Oral implant accuracy evaluation method, system and terminal equipment

Abstract

The embodiment of the present application provides a method, system and terminal device for evaluating the accuracy of oral implants, the method comprising: obtaining a preoperative CBCT image of the patient's oral cavity with a positioning guide, identifying optical positioning markers in the preoperative CBCT image to establish a preoperative local coordinate system; implanting the implant into the patient's oral cavity according to the planned implant implantation position, the implant implantation position including the expected position of the apex point and the implantation point of the implant in the preoperative local coordinate system; obtaining a postoperative CBCT image of the patient's oral cavity with a positioning guide; identifying optical positioning markers in the postoperative CBCT image to establish a postoperative local coordinate system, identifying the actual position of the apex point and the implantation point; calculating the position deviation corresponding to the apex point and the implantation point and the angle deviation of the implant according to the expected position and the actual position. The evaluation method can quickly, accurately and objectively evaluate the implantation accuracy of the implant.

Description

Technical Field

[0001] The present application relates to the field of oral implant technology, and in particular to an oral implant accuracy evaluation method, system and terminal device. Background Art

[0002] Robot-assisted oral implantation is a popular technology field that has emerged in recent years. Robot-assisted implantation can improve the accuracy of implantation. The supporting navigation system can display the implantation status in real time, providing objective and quantifiable data and indicators for doctors to judge the accuracy of implantation. There are currently two common methods for evaluating the accuracy of implantation assisted by robot navigation systems: (1) The first method is based on the evaluation of three-dimensional mesh model fusion. The fusion of three-dimensional mesh models reconstructed only based on CBCT images (i.e., cone beam CT images) is affected by the reconstruction accuracy and has large errors. There are both three-dimensional models reconstructed by CBCT and three-dimensional models reconstructed by oral scans. The process is complicated, time-consuming and expensive. (2) The second method is based on the evaluation after fusion of CBCT data. The accuracy of image fusion is not high. After fusion, people need to manually select appropriate cross-sectional views to mark the apex and implantation point of the implant. The operation process is complicated and the errors caused by human operation will directly affect the accuracy of the measurement results. Summary of the invention

[0003] In view of this, the embodiments of the present application provide an oral implant accuracy evaluation method, system and terminal device.

[0004] In a first aspect, the present application provides an oral implant accuracy evaluation method, comprising:

[0005] Acquire a preoperative CBCT image of the patient's oral cavity with a positioning guide plate, wherein the positioning guide plate is provided with a plurality of optical positioning marking points;

[0006] Identify each of the optical positioning marker points in the preoperative CBCT image, and establish a preoperative local coordinate system formed by the optical positioning marker points;

[0007] implanting the implant into the patient's oral cavity according to the planned implant implantation position, wherein the implant implantation position includes the apex point of the implant and the expected position of the implantation point in the preoperative local coordinate system;

[0008] Acquire a postoperative CBCT image of the patient's oral cavity with the positioning guide;

[0009] Identify each of the optical positioning mark points in the postoperative CBCT image, establish a postoperative local coordinate system formed by the optical positioning mark points, and identify the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system;

[0010] According to the expected position and the actual position of the root apex point and the implantation point, the position deviation corresponding to the root apex point and the implantation point and the angle deviation of the implant are calculated.

[0011] In a second aspect, the present application also provides an oral implant accuracy evaluation system, including:

[0012] An image acquisition module, used to acquire a preoperative CBCT image of the patient's oral cavity with a positioning guide, wherein the positioning guide is provided with a plurality of optical positioning marking points;

[0013] A coordinate system establishment module, used for identifying each of the optical positioning mark points in the preoperative CBCT image, and establishing a preoperative local coordinate system formed by the optical positioning mark points;

[0014] An implant control module, used for implanting the implant into the patient's oral cavity according to the planned implant implantation position, wherein the implant implantation position includes the apex point of the implant and the expected position of the implantation point in the preoperative local coordinate system;

[0015] The image acquisition module is also used to acquire a postoperative CBCT image of the patient's oral cavity with the positioning guide plate;

[0016] An implant position recognition module, used to recognize each of the optical positioning mark points in the postoperative CBCT image, establish a postoperative local coordinate system formed by the optical positioning mark points, and recognize the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system;

[0017] The deviation calculation module is used to calculate the position deviation corresponding to the root apex point and the implantation point and the angle deviation of the implant according to the expected position and the actual position of the root apex point and the implantation point.

