Joint prosthesis replacement training method and device based on entity model, equipment and medium

Abstract

The invention discloses a joint prosthesis replacement training method, device and equipment based on an entity model and a medium, and belongs to the technical field of replacement training. The method comprises the following steps: acquiring a target filing position of a target joint in a solid model; in the grinding and filing process of the target joint, a first pose parameter of the grinding and filing tool under the optical positioning system is obtained, and grinding and filing parameters of the grinding and filing tool on the target joint are calculated based on the first pose parameter; identifying whether the file grinding parameters reach a target file grinding position or not; if yes, acquiring a second pose parameter of the joint prosthesis under the optical positioning system after replacement of the joint prosthesis is completed, and calculating a space expression parameter of the joint prosthesis based on the second pose parameter; and performing replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and the spatial expression parameters. According to the technical scheme, the training effect of joint prosthesis replacement can be improved, the intuition of training result feedback is ensured, and the training efficiency is improved.

Description

Technical Field

[0001] This application belongs to the technical field of replacement training, and specifically relates to a joint prosthesis replacement training method, device, equipment and medium based on an entity model. Background Art

[0002] Joint prosthesis replacement training is a process of systematically and standardly educating and skill-training replacement personnel so that they master joint prosthesis replacement skills. Since joint replacement is relatively complex, in order to ensure the success rate of the prosthesis replacement result, it is necessary to evaluate and train the replacement operation of the replacement personnel to ensure the safety of the replacement.

[0003] In the prior art, the replacement training method of joint prostheses is usually that during the actual joint replacement process, a replacement personnel with replacement experience performs actual replacement operations, and other personnel accumulate training experience by observing the replacement steps and recording replacement data, or by means of virtual learning, using virtual replacement tools and virtual prostheses to grind and replace a pre-constructed virtual joint model, and determine whether the replacement is successful according to the shape of the replacement model finally displayed by the virtual system.

[0004] However, the training methods in the prior art cannot provide a training simulation environment that can interact with entities, nor can they provide replacement navigation during the replacement training process, so the training effect cannot be guaranteed. Moreover, the prior art cannot quantitatively evaluate the replacement training results, and there is a problem that the training result feedback is not intuitive enough, thus resulting in a low training efficiency. Summary of the Invention

[0005] The purpose of the embodiments of this application is to provide a joint prosthesis replacement training method, device, equipment and medium based on an entity model, which solves the problems in the prior art that the training effect cannot be guaranteed, the training result feedback is not intuitive enough, and the training efficiency is low. By calculating the spatial performance parameters of the joint prosthesis when the grinding parameters of the target joint in the entity model by the grinding tool reach the target grinding position, and performing replacement evaluation on the joint replacement result of the target joint based on a pre-set replacement evaluation comparison table and the spatial performance parameters, the purpose of providing an entity interaction training simulation environment can be achieved, which is beneficial to improving the training effect of joint prosthesis replacement, ensuring the intuitiveness of the training result feedback and improving the training efficiency.

[0006] In a first aspect, the embodiments of this application provide a joint prosthesis replacement training device based on an entity model, and the method includes:

[0007] Obtain the target grinding position of the target joint in the entity model;

[0008] During the grinding and filing process of the target joint, obtain the first pose parameters of the grinding and filing tool under the optical positioning system, and calculate the grinding and filing parameters of the grinding and filing tool for the target joint based on the first pose parameters;

[0009] Identify whether the grinding and filing parameters reach the target grinding and filing position;

[0010] If so, after completing the joint prosthesis replacement, obtain the second pose parameters of the joint prosthesis under the optical positioning system, and calculate the spatial performance parameters of the joint prosthesis based on the second pose parameters;

[0011] Evaluate the joint replacement result of the target joint based on the pre-set replacement evaluation comparison table and the spatial performance parameters.

[0012] Furthermore, obtaining the target grinding and filing position of the target joint in the solid model includes:

[0013] Extract the point cloud of the three-dimensional model of the target joint in the image space from the pre-constructed solid model to obtain the point cloud data of the target joint;

[0014] Calculate the center-of-sphere coordinates and the target grinding and filing direction of the target joint in the image space based on the fitting algorithm and the point cloud data;

[0015] Obtain the conversion relationship between the optical positioning system and the image space, and determine the target grinding and filing position of the target joint based on the center-of-sphere coordinates, the target grinding and filing direction, and the conversion relationship.

[0016] Furthermore, calculating the center-of-sphere coordinates and the target grinding and filing direction of the target joint in the image space based on the fitting algorithm and the point cloud data includes:

[0017] Perform edge plane fitting on the target joint based on the plane fitting algorithm and the point cloud data to obtain the plane normal vector and the centroid coordinates of the target joint in the image space;

[0018] Perform spherical fitting on the target joint based on the iterative algorithm and the point cloud data to obtain the center-of-sphere coordinates of the target joint in the image space;

[0019] Calculate the angle between the direction vector from the centroid coordinates to the center-of-sphere coordinates and the plane normal vector, and identify whether the angle is greater than the preset angle threshold;

[0020] In the case where the angle is greater than the preset angle threshold, determine the opposite direction of the plane normal vector as the target grinding and filing direction of the target joint in the image space.

[0021] Furthermore, the construction process of the three-dimensional model of the target joint in the image space includes:

[0022] Obtain multiple two-dimensional images of the solid model, and perform three-dimensional reconstruction on the solid model based on the multiple two-dimensional images to obtain the overall three-dimensional model of the solid model in the image space;

[0023] Perform structure segmentation on the overall three-dimensional model based on a pre-trained structure segmentation model to obtain the three-dimensional model of the target joint in the image space.

[0024] Further, the process of determining the conversion relationship between the optical positioning system and the image space includes:

[0025] Obtain the first point cloud coordinates of multiple preset marker points on the three-dimensional model in the image space, and the second point cloud coordinates in the optical positioning system;

[0026] Perform rough registration on the image space and the optical positioning system based on the first point cloud coordinates and the second point cloud coordinates to obtain a rough registration conversion relationship;

[0027] Obtain multiple third point cloud coordinates collected by the probe tool for the target joint in the optical positioning system, and perform fine registration on the image space and the optical positioning system based on the first point cloud coordinates and the third point cloud coordinates to obtain a fine registration conversion relationship;

[0028] Determine the conversion relationship between the optical positioning system and the image space based on the rough registration conversion relationship and the fine registration conversion relationship.

