Orthodontic anchorage nail implantation navigation system and method based on mixed reality technology

Abstract

The present invention discloses an orthodontic anchorage pin implantation navigation system and method based on mixed reality technology, which relates to the field of orthodontic surgical navigation technology, including collecting patient orthodontic anchorage pin implantation surgical data, and performing spatial registration based on a deep learning feature matching algorithm to generate a patient-specific three-dimensional anatomical model; generating anchorage pin implantation point coordinates and an angle planning scheme based on the patient-specific three-dimensional anatomical model, and synchronously setting a safety boundary threshold to adjust the implantation point and angle parameters; loading the patient-specific three-dimensional anatomical model and the final planned implantation point coordinates into customized MR glasses, and using an occlusion elimination algorithm to superimpose virtual navigation markers on a real surgical field to generate a three-dimensional postoperative simulation report. The present invention achieves high precision and high reliability of the implantation anatomical basis, can effectively improve the controllability and safety of surgical operations, and improve the accuracy, efficiency and treatment effect of orthodontic anchorage pin implantation.

Description

Technical Field

[0001] The present invention relates to the technical field of oral orthodontic surgery navigation, and in particular to an oral orthodontic anchorage nail implantation navigation system and method based on mixed reality technology. Background Art

[0002] In orthodontic treatment, the implantation of anchorage screws (also known as micro-implants, bone screws, or temporary anchorage devices) has important clinical significance, mainly reflected in the following aspects: providing stable anchorage, precisely controlling tooth movement, expanding the scope of indications, shortening treatment time, and being minimally invasive and reversible. Therefore, the rational use of anchorage screws can significantly improve treatment outcomes and reduce treatment difficulty. However, traditional anchorage screw implantation surgery relies on the doctor's experience and preoperative two-dimensional / static three-dimensional images (such as X-rays / maxillofacial bone tissue); the lack of tactile perception during implantation prevents the doctor from sensing changes in bone density and implant resistance in real time, leading to excessive force or slippage; clinical decision-making relies on subjective judgment and lacks intelligent planning tools, resulting in the following defects: anatomical structures such as bones, blood vessels, and nerves cannot be displayed dynamically in real time during surgery, which can easily cause intraoperative anatomical damage; the adjustment of implant depth and angle relies on the doctor's feel, which lacks precision; and the need to repeatedly refer to and check preoperative static images during surgery, which prolongs the operation time and reduces the patient's surgical comfort experience.

[0003] While existing technologies have proposed navigation systems based on static maxillofacial bone tissue, they haven't addressed the integration of multimodal data fusion, real-time interaction, and tactile feedback. Patients must remain stationary, and doctors cannot perform the entire anchorage pin implantation procedure with real-time dynamic visualization. Summary of the Invention

[0004] The present invention is proposed in view of the problems existing in the existing methods for navigating the implantation of orthodontic anchorage nails based on mixed reality technology. Therefore, the problem to be solved by the present invention is how to provide a system and method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides an orthodontic anchorage pin implantation navigation method based on mixed reality technology, which comprises collecting a patient's orthodontic anchorage pin implantation surgical data, and spatially registering the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific three-dimensional anatomical model;

[0007] Generate anchorage pin implantation point coordinates and angle planning based on the patient-specific 3D anatomical model, and simultaneously set safety margin thresholds to adjust implantation point and angle parameters;

[0008] The patient-specific 3D anatomical model and the final planned implantation point coordinates are loaded into customized MR glasses. An occlusion elimination algorithm is used to overlay virtual navigation markers onto the actual surgical field. When the implantation torque value exceeds the safe range or the angle between the current instrument direction and the target direction exceeds a predetermined angle, the MR glasses project angle correction parameters in real time.

[0009] The deviation between the actual implant depth and the planned path is continuously compared. If the deviation exceeds the safety boundary threshold, a voice alarm is automatically triggered and a three-dimensional postoperative simulation report is generated.

[0010] As a preferred solution of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology described in the present invention, the patient's oral orthodontic anchorage nail implantation surgery data includes maxillofacial bone tissue data, blood vessel and nerve tube distribution data and tooth surface morphology data.