[0018] In a third aspect, an embodiment of the present application further provides a terminal device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the above-mentioned method for evaluating the implantation accuracy of an oral implant surgery robot.

[0019] In a fourth aspect, an embodiment of the present application further provides a readable storage medium storing a computer program, which, when executed on a processor, implements the above-mentioned method for evaluating the implantation accuracy of an oral implant surgery robot.

[0020] The embodiments of the present application have the following beneficial effects:

[0021] The oral implant accuracy evaluation method of the embodiment of the present application obtains a preoperative CBCT image of the patient's oral cavity with a positioning guide, uses optical positioning marking points to establish a preoperative local coordinate system in the preoperative CBCT image, and after the implant is implanted in the patient's oral cavity, uses the same optical positioning marking points to establish a postoperative local coordinate system in the postoperative CBCT image, and identifies the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system, and then uses the expected positions of the apex point and the implantation point of the implant in the preoperative local coordinate system and the actual positions in the postoperative local coordinate system to calculate the deviation, so as to obtain the implantation accuracy of the implant. This method is based on oral CBCT images and can quickly, accurately and objectively evaluate the implantation accuracy of the implant. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart showing the oral implant accuracy evaluation method according to an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the structure of a positioning guide plate with optical positioning marking points according to an embodiment of the present application is shown;

[0025] Figure 3 A flowchart showing construction of a local coordinate system in a preoperative CBCT image in an embodiment of the present application is shown;

[0026] FIG4(a) and FIG4(b) respectively show the comparison diagrams of the effects of different window width and window position settings;

[0027] Figure 5 A schematic diagram showing a local coordinate system in a preoperative CBCT image according to an embodiment of the present application is shown;

[0028] FIG6( a ) and FIG6( b ) respectively show the top cross section of the implant and the schematic structural diagrams of the apex and implantation point of the implant according to the embodiment of the present application;

[0029] Figure 7 A flow chart showing the position identification of the root apex point and the implantation point according to an embodiment of the present application;

[0030] Figure 8 The section and coordinate system direction of the CBCT image of the embodiment of the present application are shown;

[0031] Fig. 9A flow chart of target cross-sectional image screening according to an embodiment of the present application is shown;

[0032] Fig.10 Schematic diagrams showing different slopes of a local image of an implant region according to an embodiment of the present application;

[0033] Fig.11 A schematic diagram showing the Harris corner point detection of the implant corner point according to an embodiment of the present application;

[0034] Fig.12 A flow chart showing the actual positions of the root apex point and the implantation point according to an embodiment of the present application is shown;

[0035] Fig.13 A flowchart of the planting deviation calculation of an embodiment of the present application is shown;

[0036] Fig.14 A structural schematic diagram of an oral implant accuracy evaluation system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0038] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0039] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0040] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0041] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0042] Please refer to Figure 1 , is a flow chart of the oral implant accuracy evaluation method proposed in the embodiment of the present application. Exemplarily, the oral implant accuracy evaluation method includes the following steps S110 to S160:

[0043] Step S110, obtaining a preoperative CBCT image of the patient's oral cavity with a positioning guide, wherein the positioning guide is provided with a plurality of optical positioning marking points.

[0044] The positioning guide plate refers to a simple mold customized according to the patient's oral condition. Usually, the doctor designs a guide plate based on the patient's oral CT scan, which can be placed in the mouth to occlude the teeth and mark the corresponding implant position. In this embodiment, the positioning guide plate is provided with some optical positioning markers (Markers), also known as optical positioning devices, which are mainly implemented by using multiple iron beads, such as Figure 2 Correspondingly, these optical positioning markers will appear circular in the CBCT image.

[0045] Demonstratively, the patient can be photographed with the positioning guide before the implant surgery to obtain the original CBCT image, and then the original CBCT image is de-artifacted to obtain the above-mentioned preoperative CBCT image. The acquired CBCT image consists of different tomographic image sequences, and the serial numbers of these tomographic image sequences are from 0 to N, and the serial numbers are automatically generated by CBCT shooting, wherein the serial number represents the position of the tomographic image in the Z-axis direction in the CBCT image space. It is worth noting that the pixel interval of the captured CBCT image is required to be less than 0.3 mm to ensure the accuracy of implantation, etc.

