Digital intelligent diagnosis method for orthodontics

Abstract

The invention discloses an orthodontic digital intelligent diagnosis method, and relates to the technical field of orthodontics. The method is applied to an oral cavity digital diagnosis system, and comprises the following steps: acquiring oral scanning data of a target patient, and generating an oral cavity three-dimensional model; extracting state information of a plurality of teeth from the oral cavity three-dimensional model, wherein the state information comprises tooth sizes, displacement distances and torsion angles; performing symptom analysis on the state information of the plurality of teeth, and determining a plurality of reference tooth models from the state information; and generating an oral initial diagnosis report of the target patient based on the plurality of reference tooth models. By implementing the technical scheme provided by the invention, the problem that the reference value of an orthodontic initial diagnosis report is relatively low is solved.

Description

Technical Field

[0001] The present application relates to the technical field of orthodontics, and specifically to a digital intelligent diagnosis method for orthodontics. Background Art

[0002] With the development of oral medicine, orthodontic diagnosis, supported by advanced testing instruments, can provide clearer and more detailed diagnostic data for the diagnostic process, thereby improving the effectiveness of orthodontic treatment plans.

[0003] At present, when making an orthodontic diagnosis, the oral cavity will first be scanned to obtain a 3D model image of the oral cavity. The diagnosing doctor can then understand the patient's oral tooth arrangement and the misalignment between the teeth and the jaw from the 3D model image of the oral cavity, and finally make a diagnosis plan based on the patient's oral abnormalities. In this plan, in order to improve the efficiency of diagnosis, a deep learning network will be used to make an initial diagnosis of the 3D model image of the oral cavity and generate an initial diagnosis report, which will serve as the basis for the subsequent diagnosis of the doctor. However, the initial diagnosis report has a relatively fixed description of oral diseases, and it is impossible to make differentiated descriptions of the symptoms according to different patients, resulting in a low reference value of the initial diagnosis report. Summary of the invention

[0004] In order to solve the problem that the reference value of the initial diagnosis report of orthodontics is low, the present application provides a digital intelligent diagnosis method for orthodontics.

[0005] In a first aspect, the present application provides an intelligent digital diagnosis method for orthodontics, which is applied to an oral digital diagnosis system. The method comprises: Obtain oral scan data of the target patient and generate an oral 3D model; extract status information of multiple teeth from the oral 3D model, the status information including tooth size, displacement distance and torsion angle; perform pathological analysis on the status information of multiple teeth and determine multiple reference tooth models; generate an initial oral diagnosis report for the target patient based on the multiple reference tooth models.

[0006] In a second aspect, the present application provides an oral orthodontic digital intelligent diagnosis system, the system is an oral digital diagnosis system, the system includes an acquisition module, a processing module and an output module, wherein: An acquisition module is used to acquire the oral scan data of the target patient and generate a three-dimensional oral model; A processing module, used for extracting status information of multiple teeth from the three-dimensional model of the oral cavity, the status information including tooth size, displacement distance and torsion angle; Performing pathological analysis on status information of a plurality of teeth, and determining a plurality of reference tooth models therefrom; The output module is used to generate an initial oral diagnosis report of a target patient based on multiple reference tooth models.

[0007] Optionally, the processing module is also used to construct a reference coordinate system of the oral three-dimensional model; obtain a point cloud data set of the oral three-dimensional model, the point cloud data set comprising multiple oral feature points, wherein each oral feature point stores point coordinates and RGB values; based on the point cloud data set, determine multiple edge feature points corresponding to each of the multiple teeth; calculate the state information of the first tooth in the reference coordinate system based on the multiple edge feature points of the first tooth and a preset standard tooth model, the first tooth being any one of the multiple teeth.

[0008] Optionally, the processing module is also used to construct the point cloud data set into an RGB oral model in the RGB color space; extract the RGB tooth model in the RGB oral model, and convert the RGB tooth model into a grayscale image; calculate the gradient amplitude of each RGB point in the grayscale image, and generate a gradient image; perform image segmentation on the gradient image to obtain point cloud data sets corresponding to multiple tooth edges and point cloud data sets corresponding to multiple teeth; determine the first center points corresponding to multiple teeth from the point cloud data sets corresponding to multiple tooth edges, and determine the second center points corresponding to multiple teeth from the point cloud data sets corresponding to multiple teeth; construct the first center points corresponding to multiple teeth into a first tooth arrangement curve, and construct the second center points corresponding to multiple teeth into a second tooth arrangement curve; compare the first tooth arrangement curve with the second tooth arrangement curve to obtain the overlap between the two; if the overlap is greater than or equal to the preset overlap, the feature points in the point cloud data sets corresponding to the multiple tooth edges are used as the edge feature points of the multiple teeth.

[0009] Optionally, the processing module is also used to analyze the influencing factors of multiple state data of the second tooth to obtain multiple influence values ​​corresponding to each of the multiple state data, wherein the multiple state data constitute the information of the second tooth, and the second tooth is any one of the multiple teeth; construct the influence values ​​corresponding to the multiple state data into an influence matrix; apply multiple groups of preset interference matrices to the influence matrix, and calculate the eigenvalues ​​of the influence matrix under the multiple groups of preset interference matrices; calculate the eigenvalue change interval of multiple eigenvalues; if the eigenvalue change interval is within the preset eigenvalue interval, determine that the second tooth is a reference tooth model.

