Methods, systems, storage media, and computer products for guiding bone registration

Abstract

This application relates to a method, system, storage medium, and computer program product for guiding bone registration. The method includes: acquiring imaging data of bone tissue for a surgical subject using a visualization device; constructing a three-dimensional bone model of the bone tissue based on the imaging data; determining reference bone registration points based on the pixels in the imaging data; projecting the three-dimensional bone model and reference bone registration points onto the bone tissue using the visualization device, so that the three-dimensional bone model and reference bone registration points cover the surface of the bone tissue; acquiring the reference bone registration points on the bone tissue using an acquisition device to obtain the acquisition coordinates of the reference bone registration points in the acquisition device's coordinate system; and performing preoperative registration of the three-dimensional bone model and bone tissue using the acquisition coordinates of the reference bone registration points in the acquisition device's coordinate system and the coordinates of the registration points on the preoperative three-dimensional bone model. This method can improve the accuracy of acquiring bone registration points.

Description

Technical Field

[0001] This application relates to the field of robot-assisted surgical systems, and in particular to a method, system, storage medium, and computer product for guiding bone registration. Background Technology

[0002] With the development of robotics technology, robots are often used in surgical treatment techniques; for example, total knee replacement surgery robots. This type of robot consists of three parts: a robotic arm trolley, a navigation trolley, and a surgical trolley. The entire surgical planning requires bone registration to accurately guide the robotic arm to perform bone resection.

[0003] In clinical surgery, surgeons typically acquire bone registration points by observing the patient's surgical location and using a 3D model displayed on the navigation trolley screen. However, this method only acquires bone registration points in approximate locations, resulting in insufficient precision and ultimately inaccurate registration results. Therefore, a guided bone registration method is urgently needed. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, system, computer-readable storage medium, and computer program product for obtaining bone registration points that can improve the accuracy of bone registration point selection, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for guiding bone registration. The method includes:

[0006] Using visualization equipment, imaging data of bone tissue for the surgical subject is acquired, and a three-dimensional bone model of the bone tissue is constructed to determine reference bone registration points;

[0007] The visualization device is used to project the three-dimensional bone model and the reference bone registration point onto the bone tissue, so that the three-dimensional bone model and the reference bone registration point cover the surface of the bone tissue.

[0008] The reference bone registration point on the bone tissue is acquired using the acquisition device, and the acquisition coordinates of the reference bone registration point in the coordinate system of the acquisition device are obtained.

[0009] The coordinates of the reference bone registration point in the acquisition device coordinate system and the coordinates of the registration point on the preoperative three-dimensional bone model; and

[0010] Register the preoperative three-dimensional bone model and bone tissue, wherein the preoperative three-dimensional bone model is constructed from preoperative images acquired of the surgical subject.

[0011] In one embodiment, after constructing a three-dimensional bone model of the bone tissue based on imaging data, the method further includes:

[0012] The three-dimensional bone model was projected onto the bone tissue, and the projection effect was used to evaluate whether the three-dimensional bone model met the expected effect.

[0013] If the desired effect is not achieved, new imaging data is acquired, and a three-dimensional bone model of the bone tissue is constructed based on the new imaging data. The above process is repeated until the three-dimensional bone model created meets the desired effect.

[0014] In one embodiment, projecting a three-dimensional bone model onto bone tissue includes:

[0015] The projection position is determined based on the bone tissue positioning equipment;

[0016] Based on the projection position, the three-dimensional bone model is projected onto the bone tissue.

[0017] In one embodiment, determining the reference bone registration point includes:

[0018] The registration point is determined based on the pixels in the imaging data;

[0019] The color features of the points to be registered are compared with the color features of abnormal bone tissue conditions, and the points to be registered are screened based on the comparison results.

[0020] Among the remaining target registration sites after screening, reference bone registration sites are determined.

[0021] In one embodiment, determining reference bone registration points from the remaining target registration points after screening includes:

[0022] Based on the shape of the bone tissue, the bone tissue is divided into multiple regions;

[0023] Determine the target area to which each target registration point belongs, and select at least one target registration point from each target area so that the total number of selected target registration points reaches the preset number.

[0024] In one embodiment, the preoperative three-dimensional bone model and bone tissue are registered by acquiring coordinates and the coordinates of registration points on the preoperative three-dimensional bone model, including:

[0025] Determine the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates in the acquisition device coordinate system;

[0026] Based on the model coordinates of each reference bone registration point in the model coordinate system, each reference bone registration point is transformed from the model coordinate system to the auxiliary coordinate system to obtain the first auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system.

[0027] Based on the acquisition coordinates of each reference bone registration point in the acquisition device coordinate system, each reference bone registration point is transformed from the acquisition device coordinate system to the auxiliary coordinate system to obtain the second auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system;

[0028] The first auxiliary coordinates of each reference bone registration point are compared with the corresponding second auxiliary coordinates. All reference bone registration points are then filtered to obtain the bone registration points.

[0029] Preoperative registration of the three-dimensional bone model and bone tissue is performed by using the coordinates of the bone registration points and the coordinates of the registration points on the preoperative three-dimensional bone model.

[0030] In one embodiment, during surgery on bone tissue, the surgeon determines the real-time blind spot of the bone tissue based on the surgeon's real-time field of vision, and displays the corresponding area of ​​the real-time blind spot in the three-dimensional bone model in real time.

[0031] The model that displays the corresponding area of ​​the real-time blind spot in the 3D bone model is used as the reference 3D bone model.

[0032] Obtain the surgeon's operating instructions, adjust the posture of the reference 3D bone model according to the operating instructions, and display the reference 3D bone model according to the adjusted posture.

[0033] Secondly, this application also provides a system for guiding bone registration. The system includes:

[0034] A visualization device acquires imaging data of bone tissue for a surgical subject, constructs a three-dimensional bone model of the bone tissue based on the imaging data, and determines reference bone registration points;

[0035] The visualization device projects the three-dimensional bone model and the reference bone registration point onto the bone tissue, so that the three-dimensional bone model and the reference bone registration point cover the surface of the bone tissue;

[0036] The acquisition device acquires the reference bone registration point on the bone tissue to obtain the acquisition coordinates of the reference bone registration point in the acquisition device coordinate system;

[0037] The registration module is used to register the preoperative three-dimensional bone model and bone tissue using the acquired coordinates and the coordinates of the registration points on the preoperative three-dimensional bone model. The preoperative three-dimensional bone model is constructed from the preoperative acquired images of the surgical subject.

