Positioning navigation method, device and installation robot during surgery

Abstract

The present invention discloses a positioning and navigation method, device and installation robot for surgery. The method comprises: obtaining medical imaging data of a target object, wherein the medical imaging data at least includes a target bone of the target object and an original bone surface of the target bone; making a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data; selecting a virtual bone surface that fits the original bone surface according to the medical imaging data; positioning the virtual bone surface that fits the original bone surface, and fitting the repaired three-dimensional joint prosthesis model to the target bone. The present invention solves the technical problems of low installation efficiency and inaccurate positioning in the positioning and navigation method for surgery in the related art.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, in particular to the field of joint replacement technology, and specifically to a positioning navigation method, device and installation robot during surgery. Background Art

[0002] Shoulder replacement is required for patients with humeral head necrosis, severe comminuted proximal humeral fractures and glenohumeral arthritis. Different shoulder prostheses are used when different parts of the shoulder joint are seriously injured. There are two main types of shoulder prostheses in the prior art: one is a positive shoulder prosthesis used when severe injuries occur at the humeral head, and the other is a reverse shoulder prosthesis used when severe injuries occur at the rotator cuff.

[0003] Regardless of whether it is a normal shoulder prosthesis or a reverse shoulder prosthesis, an effective surgical positioning guide device and method are needed during the operation to help orient the glenoid prosthesis to improve the final placement of the prosthesis. Due to different medical imaging equipment, different shooting environments and various error sources that may interfere during the shooting process, the joint prosthesis installation efficiency is low and the installation positioning accuracy is poor, which makes the operation have certain risks.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a positioning and navigation method, a device and an installation robot for surgery, so as to at least solve the technical problems of low installation efficiency and inaccurate positioning existing in the positioning and navigation method for surgery in the related art.

[0006] According to one aspect of an embodiment of the present invention, a positioning and navigation method during surgery is provided, comprising: acquiring medical imaging data of a target object, wherein the medical imaging data at least includes a target bone of the target object and an original bone surface of the target bone; making a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data; selecting a virtual bone surface that fits well with the original bone surface according to the medical imaging data; using the virtual bone surface that fits well with the original bone surface for positioning, and fitting the repaired three-dimensional joint prosthesis model to the target bone.

[0007] Optionally, if the virtual bone surface is a joint bone surface, a virtual bone surface that fits the original bone surface is selected according to the medical imaging data, including: dividing the joint bone surface into a plurality of different sub-bone surfaces according to the medical imaging data; obtaining a plurality of candidate bone surfaces corresponding to the joint bone surface, and dividing the plurality of candidate bone surfaces into a plurality of candidate sub-bone surfaces corresponding to the plurality of sub-bone surfaces; obtaining a palpable score for each of the candidate bone surfaces, wherein the palpable score is used to reflect the possibility of contacting the bone surface during the prosthetic replacement surgery, and is related to the patient's condition, cartilage, and available bone. The method is related to the surgical surface and the doctor's surgical approach; specificity calculations are performed on multiple candidate sub-bone surfaces according to the above medical imaging data to obtain specificity values ​​corresponding to each of the above candidate sub-bone surfaces, wherein the above specificity calculations include: specific structure scoring, flatness calculations, and symmetry parameter calculations; image confidence assessments are performed on multiple above candidate sub-bone surfaces according to the above medical imaging data to obtain confidence values ​​related to multiple above candidate sub-bone surfaces; and the above virtual bone surface that fits the above original bone surface is selected from the multiple above candidate bone surfaces according to the above palpable scores, the above confidence values, and the above specificity values.

[0008] Optionally, based on the above-mentioned palpable score, the above-mentioned confidence value and the above-mentioned specificity value, the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface is selected from the multiple above-mentioned alternative bone surfaces, including: calculating the joint specificity value of each above-mentioned alternative bone surface based on the multiple above-mentioned specificity values ​​corresponding to each above-mentioned alternative bone surface; calculating the joint confidence value of each above-mentioned alternative bone surface based on the multiple above-mentioned confidence values ​​corresponding to each above-mentioned alternative bone surface; calculating the joint score of each above-mentioned alternative bone surface based on the above-mentioned palpable score, the above-mentioned joint confidence value and the above-mentioned joint specificity value; and selecting the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface from the multiple above-mentioned alternative bone surfaces based on the above-mentioned joint score.

[0009] Optionally, specific calculations are performed on multiple candidate sub-bone surfaces according to the above-mentioned medical imaging data to obtain specificity values ​​corresponding to each of the above-mentioned candidate sub-bone surfaces, including: point cloud data is obtained by reverse engineering according to the above-mentioned medical imaging data; the specific structure of each of the above-mentioned candidate sub-bone surfaces is scored according to the above-mentioned point cloud data to obtain a first score, wherein the above-mentioned specific structure is a structure containing concave features and protrusion characteristics; the flatness of each of the above-mentioned candidate sub-bone surfaces is scored according to the above-mentioned point cloud data to obtain a second score, wherein the above-mentioned flatness is used to reflect the degree of convergence between the overall structure of the above-mentioned candidate sub-bone surface and the plane; the symmetry of each of the above-mentioned candidate sub-bone surfaces is scored according to the above-mentioned point cloud data to obtain a third score, wherein the above-mentioned symmetry is used to reflect the overall symmetry of the above-mentioned candidate sub-bone surfaces; a weight is assigned to the above-mentioned first score, the above-mentioned second score and the above-mentioned third score respectively to obtain a first weight value, a second weight value and a third weight value; the specificity value corresponding to each of the above-mentioned candidate sub-bone surfaces is calculated according to the above-mentioned first score, the above-mentioned second score, the above-mentioned third score, the above-mentioned first weight value, the above-mentioned second weight value and the above-mentioned third weight value.

