Personalized tooth modeling method and system based on digital oral cavity imaging

Abstract

The invention discloses a personalized tooth modeling method and system based on digital oral cavity imaging, and relates to the technical field of digital modeling. The invention discloses a personalized tooth modeling system based on digital oral imaging. The personalized tooth modeling system comprises a data acquisition module, a model construction module, a model fusion module, a tooth gap labeling module, a tooth health prediction module and a nursing matching module. According to the method, the personalized tooth model is generated by synthesizing the tooth structure and activity range data of the user, and the deep cleaning scheme and the daily nursing scheme are accurately matched according to the tooth gap and tooth surface health condition, so that the nursing scheme of each user can be customized according to the unique oral cavity condition; by comprehensively acquiring the tooth and jaw structure, the tooth movement range and the health information of the user, the accuracy and comprehensiveness of the model are ensured, and sufficient data support is provided for subsequent cleaning and nursing schemes.

Description

Technical Field

[0001] The present invention relates to the technical field of digital modeling, and in particular to a personalized tooth modeling method and system based on digital oral imaging. Background Art

[0002] As people pay more attention to oral health, tooth cleaning and care has become an important part of daily life. However, due to the differences in tooth structure and health status of each person, traditional tooth cleaning methods are difficult to achieve personalized care and often cannot effectively cover all hidden areas of teeth, especially the gaps between teeth and the root area. With the continuous development of digital oral imaging technology, personalized dental care based on digital models has gradually become a trend.

[0003] At present, digital oral scanning technology and 3D modeling technology have been widely used in tooth detection and treatment design. By using oral digital scanners (such as CBCT equipment) and magnetic position sensors, the visible and invisible parts of teeth (such as roots, alveolar bones, etc.) can be scanned with high precision to generate 3D digital models. These models can provide doctors with detailed structural data of teeth and periodontal tissues, thereby providing data support for personalized treatment plans.

[0004] However, most of the existing digital tooth modeling technologies focus on physical structure modeling of teeth and basic diagnostic support, lacking comprehensive analysis of dental health information and automatic matching of personalized care plans. For example, existing technologies are usually unable to automatically match appropriate deep cleaning tools and daily care plans based on factors such as the specific exposure of tooth gaps and the health status of tooth surfaces. In addition, since each person's dental condition is different, existing universal care plans cannot be accurately customized to the specific needs of each user. Summary of the invention

[0005] A personalized tooth modeling method based on digital oral imaging comprises the following steps:

[0006] Step S1: obtaining scanned image data of the visible part of the user's teeth through a digital oral scanner; obtaining structural image data of the invisible part of the user's teeth through a CBCT device; obtaining the range of motion data of the user's jawbone through a magnetic position sensor; and collecting the user's dental health information; the invisible part includes the tooth root, alveolar bone, dental calculus and jawbone in the soft tissue hidden under the surface gums; the dental health information includes brushing data and diet data;

[0007] Step S2: Generate a three-dimensional digital model of the crown surface by scanning the image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including the tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jawbone by scanning the image data, which are recorded as tooth positive model 2 and jawbone model respectively;

[0008] Step S3: Fit the positive tooth model 1 and the positive tooth model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model; the tooth model simulates the range of motion of the tooth through the range of motion data;

[0009] Step S4: inputting the full positive model into the tooth gap analysis model for calculation to obtain the tooth gap annotation information of the full positive model; the tooth gap annotation information is divided into two categories, namely, tooth gap annotation information for removing tartar and retaining tartar; the tooth gap includes crown gap and root gap;

[0010] Step S5: inputting the user's dental health information and the full positive model with tooth gap annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information; the dental health prediction information includes tooth surface health information and tooth gap health information;

[0011] Step S6: Match a personalized dental care plan for the user based on the tooth model and dental health prediction information, obtain the tooth gap health level based on the tooth gap health information corresponding to the tooth gap, and match a deep dental care plan for the user based on the tooth gap health level; match a daily dental care plan for the user based on the tooth surface health information.

[0012] As a preferred technical solution of the present invention, the step of generating a three-dimensional digital model of the crown surface by scanning image data includes:

[0013] Data collection: Use a high-precision digital oral scanner to scan the user's tooth surface in sections to obtain multiple sections of scanned image data, which are stored in the form of point cloud data;

[0014] Preprocessing: Process the point cloud data corresponding to the scanned image data. The processing operations include noise filtering, point cloud simplification and point cloud registration; integrate the segmented scanned image data into a complete point cloud model;

[0015] Initial model construction: Use a meshing algorithm to convert the processed point cloud data into a triangular patch structure to generate a preliminary three-dimensional digital model of the crown surface;

[0016] Model optimization: Perform surface repair and smoothing on the preliminary 3D digital model; enhance the model's detail accuracy and preserve the true texture of the crown surface through size correction and texture mapping;

[0017] Model storage: Save the optimized 3D digital model in 3D data format for subsequent fitting, analysis and design.