[0038] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the bootloader registration method as described above.

[0039] This application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the bootloader registration method as described above.

[0040] The aforementioned method, system, storage medium, and computer program product for guided bone registration acquire imaging data of bone tissue for the surgical subject using a visualization device; construct a three-dimensional bone model of the bone tissue based on the imaging data; determine reference bone registration points based on the pixels in the imaging data, and determine the model coordinates of the reference bone registration points in the model coordinate system of the three-dimensional bone model; project the three-dimensional bone model and reference bone registration points onto the bone tissue using a visualization device, so that the three-dimensional bone model and reference bone registration points cover the surface of the bone tissue; acquire the reference bone registration points on the three-dimensional bone model using an acquisition device, obtaining the acquisition coordinates of the reference bone registration points in the acquisition device coordinate system; and perform preoperative registration of the three-dimensional bone model and bone tissue using the acquisition coordinates of the reference bone registration points in the acquisition device coordinate system and the coordinates of the registration points on the preoperative three-dimensional bone model, where the preoperative three-dimensional bone model is constructed from preoperative images of the surgical subject. This method can improve the accuracy of acquiring bone registration points, thereby improving registration accuracy. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating a method for guiding bone registration in one embodiment;

[0042] Figure 2 This is a schematic diagram of an AR device scanning a knee joint in one embodiment;

[0043] Figure 3 This is a schematic diagram of a 3D structured light scanner scanning a knee joint in one embodiment;

[0044] Figure 4 This is a schematic diagram of a three-dimensional bone model and a reference bone registration point projected onto the surface of bone tissue in one embodiment;

[0045] Figure 5 This is a schematic diagram of a data acquisition device acquiring reference bone registration points in one embodiment;

[0046] Figure 6 This is a schematic diagram illustrating the model matching between an intraoperative 3D bone model and a preoperative 3D bone model in one embodiment.

[0047] Figure 7 This is a schematic diagram illustrating the formation of multiple target regions after dividing bone tissue into regions in one embodiment.

[0048] Figure 8 This is a schematic projection of a three-dimensional bone model in one embodiment;

[0049] Figure 9 This is a schematic projection of a three-dimensional bone model in one embodiment;

[0050] Figure 10 This is a schematic diagram of a three-dimensional bone model in one embodiment;

[0051] Figure 11 Another embodiment is a method for guiding bone registration;

[0052] Figure 12 This is a flowchart illustrating a method for guiding bone registration in one embodiment;

[0053] Figure 13 This is a schematic diagram illustrating a scenario for obtaining bone registration points in one embodiment;

[0054] Figure 14 This is a flowchart illustrating a method for guiding bone registration in one embodiment;

[0055] Figure 15 This is a schematic diagram illustrating a scenario for obtaining bone registration points in one embodiment;

[0056] Figure 16 This is a flowchart illustrating a method for guiding bone registration in one embodiment;

[0057] Figure 17 This is a structural block diagram of a system for guiding bone registration in one embodiment;

[0058] Figure 18 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It is understood that the terms "first," "second," etc., used in this application may be used to describe various technical terms, but unless otherwise specified, these technical terms are not limited to these terms. These terms are only used to distinguish one technical term from another. For example, without departing from the scope of this application, the third preset threshold and the fourth preset threshold may be the same or different.

[0061] In one embodiment, such as Figure 1As shown, a method for guiding bone registration is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0062] 101. Obtain imaging data of bone tissue for the surgical subject using visualization equipment;

[0063] 102. Based on the imaging data, construct a three-dimensional bone model of the bone tissue;

[0064] 103. Based on the pixels in the imaging data, determine the reference bone registration point and the model coordinates of the reference bone registration point in the model coordinate system of the three-dimensional bone model.

[0065] 104. Using a visualization device, project the three-dimensional bone model and reference bone registration points onto the bone tissue so that the three-dimensional bone model and reference bone registration points cover the surface of the bone tissue.

[0066] 105. Using the acquisition device, the reference bone registration point on the bone tissue is acquired, and the acquisition coordinates of the reference bone registration point in the coordinate system of the acquisition device are obtained.

[0067] 106. By referencing the acquisition coordinates of the bone registration point in the acquisition device coordinate system and the coordinates of the registration point on the preoperative three-dimensional bone model, the preoperative three-dimensional bone model and bone tissue are registered. The preoperative three-dimensional bone model is constructed from the preoperative acquired images of the surgical subject.

[0068] The visualization device can be an AR device, a combination of a 3D holographic projector and a 3D structured light scanner, or a combination of both. The AR device can be AR glasses. The bone tissue can include the knee joint, hip joint, and spine, etc.

[0069] The imaging data is obtained by scanning or capturing images using a visualization device. The imaging data refers to data that can be used to construct a three-dimensional model. The embodiments of this invention do not specifically limit the type of imaging data, including but not limited to: data in STL format, data in OBJ format, and data in FBX format.

[0070] A 3D bone model can be obtained by processing imaging data using an imaging data processing device integrated into the visualization device, or by processing imaging data using an imaging data processing device separate from the visualization device. When the 3D bone model is reconstructed by the processing device, the imaging data processing device will send the 3D bone model to the visualization device. The imaging data processing device can be a computer.

[0071] In one example, when the visualization device is an AR device, the AR device can directly scan the bone tissue of the surgical subject to obtain imaging data. The processing device reconstructs a three-dimensional bone model based on the imaging data and projects the reconstructed three-dimensional bone model onto the surface of the bone tissue through the AR device. Figure 2 This is a schematic diagram of an AR device scanning a knee joint, including AR device 1 scanning bone tissue 4 with tibial targets 2 and femoral targets 3 arranged thereon; wherein, bone tissue 4 includes at least the area where the femur and tibia connect, i.e., the knee joint, exposed in the surgical scene. The depth camera of AR device 1 scans the bones of the patient's knee joint and at least one of the tibial targets 2 and femoral targets 3, extracts the bone data of the knee joint, and uploads it to a processing device.

