Orthopedic surgical navigation method, apparatus and system, and electronic device and storage medium

Abstract

The present application relates to the technical field of computers. Provided are an orthopedic surgical navigation method, apparatus and system, and an electronic device and a storage medium. The method comprises: on the basis of a first image and a second image, generating a three-dimensional bone model of an affected bone; on the basis of the three-dimensional bone model and each bony landmark on the three-dimensional bone model, acquiring surgical parameters corresponding to the affected bone; on the basis of the correlation between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, registering the affected bone with the three-dimensional bone model, and establishing a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image; and on the basis of the surgical parameters corresponding to the affected bone, and the mapping relationship, performing surgical navigation.

Description

Orthopedic surgical navigation methods, devices, systems, electronic equipment and storage media

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese patent application No. 202411928576.4, filed on December 25, 2024, entitled "Orthopedic Surgical Navigation Method, Device, System, Electronic Device and Storage Medium", which is incorporated herein by reference in its entirety. Technical Field

[0003] This application relates to the field of computer technology, and in particular to an orthopedic surgical navigation method, device, system, electronic device, and storage medium. Background Technology

[0004] Surgical navigation is a visual image-guided surgical technique developed using medical images such as ultrasound, X-rays, CT (computed tomography), and MRI (magnetic resonance imaging) as the basis, and with the help of computers, precision instruments, and image processing technology. Surgical navigation can track the position of surgical instruments in real time through three-dimensional digitization of the patient's lesions, enabling visualization and automation of surgical procedures, thereby assisting doctors or robots to complete surgical tasks more quickly, accurately, and safely.

[0005] However, in orthopedic surgery, traditional surgical navigation methods are difficult to achieve objective and quantitative preoperative surgical planning when the patient's affected bone has bone defects and / or morphological abnormalities. This leads to unstable surgical outcomes, increases surgical risks, and affects the patient's postoperative recovery and final efficacy.

[0006] Furthermore, traditional surgical navigation methods struggle to accurately locate the affected bone in cases of bone defects or morphological abnormalities, hindering accurate intraoperative calibration and guidance. Therefore, achieving more objective and quantitative preoperative surgical planning and more accurate spatial localization of the affected bone during orthopedic surgery in cases of bone defects and / or morphological abnormalities is a pressing technical challenge in this field. Summary of the Invention

[0007] This application provides an orthopedic surgical navigation method, device, system, electronic device, and storage medium to address the shortcomings of existing technologies in achieving objective and quantitative preoperative surgical planning and accurate spatial positioning of the affected bone during orthopedic surgery when the patient has bone defects and / or morphological abnormalities. The application aims to achieve more objective and quantitative preoperative surgical planning and more accurate spatial positioning of the affected bone during orthopedic surgery when the patient has bone defects and / or morphological abnormalities.

[0008] This application provides a method for orthopedic surgical navigation, including:

[0009] Based on the first image and the second image, a three-dimensional bone model of the affected bone is generated. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human skeletons symmetrically distributed with the spine as the midline.

[0010] Multiple bony landmarks are determined on the three-dimensional bone model. Based on the three-dimensional bone model and each of the bony landmarks on the three-dimensional bone model, surgical parameters corresponding to the affected bone are obtained. The surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis model, prosthesis size, and prosthesis installation position.

[0011] Based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, the affected bone and the three-dimensional bone model are registered to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0012] Surgical navigation is performed based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0013] This application also provides an orthopedic surgical navigation device, including the following modules:

[0014] The data acquisition module is used to generate a three-dimensional bone model of the affected bone based on the first image and the second image. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human skeletons symmetrically distributed with the spine as the midline.

[0015] The preoperative planning module is used to determine multiple bony landmarks on the three-dimensional bone model, and to obtain surgical parameters corresponding to the affected bone based on the three-dimensional bone model and each of the bony landmarks on the three-dimensional bone model. The surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis model, prosthesis size and prosthesis installation position.

[0016] The intraoperative registration module is used to register the affected bone and the three-dimensional bone model based on the correspondence between each of the bony landmarks on the three-dimensional bone model and each of the bony landmarks on the affected bone, and to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0017] The intraoperative execution module is used to perform surgical navigation based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0018] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described orthopedic surgical navigation methods.

[0019] This application also provides an orthopedic surgical navigation system, including: an electronic device as described above and a surgical navigation device; the electronic device is communicatively connected to the surgical navigation device.

[0020] According to the orthopedic surgical navigation system provided in this application, it further includes: a human-computer interaction device; the human-computer interaction device is communicatively connected to the electronic device.

[0021] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the orthopedic surgical navigation method as described above.

[0022] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described orthopedic surgical navigation methods.

[0023] The orthopedic surgical navigation method, device, system, electronic equipment, and storage medium provided in this application generate a three-dimensional bone model of the affected bone by combining preoperative medical images of the affected bone with medical images of the corresponding healthy bone. This model can more accurately reflect the healthy morphology of the affected bone even when bone defects and / or morphological abnormalities exist. Furthermore, it allows for the acquisition of corresponding surgical parameters based on the three-dimensional bone model, making preoperative surgical planning more objective and quantitative. During orthopedic surgery, by registering bony landmarks on the three-dimensional bone model with actual bony landmarks on the affected bone, a precise mapping relationship can be established between the affected bone and the three-dimensional bone model. This enables accurate spatial positioning of the affected bone during surgery. Based on the corresponding surgical parameters and the mapping relationship with the three-dimensional bone model, the condition of the affected bone can be displayed in real time during surgery. This allows for more accurate spatial positioning of the affected bone during orthopedic surgery, providing doctors with intuitive visual guidance and helping them make more informed decisions during surgery. This reduces surgical complications and postoperative recovery time, significantly improves the accuracy and reliability of orthopedic surgery, effectively reduces surgical risks, and achieves more stable surgical outcomes. Attached Figure Description

[0024] 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 some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 is a flowchart illustrating the orthopedic surgical navigation method provided in this application.

[0026] Figure 2 is a schematic diagram of the orthopedic surgical navigation device provided in this application.

[0027] Figure 3 is a schematic diagram of the structure of the electronic device provided in this application.

[0028] Figure 4 is one of the structural schematic diagrams of the orthopedic surgical navigation system provided in this application.

[0029] Figure 5 is the second structural schematic diagram of the orthopedic surgical navigation system provided in this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0032] In the description of this application, the terms "first," "second," etc., 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 where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, in the description of this application, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0033] It should be noted that orthopedic surgery is a surgical treatment method for diseases of the skeletal system, encompassing various surgical types. The general procedure for orthopedic surgery typically includes preoperative examination, selection of surgical approach, surgical operation, and postoperative management.

[0034] In related technologies, before performing orthopedic surgery, surgeons can only plan the surgical procedure based on subjective experience using CT images of the affected bone taken before surgery. When planning the surgical procedure based on subjective experience, surgeons are limited to qualitative analysis of whether the patient's affected bone is suitable for surgery, making it difficult to quantitatively plan the surgical plan. For example, it is difficult to quantitatively plan the size of the osteotomy, the size of the implanted prosthesis, and the optimal placement of the prosthesis. Consequently, during orthopedic surgery, the lack of objective and quantitative preoperative surgical planning forces surgeons to rely solely on subjective experience, leading to unstable surgical outcomes, increased surgical risks, and impacts on postoperative recovery and final treatment results.

[0035] Furthermore, the bones are obscured by surrounding tissues such as muscles, blood vessels, and nerves, making it difficult for doctors to accurately determine the entire shape of the affected bone with the naked eye. In cases where the patient's affected bone has bone defects or abnormal shapes, doctors also find it difficult to accurately determine the degree of bone defects or abnormal bone shapes through visual observation. This may lead to errors in surgical procedures, affecting the precision and safety of the surgery.

[0036] For example, shoulder replacement surgery is an orthopedic procedure used to treat severe shoulder pain and dysfunction. Shoulder replacement surgery is typically performed on patients experiencing persistent pain and limited function due to shoulder arthritis, shoulder fractures, rotator cuff tears, or other conditions that damage the shoulder joint.

[0037] Artificial shoulder arthroplasty includes hemiarthroplasty, total shoulder arthroplasty, and reverse total shoulder arthroplasty. Hemiarthroplasty is primarily used for arthritis involving the humeral head and osteonecrosis not involving the labrum, as well as severe proximal humeral fractures. Total shoulder arthroplasty is mainly used for osteoarthritis, inflammatory arthritis, osteonecrosis involving the labrum, and postmenopausal degenerative joint diseases. Reverse total shoulder arthroplasty is primarily used for patients with osteoarthritis and complex humeral fractures. The indications for reverse total shoulder arthroplasty, which differ from total and hemiarthroplasty, are mainly those with severe rotator cuff tears or loss but with intact biceps brachii function. Because of its good recovery rate and lower revision rate compared to total shoulder arthroplasty, it is currently the most widely used shoulder arthroplasty procedure.