[0029] Further, the spatial performance parameters include the prosthetic anteversion angle and the prosthetic abduction angle of the joint prosthesis after replacement;

[0030] Perform replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and spatial performance parameters, including:

[0031] Identify the target anteversion angle range corresponding to the prosthetic anteversion angle in the preset replacement evaluation comparison table, and read the first score corresponding to the target anteversion angle range;

[0032] Identify the target abduction angle range corresponding to the prosthetic abduction angle in the preset replacement evaluation comparison table, and read the second score corresponding to the target abduction angle range;

[0033] Integrate the first score and the second score to obtain the joint replacement evaluation score for the target joint.

[0034] Further, before performing replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and spatial performance parameters, the method further includes:

[0035] Obtain the initial length of the associated joint of the target joint in the solid model, and obtain the final length of the associated joint after replacement;

[0036] Correspondingly, the first score and the second score are integrated to obtain a joint replacement evaluation score for the target joint, including:

[0037] Determine the replacement error of the joint replacement result based on the initial length and the final length;

[0038] Integrate the first score, the second score, and the replacement error to obtain a joint replacement evaluation score for the target joint.

[0039] In a second aspect, an embodiment of the present application provides a method for training joint prosthesis replacement based on an entity model. The method includes:

[0040] A target position acquisition module, configured to acquire the target rasping position of the target joint in the entity model;

[0041] A rasping parameter calculation module, configured to acquire the first pose parameter of the rasping tool under the optical positioning system during the rasping process of the target joint, and calculate the rasping parameters of the rasping tool for the target joint based on the first pose parameter;

[0042] A rasping parameter identification module, configured to identify whether the rasping parameters reach the target rasping position;

[0043] A spatial performance parameter calculation module, configured to, when the rasping parameters reach the target rasping position, acquire the second pose parameter of the joint prosthesis under the optical positioning system after the joint prosthesis replacement is completed, and calculate the spatial performance parameters of the joint prosthesis based on the second pose parameter;

[0044] A replacement evaluation module, configured to perform a replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and the spatial performance parameters.

[0045] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0047] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the method described in the first aspect.

[0048] In an embodiment of the present application, the target grinding position of the target joint in the entity model is obtained; during the grinding process of the target joint, the first pose parameter of the grinding tool under the optical positioning system is obtained, and the grinding parameter of the grinding tool for the target joint is calculated based on the first pose parameter; it is identified whether the grinding parameter reaches the target grinding position; if so, after the joint prosthesis replacement is completed, the second pose parameter of the joint prosthesis under the optical positioning system is obtained, and the spatial performance parameter of the joint prosthesis is calculated based on the second pose parameter; the joint replacement result of the target joint is evaluated based on the pre-set replacement evaluation comparison table and the spatial performance parameter. Through the above joint prosthesis replacement training method based on the entity model, the problems existing in the prior art, such as the inability to ensure the training effect, the lack of intuitive feedback of the training result, and the low training efficiency, are solved. By calculating the spatial performance parameter of the joint prosthesis when the grinding parameter of the grinding tool for the target joint in the entity model reaches the target grinding position, and evaluating the joint replacement result of the target joint based on the pre-set replacement evaluation comparison table and the spatial performance parameter, the purpose of providing an entity interaction training simulation environment can be achieved, which is beneficial to improving the training effect of joint prosthesis replacement, ensuring the intuitiveness of the training result feedback, and improving the training efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 FIG. is a schematic flowchart of a joint prosthesis replacement training method based on an entity model provided by the present application;

[0050] Figure 2 FIG. is a schematic diagram of hip joint prosthesis replacement provided by the present application;

[0051] Figure 3 FIG. is a schematic diagram of obtaining the target grinding position provided by the present application;

[0052] Figure 4 FIG. is a schematic flowchart of another joint prosthesis replacement training method based on an entity model provided by the present application;

[0053] Figure 5 FIG. is a schematic structural diagram of a joint prosthesis replacement training device based on an entity model provided by the present application;

[0054] Figure 6 FIG. is a schematic structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following provides a more detailed description of specific embodiments of this application with reference to the accompanying drawings. It can be understood that the specific embodiments described herein are merely for explaining this application and not for limiting this application. Additionally, it should be noted that for ease of description, only parts related to this application are shown in the drawings rather than all content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. When the operations are completed, the process can be terminated, but there can also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0056] The following will clearly describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of this application.

[0057] The terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. generally belong to the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the description and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0058] The following will provide a detailed description of the joint prosthesis replacement training method, device, equipment, and medium based on an entity model provided by this application with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0059] Figure 1 is a schematic flowchart of the joint prosthesis replacement training method based on an entity model provided by this application. As Figure 1 shown, it specifically includes the following steps:

[0060] S101, obtain the target rasping position of the target joint in the entity model.

[0061] First, the usage scenario of this solution can be a scenario for joint prosthesis replacement training, especially a scenario where an entity model is provided for prosthesis replacement training and the training results are fed back through quantitative evaluation. This solution will mainly take the training of hip joint prosthesis replacement using an entity model simulating the hip joint as an example for illustration. When the grinding parameters of the grinding tool for the target joint in the entity model reach the target grinding position, the spatial performance parameters of the joint prosthesis are calculated, and the joint replacement result of the target joint is evaluated based on the preset replacement evaluation comparison table and the spatial performance parameters, so as to achieve the purpose of providing an entity interaction training simulation environment, which is beneficial to improving the training effect of joint prosthesis replacement, ensuring the intuitiveness of training result feedback, and improving training efficiency.

[0062] Based on the above usage scenario, it can be understood that the execution subject of this application can be an electronic device with capabilities such as data reading, calculation, and processing result feedback.

[0063] Among them, the entity model can be a three-dimensional model constructed according to the parameters of the actual joint and can be actually ground and prosthesis installed. For example: a simulated hip joint entity model.

[0064] Figure 2 It is a schematic diagram of hip joint prosthesis replacement provided by this application.

[0065] As Figure 2 shown, on the left side of the figure is the replacement prosthesis of the hip joint, and the replacement prosthesis includes the acetabular cup and femoral prosthesis in the figure. On the right side is the whole hip joint after completing joint prosthesis replacement. The entity model in this solution can be a hip joint entity model, which includes an acetabular entity model and a femoral entity model. The process of hip joint prosthesis replacement is mainly the cutting of the acetabulum and femur and the installation of the prosthesis. This solution mainly focuses on the grinding and cutting training and prosthesis replacement and installation training of the simulated acetabular entity model.