[0010] Optionally, image confidence assessment is performed on the multiple candidate sub-bone surfaces based on the above-mentioned medical imaging data to obtain the multiple confidence values ​​associated with the above-mentioned candidate sub-bone surfaces, including: calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the above-mentioned medical imaging data; image confidence assessment is performed on the multiple candidate sub-bone surfaces based on the above-mentioned average signal-to-noise ratio to obtain the multiple confidence values ​​associated with the above-mentioned candidate sub-bone surfaces.

[0011] Optionally, calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the above-mentioned medical image data includes: using a segmentation frame to segment the three-dimensional images of different layers in the above-mentioned medical image data to obtain multiple segmented local images; performing denoising processing on the multiple local images respectively to obtain multiple processed local images, wherein the denoising processing includes but is not limited to mean filtering processing, adaptive Wiener filtering processing, median filtering processing, and Bayesian filtering processing; calculating multiple first signal-to-noise ratios corresponding to the multiple processed local images; after moving the above-mentioned segmentation frame by a predetermined number of pixel steps, using a next segmentation frame to repeat the above-mentioned segmentation processing and the above-mentioned denoising processing to obtain a second signal-to-noise ratio, until the above-mentioned segmentation frame coincides with the above-mentioned next segmentation frame; and calculating the above-mentioned average signal-to-noise ratio of each of the above-mentioned pixels in the above-mentioned processed local images according to the above-mentioned first signal-to-noise ratio and the above-mentioned second signal-to-noise ratio.

[0012] Optionally, a combined score of each of the above-mentioned alternative bone surfaces is calculated based on the above-mentioned accessibility score, the above-mentioned combined confidence value and the above-mentioned combined specificity value, including: assigning a weight to the above-mentioned accessibility score, the above-mentioned combined confidence value and the above-mentioned combined specificity value respectively, to obtain a fourth weight value, a fifth weight value and a sixth weight value; and calculating the above-mentioned combined score of each of the above-mentioned alternative bone surfaces based on the above-mentioned accessibility score, the above-mentioned combined confidence value, the above-mentioned combined specificity value, the above-mentioned fourth weight value, the above-mentioned fifth weight value and the above-mentioned sixth weight value.

[0013] Optionally, the virtual bone surface that fits the original bone surface is used for positioning, and the repaired three-dimensional joint prosthesis model is fitted and installed on the target bone, including: using the virtual bone surface that fits the original bone surface for positioning to determine characteristic marking points and reserved connection ports; according to the characteristic marking points and the reserved connection ports, the repaired three-dimensional joint prosthesis model is fitted and installed on the target bone, wherein the connection position and / or direction of the repaired three-dimensional joint prosthesis model and the target bone are uniquely determined.

[0014] According to another aspect of an embodiment of the present invention, a positioning and navigation device during surgery is also provided, including: an acquisition module, used to acquire medical imaging data of a target object, wherein the medical imaging data at least includes a target bone of the target object and an original bone surface of the target bone; a production module, used to produce a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data; a selection module, used to select a virtual bone surface that fits well with the original bone surface according to the medical imaging data; and an installation module, used to use the virtual bone surface that fits well with the original bone surface for positioning, and to fit the repaired three-dimensional joint prosthesis model to the target bone.

[0015] According to another aspect of an embodiment of the present invention, there is also provided a joint prosthesis installation robot, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute any one of the above-mentioned intraoperative positioning and navigation methods through the computer program.

[0016] In an embodiment of the present invention, a positioning and navigation method is adopted during surgery, by obtaining medical image data of the target object, wherein the above-mentioned medical image data at least includes the target bone of the above-mentioned target object and the original bone surface of the above-mentioned target bone; a three-dimensional joint prosthesis model adapted to the above-mentioned target bone is produced according to the above-mentioned medical image data; a virtual bone surface that fits well with the above-mentioned original bone surface is selected according to the above-mentioned medical image data; the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface is used for positioning, and the repaired three-dimensional joint prosthesis model is fit-fitted and installed with the above-mentioned target bone, thereby achieving the purpose of accurately obtaining the installation positioning and automatically completing the fitting installation of the three-dimensional joint prosthesis model, thereby realizing the technical effect of improving the positioning and navigation efficiency and installation accuracy during surgery, and further solving the technical problems of low installation efficiency and inaccurate positioning existing in the positioning and navigation method during surgery in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a positioning navigation method during surgery according to an embodiment of the present invention;

[0019] Figure 2 is a flowchart of another optional intraoperative positioning navigation method according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of an optional orientation device for shoulder arthroplasty according to an embodiment of the present invention;

[0021] Figure 4a is a schematic diagram of an optional bone surface fitting module according to an embodiment of the present invention;

[0022] Figure 4b is a schematic diagram of assembling an optional bone surface fitting module and a patient marker according to an embodiment of the present invention;

[0023] Figure 4c is a schematic diagram of assembling another optional bone surface fitting module and a patient marker according to an embodiment of the present invention;

[0024] Figure 4d is a schematic structural diagram of an optional humerus of a patient after osteotomy according to an embodiment of the present invention;

[0025] Figure 5 It is a schematic diagram of the structure of a positioning navigation device during surgery according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention are explained below:

[0029] Shoulder joint: It is composed of the glenoid cavity of the scapula and the humeral head, and is a ball-and-socket joint. Because the humeral head is relatively large and spherical, it only surrounds 1 / 3 of the humeral head, and the joint capsule is thin and loose. Therefore, the shoulder joint is the joint with the largest range of motion and the most flexible in the human body. It can do flexion, extension, adduction, abduction, internal rotation, external rotation, and circumduction.

[0030] Example 1

[0031] According to an embodiment of the present invention, an embodiment of a method for positioning navigation during surgery is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1 FIG. 1 is a flow chart of a positioning navigation method during surgery according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0033] Step S102, obtaining medical image data of the target object, wherein the medical image data at least includes a target bone of the target object and an original bone surface of the target bone;

[0034] Step S104, producing a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data;

[0035] Step S106, selecting a virtual bone surface that fits the original bone surface according to the medical image data;

[0036] Step S108, using the virtual bone surface that fits the original bone surface for positioning, the repaired three-dimensional joint prosthesis model is fitted and installed on the target bone.