[0072] In one example, when the visualization device is a combination of a 3D holographic projector and a 3D structured light scanner, the 3D structured light scanner scans the bone tissue of the surgical subject to obtain imaging data of the bone tissue. This imaging data is then transmitted to an imaging data processing device. The imaging data processing device processes the imaging data to obtain a three-dimensional bone model, which is then transmitted to the 3D holographic projector. The 3D holographic projector projects the three-dimensional bone model onto the target projection area according to projection instructions. Figure 3 This is a schematic diagram of a 3D structured light scanner scanning a knee joint. The 3D structured light scanner 6 scans bone tissue 4 with tibial targets 2 and femoral targets 3 arranged on it. A display screen 5 shows a three-dimensional bone model. The bone tissue 4 includes at least the area where the femur and tibia connect, i.e., the knee joint, exposed in the surgical scene. Tibial targets 2 and femoral targets 3 are positioning devices, and their coordinate systems are the target coordinate system. During the operation, the surgical robot's robotic arm operates within the target coordinate system; that is, the surgical robot's robotic arm moves according to coordinates within the target coordinate system.

[0073] In one example, when the visualization device is a combination of an AR device and a 3D structured light scanner, the 3D structured light scanner scans the bone tissue of the surgical subject to obtain imaging data of the bone tissue, and then transmits the imaging data to the imaging data processing device. The imaging data processing device processes the imaging data to obtain a three-dimensional bone model, and then transmits the three-dimensional bone model to the AR device. The AR device projects the reconstructed three-dimensional bone model onto the surface of the bone tissue.

[0074] There are multiple reference bone registration points. These reference bone registration points can be pixels or feature points obtained by processing pixels. When the reference bone registration point is a pixel, it is selected from all pixels in the imaging data according to preset conditions. When the reference bone registration point is a feature point, during the acquisition of the reference registration point, the pixels are first divided into regions, ensuring that each region has at least one pixel. A feature point is determined based on the pixels in each region, resulting in multiple feature points. The reference bone registration point is then selected from all the feature points. The method for processing pixels to obtain feature points is not specifically limited in this embodiment, but includes, but is not limited to, averaging the coordinates of the pixels in each region and using the average as the coordinates of the corresponding feature point. For example, if the coordinates of the pixels in a certain region are A(1, 1, 1) and (1, 2, 1), then the coordinates of the corresponding feature point are (1, 1.5, 1).

[0075] The model coordinates in the model coordinate system where the 3D bone model is located refer to the coordinates of the 3D bone model in the coordinate system of the visualization device. After determining the reference bone registration points on the 3D bone model, it is necessary to determine the coordinates of each reference bone registration point in the coordinate system of the visualization device.

[0076] The acquisition device is used to acquire reference bone registration points. This embodiment of the invention does not specifically limit the acquisition device, but includes, but is not limited to, acquisition targets and probes. The acquisition method includes sequentially acquiring reference bone registration points and acquiring data according to different regions of the bone tissue. Furthermore, the coordinate system of the acquisition device refers to the coordinate system in which the acquisition device is located.

[0077] The reconstructed three-dimensional bone model and reference bone registration points will be superimposed on the actual bone tissue surface of the surgical subject, and reference bone registration points will be collected on the actual bone tissue using acquisition equipment. Figure 4 This is a schematic diagram of the visualization device being an AR device, showing how the AR device 1 projects the three-dimensional bone model 8 and the reference bone registration point 7 onto the surface of the bone tissue 4.

[0078] Collecting reference bone registration points on bone tissue refers to taking a sample by contacting or smearing the collection device at the location corresponding to the reference bone registration point on the bone tissue. Figure 5A schematic diagram of the acquisition device acquiring reference bone registration points is shown. The acquisition device 9 acquires reference bone registration points 7 on bone tissue 4 and projects them onto a three-dimensional bone model 8 on bone tissue 4. The coordinates of the reference bone registration points 7 acquired by the acquisition device 9 are the coordinates in the acquisition device coordinate system. The transformation matrix between the acquisition device coordinate system and the target coordinate system can be determined by the optical positioning instrument. The transformation matrix between the acquisition device coordinate system and the target coordinate system is used as the second transformation matrix. The coordinates of the reference bone registration points in the acquisition device coordinate system and the second transformation matrix are used to convert the coordinates in the acquisition device coordinate system into the coordinates in the target coordinate system.

[0079] It is worth mentioning that a three-dimensional bone model can be a model containing multiple bone tissues or a model containing only one bone tissue. For example, the knee joint is composed of the femur, patella, and tibia. Therefore, a three-dimensional bone model can be a three-dimensional bone model containing the femur, patella, and tibia, or it can be a three-dimensional bone model containing only one of the femur, patella, or tibia.

[0080] Preoperative image acquisition refers to the images obtained by acquiring images of the surgical subject before surgery. A preoperative three-dimensional bone model is constructed based on the preoperative images. The bone tissue corresponding to the intraoperative three-dimensional bone model should be the same as the bone tissue corresponding to the preoperative three-dimensional bone model. For example, if the preoperative three-dimensional bone model is reconstructed based on the preoperative images of the patella, then the intraoperative three-dimensional bone model should also be reconstructed based on the imaging data of the patella.

[0081] It is worth mentioning that the visualization device is equipped with a positioning device that can be identified by the optical locator. For example, if the visualization device is an AR device or a combination of an AR device and a 3D structured light scanner, the positioning device is mounted on the surface of the AR device and can be detected by the optical locator. If the visualization device is a combination of a 3D holographic projector and a 3D structured light scanner, the positioning device is mounted on the surface of the 3D holographic projector and can be detected by the optical locator. The optical locator can determine the location of the visualization device based on the positioning device on the visualization device, thereby determining the transformation relationship between the coordinate system of the optical locator and the coordinate system of the visualization device; where the coordinate system of the optical locator is the optical positioning coordinate system, and the coordinate system of the visualization device is the visualization device coordinate system.

[0082] The coordinates of the registration point on the preoperative 3D bone model refer to the coordinates of the registration point in the preoperative 3D bone model coordinate system. The preoperative 3D bone model coordinate system refers to the coordinate system in which the preoperative 3D bone model is located.