[0046] Step S120, identifying each optical positioning mark point in the preoperative CBCT image, and establishing a preoperative local coordinate system formed by the optical positioning mark points.

[0047] The preoperative local coordinate system refers to a local coordinate system established in the preoperative CBCT image based on the optical positioning markers. The term "preoperative" is used here mainly to distinguish it from the local coordinate system established in the postoperative CBCT image mentioned later. In this embodiment, the positions of the optical positioning markers in the preoperative CBCT image are first identified, and then a local coordinate system is constructed using these optical positioning markers, which is used as a reference coordinate system for implantation and evaluation.

[0048] like Figure 3 As shown, in one implementation, step S120 includes the following sub-steps S210 to S240:

[0049] Sub-step S210 , converting the formats of different slice images of the preoperative CBCT image to obtain cross-sectional images of corresponding views.

[0050] Typically, captured CBCT images are usually output in DICOM format. However, the grayscale value (i.e., CT value) of the pixels of DICOM format images is usually -1024 to 3071, which is beyond the limit of human eye recognition. Therefore, it needs to be converted into a PNG format image in the range of 0-255.

[0051] Exemplarily, when converting the format of the tomographic image, the upper and lower boundary values ​​of the required CT value range can be determined according to the set window position X and window width Y. For example, the upper boundary value is X+Y / 2, and the lower boundary value is XY / 2; then, the CT value of the tomographic image in the range of [XY / 2, X+Y / 2] is linearly mapped to the range of 0-255, and the CT value below the lower boundary value is set to 0, and the CT value of the upper boundary value is set to 255, thereby obtaining an image in PNG format. Among them, the image in PNG format is an image parallel to the XY plane, and therefore is also a cross-sectional image of the CBCT image. It can be understood that in the process of CBCT imaging, the higher the density of the object or the higher the radiopacity (performance of preventing X-ray penetration), the higher its CT value in the CBCT image. By setting the window width and window position, only the image area formed by iron beads and glue can be retained in the PNG format image. For example, when the window level is set to 862 and the window width is set to 2499, a slice image as shown in FIG4(a) can be obtained; and when the window level is set to 2715 and the window width is set to 884, a slice image showing only iron beads and glue with radiation-blocking properties can be obtained as shown in FIG4(b).

[0052] Sub-step S220, based on the diameter of the circle of the optical positioning mark point in the preoperative CBCT image, using Hough circle transform to detect the circles existing in each cross-sectional image and the coordinates of the center of each circle.

[0053] Sub-step S230, according to the coordinates of the center of the same circle in different slices and the serial number of the corresponding slice, obtain the three-dimensional coordinates of the center of the sphere corresponding to the current circle in the preoperative CBCT image.

[0054] Among them, the DICOM format image can reflect the real volume size of the object, and its principle is to represent the image of the tomographic view of the object. Assuming that the pixel interval of the CBCT image is x millimeters, and the diameter of the iron bead is y millimeters, the number of pixels occupied by the iron bead in the CBCT image (that is, the diameter of the circle formed) is D=y / x. Therefore, according to the number of occupied pixels, the radius range of the circle can be set to [1, D / 2+1], where the minimum radius is 1 and the maximum is D / 2+1. It can be understood that by expanding the detection radius range, the circle formed by the iron bead in different tomographic images can be detected.

[0055] Furthermore, the coordinate values ​​of the centers of these circles on the X-axis and Y-axis can be obtained by using the Hough circle transform (i.e., Hough circle transform), and the coordinate value of the Z-axis is represented by the serial number of the corresponding tomographic image. Among them, if the absolute value of the difference between the coordinate values ​​of the X-axis and Y-axis of the center of a circle is less than D / 2, it is considered to be formed by the same iron bead. Then, the three-dimensional coordinates of an iron bead can be calculated by the average value of the X, Y, and Z coordinate values ​​of these circles belonging to the same circle. Finally, the X, Y, and Z coordinate values ​​of the detected iron bead are multiplied by the voxel spacing of the CBCT image in the X, Y, and Z directions to obtain the three-dimensional coordinate value of the iron bead in the CBCT image. For example, if the voxel spacing of the CBCT image in the X, Y, and Z directions is (XS, YS, ZS), the three-dimensional coordinates of the iron bead in the CBCT image are (X*XS, Y*YS, Z*ZS).