[0038] Shoulder replacement surgery involves removing the damaged joint surface (osteotomy) and implanting an artificial prosthesis to replace the damaged joint, thereby reducing pain and restoring joint function. The general procedure for shoulder surgery includes preoperative examination (e.g., medical imaging), surgical approach, dislocation of the humeral head, osteotomy and medullary canal reaming, prosthesis placement, rotator cuff repair, and postoperative evaluation. Among these, osteotomy and prosthesis placement are the most critical steps. Factors such as the amount of osteotomy, the angle of the osteotomy plane, the location of the prosthesis mounting holes, and the fit of the prosthesis implantation surface directly affect the success of the surgery. Improper prosthesis placement or poor implantation technique can lead to postoperative pain, joint instability, dislocation, or prosthesis loosening. High-quality osteotomy and prosthesis placement are core clinical demands for surgeons. Developing a personalized surgical plan before surgery, selecting a suitable prosthesis, simulating joint range of motion, and using navigation technology during osteotomy to assist surgeons in completing the preoperative plan can improve the accuracy of osteotomy and prosthesis placement, thereby reducing postoperative complications and improving the quality of the surgery. Furthermore, preoperative planning can predict the accuracy and stability of prosthesis placement, adjust the range of motion of the joint, and plan postoperative rehabilitation, thereby improving surgical outcomes.

[0039] However, in traditional shoulder replacement surgery, surgeons can only roughly plan the surgical procedure in a 2D plane based on preoperative medical images and experience. This planning is limited to a qualitative analysis of whether the patient's joint condition is suitable for surgery, lacking quantitative analysis, such as the size of the prosthesis, its placement direction, or the amount of osteotomy. Therefore, it is difficult for surgeons to develop personalized surgical plans, and even more difficult to simulate the impact of factors affecting postoperative joint mobility and other postoperative outcomes. During the operation, due to the lack of quantitative preoperative planning, surgeons can only make judgments based on experience within the limited time available. For example, in cases of bone defects or abnormal glenoid morphology, the surgeon may misjudge the glenoid morphology, leading to incorrect base placement. In patients with proximal humeral fractures, the lack of clear bony alignment landmarks makes it difficult to determine the height and anteroposterior angle of the humeral manubrium during surgery, affecting the surgeon's judgment. The lack of precise prosthesis positioning technology may lead to postoperative prosthesis placement deviating from the optimal state, thus affecting the recovery of joint function.

[0040] Surgical navigation can track the position of surgical instruments in real time through three-dimensional digital lesion tissue of the patient, enabling visualization and automation of surgical procedures, thereby assisting doctors or robots to complete surgical tasks more quickly, accurately and safely.

[0041] However, when there are bone defects or morphological abnormalities in the affected bone, medical imaging may not accurately reflect the true condition of the affected bone. Consequently, traditional surgical navigation methods are unable to achieve objective and quantitative preoperative surgical planning when the patient's affected bone has bone defects and / or morphological abnormalities.

[0042] Furthermore, bone defects and / or morphological abnormalities in the affected bone may cause changes in the iconic structures of the skeleton, making it difficult for traditional surgical navigation methods to accurately locate the affected bone in cases of bone defects or morphological abnormalities. Consequently, it becomes difficult to achieve accurate intraoperative calibration and guidance based on traditional surgical navigation methods.

[0043] For example, during a reverse shoulder replacement surgery, screws are needed for base installation. However, due to the thinness of the glenoid bone, if the affected bone cannot be accurately aligned and guided during the operation, the screws may penetrate the glenoid, leading to surgical failure.

[0044] To address this issue, this application provides an orthopedic surgical navigation method. The orthopedic surgical navigation method provided by this application, comprising preoperative planning, intraoperative registration, and intraoperative execution, solves the technical problems of traditional surgical navigation methods in cases where the patient has bone defects and / or morphological abnormalities. These methods struggle to achieve objective and quantitative preoperative surgical planning and accurate spatial positioning of the affected bone, leading to difficulties in accurate intraoperative calibration and guidance. This improves the stability of surgical outcomes and reduces surgical risks and postoperative complications.

[0045] The preoperative planning component includes the reconstruction of a three-dimensional bone model based on the patient's preoperative medical images. This allows doctors to plan the surgical steps in detail before the operation, including the selection, position, and angle adjustment of the scapular and humeral prostheses. It also allows for the simulation of joint mobility to predict postoperative joint function, reduce intraoperative decision-making time, and improve the accuracy of the operation.

[0046] The intraoperative registration component involves establishing a correspondence between the patient's affected bone and the three-dimensional bone model through a registration algorithm. This enables precise matching between the patient's affected bone and the preoperatively constructed three-dimensional bone model, providing accurate reference for intraoperative navigation.

[0047] The intraoperative navigation system tracks the position of surgical instruments and displays it in real time, ensuring the surgeon has a clear understanding of the surgical progress. It calculates the distance and angular deviation between the surgical instruments and the target location, providing the surgeon with precise navigation information. Visual feedback is provided to help the surgeon adjust the position and orientation of the surgical instruments, ensuring the surgery is executed precisely according to the preoperative plan.

[0048] The orthopedic surgical navigation method provided in this application is described below with reference to Figure 1.

[0049] Figure 1 is a flowchart of the orthopedic surgical navigation method provided in this application. As shown in Figure 1, the method includes the following steps: Step 101: Based on the first image and the second image, generate a three-dimensional bone model of the affected bone. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human bones symmetrically distributed with the spine as the midline.

[0050] It should be noted that the execution subject of this application embodiment is an orthopedic surgical navigation device. The above-mentioned orthopedic surgical navigation device can be configured in electronic devices such as computers or servers.

[0051] Specifically, the orthopedic surgical navigation method provided in this application can provide surgical navigation for doctors performing orthopedic surgery before and during the orthopedic surgery on the patient's affected bone, thereby improving the accuracy, safety and efficiency of the orthopedic surgery.

[0052] Understandably, to maintain balance and stability, the human skeleton is symmetrically distributed with the spine as the midline. Typically, most bones in the skull, trunk, and limbs appear in pairs, such as the scapula, humerus, ulna, radius, femur, patella, tibia, and fibula located on either side of the spine.

[0053] In this embodiment, the affected bone and the healthy bone are a pair of human skeletons symmetrically distributed with the spine as the midline. The affected bone is the bone on the surgical side that requires orthopedic surgery, and the healthy bone is the bone on the healthy side that corresponds to the affected bone and does not require orthopedic surgery. The surgical side is the side of the body that requires orthopedic surgery, and the healthy side is the side of the body that does not require orthopedic surgery.

[0054] When a patient's affected bone has bone defects and / or morphological abnormalities, it is difficult to generate a complete and accurate three-dimensional bone model based solely on the image of the affected bone. Therefore, in this embodiment, the image of the patient's healthy side is used for mapping, which can generate a complete and accurate three-dimensional bone model and bony landmarks of the affected bone, thereby improving the accuracy of preoperative surgical planning.

[0055] It is understood that the patient and the affected bone in the embodiments of this application can be determined based on actual needs. The embodiments of this application do not impose specific limitations on the patient and the affected bone.

[0056] Optionally, the orthopedic surgery performed on the patient's affected bone may be a shoulder replacement surgery. The affected bone in the patient may be the scapula, humerus, or clavicle.

[0057] Before performing orthopedic surgery on the patient's affected bone, medical images of the affected bone are obtained as the first image, and medical images of the corresponding healthy bone are obtained as the second image.

[0058] It should be noted that the medical images of the affected bone and healthy bone in the embodiments of this application may include, but are not limited to, medical images such as X-ray images, CT images and MRI images of the affected bone and healthy bone.

[0059] It is understood that medical images such as X-ray images, CT images, and MRI images follow standardized patient positioning, fixed imaging equipment, image reconstruction and localization methods, and standardized reports and markings. Therefore, the orientation of the affected bone in these medical images is relatively fixed. In this embodiment, the horizontal direction in the above medical images can be defined as the X-axis direction, and the vertical direction in the above medical images can be defined as the Y-axis direction.

[0060] In this embodiment, medical images of the patient's affected bone and the corresponding healthy bone can be obtained in various ways before orthopedic surgery. For example, medical images of the patient's affected bone and the corresponding healthy bone can be obtained through data query; or, medical images of the patient's affected bone and the corresponding healthy bone can be obtained based on user input. This embodiment does not limit the specific method for obtaining the medical images of the patient's affected bone and the corresponding healthy bone.