[0083] After obtaining the bone registration points, it is necessary to perform best-fit registration between the preoperative 3D bone model and the bone tissue to determine the registration matrix between the bone tissue and the intraoperative 3D bone model. Specifically, using an optical positioning device, the transformation matrix between the acquisition device coordinate system and the target coordinate system is determined. This transformation matrix is ​​used as the first transformation matrix. Based on this first transformation matrix, the acquisition coordinates of the reference bone registration points in the acquisition device coordinate system are converted to coordinates in the target coordinate system. Reference bone registration points on the bone tissue are then selected according to the screening criteria to obtain the final bone registration points. The intraoperative 3D bone model is matched with the preoperative 3D bone model to determine the registration point on the preoperative 3D bone model corresponding to the bone registration point on the bone tissue. The model coordinates of the preoperative bone registration point in the model coordinate system of the preoperative 3D bone model are used as the preoperative coordinates of the preoperative bone registration point. Based on the acquisition coordinates of the bone registration point in the acquisition device coordinate system and the preoperative coordinates of the preoperative bone registration point, the registration matrix between the preoperative 3D bone model and the bone tissue can be determined. The preoperative bone registration point refers to the registration point on the preoperative 3D bone model.

[0084] Figure 6 This diagram illustrates the model matching between an intraoperative 3D bone model with bone registration points and a preoperative 3D bone model, including a preoperative 3D bone model 10, an intraoperative 3D bone model 8, and bone registration points 11.

[0085] Specifically, the projection of the 3D bone model and the reference bone registration point onto the bone tissue can occur at the same time or at different times. For example, the 3D bone model can be projected onto the bone tissue surface first using a visualization device, and then the reference bone registration point can be projected onto the bone tissue surface; alternatively, both the 3D bone model and the reference bone registration point can be projected onto the bone tissue simultaneously. The ratio between the 3D bone model projected onto the bone tissue surface and the bone tissue is 1:1; therefore, the 3D bone model completely covers the bone tissue surface.

[0086] The method provided in this invention, through a visualization device, can obtain imaging data of the bone tissue of the surgical subject. This imaging data allows for the reconstruction of a three-dimensional bone model and the identification of reference bone registration points. By comparing the model coordinates of each reference bone registration point with the acquired coordinates in the acquisition device's coordinate system, the reference bone registration points can be filtered, thereby improving the accuracy of point selection. Furthermore, by comparing the locations of the reference bone registration points, the acquisition accuracy of bone registration points can be improved. Simultaneously, since preoperative planning of bone registration points is unnecessary, the steps involved in preoperative bone registration point planning are reduced.

[0087] In conjunction with the above embodiments, in one embodiment, after constructing a three-dimensional bone model of bone tissue based on imaging data, the method further includes:

[0088] The three-dimensional bone model was projected onto the bone tissue, and the projection effect was used to evaluate whether the three-dimensional bone model met the expected effect.

[0089] If the results do not meet expectations, acquire new imaging data and construct a three-dimensional bone model of the bone tissue based on the new imaging data. Repeat the above process until the created three-dimensional bone model meets the expected results.

[0090] The projection effect includes the accuracy of the 3D bone model and the degree of overlap between the 3D bone model and the actual bone tissue.

[0091] Specifically, after projecting the 3D bone model onto the bone tissue, the terminal determines whether the 3D model meets the expected effect based on the accuracy of the projected 3D bone model and the overlap between the 3D bone model and the actual bone tissue. If the accuracy of the projected 3D bone model reaches the preset accuracy and the overlap between the 3D bone model and the actual bone tissue reaches the preset overlap, then it meets the expected effect, and the reference bone registration point can be determined based on the current imaging data. If the accuracy of the projected 3D bone model does not reach the preset accuracy or the overlap between the 3D bone model and the actual bone tissue does not reach the preset overlap, then it does not meet the expected effect. In this case, the visualization device is controlled to reacquire the imaging data of the bone tissue of the surgical subject, and a 3D bone model of the bone tissue is constructed based on the new imaging data. The above process is repeated until the created 3D bone model meets the expected effect.

[0092] The method provided in this embodiment of the invention can improve the accuracy of three-dimensional bone model projection by evaluating the projection effect of the three-dimensional bone model.

[0093] In conjunction with the above embodiments, in one embodiment, projecting a three-dimensional bone model onto bone tissue includes:

[0094] The projection position is determined based on the bone tissue positioning equipment;

[0095] Based on the projection position, the three-dimensional bone model is projected onto the bone tissue.

[0096] The positioning device can be a target, such as a tibial target or a femoral target.

[0097] Specifically, by determining the coordinates of the location of the positioning device of the bone tissue, the visualization device can determine the coordinates of the projection position of the three-dimensional bone model, thereby projecting the three-dimensional bone model of the bone tissue onto the corresponding projection position, so that the three-dimensional bone model can be superimposed on the bone tissue.

[0098] The method provided in this embodiment of the invention can determine the position of bone tissue through a positioning device, thereby improving the projection accuracy of the three-dimensional bone model and thus improving the overlap between the three-dimensional bone model and the bone tissue.

[0099] In conjunction with the above embodiments, in one embodiment, determining a reference bone registration point based on pixels in the imaging data includes:

[0100] The points to be registered are determined based on the pixels in the imaging data;

[0101] The color features of the points to be registered are compared with the color features of abnormal bone tissue conditions, and the points to be registered are screened based on the comparison results.

[0102] Among the remaining target registration points after screening, reference bone registration points are determined.

[0103] The points to be registered can be pixels or feature points determined from pixels. For example, if the imaging data contains 100 pixels, these 100 pixels are used as the points to be registered. Alternatively, if the imaging data contains 100 pixels, each group of four adjacent pixels is used to determine a feature point, resulting in 25 feature points, which are then used as the points to be registered. Furthermore, each pixel corresponds to image information, including the color and position of its corresponding coordinates. Correspondingly, each feature point determined from each group of pixels also includes corresponding image information.

[0104] Abnormal bone tissue conditions include damage, osteophytes, etc. When bone tissue is in an abnormal state, the color or shape of the bone tissue in the corresponding area is different from that of bone tissue in a normal state.