[0066] The entity model has the same shape characteristics and three-dimensional structure as the real joint. By using the entity model for joint prosthesis replacement training, the purpose of constructing an entity interaction training environment can be achieved. The target joint can be the joint that needs to be cut, ground, and prosthesis replaced during the joint prosthesis replacement process. The target joint in this solution mainly refers to the acetabulum. The target grinding position can be the final position reached by the grinding tool on the target joint after grinding the target joint with the grinding tool. The target grinding position can be a specific position or a grinding range. It can be determined whether the grinding is completed and whether it meets the grinding safety by real-time identifying whether the grinding end of the grinding tool reaches this position or within this range. The target grinding position can include the target grinding anteversion angle, target grinding abduction angle, and target grinding depth of the target joint.

[0067] In one embodiment, a predetermined target filing position when filing a target joint in an entity model can be obtained. The way to determine the target filing position can be to fit the original filing surface of the target joint through a fitting algorithm to obtain the center position of the target joint, that is, the center position of the spherical surface of the acetabulum entity model, and calculate the plane normal vector of the original filing surface to obtain the filing direction for filing the target joint. The prosthesis radius of the prosthesis to be replaced can be obtained, and the target filing position can be determined according to the center position, filing direction and prosthesis radius.

[0068] S102. During the filing process of the target joint, obtain the first pose parameter of the filing tool under the optical positioning system, and calculate the filing parameter of the filing tool for the target joint based on the first pose parameter.

[0069] Among them, the first pose parameter can be the real-time pose of the filing tool under the optical positioning system during the filing process of the target joint. The filing tool in this solution is mainly an acetabular file. The filing end of the acetabular file for filing the acetabulum entity model is a sphere, and the filing direction and filing position of the acetabular file can be determined according to the pose parameter of the acetabular file. The filing parameter can be the real-time filing direction and filing position corresponding to the filing tool when the filing tool files the target joint. The filing parameter can include the filing anteversion angle, filing abduction angle and filing depth.

[0070] In one embodiment, during the filing process of the target joint, the coordinates of the reflective mark preset on the filing tool under the optical positioning system can be recognized and obtained in real time, and the first pose parameter of the filing tool under the optical positioning system can be determined according to the coordinates of the reflective mark under the optical positioning system and the setting position of the reflective mark on the filing tool, and the filing parameter of the filing end of the filing tool for the target joint can be determined according to the real-time change of the first pose parameter.

[0071] S103. Identify whether the filing parameter reaches the target filing position.

[0072] In one embodiment, it can be determined in real time whether the filing parameter reaches the filing range or specific parameter value of the target filing position to determine whether the filing tool files safely and whether the filing of the target joint is completed.

[0073] S104. If so, after completing the replacement of the joint prosthesis, obtain the second pose parameter of the joint prosthesis under the optical positioning system, and calculate the spatial performance parameter of the joint prosthesis based on the second pose parameter.

[0074] Among them, the second pose parameter can be the real-time pose of the joint prosthesis under the optical positioning system during and after the placement process. The joint prosthesis in this solution is mainly the acetabular cup prosthesis. The spatial performance parameter of the joint prosthesis can be the real-time spatial parameter corresponding to the outer surface of the joint prosthesis during and after the placement process. The spatial performance parameter of the joint prosthesis represents the position and opening direction of the prosthesis after the joint prosthesis replacement is completed. The spatial performance parameter of the joint prosthesis can include the anteversion angle, abduction angle of the joint prosthesis, and the installation depth of the prosthesis.

[0075] In one embodiment, if the grinding parameter reaches the target grinding position, it can be determined that the grinding tool has completed grinding of the target joint. The coordinates of the reflective marker pre-set on the joint prosthesis can be identified under the optical positioning system, and the real-time pose parameters of the joint prosthesis under the optical positioning system can be determined according to the setting position of the reflective marker on the joint prosthesis. When the prosthesis replacement completion instruction is received or it is recognized that the real-time pose parameters of the joint prosthesis do not change within the preset duration, it is determined that the joint prosthesis replacement is completed. After the joint prosthesis replacement is completed, the second pose parameter of the joint prosthesis under the optical positioning system is obtained, and the position and opening orientation of the joint prosthesis are calculated according to the second pose parameter to obtain the spatial performance parameter of the joint prosthesis.

[0076] S105, perform replacement evaluation on the joint replacement result of the target joint based on the pre-set replacement evaluation comparison table and the spatial performance parameter.

[0077] Among them, the pre-set replacement evaluation comparison table can be a table pre-set for scoring the deviation degree between the actual result and the standard result of the joint prosthesis replacement. The pre-set replacement evaluation comparison table can include multiple ranges divided for the spatial performance parameter and the corresponding scoring values for each range.

[0078] In one embodiment, the range corresponding to the spatial performance parameter in the pre-set replacement evaluation comparison table can be identified, and the replacement evaluation of the joint replacement result of the target joint can be performed according to the evaluation score corresponding to the range.

[0079] The technical solution provided by the embodiments of the present application is to obtain the target grinding position of the target joint in the solid model; during the grinding process of the target joint, obtain the first pose parameter of the grinding tool under the optical positioning system, and calculate the grinding parameter of the grinding tool for the target joint based on the first pose parameter; identify whether the grinding parameter reaches the target grinding position; if so, obtain the second pose parameter of the joint prosthesis under the optical positioning system after the joint prosthesis replacement is completed, and calculate the spatial performance parameter of the joint prosthesis based on the second pose parameter; perform replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameter. Through the above joint prosthesis replacement training method based on the solid model, the problems existing in the prior art, such as the inability to ensure the training effect, the lack of intuitive feedback of the training result, and the low training efficiency, are solved. By calculating the spatial performance parameter of the joint prosthesis when the grinding parameter of the grinding tool for the target joint in the solid model reaches the target grinding position, and performing replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameter, the purpose of providing a solid interaction training simulation environment can be achieved, which is beneficial to improving the training effect of joint prosthesis replacement, ensuring the intuitiveness of the training result feedback, and improving the training efficiency.

[0080] Figure 3 It is a schematic diagram of obtaining the target grinding position provided by the present application. As Figure 3 shown, it specifically includes the following steps:

[0081] S301, perform point cloud extraction on the three-dimensional model of the target joint in the image space of the pre-constructed solid model to obtain the point cloud data of the target joint.

[0082] Among them, the point cloud data of the target joint can be the point cloud coordinates of the surface point cloud of the three-dimensional model of the target joint in the image space coordinate system. In this solution, the point cloud of the target joint mainly refers to the surface point cloud of the three-dimensional model of the acetabulum.