[0018] As a preferred technical solution of the present invention, the steps of generating a three-dimensional digital model of the jaw bone including the tooth root, alveolar bone and dental calculus through structural image data include:

[0019] Data collection: The structural image data of the user's oral cavity is obtained through the CBCT device. The structural image includes complete image information including tooth roots, alveolar bones, dental calculus and jaw bones;

[0020] Preprocessing: Preprocess the structural image data. The preprocessing operations include grayscale calibration, noise removal and image enhancement.

[0021] Image segmentation: Use image segmentation to segment the target areas of tooth root, alveolar bone, dental calculus and jawbone from the preprocessed structural image data, where dental calculus is extracted by refinement segmentation technology;

[0022] Initial model construction: The segmented target area is converted into a 3D model through a 3D reconstruction algorithm, and volume reconstruction is used to generate a preliminary digital 3D model of the tooth root, alveolar bone, dental calculus, and a preliminary digital 3D model of the jawbone;

[0023] Model optimization: Smoothing and topology optimization of the generated preliminary digital 3D model;

[0024] Model storage: Save the optimized preliminary numerical 3D model in 3D data format.

[0025] As a preferred technical solution of the present invention, the steps of fitting the positive tooth model 1 and the positive tooth model 2 to obtain a full positive model include:

[0026] The coordinate difference of data acquisition is eliminated by calibrating the equipment, so that the three-dimensional digital models of the positive dental model 1 and the positive dental model 2 are in the same coordinate system;

[0027] Mark the key points of the tooth model, including the cervical margin at the junction of the crown and root, the cusp point and the significant feature points of the alveolar bone, and use the feature point matching method for preliminary alignment;

[0028] The point cloud registration algorithm is used to accurately align the overlapping areas of positive mold 1 and positive mold 2, and the overlapping error of the two models is optimized through non-rigid registration;

[0029] A surface interpolation algorithm is used to generate a smooth transition area at the junction of the crown and root to ensure the consistency and continuity of the model boundary;

[0030] The positive tooth model 1 and the positive tooth model 2 are combined to generate a complete three-dimensional digital model of the tooth as a full positive model through Boolean operation;

[0031] The full positive model is fitted with the jaw model by the same method to obtain the tooth model, and the range of tooth movement is added to the tooth model.

[0032] As a preferred technical solution of the present invention, the step of simulating the range of motion of teeth by using the range of motion data includes:

[0033] The magnetic position sensor is used to obtain the range of motion data of the user's jaw, including the following steps: fixing the magnetic transmitter at a stable position on the patient's head, installing the magnetic receiver on the mandible, and stabilizing the receiver by a bracket or a dental tray; setting the patient's initial static state as a reference zero point through a calibration step, and recording the initial position information of the jaw in three-dimensional space; guiding the patient to complete standardized actions such as opening and closing the mouth, protruding, retracting, and moving left and right, and the sensor records the jaw movement trajectory in real time; filtering and coordinate conversion of the recorded data to obtain the range of motion data of the user's jaw, and adding it to the reference coordinate system of the tooth model;

[0034] The range of motion data is used to establish a motion model of the mandibular joint, simulate joint rotation and sliding, and apply it as a motion parameter to the tooth model to simulate the range of motion; the rotation and displacement of the teeth are simulated through the rigid body kinematics formula to generate the motion trajectory of the teeth.

[0035] As a preferred technical solution of the present invention, the step of inputting the full positive model into the tooth gap analysis model for calculation to obtain the tooth gap annotation information of the full positive model includes:

[0036] Model layer division: The full positive model is divided into layers, including the crown layer, root layer and alveolar bone layer;

[0037] Model loading and calibration: Input the layered full-positive model into the tooth space analysis model to align the coordinate system;

[0038] Data classification and analysis, including the height of contact points, degree of gap exposure and root surface exposure;

[0039] A1. Classification of contact points: By analyzing the total distance from the occlusal surface to the junction of the tooth root and the bone edge, the tooth model is divided into the upper 1 / 3, middle 1 / 3 and lower 1 / 3, marked as high, middle and low respectively;

[0040] A2. Classification of space exposure: According to the lateral loss level of space exposure, it is divided into 1 degree (1 / 3) of space exposure, 2 degree (2 / 3) of space exposure and 3 degree (3 / 3) of space exposure, and the space areas are marked one by one;

[0041] A3. Classification of root surface exposure: Compare the relative position of the uppermost part of the bone junction with the enamel-cementum junction of the normal binding site, and mark the scale of the exposed part of the root surface; according to the exposure depth, it is divided into mild level within 3mm, moderate level of 3-6mm and severe level above 6mm;

[0042] Hollow body modeling: According to the gaps between teeth, two types of closed hollow bodies are generated, including hollow body A and hollow body B, which are recorded as crown gap and root gap respectively; the volume, shape and boundary characteristics of hollow body A and hollow body B are analyzed and a detailed geometric description is generated; the crown gap is a closed geometric body generated by the boundary curve and surface of the exposed space between the crowns, and the crown gap is a closed geometric body generated by the contour of the exposed area between the roots;

