Oral implant surgery navigation optimization method, device and system, and storage medium

Abstract

The invention relates to the technical field of surgical navigation, and discloses an oral implant surgical navigation optimization method, which comprises the following steps: performing three-dimensional surface reconstruction on an oral image to obtain a tooth surface model; according to an initial transformation matrix from the oral cavity image to the dental drill point, obtaining a first coordinate of the drill point in an oral cavity image coordinate system; and correcting the initial transformation matrix according to the first coordinate and the shortest spatial distance of the tooth surface model to obtain a target transformation matrix. Through a distance deviation detection and matrix feedback correction mechanism, pose errors caused by mechanical deformation, patient micromotion or optical distortion are compensated in real time in an operation, so that the display position of a dental drill point in an image space is kept consistent with an actual physical position, and the defect that dynamic errors cannot be corrected through traditional static calibration is overcome. And the precision of surgical navigation is improved, so that the requirements of high-precision oral implant surgery are met. The invention further discloses an oral implant surgery navigation optimization device and system and a storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of surgical navigation, for example to a method, device, system and computer readable storage medium for optimizing oral implant surgery navigation. BACKGROUND

[0002] Currently, in oral implant surgery, accurate implantation of the implant is the key to ensuring the success of the surgery, and the position and direction thereof directly affect the effect of subsequent denture repair and the recovery of the patient's oral function. Currently, doctors mainly rely on clinical experience and intraoperative hand feeling to judge the implantation position of the implant, which is greatly affected by individual experience differences of doctors, and problems such as deviation of the implant position and angle deviation often occur, which not only may prolong the postoperative recovery time of the patient, but also may cause complications such as nerve damage and implant loosening. Therefore, how to reduce the dependence on the experience of doctors and improve the stability of implant positioning has become a problem to be solved in the field of oral implantation.

[0003] To solve the above problems, the related art calibrates the dental drill statically before the surgery to determine the initial position relationship between the dental drill and the image space. During the surgery, the position of the dental drill is tracked in real time by an optical tracking device, which is displayed in the image space to provide visual navigation for the doctor.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art: The related art reduces the dependence on the experience of doctors to some extent and improves the stability of implant positioning. However, the related art only relies on preoperative static calibration and an initial registration matrix, and cannot cope with the deviation between the actual pose of the dental drill and the image display pose caused by factors such as mechanical deformation, patient micro-motion, optical system distortion, etc., so that the coordinates of the needle tip of the dental drill in the image coordinate system and the actual position have errors, which affects the navigation accuracy and makes it difficult to meet the needs of high-precision implant surgery.

[0005] It should be noted that the information disclosed in the above BACKGROUND section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] To have a basic understanding of some aspects of the disclosed embodiments, a brief overview is given below. The overview is not an extensive review of the application, nor is it intended to identify key / important elements of the application or delineate the scope of the embodiments. It is only a prelude to the detailed description that follows.

[0007] The embodiments of the present disclosure provide a method, device, system and computer readable storage medium for optimizing oral implant surgery navigation to reduce the error between the coordinates of the needle tip of the dental drill in the image coordinate system and the actual position, improve the accuracy of surgical navigation, and meet the needs of high-precision oral implant surgery.

[0008] In some embodiments, the method comprises: performing three-dimensional surface reconstruction on the oral cavity image to obtain a tooth surface model; obtaining a first coordinate of a drill needle tip in the oral cavity image coordinate system according to an initial transformation matrix of the oral cavity image to the drill needle; and correcting the initial transformation matrix according to a shortest spatial distance between the first coordinate and the tooth surface model to obtain a target transformation matrix.

[0009] Optionally, after obtaining the tooth surface model, the method further comprises: creating a visualization node of the tooth surface model. The visualization node data is rendered by using a rendering technology to realize interactive display of the tooth surface model.

[0010] Optionally, the initial transformation matrix is obtained in the following manner: obtaining a first transformation matrix of the oral cavity image to the patient, a second transformation matrix of the patient to the camera, a third transformation matrix of the camera to the dental engine, and a fourth transformation matrix of the dental engine to the drill needle; and determining the initial transformation matrix according to the first transformation matrix, the second transformation matrix, the third transformation matrix, and the fourth transformation matrix.

[0011] Optionally, the fourth transformation matrix is obtained in the following manner: replacing the drill needle on the dental engine with a calibration object; obtaining a fifth transformation matrix of the dental engine to the camera, a sixth transformation matrix of the camera to the calibration object, and a seventh transformation matrix of the calibration object to the drill needle; and determining the fourth transformation matrix according to the fifth transformation matrix, the sixth transformation matrix, and the seventh transformation matrix.

[0012] Optionally, the initial transformation matrix is corrected according to the shortest spatial distance between the first coordinate and the tooth surface model to obtain the target transformation matrix, comprising: calculating the shortest spatial distance between the first coordinate and the tooth surface model; correcting the seventh transformation matrix of the calibration object to the drill needle according to the shortest spatial distance to obtain an eighth transformation matrix of the calibration object to the drill needle according to the vector projection principle; and recalculating the initial transformation matrix according to the eighth transformation matrix to obtain the target transformation matrix.

[0013] Optionally, the initial transformation matrix is recalculated according to the eighth transformation matrix to obtain the target transformation matrix, comprising: recalculating the fourth transformation matrix of the dental engine to the drill needle according to the eighth transformation matrix to obtain a ninth transformation matrix of the dental engine to the drill needle; and recalculating the initial transformation matrix according to the ninth transformation matrix to obtain the target transformation matrix.

[0014] Optionally, the shortest spatial distance between the first coordinate and the tooth surface model is calculated, comprising: searching for a nearest point in the tooth surface model by using a nearest point search algorithm; obtaining a second coordinate of the nearest point; and taking a distance between the first coordinate and the second coordinate as the shortest spatial distance. In some embodiments, the device comprises a processor and a memory storing program instructions, the processor is configured to execute the above-mentioned oral implant surgery navigation optimization method when executing the above-mentioned program instructions.

[0015] In some embodiments, the system comprises a system body, and the above-mentioned oral implant surgery navigation optimization device is installed on the system body.

[0016] In some embodiments, the computer readable storage medium stores program instructions, the program instructions execute the above-mentioned oral implant surgery navigation optimization method when running.

[0017] The oral implant surgery navigation optimization method and device, system and computer readable storage medium provided by the embodiments of the present disclosure can achieve the following technical effects: Through the distance deviation detection and matrix feedback correction mechanism, the pose error caused by mechanical deformation, patient micro-motion or optical distortion is compensated in real time during the operation, so that the display position of the dental drill needle in the image space is consistent with the actual physical position, thereby eliminating the defect that the traditional static calibration cannot correct dynamic error. The error between the coordinates of the needle tip of the dental drill needle in the image coordinate system and the actual position is reduced, the precision of the surgical navigation is improved, and the demand of high-precision oral implant surgery is met.