[0083] In one embodiment, a point cloud extraction algorithm can be used to perform point cloud extraction on the three-dimensional model of the target joint in the image space of the pre-constructed solid model, and read the point cloud coordinates of each extracted point cloud in the image space coordinate system to obtain the point cloud data of the target joint.

[0084] In one embodiment, the construction process of the three-dimensional model of the target joint in the image space includes: obtaining multiple two-dimensional images of the solid model, performing three-dimensional reconstruction on the solid model based on the multiple two-dimensional images to obtain the overall three-dimensional model of the solid model in the image space; performing structure segmentation on the overall three-dimensional model based on the pre-trained structure segmentation model to obtain the three-dimensional model of the target joint in the image space.

[0085] Among them, multiple two-dimensional images of the solid model can be multiple two-dimensional CT images obtained by scanning the solid model. By superimposing the multiple two-dimensional CT images, three-dimensional reconstruction of the solid model can be performed. The overall three-dimensional model can be a virtual three-dimensional model with the same shape, size, and structure as the solid model of the entire hip joint. The structure segmentation model can be a pre-trained deep learning model used to split the acetabular three-dimensional model in the three-dimensional model of the entire hip joint. For example: the nnU-Net deep learning model.

[0086] In one embodiment, multiple two-dimensional images obtained by scanning the solid model can be acquired, the multiple two-dimensional images are superimposed in the scanning order, three-dimensional reconstruction of the solid model is performed to obtain the overall three-dimensional model of the solid model in the image space, that is, the solid model of the entire hip joint. The pre-trained structure segmentation model is used to perform structure segmentation on the overall three-dimensional model to obtain the three-dimensional model of the target joint in the image space, that is, the acetabular three-dimensional model in the image space.

[0087] For example: Using the deep learning segmentation algorithm in the nnU-Net network architecture, the two-dimensional images are efficiently segmented through multiple layers of encoder and decoder structures, and the segmentation results are superimposed to obtain the three-dimensional model of the target joint. The nnU-Net network architecture includes multiple convolutional, pooling, upsampling, and skip connection layers. The segmentation calculation process of the entire model can be represented by the following formula:

[0088]

[0089] Among them, is the model output, and has the same image height, image width, and image depth as the input image, and includes the output categories after image segmentation. The forward propagation process of the structure segmentation model is completed through the stacking of multiple encoder and decoder layers.

[0090] S302, Calculate the center-of-sphere coordinates and the target rasping direction of the target joint in the image space based on the fitting algorithm and the point cloud data.

[0091] Among them, the fitting algorithm can be a calculation process of using a function or model to fit the existing data points to describe the data change trend and predict or reconstruct the position data points. The fitting algorithm in this solution is an algorithm for fitting the rasping surface in the hip joint solid model. The rasping surface in this solution is the acetabular fossa. The center-of-sphere coordinates can be the original coordinates corresponding to the original center-of-sphere position of the acetabular fossa in the image space before the hip joint solid model is rasped. The target rasping direction can be the movement direction of the rasping end of the acetabular rasp during the process of rasping the acetabular fossa of the hip joint solid model from the initial position to the target position.

[0092] In one embodiment, a spherical fitting can be performed on the acetabular fossa of the target joint using a fitting algorithm and point cloud data to obtain the center coordinates and radius of the target joint. PCA principal component analysis can be performed on the point cloud data to obtain the normal vector of the target joint, and the normal vector can be used as the target rasping direction.

[0093] In one embodiment, calculating the center coordinates and target rasping direction of the target joint in the image space based on the fitting algorithm and point cloud data includes: performing edge plane fitting on the target joint based on the plane fitting algorithm and point cloud data to obtain the plane normal vector and centroid coordinates of the target joint in the image space; performing spherical fitting on the target joint based on the iterative algorithm and point cloud data to obtain the center coordinates of the target joint in the image space; calculating the angle between the direction vector from the centroid coordinates to the center coordinates and the plane normal vector, and identifying whether the angle is greater than a preset angle threshold; and in the case where the angle is greater than the preset angle threshold, determining the opposite direction of the plane normal vector as the target rasping direction of the target joint in the image space.

[0094] Among them, edge plane fitting can be a process of performing plane fitting on the edge point cloud of the target joint to obtain a reference plane. In this solution, edge plane fitting is used to calculate the opening orientation of the acetabular fossa to determine the rasping direction for rasping the acetabular fossa. Spherical fitting can be a process of performing spherical fitting on the rasping point cloud of the target joint to obtain a sphere that matches the rasping surface of the target joint. In this solution, spherical fitting is used to calculate the center coordinates and radius of the acetabular fossa, and further determine the rasping depth. The preset angle threshold can be the maximum value of the angle between the vector from the centroid to the center when the direction of the normal vector is the same as the rasping direction. In this solution, the preset angle threshold is set to 90°.

[0095] In one embodiment, the centroid of the point cloud on the three-dimensional acetabular model can be calculated by the following formula:

[0096]

[0097] Among them, c is the centroid vector of the point cloud, and p i is the point cloud coordinate on the three-dimensional acetabular model.

[0098] p i can be expressed as:

[0099]

[0100] The point cloud data of the acetabular fossa can be expressed as:

[0101]

[0102] Among them, N is the number of points in the point cloud.

[0103] The plane fitting of the acetabular rim can be performed using the SVD algorithm, and the point cloud data is centered by the following formula:

[0104] p i ' = p i - c.

[0105] The point cloud matrix is constructed and singular value decomposition (SVD) is performed by the following formula:

[0106]

[0107] A = UΣV T ;

[0108] where A is the original point cloud data matrix, usually each row represents the coordinates of a point, U is an m×m orthogonal matrix, whose columns are the left singular vectors of matrix A, Σ is an m×n diagonal matrix, where the elements on the diagonal are the singular values, usually arranged in descending order, and V T is an n×n orthogonal matrix, whose rows are the right singular vectors of matrix A.

[0109] The plane normal vector of the target joint in the image space is the minimum eigenvector in the SVD calculation result:

[0110]

[0111] where a, b, and c are the elements in the plane normal vector.

[0112] The offset of the plane from the origin is calculated by the following formula:

[0113]

[0114] where d is the offset of the plane from the origin.

[0115] The acetabular rim fitting plane equation is expressed by the following expression:

[0116] ax + by + cz + d = 0.