[0056] As a preferred solution, considering the accuracy of some image recognition, before selecting the sphere center for establishing the local coordinate system, objects that are mistakenly identified as iron balls will be filtered out. For example, if the number of identified sphere centers exceeds the number of the above-mentioned optical positioning mark points, the centroids of all sphere centers are calculated by clustering algorithms, and the sphere centers farthest from the centroid are deleted until the number of remaining sphere centers meets the requirements.

[0057] Sub-step S240, selecting three sphere centers that are not on the same straight line according to the three-dimensional coordinates, and constructing a preoperative local coordinate system in the preoperative CBCT image.

[0058] For example, three sphere centers that are not on the same straight line are randomly selected from the identified sphere centers (referred to as sphere centers) to establish a local coordinate system. For example, for the three sphere centers A, B, and C, Figure 5As shown, A is taken as the origin, the vector formed from point A to point B is taken as the X axis, the vector formed from point A to point C is taken as the Y axis, the cross product of vectors X and Y is taken as the Z axis, and then the cross product of Z and Y is used to obtain the new X' axis, so as to combine into a rectangular coordinate system S1, that is, the above-mentioned preoperative local coordinate system. It can be understood that by solving the transformation matrix Matrix1 from the global coordinate system S of the CBCT image to the local coordinate system S1, it can be used to calculate the coordinate value of the implant in the local coordinate system S1 formed by the iron bead.

[0059] Step S130, implanting the implant into the patient's oral cavity according to the planned implant implantation position, wherein the implant implantation position includes the apex point of the implant and the expected position of the implantation point in the preoperative local coordinate system.

[0060] Therefore, based on the expected position of the implant planned by the preoperative CBCT image, the implant is implanted at the corresponding position in the patient's mouth. For example, FIG6(a) shows the top cross section of the implant, and FIG6(b) shows the position of the apex point and the implantation point. For example, the expected position of the implant (STL model) in the preoperative CBCT image can be planned on the robot navigation system software, and the coordinate values ​​of the implantation point P1 and the apex point P2 of the implant are recorded, and then multiplied by the above-mentioned transformation matrix Matrix1, the coordinate values ​​of the implantation point P1 and the apex point P2 in the preoperative local coordinate system S1 formed by the iron bead can be obtained, which are recorded as P11 and P21 here.

[0061] Step S140, obtaining a postoperative CBCT image of the patient's oral cavity with the positioning guide.

[0062] After the implant surgery, the patient can take the above-mentioned positioning guide again to take the original CBCT image after surgery, and perform artifact removal operations on the original CBCT image after surgery to obtain the postoperative CBCT image. It can be understood that the acquisition method and requirements of the postoperative CBCT image are the same as those of the preoperative CBCT image, and will not be repeated here.

[0063] Step S150, identifying each optical positioning mark point in the postoperative CBCT image, establishing a postoperative local coordinate system formed by the optical positioning mark points, and identifying the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system.

[0064] Similarly, the above step S120 can be used to identify each optical positioning mark point in the postoperative CBCT image, and establish the corresponding postoperative local coordinate system S2, and the transformation matrix Matrix2 from the global coordinate system of the postoperative CBCT image to the local coordinate system S2 can be obtained. Then, the position of the apex point and the implantation point of the postoperative implant in the postoperative local coordinate system S2 is identified, such as Figure 7 As shown, in one embodiment, the following sub-steps S310 to S340 are included:

[0065] Sub-step S310, multi-planar reconstruction is performed on the postoperative CBCT image to obtain different re-sliced ​​tomographic images. Multi-planar reconstruction (MPR) refers to combining DICOM format images composed of multiple cross-sections into a three-dimensional image, and then re-slicing from the sagittal plane to generate multiple new sagittal tomographic images. For example, the DICOM section and coordinate system direction can refer to Figure 8 shown.

[0066] Sub-step S320, convert each tomographic image to obtain a cross-sectional image of the corresponding view. The implant is mostly made of steel or titanium, which has a similar density and CT value to the iron bead. Therefore, the processing operation and the setting of the window width and window position can be specifically referred to in the above step S210, which will not be repeated here.