[0011] As a preferred solution of the oral orthodontic anchorage pin implantation navigation method based on mixed reality technology of the present invention, wherein: generating a patient-specific three-dimensional anatomical model includes:

[0012] The acquired data of patients' orthodontic anchorage implantation surgery were preprocessed and resampled to a uniform voxel size through trilinear interpolation.

[0013] A multi-scale 3D deep neural network was used to extract spatial distribution features from patients' orthodontic anchorage pin implantation surgery data.

[0014] The blood vessel and nerve tube distribution data and the tooth surface morphology data coordinate system are aligned to the maxillofacial bone tissue coordinate system to construct a multimodal fused voxel image to form a patient-specific three-dimensional anatomical model. , expressed as:

[0015] ;

[0016] in: is the voxel image after multimodal fusion, For the The coordinates of the tooth root center point, is the neural tube path trajectory function, For spatial points The bone density value at .

[0017] As a preferred solution of the oral orthodontic anchorage pin implantation navigation method based on mixed reality technology of the present invention, wherein: the anchorage pin implantation point coordinates and angle planning scheme generated based on the patient-specific three-dimensional anatomical model includes:

[0018] Based on the obtained patient-specific three-dimensional anatomical model, a local voxel block is cut out from the center of each tooth root to be implanted and the surrounding sphere with a predetermined radius;

[0019] Obtain the root curvature, the gradient amplitude of the bone density gradient and the minimum value of the proximity distance between each root point and the neural canal;

[0020] The local voxel block and the gradient amplitude of the corresponding bone density gradient are input into the convolutional neural network, and the root curvature and the minimum value of the proximity distance between each root point and the neural canal are used as additional inputs of the fully connected layer to output the implant suitability score;

[0021] The training set is generated by historical cases and postoperative evaluation annotations, and the loss function is cross entropy loss , expressed as:

[0022] ;

[0023] in: For implant suitability score, For clinical surgical results, is the index variable;

[0024] Automatically plan the implantation point and angle, and define the objective function as:

[0025] ;

[0026] in: is the objective function of implantation point and angle planning, are the implantation point coordinates, is the angle; is the bone density value, is the root curvature, is the proximity distance from the tooth root point to the neural canal, 、 and is the indicator weight;

[0027] The objective function is optimized and solved using the gradient descent method. If the candidate solution does not meet the safety threshold, it is automatically eliminated and re-searched, and the current implantation point and angle are rendered in real time on the MR glasses interface.

[0028] As a preferred solution of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology of the present invention, wherein: the method of superimposing the virtual navigation mark on the real surgical field using the occlusion elimination algorithm includes:

[0029] Import the patient-specific 3D anatomical model and the obtained implantation point coordinates and angles into the customized MR glasses, perform internal and external calibration of the MR glasses, and extract ORB or SIFT feature points from the binocular image pair;

[0030] For each model implant point, obtain the depth of the current view and the depth measured by the sensor; if the depth of the current view is greater than the depth measured by the sensor plus the tolerance, it is considered to be occluded and the occluded implant point is removed from the rendering;

[0031] Obtaining bone density at the implantation point to generate a tactile signal, and calculating the instantaneous frequency of the tactile signal and the angle between the current device direction and the target direction;

[0032] If the implant torque value is not within the predetermined safety range or the angle between the current instrument direction and the target direction exceeds the predetermined angle, a dual-modal alarm is issued through touch and vision, the navigation mark turns red, and a warning bar flashes at the edge of the MR glasses' field of view, the vibration tactile signal is updated, and the correction instruction is overwritten and superimposed on the MR glasses' field of view in the form of an arrow or numerical angle.

[0033] As a preferred solution of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology of the present invention, the expression of the instantaneous frequency of the tactile signal is:

[0034] ;

[0035] in: is the instantaneous frequency, is the reference frequency, As a reference bone density, is the bone density conversion coefficient, is the bone density at the implantation site;

[0036] The angle between the current device direction and the target direction is expressed as:

[0037] ;

[0038] in: is the angle between the current device direction and the target direction, is the current device direction, For the target direction, is the norm.