[0037] Optionally, the target bone may be but is not limited to a scapula; a three-dimensional joint prosthesis model adapted to the target bone may be reverse engineered based on the medical imaging data, and the medical imaging data may be acquired through multiple modalities such as CT images and magnetic resonance imaging, but is not limited to.

[0038] Optionally, the above-mentioned virtual bone surface can be but is not limited to a single bone surface or multiple composite bone surfaces (i.e., a combined bone surface); it can be but is not limited to selecting the combined bone surface with the best comprehensive score of joint score, confidence value and specificity value as the above-mentioned virtual bone surface, or selecting a single bone surface with the best confidence value and specificity value as the above-mentioned virtual bone surface.

[0039] Optionally, the connection position and / or direction between the three-dimensional joint prosthesis model after the repair process and the target bone is uniquely determined. The repair process may be, but is not limited to, filling of bone defects; repairing the three-dimensional joint prosthesis model using universal patches or personalized designs for the patient; and making a three-dimensional joint prosthesis model that matches the target bone by machine processing or 3D printing.

[0040] In an embodiment of the present invention, a positioning and navigation method is adopted during surgery, by obtaining medical image data of the target object, wherein the above-mentioned medical image data at least includes the target bone of the above-mentioned target object and the original bone surface of the above-mentioned target bone; a three-dimensional joint prosthesis model adapted to the above-mentioned target bone is produced according to the above-mentioned medical image data; a virtual bone surface that fits well with the above-mentioned original bone surface is selected according to the above-mentioned medical image data; the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface is used for positioning, and the repaired three-dimensional joint prosthesis model is fit-fitted and installed with the above-mentioned target bone, thereby achieving the purpose of accurately obtaining the installation positioning and automatically completing the fitting installation of the three-dimensional joint prosthesis model, thereby realizing the technical effect of improving the positioning and navigation efficiency and installation accuracy during surgery, and further solving the technical problems of low installation efficiency and inaccurate positioning existing in the positioning and navigation method during surgery in the related art.

[0041] In an optional embodiment, if the virtual bone surface is a combined bone surface, selecting a virtual bone surface that fits the original bone surface according to the medical image data includes:

[0042] Step S202, dividing the joint bone surface into a plurality of different sub-bone surfaces according to the medical image data;

[0043] Step S204, obtaining a plurality of candidate bone surfaces corresponding to the joint bone surface, and dividing the plurality of candidate bone surfaces into a plurality of candidate sub-bone surfaces corresponding to the plurality of sub-bone surfaces;

[0044] Step S206, obtaining a touchability score for each of the candidate bone surfaces, wherein the touchability score is used to reflect the possibility of contacting the bone surface during the prosthesis replacement surgery, and is related to the patient's condition, cartilage, available bone surface, and the doctor's surgical approach;

[0045] Step S208, performing specificity calculations on the multiple candidate sub-bone surfaces respectively according to the medical imaging data to obtain a specificity value corresponding to each of the candidate sub-bone surfaces, wherein the specificity calculations include: specific structure scoring, flatness calculation, and symmetry parameter calculation;

[0046] Step S210, performing image confidence evaluation on the plurality of candidate sub-bone surfaces according to the medical image data to obtain confidence values ​​associated with the plurality of candidate sub-bone surfaces;

[0047] Step S212, selecting the virtual bone surface that fits the original bone surface from the plurality of candidate bone surfaces according to the accessibility score, the confidence value and the specificity value.

[0048] Optionally, the above-mentioned palpability score is used to reflect the possibility of contacting the bone surface during prosthetic replacement surgery, which is related to the patient's condition, cartilage, available bone surface, and the doctor's surgical approach.

[0049] It should be noted that the palpable score is used to reflect the possibility of contacting the bone surface during prosthetic replacement surgery. Due to different patient conditions, cartilage influences, and different surgical approaches actually used by doctors during surgery, the bone surfaces that can be used by different patients will vary greatly. This has little effect when a single bone surface is contacted, but because the combined bone surface alignment is to achieve high precision by expanding the contact range as much as possible, the palpable score is very important when the combined bone surfaces are used.

[0050] Optionally, the above-mentioned accessibility score can be determined by, but not limited to, an empirical calibration method. It should be noted that the accessibility score is difficult to evaluate in practice. The empirical calibration method is used to collect medical imaging data of multiple patients, and the doctor first performs accessibility labeling processing. For example, completely accessible is labeled as 1, and completely inaccessible is labeled as 0. The scores of multiple patients can be simultaneously projected onto a standard bone model by, but not limited to, a three-dimensional projection algorithm to calculate a 3D thermal value map of the accessibility score, and the above 3D thermal value map is used as a benchmark for subsequent calculation of the accessibility score.

[0051] It is still necessary to explain that in reality, doctors can manually adjust the palpable score, and the adjustment results can be fed back to the operating software, which can further modify the above 3D thermal value map. It can be seen that the above 3D thermal value map can be continuously optimized as the number of cases continues to increase.

[0052] As an optional embodiment, Figure 2 is a flowchart of another optional intraoperative positioning navigation method according to an embodiment of the present invention, such as Figure 2 As shown, according to the above-mentioned palpable score, the above-mentioned confidence value and the above-mentioned specificity value, the above-mentioned virtual bone surface that fits the above-mentioned original bone surface is selected from the multiple above-mentioned alternative bone surfaces, including:

[0053] Step S302, based on the multiple specific values ​​corresponding to each of the candidate bone surfaces, calculate a joint specific value of each of the candidate bone surfaces;

[0054] Step S304, based on the multiple confidence values ​​corresponding to each of the candidate bone surfaces, calculate a joint confidence value of each of the candidate bone surfaces;

[0055] Step S306, calculating a joint score of each of the candidate bone surfaces according to the palpable score, the joint confidence value and the joint specificity value;

[0056] Step S308, selecting the virtual bone surface that fits the original bone surface best from the plurality of candidate bone surfaces based on the combined score.