[0067] Sub-step S330, using a contour detection algorithm to find the largest contour in each cross-sectional image, and obtain the bounding box size of each largest contour. For example, the contour detection algorithm FindContours in OpenCV can be used to find the largest contour in each PNG image.

[0068] Sub-step S340 , filtering all cross-sectional images according to the actual size of the implant and the size of the bounding box of the maximum contour to obtain candidate cross-sectional images containing the implant.

[0069] For example, if the actual width of the implant is width and the length is length, if the voxel of the CBCT image is a cube, that is, the spacing (denoted as Spacing) in the three directions of X, Y, and Z is the same, then the width W of the implant in the cross-sectional image (PNG format) is Width / Spacing, and the length L is Length / Spacing. The filtering accuracy A (range 0 to 1) is specified, and the contours whose width is not in [W*A, W*(2-A)] and whose length is not in [L*A, L*(2-A)] are filtered, thereby including the candidate cross-sectional image of the implant.

[0070] Sub-step S350, selecting a target cross-sectional image closest to the central section of the implant from the candidate cross-sectional images.

[0071] like Fig. 9 As shown, in one embodiment, the screening process includes the following sub-steps S351 to S354:

[0072] Sub-step S351, extracting the implant area in each candidate cross-sectional image to obtain the corresponding local image; sub-step S352, calculating the implant slope in the local image, and rotationally correcting the local image according to the implant area and implant slope of the implant in the oral cavity to obtain a corrected image; sub-step S353, scaling the corrected image according to the size of the standard image, and calculating the structural similarity between the scaled image and the standard image; sub-step S354, selecting the candidate cross-sectional image corresponding to the maximum value from each structural similarity as the target cross-sectional image closest to the central section of the implant.

[0073] Usually, the same implant will form multiple cross-sectional images in the DICOM format image, and the implantation point and the root apex are both located on the most central cross-sectional image. Therefore, it is necessary to make a standard implant center cross-sectional image, which can be made using an STL model. When screening, extract the implant area in the cross-sectional image, that is, crop to obtain the corresponding local image, and calculate the corresponding slope K, such as the rotation angle, etc. Fig.10 As shown; then, the image rotation correction is performed according to the implantation area of ​​the implant in the oral cavity (such as the maxillary bone or the mandibular bone), and then the extracted image is scaled, that is, transformed into the same pixel size as the standard image, and then the SSIM (structural similarity) index is used to compare the similarity between the current scaled image and the standard image, and the image with the largest SSIM index is used as the final section image where the implant is located.

[0074] Sub-step S360, detecting multiple corner points of the implant in the target cross-sectional image, and determining the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system from the multiple corner points.

[0075] For example, the Harris corner detection algorithm can be used to detect the corner points (boundary points) of the implant in the PNG image, such as Fig.11 The actual positions of the apex and implantation points are then determined from these corner points, as shown in Fig.12 As shown, the determination process may include the following sub-steps S361 to S364:

[0076] Sub-step S361, calculate the Euclidean distance from each corner point to the origin of the postoperative local coordinate system and select several point pairs with the farthest distance; sub-step S362, determine the first point pair closest to the implantation point and the second point pair closest to the apex point among the several point pairs according to the different opening directions of the implant; sub-step S363, take the coordinate average of the two points close to the implantation point in the first point pair and the second point pair as the coordinate of the implantation point in the local coordinate system; sub-step S364, take the coordinate average of the two points close to the apex point in the first point pair and the second point pair as the coordinate of the apex point in the local coordinate system.

[0077] Specifically, according to the different opening directions of the implant, where the opening is downward in the maxillary bone and upward in the mandibular bone, corresponding to the size of the Y value in the coordinate system, it is possible to determine which point in the point pair is close to the implantation point and which point is close to the apex point of the implant, and then take the average of the coordinate values ​​of the two points in the two point pairs close to the implantation point as the coordinates of the implantation point. Similarly, the coordinates of the apex point of the implant can be obtained.