[0105] The target registration points refer to the remaining registration points after some registration points have been removed.

[0106] Specifically, based on the color features and position in the image information of each point to be registered, the points to be registered corresponding to the abnormal bone tissue regions can be determined from all the points to be registered. The points to be registered corresponding to the abnormal bone tissue regions are then removed, and the remaining points to be registered are taken as the target bone registration points.

[0107] The method provided in this invention identifies bone tissue in abnormal states, such as damage or osteophytes, based on its actual morphology. It removes the registration points corresponding to abnormal bone tissue, obtaining the registration points corresponding to normal bone tissue. This improves the accuracy of bone registration point acquisition and, consequently, the accuracy of bone registration point registration.

[0108] In conjunction with the above embodiments, in one embodiment, determining reference bone registration points from the remaining target registration points after screening includes:

[0109] Based on the shape of the bone tissue, the bone tissue is divided into multiple regions;

[0110] Determine the target area to which each target registration point belongs, and select at least one target registration point from each target area so that the total number of selected target registration points reaches the preset number.

[0111] The present invention does not specifically limit the number of target regions, but can determine the number of target regions according to the specific shape of the bone tissue.

[0112] Figure 7 A schematic diagram of multiple target regions formed after dividing bone tissue into regions includes: a reference bone registration point 7 collected by acquisition device 9 on bone tissue 4, a three-dimensional bone model 8 projected on bone tissue 4, and target regions 12. Figure 7 The dashed lines represent the 3D bone model projected onto the bone tissue surface, while the small areas formed by the solid lines represent the defined target regions. Figure 7 To collect data on the target, a reference registration point is collected in one of the target regions.

[0113] Specifically, after dividing the bone tissue into multiple regions based on its shape characteristics, each region is a target region. Based on the location information in the image information of the target registration points, the target region to which each target registration point belongs can be determined; at least one target registration point is selected from each target region, so that the total number of selected target registration points reaches a preset number.

[0114] The present invention does not specifically limit the number of target registration points selected in the target area, including but not limited to: a target area with a large total number of target registration points having a large number of target registration points selected, and a target area with a small total number of target registration points having a small number of target registration points selected. For example, if the total number of target registration points in target area A is 50 and the total number of target registration points in target area B is 10, then the number of target registration points selected from target area A is greater than the number of target registration points selected from target area B.

[0115] The method provided in this invention divides bone tissue into regions to obtain multiple target regions, and determines at least one target registration point from the target regions, thereby expanding the selection range of bone registration points.

[0116] In conjunction with the above embodiments, in one embodiment, preoperative registration of the three-dimensional bone model and bone tissue is performed by acquiring coordinates and the coordinates of registration points on the preoperative three-dimensional bone model, including:

[0117] Determine the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates in the acquisition device coordinate system;

[0118] Based on the model coordinates of each reference bone registration point in the model coordinate system, each reference bone registration point is transformed from the model coordinate system to the auxiliary coordinate system to obtain the first auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system.

[0119] Based on the acquisition coordinates of each reference bone registration point in the acquisition device coordinate system, each reference bone registration point is transformed from the acquisition device coordinate system to the auxiliary coordinate system to obtain the second auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system;

[0120] The first auxiliary coordinates of each reference bone registration point are compared with the corresponding second auxiliary coordinates. All reference bone registration points are then filtered to obtain the bone registration points.

[0121] Preoperative registration of the three-dimensional bone model and bone tissue is performed by using the coordinates of the bone registration points and the coordinates of the registration points on the preoperative three-dimensional bone model.

[0122] In this context, the auxiliary coordinate system refers to the target coordinate system. During the operation, the surgical robot's robotic arm moves according to the coordinates in the target coordinate system. The model coordinate system refers to the coordinate system of the visualization device. The acquisition coordinates of the bone registration point refer to the coordinates of the bone registration point in the acquisition device coordinate system. The coordinates of the registration point on the preoperative 3D bone model refer to the coordinates of the registration point in the preoperative 3D bone model coordinate system. The preoperative 3D bone model coordinate system refers to the coordinate system in which the preoperative 3D bone model is located.

[0123] The number of registration points on the preoperative 3D bone model is the same as the number of bone registration points. Based on the position of the bone registration points on the 3D bone model, the position of the registration points on the preoperative 3D bone model is determined. Based on the position of the registration points on the preoperative 3D bone model, the coordinates of the registration points in the coordinate system of the preoperative 3D bone model are determined, which are used as the preoperative coordinates of the registration points.

[0124] Specifically, using an optical positioning device, the coordinate transformation matrix between the visualization device coordinate system and the target coordinate system, as well as the coordinate transformation matrix between the acquisition device coordinate system and the target coordinate system, can be determined. Using the coordinate transformation matrix between the visualization device coordinate system and the target coordinate system, and the model coordinates of each reference bone registration point in the model coordinate system, each reference bone registration point can be transformed from the model coordinate system to the auxiliary coordinate system, obtaining the first auxiliary coordinates of each reference bone registration point in the target coordinate system. Using the coordinate transformation matrix between the acquisition device coordinate system and the target coordinate system, and the acquisition coordinates of each reference bone registration point in the acquisition device coordinate system, each reference bone registration point can be transformed from the acquisition device coordinate system to the auxiliary coordinate system, obtaining the second auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system. The coordinate error between the first auxiliary coordinate and the corresponding second auxiliary coordinate of each reference bone registration point is determined, and reference bone registration points with coordinate errors less than the error threshold are designated as bone registration points. Using the acquisition coordinates of bone registration points on bone tissue and the preoperative coordinates of registration points on the preoperative 3D bone model, the transformation matrix between the acquisition device coordinate system and the preoperative 3D model coordinate system is determined, achieving preoperative registration of the 3D bone model and bone tissue.

[0125] The method provided in this embodiment of the invention can determine the first auxiliary coordinates and the corresponding second auxiliary coordinates of each reference bone registration point by transforming the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates of each reference bone registration point in the acquisition device coordinate system. By comparing the first auxiliary coordinates and the corresponding second auxiliary coordinates of each reference bone registration point, the bone registration points used for registration are determined. The registration points are then registered with the registration points of the preoperative three-dimensional bone model, thereby improving the registration accuracy.