[0057] It can be understood that the higher the above combined score is, the better the fit between the alternative bone surface and the original bone surface is, and the lower the above combined score is, the worse the fit between the alternative bone surface and the original bone surface is.

[0058] Optionally, by calculating the mean value of the above-mentioned specificity values ​​corresponding to a plurality of alternative sub-bone faces in each of the above-mentioned alternative bone faces, the joint specificity value of each of the above-mentioned alternative bone faces is obtained. Or by weighted average calculation of the above-mentioned specificity values ​​corresponding to a plurality of alternative sub-bone faces in each of the above-mentioned alternative bone faces, the joint specificity value of each of the above-mentioned alternative bone faces is obtained, wherein the weight of the above-mentioned weighted average calculation can be but not limited to area weight, specificity weight, etc.; wherein, the above-mentioned area weight is the proportion of the area of ​​each alternative sub-bone face to the total area of ​​the alternative bone face; the above-mentioned specificity weight is about to use the specificity value of each alternative sub-bone face as weight, thereby amplifying the proportion of the specificity feature of the bone face in the joint scoring. Generally speaking, when the specificity is similar, the larger the area, the better the bone face fitting effect.

[0059] Optionally, the combined confidence value of each of the above-mentioned alternative bone surfaces is obtained by calculating the average value of the above-mentioned confidence values ​​corresponding to multiple alternative sub-bone surfaces in each of the above-mentioned alternative bone surfaces. Alternatively, the combined confidence value of each of the above-mentioned alternative bone surfaces is obtained by weighted average calculation of the above-mentioned confidence values ​​corresponding to multiple alternative sub-bone surfaces in each of the above-mentioned alternative bone surfaces, wherein the weight of the above-mentioned weighted average calculation may be, but is not limited to, an area weight, a specificity weight, and the like; wherein the above-mentioned area weight is the proportion of the area of ​​each alternative sub-bone surface to the total area of ​​the alternative bone surface; and the above-mentioned specificity weight is to use the specificity value of each alternative sub-bone surface as a weight, thereby amplifying the proportion of the specific characteristics of the bone surface in the combined score.

[0060] It should be noted that the palpable score is used to reflect the possibility of contacting the bone surface during prosthetic replacement surgery. Due to different patient conditions, cartilage influences, and different surgical approaches actually used by doctors during surgery, the bone surfaces that can be used by different patients will vary greatly. This has little effect when a single bone surface is in contact. However, since the combined bone surface alignment is to achieve high precision by expanding the contact range as much as possible, the palpable score is included in the calculation range of the combined score to improve the accuracy of the combined score calculation, thereby selecting a virtual bone surface that is more closely matched to the original bone surface.

[0061] In an optional embodiment, specificity calculations are performed on a plurality of candidate sub-bone surfaces respectively according to the medical imaging data to obtain specificity values ​​corresponding to each of the candidate sub-bone surfaces, including:

[0062] Step S402, obtaining point cloud data by reverse engineering based on the above medical image data;

[0063] Step S404, scoring the specific structure of each of the candidate sub-bone surfaces according to the point cloud data to obtain a first score, wherein the specific structure is a structure including concave features and protrusion features;

[0064] Step S406, scoring the flatness of each of the candidate sub-bone surfaces according to the point cloud data to obtain a second score, wherein the flatness is used to reflect the degree of closeness between the entirety of the candidate sub-bone surface and the plane;

[0065] Step S408, scoring the symmetry of each of the candidate sub-bone surfaces according to the point cloud data to obtain a third score, wherein the symmetry is used to reflect the overall symmetry of the candidate sub-bone surfaces;

[0066] Step S410, assigning a weight to the first score, the second score, and the third score respectively, to obtain a first weight value, a second weight value, and a third weight value;

[0067] Step S412, based on the first score, the second score, the third score, the first weight value, the second weight value and the third weight value, calculate the specificity value corresponding to each of the above-mentioned candidate sub-bone surfaces.

[0068] Optionally, the above-mentioned specific structure is a structure containing concave features and protrusion characteristics. For example, for the above-mentioned concave features, the ratio of the concave depth to the concave width (i.e., the aspect ratio) is calculated, and the aspect ratio of the above-mentioned concave features is used as the structural score. The higher the structural score, the more significant the guiding effect of the concave feature in the bone surface fitting. The specific structural score of each of the above-mentioned alternative sub-bone surfaces is calculated according to the number of specific structures and the structural score, and this is used as the above-mentioned first score.

[0069] Optionally, the flatness is used to reflect the degree of convergence between the whole of the candidate sub-bone surface and the plane. The flatness can be calculated by, but not limited to, the three-point method, the diagonal method, the least square method, and the minimum area method, wherein the higher the flatness, the lower the characteristics of the candidate sub-bone surface in bone-surface fitting and the worse the guiding property.

[0070] Optionally, the above symmetry is used to reflect the overall symmetry of the above-mentioned alternative sub-bone surface. The higher the above symmetry is, the lower the characteristics of the alternative sub-bone surface in bone surface fitting and the worse the guidance.

[0071] Optionally, a weight is respectively assigned to the first score (ISS), the second score (PP) and the third score (SP) to obtain a first weight value W(ISN), a second weight value W(PP) and a third weight value W(SP), and the specificity value Spe corresponding to each of the above-mentioned alternative sub-bone surfaces is calculated by the following formula: Spe = W(ISN)*ISN–W(PP)*PP–W(SP)*SP.