[0061] After obtaining medical images of the patient's affected bone and the corresponding healthy bone, the medical image of the affected bone can be designated as the first image, and the medical image of the corresponding healthy bone can be designated as the second image. Then, based on the first and second images, a three-dimensional bone model of the affected bone can be generated through data calculation, mathematical statistics, or deep learning techniques.

[0062] As an optional embodiment, generating a three-dimensional bone model of the affected bone based on the first image and the second image includes: constructing a first three-dimensional point cloud model based on the first image and constructing a second three-dimensional point cloud model based on the second image.

[0063] Specifically, after acquiring the first and second images, numerical calculations, mathematical statistics, and deep learning can be used to construct a first three-dimensional point cloud model based on the first image and a second three-dimensional point cloud model based on the second image.

[0064] As an optional embodiment, constructing a first three-dimensional point cloud model based on the first image includes: performing data preprocessing on the first image to obtain the data preprocessed first image, provided that the image quality of the first image meets a preset standard.

[0065] Based on the distribution of bone fragments in the affected bone, the first image after data preprocessing is segmented to obtain multiple sub-images corresponding to the first image. Each sub-image includes only one bone fragment from the affected bone.

[0066] The sub-image of the largest bone block in the affected bone is identified as the target sub-image. Then, based on the target sub-image, a three-dimensional point cloud model of the largest bone block in the affected bone is constructed as the first three-dimensional point cloud model.

[0067] It should be noted that, given the poor image quality of the first and second images, it is difficult to generate a 3D point cloud model based on them. Therefore, in this embodiment, a preset standard can be set based on prior knowledge and / or actual conditions, and the first and second images can be checked based on the preset standard to determine whether their image quality meets the requirements for generating a 3D point cloud model.

[0068] If the image quality of the first and second images meets a preset standard, it can be determined that the image quality of the first and second images is sufficient to generate a 3D point cloud model. Therefore, data preprocessing can be performed on the first image to further improve its image quality. This data preprocessing may include image denoising, contrast enhancement, and image sharpening.

[0069] It should be noted that, considering the possibility of bone fracture, after preprocessing the first image, it can be segmented to obtain multiple sub-images corresponding to the first image. Each sub-image corresponding to the first image includes only one bone fragment from the affected bone.

[0070] After obtaining the sub-images corresponding to the first image, the sub-image including the largest bone fragment in the affected bone can be identified as the target sub-image. Then, based on the target sub-image, a three-dimensional point cloud model of the largest bone fragment in the affected bone can be generated as the first three-dimensional point cloud model.

[0071] It should be noted that, in this embodiment, the Marching Cubes (MC) algorithm can be used to generate a three-dimensional point cloud model of the largest bone fragment in the affected bone based on the aforementioned target sub-image, serving as the first three-dimensional point cloud model. Alternatively, in this embodiment, the Marching Cubes algorithm can also be used to generate a three-dimensional point cloud model of the healthy bone corresponding to the affected bone based on the second image, serving as the second three-dimensional point cloud model.

[0072] The moving cube algorithm is a well-established algorithm for extracting isosurfaces. Its basic idea is to process cubes (voxels) in the data field one by one, separating the cubes that intersect with the isosurfaces, and using interpolation to calculate the intersection points of the isosurfaces with the cube edges. Based on the relative position of each vertex of the cube to the isosurface, the intersection points of the isosurfaces with the cube edges are connected in a certain way to generate an isosurface, which serves as an approximate representation of the isosurface within the cube. This is because the moving cube algorithm has a fundamental assumption: the data field along the edges of the hexahedron changes continuously. That is, if two vertices of an edge are greater than or less than the value of the isosurface, then there is one and only one point on that edge that is the intersection point of the edge and the isosurface.

[0073] This application embodiment preprocesses the first image to ensure that the image's clarity, contrast, and other properties meet the preset standards for subsequent analysis or modeling, which helps reduce analysis errors caused by poor image quality. By identifying the sub-image containing the largest bone block of the affected bone as the target sub-image and constructing a three-dimensional point cloud model based on the sub-image, the possibility of bone fracture in the affected bone can be fully considered, providing a more accurate data basis for generating a three-dimensional bone model of the affected bone.

[0074] Extract the centroids of the first and second 3D point cloud models. Based on the centroids of the first and second 3D point cloud models, mirror the second 3D point cloud model along the horizontal direction to obtain the third 3D point cloud model.

[0075] Specifically, in the embodiments of this application, S can be used to represent the first three-dimensional point cloud model and D can be used to represent the second three-dimensional point cloud model.

[0076] After constructing the first 3D point cloud model S and the second 3D point cloud model D, the centroid P of the first 3D point cloud model S can be extracted. c1 The centroid P of the second 3D point cloud model D c2 .

[0077] The position information of the centroid of a 3D point cloud model can be calculated using the following formula:

[0078] Among them, P c This represents the position information of the centroid of a 3D point cloud model; r i This represents the position information of the i-th point in the 3D point cloud model; n represents the number of points in the 3D point cloud model; m i The mass of the i-th point in the 3D point cloud model is represented by m in this embodiment. i The value of is 1; i represents a positive integer greater than zero.

[0079] It should be noted that in the embodiments of this application, coordinate values ​​can be used to represent the position information of any point in the three-dimensional point cloud model, or coordinate values ​​can be used to represent the position information of the centroid of the three-dimensional point cloud model.

[0080] Obtain the centroid P of the first 3D point cloud model S c1 The centroid P of the second 3D point cloud model D c2 Then, the centroid P of the second 3D point cloud model D can be used as a basis. c2 The coordinates of each point in the second 3D point cloud model D are mirrored and flipped horizontally to obtain the third 3D point cloud model Q1.

[0081] The position information of the i-th point in the third 3D point cloud model Q1 can be represented by the following formula: T1(x i )=2*P c2 [0]-x i

[0082] Where, x i P represents the position information of the i-th point in the second 3D point cloud model D. c2 [0] represents the centroid P of the second three-dimensional point cloud model D. c2 Location information; T1(x i ) represents the position information of the i-th point in the second 3D point cloud model D after a horizontal mirror flip, which is the position information of the i-th point in the third 3D point cloud model Q1; T1={T1(x1),T1(x2),…,T1(x... i ),…,T1(x I )}, where I represents the number of points in the second three-dimensional point cloud model D.

[0083] Align the first and third 3D point cloud models based on their centroids.

[0084] Specifically, after obtaining the third 3D point cloud model Q1, it can be done according to... Translate the aforementioned third 3D point cloud model Q1 to align the third 3D point cloud model Q1 with the first 3D point cloud model S.

[0085] The feature descriptor of each point in the third 3D point cloud model is obtained. Then, based on the feature descriptor of each point in the third 3D point cloud model, the consistency initial registration algorithm is used to perform coarse registration of the point cloud between the third 3D point cloud model and the first 3D point cloud model to obtain the fourth 3D point cloud model.

[0086] It should be noted that SPFH (Simplified Point Feature Histograms) feature vectors are a feature representation method used to describe the local geometric relationships of each point in a point cloud. The dimension of an SPFH feature vector is 33. SPFH features are generated by calculating the geometric relationships between a point and its neighbors. An SPFH feature vector consists of three angle histograms: the angle between the normal vector of the point and the normal vector of its neighbors, the angle between the normal vector of the point and the line connecting the two points, and the angle between the normal vector of the neighboring point and the line connecting the two points.

[0087] FPFH (Fast Point Feature Histograms) feature vectors are a type of feature descriptor widely used in point cloud processing.

[0088] For the p-th point in the third 3D point cloud model Q1, the SPFH feature vector of the p-th point in the third 3D point cloud model Q1 can be calculated numerically. Here, p represents a positive integer greater than zero.

[0089] After obtaining the SPFH feature vector of the p-th point in the third 3D point cloud model Q1, the FPFH feature vector of the p-th point in the third 3D point cloud model Q1 can be obtained by weighted summation of the SPFH features of the neighboring points of the p-th point in the third 3D point cloud model Q1. The specific calculation formula is as follows:

[0090] Where FPFH(p) represents the FPFH feature vector of the p-th point in the third 3D point cloud model Q1; SPFH(p) represents the SPFH feature vector of the p-th point in the third 3D point cloud model Q1; p j SPFH(p) represents the j-th neighboring point of the p-th point in the third 3D point cloud model Q1; j ) represents the j-th neighbor point p of the p-th point in the third 3D point cloud model Q1. j SPFH eigenvectors; d(p,p j ) represents the p-th point and its j-th neighboring point p in the third 3D point cloud model Q1. j The distance between them; j represents a positive integer greater than zero; J represents the total number of neighborhood points of the p-th point in the third 3D point cloud model Q1.

