meets design requirements.

[0064] A virtual environment is constructed to simulate the implantation of a bone graft supporting a physical entity, detecting spatial interference between the bone graft and surrounding tissue. This virtual environment is a computer simulation that recreates the bone graft implantation scenario during surgery. By simulating the implantation process, the spatial relationship between the bone graft and surrounding tissue can be observed, analyzing whether interference or mismatch will occur. This simulation helps assess the implantation effect before actual surgery, avoiding potential surgical risks.

[0065] If the spatial interference state meets the preset interference standard, the simulated bone implantation result is obtained. By comparing the simulation result with the preset interference standard, it is determined whether the bone-supporting entity can smoothly contact the bone during the actual implantation process and ensure that it does not interfere with or conflict with surrounding tissues. If the simulation result meets the standard, it can be determined that the bone design and implantation plan are feasible, and preparations can be made for the actual surgery.

[0066] The spatial interference state of the bone fragment supporting the entity is collected in real time and dynamically adjusted, and the iterative optimization of the bone fragment positioning prediction model is recorded.

[0067] Furthermore, this application also includes: acquiring the spatial interference state of the bone-supported entity in real time through a pre-embedded bone-segment sensing unit; acquiring the theoretical pressure range corresponding to the current surgical stage and acquiring the theoretical spatial interference state; calculating the state deviation between the spatial interference state and the theoretical spatial interference state, determining whether the state deviation exceeds a preset safety threshold, and generating a comparison analysis result containing deviation details.

[0068] Specifically, acquiring the spatial interference state of the bone-supported entity in real time through pre-embedded bone fragment sensing units refers to installing sensors inside or on the surface of the bone fragment support entity to monitor the spatial interference between the bone fragment and surrounding tissues during implantation. The sensing units can detect changes in the relative position between the bone fragment and surrounding tissues and transmit the interference data to the monitoring system in real time, thus providing real-time feedback for subsequent interference analysis.

[0069] Obtaining the theoretical pressure range and theoretical spatial interference state corresponding to the current surgical stage means calculating and determining the theoretically possible pressure range between the bone fragment and surrounding tissues during the operation, based on the current surgical stage and the specific circumstances of bone fragment implantation. The theoretical spatial interference state, obtained through simulation or calculation, represents the possible interference between the bone fragment and surrounding tissues without intervention. This step provides benchmark data for subsequent comparisons between actual interference and theoretical interference states.

[0070] Calculating the deviation between the actual spatial interference state and the theoretical spatial interference state, and determining whether the deviation exceeds a preset safety threshold, means comparing the actual spatial interference data obtained by the sensing unit with the theoretically calculated interference data and calculating the deviation between the two. If the deviation exceeds the set safety threshold, it indicates that the degree of interference between the bone fragment and surrounding tissues may negatively affect the surgical procedure or postoperative outcome. In this case, it is determined whether further adjustments to the position or angle of the bone fragment are needed to ensure safety.

[0071] Generating comparative analysis results with detailed deviation information and making dynamic adjustments refers to generating a detailed analysis report based on the calculated state deviation, including key information such as deviation values ​​and instances exceeding safety thresholds. Based on these analysis results, the position or angle of the bone fragment is adjusted in real time to ensure precise implantation and avoid excessive interference with surrounding tissues. Simultaneously, these adjustments are recorded and used to iteratively optimize the bone fragment positioning prediction model, continuously improving prediction accuracy and adaptability.

[0072] In summary, the bone fragment three-dimensional positioning adaptive adjustment method combined with big data provided in this application has the following technical effects: by realizing the real-time optimization and dynamic adjustment of bone fragment positioning and design scheme, the technical effect of improving the matching accuracy between bone fragments and skeletal structures is achieved.

[0073] Example 2: Based on the same inventive concept as the bone fragment three-dimensional positioning adaptive adjustment method combining big data in the foregoing examples, this application also provides a bone fragment three-dimensional positioning adaptive adjustment device combining big data. Please refer to the appendix. Figure 2 The system includes: a 3D model building module 1 for acquiring 3D image data of the surgical site and building a 3D model of the bone tissue based on the 3D image data; a bone fragment positioning prediction model building module 2 for calling historical surgical case data for feature extraction and training to build a bone fragment positioning prediction model; a screening module 3 for inputting the 3D model of the bone tissue into the bone fragment positioning prediction model, matching similar case data from the historical surgical case data, and filtering out the optimal position and optimal angle based on the similar case data; a scheme determination module 4 for searching the material database according to the optimal position and optimal angle to determine the bone fragment support shape design scheme; a bone fragment simulation implantation result obtaining module 5 for manufacturing a bone fragment support entity according to the bone fragment support shape design scheme, and performing implantation simulation in a virtual environment to obtain the bone fragment simulation implantation result; and an iterative optimization module 6 for real-time acquisition of the spatial interference state of the bone fragment support entity, dynamic adjustment, and recording the iterative optimization for the bone fragment positioning prediction model.