[0043] Gap detection and calculation: Apply point cloud distance calculation and volume analysis algorithms to measure the three-dimensional volume and minimum distance of empty body A and empty body B; generate independent annotations for areas containing dental calculus, and record the volume of empty bodies with and without dental calculus;

[0044] Classification and annotation generation: Generate three types of annotation information by combining the high and low classification of contact points, the classification of gap exposure and the classification of root surface exposure; use color and layer to annotate empty body A and empty body B, and display them in a classified and graded manner;

[0045] Result export and application: Output the classification annotation information and the empty body model as tooth space annotation information; record the classification results as a classification data table and export it.

[0046] As a preferred technical solution of the present invention, the steps of inputting the user's dental health information and the full positive model with tooth space annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information include:

[0047] Data preparation: Import the full positive model with tooth gap annotations, and ensure that the model contains the classified annotation information of crown gaps and root gaps; load the user's dental health information, including brushing habits and eating habits, and standardize it into feature values ​​recognized by the model;

[0048] Data fusion: Extract geometric features from the full positive model, including gap volume, gap distribution, exposure degree and root surface exposure scale; extract behavioral features from user health information, such as brushing intensity, cleaning area and potential impact of diet structure; merge geometric features and behavioral features into a complete data set and perform unified quantitative processing;

[0049] Health risk assessment: Input the fused data into the dental health prediction model to evaluate the correlation between tooth gaps and dental health information; Based on the model calculation results, evaluate the cleaning difficulty and potential health risks of tooth gaps and generate the risk level of the cleaning area; Based on the root exposure and gap characteristics, predict the probability of tartar accumulation, gingival recession and root caries;

[0050] Generate user's dental health prediction information, including the following: Tooth surface health information: the cleaning status and health level of the tooth surface; Tooth gap health information: the health status and risk assessment of the crown gap and root gap.

[0051] As a preferred technical solution of the present invention, the steps of matching a personalized dental care plan for a user according to a dental model and dental health prediction information include:

[0052] Matching deep dental care plans according to the tooth gap health level: combining the empty body A and the empty body B of a tooth gap to obtain the complete gap structure of the current part, obtaining the classification of the current part according to the classification data table, and dividing the tooth gap health level, which includes healthy, mild risk, moderate risk and high risk. The tooth gap area with a health level below the set threshold requires intensive care; matching deep care tools and care plans according to the tooth gap health level; the care tools include customized brush heads and corresponding navigation grooves;

[0053] Match daily dental care plans based on tooth surface health information: Based on tooth surface health information, the tooth surface conditions are divided into healthy, slightly damaged, moderately damaged and severely damaged, and daily care tools and methods are matched according to different levels;

[0054] The tooth model is used to obtain the range of activity of the user's teeth and match the tooth care method according to the range of activity;

[0055] Integrate the in-depth dental care plan with the daily dental care plan to generate the final user-personalized dental care plan.

[0056] A personalized tooth modeling system based on digital oral imaging, including the following modules:

[0057] Data acquisition module: used to obtain scanned image data of the visible part of the user's teeth through a digital oral scanner; obtain structural image data of the invisible part of the user's teeth through a CBCT device; obtain the range of motion data of the user's jaw through a magnetic position sensor; and collect the user's dental health information;

[0058] Model building module: used to generate a three-dimensional digital model of the crown surface through scanning image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jaw through structural image data, which are recorded as tooth positive model 2 and jaw model respectively;

[0059] Model fusion module: used to fit the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model;

[0060] Tooth gap marking module: used to input the full positive model into the tooth gap analysis model for calculation, and obtain the tooth gap marking information of the full positive model;

[0061] Dental health prediction module: used to input the user's dental health information and the full positive model with tooth space annotations into the dental health prediction model for calculation to obtain the user's dental health prediction information;

[0062] Care matching module: used to match personalized dental care plans for users based on dental models and dental health prediction information.

[0063] The present invention has the following advantages:

[0064] The present invention generates a personalized tooth model by integrating the user's tooth structure and range of motion data, and accurately matches the deep cleaning plan and daily care plan according to the tooth gap and tooth surface health, ensuring that each user's care plan can be customized according to their unique oral condition; by combining digital oral scanning, CBCT imaging technology and magnetic position sensors, it can fully obtain the user's tooth and jaw structure, tooth range of motion and health information, ensure the accuracy and comprehensiveness of the model, and provide sufficient data support for subsequent cleaning and care plans.

[0065] The present invention conducts a detailed analysis of the crown gap and root gap, and classifies them according to the exposure degree and health level. It can accurately identify the hidden parts of the teeth and the cleaning difficulty, and provide users with accurate deep care solutions. According to the tooth gap and tooth surface health level, the present invention automatically recommends and matches customized brush heads and brushing guides to ensure that the cleaning tools can accurately reach and effectively clean the hard-to-reach tooth gaps, thereby improving cleaning efficiency and effectiveness.