[0018] The foregoing general description and the following description are only exemplary and explanatory, and are not used to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0019] One or more embodiments are exemplarily illustrated by corresponding drawings, which do not constitute limitation on the embodiments, elements with the same reference numerals in the drawings are shown as similar elements, the drawings do not constitute proportional limitation, and wherein: Figure 1 is a schematic diagram of an oral implant surgery navigation optimization method provided by an embodiment of the present disclosure; Figure 2 is a schematic diagram of another oral implant surgery navigation optimization method provided by an embodiment of the present disclosure; Figure 3 is a schematic diagram of another oral implant surgery navigation optimization method provided by an embodiment of the present disclosure; Figure 4 is a schematic diagram of another oral implant surgery navigation optimization method provided by an embodiment of the present disclosure; Figure 5 is a schematic diagram of an oral implant surgery navigation optimization device provided by an embodiment of the present disclosure; REFERENCE SIGNS: 800: oral implant surgery navigation optimization device; 801: processor; 802: memory; 803: communication interface; 804: bus. DETAILED DESCRIPTION

[0020] In order to enable a more detailed understanding of the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure is described in detail below with reference to the accompanying drawings, which are only used for reference and do not limit the embodiments of the present disclosure. In the following technical description, in order to facilitate explanation, a plurality of details are provided to provide a full understanding of the disclosed embodiments. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be simplified to facilitate the drawings.

[0021] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0022] In the embodiments of the present disclosure, the terms "upper", "lower", "inner", "middle", "outer", "front", "back", and the like indicate the orientation or positional relationship shown in the drawings. These terms are mainly used to better describe the embodiments of the present disclosure and its embodiments, and are not used to limit the indicated devices, elements or components must have a specific orientation, or be constructed and operated in a specific orientation. In addition, in addition to indicating the orientation or positional relationship, the above-mentioned terms can also be used to represent other meanings, for example, the term "upper" can also be used to represent a certain attachment relationship or connection relationship in some cases. For those skilled in the art, the specific meaning of these terms in the embodiments of the present disclosure can be understood according to the specific circumstances.

[0023] In addition, the terms "set", "connected", "fixed" should be broadly understood. For example, "connected" can be fixedly connected, detachably connected, or integrally configured; can be mechanically connected, or electrically connected; can be directly connected, or indirectly connected through an intermediate medium, or internal communication between two devices, elements or components. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present disclosure can be understood according to the specific circumstances.

[0024] Unless otherwise specified, the term "a plurality of" means two or more.

[0025] In the embodiments of the present disclosure, the character " / " represents that the objects before and after the character are in an "or" relationship. For example, A / B means A or B.

[0026] The term "and / or" is a description of the association relationship of the objects, which means that there can be three relationships. For example, A and / or B means that there are three relationships of A or B, or A and B.

[0027] The term "corresponding" can refer to an association relationship or a binding relationship. A and B correspond to each other means that A and B are in an association relationship or a binding relationship.

[0028] It should be noted that the embodiments in the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0029] Figures 1 to 4 FIG. 1 is a schematic diagram of a dental implant surgery navigation optimization method provided by an embodiment of the present disclosure. Any one of the following methods can be executed in the system, or in a server or terminal device in communication connection with the system.

[0030] In combination with Figure 1 As shown in the figure, the present disclosure provides a dental implant surgery navigation optimization method, which comprises the following steps. S01, performing three-dimensional surface reconstruction on the oral image to obtain a tooth surface model.

[0031] S02, obtaining a first coordinate of a drill needle tip in an oral image coordinate system according to an initial transformation matrix of the oral image to the drill needle.

[0032] S03, correcting the initial transformation matrix according to the shortest spatial distance between the first coordinate and the tooth surface model to obtain a target transformation matrix.

[0033] In the embodiments of the present application, the oral image includes but is not limited to oral CBCT image, oral cone beam CT image and the like. These images need to be preprocessed, which can include one or more of image cropping, denoising, standardization, to remove irrelevant areas, reduce noise interference and unify data format. The three-dimensional surface reconstruction is to process the preprocessed oral image by using a three-dimensional reconstruction technology to construct a three-dimensional model capable of reflecting the dental anatomy structure. The three-dimensional reconstruction technology includes but is not limited to an implementation method based on an improved MarchingCube algorithm, a voxel reconstruction method and the like. The improved MarchingCube algorithm identifies the bone tissue region by judging the relationship between the voxel gray value and the set threshold, and then reconstructs the tooth surface model containing the fine structure. The tooth surface model refers to the digital geometric object output by the three-dimensional surface reconstruction, which accurately represents the anatomical surface of the tooth and adjacent bone tissue, and is used as a spatial reference in surgical navigation. For example, the tooth surface model can be stored as a mesh file (such as OBJ format) or embedded in a visualization node (such as an OpenGL rendering object), which contains curvature characteristics and topological relationships.

[0034] By using the oral implant surgery navigation optimization method provided by the embodiments of the present application, the tooth surface model is obtained by three-dimensional surface reconstruction of the oral image, which provides an accurate reference for the spatial position comparison between the drill needle tip and the tooth surface. The tooth surface model is reconstructed based on the preprocessed oral image data, which can accurately reflect the anatomical structure of the tooth. The first coordinate of the drill needle tip in the oral image coordinate system is obtained through the initial transformation matrix of the oral image to the dental drill, which can clearly indicate the position of the drill needle tip in the image space and establish the corresponding relationship between the drill needle in reality and the image space. Then, the target transformation matrix is obtained by correcting the initial transformation matrix according to the shortest spatial distance between the first coordinate and the tooth surface model, which can detect and quantify the deviation between the actual position of the drill needle tip and the image display position in real time, and dynamically compensate for the deviation through the correction matrix, thereby effectively reducing the error between the actual pose of the drill needle and the image display pose caused by factors such as mechanical deformation, patient micro-motion, optical system distortion, improving the accuracy of surgical navigation, ensuring the consistency of virtual and real spaces, providing more reliable navigation support for oral implant surgery, and improving the safety of the surgery.

[0035] In combination with Figure 2 The embodiments of the present application provide another oral implant surgery navigation optimization method, which includes: S21, retrieving a preprocessed oral image data node; wherein the preprocessing includes image cropping, denoising and / or standardization.

[0036] S22, when the oral image data node does not exist, terminating the three-dimensional surface reconstruction of the oral image.

[0037] S23, when the oral image data node exists, a first algorithm is used to perform three-dimensional surface reconstruction on the oral image to obtain a tooth surface model.

[0038] S02, according to an initial transformation matrix of the oral image to the dental drill needle, a first coordinate of the drill needle tip in the oral image coordinate system is obtained.

[0039] S03, the initial transformation matrix is corrected according to the shortest spatial distance between the first coordinate and the tooth surface model to obtain a target transformation matrix.