[0091] After obtaining the FPFH feature vector FPFH(p) of the p-th point in the third 3D point cloud model Q1, the FPFH feature vector FPFH(p) of the p-th point in the third 3D point cloud model Q1 can be determined as the feature descriptor of the p-th point in the third 3D point cloud model Q1.

[0092] After obtaining the feature descriptor of the p-th point in the third 3D point cloud model Q1, the embodiments of this application can use the Sample Consensus Initial Alignment (SAC-IA) algorithm to coarsely register the point clouds of the third 3D point cloud model Q1 and the first 3D point cloud model S. The specific steps include: selecting K sampling points from the third 3D point cloud model Q1, where K represents a positive integer greater than zero.

[0093] It should be noted that, in order to ensure that the sampling points selected from the third 3D point cloud model Q1 have different FPFH features, in this embodiment of the application, the distance between any two sampling points selected from the third 3D point cloud model Q1 is greater than a predefined distance threshold d.

[0094] For the k-th sampling point in the third 3D point cloud model Q1, based on the feature descriptor FPFH(k) of the k-th sampling point in the third 3D point cloud model Q1, one or more points in the first 3D point cloud model S that have similar FPFH features to the k-th sampling point in the third 3D point cloud model Q1 can be identified as similar points corresponding to the k-th sampling point in the third 3D point cloud model Q1.

[0095] It should be noted that if the Euclidean distance between the FPFH feature of any point in the first three-dimensional point cloud model S and the feature descriptor FPFH(k) of the kth sampling point in the third three-dimensional point cloud model Q1 is less than a preset value, it can be determined that any point in the first three-dimensional point cloud model S and the kth sampling point in the third three-dimensional point cloud model Q1 have similar FPFH features.

[0096] If there is only one similar point corresponding to the k-th sampling point in the third 3D point cloud model Q1, then the similar point corresponding to the k-th sampling point in the third 3D point cloud model Q1 can be determined as the associated point corresponding to the k-th sampling point in the third 3D point cloud model Q1. If there are multiple similar points corresponding to the k-th sampling point in the third 3D point cloud model Q1, then any one of the similar points corresponding to the k-th sampling point in the third 3D point cloud model Q1 can be determined as the associated point corresponding to the k-th sampling point in the third 3D point cloud model Q1.

[0097] After determining the associated point corresponding to the k-th sampling point in the third 3D point cloud model Q1, the rigid transformation matrix between the k-th sampling point and its associated point in the third 3D point cloud model Q1 can be calculated. Then, by solving the distance error sum function, the matching degree between the k-th sampling point and its associated point in the third 3D point cloud model Q1 can be obtained. A higher matching degree between the k-th sampling point and its associated point in the third 3D point cloud model Q1 indicates a higher degree of matching.

[0098] The distance error function can be represented using the Huber penalty function, denoted as . in:

[0099] Where, m k Indicates a predefined threshold; l k This represents the distance difference between the k-th sampling point in the third 3D point cloud model Q1 and the diameter of the associated point corresponding to the k-th sampling point in the third 3D point cloud model Q1.

[0100] By coarsely registering the point clouds of the third 3D point cloud model Q1 and the first 3D point cloud model S, a set of optimal transformations T3 that minimizes the aforementioned Huber penalty function can be found. The optimal transformation T3 can be obtained using a gradient-based optimization algorithm.

[0101] Transforming the third 3D point cloud model Q1 according to the optimal transformation T3 yields the fourth 3D point cloud model Q2.

[0102] The iterative nearest point algorithm and singular value decomposition were used to perform fine registration of the fourth 3D point cloud model and the first 3D point cloud model to obtain the 3D bone model of the affected bone.

[0103] Specifically, after obtaining the fourth 3D point cloud model Q2, the Iterative Closest Point (ICP) algorithm can be used to perform fine point cloud registration between the fourth 3D point cloud model Q2 and the first 3D point cloud model S. The specific steps include: using an initial transformation T = [R,t] to transform all points in the fourth 3D point cloud model Q2 to the first 3D point cloud model S, and defining the following energy function:

[0104] Where func represents the energy function value; s iThe transformation parameter q represents the closest point in point cloud S after the transformation of the i-th point in the fourth 3D point cloud model Q2; R represents the first transformation parameter; t represents the second transformation parameter; q i This represents the i-th point in the fourth 3D point cloud model Q2.

[0105] It should be noted that the optimization objective of the energy function in this embodiment is to minimize the energy function value func.

[0106] The Singular Value Decomposition (SVD) algorithm is used to obtain the optimal solutions for the first transformation parameter R and the second transformation parameter t, resulting in transformation T4. In this embodiment, the optimal solutions for the first transformation parameter R and the second transformation parameter t are the values ​​of the first transformation parameter R and the second transformation parameter t that minimize the value of func. The specific method for obtaining transformation T4 based on the optimal solutions for the first transformation parameter R and the second transformation parameter t is as follows: the top-left 3x3 matrix is ​​transformed to represent the optimal solution for the first transformation parameter R, the right-hand 3x1 matrix to represent the optimal solution for the second transformation parameter t, and the bottom row is padded with 0, 0, 0, 1 to obtain transformation T4.

[0107] Transform the fourth 3D point cloud model Q2 according to the optimal transformation T4 to obtain the 3D bone model of the affected bone.

[0108] Transformation from the second 3D point cloud model D to the first 3D point cloud model S

[0109] In this embodiment, after constructing a first 3D point cloud model based on a first image and a second 3D point cloud model based on a second image, the centroids of the first and second 3D point cloud models are extracted. Then, the second 3D point cloud model is mirrored along the horizontal direction based on these centroids to obtain a third 3D point cloud model. This achieves symmetrical processing of the second 3D point cloud model. A consistent initial registration algorithm is used to perform coarse point cloud registration between the first and third 3D point cloud models to obtain a fourth 3D point cloud model. This quickly establishes the initial correspondence between the first and third 3D point cloud models, helping to narrow the calculation range for subsequent fine registration and improve registration efficiency. By iteratively optimizing the transformation relationship between the first and fourth 3D point cloud models, the error between them can be gradually reduced, ultimately achieving accurate registration between the first and second 3D point cloud models and obtaining a 3D bone model of the affected bone. This provides a more accurate data foundation for subsequent surgical planning and intraoperative surgical navigation for the affected bone.

[0110] Step 102: Determine multiple bony landmarks on the three-dimensional bone model. Based on the three-dimensional bone model and the bony landmarks on the three-dimensional bone model, obtain the surgical parameters corresponding to the affected bone. The surgical parameters include at least one of the following: osteotomy location, osteotomy size, prosthesis model, prosthesis size, and prosthesis installation location.

[0111] Specifically, after obtaining the three-dimensional bone model of the affected bone, multiple bony landmarks can be determined on the three-dimensional bone model of the affected bone. Among them, bony landmarks refer to bones in certain parts of the human body that often form obvious bulges or depressions, and are often used clinically for localization and other applications, thus becoming bony landmarks; in the embodiments of this application, bony landmarks can be determined on the three-dimensional bone model of the affected bone using an interactive picking method.

[0112] As an optional embodiment, multiple bony landmarks are determined on the three-dimensional bone model, including: determining several bony landmarks at the proximal end of the three-dimensional bone model and several bony landmarks at the distal end of the three-dimensional bone model, wherein the proximal end is the end closer to the incision and the distal end is the end farther from the incision.

[0113] It should be noted that, in the embodiments of this application, multiple bony landmarks on the three-dimensional bone model of the affected bone are evenly distributed on the end of the affected bone near the incision and the end away from the incision.

[0114] It should be noted that an incision, in orthopedic surgery, refers to the skin and tissue structures cut open to expose the surgical site and perform surgical procedures. The specific location of the incision can be determined based on the first imaging.

[0115] Based on the three-dimensional bone model of the affected bone and the bony landmarks on the model, surgical parameters corresponding to the affected bone can be obtained. For example, based on the three-dimensional bone model of the affected bone and the bony landmarks on the model, the prosthesis model can be automatically selected, and the initial prosthesis planning posture can be set according to the patient's personalized characteristics. Based on the three-dimensional bone model of the affected bone and the bony landmarks on the model, the offset between the three-dimensional bone model of the affected bone and the first three-dimensional point cloud model can also be obtained, and the prosthesis planning can be adjusted according to the offset.