[0072] In an optional embodiment, image confidence evaluation is performed on the plurality of candidate sub-bone surfaces according to the medical image data to obtain confidence values ​​related to the plurality of candidate sub-bone surfaces, including:

[0073] Step S502, calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the above medical image data;

[0074] Step S504, performing image confidence evaluation on the multiple candidate sub-bone surfaces according to the above average signal-to-noise ratio to obtain the above confidence values ​​related to the multiple candidate sub-bone surfaces.

[0075] As an optional embodiment, calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the medical image data includes:

[0076] Step S602, using a segmentation frame to segment the three-dimensional images of different layers in the medical image data to obtain a plurality of segmented local images;

[0077] Step S604, performing denoising processing on the plurality of the local images to obtain a plurality of processed local images, wherein the denoising processing includes but is not limited to mean filtering processing, adaptive Wiener filtering processing, median filtering processing, and Bayesian filtering processing;

[0078] Step S606, calculating a plurality of first signal-to-noise ratios corresponding to the plurality of processed local images;

[0079] Step S608, after moving the above segmentation frame by a predetermined number of pixel steps, repeating the above segmentation process and the above denoising process with the next segmentation frame to obtain a second signal-to-noise ratio, until the above segmentation frame overlaps with the next segmentation frame;

[0080] Step S610: calculating the average signal-to-noise ratio of each pixel in the processed local image according to the first signal-to-noise ratio and the second signal-to-noise ratio.

[0081] Optionally, the size of the partial image may be, but is not limited to, 8*8 or 16*16.

[0082] Optionally, the above-mentioned denoising processing includes but is not limited to mean filtering processing, adaptive Wiener filtering processing, median filtering processing, and Bayesian filtering processing.

[0083] Optionally, the predetermined number of pixel steps may be set according to actual operation needs, for example, the predetermined number of pixel steps may be set to 2 pixel steps. After the segmentation frame is moved by 2 pixel steps, the segmentation process and the denoising process are repeated with the next segmentation frame to obtain a second signal-to-noise ratio until the segmentation frame coincides with the next segmentation frame.

[0084] Optionally, after the segmentation frame overlaps with the next segmentation frame, the average signal-to-noise ratio of each pixel in the processed local image is calculated according to the first signal-to-noise ratio and the second signal-to-noise ratio.

[0085] Optionally, the number of times the signal-to-noise ratio is calculated is determined according to the above-mentioned predetermined number of pixel steps and the size of the above-mentioned local image. For example, if the local image is 8*8 and the step size is 2, the signal-to-noise ratio of each pixel will be calculated 4 times again; the average signal-to-noise ratio tensor is determined according to the above-mentioned average signal-to-noise ratio, wherein the above-mentioned signal-to-noise ratio tensor actually corresponds to the average signal-to-noise ratio of each pixel in the three-dimensional image.

[0086] In an optional embodiment, a joint score of each of the candidate bone surfaces is calculated based on the above-mentioned palpable score, the above-mentioned joint confidence value and the above-mentioned joint specificity value, including:

[0087] Step S702, assigning a weight to the reachability score, the joint confidence value and the joint specificity value respectively, to obtain a fourth weight value, a fifth weight value and a sixth weight value;

[0088] Step S704, calculating the above-mentioned joint score of each of the above-mentioned candidate bone surfaces according to the above-mentioned accessibility score, the above-mentioned joint confidence value, the above-mentioned joint specificity value, the above-mentioned fourth weight value, the above-mentioned fifth weight value and the above-mentioned sixth weight value.

[0089] It should be noted that the palpable score is used to reflect the possibility of contacting the bone surface during prosthetic replacement surgery. Due to different patient conditions, cartilage influences, and different surgical approaches actually used by doctors during surgery, the bone surfaces that can be used by different patients will vary greatly. This has little effect when a single bone surface is in contact, but because the combined bone surface registration is to achieve high precision by expanding the contact range as much as possible, the palpable score is included in the calculation range of the combined score, and appropriate weights are assigned to the above-mentioned combined score, the above-mentioned confidence value, and the above-mentioned specificity value, respectively, in order to improve the accuracy of the combined score calculation, and then select a virtual bone surface that is more closely matched to the original bone surface.

[0090] In an optional embodiment, the virtual bone surface that fits the original bone surface is used for positioning, and the repaired three-dimensional joint prosthesis model is fitted and installed on the target bone, including:

[0091] Step S802, positioning using the virtual bone surface that fits the original bone surface to determine the characteristic marking points and the reserved connection ports;

[0092] Step S804, according to the characteristic marking points and the reserved connection ports, the repaired three-dimensional joint prosthesis model is fitted and installed on the target bone.

[0093] Optionally, the above-mentioned characteristic marking points (such as doctor / patient markers) may be determined by, but not limited to, infrared light ball arrays (active / passive), QR codes, stripe sequences, etc.

[0094] Optionally, the above-mentioned reserved interface may be, but is not limited to, a threaded interface, or other forms of connection interfaces.

[0095] Optionally, the connection position and / or direction between the repaired three-dimensional joint prosthesis model and the target bone is uniquely determined, and a variety of connection methods between the repaired three-dimensional joint prosthesis model and the target bone can be designed through the reserved connection port.