[0040] In the embodiments of the present application, the pre-processed oral image data node refers to a structured data unit that stores the pre-processed oral image data, which can be a data file with a specific naming identifier, a database entry or a data object in memory, for example, a data node named "CBCTBoundingShape_cropped", which is used to centrally store and manage the pre-processed oral image information, so that the system can quickly retrieve and use it.

[0041] In the embodiments of the present application, retrieval refers to the system locating the oral image data node in the data storage module through a programmed query mechanism, which involves calling a database query interface or a file access function to verify the existence of the node. For example, retrieval can be performed in a relational database through an SQL statement (such as a SELECT query), or in local storage through an operating system level file path check (such as the Python os.path.exists() function). When the oral image data node does not exist, it means that the node has not been retrieved in the specified storage location or database index, and the system triggers the subsequent termination operation based on the returned missing state. For example, the node may not exist due to data not being imported, path errors or deletion operations, and the system confirms this state through a Boolean flag or an exception catching mechanism. Termination refers to the system immediately terminating the three-dimensional surface reconstruction process of the oral image, and generating an error handling response to avoid invalid consumption of computing resources. For example, termination can include returning an error code (such as 404 Not Found), recording a log event or popping up a user prompt message, but not performing any reconstruction-related calculations.

[0042] In the embodiments of the present application, preprocessing is a preliminary processing operation on the original oral image, which aims to improve the quality of the image data. Preprocessing includes but is not limited to image cropping, denoising and standardization. Image cropping is to remove areas of the oral image that are not related to the tooth structure, denoising is to reduce noise interference in the image using algorithms such as Gaussian filtering and median filtering, and standardization is to unify the gray scale range, resolution and other parameters of the image, so that the image data meets the requirements of subsequent processing.

[0043] In the embodiments of the present application, the tooth surface model is a three-dimensional model obtained through three-dimensional surface reconstruction, which can accurately reflect the anatomical structure and surface morphology of the tooth, including the contour, texture and other detailed features of the tooth. The model serves as a reference benchmark for subsequent judgment of the position deviation of the drill needle tip and provides intuitive three-dimensional visual basis for surgical navigation.

[0044] In the embodiments of the present application, the first algorithm includes any one of Marching Cubes, Dual Contouring, Tetrahedral Meshing and improved marching cubes algorithm. Marching Cubes generates a triangular facet mesh through threshold segmentation and voxel edge interpolation, Dual Contouring uses Hermite data to maintain sharp features, Tetrahedral Meshing directly generates tetrahedral elements to support subsequent finite element analysis, and the improved marching cubes algorithm increases adaptive subdivision or multi-resolution strategy on the basis of the classic Marching Cubes to improve the detail performance. The system automatically selects or configures any one of the above algorithms to perform three-dimensional surface reconstruction according to the accuracy requirement, computing resource or real-time requirement, and obtains the tooth surface model. In actual application, the first algorithm is used for three-dimensional surface reconstruction of the oral image, including: using the vtkMarchingCubes method to perform three-dimensional reconstruction processing on the acquired effective CBCT oral image data; wherein the vtkMarchingCubes method realizes the reconstruction process by using the improved Marching Cube algorithm, and the calculation formula of the improved Marching Cube algorithm is as follows: f (x,y,z) = I (x,y,z) - T; wherein I (x,y,z) represents the voxel gray value, i.e. the gray information of the voxel at the three-dimensional space coordinates (x,y,z) in the CBCT oral image; T is a set threshold value (such as 1500HU) for judging whether the voxel belongs to the bone tissue region; f (x,y,z) is a result calculated by the voxel gray value and the set threshold value, and when f (x,y,z) ≥ 0, it is judged that the region where the voxel is located is a bone tissue region. Through the three-dimensional reconstruction processing by the above improved Marching Cube algorithm, the bone tissue region can be accurately identified to realize the three-dimensional surface mesh reconstruction containing the subtle anatomical structure.

[0045] The preprocessing includes image cropping, denoising and / or standardization. This process can remove irrelevant areas by cropping to reduce redundant data, reduce noise interference in the image by denoising, and unify data formats or gray scale parameters by standardization, thereby improving the quality of the oral image data and providing more reliable original data for subsequent reconstruction. The data nodes of the oral image data are searched, and the reconstruction is terminated when the data nodes do not exist, which can avoid invalid reconstruction operations caused by data loss, save system resources, and ensure that the subsequent reconstruction process is based on valid data, thereby reducing the generation of error results. In the case where the data nodes exist, the first algorithm is used for three-dimensional surface reconstruction. Since the input image data is optimized by preprocessing, the interference of data problems on reconstruction can be reduced, which helps the first algorithm to more accurately perform reconstruction, thereby improving the accuracy and reliability of three-dimensional surface reconstruction and providing a more accurate reference benchmark for the comparison of the spatial positions of the drill needle tip and the tooth surface in subsequent surgical navigation.

[0046] Optionally, after the three-dimensional surface reconstruction of the oral image, the method further includes: performing smoothing processing on the reconstructed three-dimensional surface by using a second algorithm.

[0047] In the embodiments of the present application, the second algorithm is used to perform smoothing processing on the reconstructed three-dimensional surface, including: eliminating surface sawtooth phenomenon by using a parameter-adjustable iterative smoothing algorithm; wherein the second algorithm belongs to a mesh smoothing algorithm based on vertex position optimization, and specifically includes a Laplacian smoothing algorithm, a Taubin smoothing algorithm or a Butterworth filter smoothing algorithm. The second algorithm is used to perform smoothing processing on the reconstructed three-dimensional surface, and further includes: optimizing the smoothing effect by using multi-level iteration control, such as setting an initial iteration number N1 (for example, 3 times) and a termination iteration number N2 (for example, 5 times), and dynamically adjusting the value range of the relaxation factor γ in each iteration according to the surface curvature change. The second algorithm is used to perform smoothing processing on the reconstructed three-dimensional surface, and further includes: combining local optimization and global optimization by using a hybrid smoothing strategy, such as first using a local optimization algorithm (such as Laplacian smoothing) to preliminarily smooth the surface model to eliminate high-frequency noise; and then using a global optimization algorithm (such as Taubin smoothing) to perform overall shape correction on the preliminarily smoothed model.

[0048] In actual application, the second algorithm is used to perform smoothing processing on the reconstructed three-dimensional surface, including: performing smoothing processing on the reconstructed three-dimensional surface based on the Laplacian smoothing algorithm, and the calculation formula of the Laplacian smoothing algorithm is as follows: Vi'=Vi+γΣ(Vj−Vi); Wherein, Vi is a vertex coordinate, indicating the spatial coordinate of a certain vertex in the reconstructed three-dimensional surface mesh; Vj is all adjacent vertex coordinates directly connected with the vertex coordinate Vi, that is, the spatial coordinates of other vertices directly adjacent to the vertex coordinate Vi; Σ(Vj-Vi) represents the sum of the coordinate differences between the vertex coordinate Vi and all adjacent vertex coordinates Vj, for reflecting the positional relationship between Vi and the surrounding vertices; γ is a relaxation factor, taking a value in the range of 0.1-0.3, for controlling the degree of smoothing processing, and by adjusting the value, the surface sawtooth phenomenon can be effectively eliminated while the important anatomical features are maintained; Vi' is the new coordinate of the vertex coordinate Vi after smoothing processing, and the above formula is a mathematical expression based on the post-processing function of the Laplacian smoothing algorithm, for optimizing the quality of the reconstructed three-dimensional surface.