[0116] Specifically, the steps for obtaining the initial prosthesis planning based on the three-dimensional bone model of the affected bone and the bony landmarks on the three-dimensional bone model can include: First, calculating parameters such as bone surface width, height, center position of the bone surface, anteversion angle, supination angle, and neck-shaft angle based on the coordinates of the bony landmarks; Second, using the bone surface width and height, finding the prosthesis with the closest size in the prosthesis library according to the matching principle as the initial prosthesis; Third, placing the prosthesis at the calculated center position of the bone surface; Finally, rotating the prosthesis in space according to the different requirements of each site, such as anteversion angle and supination angle, to obtain the initial planned pose.

[0117] It should be noted that when the orthopedic surgery for the affected bone is a shoulder replacement surgery, based on the three-dimensional bone model of the affected bone and the bony landmarks on the three-dimensional bone model, three different surgical plans can be obtained: normal shoulder, partial shoulder, and reverse shoulder. It can also provide the offset of the humerus on the surgical side relative to the preoperative side and relative to the contralateral side, and adjust the prosthesis planning according to the offset.

[0118] Step 103: Based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, register the affected bone and the three-dimensional bone model to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0119] Specifically, after obtaining a three-dimensional bone model of the affected bone and determining multiple bony landmarks on the three-dimensional bone model of the affected bone, the three-dimensional bone model of the affected bone and the bony landmarks on the three-dimensional bone model can be displayed in a human-computer interaction device.

[0120] During orthopedic surgery on a affected bone, doctors can use probes and other devices to determine the bony landmarks on the affected bone based on the three-dimensional bone model of the affected bone, the bony landmarks on the three-dimensional bone model, and the prompts displayed on the human-computer interaction device. This establishes a correspondence between the bony landmarks on the three-dimensional bone model of the affected bone and the bony landmarks on the affected bone.

[0121] For example, in cases where bony landmarks include the medial epicondyle and lateral epicondyle of the distal humerus, a probe can be used to locate these bony landmarks on the affected bone without puncturing the patient's skin.

[0122] After establishing the correspondence between the bony landmarks on the three-dimensional bone model of the affected bone and the bony landmarks on the affected bone, the affected bone and the three-dimensional bone model of the affected bone can be registered based on the correspondence between the bony landmarks on the three-dimensional bone model of the affected bone and the bony landmarks on the affected bone, and the mapping relationship between the three-dimensional bone model and / or the first image of the affected bone can be established.

[0123] As an optional embodiment, based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, the affected bone and the three-dimensional bone model are registered to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image, including: establishing a first registration coordinate system corresponding to the affected bone based on the positional relationship between each bony landmark on the affected bone, and establishing a second registration coordinate system corresponding to the three-dimensional bone model based on the positional relationship between each bony landmark on the three-dimensional bone model.

[0124] It should be noted that the relevant techniques use a point-pair registration algorithm to register two 3D models, that is, to calculate the registration matrix based on 4-6 corresponding points on the two 3D models. However, for the registration of the affected bone and its 3D bone model, the determination of bony landmarks on the affected bone is easily affected by factors such as the patient's soft tissue and cartilage, resulting in inaccurate determination of the bony landmarks. Furthermore, the limited surgical area that can be operated on the affected bone leads to a relatively large error in the registration of the affected bone and its 3D bone model based on the aforementioned registration algorithm.

[0125] In response, this application provides an improved registration method. The improved registration method in this application establishes a registration coordinate system and performs two registrations on the affected bone and its three-dimensional bone model.

[0126] Specifically, in this embodiment of the application, a first registration coordinate system corresponding to the affected bone can be established through mathematical methods based on the positional relationship between bony landmarks on the affected bone, and a second registration coordinate system corresponding to the three-dimensional bone model can be established through mathematical methods based on the positional relationship between bony landmarks on the three-dimensional bone model.

[0127] It is understood that the methods for establishing the first registration coordinate system corresponding to the affected bone and the second registration coordinate system corresponding to the three-dimensional bone model are the same in the embodiments of this application.

[0128] As an optional embodiment, each bony landmark on the three-dimensional bone model includes two bony landmarks located on the medial and lateral sides of the proximal end of the three-dimensional bone model, and two bony landmarks located on the medial and lateral sides of the distal end of the three-dimensional bone model, respectively; each bony landmark on the affected bone includes two bony landmarks located on the medial and lateral sides of the proximal end of the affected bone, and two bony landmarks located on the medial and lateral sides of the distal end of the affected bone, respectively.

[0129] Based on the positional relationship between various bony landmarks on the affected bone, a first registration coordinate system corresponding to the affected bone is established. Based on the positional relationship between various bony landmarks on the three-dimensional bone model, a second registration coordinate system corresponding to the three-dimensional bone model is established. This includes: taking the direction from the bony landmark located on the medial side of the proximal end of the affected bone to the bony landmark located on the lateral side of the proximal end of the affected bone as the X-axis direction of the first registration coordinate system; taking the midpoint of the line connecting the two bony landmarks located on the medial and lateral sides of the distal end of the affected bone as the origin of the first registration coordinate system; and taking the upward direction passing through the origin of the first registration coordinate system and perpendicular to the plane containing the two bony landmarks located on the medial and lateral sides of the proximal end of the affected bone as the Y-axis of the first registration coordinate system.

[0130] The X-axis of the second registration coordinate system is defined as the direction from the bony landmark located on the medial side of the proximal end of the three-dimensional bone model to the bony landmark located on the lateral side of the proximal end of the three-dimensional bone model. The origin of the second registration coordinate system is defined as the midpoint of the line connecting the two bony landmarks located on the medial and lateral sides of the distal end of the three-dimensional bone model. The Y-axis of the second registration coordinate system is defined as the upward direction passing through the origin of the second registration coordinate system and perpendicular to the plane containing the two bony landmarks located on the medial and lateral sides of the proximal end of the three-dimensional bone model.

[0131] Specifically, taking the humerus as the affected bone, the bony landmarks on the affected bone include bony landmark 1 and bony landmark 2 located on both sides of the proximal end of the humerus, as well as bony landmark A located on the medial epicondyle of the humerus and bony landmark B located on the lateral epicondyle of the humerus.

[0132] The bony landmarks on the three-dimensional bone model of the affected bone include bony landmarks 1 and 2 located on both sides of the proximal end of the three-dimensional bone model of the humerus, as well as bony landmark A located on the medial epicondyle of the three-dimensional bone model of the humerus and bony landmark B located on the lateral epicondyle of the three-dimensional bone model of the humerus.

[0133] The vector pointing from bony landmark A located on the medial epicondyle of the humerus to bony landmark B located on the lateral epicondyle of the humerus The X-axis of the first registration coordinate system is defined by the midpoint of the line connecting bony landmark 1 and bony landmark 2 located on both sides of the proximal end of the humerus. The plane AOB is defined by the origin O of the first registration coordinate system and the bony landmark A located on the medial epicondyle of the humerus pointing to the bony landmark B located on the lateral epicondyle of the humerus. The direction that passes through the origin O of the first registration coordinate system and is perpendicular to the plane AOB upward is defined as the Y-axis of the first registration coordinate system. Thus, the first registration coordinate system can be obtained.

[0134] Similarly, the vector pointing from bony landmark A located on the inner epicondyle of the humerus in a three-dimensional bone model to bony landmark B located on the lateral epicondyle of the humerus is... The X-axis of the second registration coordinate system is defined by the midpoint of the line connecting bony landmark 1 and bony landmark 2 on both proximal sides of the three-dimensional bone model of the humerus. The plane AOB is defined by the origin O of the second registration coordinate system and the bony landmark A on the medial epicondyle of the three-dimensional bone model of the humerus pointing to the bony landmark B on the lateral epicondyle of the humerus. The direction that passes through the origin O of the second registration coordinate system and is perpendicular to the plane AOB upward is defined as the Y-axis of the second registration coordinate system. Thus, the second registration coordinate system can be obtained.

[0135] Establish the representation matrix of the first registration coordinate system and the representation matrix of the second registration coordinate system, and calculate the transformation matrix between the representation matrices of the first registration coordinate system and the second registration coordinate system as the target transformation matrix.

[0136] Specifically, the representation matrix O of the first registration coordinate system is established using mathematical methods. img The representation matrix O of the second registration coordinate system patient Then, the representation matrix O of the first registration coordinate system can be calculated. img The representation matrix O of the second registration coordinate system patient The transformation matrix between them is used as the target transformation matrix T. p2i-coarse The specific calculation formula is as follows:

[0137] Based on the target transformation matrix, spatial transformation is performed on each bony landmark on the affected bone to obtain the first spatial point set. Based on each bony landmark on the affected bone, the first transformation matrix is ​​calculated using the normal distribution transformation algorithm.