[0096] In an optional embodiment, the positioning navigation method in the above surgery can be applied to a directional device for shoulder arthroplasty, such as Figure 3 As shown, the orientation device at least includes: a bone surface fitting module, a doctor / patient marker (i.e., a characteristic marking point), a positioning module, a processing module, a display module, and a storage module. Figure 4a As shown) is used to reverse engineer a three-dimensional joint prosthesis model of the patient's bones based on the medical imaging data of the patient obtained in advance, and to repair and improve the three-dimensional joint prosthesis model. After meeting the requirements of the customized processing system, a tool is designed that can complement and match the original bone surface of the patient, wherein the bone surface fitting module has a reserved interface in the form of threads and the like. The doctor / patient Marker is connected to the bone surface fitting module through the reserved interface, wherein the doctor / patient Marker can be, but is not limited to, an infrared light ball array (active / passive), a QR code, a stripe sequence, and other feature marking points with the same technical principle; the connection position and connection direction between the doctor / patient Marker and the bone surface fitting module are unique, or a variety of different connection methods can be designed through the preset interface; optionally, the connection method (i.e., the spatial conversion relationship) between the doctor / patient Marker and the bone surface fitting module is obtained by consulting the pre-designed 3D processing file, Figure 4b A connection method between the above-mentioned doctor / patient marker and the above-mentioned bone surface fitting module is shown. The above-mentioned positioning module is used to detect and identify the array pattern, and the identified array pattern can be converted into a three-dimensional spatial coordinate for positioning and tracking the patient's bones and surgical tools. The above-mentioned communication module is used to process the medical image data acquired by the above-mentioned positioning module, and output the processed medical image data to the above-mentioned data processing module. The above-mentioned data processing module is used to read the underlying data pre-stored in the storage module, including tool models, planning files and other data required for surgical navigation, and receive the above-mentioned processed medical image data output by the above-mentioned communication module, and after processing the above-mentioned underlying data and the above-mentioned processed medical image data, generate a rendering picture and transmit it to the display module. The above-mentioned display module dynamically visualizes the surgical tools, patient bones, and three-dimensional joint prosthesis models, and quantitatively displays the implantation position and implantation angle of the three-dimensional joint prosthesis model after repair.

[0097] It should be noted that, in the preoperative planning stage, the patient's skeletal model is mainly used, and the medical imaging data obtained through one or more modalities such as CT images, MRI, etc. are reversed to obtain the above-mentioned patient's skeletal model. In the preoperative planning stage, the three-dimensional joint prosthesis model can be marked with the center point of the glenoid cavity, or other points / lines / axes with guiding value on the 3D model. The spatial information of preoperative planning can be introduced through the bone surface fitting module and the fixed assembly relationship of the optical positioning doctor / patient marker, such as Figure 4c As shown, the diagram only shows the implantation direction and the center of the glenoid cavity. Other spatial information of the preoperative planning can also be displayed. Based on the above preoperative planning, the following can be finally obtained: Figure 4d The humerus is shown after osteotomy.

[0098] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0100] Example 2

[0101] In this embodiment, a positioning navigation device for surgery is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0102] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing the positioning navigation method in the above-mentioned surgery. Figure 5 FIG. 1 is a schematic diagram of a positioning navigation device in surgery according to an embodiment of the present invention. Figure 5 As shown, the positioning navigation device in the above surgery includes: an acquisition module 40, a production module 42, a selection module 44, and an installation module 46, wherein:

[0103] An acquisition module 40 is used to acquire medical image data of a target object, wherein the medical image data at least includes a target bone of the target object and an original bone surface of the target bone;

[0104] A production module 42, used for producing a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data;

[0105] A selection module 44 is used to select a virtual bone surface that fits the original bone surface according to the medical image data;

[0106] The installation module 46 is used to use the virtual bone surface that fits the original bone surface for positioning, and fit the repaired three-dimensional joint prosthesis model to the target bone.

[0107] In an embodiment of the present invention, a positioning and navigation method during surgery is adopted, and an acquisition module 40 is set to obtain medical image data of the target object, wherein the above-mentioned medical image data at least includes the target bone of the above-mentioned target object and the original bone surface of the above-mentioned target bone; a production module 42 is used to produce a three-dimensional joint prosthesis model adapted to the above-mentioned target bone according to the above-mentioned medical image data; a selection module 44 is used to select a virtual bone surface that fits well with the above-mentioned original bone surface according to the above-mentioned medical image data; an installation module 46 is used to use the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface for positioning, and fit the repaired three-dimensional joint prosthesis model with the above-mentioned target bone to achieve the purpose of accurately obtaining the installation positioning and automatically completing the fitting installation of the three-dimensional joint prosthesis model, thereby achieving the technical effect of improving the positioning and navigation efficiency and installation accuracy during surgery, and then solving the technical problems of low installation efficiency and inaccurate positioning in the positioning and navigation methods during surgery in the related art.

[0108] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0109] It should be noted that the acquisition module 40, the production module 42, the selection module 44, and the installation module 46 correspond to steps S102 to S108 in Example 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the modules as part of the device can be run in a computer terminal.

[0110] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in Example 1, which will not be repeated here.

[0111] The above-mentioned positioning navigation device during surgery may also include a processor and a memory. The above-mentioned acquisition module 40, production module 42, selection module 44, installation module 46, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0112] The processor includes a kernel, which retrieves the corresponding program unit from the memory. The kernel may be one or more. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory includes at least one memory chip.

[0113] According to an embodiment of the present application, a joint prosthesis installation robot is also provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute any one of the above-mentioned intraoperative positioning and navigation methods through the computer program.

[0114] According to an embodiment of the present application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein when the program is run, any one of the positioning and navigation methods in surgery is executed.

[0115] According to an embodiment of the present application, an embodiment of a computer program product is also provided, which, when executed on a data processing device, is suitable for executing a program that initializes any of the steps of the intraoperative positioning navigation method described above.

[0116] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: dividing the above-mentioned joint bone surface into a plurality of different sub-bone surfaces according to the above-mentioned medical image data; obtaining a plurality of candidate bone surfaces corresponding to the above-mentioned joint bone surface, and dividing the plurality of the above-mentioned candidate bone surfaces into a plurality of candidate sub-bone surfaces corresponding to the plurality of the above-mentioned sub-bone surfaces; obtaining a palpable score for each of the above-mentioned candidate bone surfaces, wherein the above-mentioned palpable score is used to reflect the possibility of contacting the bone surface during the prosthesis replacement surgery, and is related to the patient's condition, cartilage, usable bone surface, medical The method is related to the surgical approach; performing specificity calculations on multiple candidate sub-bone surfaces according to the medical imaging data to obtain a specificity value corresponding to each of the above-mentioned candidate sub-bone surfaces, wherein the above-mentioned specificity calculations include: specific structure scoring, flatness calculations, and symmetry parameter calculations; performing image confidence assessments on the multiple above-mentioned candidate sub-bone surfaces according to the medical imaging data to obtain confidence values ​​related to the multiple above-mentioned candidate sub-bone surfaces; and selecting the above-mentioned virtual bone surface that fits the above-mentioned original bone surface from the multiple above-mentioned candidate bone surfaces according to the above-mentioned palpable scores, the above-mentioned confidence values, and the above-mentioned specificity values.