[0126] In one embodiment, based on the above embodiments, during bone surgery, the surgeon's real-time blind spot is determined according to the surgeon's real-time field of vision. The corresponding area of ​​this blind spot is then displayed in a 3D bone model in real time. This model, displaying the corresponding area of ​​the blind spot in the 3D bone model, serves as a reference 3D bone model. The surgeon's operational instructions are obtained, and the posture of the reference 3D bone model is adjusted according to these instructions. The reference 3D bone model is then displayed according to the adjusted posture. Furthermore, the 3D bone model is also displayed on a screen.

[0127] The operational commands refer to gestures, voice commands, and eye-tracking commands. The reference 3D bone model provides the surgeon with the optimal viewing angle for reference bone registration points. Gestures, voice commands, and eye-tracking commands can be used to rotate the reference 3D bone model, changing the viewing angle.

[0128] Real-time display of the corresponding area of ​​the real-time blind spot in the three-dimensional bone model refers to the real-time display of the three-dimensional bone model in the corresponding area through a visualization device. The corresponding area can be determined according to the surgical requirements. For example, the corresponding area can be next to the bone tissue.

[0129] Figure 8 This is a projection diagram of a 3D bone model when the visualization device is an AR device. The AR device projects the 3D bone model onto the bone tissue surface and also projects it alongside the bone tissue. The 3D bone model projected alongside the bone tissue also contains the same reference bone registration points as the 3D bone model projected onto the bone tissue surface. The 3D bone model projected alongside the bone tissue can move its position according to surgical needs. Furthermore, the 3D bone model projected alongside the bone tissue can automatically switch perspectives based on gestures, voice commands, and eye tracking, providing the surgeon with optimal observation results. Figure 8 The display screen is used to display a three-dimensional bone model and reference bone registration points, including: AR device 1, tibial target 2, femoral target 3, bone tissue 4, display screen 5 and a three-dimensional bone model 8 projected on the surface of bone tissue 4, reference bone registration points 7 on bone tissue 4, a three-dimensional bone model 12 projected next to bone tissue 4 and reference bone registration points 13 on three-dimensional bone model 12.

[0130] Figure 9 When the visualization device is a combination of a 3D holographic projector and a 3D structured light scanner, the projection diagram of the three-dimensional bone model includes: a 3D holographic projector 14 for projecting the three-dimensional bone model, a tibial target 2, a three-dimensional bone model 12 projected next to the bone tissue 4, a three-dimensional bone model 8 projected onto the surface of the bone tissue 4, a reference bone registration point 7 on the bone tissue 4, a display screen 5, a reference bone registration point 13 on the three-dimensional bone model 12, and a three-dimensional bone model 15 displayed on the display screen. While the three-dimensional bone model is projected onto the surface of the bone tissue using one 3D holographic projector, another 3D holographic projector projects the three-dimensional bone model next to the bone tissue. The three-dimensional bone model projected next to the bone tissue also contains the same reference bone registration points as the three-dimensional bone model projected onto the surface of the bone tissue. The three-dimensional bone model projected next to the bone tissue can be moved according to surgical needs. Furthermore, the three-dimensional bone model projected next to the bone tissue can automatically switch viewing angles according to gestures, voice commands, and eye-tracking commands, providing the surgeon with the best observation effect.

[0131] Specifically, for the observation of surgical personnel, during the bone tissue surgery, a three-dimensional bone model needs to be projected onto two different areas and displayed on a single screen. A schematic diagram of this projection is shown below. Figure 10As shown, the three-dimensional bone model 4 is a three-dimensional bone model projected onto the surface of the bone tissue 4; the three-dimensional bone model 12 is a three-dimensional bone model projected next to the bone tissue 4, and the three-dimensional bone model 12 can automatically switch perspectives according to preset rules; the three-dimensional bone model 15 is a three-dimensional bone model displayed on the display screen.

[0132] The method provided in this invention, by referencing a three-dimensional bone model, can provide the best viewing angle for reference bone registration points, thereby improving the accuracy of locating and collecting reference bone registration points; in addition, the reference three-dimensional bone model can provide intelligent guidance for the surgeon, realizing the function of human-computer interaction.

[0133] In conjunction with the above embodiments, in one embodiment, such as Figure 11 As shown, a method for guiding bone registration includes:

[0134] 1101. Obtain preoperative CT scan images, construct a preoperative 3D model based on the preoperative CT scan images, and segment the preoperative 3D model according to surgical requirements to obtain a preoperative CT segmentation model.

[0135] 1102. Using a visualization device, acquire imaging data of the bone tissue of the surgical subject; construct a three-dimensional bone model of the bone tissue based on the imaging data; determine the reference bone registration point based on the pixels in the imaging data, and determine the model coordinates of the reference bone registration point in the model coordinate system of the three-dimensional bone model; project the three-dimensional bone model and the reference bone registration point onto the bone tissue using a visualization device, so that the three-dimensional bone model and the reference bone registration point cover the surface of the bone tissue.

[0136] 1103. Using the acquisition device, the reference bone registration points on the three-dimensional bone model are acquired to obtain the acquisition coordinates of the reference bone registration points in the coordinate system of the acquisition device;

[0137] 1104. Based on the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates in the acquisition device coordinate system, all reference bone registration points are filtered to obtain the bone registration points of the intraoperative three-dimensional bone model.

[0138] 1105. Perform optimal matching between the preoperative CT segmentation model and the intraoperatively constructed 3D bone model to obtain the bone registration points on the preoperative CT segmentation model. Based on the bone registration points on the preoperative CT segmentation model and the bone registration points on the bone tissue, determine the registration matrix between the preoperative CT segmentation model and the bone tissue. Here, the preoperative CT segmentation model refers to the preoperative 3D bone model, and the bone registration points on the preoperative CT segmentation model refer to the registration points on the preoperative 3D bone model.

[0139] Figure 12 This is a flowchart illustrating the method for guiding bone registration when the visualization device is an AR device. Figure 12 In this system, the computing unit is used to reconstruct a three-dimensional bone model based on imaging data, as well as perform related logical operations during the bone registration and acquisition process.