[0039] In a second aspect, the present invention provides an orthodontic anchorage pin implantation navigation system based on mixed reality technology, which comprises:

[0040] The multimodal image fusion module is used to obtain the patient's orthodontic anchorage pin implantation surgical data and spatially register the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific 3D anatomical model;

[0041] The tactile feedback module includes a mechanical sensor and a micro-vibration motor. The mechanical sensor is used to monitor the implant torque value, and the micro-vibration motor is used to monitor the vibration intensity and frequency to feedback bone density changes, identify dangerous areas, and trigger an alarm to remind you when approaching the dangerous area;

[0042] MR visualization real-time navigation module, used to superimpose virtual navigation markers onto the real surgical field through SLAM spatial anchoring technology and occlusion elimination algorithm;

[0043] Customized MR glasses integration module for displaying patient-specific 3D anatomical models and virtual navigation markers through MR glasses, enabling multimodal interaction through gesture control, voice commands, and physical buttons;

[0044] The clinical decision-making module is used to output the implant suitability score through a deep learning model, generate the optimal anchorage nail implantation path planning scheme, dynamically evaluate surgical risks based on preset safety thresholds, provide deviation correction suggestions, and generate a postoperative three-dimensional effect simulation report and quantitative evaluation indicators.

[0045] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology are implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a method for navigating the implantation of orthodontic anchorage pins based on mixed reality technology are implemented.

[0047] The beneficial effects of the present invention are: on the one hand, the present invention utilizes deep learning-driven multimodal spatial registration and personalized three-dimensional modeling to achieve high precision and high reliability of the anatomical basis of implantation; on the other hand, it combines intelligent program planning, dynamic setting of safety thresholds, MR real-time navigation and multimodal early warning to effectively improve the controllability and safety of surgical operations, and improve the accuracy, efficiency and treatment effect of oral orthodontic anchorage nail implantation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a structural diagram of the orthodontic anchorage pin implantation navigation system based on mixed reality technology;

[0050] Figure 2 Flowchart of the navigation method for orthodontic anchorage pin implantation based on mixed reality technology. DETAILED DESCRIPTION

[0051] To make the above-mentioned objects, features, and advantages of the present invention more easily understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it constitute a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Reference Figure 1 , which is the first embodiment of the present invention, provides an orthodontic anchorage pin implantation navigation method based on mixed reality technology, comprising:

[0055] S1: Collect the patient's orthodontic anchorage pin implantation surgical data, and perform spatial registration of the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific 3D anatomical model;

[0056] Specifically, a cone-beam CT scanner was used to obtain maxillofacial bone tissue data; a T2-weighted MRI scan was used to obtain blood vessel and nerve canal distribution data; and a three-dimensional optical scanner was used to obtain tooth surface morphology data.

[0057] The acquired data were preprocessed, resampled to a uniform voxel size by trilinear interpolation, and the grayscale values ​​were normalized to the interval [0, 1];

[0058] Perform deep feature extraction and matching, and use a multi-scale 3D deep neural network to extract spatial distribution features from patients' orthodontic anchorage pin implantation surgery data;

[0059] Based on the reference points, the coordinate system of the blood vessel and nerve tube distribution data and the tooth surface morphology data is aligned to the maxillofacial bone tissue coordinate system. All the registered data are converted to the same coordinate system to construct a multimodal fused voxel image.

[0060] Use doctor annotations or depth models to mark the root center, nerve canal path, bone density distribution, and ultimately create a patient-specific 3D anatomical model Expressed as:

[0061] ;

[0062] in: is the voxel image after multimodal fusion, For the The coordinates of the tooth root center point, is the neural tube path trajectory function, For spatial points The bone density value at .

[0063] S2: Generate the anchorage pin implantation point coordinates and angle planning scheme based on the patient-specific 3D anatomical model, and simultaneously set the safety margin threshold to adjust the implantation point and angle parameters;

[0064] Specifically, based on the obtained patient-specific three-dimensional anatomical model, local voxel subdomains are extracted, and local voxel blocks are cropped from the center of each tooth root to be implanted and a sphere with a predetermined radius around it.

[0065] Obtain the root curvature, the gradient amplitude of the bone density gradient and the minimum value of the proximity distance between each root point and the neural canal;

[0066] The local voxel block and the gradient amplitude of the corresponding bone density gradient are input into the convolutional neural network, and the root curvature and the minimum value of the proximity distance between each root point and the neural canal are used as additional inputs of the fully connected layer to output the implant suitability score;

[0067] The training set is generated by historical cases and postoperative evaluation annotations, and the loss function is cross entropy loss , expressed as:

[0068] ;

[0069] in: For implant suitability score, For clinical surgical results, is the index variable.