[0117] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: based on the multiple specific values ​​corresponding to each of the above-mentioned alternative bone surfaces, calculating the joint specificity value of each of the above-mentioned alternative bone surfaces; based on the multiple confidence values ​​corresponding to each of the above-mentioned alternative bone surfaces, calculating the joint confidence value of each of the above-mentioned alternative bone surfaces; according to the above-mentioned accessible score, the above-mentioned joint confidence value and the above-mentioned joint specificity value, calculating the joint score of each of the above-mentioned alternative bone surfaces; according to the above-mentioned joint score, selecting the above-mentioned virtual bone surface that fits the above-mentioned original bone surface from the multiple above-mentioned alternative bone surfaces.

[0118] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining point cloud data by reverse engineering based on the above-mentioned medical imaging data; scoring the specific structure of each of the above-mentioned candidate sub-bone surfaces based on the above-mentioned point cloud data to obtain a first score, wherein the above-mentioned specific structure is a structure containing concave features and protrusion characteristics; scoring the flatness of each of the above-mentioned candidate sub-bone surfaces based on the above-mentioned point cloud data to obtain a second score, wherein the above-mentioned flatness is used to reflect the degree of convergence between the overall structure of the above-mentioned candidate sub-bone surface and the plane; scoring the symmetry of each of the above-mentioned candidate sub-bone surfaces based on the above-mentioned point cloud data to obtain a third score, wherein the above-mentioned symmetry is used to reflect the overall symmetry of the above-mentioned candidate sub-bone surface; assigning a weight to the above-mentioned first score, the above-mentioned second score and the above-mentioned third score respectively, to obtain a first weight value, a second weight value and a third weight value; and calculating the specificity value corresponding to each of the above-mentioned candidate sub-bone surfaces based on the above-mentioned first score, the above-mentioned second score, the above-mentioned third score, the above-mentioned first weight value, the above-mentioned second weight value and the above-mentioned third weight value.

[0119] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the above-mentioned medical imaging data; performing image confidence evaluation on multiple candidate sub-bone surfaces based on the above-mentioned average signal-to-noise ratio, and obtaining the above-mentioned confidence values ​​related to the above-mentioned multiple candidate sub-bone surfaces.

[0120] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: using a segmentation frame to segment the three-dimensional images of different layers in the above-mentioned medical image data to obtain multiple segmented local images; performing denoising processing on the multiple local images respectively to obtain multiple processed local images, wherein the above-mentioned denoising processing includes but is not limited to mean filtering processing, adaptive Wiener filtering processing, median filtering processing, and Bayesian filtering processing; calculating multiple first signal-to-noise ratios corresponding to the multiple processed local images; after moving the above-mentioned segmentation frame by a predetermined number of pixel steps, using the next segmentation frame to repeat the above-mentioned segmentation processing and the above-mentioned denoising processing to obtain a second signal-to-noise ratio, until the above-mentioned segmentation frame coincides with the above-mentioned next segmentation frame; and calculating the above-mentioned average signal-to-noise ratio of each of the above-mentioned pixels in the above-mentioned processed local images based on the above-mentioned first signal-to-noise ratio and the above-mentioned second signal-to-noise ratio.

[0121] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: assigning a weight to the above-mentioned accessibility score, the above-mentioned joint confidence value and the above-mentioned joint specificity value respectively, to obtain a fourth weight value, a fifth weight value and a sixth weight value; and calculating the above-mentioned joint score of each of the above-mentioned alternative bone surfaces based on the above-mentioned accessibility score, the above-mentioned joint confidence value, the above-mentioned joint specificity value, the above-mentioned fourth weight value, the above-mentioned fifth weight value and the above-mentioned sixth weight value.

[0122] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: using the above-mentioned virtual bone surface that fits well with the above-mentioned original bone surface for positioning to determine characteristic marking points and reserved connection ports; according to the above-mentioned characteristic marking points and the above-mentioned reserved connection ports, fitting the above-mentioned repaired three-dimensional joint prosthesis model with the above-mentioned target bone, wherein the connection position and / or direction of the above-mentioned repaired three-dimensional joint prosthesis model with the above-mentioned target bone is uniquely determined.

[0123] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0124] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0127] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0129] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A positioning navigation method during surgery, characterized in that: include: Acquire medical image data of a target object, wherein the medical image data at least includes a target bone of the target object and an original bone surface of the target bone; Produce a three-dimensional joint prosthesis model adapted to the target bone according to the medical imaging data; Selecting a virtual bone surface that fits the original bone surface according to the medical image data; Positioning is performed using the virtual bone surface that fits closely with the original bone surface; Among them, if the virtual bone surface is a joint bone surface, a virtual bone surface that fits the original bone surface is selected according to the medical image data, including: dividing the joint bone surface into a plurality of different sub-bone surfaces according to the medical image data; obtaining a plurality of candidate bone surfaces corresponding to the joint bone surface, and dividing the plurality of candidate bone surfaces into a plurality of candidate sub-bone surfaces corresponding to the plurality of sub-bone surfaces; obtaining a touchability score for each of the candidate bone surfaces, wherein the touchability score is used to reflect the possibility of contacting the bone surface during the prosthesis replacement surgery, and is related to the patient's condition, cartilage, and available bone surface. , which is related to the doctor's surgical approach; performing specificity calculations on multiple candidate sub-bone surfaces according to the medical imaging data to obtain specificity values ​​corresponding to each of the candidate sub-bone surfaces, wherein the specificity calculations include: specific structure scoring, flatness calculations, and symmetry parameter calculations; performing image confidence evaluations on multiple candidate sub-bone surfaces according to the medical imaging data to obtain confidence values ​​related to multiple candidate sub-bone surfaces; selecting the virtual bone surface that fits the original bone surface from the multiple candidate bone surfaces according to the palpable score, the confidence value, and the specificity value.