[0117] The spherical surface is fitted using the Gauss-Newton iteration method, and the fitted spherical surface is expressed by the following formula:

[0118] (x - x o ) 2 + (y - y o ) 2 + (z - z o ) 2 = R 2 ;

[0119] where the center coordinates of the sphere are o = (x o , y o, z o ) T 。

[0120] Iteratively calculate the point cloud coordinates through the following formula to obtain the center coordinates of the sphere and the radius of the fitted spherical surface:

[0121]

[0122] Where, R is the radius of the acetabular fossa, and E is the error function.

[0123] Calculate the vector from the centroid to the center of the sphere through the following formula:

[0124]

[0125] Where, is the vector from the centroid to the center of the sphere.

[0126] Calculate the angle between the vector from the centroid to the center of the sphere and the plane normal vector through the following formula:

[0127]

[0128] Where, θ is the angle between the vector from the centroid to the center of the sphere and the plane normal vector.

[0129] If the angle is greater than 90°, then determine the opposite direction of the normal vector direction as the target grinding direction.

[0130] In this solution, by performing edge plane fitting and spherical fitting on the target joint based on the plane fitting algorithm, the plane normal vector, centroid coordinates, and center coordinates of the sphere of the target joint in the image space are obtained, the angle between the direction vector from the centroid coordinates to the center coordinates of the sphere and the plane normal vector is calculated, and the opposite direction of the plane normal vector is determined as the target grinding direction of the target joint in the image space, which can improve the accuracy of the determination result of the target grinding direction.

[0131] S303. Obtain the conversion relationship between the optical positioning system and the image space, and determine the target grinding position of the target joint based on the center coordinates of the sphere, the target grinding direction, and the conversion relationship.

[0132] In one embodiment, the pre-calculated conversion relationship between the optical positioning system and the image space can be obtained, and according to the conversion relationship, the center coordinates of the sphere and the target grinding direction are converted from the image control to the optical positioning system to obtain the target grinding position of the target joint in the optical positioning system.

[0133] In one embodiment, the process of determining the conversion relationship between the optical positioning system and the image space includes: obtaining the first point cloud coordinates of multiple preset marker points on the three-dimensional model in the image space and the second point cloud coordinates in the optical positioning system; performing rough registration on the image space and the optical positioning system based on the first point cloud coordinates and the second point cloud coordinates to obtain a rough registration conversion relationship; obtaining multiple third point cloud coordinates collected by the probe tool for the target joint in the optical positioning system, and performing fine registration on the image space and the optical positioning system based on the first point cloud coordinates and the third point cloud coordinates to obtain a fine registration conversion relationship; determining the conversion relationship between the optical positioning system and the image space based on the rough registration conversion relationship and the fine registration conversion relationship.

[0134] Among them, the preset marker points can be multiple reflective markers set on the target joint solid model. The first point cloud coordinates can be the coordinates of the point cloud of the preset marker points at the corresponding positions on the three-dimensional model of the target joint in the image space. The second point cloud coordinates can be the coordinates of the point cloud of the preset marker points at the corresponding positions on the three-dimensional model of the target joint in the optical positioning system. Rough registration can be an algorithm for roughly aligning the image space and the optical positioning system using the SVD algorithm and the coordinates of the preset marker point positions in different spaces. The number of preset marker points in the rough registration process is preferably four. The probe tool can be a device for collecting the point cloud coordinates of the grinding surface of the target joint in the optical positioning system. A reflective marker is set at the tip of the probe tool, and the point cloud coordinates of the contact point between the tip and the target joint can be directly read by the optical positioning system. The third point cloud coordinates can be the coordinates of the point cloud of the contact between the tip of the probe tool and the target joint in the optical positioning system. Fine registration can be an algorithm for precisely aligning the image space and the optical positioning system using the ICP algorithm and the coordinates of multiple groups of point clouds in different spaces.

[0135] In one embodiment, the first point cloud coordinates of multiple preset marker points on the three-dimensional model in the image space and the second point cloud coordinates in the optical positioning system can be obtained respectively, and the first point cloud coordinates and the second point cloud coordinates are used as the input of the SVD algorithm to perform rough registration on the image space and the optical positioning system to obtain a rough registration conversion relationship.

[0136] The multiple third point cloud coordinates collected by the contact of the probe tool with the target joint solid model in the optical positioning system can be obtained, and the first point cloud coordinates and the third point cloud coordinates are used as the input of the ICP algorithm to perform fine registration on the image space and the optical positioning system to obtain a fine registration conversion relationship.

[0137] The goal of the ICP algorithm is to align the point cloud coordinates in the image space with the point cloud coordinates in the optical positioning system, and find the optimal rigid body transformation to minimize the distance between the transformed point cloud and the target point cloud. The minimization of the distance between the transformed point cloud and the target point cloud can be represented by the following formula:

[0138]

[0139] where q i is the third point cloud coordinate, p i is the first point cloud coordinate, R is the rotation matrix in the rough registration transformation relationship, t is the translation matrix in the rough registration transformation relationship, and N is the number of point clouds.

[0140] After obtaining the fine registration transformation relationship by using the ICP algorithm, the transformation relationship between the image space coordinate system and the optical positioning system coordinate system can be calculated through the following formula:

[0141] M3 = M2M1;

[0142] where M3 is the final transformation matrix between the image space and the optical positioning system, M2 is the fine registration matrix between the image space and the optical positioning system, and M1 is the rough registration matrix between the image space and the optical positioning system.

[0143] In this solution, the rough registration of the image space and the optical positioning system is performed by obtaining the first point cloud coordinates of multiple preset marker points on the three-dimensional model in the image space and the second point cloud coordinates in the optical positioning system, and the fine registration of the image space and the optical positioning system is performed by obtaining multiple third point cloud coordinates collected by the probe tool for the target joint in the optical positioning system. Furthermore, based on the rough registration transformation relationship and the fine registration transformation relationship, the transformation relationship between the optical positioning system and the image space is determined, which can achieve the purpose of accurately registering the optical positioning system and the image space, improve the navigation accuracy in the subsequent joint prosthesis replacement training process, and is beneficial to improving the training effect.

[0144] The technical solution provided by the embodiment of the present application extracts the point cloud of the target joint in the three-dimensional model in the image space from the pre-constructed entity model to obtain the point cloud data of the target joint, calculates the center coordinates of the sphere and the target grinding direction of the target joint in the image space based on the fitting algorithm and the point cloud data, and determines the target grinding position of the target joint based on the center coordinates of the sphere, the target grinding direction, and the transformation relationship between the optical positioning system and the image space, which can achieve the purpose of grinding planning for joint prosthesis replacement training, is beneficial to improving the grinding navigation accuracy in the training process, and improves the efficiency of joint prosthesis replacement training.