[0070] Automatically plan the implant point and angle, taking into account bone quality, curvature, and nerve risk, and define the objective function as follows:

[0071] ;

[0072] in: is the objective function of implantation point and angle planning, are the implantation point coordinates, is the angle; is the bone density value, is the root curvature, is the proximity distance from the tooth root point to the neural canal, 、 and is the indicator weight, which is set through reinforcement learning or clinical experience;

[0073] The constraints are the distance between tooth roots and the proximity distance from the tooth root point to the neural tube. The gradient descent method is used to optimize the objective function. If the candidate solution does not meet the safety threshold, it is automatically eliminated and the search is repeated.

[0074] Real-time feedback: the current implant point and angle are rendered in real time on the MR glasses interface, and a safety boundary color band is displayed (green - safe, yellow - warning, red - dangerous).

[0075] S3: The patient-specific 3D anatomical model and the final planned implantation point coordinates are loaded into customized MR glasses. The virtual navigation mark is superimposed on the real surgical field using the occlusion elimination algorithm. The deviation between the actual implantation depth and the planned path is continuously compared. If the deviation exceeds the safety boundary threshold, a voice alarm is automatically triggered and a 3D postoperative simulation report is generated.

[0076] Specifically, the patient-specific three-dimensional anatomical model and the obtained implantation point coordinates and angles are imported into the customized MR glasses integration module.

[0077] The system defines an initial rigid transformation between the 3D model coordinate system and the world coordinate system of the MR device, and performs internal and external calibration of the MR glasses. Internally, the focal length, principal point, and distortion coefficient of the MR glasses' binocular cameras are calibrated. Externally, the relative pose of the left and right cameras is determined using a standard checkerboard calibration or a handheld calibration plate.

[0078] ORB or SIFT feature points are extracted from the binocular image pair in each frame, and descriptor matching is used for tracking: 2D-2D matching is established between adjacent frames, and 3D feature point trajectories are recovered by triangulation.

[0079] Based on the pose estimation algorithm, combined with RANSAC, we select n corresponding pairs of 3D-2D points from the known model to solve the camera pose, and use graph optimization to globally optimize the camera pose and map points.

[0080] Static features such as the operating table and instruments on the patient's head are selected as anchor points. Once detected for the first time, the relative relationship between the model and the real environment is continuously locked.

[0081] Use binocular or ToF sensors to obtain a depth map. For each implant point on the model, obtain the depth of the current view and the depth measured by the sensor. If the depth of the current view is greater than the sensor-measured depth plus the tolerance, it is considered occluded and the occluded implant point is removed from the rendering to ensure that the virtual navigation mark appears only in areas not blocked by real instruments or tissues.

[0082] The built-in torque sensor of the anchorage nail implantation device samples in real time to obtain the torque value, predetermine the safety range, read the bone density at the corresponding implantation point from the model, generate a tactile signal with a vibration frequency inversely proportional to the bone density, and calculate the instantaneous frequency of the tactile signal, which is expressed as:

[0083] ;

[0084] in: is the instantaneous frequency of the tactile signal, is the reference frequency, As a reference bone density, is the bone density conversion coefficient, is the bone density at the implantation site;

[0085] The angle between the current device direction and the target direction is calculated in real time and expressed as:

[0086] ;

[0087] in: is the angle between the current device direction and the target direction, is the current device direction, For the target direction, is the norm;

[0088] If the torque value is not within the predetermined safety range or the angle between the current device direction and the target direction exceeds the predetermined angle, a dual-modal alarm is issued through touch and vision, the navigation mark turns red, a warning bar flashes at the edge of the MR glasses' field of view, the vibration tactile signal is updated, and the correction instruction is overwritten and superimposed on the MR glasses' field of view in the form of an arrow or numerical angle.