[0049] In this way, by using the second algorithm to perform smoothing processing on the three-dimensional surface after the three-dimensional surface reconstruction of the oral image, the surface sawtooth phenomenon caused by image noise and partial volume effect is eliminated, and the tooth surface model is more accurately restored to the real anatomical structure. The smoothing processing optimizes the model surface quality while maintaining the key anatomical features, provides a high-fidelity geometric reference for subsequent calculation of the shortest spatial distance between the drill needle tip and the tooth surface, thereby improving the accuracy of the pose error detection, enhancing the effectiveness of the dynamic matrix correction, and finally improving the spatial matching accuracy of the surgical navigation.

[0050] Optionally, after obtaining the tooth surface model, the method further includes: creating a visualization node of the tooth surface model; and rendering the visualization node data by using a rendering technology to realize interactive display of the tooth surface model.

[0051] In the embodiments of the present application, the visualization node of the tooth surface model is created by encapsulating metadata identifiers of the three-dimensional tooth surface model through a data structure. The visualization node includes geometric properties (such as vertex coordinates and face index) of the tooth surface model, material properties (such as color and transparency), and spatial transformation properties (such as translation and rotation), and is bound to the three-dimensional surface model through a unique identifier.

[0052] In the embodiments of the present application, the visualization node data is rendered by using a rendering technology, including: realizing real-time dynamic display of the three-dimensional tooth surface model through a graphics processing interface technology. The graphics processing interface technology includes a rendering pipeline based on rasterization (such as OpenGL and Vulkan) or a rendering engine based on ray tracing (such as DirectX Raytracing). Specifically, in the rasterization rendering, a polygon filling algorithm (such as Gouraud shading and Phong shading) is used to generate surface light and shadow effects, and a Z-Buffer algorithm is used to solve depth conflicts; in the ray tracing rendering, a path tracing algorithm is used to calculate global illumination, and depth of field blurring and anti-aliasing processing are used to enhance the visual realism.

[0053] In the embodiments of the present application, the interactive display of the tooth surface model is implemented, including: driving real-time update of the three-dimensional view through a user input device. Specifically, the interactive signals (such as rotation, scaling, and translation) of the user input device (such as a mouse, a touchpad, and a space controller) are acquired, and the interactive signals are converted into incremental parameters of a camera transformation matrix; the camera transformation matrix is updated through matrix superposition operation, and the updated camera transformation matrix M new = M old ×ΔM, wherein M old is the camera transformation matrix before the update, and ΔM is a rotation and translation sub-matrix generated from the incremental parameters; the updated camera transformation matrix is applied to a rendering pipeline to trigger view redrawing of the three-dimensional surface model.

[0054] In actual application, after the three-dimensional surface reconstruction of the oral image to obtain the tooth surface model, the system automatically creates a visualization node corresponding to the tooth surface model, which can be named as “Reconstructed CBCT surface”; the system uses a graphic processing interface technology (such as OpenGL, Vulkan, or DirectX) to accelerate the rendering processing of the visualization node data, to realize the interactive display of the tooth surface model; in the display interface, a specific color (such as red) is used to identify the final reconstruction result and / or to automatically hide the display content irrelevant to the current operation, so as to provide a clear and focused three-dimensional visualization operation interface for the doctor.

[0055] In this way, by creating the visualization node after obtaining the tooth surface model and using the rendering technology to realize the interactive display, the three-dimensional anatomical structure is converted into an intuitive and visual graphic interface, so that the operator can observe the spatial positional relationship between the drill needle and the tooth surface in real time. By enhancing the real-time and accuracy of the visual feedback, the operator can quickly identify the pose deviation (such as the actual contact between the drill needle and the tooth in the image display), provide an intuitive basis for triggering precision optimization, thereby improving the intraoperative decision-making efficiency and reducing the risk of misoperation.

[0056] In combination with the method shown in Figure 3 , the embodiments of the present disclosure provide another oral implant surgery navigation optimization method, including: S01, performing three-dimensional surface reconstruction on the oral image to obtain a tooth surface model.

[0057] S31, judging whether the position of the drill needle tip in the real space and the image space is consistent.

[0058] S32, when the position of the drill needle tip in the real space and the image space is inconsistent, determining a first coordinate of the drill needle tip in the oral image coordinate system.

[0059] S33, when the drill needle tip is consistent in the real space and the image space, stop acquiring the first coordinate of the drill needle tip in the oral image coordinate system.

[0060] S02, according to the initial transformation matrix of the oral image to the dental drill drill needle, acquiring the first coordinate of the drill needle tip in the oral image coordinate system.

[0061] S03, according to the shortest spatial distance between the first coordinate and the tooth surface model, correcting the initial transformation matrix to obtain the target transformation matrix.

[0062] In the embodiments of the present application, the real space refers to the physical space where the drill needle, teeth and other entities are located, that is, the three-dimensional space where the surgical operation actually occurs, which contains the real position, shape and mutual relationship of the entity, such as the spatial scene where the drill needle tip actually contacts the tooth surface, the physical environment where the patient's oral cavity and surrounding tissues are located, etc. The image space refers to a virtual three-dimensional space constructed based on oral image data, which is formed by processing the oral image, such as three-dimensional reconstruction, and can reflect the virtual shape and position of the anatomical structure such as teeth, such as the virtual coordinate system space where the tooth surface model reconstructed by CBCT image is located, the digital oral virtual space constructed by oral scanning image, etc.

[0063] In the embodiments of the present application, judging whether the position of the drill needle tip in the real space and the image space is consistent includes: verifying the spatial consistency of the real contact point and the image model (tooth surface model) corresponding point through a geometric matching algorithm; wherein the geometric matching algorithm includes a single-point matching algorithm based on nearest point search or a multi-point matching algorithm based on surface curvature matching. Specifically, the multi-point matching algorithm extracts a plurality of neighborhood points around the real contact point, calculates the curvature difference ΔK of the corresponding region of the image model (tooth surface model), and determines that the position is consistent when ΔK≤ΔK threshold (like Δ Kthreshold =0.1). Through the above method, the position deviation of virtual and real space can be distinguished within a small error range, and false judgment caused by measurement noise or deformation is avoided, which provides clear decision basis for whether to trigger precision optimization subsequently.