[0145] Figure 4 is a schematic flowchart of another method for joint prosthesis replacement training based on an entity model provided by the present application. As Figure 4 shown, it specifically includes the following steps:

[0146] S401, obtain the target grinding position of the target joint in the entity model.

[0147] S402. During the grinding and filing process of the target joint, obtain the first pose parameters of the grinding and filing tool under the optical positioning system, and calculate the grinding and filing parameters of the grinding and filing tool for the target joint based on the first pose parameters.

[0148] S403. Identify whether the grinding and filing parameters reach the target grinding and filing position.

[0149] S404. If so, after completing the joint prosthesis replacement, obtain the second pose parameters of the joint prosthesis under the optical positioning system, and calculate the spatial performance parameters of the joint prosthesis based on the second pose parameters. The spatial performance parameters include the prosthesis anteversion angle and the prosthesis abduction angle of the joint prosthesis after the replacement is completed.

[0150] S405. Identify the target anteversion angle range corresponding to the prosthesis anteversion angle in the pre-set replacement evaluation comparison table, and read the first score corresponding to the target anteversion angle range.

[0151] Among them, the prosthesis anteversion angle can be the joint prosthesis, that is, the forward tilt angle on the horizontal plane after the acetabular cup replacement is completed. The prosthesis abduction angle can be the outward tilt angle on the coronal plane after the joint prosthesis replacement is completed. The target anteversion angle range can be one of the anteversion angle ranges divided in the pre-set replacement evaluation comparison table to which the prosthesis anteversion angle belongs.

[0152] In one embodiment, according to the magnitude relationship between the prosthesis anteversion angle and the boundary values of each anteversion angle range in the pre-set replacement evaluation comparison table, determine the anteversion angle range where the prosthesis anteversion angle is located as the corresponding target anteversion angle range, and read the first score corresponding to the target anteversion angle range in the pre-set replacement evaluation comparison table.

[0153] S406. Identify the target abduction angle range corresponding to the prosthesis abduction angle in the pre-set replacement evaluation comparison table, and read the second score corresponding to the target abduction angle range.

[0154] Among them, the target abduction angle range can be one of the abduction angle ranges divided in the pre-set replacement evaluation comparison table to which the prosthesis abduction angle belongs.

[0155] In one embodiment, according to the magnitude relationship between the prosthesis abduction angle and the boundary values of each abduction angle range in the pre-set replacement evaluation comparison table, determine the abduction angle range where the prosthesis abduction angle is located as the corresponding target abduction angle range, and read the second score corresponding to the target abduction angle range in the pre-set replacement evaluation comparison table.

[0156] S407. Integrate the first score and the second score to obtain the joint replacement evaluation score for the target joint.

[0157] In one embodiment, the preset replacement evaluation comparison table may simultaneously include the evaluation relationship of the anteversion angle score of the replacement prosthesis and the evaluation relationship of the abduction angle score of the replacement prosthesis, as shown in Table 1 below.

[0158]

[0159]

[0160] Table 1

[0161] Therefore, the sum of the evaluation scores of the anteversion angle of the replacement prosthesis and the evaluation score of the abduction angle of the replacement prosthesis can be calculated to obtain the replacement evaluation score for evaluating the joint replacement result.

[0162] And the preset replacement evaluation comparison table may also simultaneously include the evaluation relationship of the anteversion angle score at the end of rasping and the evaluation relationship of the abduction angle score at the end of rasping, as shown in Table 2 below.

[0163]

[0164]

[0165] Table 2

[0166] Therefore, after obtaining the rasping score for evaluating the rasping result, can the replacement evaluation score and the rasping score be integrated to obtain the final joint replacement evaluation score.

[0167] In one embodiment, before performing the replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameters, the method further includes: obtaining the initial length of the associated joint of the target joint in the solid model, and obtaining the final length of the associated joint after the replacement is completed; correspondingly, integrating the first score and the second score to obtain the joint replacement evaluation score of the target joint, including: determining the replacement error of the joint replacement result based on the initial length and the final length; integrating the first score, the second score and the replacement error to obtain the joint replacement evaluation score of the target joint.

[0168] Among them, the associated joint may be a joint in the entire solid model that can be affected by the rasping and prosthesis replacement operations of the target joint. The associated joint in this solution is mainly the leg. The initial length may be the length of the leg before the joint prosthesis replacement. The final length is the length of the leg after the joint prosthesis replacement. The replacement error may be a parameter representing the degree of influence of the joint prosthesis replacement on the length of the associated joint. The replacement error may be represented by the difference between the final length and the initial length.

[0169] In one embodiment, two measurement sampling points can be preset on the associated joint respectively, and by measuring the distances between the two measurement sampling points before and after the joint prosthesis replacement respectively, the initial length and the final length of the associated joint of the target joint in the solid model can be obtained. Calculate the difference between the initial length and the final length, and determine the replacement error of the joint replacement result as the difference value. The replacement evaluation comparison table can also include the evaluation relationship of the replacement error score after the replacement is completed, as shown in Table 3 below.

[0170]

[0171] Table 3

[0172] The error evaluation score corresponding to the replacement error can be determined according to the replacement error score evaluation relationship. Calculate the sum of the first score, the second score and the error evaluation score to obtain the joint replacement evaluation score for the target joint.

[0173] In this solution, by obtaining the initial length of the associated joint of the target joint in the solid model and the final length after the replacement is completed to determine the replacement error of the joint replacement result, integrating the first score, the second score and the replacement error, and obtaining the joint replacement evaluation score for the target joint, it can achieve taking the influence degree of the joint prosthesis replacement on the associated joint as an evaluation factor for the joint prosthesis replacement training result, and further improve the accuracy and comprehensiveness of the evaluation of the joint prosthesis replacement training result.

[0174] The technical solution provided by the embodiment of the present application can determine the corresponding first score by identifying the target inclination angle range corresponding to the prosthesis anteversion angle in the preset replacement evaluation comparison table, determine the corresponding second score by identifying the target abduction angle range corresponding to the prosthesis abduction angle in the preset replacement evaluation comparison table, and integrate the first score and the second score to obtain the joint replacement evaluation score for the target joint, so as to achieve the purpose of quantitatively evaluating the replacement training result and ensure the intuitiveness of the training result feedback.