[0089] The deviation value between the actual implantation depth and the planned path is continuously compared during the operation. When the deviation value exceeds the safety boundary threshold, a real-time voice alarm is triggered, and the deviation value and arrow indicating the correction direction are highlighted in the MR field of view. After the operation is completed, a three-dimensional postoperative simulation report is generated based on the implantation torque value, actual implantation angle and deviation correction record. Quantitative evaluation indicators such as the minimum spacing between adjacent anatomical structures of the anchorage pin and the maximum bone density variation coefficient are output to generate a three-dimensional postoperative simulation report.

[0090] Furthermore, this embodiment also provides an orthodontic anchorage pin implantation navigation system based on mixed reality technology, including:

[0091] The multimodal image fusion module is used to obtain the patient's orthodontic anchorage pin implantation surgical data and spatially register the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific 3D anatomical model;

[0092] The tactile feedback module includes a mechanical sensor and a micro-vibration motor. The mechanical sensor is used to monitor the implant torque value, and the micro-vibration motor is used to monitor the vibration intensity and frequency to feedback bone density changes, identify dangerous areas, and trigger an alarm to remind you when approaching the dangerous area;

[0093] MR visualization real-time navigation module, used to superimpose virtual navigation markers onto the real surgical field through SLAM spatial anchoring technology and occlusion elimination algorithm;

[0094] A customized MR glasses integration module for displaying patient-specific 3D anatomical models and virtual navigation markers through MR glasses, enabling multimodal interaction through gesture control, voice commands, and physical buttons;

[0095] The clinical decision-making module is used to output the implant suitability score through a deep learning model, generate the optimal anchorage nail implantation path planning scheme, dynamically evaluate surgical risks based on preset safety thresholds, provide deviation correction suggestions, and generate a postoperative three-dimensional effect simulation report and quantitative evaluation indicators.

[0096] This embodiment also provides a computer device, which is suitable for the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement all or part of the steps of the method described in the embodiment of the present invention as proposed in the above embodiment.

[0097] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, executes the method of any optional implementation of the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0098] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. Technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] In summary, on the one hand, the present invention utilizes deep learning-driven multimodal spatial registration and personalized three-dimensional modeling to achieve high precision and high reliability of the anatomical basis of implantation; on the other hand, it combines intelligent program planning, dynamic setting of safety thresholds with MR real-time navigation and multimodal early warning to effectively enhance the controllability and safety of surgical operations, and improve the accuracy, efficiency and treatment effect of orthodontic anchorage nail implantation.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology, characterized by: include, Collect the patient's orthodontic anchorage pin implantation surgical data, and perform spatial registration of the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific 3D anatomical model; Generate anchorage pin implantation point coordinates and angle planning based on the patient-specific 3D anatomical model, and simultaneously set safety margin thresholds to adjust implantation point and angle parameters; The generation of the anchorage pin implantation point coordinates and angle planning scheme based on the patient-specific three-dimensional anatomical model includes: Based on the obtained patient-specific three-dimensional anatomical model, a local voxel block is cut out from the center of each tooth root to be implanted and the surrounding sphere with a predetermined radius; Obtain the root curvature, the gradient amplitude of the bone density gradient and the minimum value of the proximity distance between each root point and the neural canal; The local voxel block and the gradient amplitude of the corresponding bone density gradient are input into the convolutional neural network, and the root curvature and the minimum value of the proximity distance between each root point and the neural canal are used as additional inputs of the fully connected layer to output the implant suitability score; The training set is generated by historical cases and postoperative evaluation annotations, and the loss function is cross entropy loss , expressed as: ； in: For implant suitability score, For clinical surgical results, is the index variable; Automatically plan the implantation point and angle, and define the objective function as: ； in: is the objective function of implantation point and angle planning, are the implantation point coordinates, is the angle; is the bone density value, is the root curvature, is the proximity distance from the tooth root point to the neural canal, 、 and is the indicator weight; The objective function is optimized and solved using the gradient descent method. If the candidate solution does not meet the safety threshold, it is automatically eliminated and re-searched. The current implantation point and angle are rendered in real time on the MR glasses interface. The patient-specific three-dimensional anatomical model and the final planned implantation point coordinates are loaded into customized MR glasses. The virtual navigation mark is superimposed on the real surgical field using the occlusion elimination algorithm. The deviation value between the actual implantation depth and the planned path is continuously compared. If the deviation value exceeds the safety boundary threshold, a voice alarm is automatically triggered and a three-dimensional postoperative simulation report is generated.