[0064] In the embodiment of the present application, when the position of the drill needle tip in the real space is inconsistent with the position of the drill needle tip in the image space, the first coordinate of the drill needle tip in the oral image coordinate system is determined by: starting the coordinate acquisition process through a dynamic triggering mechanism. Specifically, after detecting the inconsistency, the system automatically activates the high sampling rate mode (such as increasing from 50 Hz to 200 Hz) of the optical tracking device, and locks the current drill needle posture; the initial transformation matrix of the oral image to the dental drill needle is obtained by multi-level matrix cascade calculation, and the translation component is extracted from the initial transformation matrix as the first coordinate. When the position of the drill needle tip in the real space is consistent with the position of the drill needle tip in the image space, the first coordinate of the drill needle tip in the oral image coordinate system is stopped. After the system detects the consistency, a low-power instruction (such as switching to a 50 Hz sampling rate) is sent to the optical tracking device, and the drill needle posture is unlocked; at the same time, a "stop collecting" signal is sent to the coordinate calculation module through the event bus, and the subsequent matrix cascade calculation and first coordinate extraction operation are blocked.

[0065] The oral implant surgery navigation optimization method provided by the embodiment of the present application can determine whether the position of the drill needle tip in the real space is consistent with the position of the drill needle tip in the image space before obtaining the first coordinate of the drill needle tip in the oral image coordinate system according to the initial transformation matrix of the oral image to the dental drill needle. This operation can avoid unnecessary coordinate acquisition process. When the positions are consistent, it indicates that the pose deviation of the drill needle is within an acceptable range, and subsequent coordinate acquisition and correction are not required, thereby reducing invalid calculation of the system and saving surgery time and system resources. When the positions are inconsistent, the first coordinate is determined, which can ensure that the subsequent error detection and correction work is carried out only when there is a deviation, so that the precision optimization is more targeted, unnecessary operation steps are avoided to interfere with the surgery process, and the efficiency of the surgery navigation is improved.

[0066] Optionally, determining whether the position of the drill needle tip in the real space is consistent with the position of the drill needle tip in the image space comprises: abutting the drill needle tip in the real space against a first position on the tooth surface; determining a second position on the tooth surface model corresponding to the first position; determining whether the drill needle tip in the image space abuts against the second position; when the drill needle tip in the image space abuts against the second position, determining that the position of the drill needle tip in the real space is consistent with the position of the drill needle tip in the image space; and when the drill needle tip in the image space does not abut against the second position, determining that the position of the drill needle tip in the real space is inconsistent with the position of the drill needle tip in the image space.

[0067] In the embodiment of the present application, the first position of the drill needle tip in the real space is pressed against the tooth surface, comprising: verifying the actual contact state of the needle tip and the tooth surface by a physical contact detection module. Wherein, the physical contact detection module contains a contact judgment mechanism based on a force feedback sensor or a contact recognition algorithm based on optical markers. For example, the force feedback sensor determines the completion of contact by measuring the normal pressure (threshold range 0.5-2N) applied by the needle tip to the tooth surface; the optical marker recognition algorithm determines the contact state by comparing the coincidence degree (coincidence area ratio ≥80%) of the needle tip marker point and the tooth surface reflection marker point.

[0068] In the embodiment of the present application, the second position corresponding to the first position in the tooth surface model is determined, comprising: using a multi-scale feature matching algorithm to establish the association between the real contact point and the corresponding point in the image model. Wherein, the multi-scale feature matching algorithm contains a single-point matching algorithm based on local curvature features or a regional matching algorithm based on surface topological features. For example, the single-point matching algorithm searches for a point with the same geometric features in the tooth surface model by extracting the normal vector direction and the curvature radius of the real contact point; the regional matching algorithm performs similarity matching (similarity threshold ≥0.7) between the parameter distribution of the corresponding region in the model and the surface parameters (such as Gaussian curvature K, mean curvature H) of the neighborhood around the contact point. Through the above method, accurate mapping from the physical contact point to the virtual model point can be realized, providing geometric reference for the consistency judgment of virtual and real space positions.

[0069] In the embodiment of the present application, whether the drill needle tip in the image space is pressed against the second position is judged, comprising: quantifying the position deviation of virtual and real space by a dynamic distance threshold judgment algorithm; wherein, the dynamic distance threshold algorithm contains a fixed threshold judgment based on contact accuracy level or an adaptive threshold adjustment based on environmental noise level. For example, the fixed threshold judgment sets the distance threshold d threshold =1mm, and when the distance d between the needle tip and the second position in the image space is d threshold ≤d threshold =σ×α+0.5mm. Thus, under different accuracy requirements and environmental interference conditions, effective contact and invalid deviation can be reasonably distinguished, and false judgment caused by system noise can be avoided. When the drill needle tip in the image space is pressed against the second position, it is determined that the position of the drill needle tip in the real space is consistent with that in the image space, comprising: generating a consistency verification signal by a state confirmation mechanism. Specifically, when the distance d between the needle tip and the second position in the image space satisfies d thresholdWhen the position consistency is determined, the trigger state confirmation module generates a "PositionConsistency" event; the event is transmitted to the surgical navigation interface through the message queue, and the green confirmation mark is activated and the precision optimization button is disabled.

[0070] In this way, when determining whether the position of the drill needle tip in the real space and the image space is consistent, the first position of the drill needle tip abutting against the tooth surface in the real space is determined, the second position corresponding to the first position in the tooth surface model is determined, and then whether the drill needle tip in the image space abuts against the second position is determined to determine whether the positions are consistent. This process establishes a direct association between the real contact point and the corresponding point in the image model, and provides a clear reference standard for determining the position consistency. Therefore, the above method can intuitively and specifically detect the position matching of the drill needle tip in the real space and the image space, avoid ambiguous judgment logic, accurately distinguish whether the positions are consistent, and provide a clear basis for whether the first coordinate of the drill needle tip in the oral image coordinate system needs to be obtained, thereby ensuring that further error processing is only carried out when the positions are inconsistent, and improving the reliability and pertinence of the judgment.

[0071] Optionally, determining whether the drill needle tip in the image space abuts against the second position comprises: when the distance between the drill needle tip in the image space and the second position is greater than or equal to a distance threshold, it is determined that the drill needle tip in the image space does not abut against the second position; and when the distance between the drill needle tip in the image space and the second position is less than the distance threshold, it is determined that the drill needle tip in the image space abuts against the second position.

[0072] In this way, when determining whether the drill needle tip in the image space abuts against the second position, the distance between the drill needle tip in the image space and the second position is compared with the threshold value by setting the distance threshold value, and it is determined that the drill needle tip does not abut against the second position when the distance is greater than or equal to the threshold value, and it is determined that the drill needle tip abuts against the second position when the distance is less than the threshold value, thereby providing a quantitative standard for the determination. Since a certain range of small errors is allowed in the operation, the setting of the distance threshold value can reasonably distinguish between acceptable deviations and significant deviations that need to be corrected, avoid unnecessary precision optimization operations due to small errors, and ensure that significant deviations can be detected in time, thereby making the determination result more in line with the actual needs of the operation and improving the objectivity and accuracy of the position consistency determination, thereby providing a reliable basis for whether to perform drill precision optimization.