[0066] The present invention simplifies the tooth care process and reduces the complexity and errors of manual operations through automated processing of digital models and precise matching of care plans, thus providing users with a more convenient and accurate oral care experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1A schematic diagram of the structure of a personalized tooth modeling system based on digital oral imaging adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0069] Embodiment 1, a personalized tooth modeling method based on digital oral imaging, comprising the following steps:

[0070] Step S1: obtaining scanned image data of the visible part of the user's teeth through a digital oral scanner; obtaining structural image data of the invisible part of the user's teeth through a CBCT device; obtaining the range of motion data of the user's jawbone through a magnetic position sensor; and collecting the user's dental health information; the invisible part includes the tooth root, alveolar bone, dental calculus and jawbone in the soft tissue hidden under the surface gums; the dental health information includes brushing data and diet data;

[0071] Step S2: Generate a three-dimensional digital model of the crown surface by scanning the image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including the tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jawbone by scanning the image data, which are recorded as tooth positive model 2 and jawbone model respectively;

[0072] The steps of generating a three-dimensional digital model of the crown surface by scanning image data include:

[0073] Data collection: Use a high-precision digital oral scanner to scan the user's tooth surface in sections to obtain multiple sections of scanned image data, which are stored in the form of point cloud data;

[0074] Preprocessing: Process the point cloud data corresponding to the scanned image data. The processing operations include noise filtering, point cloud simplification and point cloud registration; integrate the segmented scanned image data into a complete point cloud model;

[0075] Initial model construction: Use a meshing algorithm to convert the processed point cloud data into a triangular patch structure to generate a preliminary three-dimensional digital model of the crown surface;

[0076] Model optimization: Perform surface repair and smoothing on the preliminary 3D digital model; enhance the model's detail accuracy and preserve the true texture of the crown surface through size correction and texture mapping;

[0077] Model storage: Save the optimized 3D digital model in 3D data format for subsequent fitting, analysis and design.

[0078] The steps of generating a three-dimensional digital model of the jaw bone including the tooth root, alveolar bone and dental calculus by using the structural image data include:

[0079] Data collection: The structural image data of the user's oral cavity is obtained through the CBCT device. The structural image includes complete image information including tooth roots, alveolar bones, dental calculus and jaw bones;

[0080] Preprocessing: Preprocess the structural image data. The preprocessing operations include grayscale calibration, noise removal and image enhancement.

[0081] Image segmentation: Use image segmentation to segment the target areas of tooth root, alveolar bone, dental calculus and jawbone from the preprocessed structural image data, where dental calculus is extracted by refinement segmentation technology;

[0082] Initial model construction: The segmented target area is converted into a 3D model through a 3D reconstruction algorithm, and volume reconstruction is used to generate a preliminary digital 3D model of the tooth root, alveolar bone, dental calculus, and a preliminary digital 3D model of the jawbone;

[0083] Model optimization: Smoothing and topology optimization of the generated preliminary digital 3D model;

[0084] Model storage: Save the optimized preliminary numerical 3D model in 3D data format.

[0085] Step S3: Fit the positive tooth model 1 and the positive tooth model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model; the tooth model simulates the range of motion of the tooth through the range of motion data;

[0086] The steps of fitting the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model include:

[0087] The coordinate difference of data acquisition is eliminated by calibrating the equipment, so that the three-dimensional digital models of the positive dental model 1 and the positive dental model 2 are in the same coordinate system;

[0088] Mark the key points of the tooth model, including the cervical margin at the junction of the crown and root, the cusp point and the significant feature points of the alveolar bone, and use the feature point matching method for preliminary alignment;

[0089] The point cloud registration algorithm is used to accurately align the overlapping areas of positive mold 1 and positive mold 2, and the overlapping error of the two models is optimized through non-rigid registration;

[0090] A surface interpolation algorithm is used to generate a smooth transition area at the junction of the crown and root to ensure the consistency and continuity of the model boundary;

[0091] The positive tooth model 1 and the positive tooth model 2 are combined to generate a complete three-dimensional digital model of the tooth as a full positive model through Boolean operation;

[0092] The full positive model is fitted with the jaw model by the same method to obtain the tooth model, and the range of tooth movement is added to the tooth model.