[0138] It should be noted that the representation matrix O of the first registration coordinate system img The 3x3 matrix in the upper left corner represents the direction vectors of the X-axis, Y-axis, and Z-axis in the first registration coordinate system. The 3x1 matrix to the right of the above 3x3 matrix represents the origin coordinates of the first registration coordinate system. The 1x3 matrix below the above 3x3 and 3x1 matrices represents {0, 0, 0, 1}.

[0139] The representation matrix O of the second registration coordinate system patient The 3x3 matrix in the upper left corner represents the direction vectors of the X-axis, Y-axis, and Z-axis in the second registration coordinate system. The 3x1 matrix to the right of the above 3x3 matrix represents the origin coordinates of the second registration coordinate system. The 1x3 matrix below the above 3x3 and 3x1 matrices represents {0, 0, 0, 1}.

[0140] Specifically, in the embodiments of this application, P can be used to represent the bony landmark point cloud on the affected bone, and Q can be used to represent the bony landmark point cloud on the three-dimensional bone model of the affected bone.

[0141] Based on the target change matrix T p2i-coarse By performing a spatial transformation on the bony landmark point cloud P on the affected bone, the bony landmark point cloud P on the affected bone can be transformed to the second registration coordinate system to obtain the first spatial point set P1.

[0142] Based on the bony landmark point cloud Q on the three-dimensional bone model of the affected bone, the first transformation matrix T can be calculated using the Normal Distribution Transform (NDT) algorithm. 1The specific calculation steps include: dividing the bony landmark point cloud Q on the three-dimensional bone model into multiple grids, and calculating the mean value in each grid. The calculation formula is as follows:

[0143] Where μ represents the mean value in the grid; n represents the number of bony landmarks in the grid; b i This represents the position information of the i-th bony landmark in the grid.

[0144] The covariance of each grid cell is calculated using the following formula:

[0145] in,(*) T This indicates transpose.

[0146] Construct a normal distribution N(μ, Σ), whose probability density function p(b) i This can be represented as:

[0147] Using the initial transformation T = [R,t] to transform all points in the first spatial point set P1, the following evaluation function score(p) is established:

[0148] Among them, y i μ represents the i-th point in the first spatial point set P1; i Indicates y i The mean of the mesh containing the bony landmark point cloud Q mapped onto the 3D bone model after the initial transformation T = [R,t]; T(y i ) represents the i-th point y in the first spatial point set P1. i The value after transformation according to the initial transformation T = [R, t].

[0149] The above evaluation function is optimized using Newton's optimization method, that is, to find the transformation parameter T = [R,t] that makes the value of the evaluation function score(p) optimal. The key step in the optimization is to solve for the Jacobian matrix and the Hessian matrix.

[0150] Repeat the above steps to optimize the evaluation function until the convergence condition is met, and obtain the first transformation matrix T. 1 .

[0151] A second set of spatial points is obtained by performing a spatial transformation on the first set of spatial points based on the first transformation matrix.

[0152] Specifically, obtain the first transformation matrix T. 1 Then, based on the first transformation matrix T 1 By performing a spatial transformation on the first spatial point set P1, we can obtain the second spatial point set P2.

[0153] The iterative nearest point algorithm and singular value decomposition are used to register the second spatial point set and each bony landmark on the three-dimensional bone model to obtain the first registration matrix that describes the mapping relationship between the affected bone and the three-dimensional bone model.

[0154] Specifically, after obtaining the second spatial point set P2, the iterative nearest point algorithm can be used to perform fine point cloud registration between the second spatial point set P2 and the bony landmark point cloud Q on the three-dimensional bone model of the affected bone. The specific steps include: using T = [R, t] to transform all points in the second spatial point set P2 to the bony landmark point cloud Q on the three-dimensional bone model of the affected bone, and defining the following energy function:

[0155] Where func′ represents the energy function value; w i The i-th point in the second spatial point set P2 is the closest point after transformation into the bony landmark point cloud Q; R represents the first transformation parameter; t represents the second transformation parameter; l i Let represent the i-th point in the second spatial point set P2.

[0156] It should be noted that the optimization objective of the energy function in this embodiment is to minimize the energy function value func′.

[0157] The optimal solutions for the first transformation parameter R and the second transformation parameter t are obtained using the Singular Value Decomposition (SVD) algorithm, thus yielding the second transformation matrix T. 2 In this embodiment, the optimal solution for the first transformation parameter R and the second transformation parameter t is the value of the first transformation parameter R and the value of the second transformation parameter t when the value of func′ is minimized. Based on the optimal solution for the first transformation parameter R and the second transformation parameter t, the second transformation matrix T is obtained. 2 The specific method is as follows: transform the top left 3x3 matrix to obtain the optimal solution for the first transformation parameter R, the right 3x1 matrix to obtain the optimal solution for the second transformation parameter t, and fill the bottom row with 0, 0, 0, 1 to obtain the second transformation matrix T. 2 .

[0158] The first registration matrix T is used to describe the mapping relationship between the affected bone and the three-dimensional bone model. p2i-fine =T 1 *T 2 .

[0159] Based on the mapping relationship between the three-dimensional bone model and the first image, and the first registration matrix, a second registration matrix is ​​obtained to describe the mapping relationship between the affected bone and the first image.

[0160] Specifically, obtain the first registration matrix T. p2i-fineSubsequently, based on the mapping relationship between the three-dimensional bone model of the affected bone and the first image, and the first registration matrix T, the model can be further refined. p2i-fine A second registration matrix is ​​obtained through numerical calculation to describe the mapping relationship between the affected bone and the first image.

[0161] This application embodiment establishes a first registration coordinate system corresponding to the affected bone based on the positional relationships between various bony landmarks on the affected bone, and a second registration coordinate system corresponding to the three-dimensional bone model based on the positional relationships between various bony landmarks on the three-dimensional bone model. Then, it establishes representation matrices for the first and second registration coordinate systems, calculates the transformation matrix between the representation matrices of the first and second registration coordinate systems as the target transformation matrix, performs spatial transformation on the bony landmarks on the affected bone based on the target transformation matrix, obtains a first spatial point set, and calculates the first transformation matrix based on the bony landmarks on the affected bone using a normal distribution transformation algorithm. Finally, it performs spatial transformation on the first spatial point set based on the first transformation matrix. A second spatial point set is obtained through inter-point transformation. The iterative nearest point algorithm and singular value decomposition are used to register the second spatial point set with each bony landmark on the three-dimensional bone model, obtaining the first registration matrix to describe the mapping relationship between the affected bone and the three-dimensional bone model. By establishing the registration coordinate system corresponding to the affected bone and the three-dimensional bone model and calculating the transformation matrix between them, the spatial relationship between the affected bone and the three-dimensional bone model can be described more accurately. This overcomes the limitations of traditional point-pair-based registration algorithms and reduces the registration error caused by inaccurate bony landmarks on the affected bone or limited surgical area. Combining the normal distribution transformation algorithm and the iterative nearest point algorithm for spatial transformation and registration significantly improves the registration accuracy and robustness between the affected bone and the three-dimensional bone model.

[0162] Step 104: Perform surgical navigation based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0163] Specifically, after obtaining the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the image of the affected bone, the orthopedic surgical operation of the affected bone can be completed using a surgical navigation device based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the image of the affected bone.

[0164] When a doctor performs orthopedic surgery on a bone using a handheld surgical navigation device, the human-computer interaction device can display real-time images of the bone during the operation, as well as the spatial position and pose of the surgical navigation device. It can also calculate the distance, angle, and other deviations between the surgical navigation device and any position on the bone, providing visual feedback.

[0165] When bone grinding is required, to enhance visual feedback during the grinding process, the 3D bone model of the affected bone can be colored according to the corresponding surgical parameters, with red, white, and green representing over-grinded, appropriately ground, and under-grinded areas, respectively. During the grinding process, the coloring information in the 3D bone model can be updated in real time based on the actual grinding status and the position of the grinding tool, thus reflecting the grinding progress and ensuring the grinding of the affected area is completed.

[0166] When grinding is required to implant central screws, fixation screws, or non-fixation screws into the affected bone, the central screws, fixation screws, and non-fixation screws can be tracked and displayed in real time. Furthermore, by calculating the distance of the central screw through the three-dimensional bone model of the affected bone, the direction of the central screw can be adjusted to ensure that the central screw does not protrude from the bone surface. At the same time, the direction of the fixation screws and non-fixation screws can be adjusted according to the patient's bony physiological structure, thereby achieving the most stable base fixation effect.