[0078] It can be understood that the sagittal plane corresponds to the YZ plane of the CBCT image, and the X coordinate value measured by the OpenCV function corresponds to the Y index coordinate value of the CBCT image. The index coordinate value of the implant in the Z axis direction in the CBCT image can be obtained by subtracting the Y coordinate value measured by the OpenCV function from the size of the image Y axis dimension. The index coordinate value of the implant in the X axis direction is determined by the serial number of the PNG image (generated when re-slicing). The coordinate values ​​of the implant point P3 and the apex point P4 in the CBCT image can be obtained by multiplying the measured index coordinate value by the pixel interval of the corresponding coordinate axis on the postoperative CBCT image. Correspondingly, the implant point P3 and the apex point P4 are multiplied by the above-mentioned transformation matrix Matrix2 to obtain their coordinate values ​​in the postoperative local coordinate system S2, which are recorded as P32 and P42 here.

[0079] Step S160, calculating the position deviation corresponding to the apex point and the implantation point and the angle deviation of the implant according to the expected position and the actual position of the apex point and the implantation point.

[0080] like Fig.13 As shown, in one implementation, step S160 includes the following sub-steps S410 to S430:

[0081] Sub-step S410, calculating the Euclidean distance between the expected position and the actual position of the implantation point as the position deviation of the implantation point. Specifically, the Euclidean distance between the points P11 and P32 is used as the distance deviation of the implantation point of the implant.

[0082] Sub-step S420, calculating the Euclidean distance between the expected position and the actual position of the apex point as the position deviation of the apex point. Specifically, the Euclidean distance between the points P21 and P43 is used as the distance deviation of the apex point of the implant.

[0083] Sub-step S430, based on the first vector formed from the implant point to the apex point in the preoperative CBCT image and the second vector formed from the implant point to the apex point in the postoperative CBCT image, calculate the angle between the first vector and the second vector as the angular deviation of the implant. Specifically, the first vector V1 = P21-P11, the second vector V2 = P42-P32, and the angle between the two vectors V1 and V2 is calculated as the angular deviation of the implant. Thus, the accuracy of implantation can be evaluated by the distance deviation between the implant point and the apex point and the size of the angle deviation.

[0084] The oral implant accuracy evaluation method of the embodiment of the present application obtains a preoperative CBCT image of the patient's oral cavity with a positioning guide, uses optical positioning marking points to establish a preoperative local coordinate system in the preoperative CBCT image, and after the implant is implanted in the patient's oral cavity, uses the same optical positioning marking points to establish a postoperative local coordinate system in the postoperative CBCT image, and identifies the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system, and then uses the expected positions of the apex point and the implantation point of the implant in the preoperative local coordinate system and the actual positions in the postoperative local coordinate system to calculate the deviation, so as to obtain the implantation accuracy of the implant. This method is based on oral CBCT images and can quickly, accurately and objectively evaluate the implantation accuracy of the implant.

[0085] Please refer to Fig.14 Based on the oral implant accuracy evaluation method of the above embodiment, the present application embodiment proposes an oral implant accuracy evaluation system 100. Exemplarily, the oral implant accuracy evaluation system 100 includes:

[0086] The image acquisition module 110 is used to acquire a preoperative CBCT image of the patient's oral cavity with a positioning guide, wherein the positioning guide is provided with a plurality of optical positioning marking points.

[0087] The coordinate system establishing module 120 is used to identify each of the optical positioning marker points in the preoperative CBCT image and establish a preoperative local coordinate system formed by the optical positioning marker points.

[0088] The implant control module 130 is used to implant the implant into the patient's oral cavity according to the planned implant implantation position, wherein the implant implantation position includes the apex point of the implant and the expected position of the implantation point in the preoperative local coordinate system.

[0089] The image acquisition module 110 is also used to acquire a post-operative CBCT image of the patient's oral cavity with the positioning guide.

[0090] The implant position identification module 140 is used to identify each of the optical positioning mark points in the postoperative CBCT image, establish a postoperative local coordinate system formed by the optical positioning mark points, and identify the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system.

[0091] The deviation calculation module 150 is used to calculate the position deviation corresponding to the root apex point and the implantation point and the angle deviation of the implant according to the expected position and the actual position of the root apex point and the implantation point.

[0092] It can be understood that the device of this embodiment corresponds to the method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.

[0093] The present application also provides a terminal device, such as a computer. Exemplarily, the terminal device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program, so that the terminal device executes the functions of each module in the above-mentioned oral implant accuracy evaluation method or the above-mentioned oral implant accuracy evaluation system.