[0073] Optionally, the first coordinate of the drill needle tip in the oral image coordinate system is obtained according to the initial transformation matrix of the oral image to the drill bit drill needle, comprising: calculating the initial transformation matrix of the oral image to the drill bit drill needle; and extracting the first coordinate from the initial transformation matrix.

[0074] In the embodiments of the present application, the first coordinate is extracted from the initial transformation matrix, including: directly parsing the translation component as the needle tip coordinate from the data structure (for example, a 4x4 homogeneous transformation matrix, a 3x4 affine transformation matrix, or a rotation and translation combination parameter) in the initial transformation matrix representing the spatial pose relationship; wherein the translation component corresponds to the element of a specific storage location in the initial transformation matrix, the X-axis coordinate value is taken from the index [0, 3] position (or the 0th element of the translation vector) in the data structure, the Y-axis coordinate value is taken from the index [1, 3] position (or the 1st element of the translation vector) in the data structure, and the Z-axis coordinate value is taken from the index [2, 3] position (or the 2nd element of the translation vector) in the data structure, which is defined as a three-dimensional point coordinate data structure (for example, a C++ array, a Python tuple, or a custom Point3D class instance) in the system; the coordinate value extraction and storage are automatically completed through a programming interface (for example, a matrix index operator [], a getTranslation() method, or a vector extraction function), and a first coordinate data entity is generated.

[0075] In this way, when the first coordinate of the drill needle tip in the oral image coordinate system is obtained according to the initial transformation matrix from the oral image to the dental drill needle, the initial transformation matrix is first calculated, and then the first coordinate is extracted from the matrix, thereby establishing the spatial position relationship between the oral image and the dental drill needle through matrix operation. The initial transformation matrix integrates the position relationships of multiple links such as the oral image to the patient, the patient to the camera, the camera to the dental engine, the dental engine to the drill needle, and can comprehensively reflect the pose of the drill needle tip in the image space, while the direct extraction of the coordinate from the matrix ensures the accuracy and directness of the first coordinate, avoiding errors that may be introduced by additional conversion processes. Through the above-mentioned manner, the position of the drill needle tip in the image coordinate system is determined, which provides accurate coordinate basis for subsequent calculation of the shortest spatial distance between the drill needle tip and the tooth surface model, thereby enabling more accurate detection of the pose deviation.

[0076] Optionally, the initial transformation matrix is obtained in the following manner: obtaining a first transformation matrix from the oral image to the patient, a second transformation matrix from the patient to the camera, a third transformation matrix from the camera to the dental engine, and a fourth transformation matrix from the dental engine to the drill needle; and determining the initial transformation matrix according to the first transformation matrix, the second transformation matrix, the third transformation matrix, and the fourth transformation matrix.

[0077] In the embodiments of the present application, the initial transformation matrix is determined according to the first transformation matrix, the second transformation matrix, the third transformation matrix, and the fourth transformation matrix, including: calculating the initial transformation matrix through matrix cascade operation, that is, the initial transformation matrix is the result of multiplying the first transformation matrix, the second transformation matrix, the third transformation matrix, and the fourth transformation matrix in order.

[0078] In this way, the first transformation matrix (image to patient) carries the preoperative registration result, the second transformation matrix (patient to camera) and the third transformation matrix (camera to dental machine) capture the intraoperative pose changes of the patient and the dental machine in real time through the optical tracking device, and the fourth transformation matrix (dental machine to drill needle) establishes the fixed relationship between the drill needle and the dental machine based on the preoperative calibration. The multi-level matrix cascade fuses the static calibration parameters and the dynamic tracking data, provides a real-time updated spatial conversion basis for the coordinate calculation of the drill needle tip in the image space, and thus improves the timeliness and accuracy of the virtual-real space pose association, and overcomes the defect that the traditional single static matrix cannot respond to the intraoperative dynamic changes.

[0079] Optionally, the fourth transformation matrix is obtained in the following manner: replacing the drill needle on the dental machine with a calibration object; obtaining a fifth transformation matrix of the dental machine to the camera, a sixth transformation matrix of the camera to the calibration object, and a seventh transformation matrix of the calibration object to the drill needle; and determining the fourth transformation matrix according to the fifth transformation matrix, the sixth transformation matrix, and the seventh transformation matrix.

[0080] In the embodiments of the present application, the calibration object has a preset geometric configuration and is provided with a spatial positioning marker group (such as an array of spherical reflective balls, a planar coded marker, or a corner point feature), which constitutes a calibration object coordinate system. The seventh transformation matrix of the calibration object to the drill needle is obtained by: calculating an axial directional vector of the drill needle based on the preset physical reference point coordinates of the calibration object through a spatial vector calculation method (such as vector cross product, dot product, or least squares fitting); determining a rotation angle difference value according to the spatial included angle between the standard axial direction (such as the Z-axis) of the world coordinate system and the axial directional vector of the drill needle; calling a rotation correction function (such as RotateWXYZ(), setFromToRotation(), or AngleAxis()) in a three-dimensional space transformation interface (such as vtkTransform, Unity Transform, or Eigen library) to perform pose correction on the drill needle tip according to the aforementioned rotation angle difference value, and output the seventh transformation matrix of the calibration object to the drill needle.

[0081] In the embodiments of the present application, the fourth transformation matrix is determined according to the fifth transformation matrix, the sixth transformation matrix, and the seventh transformation matrix, including: calculating the fourth transformation matrix through matrix cascade operation, that is, the fourth transformation matrix is the result of multiplying the fifth transformation matrix, the sixth transformation matrix, and the seventh transformation matrix in sequence.

[0082] Thus, by indirectly calibrating the spatial relationship between the dental engine and the drill needle through the intermediary of the calibration object, replacing the drill needle with the calibration object with optical markers, sequentially obtaining the fifth transformation matrix (dental engine to camera), the sixth transformation matrix (camera to calibration object), and the seventh transformation matrix (calibration object to drill needle), and then calculating the fourth transformation matrix (dental engine to drill needle) through three-level matrix cascading, the calibration problem of small-size drill needles being difficult to directly optically track is solved. The calibration object is used to expand the tracking marker points, the pose of the calibration object is accurately captured by the camera, and then the accurate pose parameters of the drill needle relative to the dental engine are indirectly derived in combination with the fixed geometric relationship (the seventh transformation matrix) between the calibration object and the drill needle, thereby providing a reliable end-space conversion basis for the initial transformation matrix chain, and thus the accuracy of the calculation of the coordinates of the needle tip of the drill needle is ensured.

[0083] Optionally, before the target transformation matrix is obtained by correcting the initial transformation matrix according to the shortest spatial distance between the first coordinates and the tooth surface model, the method further includes: searching for a tooth surface model data node; when the tooth surface model data node does not exist, terminating the correction of the initial transformation matrix according to the shortest spatial distance between the first coordinates and the tooth surface model; and when the tooth surface model data node exists, determining to correct the initial transformation matrix according to the shortest spatial distance between the first coordinates and the tooth surface model.