[0175] Figure 5 It is a schematic structural diagram of a joint prosthesis replacement training device based on a solid model provided by the present application. As Figure 5 shown, it specifically includes the following:

[0176] A target position acquisition module 501, configured to acquire the target filing position of the target joint in the solid model;

[0177] A filing parameter calculation module 502, configured to acquire the first pose parameter of the filing tool under the optical positioning system during the filing process of the target joint, and calculate the filing parameters of the filing tool for the target joint based on the first pose parameter;

[0178] A filing parameter identification module 503, configured to identify whether the filing parameters reach the target filing position;

[0179] A spatial representation parameter calculation module 504, configured to obtain second pose parameters of the joint prosthesis under the optical positioning system after the joint prosthesis replacement is completed when the grinding parameters reach the target grinding position, and calculate spatial representation parameters of the joint prosthesis based on the second pose parameters;

[0180] A replacement evaluation module 505, configured to perform replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and spatial representation parameters.

[0181] Further, the target position acquisition module 501 is specifically configured to:

[0182] Extract point cloud data of the target joint by performing point cloud extraction on the three-dimensional model of the target joint in the image space in the pre-constructed solid model;

[0183] Calculate the center-of-sphere coordinates and the target grinding direction of the target joint in the image space based on a fitting algorithm and the point cloud data;

[0184] Obtain the conversion relationship between the optical positioning system and the image space, and determine the target grinding position of the target joint based on the center-of-sphere coordinates, the target grinding direction, and the conversion relationship.

[0185] Further, the target position acquisition module 501 is specifically configured to:

[0186] Perform edge plane fitting on the target joint based on a plane fitting algorithm and the point cloud data to obtain the plane normal vector and the centroid coordinates of the target joint in the image space;

[0187] Perform spherical fitting on the target joint based on an iterative algorithm and the point cloud data to obtain the center-of-sphere coordinates of the target joint in the image space;

[0188] Calculate the angle between the direction vector from the centroid coordinates to the center-of-sphere coordinates and the plane normal vector, and identify whether the angle is greater than a preset angle threshold;

[0189] When the angle is greater than the preset angle threshold, determine the opposite direction of the plane normal vector as the target grinding direction of the target joint in the image space.

[0190] Further, the target position acquisition module 501 is specifically configured to:

[0191] Obtain multiple two-dimensional images of the solid model, perform three-dimensional reconstruction on the solid model based on the multiple two-dimensional images to obtain the overall three-dimensional model of the solid model in the image space;

[0192] Perform structure segmentation on the overall three-dimensional model based on a pre-trained structure segmentation model to obtain the three-dimensional model of the target joint in the image space.

[0193] Further, the target position acquisition module 501 is specifically configured to:

[0194] Obtain the first point cloud coordinates of multiple preset marker points on the three-dimensional model in the image space and the second point cloud coordinates in the optical positioning system;

[0195] Perform rough registration on the image space and the optical positioning system based on the first point cloud coordinates and the second point cloud coordinates to obtain a rough registration transformation relationship;

[0196] Obtain multiple third point cloud coordinates collected by the probe tool for the target joint in the optical positioning system, and perform fine registration on the image space and the optical positioning system based on the first point cloud coordinates and the third point cloud coordinates to obtain a fine registration transformation relationship;

[0197] Determine the transformation relationship between the optical positioning system and the image space based on the rough registration transformation relationship and the fine registration transformation relationship.

[0198] Further, the spatial performance parameters include the prosthetic anteversion angle and the prosthetic abduction angle of the joint prosthesis after replacement;

[0199] The replacement evaluation module 505 is specifically configured to:

[0200] Identify the target anteversion angle range corresponding to the prosthetic anteversion angle in the preset replacement evaluation comparison table, and read the first score corresponding to the target anteversion angle range;

[0201] Identify the target abduction angle range corresponding to the prosthetic abduction angle in the preset replacement evaluation comparison table, and read the second score corresponding to the target abduction angle range;

[0202] Integrate the first score and the second score to obtain the joint replacement evaluation score for the target joint.

[0203] Further, the replacement evaluation module 505 is further configured to:

[0204] Obtain the initial length of the associated joint of the target joint in the solid model, and obtain the final length of the associated joint after replacement;

[0205] Correspondingly, the replacement evaluation module 505 is specifically configured to:

[0206] Determine the replacement error of the joint replacement result based on the initial length and the final length;

[0207] Integrate the first score, the second score and the replacement error to obtain the joint replacement evaluation score for the target joint.

[0208] In the technical solution provided by the embodiment of the present application, the target position acquisition module is used to acquire the target grinding position of the target joint in the entity model; the grinding parameter calculation module is used to acquire the first pose parameter of the grinding tool under the optical positioning system during the grinding process of the target joint, and calculate the grinding parameters of the grinding tool for the target joint based on the first pose parameter; the grinding parameter recognition module is used to recognize whether the grinding parameters reach the target grinding position; the spatial performance parameter calculation module is used to, when the grinding parameters reach the target grinding position, acquire the second pose parameter of the joint prosthesis under the optical positioning system after the joint prosthesis replacement is completed, and calculate the spatial performance parameters of the joint prosthesis based on the second pose parameter; the replacement evaluation module is used to perform replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameters. Through the above joint prosthesis replacement training device based on the entity model, the problems existing in the prior art, such as the inability to ensure the training effect, the lack of intuitive feedback of the training result, and the low training efficiency, are solved. By calculating the spatial performance parameters of the joint prosthesis when the grinding parameters of the grinding tool for the target joint in the entity model reach the target grinding position, and performing replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameters, the purpose of providing an entity interaction training simulation environment can be achieved, which is beneficial to improving the training effect of joint prosthesis replacement, ensuring the intuitiveness of the training result feedback, and improving the training efficiency.

[0209] The joint prosthesis replacement training device based on the entity model in the embodiment of the present application can be a device, or a component, an integrated circuit, or a chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiment of the present application does not make specific limitations.

[0210] The joint prosthesis replacement training device based on the entity model in the embodiment of the present application can be a device with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems. The embodiment of the present application does not make specific limitations.

[0211] The joint prosthesis replacement training device based on an entity model provided by this application can implement each process achieved by the above method embodiments. To avoid repetition, it will not be elaborated here.