[0094] The present application also provides a readable storage medium for storing the computer program used in the above-mentioned terminal device.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0096] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0097] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a smart phone, 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 application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0098] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for evaluating the accuracy of oral implantation, characterized in that: include: Acquire a preoperative CBCT image of the patient's oral cavity with a positioning guide plate, wherein the positioning guide plate is provided with a plurality of optical positioning marking points; Identify each of the optical positioning marker points in the preoperative CBCT image, and establish a preoperative local coordinate system formed by the optical positioning marker points; implanting the implant into the patient's oral cavity according to the planned implant placement position, wherein the implant placement position includes the apex point of the implant and the expected position of the implant point in the preoperative local coordinate system; Acquire a postoperative CBCT image of the patient's oral cavity with the positioning guide; Identify each of the optical positioning mark points in the postoperative CBCT image, establish a postoperative local coordinate system formed by the optical positioning mark points, and identify the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system; Calculating the position deviations corresponding to the apex point and the implantation point and the angle deviation of the implant according to the expected positions and the actual positions of the apex point and the implantation point; The establishment of the preoperative local coordinate system formed by the optical positioning mark points includes: obtaining the three-dimensional coordinates of the sphere center corresponding to each of the optical positioning mark points in the preoperative CBCT image; selecting three sphere centers that are not on the same straight line according to the three-dimensional coordinates to construct the preoperative local coordinate system in the preoperative CBCT image; The acquisition of the desired positions of the apex point and the implantation point of the implant in the preoperative local coordinate system includes: solving the transformation matrix from the global coordinate system of the CBCT image to the local coordinate system; planning the desired position of the implant in the preoperative CBCT image on the robot navigation system software, recording the coordinate values ​​of the implantation point and the apex point of the implant, and then multiplying them by the transformation matrix to obtain the coordinate values ​​of the implantation point and the apex point in the preoperative local coordinate system formed by the iron bead; The calculation of the angular deviation of the implant includes: based on a first vector formed from the implantation point to the root apex point in the preoperative CBCT image and a second vector formed from the implantation point to the root apex point in the postoperative CBCT image, calculating the angle between the first vector and the second vector as the angular deviation of the implant.

2. The method for evaluating the accuracy of oral implantation according to claim 1, characterized in that: The step of identifying each of the optical positioning mark points in the preoperative CBCT image and obtaining the three-dimensional coordinates of the center of a sphere corresponding to each of the optical positioning mark points in the preoperative CBCT image includes: Performing format conversion on different tomographic images of the preoperative CBCT image to obtain cross-sectional images of corresponding views; According to the diameter of the circle of the optical positioning mark point in the preoperative CBCT image, using Hough circle transform to detect the circles existing in each of the cross-sectional images and the coordinates of the center of each circle; According to the coordinates of the center of the same circle in different slices and the serial numbers of the corresponding slices, the three-dimensional coordinates of the center of the sphere corresponding to the current circle in the preoperative CBCT image are obtained.

3. The method for evaluating the accuracy of oral implantation according to claim 2, characterized in that: The method of selecting three sphere centers that are not on the same straight line according to the three-dimensional coordinates also includes: If the number of the identified spherical centers exceeds the number of the optical positioning mark points in the positioning guide, the center of mass of all spherical centers is calculated by a clustering algorithm, and the spherical center farthest from the center of mass is deleted until the number of remaining spherical centers meets the requirement.

4. The method for evaluating the accuracy of oral implantation according to claim 1, characterized in that: The identifying the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system comprises: Performing multi-planar reconstruction on the postoperative CBCT image to obtain re-sliced ​​tomographic images of different sections; Convert each of the tomographic images to obtain a cross-sectional image of a corresponding view; Using a contour detection algorithm to find the maximum contour in each of the cross-sectional images, and obtaining the size of the bounding box of each of the maximum contours; Filtering all cross-sectional images according to the actual size of the implant and the size of the bounding box of the maximum contour to obtain a candidate cross-sectional image containing the implant; Selecting a target cross-sectional image that is closest to the central section of the implant from the candidate cross-sectional images; A plurality of corner points of the implant in the target cross-sectional image are detected, and actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system are determined from the plurality of corner points.