[0084] Thus, before the target transformation matrix is obtained by correcting the initial transformation matrix according to the shortest spatial distance between the first coordinates and the tooth surface model, the tooth surface model data node is searched for first, and when the node does not exist, the correction operation is terminated, and when the node exists, the correction is determined to be performed, so that the correction operation can be ensured to be based on an effective tooth surface model. Because the tooth surface model is a key reference for calculating the shortest spatial distance, if the data node does not exist, the subsequent distance calculation and matrix correction will lose the basis, which may lead to an incorrect result. By searching for the node to confirm that the node exists before performing the correction, invalid or incorrect operations caused by data loss can be avoided, system resources can be saved, and a basis for accurately calculating the shortest spatial distance and effectively correcting the initial transformation matrix is provided, thereby improving the reliability of the correction process.

[0085] In combination with Figure 4 As shown in FIG. 1, the disclosure provides another method for optimizing oral implant surgery navigation, which includes the following steps. S01, performing three-dimensional surface reconstruction on the oral image to obtain a tooth surface model.

[0086] S02, obtaining first coordinates of a drill needle tip in an oral image coordinate system according to an initial transformation matrix of the oral image to the drill needle.

[0087] S41, calculating the shortest spatial distance between the first coordinates and the tooth surface model.

[0088] S42, according to the shortest spatial distance, the seventh transformation matrix of the calibration object to the drill needle is corrected according to the vector projection principle to obtain the eighth transformation matrix of the calibration object to the drill needle.

[0089] S43, the initial transformation matrix is recalculated according to the eighth transformation matrix to obtain the target transformation matrix.

[0090] In the embodiment of the present application, according to the shortest spatial distance, the seventh transformation matrix of the calibration object to the drill needle is corrected according to the vector projection principle to obtain the eighth transformation matrix of the calibration object to the drill needle, including: extracting a direction vector representing the axial direction of the drill needle from the data structure of the seventh transformation matrix by using a vector analysis method; wherein the direction vector representing the axial direction of the drill needle can be extracted by matrix index operation or calling a direction vector acquisition interface; performing normalization mathematical processing on the direction vector; wherein the normalization mathematical processing includes calculating the module length of the direction vector and performing proportional scaling of each component to generate a unit direction vector: the X component of the normalized direction vector, the Y component of the normalized direction vector and / or the Z component of the normalized direction vector; based on the shortest spatial distance d and the normalized direction vector, the translation component of the seventh transformation matrix is updated by applying the vector projection compensation rule; wherein the update formula of the position element of the transformation matrix [0, 3] is: the original value + d x the X component of the normalized direction vector, the update formula of the position element of the transformation matrix [1, 3] is: the original value + d x the Y component of the normalized direction vector, and the update formula of the position element of the transformation matrix [2, 3] is: the original value + d x the Z component of the normalized direction vector; the rotation component of the seventh transformation matrix is kept unchanged, the updated translation component is written into the data structure of the seventh transformation matrix, and the eighth transformation matrix of the calibration object to the drill needle is generated.

[0091] By using the oral implant surgery navigation optimization method provided by the embodiments of the present application, the shortest spatial distance between the first coordinate and the tooth surface model is taken as a quantitative index of the pose deviation, and the seventh transformation matrix of the calibration object to the drill needle is corrected (the translation component thereof is updated) based on the vector projection principle, so that the precise tracing and compensation of dynamic errors are realized. The shortest spatial distance objectively reflects the offset between the actual position of the drill needle and the image display, and the vector projection principle ensures that the correction direction is along the axial direction of the drill needle (determined by the third column direction vector of the seventh transformation matrix), so that the translation compensation amount (distance value x normalized direction vector) accurately corresponds to the deformation direction in the physical space. Then, the initial transformation matrix chain is updated by the eighth transformation matrix, and the error compensation is transmitted to the entire spatial mapping system, so that the core error source caused by the deformation of the connection between the calibration object and the drill needle is eliminated in a targeted manner on the premise of maintaining the integrity of the matrix cascade structure, and the virtual-to-real space registration accuracy is improved.

[0092] Optionally, the initial transformation matrix is recalculated according to the eighth transformation matrix to obtain a target transformation matrix, including: recalculating the fourth transformation matrix from the dental engine to the drill needle according to the eighth transformation matrix to obtain a ninth transformation matrix from the dental engine to the drill needle; and recalculating the initial transformation matrix according to the ninth transformation matrix to obtain the target transformation matrix.

[0093] In this way, by limiting the update of only the end transformation matrix (the fourth transformation matrix) directly related to the drill needle, it is ensured that the correction amount acts accurately on the deformation core link (the connection between the calibration object and the drill needle), and then through the step-by-step transmission of the matrix chain, the local correction is mapped to the entire space conversion system, thereby maintaining the mathematical rigor of the multi-level coordinate conversion relationship, avoiding interference with the error link (such as the image registration matrix), and thus ensuring the physical reasonableness and global consistency of the target transformation matrix after correction, and realizing the directionality and systematicness of error compensation.

[0094] Optionally, the shortest spatial distance between the first coordinate and the tooth surface model is calculated, including: searching for a nearest point in the tooth surface model using a nearest point search algorithm; obtaining a second coordinate of the nearest point; and taking the distance between the first coordinate and the second coordinate as the shortest spatial distance.

[0095] In the embodiments of the present application, the nearest point search algorithm includes an accelerated search algorithm based on spatial indexing (such as octree accelerated search) or a direct search algorithm based on iterative optimization (such as gradient descent method). For example, the octree accelerated search quickly locates the potential candidate area by dividing the tooth surface model into multiple levels of subspaces using the spatial division characteristics; the gradient descent method gradually converges to the nearest point from the initial guess point along the surface curvature direction through the iterative approximation strategy.

[0096] In the embodiments of the present application, the second coordinate of the nearest point is obtained, including: determining the spatial position of the nearest point through surface parameterization mapping. Specifically, when the octree accelerated search is used, the three-dimensional coordinates of the nearest point are directly returned through the nearest neighbor search interface (such as the FindClosestPoint method of the VTK library); when the gradient descent method is used, the convergence is determined through the iterative termination condition (such as the displacement of adjacent iteration points being less than ε = 0.01 mm), and the coordinates of the final convergence point are recorded as the second coordinates.

[0097] In the embodiment of the present application, the distance between the first coordinate and the second coordinate is taken as the shortest spatial distance, which comprises: quantifying the contact deviation of virtual and real spaces by the Euclidean distance formula. Specifically, the Euclidean distance formula d = √[(x1-x2)²+(y1-y2)²+(z1-z2)²] between two points in a three-dimensional space is adopted, where (x1, y1, z1) is the first coordinate and (x2, y2, z2) is the second coordinate. Further comprising: introducing an error tolerance correction mechanism in the calculation process, when the calculated distance d is less than the preset minimum non-zero threshold δ (such as δ = 0.001 mm), it is corrected to δ to avoid division by zero exception; when the calculated distance d exceeds the maximum effective threshold Δ (such as Δ = 5 mm), it is determined as invalid measurement and triggers the exception handling process. Through the above method, while ensuring the mathematical rigor of distance calculation, the robustness of the system to extreme cases is enhanced, providing a reliable error quantification basis for subsequent matrix correction.