2. The method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology according to claim 1, characterized in that: The patient's oral orthodontic anchorage pin implantation surgery data includes maxillofacial bone tissue data, blood vessel and nerve canal distribution data, and tooth surface morphology data.

3. The method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology according to claim 2, characterized in that: Generating a patient-specific three-dimensional anatomical model comprises: The acquired data of patients' orthodontic anchorage implantation surgery were preprocessed and resampled to a uniform voxel size through trilinear interpolation. A multi-scale 3D deep neural network was used to extract spatial distribution features from patients' orthodontic anchorage pin implantation surgery data. The blood vessel and nerve tube distribution data and the tooth surface morphology data coordinate system are aligned to the maxillofacial bone tissue coordinate system to construct a multimodal fused voxel image to form a patient-specific three-dimensional anatomical model. , expressed as: ； in: is the voxel image after multimodal fusion, For the The coordinates of the tooth root center point, is the neural tube path trajectory function, For spatial points The bone density value at .

4. The method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology according to claim 3, characterized in that: The method of superimposing the virtual navigation mark on the real surgical field by using the occlusion elimination algorithm includes: Import the patient-specific 3D anatomical model and the obtained implantation point coordinates and angles into the customized MR glasses, perform internal and external calibration of the MR glasses, and extract ORB or SIFT feature points from the binocular image pair; For each model implant point, obtain the depth of the current view and the depth measured by the sensor; if the depth of the current view is greater than the depth measured by the sensor plus the tolerance, it is considered to be occluded and the occluded implant point is removed from the rendering; Obtaining bone density at the implantation point to generate a tactile signal, and calculating the instantaneous frequency of the tactile signal and the angle between the current device direction and the target direction; If the implant torque value is not within the predetermined safety range or the angle between the current instrument direction and the target direction exceeds the predetermined angle, a dual-modal alarm is issued through touch and vision, the navigation mark turns red, and a warning bar flashes at the edge of the MR glasses' field of view, the vibration tactile signal is updated, and the correction instruction is overwritten and superimposed on the MR glasses' field of view in the form of an arrow or numerical angle.

5. The method for navigating the implantation of orthodontic anchorage nails based on mixed reality technology according to claim 4, characterized in that: The instantaneous frequency of the tactile signal is expressed as: ； in: is the instantaneous frequency, is the reference frequency, As a reference bone density, is the bone density conversion coefficient, is the bone density at the implantation site; The angle between the current device direction and the target direction is expressed as: ； in: is the angle between the current device direction and the target direction, is the current device direction, For the target direction, is the norm.

6. An orthodontic anchorage nail implantation navigation system based on mixed reality technology, based on the orthodontic anchorage nail implantation navigation method based on mixed reality technology according to any one of claims 1 to 5, characterized in that: include, The multimodal image fusion module is used to obtain the patient's orthodontic anchorage pin implantation surgical data and spatially register the patient's orthodontic anchorage pin implantation navigation data based on a deep learning feature matching algorithm to generate a patient-specific 3D anatomical model; The tactile feedback module includes a mechanical sensor and a micro-vibration motor. The mechanical sensor is used to monitor the implant torque value, and the micro-vibration motor is used to monitor the vibration intensity and frequency to feedback bone density changes, identify dangerous areas, and trigger an alarm to remind you when approaching the dangerous area; MR visualization real-time navigation module, used to superimpose virtual navigation markers onto the real surgical field through SLAM spatial anchoring technology and occlusion elimination algorithm; Customized MR glasses integration module for displaying patient-specific 3D anatomical models and virtual navigation markers through MR glasses, enabling multimodal interaction through gesture control, voice commands, and physical buttons; The clinical decision-making module is used to output the implant suitability score through a deep learning model, generate the optimal anchorage nail implantation path planning scheme, dynamically evaluate surgical risks based on preset safety thresholds, provide deviation correction suggestions, and generate a postoperative three-dimensional effect simulation report and quantitative evaluation indicators.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the oral orthodontic anchorage nail implantation navigation method based on mixed reality technology according to any one of claims 1 to 5 are implemented.

Images