[0074] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used for: separating the three-dimensional image data to obtain the bone tissue region and the background region; performing three-dimensional reconstruction of the bone tissue region to generate an initial three-dimensional bone tissue model; marking anatomical landmarks on the initial three-dimensional bone tissue model and calculating the spatial positional relationship between the anatomical landmarks; determining the gray value distribution of the bone tissue region and quantifying the density distribution parameter; and constructing the three-dimensional bone tissue model based on the spatial positional relationship and the density distribution parameter.

[0075] Furthermore, the bone fragment 3D positioning adaptive adjustment device combining big data is also used for: preprocessing the 3D image data to obtain tissue edges, the preprocessing including anisotropic filtering for noise reduction and contrast adaptive enhancement; based on the tissue edges, setting a separation threshold using a grayscale histogram analysis method to separate the background region and tissue region in the 3D image data to obtain initial separation data; using preset high-density feature points of the tissue region in the initial separation data as seed points, expanding to neighboring pixels according to a preset grayscale similarity criterion to extract the bone tissue region; using an edge detection operator to extract the contour features of the bone tissue region, and filling the bone tissue region with morphological opening and closing operations; distinguishing the bone tissue region from the residual soft tissue region using a shape feature analysis algorithm, and removing artifact regions to obtain the separated bone tissue region; and extracting the bone tissue region based on the 3D image data to obtain the background region.

[0076] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used for: collecting the historical surgical case data, which includes preoperative imaging data, bone fragment design parameters, surgical operation records, and postoperative follow-up effect evaluation data; extracting bone fragment positioning feature vectors and bone fragment positioning effect feature vectors from the standardized historical surgical case data, which include anatomical structure features, lesion type features, and biomechanical features; and training the bone fragment positioning feature vectors and bone fragment positioning effect feature vectors using machine learning algorithms to establish the bone fragment positioning prediction model.

[0077] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used for: converting the bone tissue three-dimensional model into a feature vector matrix to be matched; inputting the feature vector matrix to be matched into the bone fragment positioning prediction model, calculating the distance measure between the feature vector matrix to be matched and the historical surgical case data; filtering out a set of candidate cases within a preset distance threshold based on the distance measure; performing anatomical structure similarity and pathological feature similarity analysis on the set of candidate cases, and outputting the case with the highest similarity score as the similar case data.

[0078] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used to: extract the three-dimensional coordinate data and fixed angle parameters of the bone fragment implantation position from the similar case data; combine the anatomical morphological features of the three-dimensional model of the bone tissue to perform coordinate adaptation on the three-dimensional coordinate data and fixed angle parameters to obtain a set of candidate adaptation positions and a set of candidate adaptation angles; simulate the mechanical conduction performance of the bone fragment based on the set of candidate adaptation positions and the set of candidate adaptation angles; and based on the mechanical conduction performance analysis results, select the adaptation position and adaptation angle with a preset stress distribution and a preset stability threshold as the optimal position and optimal angle.

[0079] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used for: determining the support area to be covered by the bone fragment based on the optimal position and optimal angle; generating an initial geometric shape contour of the bone fragment according to the three-dimensional curved surface morphology of the support area; searching the material database and selecting a list of candidate materials that meet preset biocompatibility and mechanical performance support requirements based on the initial geometric shape contour; determining a target material formula from the candidate material list according to the patient's bone density parameters and expected load requirements; and generating the bone fragment support shape design scheme by combining the initial geometric shape contour and the target material formula.

[0080] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combining big data is also used to: map the bone fragment support shape design scheme into layered slice data suitable for additive manufacturing equipment; configure printing parameters according to the layered slice data, and form the bone fragment support entity through additive manufacturing process; construct the virtual environment, simulate the implantation of the bone fragment support entity in the virtual environment, detect the spatial interference state between the bone fragment support entity and the surrounding tissue in the virtual environment, and if the spatial interference state meets the preset interference standard, obtain the simulated implantation result of the bone fragment.