[0212] As Figure 6 shown, an embodiment of this application further provides an electronic device 600, including a processor 601, a memory 602, and a program or instruction stored on the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, it implements each process of the above embodiment of the joint prosthesis replacement training device based on an entity model and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0213] It should be noted that the electronic device in the embodiment of this application includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0214] An embodiment of this application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above embodiment of the joint prosthesis replacement training device based on an entity model and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0215] Among them, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks, or optical discs, etc.

[0216] Another embodiment of this application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or instruction to implement each process of the above embodiment of the joint prosthesis replacement training device based on an entity model and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0217] It should be understood that the chip mentioned in the embodiment of this application can also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0218] It should be noted that in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0219] From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0220] The embodiments of the present application have been described above with reference to the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present application, without departing from the purpose of the present application and the scope protected by the claims, can still make many forms, all of which fall within the protection scope of the present application.

[0221] The above is only the preferred embodiment of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions that can be made by those skilled in the art will not depart from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, it may also include more other equivalent embodiments, and the scope of the present application is determined by the scope of the claims.

Claims

1. A joint prosthesis replacement training method based on a physical model, characterized in that: The method comprises: Obtaining a target grinding and filing position of a target joint in a solid model; During the filing of the target joint, obtaining first posture parameters of the filing tool under the optical positioning system, and calculating filing parameters of the filing tool on the target joint based on the first posture parameters; identifying whether the filing parameter reaches the target filing position; If so, obtaining second posture parameters of the joint prosthesis under the optical positioning system after completing the joint prosthesis replacement, and calculating the spatial performance parameters of the joint prosthesis based on the second posture parameters; The joint replacement result of the target joint is evaluated based on the preset replacement evaluation comparison table and the spatial performance parameters.

2. The joint prosthesis replacement training method based on a physical model according to claim 1, characterized in that: The step of obtaining a target filing position of a target joint in a solid model includes: Performing point cloud extraction on a three-dimensional model of a target joint in an image space in a pre-built solid model to obtain point cloud data of the target joint; Calculate the spherical center coordinates and target grinding direction of the target joint in the image space based on the fitting algorithm and the point cloud data; A conversion relationship between the optical positioning system and the image space is acquired, and a target filing position of the target joint is determined based on the spherical center coordinates, the target filing direction, and the conversion relationship.

3. The joint prosthesis replacement training method based on a physical model according to claim 2, characterized in that: The calculating of the spherical center coordinates and the target filing direction of the target joint in the image space based on the fitting algorithm and the point cloud data includes: Performing edge plane fitting on the target joint based on a plane fitting algorithm and the point cloud data to obtain a plane normal vector and centroid coordinates of the target joint in the image space; Performing spherical fitting on the target joint based on an iterative algorithm and the point cloud data to obtain the spherical center coordinates of the target joint in the image space; Calculating the angle between the direction vector pointing from the centroid coordinate to the spherical center coordinate and the plane normal vector, and identifying whether the angle is greater than a preset angle threshold; When the angle is greater than a preset angle threshold, the opposite direction of the plane normal vector is determined as the target filing direction of the target joint in the image space.

4. The joint prosthesis replacement training method based on a physical model according to claim 2, characterized in that: The process of constructing the three-dimensional model of the target joint in the image space includes: Acquiring multiple two-dimensional images of the entity model, and performing three-dimensional reconstruction of the entity model based on the multiple two-dimensional images to obtain an overall three-dimensional model of the entity model in the image space; The overall three-dimensional model is structurally segmented based on a pre-trained structural segmentation model to obtain a three-dimensional model of the target joint in the image space.

5. The joint prosthesis replacement training method based on a physical model according to claim 2, characterized in that: The process of determining the conversion relationship between the optical positioning system and the image space includes: Obtaining first point cloud coordinates of a plurality of preset marking points on the three-dimensional model in the image space and second point cloud coordinates in the optical positioning system; Performing a coarse registration between the image space and the optical positioning system based on the first point cloud coordinates and the second point cloud coordinates to obtain a coarse registration transformation relationship; Acquire a plurality of third point cloud coordinates of the target joint collected by the probe tool in the optical positioning system, and perform precise registration of the image space and the optical positioning system based on the first point cloud coordinates and the third point cloud coordinates to obtain a precise registration transformation relationship; A transformation relationship between the optical positioning system and the image space is determined based on the coarse registration transformation relationship and the fine registration transformation relationship.

6. The joint prosthesis replacement training method based on a physical model according to claim 1, characterized in that: The spatial performance parameters include the prosthesis anteversion angle and prosthesis abduction angle of the joint prosthesis after replacement; The performing replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameters includes: Identifying a target anteversion angle range corresponding to the prosthesis anteversion angle in a preset replacement evaluation comparison table, and reading a first score corresponding to the target anteversion angle range; Identifying a target abduction angle range corresponding to the prosthesis abduction angle in a preset replacement evaluation comparison table, and reading a second score corresponding to the target abduction angle range; The first score and the second score are integrated to obtain a joint replacement assessment score for the target joint.

7. The joint prosthesis replacement training method based on a physical model according to claim 6, characterized in that: Before performing a replacement evaluation on the joint replacement result of the target joint based on the preset replacement evaluation comparison table and the spatial performance parameters, the method further includes: Obtaining an initial length of a joint associated with the target joint in the solid model, and obtaining a final length of the joint associated with the target joint after replacement; Accordingly, the integration of the first score and the second score to obtain a joint replacement assessment score for the target joint includes: determining a replacement error of the joint replacement result based on the initial length and the final length; The first score, the second score and the replacement error are integrated to obtain a joint replacement assessment score for the target joint.

8. A joint prosthesis replacement training device based on a physical model, characterized in that: The device comprises: A target position acquisition module is used to obtain a target grinding and filing position of a target joint in a solid model; a filing parameter calculation module, configured to obtain first posture parameters of the filing tool under the optical positioning system during filing of the target joint, and calculate filing parameters of the filing tool for the target joint based on the first posture parameters; a filing parameter identification module, configured to identify whether the filing parameter reaches the target filing position; a spatial performance parameter calculation module, configured to obtain second posture parameters of the joint prosthesis under the optical positioning system after the joint prosthesis replacement is completed when the grinding and filing parameters reach the target grinding and filing position, and calculate the spatial performance parameters of the joint prosthesis based on the second posture parameters; The replacement evaluation module is used to perform replacement evaluation on the joint replacement result of the target joint based on a preset replacement evaluation comparison table and the spatial performance parameters.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of a content typesetting method based on a reference document as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the content typesetting method based on the reference document are implemented as described in any one of claims 1 to 7.

Images