[0098] In this way, when calculating the shortest spatial distance between the first coordinate and the tooth surface model, the nearest point search algorithm is used to search for the nearest point to the first coordinate in the tooth surface model, which can efficiently and accurately locate the position on the tooth surface model closest to the first coordinate of the drill needle tip, avoiding errors that may be caused by manual judgment or rough estimation. After obtaining the second coordinate of the nearest point, the distance between the first coordinate and the second coordinate is taken as the shortest spatial distance, and the distance between the two coordinates is calculated to make the quantification result of the shortest spatial distance more objective and accurate. The shortest spatial distance obtained can truly reflect the deviation degree of the drill needle tip in the image space from the tooth surface model, providing a reliable quantification basis for subsequent correction of the initial transformation matrix according to the distance.

[0099] In combination with Figure 5 As shown in the figure, the embodiment of the present disclosure provides an oral implant surgery navigation optimization device 800, which comprises a processor 801 and a memory 802. Optionally, the device can also comprise a communication interface 803 and a bus 804. The processor 801, the communication interface 803, and the memory 802 can communicate with each other through the bus 804. The communication interface 803 can be used for information transmission. The processor 801 can call the logical instructions in the memory 802 to execute the oral implant surgery navigation optimization method of the above-mentioned embodiment.

[0100] In addition, the logical instructions in the memory 802 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium.

[0101] The memory 802 can be used to store software programs, computer executable programs, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The processor 801 executes the function application and data processing, i.e., implements the oral implant surgery navigation optimization method in the above embodiments, by running the program instructions / modules stored in the memory 802.

[0102] The memory 802 can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function. The data storage area can store data created according to the use of the terminal device, and the like. In addition, the memory 802 can include a high-speed random access memory, and can also include a non-volatile memory.

[0103] The embodiments of the present disclosure provide a system, which includes a system body and the oral implant surgery navigation optimization apparatus 800 described above. The oral implant surgery navigation optimization apparatus 800 is installed in the system body. The installation relationship described herein is not limited to being placed in the system, but also includes installation connection with other components of the system, including but not limited to physical connection, electrical connection or signal transmission connection, and the like. Those skilled in the art can understand that the oral implant surgery navigation optimization apparatus 800 can be adapted to a feasible system body, and thus realize other feasible embodiments.

[0104] The embodiments of the present disclosure provide a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are configured to execute the above-mentioned oral implant surgery navigation optimization method.

[0105] The technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes one or more instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present disclosure. The aforementioned storage medium can be a non-transitory storage medium, including a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0106] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0107] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0108] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to apparatuses, devices, etc.), can be implemented in other manners. For example, the apparatus embodiments described above are merely schematic. For example, the division of the units is merely logical function division. There can be other division manners in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, apparatuses, or units, and can be in electrical, mechanical, or other forms. The units described as separated components can or can not be physically separated, and components displayed as units can or can not be physical units. Some or all of the units can be selected according to actual needs to achieve the embodiments.

[0109] The flowcharts and block diagrams in the drawings show the possible implementation architectures, functions, and operations of the systems, methods, and computer program products according to the embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the drawings, the operations or steps corresponding to different blocks can also occur in different orders than those disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for optimizing navigation during oral implant surgery, characterized in that, include: Three-dimensional surface reconstruction is performed on oral images to obtain tooth surface models; Based on the initial transformation matrix from the oral image to the dental drill bit, obtain the first coordinate of the drill bit tip in the oral image coordinate system; The initial transformation matrix is ​​corrected based on the shortest spatial distance between the first coordinate and the tooth surface model to obtain the target transformation matrix.

2. The method according to claim 1, characterized in that, After obtaining the tooth surface model, the following is also included: Create visualization nodes for tooth surface models; Rendering technology is used to render the visualized node data, enabling interactive display of the tooth surface model.

3. The method according to claim 1, characterized in that, The initial transformation matrix is ​​obtained as follows: The first transformation matrix from oral images to the patient, the second transformation matrix from the patient to the camera, the third transformation matrix from the camera to the dental machine, and the fourth transformation matrix from the dental machine to the drill bit are acquired. The initial transformation matrix is ​​determined based on the first transformation matrix, the second transformation matrix, the third transformation matrix, and the fourth transformation matrix.

4. The method according to claim 3, characterized in that, The fourth transformation matrix is ​​obtained as follows: Replace the drill bit on the dental machine with a calibration object; Obtain the fifth transformation matrix from the dental machine to the camera, the sixth transformation matrix from the camera to the calibration object, and the seventh transformation matrix from the calibration object to the drill bit; The fourth transformation matrix is ​​determined based on the fifth, sixth, and seventh transformation matrices.

5. The method according to any one of claims 1 to 4, characterized in that, The initial transformation matrix is ​​corrected based on the shortest spatial distance between the first coordinate and the tooth surface model to obtain the target transformation matrix, which includes: Calculate the shortest spatial distance between the first coordinate and the tooth surface model; Based on the shortest spatial distance, the seventh transformation matrix from the calibration object to the drill bit is corrected according to the principle of vector projection, resulting in the eighth transformation matrix from the calibration object to the drill bit. The initial transformation matrix is ​​recalculated based on the eighth transformation matrix to obtain the target transformation matrix.

6. The method according to claim 5, characterized in that, The initial transformation matrix is ​​recalculated based on the eighth transformation matrix to obtain the target transformation matrix, including: The fourth transformation matrix from the dental machine to the drill bit is recalculated based on the eighth transformation moment, resulting in the ninth transformation matrix from the dental machine to the drill bit. The initial transformation matrix is ​​recalculated based on the ninth transformation matrix to obtain the target transformation matrix.

7. The method according to any one of claims 1 to 4, characterized in that, Calculate the shortest spatial distance between the first coordinate and the tooth surface model, including: The nearest point search algorithm is used to search for the point closest to the first coordinate in the tooth surface model; Get the second coordinates of the nearest point; The distance between the first coordinate and the second coordinate is taken as the shortest spatial distance.

8. A navigation optimization device for oral implant surgery, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the oral implant surgery navigation optimization method as described in any one of claims 1 to 7 when running the program instructions.

9. A system, characterized in that, include: System body; as well as, The oral implant surgery navigation optimization device as described in claim 8 is installed on the system body.

10. A computer-readable storage medium storing program instructions, characterized in that, When the program instructions are executed, they cause the computer to perform the oral implant surgery navigation optimization method as described in any one of claims 1 to 7.

Images