[0081] Furthermore, the bone fragment three-dimensional positioning adaptive adjustment device combined with big data is also used to: obtain the spatial interference state of the bone fragment supporting the entity in real time through the pre-embedded bone fragment sensing unit; obtain the theoretical pressure range corresponding to the current surgical stage and obtain the theoretical spatial interference state; calculate the state deviation between the spatial interference state and the theoretical spatial interference state, determine whether the state deviation exceeds the preset safety threshold, and generate a comparison analysis result containing deviation details.

[0082] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The bone fragment three-dimensional positioning adaptive adjustment method and specific examples combined with big data in the aforementioned embodiment one are also applicable to the bone fragment three-dimensional positioning adaptive adjustment device combined with big data in this embodiment. Through the foregoing detailed description of the bone fragment three-dimensional positioning adaptive adjustment method combined with big data, those skilled in the art can clearly understand the bone fragment three-dimensional positioning adaptive adjustment device combined with big data in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0083] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A bone fragment three-dimensional positioning adaptive adjustment method combining big data, characterized in that, include: Acquire three-dimensional image data of the surgical site, and establish a three-dimensional model of bone tissue based on the three-dimensional image data; Historical surgical case data was used to extract features and train a bone fragment localization prediction model. The three-dimensional model of the bone tissue is input into the bone fragment localization prediction model. Similar case data is matched from the historical surgical case data. Based on the similar case data, the optimal position and optimal angle are selected. Based on the optimal position and optimal angle, the material database is searched to determine the bone plate support shape design scheme; A bone support entity is manufactured according to the bone support shape design scheme, and implantation simulation is performed in a virtual environment to obtain the bone support simulation implantation result. The spatial interference state of the bone fragment supporting the entity is collected in real time and dynamically adjusted, and the iterative optimization of the bone fragment positioning prediction model is recorded.

2. The bone fragment three-dimensional positioning adaptive adjustment method combining big data as described in claim 1, characterized in that, Acquiring three-dimensional image data of the surgical site and establishing a three-dimensional model of bone tissue based on the three-dimensional image data includes: The three-dimensional image data is separated to obtain the skeletal tissue region and the background region; The bone tissue region is reconstructed in three dimensions to generate an initial three-dimensional model of the bone tissue. Anatomical landmarks are marked on the initial 3D model of bone tissue, and the spatial relationships between the anatomical landmarks are calculated. Determine the grayscale distribution of the bone tissue region and quantize the density distribution parameters; Based on the spatial relationship and the density distribution parameters, a three-dimensional model of the bone tissue is constructed.

3. The adaptive adjustment method for three-dimensional positioning of bone fragments combined with big data as described in claim 2, characterized in that, The three-dimensional image data is separated to obtain the skeletal tissue region and the background region, including: The three-dimensional image data is preprocessed to obtain tissue edges. The preprocessing includes anisotropic filtering for noise reduction and adaptive contrast enhancement. Based on the tissue edge, a separation threshold is set using a grayscale histogram analysis method to separate the background area from the tissue area in the three-dimensional image data, thus obtaining initial separation data. Using the preset high-density feature points of the tissue region in the initial separation data as seed points, the bone tissue region is extracted by expanding to neighboring pixels according to the preset gray-level similarity criterion. The contour features of the skeletal tissue region are extracted using an edge detection operator, and the skeletal tissue region is filled using morphological opening and closing operations. The shape feature analysis algorithm distinguishes the skeletal tissue region from the residual soft tissue region and removes artifact regions to obtain the separated skeletal tissue region. The background region is obtained by extracting the skeletal tissue region based on the three-dimensional image data.

4. The bone fragment three-dimensional positioning adaptive adjustment method combining big data as described in claim 1, characterized in that, Historical surgical case data was used for feature extraction and training to build a bone fragment localization prediction model, including: Collect the historical surgical case data, which includes preoperative imaging data, bone fragment design parameters, surgical operation records, and postoperative follow-up effect evaluation data; Bone fragment localization feature vector and bone fragment localization effect feature vector are extracted from the standardized historical surgical case data. The bone fragment localization feature vector includes anatomical structural features, lesion type features and biomechanical features. The bone fragment localization feature vector and bone fragment localization effect feature vector are trained using machine learning algorithms to establish the bone fragment localization prediction model.