[0140] Figure 13 When the visualization device is an AR device, the scene diagram for acquiring bone registration points includes: AR device 1, a three-dimensional bone model 12 projected next to bone tissue 4, femoral target 2, tibia target 3, rotation direction 16 of the three-dimensional bone model 12 projected next to bone tissue 4, bone tissue 4, acquisition device 9, three-dimensional bone model 8 projected on bone tissue 4, and reference bone registration point 7 on bone tissue; wherein, the rotation direction 16 of the three-dimensional bone model 12 projected next to bone tissue 4 can be controlled by commands such as gestures, voice, and eye tracking.

[0141] Figure 14 This is a flowchart illustrating a method for guiding bone registration when the visualization device is a combination of a 3D holographic projector and a 3D structured light scanner. Figure 14 In this system, the computing unit is used to reconstruct a three-dimensional bone model based on imaging data, as well as perform related logical operations during the bone registration and acquisition process.

[0142] Figure 15 When the visualization device is a combination of a 3D holographic projector and a 3D structured light scanner, a scene diagram for acquiring bone registration points is provided, including: a 3D holographic projector 6, a display screen 5, a 3D structured light scanner 17, a tibial target 2, a femoral target 3, a three-dimensional bone model 12 projected next to bone tissue 4, a reference bone registration point 7 on bone tissue 4, a three-dimensional bone model 8 projected on the surface of bone tissue, an acquisition device 9, and a reference bone registration point 13 on the three-dimensional bone model 12.

[0143] Figure 16 This is a flowchart illustrating a method for guiding bone registration when the visualization device is a combination of an AR device and a 3D structured light scanner. Figure 16 In this system, the computing unit is used to reconstruct a three-dimensional bone model based on imaging data, as well as perform related logical operations during the bone registration and acquisition process.

[0144] The method provided in this invention collects bone registration points from an intraoperative three-dimensional bone model and determines the bone registration points on the preoperative CT segmentation model based on the bone registration points from the intraoperative three-dimensional bone model, thus avoiding the step of planning bone registration points on the preoperative CT segmentation model.

[0145] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0146] Based on the same inventive concept, this application also provides a system for implementing the guide bone registration method described above. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations of one or more system embodiments for guide bone registration provided below can be found in the limitations of the guide bone registration method described above, and will not be repeated here.

[0147] In one embodiment, such as Figure 17 As shown, a system for guiding bone registration is provided, including: an acquisition module 1701, a construction module 1702, a determination module 1703, a projection module 1704, a data acquisition module 1705, and a registration module 1706, wherein:

[0148] The acquisition module 1701 is used to acquire imaging data of bone tissue of the surgical subject through a visualization device;

[0149] Module 1702 is used to construct a three-dimensional bone model of bone tissue based on imaging data;

[0150] The determination module 1703 is used to determine the reference bone registration point based on the pixels in the imaging data, and to determine the model coordinates of the reference bone registration point in the model coordinate system where the three-dimensional bone model is located.

[0151] The projection module 1704 is used to project a three-dimensional bone model and reference bone registration points onto bone tissue through a visualization device, so that the three-dimensional bone model and reference bone registration points cover the surface of the bone tissue.

[0152] The acquisition module 1705 is used to acquire reference bone registration points on bone tissue through the acquisition device, and obtain the acquisition coordinates of the reference bone registration points in the coordinate system of the acquisition device.

[0153] The registration module 1706 is used to register the preoperative three-dimensional bone model and bone tissue by referencing the acquired coordinates of the reference bone registration point in the coordinate system of the acquisition device and the coordinates of the registration point on the preoperative three-dimensional bone model. The preoperative three-dimensional bone model is constructed from the preoperative acquired images of the surgical subject.

[0154] In one embodiment, the construction module 1702 includes:

[0155] The evaluation submodule is used to project the three-dimensional bone model onto the bone tissue and evaluate whether the three-dimensional bone model meets the expected effect based on the projection effect.

[0156] The acquisition submodule is used to acquire new imaging data when the results are not as expected, and to construct a three-dimensional bone model of the bone tissue based on the new imaging data. The above process is repeated until the three-dimensional bone model created meets the expected results.

[0157] In one embodiment, the evaluation submodule includes:

[0158] The first determining submodule is used to determine the projection position based on the bone tissue positioning device;

[0159] The projection submodule is used to project the 3D bone model onto the bone tissue according to the projection position.

[0160] In one embodiment, the determining module 1703 includes:

[0161] The registration point is determined based on the pixels in the imaging data;

[0162] The first comparison submodule is used to compare the color features of the point to be registered with the color features of abnormal bone tissue, and to filter the points to be registered based on the comparison results.

[0163] The second determination submodule is used to determine reference bone registration points from the remaining target registration points after filtering.

[0164] In one embodiment, determining a submodule includes:

[0165] Dividing units are used to divide bone tissue into multiple regions according to its shape;

[0166] The determining unit is used to determine the target area to which each target registration point belongs, and to select at least one target registration point from each target area so that the total number of selected target registration points reaches a preset number.

[0167] In one embodiment, the registration module 1706 includes:

[0168] The third determination submodule is used to determine the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates in the acquisition device coordinate system.

[0169] The first transformation submodule is used to transform each reference bone registration point from the model coordinate system to the auxiliary coordinate system based on the model coordinates of each reference bone registration point in the model coordinate system, so as to obtain the first auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system.

[0170] The second transformation submodule is used to acquire coordinates of each reference bone registration point in the coordinate system of the acquisition device, transform each reference bone registration point from the coordinate system of the acquisition device to the auxiliary coordinate system, and obtain the second auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system.

[0171] The second comparison submodule is used to compare the first auxiliary coordinates of each reference bone registration point with the corresponding second auxiliary coordinates, filter all reference bone registration points, and obtain bone registration points.

[0172] The registration submodule is used to register the preoperative 3D bone model and bone tissue using the acquired coordinates of the bone registration points and the coordinates of the registration points on the preoperative 3D bone model.