[0093] The steps of simulating the range of motion of teeth using range of motion data include:

[0094] The magnetic position sensor is used to obtain the range of motion data of the user's jaw, including the following steps: fixing the magnetic transmitter at a stable position on the patient's head, installing the magnetic receiver on the mandible, and stabilizing the receiver by a bracket or a dental tray; setting the patient's initial static state as a reference zero point through a calibration step, and recording the initial position information of the jaw in three-dimensional space; guiding the patient to complete standardized actions such as opening and closing the mouth, protruding, retracting, and moving left and right, and the sensor records the jaw movement trajectory in real time; filtering and coordinate conversion of the recorded data to obtain the range of motion data of the user's jaw, and adding it to the reference coordinate system of the tooth model;

[0095] The range of motion data is used to establish a motion model of the mandibular joint, simulate joint rotation and sliding, and apply it as a motion parameter to the tooth model to simulate the range of motion; the rotation and displacement of the teeth are simulated through the rigid body kinematics formula to generate the motion trajectory of the teeth.

[0096] Step S4: inputting the full positive model into the tooth gap analysis model for calculation to obtain the tooth gap annotation information of the full positive model; the tooth gap annotation information is divided into two categories, namely, tooth gap annotation information for removing tartar and retaining tartar; the tooth gap includes crown gap and root gap;

[0097] The steps of inputting the full positive model into the tooth gap analysis model for calculation and obtaining the tooth gap annotation information of the full positive model include:

[0098] Model layer division: The full positive model is divided into layers, including the crown layer, root layer and alveolar bone layer;

[0099] Model loading and calibration: Input the layered full-positive model into the tooth space analysis model to align the coordinate system;

[0100] Data classification and analysis, including the height of contact points, degree of gap exposure and root surface exposure;

[0101] A1. Classification of contact points: By analyzing the total distance from the occlusal surface to the junction of the tooth root and the bone edge, the tooth model is divided into the upper 1 / 3, middle 1 / 3 and lower 1 / 3, marked as high, middle and low respectively;

[0102] A2. Classification of space exposure: According to the lateral loss level of space exposure, it is divided into 1 degree (1 / 3) of space exposure, 2 degree (2 / 3) of space exposure and 3 degree (3 / 3) of space exposure, and the space areas are marked one by one;

[0103] A3. Classification of root surface exposure: Compare the relative position of the uppermost part of the bone junction with the enamel-cementum junction of the normal binding site, and mark the scale of the exposed part of the root surface; according to the exposure depth, it is divided into mild level within 3mm, moderate level of 3-6mm and severe level above 6mm;

[0104] Hollow body modeling: According to the gaps between teeth, two types of closed hollow bodies are generated, including hollow body A and hollow body B, which are recorded as crown gap and root gap respectively; the volume, shape and boundary characteristics of hollow body A and hollow body B are analyzed and a detailed geometric description is generated; the crown gap is a closed geometric body generated by the boundary curve and surface of the exposed space between the crowns, and the crown gap is a closed geometric body generated by the contour of the exposed area between the roots;

[0105] Gap detection and calculation: Apply point cloud distance calculation and volume analysis algorithms to measure the three-dimensional volume and minimum distance of empty body A and empty body B; generate independent annotations for areas containing dental calculus, and record the volume of empty bodies with and without dental calculus;

[0106] Classification and annotation generation: Generate three types of annotation information by combining the high and low classification of contact points, the classification of gap exposure and the classification of root surface exposure; use color and layer to annotate empty body A and empty body B, and display them in a classified and graded manner;

[0107] Result export and application: Output the classification annotation information and the empty body model as tooth space annotation information; record the classification results as a classification data table and export it.

[0108] Step S5: inputting the user's dental health information and the full positive model with tooth gap annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information; the dental health prediction information includes tooth surface health information and tooth gap health information;

[0109] The steps of inputting the user's dental health information and the full positive model with tooth space annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information include:

[0110] Data preparation: Import the full positive model with tooth gap annotations, and ensure that the model contains the classified annotation information of crown gaps and root gaps; load the user's dental health information, including brushing habits and eating habits, and standardize it into feature values ​​recognized by the model;

[0111] Data fusion: Extract geometric features from the full positive model, including gap volume, gap distribution, exposure degree and root surface exposure scale; extract behavioral features from user health information, such as brushing intensity, cleaning area and potential impact of diet structure; merge geometric features and behavioral features into a complete data set and perform unified quantitative processing;

[0112] Health risk assessment: Input the fused data into the dental health prediction model to evaluate the correlation between tooth gaps and dental health information; Based on the model calculation results, evaluate the cleaning difficulty and potential health risks of tooth gaps and generate the risk level of the cleaning area; Based on the root exposure and gap characteristics, predict the probability of tartar accumulation, gingival recession and root caries;

[0113] Generate user's dental health prediction information, including the following: Tooth surface health information: the cleaning status and health level of the tooth surface; Tooth gap health information: the health status and risk assessment of the crown gap and root gap.

[0114] Step S6: Match a personalized dental care plan for the user based on the tooth model and dental health prediction information, obtain the tooth gap health level based on the tooth gap health information corresponding to the tooth gap, and match a deep dental care plan for the user based on the tooth gap health level; match a daily dental care plan for the user based on the tooth surface health information.