5. The adaptive adjustment method for three-dimensional positioning of bone fragments combined with big data as described in claim 1, characterized in that, The three-dimensional model of the bone tissue is input into the bone fragment localization prediction model, and similar case data is matched from the historical surgical case data, including: The three-dimensional model of the bone tissue is converted into a feature vector matrix to be matched; Input the feature vector matrix to be matched into the bone fragment localization prediction model, and calculate the distance measure between the feature vector matrix to be matched and the historical surgical case data; Based on the distance metric, a set of candidate cases within a preset distance threshold is selected; Anatomical structure similarity and pathological feature similarity analysis are performed on the candidate case set, and the case with the highest similarity score is output as the similar case data.

6. The adaptive adjustment method for three-dimensional positioning of bone fragments combined with big data as described in claim 1, characterized in that, Based on the aforementioned similar case data, the optimal location and optimal angle were selected, including: Extract the three-dimensional coordinate data and fixed angle parameters of the bone fragment implantation location from the similar case data; Based on the anatomical morphological features of the three-dimensional model of the bone tissue, coordinate adaptation is performed on the three-dimensional coordinate data and fixed angle parameters to obtain a set of candidate adaptation positions and a set of candidate adaptation angles. Based on the candidate fitting position set and candidate fitting angle set, the mechanical conduction performance of the simulated bone fragment is analyzed. Based on the mechanical conduction performance analysis results, the fitting position and fitting angle with a preset stress distribution and a preset stability threshold are selected as the optimal position and optimal angle.

7. The adaptive adjustment method for three-dimensional positioning of bone fragments combining big data as described in claim 1, characterized in that, Based on the optimal position and angle, a material database is retrieved to determine the bone plate support shape design scheme, including: Based on the optimal position and angle, determine the support area that the bone fragment needs to cover; Based on the three-dimensional curved surface morphology of the supporting region, the initial geometric outline of the bone fragment is generated; The material database is searched, and a list of candidate materials that meet the preset biocompatibility and mechanical performance requirements is selected based on the initial geometric shape profile. The target material formulation is determined from the candidate material list based on the patient's bone density parameters and expected load requirements; By combining the initial geometric shape and the target material formula, the bone plate support shape design scheme is generated.

8. The adaptive adjustment method for three-dimensional positioning of bone fragments combined with big data as described in claim 1, characterized in that, Based on the bone fragment support shape design scheme, a bone fragment support entity is manufactured, and implantation simulation is performed in a virtual environment to obtain the simulated bone fragment implantation results, including: Map the bone fragment support shape design scheme into layered slicing data suitable for additive manufacturing equipment; Based on the layered slicing data, the printing parameters are configured, and the bone-supporting entity is formed using additive manufacturing technology; The virtual environment is constructed, and the implantation of the bone fragment support entity is simulated in the virtual environment. The spatial interference state between the bone fragment support entity and the surrounding tissue in the virtual environment is detected. If the spatial interference state meets the preset interference standard, the simulated implantation result of the bone fragment is obtained.

9. The adaptive adjustment method for three-dimensional positioning of bone fragments combining big data as described in claim 1, characterized in that, Real-time acquisition of the spatial interference state of the bone-supported entity, including: The spatial interference state of the entity supported by the bone fragments is obtained in real time through the pre-embedded bone fragment sensing unit. Obtain the theoretical pressure range corresponding to the current surgical stage, and obtain the theoretical spatial interference state; The state deviation between the spatial interference state and the theoretical spatial interference state is calculated, and it is determined whether the state deviation exceeds a preset safety threshold. A comparison analysis result containing deviation details is then generated.

10. A bone fragment three-dimensional positioning adaptive adjustment device combining big data, characterized in that, The steps for implementing the adaptive adjustment method for three-dimensional positioning of bone fragments combining big data as described in any one of claims 1 to 9 include: The bone tissue 3D model building module is used to acquire 3D image data of the surgical site and build a 3D model of bone tissue based on the 3D image data. The bone fragment localization prediction model building module is used to call historical surgical case data for feature extraction and training to build a bone fragment localization prediction model. The filtering module is used to input the three-dimensional model of the bone tissue into the bone fragment positioning prediction model, match similar case data from the historical surgical case data, and filter out the optimal position and optimal angle based on the similar case data; The scheme determination module is used to retrieve the material database based on the optimal position and optimal angle to determine the bone plate support shape design scheme; The module for obtaining bone fragment simulation implantation results is used to manufacture a bone fragment support entity according to the bone fragment support shape design scheme, and to perform implantation simulation in a virtual environment to obtain bone fragment simulation implantation results. The iterative optimization module is used to collect the spatial interference state of the bone fragment supporting the entity in real time, make dynamic adjustments, and record the iterative optimization of the bone fragment positioning prediction model.

Images