2. The method according to claim 1, characterized in that According to the palpable score, the confidence value and the specificity value, selecting the virtual bone surface that fits the original bone surface from the plurality of candidate bone surfaces, comprising: Based on the multiple specific values ​​corresponding to each candidate bone surface, a joint specific value of each candidate bone surface is calculated; Based on the multiple confidence values ​​corresponding to each candidate bone surface, a joint confidence value of each candidate bone surface is calculated; Calculating a joint score for each candidate bone surface according to the palpable score, the joint confidence value and the joint specificity value; According to the joint score, the virtual bone surface that fits the original bone surface is selected from the multiple candidate bone surfaces.

3. The method according to claim 1, characterized in that Specificity calculations are performed on a plurality of candidate sub-bone surfaces respectively according to the medical image data to obtain specificity values ​​corresponding to each candidate sub-bone surface, including: Obtaining point cloud data in reverse according to the medical imaging data; Scoring the specific structure of each candidate sub-bone surface according to the point cloud data to obtain a first score, wherein the specific structure is a structure including concave features and protrusion features; Scoring the flatness of each candidate sub-bone surface according to the point cloud data to obtain a second score, wherein the flatness is used to reflect the degree of closeness between the entire candidate sub-bone surface and the plane; Scoring the symmetry of each candidate sub-bone surface according to the point cloud data to obtain a third score, wherein the symmetry is used to reflect the overall symmetry of the candidate sub-bone surface; Assigning a weight to the first score, the second score, and the third score respectively, to obtain a first weight value, a second weight value, and a third weight value; The specificity value corresponding to each of the candidate sub-bone surfaces is calculated based on the first score, the second score, the third score, the first weight value, the second weight value and the third weight value.

4. The method according to claim 1, characterized in that: Performing image confidence evaluation on the plurality of candidate sub-bone surfaces according to the medical image data to obtain confidence values ​​related to the plurality of candidate sub-bone surfaces, including: Calculating an average signal-to-noise ratio of each pixel in three-dimensional images of different layers in the medical image data; Image confidence evaluation is performed on multiple candidate sub-bone surfaces according to the average signal-to-noise ratio to obtain the confidence values ​​related to the multiple candidate sub-bone surfaces.

5. The method according to claim 4, characterized in that Calculating the average signal-to-noise ratio of each pixel in the three-dimensional images of different layers in the medical image data, comprising: Using a segmentation frame to segment the three-dimensional images of different layers in the medical image data to obtain a plurality of segmented local images; Performing denoising processing on the plurality of local images respectively to obtain a plurality of processed local images, wherein the denoising processing includes but is not limited to mean filtering processing, adaptive Wiener filtering processing, median filtering processing, and Bayesian filtering processing; Calculating a plurality of first signal-to-noise ratios corresponding to a plurality of the processed local images; After the segmentation frame is moved by a predetermined number of pixel steps, the segmentation process and the denoising process are repeated with a next segmentation frame to obtain a second signal-to-noise ratio, until the segmentation frame overlaps with the next segmentation frame; The average signal-to-noise ratio of each pixel in the processed local image is calculated according to the first signal-to-noise ratio and the second signal-to-noise ratio.

6. The method according to claim 2, characterized in that The combined score of each candidate bone surface is calculated according to the palpable score, the combined confidence value and the combined specificity value, including: Assigning a weight to the accessibility score, the joint confidence value and the joint specificity value respectively, to obtain a fourth weight value, a fifth weight value and a sixth weight value; The joint score of each of the candidate bone surfaces is calculated based on the palpability score, the joint confidence value, the joint specificity value, the fourth weight value, the fifth weight value and the sixth weight value.

7. A positioning navigation device during surgery, characterized in that: include: An acquisition module, used for acquiring medical image data of a target object, wherein the medical image data at least includes a target bone of the target object and an original bone surface of the target bone; A production module, used for producing a three-dimensional joint prosthesis model adapted to the target bone according to the medical image data; A selection module, for selecting a virtual bone surface that fits the original bone surface according to the medical image data; An installation module, used for positioning using the virtual bone surface that fits closely with the original bone surface; Wherein, the selection module is also used for: if the virtual bone surface is a joint bone surface, dividing the joint bone surface into a plurality of different sub-bone surfaces according to the medical image data; obtaining a plurality of candidate bone surfaces corresponding to the joint bone surface, and dividing the plurality of candidate bone surfaces into a plurality of candidate sub-bone surfaces corresponding to the plurality of sub-bone surfaces; obtaining a touchability score of each candidate bone surface, wherein the touchability score is used to reflect the possibility of contacting the bone surface during the prosthetic replacement surgery, and is related to the patient's condition, cartilage, usable bone surface, and doctor's surgical approach; performing specificity calculations on the plurality of candidate sub-bone surfaces according to the medical image data, respectively, to obtain a specificity value corresponding to each candidate sub-bone surface, wherein the specificity calculation includes: specific structure scoring, flatness calculation, and symmetry parameter calculation; performing image confidence evaluation on the plurality of candidate sub-bone surfaces according to the medical image data, to obtain confidence values ​​related to the plurality of candidate sub-bone surfaces; selecting the virtual bone surface that fits the original bone surface from the plurality of candidate bone surfaces according to the touchability score, the confidence value, and the specificity value.

8. A joint prosthesis installation robot, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the intraoperative positioning navigation method according to any one of claims 1 to 6 through the computer program.

Images