[0173] In one embodiment, the system further includes:

[0174] The display module is used to determine the surgeon's real-time blind spot in relation to the bone tissue during bone surgery, based on the surgeon's real-time field of vision, and to display the corresponding area of ​​the real-time blind spot in the three-dimensional bone model in real time; the model that displays the corresponding area of ​​the real-time blind spot in the three-dimensional bone model in real time is used as a reference three-dimensional bone model.

[0175] The adjustment module is used to obtain the operator's operation instructions, adjust the posture of the reference 3D bone model according to the operation instructions, and display the reference 3D bone model according to the adjusted posture.

[0176] The modules in the aforementioned bone registration system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0177] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 18As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a bootloader registration method.

[0178] Those skilled in the art will understand that Figure 18 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0179] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0180] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0181] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0182] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0183] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0184] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, The steps implemented by the processor when executing the computer program include: Using visualization equipment, imaging data of bone tissue for the surgical subject is acquired, and a three-dimensional bone model of the bone tissue is constructed to determine reference bone registration points; The visualization device is used to project the three-dimensional bone model and the reference bone registration point onto the bone tissue, so that the three-dimensional bone model and the reference bone registration point cover the surface of the bone tissue. The reference bone registration point on the bone tissue is acquired using the acquisition device, and the acquisition coordinates of the reference bone registration point in the coordinate system of the acquisition device are obtained. The preoperative three-dimensional bone model and bone tissue are registered by using the acquisition coordinates of the reference bone registration point in the acquisition device coordinate system and the coordinates of the registration point on the preoperative three-dimensional bone model. The preoperative three-dimensional bone model is constructed from the preoperative acquisition images of the surgical subject. The steps implemented by the processor when executing the computer program further include: According to the screening criteria, the reference bone registration points on the bone tissue are screened to obtain bone registration points; the preoperative three-dimensional bone model and bone tissue are registered by the acquisition coordinates of the bone registration points in the acquisition device coordinate system and the preoperative coordinates of the preoperative bone registration points; the registration point on the preoperative three-dimensional bone model corresponding to the bone registration point on the bone tissue is the preoperative bone registration point.

2. The computer device according to claim 1, characterized in that, The steps implemented by the processor when executing the computer program further include: The three-dimensional bone model is projected onto the bone tissue, and the projection effect is used to evaluate whether the three-dimensional bone model meets the expected effect. If the desired effect is not achieved, new imaging data is acquired, and a three-dimensional bone model of the bone tissue is constructed based on the new imaging data. The above process is repeated until the three-dimensional bone model created meets the desired effect.

3. The computer device according to claim 2, characterized in that, The steps implemented by the processor when executing the computer program further include: The projection position is determined based on the positioning device for the bone tissue; Based on the projection position, the three-dimensional bone model is projected onto the bone tissue.

4. The computer device according to claim 1, characterized in that, The steps implemented by the processor when executing the computer program further include: The point to be registered is determined based on the pixels in the imaging data; The color features of the points to be registered are compared with the color features of abnormal bone tissue conditions, and the points to be registered are screened based on the comparison results. Among the remaining target registration sites after screening, reference bone registration sites are determined.

5. The computer device according to claim 4, characterized in that, The steps implemented by the processor when executing the computer program further include: According to the shape of the bone tissue, the bone tissue is divided into multiple regions; Determine the target area to which each target registration point belongs, and select at least one target registration point from each target area so that the total number of selected target registration points reaches the preset number.

6. The computer device according to claim 1, characterized in that, The steps implemented by the processor when executing the computer program further include: Determine the model coordinates of each reference bone registration point in the model coordinate system and the acquisition coordinates in the acquisition device coordinate system; Based on the model coordinates of each reference bone registration point in the model coordinate system, each reference bone registration point is transformed from the model coordinate system to the auxiliary coordinate system to obtain the first auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system. Based on the acquisition coordinates of each reference bone registration point in the acquisition device coordinate system, each reference bone registration point is transformed from the acquisition device coordinate system to the auxiliary coordinate system to obtain the second auxiliary coordinates of each reference bone registration point in the auxiliary coordinate system. The first auxiliary coordinates of each reference bone registration point are compared with the corresponding second auxiliary coordinates. All reference bone registration points are then filtered to obtain the bone registration points. Preoperative three-dimensional bone model and bone tissue registration are performed using the acquired coordinates of the bone registration points and the preoperative coordinates of the preoperative bone registration points.

7. The computer device according to claim 1, characterized in that, The steps implemented by the processor when executing the computer program further include: During the surgery on the bone tissue, based on the surgeon's real-time field of vision, the surgeon's real-time blind spot for the bone tissue is determined, and the corresponding area of ​​the real-time blind spot in the three-dimensional bone model is displayed in real time. The model that displays the corresponding area of ​​the real-time visual blind spot in the three-dimensional bone model is used as the reference three-dimensional bone model. Obtain the surgeon's operating instructions, adjust the posture of the reference three-dimensional bone model according to the operating instructions, and display the reference three-dimensional bone model according to the adjusted posture.

8. A system for guiding bone registration, characterized in that, The system includes: A visualization device acquires imaging data of bone tissue for a surgical subject, constructs a three-dimensional bone model of the bone tissue based on the imaging data, and determines reference bone registration points; The visualization device projects the three-dimensional bone model and the reference bone registration point onto the bone tissue, so that the three-dimensional bone model and the reference bone registration point cover the surface of the bone tissue; The acquisition device acquires the reference bone registration point on the bone tissue to obtain the acquisition coordinates of the reference bone registration point in the acquisition device coordinate system; The registration module is used to register the preoperative three-dimensional bone model and bone tissue using the acquired coordinates and the coordinates of the registration points on the preoperative three-dimensional bone model. The preoperative three-dimensional bone model is constructed from the preoperative acquired images of the surgical subject. The registration module is further configured to filter the reference bone registration points on the bone tissue according to the screening conditions to obtain bone registration points; and to register the preoperative three-dimensional bone model and bone tissue by using the acquisition coordinates of the bone registration points in the acquisition device coordinate system and the preoperative coordinates of the preoperative bone registration points; the registration point on the preoperative three-dimensional bone model corresponding to the bone registration point on the bone tissue is the preoperative bone registration point.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the computer device as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps performed by the computer device according to any one of claims 1 to 7.

Images