[0115] Matching deep dental care plans according to the tooth gap health level: combining the empty body A and the empty body B of a tooth gap to obtain the complete gap structure of the current part, obtaining the classification of the current part according to the classification data table, and dividing the tooth gap health level, which includes healthy, mild risk, moderate risk and high risk. The tooth gap area with a health level below the set threshold requires intensive care; matching deep care tools and care plans according to the tooth gap health level; the care tools include customized brush heads and corresponding navigation grooves;

[0116] Match daily dental care plans based on tooth surface health information: Based on tooth surface health information, the tooth surface conditions are divided into healthy, slightly damaged, moderately damaged and severely damaged, and daily care tools and methods are matched according to different levels;

[0117] The tooth model is used to obtain the range of activity of the user's teeth and match the tooth care method according to the range of activity;

[0118] Integrate the in-depth dental care plan with the daily dental care plan to generate the final user-personalized dental care plan.

[0119] Example 2, a personalized tooth modeling system based on digital oral imaging, see Figure 1 As shown, the following steps are included:

[0120] Data acquisition module: used to obtain scanned image data of the visible part of the user's teeth through a digital oral scanner; obtain structural image data of the invisible part of the user's teeth through a CBCT device; obtain the range of motion data of the user's jaw through a magnetic position sensor; and collect the user's dental health information;

[0121] Model building module: used to generate a three-dimensional digital model of the crown surface through scanning image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jaw through structural image data, which are recorded as tooth positive model 2 and jaw model respectively;

[0122] Model fusion module: used to fit the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model;

[0123] Tooth gap marking module: used to input the full positive model into the tooth gap analysis model for calculation, and obtain the tooth gap marking information of the full positive model;

[0124] Dental health prediction module: used to input the user's dental health information and the full positive model with tooth space annotations into the dental health prediction model for calculation to obtain the user's dental health prediction information;

[0125] Care matching module: used to match personalized dental care plans for users based on dental models and dental health prediction information.

[0126] Embodiment 3, a personalized tooth modeling method and system based on digital oral imaging, comprising the following steps:

[0127] Data collection and modeling: The patient uses a digital oral scanner to collect images of the visible part of the teeth, and the CBCT device scans the invisible structure (including tooth roots, alveolar bones, etc.), and obtains the range of motion data of the jaw through a magnetic position sensor. The system automatically converts the collected image data into a three-dimensional digital model to generate a crown surface model, a tooth root model, and a jaw model. Based on the data of the model, the system generates a full positive model of the patient, and fits the full positive model with the jaw model to simulate the range of motion of the teeth.

[0128] Tooth gap analysis and health prediction: The system automatically analyzes the crown gap and root gap in detail, identifies the exposure of the tooth gap, and generates tooth gap annotation information based on the condition of dental calculus. The tooth model and tooth health information are input into the tooth health prediction model, and the system calculates and generates the user's tooth health prediction information, providing a detailed report on tooth surface health and tooth gap health.

[0129] Matching personalized care plans: The system matches the appropriate deep cleaning plan based on the health level of the tooth gap. If the health level of the tooth gap is low, the system will recommend the use of tools such as customized brush heads and brushing guides for deep cleaning, and adjust the cleaning path according to the range of motion of the teeth. Based on the tooth surface health information, the system matches the patient with a daily care plan, such as recommending toothpaste, toothbrush type and brushing method suitable for tooth surface health, and providing recommendations on brushing frequency.

[0130] Regular review and dynamic update: Patients perform daily care according to the recommendations and have a review after the agreed time. During the review, the patient's latest dental health data will be re-collected, and the system will dynamically update the care plan based on the new data to ensure the timeliness and pertinence of the care plan.

[0131] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A personalized tooth modeling method based on digital oral imaging, characterized in that: The following steps are involved: Step S1: obtaining scanned image data of the visible part of the user's teeth through a digital oral scanner; The structure image data of the invisible part of the user's teeth is obtained through the CBCT device; the range of motion data of the user's jawbone is obtained through the magnetic position sensor; and the user's dental health information is collected; the invisible part includes the tooth root, alveolar bone, dental calculus and jawbone in the soft tissue hidden under the surface gums; the dental health information includes brushing data and diet data; Step S2: Generate a three-dimensional digital model of the crown surface by scanning the image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including the tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jawbone by scanning the image data, which are recorded as tooth positive model 2 and jawbone model respectively; Step S3: Fit the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model; The tooth model simulates the range of motion of the tooth through the range of motion data; Step S4: input the full positive model into the tooth gap analysis model for calculation to obtain the tooth gap annotation information of the full positive model; The tooth gap marking information is divided into two categories, namely, tooth gap marking information for removing dental calculus and tooth gap marking information for retaining dental calculus; The tooth gap includes the crown gap and the root gap; Step S5: inputting the user's dental health information and the full positive model with tooth gap annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information; the dental health prediction information includes tooth surface health information and tooth gap health information; Step S6: matching a personalized dental care plan for the user according to the tooth model and the dental health prediction information, obtaining a dental gap health level according to the dental gap health information corresponding to the tooth gap, and matching a deep dental care plan for the user according to the dental gap health level; Match daily dental care plans for users based on dental health information.

2. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of generating a three-dimensional digital model of the crown surface by scanning image data include: Data collection: Use a high-precision digital oral scanner to scan the user's tooth surface in sections to obtain multiple sections of scanned image data, which are stored in the form of point cloud data; Preprocessing: Process the point cloud data corresponding to the scanned image data. The processing operations include noise filtering, point cloud simplification and point cloud registration; integrate the segmented scanned image data into a complete point cloud model; Initial model construction: Use a meshing algorithm to convert the processed point cloud data into a triangular patch structure to generate a preliminary three-dimensional digital model of the crown surface; Model optimization: Perform surface repair and smoothing on the preliminary 3D digital model; enhance the model's detail accuracy and preserve the true texture of the crown surface through size correction and texture mapping; Model storage: Save the optimized 3D digital model in 3D data format for subsequent fitting, analysis and design.

3. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of generating a three-dimensional digital model of the jaw bone including the tooth root, alveolar bone and dental calculus by using the structural image data include: Data collection: The structural image data of the user's oral cavity is obtained through the CBCT device. The structural image includes complete image information including tooth roots, alveolar bones, dental calculus and jaw bones; Preprocessing: Preprocess the structural image data. The preprocessing operations include grayscale calibration, noise removal and image enhancement. Image segmentation: Use image segmentation to segment the target areas of tooth root, alveolar bone, dental calculus and jawbone from the preprocessed structural image data, where dental calculus is extracted by refinement segmentation technology; Initial model construction: The segmented target area is converted into a 3D model through a 3D reconstruction algorithm, and volume reconstruction is used to generate a preliminary digital 3D model of the tooth root, alveolar bone, dental calculus, and a preliminary digital 3D model of the jawbone; Model optimization: Smoothing and topology optimization of the generated preliminary digital 3D model; Model storage: Save the optimized preliminary numerical 3D model in 3D data format.

4. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of fitting the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model include: The coordinate difference of data acquisition is eliminated by calibrating the equipment, so that the three-dimensional digital models of the positive dental model 1 and the positive dental model 2 are in the same coordinate system; Mark the key points of the tooth model, including the cervical margin at the junction of the crown and root, the cusp point and the significant feature points of the alveolar bone, and use the feature point matching method for preliminary alignment; The point cloud registration algorithm is used to accurately align the overlapping areas of positive mold 1 and positive mold 2, and the overlapping error of the two models is optimized through non-rigid registration; A surface interpolation algorithm is used to generate a smooth transition area at the junction of the crown and root to ensure the consistency and continuity of the model boundary; The positive tooth model 1 and the positive tooth model 2 are combined to generate a complete three-dimensional digital model of the tooth as a full positive model through Boolean operation; The full positive model is fitted with the jaw model by the same method to obtain the tooth model, and the range of tooth movement is added to the tooth model.

5. The personalized tooth modeling method based on digital oral imaging according to claim 4, characterized in that: The steps of simulating the range of motion of teeth using range of motion data include: The magnetic position sensor is used to obtain the range of motion data of the user's jaw, including the following steps: fixing the magnetic transmitter at a stable position on the patient's head, installing the magnetic receiver on the mandible, and stabilizing the receiver by a bracket or a dental tray; setting the patient's initial static state as a reference zero point through a calibration step, and recording the initial position information of the jaw in three-dimensional space; guiding the patient to complete standardized actions such as opening and closing the mouth, protruding, retracting, and moving left and right, and the sensor records the jaw movement trajectory in real time; filtering and coordinate conversion of the recorded data to obtain the range of motion data of the user's jaw, and adding it to the reference coordinate system of the tooth model; The range of motion data is used to establish a motion model of the mandibular joint, simulate joint rotation and sliding, and apply it as a motion parameter to the tooth model to simulate the range of motion; the rotation and displacement of the teeth are simulated through the rigid body kinematics formula to generate the motion trajectory of the teeth.

6. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of inputting the full positive model into the tooth gap analysis model for calculation and obtaining the tooth gap annotation information of the full positive model include: Model layer division: The full positive model is divided into layers, including the crown layer, root layer and alveolar bone layer; Model loading and calibration: Input the layered full-positive model into the tooth space analysis model to align the coordinate system; Data classification and analysis, including the height of contact points, degree of gap exposure and root surface exposure; A1. Classification of contact points: By analyzing the total distance from the occlusal surface to the junction of the tooth root and the bone edge, the tooth model is divided into the upper 1 / 3, middle 1 / 3 and lower 1 / 3, marked as high, middle and low respectively; A2. Classification of space exposure: According to the lateral loss level of space exposure, it is divided into 1 degree (1 / 3) of space exposure, 2 degree (2 / 3) of space exposure and 3 degree (3 / 3) of space exposure, and the space areas are marked one by one; A3. Classification of root surface exposure: Compare the relative position of the uppermost part of the bone junction with the enamel-cementum junction of the normal binding site, and mark the scale of the exposed part of the root surface; according to the exposure depth, it is divided into mild level within 3mm, moderate level of 3-6mm and severe level above 6mm; Hollow body modeling: According to the gaps between teeth, two types of closed hollow bodies are generated, including hollow body A and hollow body B, which are recorded as crown gap and root gap respectively; the volume, shape and boundary characteristics of hollow body A and hollow body B are analyzed and a detailed geometric description is generated; the crown gap is a closed geometric body generated by the boundary curve and surface of the exposed space between the crowns, and the crown gap is a closed geometric body generated by the contour of the exposed area between the roots; Gap detection and calculation: Apply point cloud distance calculation and volume analysis algorithms to measure the three-dimensional volume and minimum distance of empty body A and empty body B; generate independent annotations for areas containing dental calculus, and record the volume of empty bodies with and without dental calculus; Classification and annotation generation: Generate three types of annotation information by combining the high and low classification of contact points, the classification of gap exposure and the classification of root surface exposure; use color and layer to annotate empty body A and empty body B, and display them in a classified and graded manner; Result export and application: Output the classification annotation information and the empty body model as tooth space annotation information; record the classification results as a classification data table and export it.

7. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of inputting the user's dental health information and the full positive model with tooth space annotation into the dental health prediction model for calculation to obtain the user's dental health prediction information include: Data preparation: Import the full positive model with tooth gap annotations, and ensure that the model contains the classified annotation information of crown gaps and root gaps; load the user's dental health information, including brushing habits and eating habits, and standardize it into feature values ​​recognized by the model; Data fusion: Extract geometric features from the full positive model, including gap volume, gap distribution, exposure degree and root surface exposure scale; extract behavioral features from user health information, such as brushing intensity, cleaning area and potential impact of diet structure; merge geometric features and behavioral features into a complete data set and perform unified quantitative processing; Health risk assessment: Input the fused data into the dental health prediction model to evaluate the correlation between tooth gaps and dental health information; Based on the model calculation results, evaluate the cleaning difficulty and potential health risks of tooth gaps and generate the risk level of the cleaning area; Based on the root exposure and gap characteristics, predict the probability of tartar accumulation, gingival recession and root caries; Generate user's dental health prediction information, including the following: Tooth surface health information: the cleaning status and health level of the tooth surface; Tooth gap health information: the health status and risk assessment of the crown gap and root gap.

8. The personalized tooth modeling method based on digital oral imaging according to claim 1, characterized in that: The steps of matching a personalized dental care plan for a user based on the dental model and dental health prediction information include: Matching deep dental care plans according to the tooth gap health level: combining the empty body A and the empty body B of a tooth gap to obtain the complete gap structure of the current part, obtaining the classification of the current part according to the classification data table, and dividing the tooth gap health level, which includes healthy, mild risk, moderate risk and high risk. The tooth gap area with a health level below the set threshold requires intensive care; matching deep care tools and care plans according to the tooth gap health level; the care tools include customized brush heads and corresponding navigation grooves; Match daily dental care plans based on tooth surface health information: Based on tooth surface health information, the tooth surface conditions are divided into healthy, slightly damaged, moderately damaged and severely damaged, and daily care tools and methods are matched according to different levels; The tooth model is used to obtain the range of activity of the user's teeth and match the tooth care method according to the range of activity; Integrate the in-depth dental care plan with the daily dental care plan to generate the final user-personalized dental care plan.

9. A personalized tooth modeling system based on digital oral imaging, the system applying a personalized tooth modeling method based on digital oral imaging according to any one of claims 1 to 8, comprising the following modules: Data acquisition module: used to obtain scanned image data of the visible part of the user's teeth through a digital oral scanner; obtain structural image data of the invisible part of the user's teeth through a CBCT device; obtain the range of motion data of the user's jaw through a magnetic position sensor; and collect the user's dental health information; Model building module: used to generate a three-dimensional digital model of the crown surface through scanning image data, which is recorded as tooth positive model 1; generate a three-dimensional digital model including tooth root, alveolar bone and dental calculus, and a three-dimensional digital model of the jaw through structural image data, which are recorded as tooth positive model 2 and jaw model respectively; Model fusion module: used to fit the tooth positive model 1 and the tooth positive model 2 to obtain a full positive model, and fit the full positive model with the jaw model to obtain a tooth model; Tooth gap marking module: used to input the full positive model into the tooth gap analysis model for calculation, and obtain the tooth gap marking information of the full positive model; Dental health prediction module: used to input the user's dental health information and the full positive model with tooth space annotations into the dental health prediction model for calculation to obtain the user's dental health prediction information; Care matching module: used to match personalized dental care plans for users based on dental models and dental health prediction information.

Images