[0167] When a base needs to be installed on the affected bone, the real-time position and orientation of the grinding tool and the installation tool can be obtained through the tracer on the affected bone side and the tracer on the surgical navigation device, in order to calculate the distance and angle deviation of the grinding reamer and the installation tool as well as the depth from the target position.

[0168] When bone reconstruction is required, different types of osteotomy guides can be used, including standard guides and personalized guides. During osteotomy, the error between the guide plane and the planned osteotomy plane is calculated and displayed in real time through the humeral tracer and the tracer installed on the guide.

[0169] During the implantation of the prosthesis for the affected bone, the position of the affected bone and the prosthesis can be obtained in real time by the tracer installed on the prosthesis and the tracer on the affected bone, and compared with the planned position. The deviation between the axis of the affected bone and the prosthesis and the anteversion angle and the plan can be provided in real time.

[0170] After the prosthesis is installed, in reverse shoulder replacement, a probe can be used to tap the liner and further confirm whether the liner is installed in place based on the position and posture of the humeral stem. In normal shoulder and hemi-shoulder replacement, the tracer on the ball head installer can be used to determine whether the ball head on the humeral stem is installed in place.

[0171] This application's embodiments generate a three-dimensional bone model of the affected bone by combining preoperative medical images of the affected bone with medical images of the corresponding healthy bone. This model can more accurately reflect the healthy morphology of the affected bone even when bone defects and / or morphological abnormalities exist. Furthermore, surgical parameters corresponding to the affected bone can be obtained based on the three-dimensional bone model, making preoperative surgical planning more objective and quantitative. During orthopedic surgery, by registering bony landmarks on the three-dimensional bone model with actual bony landmarks on the affected bone, a precise mapping relationship can be established between the affected bone and the three-dimensional bone model. This enables accurate spatial positioning of the affected bone during surgery. Based on the surgical parameters corresponding to the affected bone and the mapping relationship with the three-dimensional bone model, the condition of the affected bone can be displayed in real time during surgery. This allows for more accurate spatial positioning of the affected bone during orthopedic surgery, providing doctors with intuitive visual guidance and helping them make more informed decisions during surgery. This reduces surgical complications and postoperative recovery time, significantly improving the accuracy and reliability of orthopedic surgery, effectively reducing surgical risks, and achieving more stable surgical outcomes.

[0172] Figure 2 is a schematic diagram of the orthopedic surgical navigation device provided in this application. The orthopedic surgical navigation device provided in this application will be described below with reference to Figure 2. The orthopedic surgical navigation device described below can be referred to in correspondence with the orthopedic surgical navigation method provided in this application described above. As shown in Figure 2, the device includes: a data acquisition module 201, a preoperative planning module 202, an intraoperative registration module 203, and an intraoperative execution module 204.

[0173] The data acquisition module 201 is used to generate a three-dimensional bone model of the affected bone based on the first image and the second image. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human skeletons symmetrically distributed with the spine as the midline.

[0174] The preoperative planning module 202 is used to determine multiple bony landmarks on the three-dimensional bone model. Based on the three-dimensional bone model and the bony landmarks on the three-dimensional bone model, the surgical parameters corresponding to the affected bone are obtained. The surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis type, prosthesis size and prosthesis installation position.

[0175] The intraoperative registration module 203 is used to register the affected bone and the three-dimensional bone model based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, and to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0176] The intraoperative execution module 204 is used for surgical navigation based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0177] Specifically, the data acquisition module 201, the preoperative planning module 202, the intraoperative registration module 203, and the intraoperative execution module 204 are electrically connected.

[0178] The orthopedic surgical navigation device in this embodiment generates a three-dimensional bone model of the affected bone by combining preoperative medical images of the affected bone and medical images of the corresponding healthy bone. This model can more accurately reflect the healthy morphology of the affected bone even when bone defects and / or morphological abnormalities exist. Furthermore, it can obtain the corresponding surgical parameters based on the three-dimensional bone model, making preoperative surgical planning more objective and quantitative. During orthopedic surgery, by registering bony landmarks on the three-dimensional bone model with actual bony landmarks on the affected bone, a precise mapping relationship can be established between the affected bone and the three-dimensional bone model. This enables accurate spatial positioning of the affected bone during surgery. Based on the corresponding surgical parameters and the mapping relationship with the three-dimensional bone model, the condition of the affected bone can be displayed in real time during surgery. This allows for more accurate spatial positioning of the affected bone during orthopedic surgery, providing doctors with intuitive visual guidance and helping them make more informed decisions during surgery. This reduces surgical complications and postoperative recovery time, significantly improving the accuracy and reliability of orthopedic surgery, effectively reducing surgical risks, and achieving more stable surgical outcomes.

[0179] Figure 3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Figure 3, the electronic device 1100 may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute an orthopedic surgical navigation method. This method includes: generating a three-dimensional bone model of the affected bone based on a first image and a second image. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the corresponding healthy bone are a pair of human skeletons symmetrically distributed around the spine. Multiple bony landmarks are determined on the three-dimensional bone model. Based on the three-dimensional bone model and the bony landmarks on the three-dimensional bone model, surgical parameters corresponding to the affected bone are obtained. The surgical parameters include at least one of osteotomy location, osteotomy size, prosthesis type, prosthesis size, and prosthesis installation location. Based on the correspondence between the bony landmarks on the three-dimensional bone model and the bony landmarks on the affected bone, the affected bone and the three-dimensional bone model are registered to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image. Surgical navigation is performed based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0180] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0181] Figure 4 is one of the structural schematic diagrams of the orthopedic surgical navigation system provided in this application. Figure 5 is another structural schematic diagram of the orthopedic surgical navigation system provided in this application. As shown in Figures 4 and 5, the orthopedic surgical navigation system 1000 includes: the electronic device 1100 as described above and the surgical navigation device 2000; the electronic device is electrically connected to the surgical navigation device.

[0182] As an optional embodiment, the orthopedic surgical navigation system also includes a human-computer interaction device 1200.

[0183] The human-computer interaction device 1200 is communicatively connected to the electronic device 1100.

[0184] The surgical navigation device 2000 includes a navigation camera 2100, a patient tracker 2200, a probe 2300, and a navigation tool 2400.

[0185] Specifically, the electronic device can communicate with the surgical navigation device to obtain the actual spatial location of the affected bone and surgical tools.

[0186] The electronic device 1100 is communicatively connected to the human-computer interaction device 1200 and the navigation camera 2100, respectively, receives information transmitted by the human-computer interaction device 1200 and the navigation camera 2100, and sends relevant information or instructions to the human-computer interaction device 1200 and the navigation camera 2100.

[0187] The navigation camera 2100 receives signals from the patient tracker 2200, probe 2300, and navigation tool 2400 to determine the relative spatial position of the surgical navigation device and the affected bone under the same spatial coordinates. With the spatial position of the affected bone and the surgical navigation device determined, the navigation camera 2100 receives signals from the probe 2300 to complete the acquisition of bony landmarks on the affected bone.

[0188] The orthopedic surgical navigation system provided in this application includes an electronic device, a surgical navigation device, and a human-computer interaction device for executing the orthopedic surgical navigation method provided in this application. It can improve the accuracy, stability, and safety of surgery, while reducing surgical time, lowering surgical risks, and improving surgical efficiency. Based on preoperative medical images of the affected bone and medical images of the corresponding healthy bone, it can complete a personalized surgical plan for the affected bone before surgery. It can use data from the healthy side to map and generate data from the affected side to handle cases of fractures or severe bone defects. It can also provide the offset of the humerus on the surgical side relative to the preoperative side and relative to the contralateral side, and adjust the prosthesis planning according to the offset. It uses an infrared camera for intraoperative navigation, providing high-precision real-time navigation while reducing the impact of the environment on the navigation camera. Real-time tool tracking and visual feedback can effectively improve the accuracy and efficiency of prosthesis implantation.