5. The method for evaluating the accuracy of oral implantation according to claim 4, characterized in that: The step of selecting a target cross-sectional image closest to a central section of the implant from the candidate cross-sectional images comprises: Extracting the implant region in each of the candidate cross-sectional images to obtain a corresponding local image; Calculating the implant slope in the local image, and performing rotation correction on the local image according to the implantation area of ​​the implant in the oral cavity and the implant slope to obtain a corrected image; Scaling the corrected image according to the size of the standard image, and calculating the structural similarity between the scaled image and the standard image; A candidate cross-sectional image corresponding to the maximum value is selected from each of the structural similarities as a target cross-sectional image closest to the central section of the implant.

6. The method for evaluating the accuracy of oral implantation according to claim 4, characterized in that: Determining the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system from the multiple corner points includes: Calculating the Euclidean distance from each corner point to the origin of the postoperative local coordinate system and selecting several point pairs with the longest distance; According to different opening directions of the implant, determining a first point pair closest to the implantation point and a second point pair closest to the root apex among the plurality of point pairs; Taking the average of the coordinates of two points in the first point pair and the second point pair close to the implantation point as the coordinate of the implantation point in the local coordinate system; The coordinate average of two points in the first point pair and the second point pair close to the root apex point is used as the coordinate of the root apex point in the local coordinate system.

7. The method for evaluating the accuracy of oral implantation according to claim 1, characterized in that: The step of calculating the corresponding position deviations of the root apex point and the implantation point according to the expected position and the actual position comprises: Calculating the Euclidean distance between the expected position and the actual position of the implantation point as the position deviation of the implantation point; The Euclidean distance between the expected position and the actual position of the root apex point is calculated as the position deviation of the root apex point.

8. An oral implant accuracy evaluation system, characterized in that: include: An image acquisition module, used to acquire a preoperative CBCT image of the patient's oral cavity with a positioning guide, wherein the positioning guide is provided with a plurality of optical positioning marking points; A coordinate system establishment module, used for identifying each of the optical positioning mark points in the preoperative CBCT image, and establishing a preoperative local coordinate system formed by the optical positioning mark points; wherein, the establishment of the preoperative local coordinate system formed by the optical positioning mark points comprises: obtaining the three-dimensional coordinates of the sphere center corresponding to each of the optical positioning mark points in the preoperative CBCT image; selecting three sphere centers that are not on the same straight line according to the three-dimensional coordinates, and constructing the preoperative local coordinate system in the preoperative CBCT image; An implant control module is used to implant an implant into a patient's oral cavity according to a planned implant implantation position, wherein the implant implantation position includes the expected position of the apex point and the implantation point of the implant in the preoperative local coordinate system; wherein the acquisition of the expected position of the apex point and the implantation point of the implant in the preoperative local coordinate system includes: solving the transformation matrix from the global coordinate system of the CBCT image to the local coordinate; planning the expected position of the implant in the preoperative CBCT image on the robot navigation system software, recording the coordinate values ​​of the implantation point and the apex point of the implant, and then multiplying by the transformation matrix to obtain the coordinate values ​​of the implantation point and the apex point in the preoperative local coordinate system formed by the iron bead; The image acquisition module is also used to acquire a postoperative CBCT image of the patient's oral cavity with the positioning guide plate; An implant position recognition module, used to recognize each of the optical positioning mark points in the postoperative CBCT image, establish a postoperative local coordinate system formed by the optical positioning mark points, and recognize the actual positions of the apex point and the implantation point of the implant in the postoperative local coordinate system; A deviation calculation module is used to calculate the position deviation corresponding to the apex point and the implantation point and the angle deviation of the implant according to the expected position and the actual position of the apex point and the implantation point; wherein the calculation of the angle deviation of the implant includes: according to a first vector formed from the implantation point to the apex point in the preoperative CBCT image and a second vector formed from the implantation point to the apex point in the postoperative CBCT image, calculating the angle between the first vector and the second vector as the angle deviation of the implant.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the method for evaluating the implantation accuracy of an oral implant surgery robot according to any one of claims 1-7.

10. A readable storage medium, characterized in that: It stores a computer program, which, when executed on a processor, implements the method for evaluating the implantation accuracy of an oral implant surgery robot according to any one of claims 1-7.

Images