[0189] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the orthopedic surgical navigation method provided by the above methods. The method includes: generating a three-dimensional bone model of the affected bone based on a first image and a second image. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the corresponding healthy bone are a pair of human skeletons symmetrically distributed with the spine as the midline. Multiple bony landmarks are identified on the bone model. Based on the three-dimensional bone model and the bony landmarks on the three-dimensional bone model, surgical parameters corresponding to the affected bone are obtained. The surgical parameters include at least one of osteotomy location, osteotomy size, prosthesis type, prosthesis size, and prosthesis installation position. Based on the correspondence between the bony landmarks on the three-dimensional bone model and the bony landmarks on the affected bone, the affected bone and the three-dimensional bone model are registered to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image. Surgical navigation is performed based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0190] Furthermore, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the orthopedic surgical navigation method provided by the above methods. The method includes: generating a three-dimensional bone model of the affected bone based on a first image and a second image, wherein the first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone, wherein the affected bone and the corresponding healthy bone are a pair of human bones symmetrically distributed with the spine as the midline; determining multiple bony landmarks on the three-dimensional bone model; obtaining surgical parameters corresponding to the affected bone based on the three-dimensional bone model and the bony landmarks on the three-dimensional bone model, wherein the surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis type, prosthesis size, and prosthesis installation position; registering the affected bone and the three-dimensional bone model based on the correspondence between the bony landmarks on the three-dimensional bone model and the bony landmarks on the affected bone, and establishing a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image; and performing surgical navigation based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

[0191] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0192] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for orthopedic surgical navigation, comprising: Based on the first image and the second image, a three-dimensional bone model of the affected bone is generated. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human skeletons symmetrically distributed with the spine as the midline. Multiple bony landmarks are determined on the three-dimensional bone model. Based on the three-dimensional bone model and each of the bony landmarks on the three-dimensional bone model, surgical parameters corresponding to the affected bone are obtained. The surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis model, prosthesis size, and prosthesis installation position. Based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, the affected bone and the three-dimensional bone model are registered to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image. Surgical navigation is performed based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

2. The orthopedic surgical navigation method of claim 1, wherein, The process of generating a three-dimensional bone model of the affected bone based on the first and second images includes: Based on the first image, a first three-dimensional point cloud model is constructed, and based on the second image, a second three-dimensional point cloud model is constructed. Extract the centroids of the first 3D point cloud model and the second 3D point cloud model. Based on the centroids of the first 3D point cloud model and the second 3D point cloud model, mirror the second 3D point cloud model along the horizontal direction to obtain the third 3D point cloud model. Based on the centroid of the first 3D point cloud model and the centroid of the third 3D point cloud model, align the first 3D point cloud model and the third 3D point cloud model. The feature descriptor of each point in the third three-dimensional point cloud model is obtained. Then, based on the feature descriptor of each point in the third three-dimensional point cloud model, the consistency initial registration algorithm is used to perform coarse point cloud registration between the third three-dimensional point cloud model and the first three-dimensional point cloud model to obtain the fourth three-dimensional point cloud model. The iterative nearest point algorithm and singular value decomposition are used to perform fine registration of the fourth three-dimensional point cloud model and the first three-dimensional point cloud model to obtain the three-dimensional bone model of the affected bone.

3. The orthopedic surgical navigation method according to claim 1, wherein, The process of registering the affected bone and the three-dimensional bone model based on the correspondence between each bony landmark on the three-dimensional bone model and each bony landmark on the affected bone, and establishing a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image, includes: Based on the positional relationship between the bony landmarks on the affected bone, a first registration coordinate system corresponding to the affected bone is established, and based on the positional relationship between the bony landmarks on the three-dimensional bone model, a second registration coordinate system corresponding to the three-dimensional bone model is established. Establish the representation matrix of the first registration coordinate system and the representation matrix of the second registration coordinate system, and calculate the transformation matrix between the representation matrix of the first registration coordinate system and the representation matrix of the second registration coordinate system as the target transformation matrix; Based on the target transformation matrix, spatial transformation is performed on each of the bony landmarks on the affected bone to obtain a first spatial point set. Based on each of the bony landmarks on the affected bone, a first transformation matrix is ​​calculated using a normal distribution transformation algorithm. Based on the first transformation matrix, the first spatial point set is spatially transformed to obtain the second spatial point set; The iterative nearest point algorithm and singular value decomposition are used to register the second spatial point set and each of the bony landmarks on the three-dimensional bone model to obtain a first registration matrix that describes the mapping relationship between the affected bone and the three-dimensional bone model. Based on the mapping relationship between the three-dimensional bone model and the first image, and the first registration matrix, a second registration matrix is ​​obtained to describe the mapping relationship between the affected bone and the first image.

4. The orthopedic surgical navigation method of claim 3, wherein, Each of the bony landmarks on the affected bone includes two bony landmarks located on the medial and lateral sides of the proximal end of the affected bone, and two bony landmarks located on the medial and lateral sides of the distal end of the affected bone, respectively. The step of establishing a first registration coordinate system corresponding to the affected bone based on the positional relationship between the bony landmarks on the affected bone includes: The X-axis of the first registration coordinate system is defined as the direction from the bony landmark located on the medial side of the proximal end of the affected bone to the bony landmark located on the lateral side of the proximal end of the affected bone. The origin of the first registration coordinate system is defined as the midpoint of the line connecting the two bony landmarks located on the medial and lateral sides of the distal end of the affected bone. The Y-axis of the first registration coordinate system is defined as the upward direction passing through the origin of the first registration coordinate system and perpendicular to the plane containing the two bony landmarks located on the medial and lateral sides of the proximal end of the affected bone. Each of the bony landmarks on the three-dimensional bone model includes two bony landmarks located on the medial and lateral sides of the proximal end of the three-dimensional bone model, and two bony landmarks located on the medial and lateral sides of the distal end of the three-dimensional bone model, respectively. Based on the positional relationships between the bony landmarks on the three-dimensional bone model, a second registration coordinate system corresponding to the three-dimensional bone model is established, including: The direction from the bony landmark located on the medial side of the proximal end of the three-dimensional bone model to the bony landmark located on the lateral side of the proximal end of the three-dimensional bone model is taken as the X-axis direction of the second registration coordinate system. The midpoint of the line connecting the two bony landmarks located on the medial and lateral sides of the distal end of the three-dimensional bone model is taken as the origin of the second registration coordinate system. The upward direction passing through the origin of the second registration coordinate system and perpendicular to the plane containing the two bony landmarks located on the medial and lateral sides of the proximal end of the three-dimensional bone model is taken as the Y-axis of the second registration coordinate system, thus obtaining the second registration coordinate system.

5. The orthopedic surgical navigation method of claim 2, wherein, The construction of the first 3D point cloud model based on the first image includes: If the image quality of the first image meets the preset standard, the first image is preprocessed to obtain the first image after data preprocessing. Based on the distribution of bone fragments in the affected bone, the first image after data preprocessing is segmented to obtain multiple sub-images corresponding to the first image, and each sub-image includes only one bone fragment of the affected bone. The sub-image of the largest bone block of the affected bone is identified as the target sub-image, and then a three-dimensional point cloud model of the largest bone block of the affected bone is constructed based on the target sub-image, which serves as the first three-dimensional point cloud model.

6. The orthopedic surgical navigation method of any one of claims 1 to 5, wherein, The determination of multiple bony landmarks on the three-dimensional bone model includes: Several bony landmarks are determined at the proximal end of the three-dimensional bone model and several bony landmarks are determined at the distal end of the three-dimensional bone model. The proximal end is the end closer to the incision, and the distal end is the end farther from the incision.

7. An orthopedic surgical navigation device, comprising: The data acquisition module is used to generate a three-dimensional bone model of the affected bone based on the first image and the second image. The first image includes a medical image of the affected bone before orthopedic surgery, and the second image includes a medical image of the healthy bone corresponding to the affected bone. The affected bone and the healthy bone corresponding to the affected bone are a pair of human skeletons symmetrically distributed with the spine as the midline. The preoperative planning module is used to determine multiple bony landmarks on the three-dimensional bone model, and to obtain surgical parameters corresponding to the affected bone based on the three-dimensional bone model and each of the bony landmarks on the three-dimensional bone model. The surgical parameters include at least one of osteotomy position, osteotomy size, prosthesis model, prosthesis size and prosthesis installation position. The intraoperative registration module is used to register the affected bone and the three-dimensional bone model based on the correspondence between each of the bony landmarks on the three-dimensional bone model and each of the bony landmarks on the affected bone, and to establish a mapping relationship between the affected bone and the three-dimensional bone model and / or the first image. The intraoperative execution module is used to perform surgical navigation based on the surgical parameters corresponding to the affected bone and the mapping relationship between the affected bone and the three-dimensional bone model and / or the first image.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the orthopedic surgical navigation method as described in any one of claims 1 to 6.

9. An orthopedic surgical navigation system, comprising: The electronic device and surgical navigation device as described in claim 8; The electronic device is communicatively connected to the surgical navigation device.

10. The orthopedic surgical navigation system of claim 9, further comprising: Human-computer interaction device; the human-computer interaction device is communicatively connected to the electronic device; The surgical navigation device includes a navigation camera, a patient tracker, a probe, and navigation tools.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the orthopedic surgical navigation method as described in any one of claims 1 to 6.

12. A computer program product comprising a computer program, wherein, When the computer program is executed by the processor, it implements the orthopedic surgical navigation method as described in any one of claims 1 to 6.

Images