[0010] Optionally, the output module is also used to analyze the influencing factors of multiple state data of the second tooth to obtain multiple influence values ​​corresponding to each of the multiple state data, wherein the multiple state data constitute the information of the second tooth, and the second tooth is any one of the multiple teeth; construct the influence values ​​corresponding to the multiple state data into an influence matrix; apply multiple groups of preset interference matrices to the influence matrix, and calculate the eigenvalues ​​of the influence matrix under the multiple groups of preset interference matrices; calculate the eigenvalue change interval of multiple eigenvalues; if the eigenvalue change interval is within the preset eigenvalue interval, determine that the second tooth is a reference tooth model.

[0011] Optionally, the output module is also used to calibrate multiple reference tooth models in the oral three-dimensional model to obtain multiple calibrated oral three-dimensional models, wherein one reference tooth model corresponds to one calibrated oral three-dimensional model; input the multiple calibrated oral three-dimensional models into the dental diagnostic model to obtain standard oral three-dimensional models corresponding to the multiple calibrated oral three-dimensional models; match the multiple reference tooth models with the multiple standard oral three-dimensional models to obtain a target standard oral three-dimensional model; and use the target standard oral three-dimensional model as a personalized orthodontic oral model.

[0012] Optionally, the output module is also used to obtain multiple treatment data corresponding to each of the multiple teeth based on the disease data of the multiple teeth, the multiple treatment data including treatment cycle, treatment process and treatment cost; calculate description scores of the multiple teeth based on preset weights of the multiple treatment data and treatment difficulty scores of the multiple teeth on the multiple treatment data; determine the description levels of the multiple teeth based on the description scores of the multiple teeth.

[0013] In a third aspect, the present application provides an electronic device comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a method as described in any one of the first aspects.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method as described in any one of the first aspects is executed.

[0015] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. In order to solve the problem of low reference value of initial diagnosis reports, the present application performs a first standardized analysis on the three-dimensional oral model of the target patient to determine the status information of multiple teeth in a standardized scale (tooth size, displacement distance, and torsion angle), and then selects normal teeth from the multiple teeth as reference tooth models. The three-dimensional oral model of the target patient is subjected to a second personalized analysis based on the multiple reference tooth models to generate an initial diagnosis report. During the second personalized analysis, each tooth in the oral cavity is divided into a description level, and teeth of different description levels have different description methods, description contents, and description order in the initial diagnosis report, thereby generating a personalized initial diagnosis report for each patient, thereby improving the reference value of the patient's initial diagnosis report. At the same time, the scheme is based on the diagnostic analysis of the patient's own teeth, which facilitates the diagnostic doctor to formulate a personalized treatment plan for the patient more quickly.

[0016] 2. When extracting the status information of multiple teeth from the oral three-dimensional model, the patient may have other dental diseases, which may result in the oral three-dimensional model being unable to give a good description of some of the patient's teeth. For example, model distortion, multiple teeth bonding, and incomplete tooth description may occur. Based on this, the present application constructs a standard reference coordinate system, and then converts the three-dimensional oral model into the RGB space, at which time the edge feature points of each tooth are described to determine the size, shape, and position of each tooth. This process utilizes the distinct and significant color characteristics of the oral cavity, and uses the RGB space instead of the original real physical space to improve the accuracy of the status information of multiple teeth extracted from the oral three-dimensional model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for digital intelligent diagnosis of orthodontics provided in an embodiment of the present application.

[0018] Figure 2 It is a structural diagram of an oral orthodontic digital intelligent diagnosis system provided in an embodiment of the present application.

[0019] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0020] Explanation of the reference numerals: 1. Acquisition module; 2. Processing module; 3. Output module; 300. Electronic device; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 305. Memory. DETAILED DESCRIPTION

[0021] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0022] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0023] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0024] In today's social environment, tooth deformity not only affects the patient's occlusal function, but also affects the patient's overall facial beauty. Therefore, orthodontics has become a major research topic in the field of oral medicine.

[0025] With the rapid development of oral medicine, the current orthodontic diagnosis is gradually becoming digital and intelligent, thereby improving the diagnostic efficiency of the doctor. During the diagnosis of orthodontics, the oral cavity will be scanned first to obtain a 3D model image of the oral cavity. The doctor can then understand the patient's oral tooth arrangement and the misalignment between the teeth and the jaw from the 3D model image, and finally make a diagnosis plan based on the abnormalities in the patient's oral cavity.

[0026] In the above scheme, in order to further improve the diagnostic efficiency of the diagnostic doctor, a deep learning network will be used to make an initial diagnosis of the oral 3D model image and generate an initial diagnosis report, which will serve as the basis for the subsequent diagnosis of the diagnostic doctor. However, the initial diagnosis report has a relatively fixed description of oral diseases and cannot make differentiated descriptions of diseases according to different patients, resulting in a low reference value of the initial diagnosis report.

[0027] In order to solve the above problems, the present application provides an intelligent digital diagnosis method for orthodontics, which is applied to an oral digital diagnosis system. Figure 1 As shown, the method includes steps S101 to S104, which are as follows: S101, obtaining oral scan data of a target patient and generating an oral 3D model.

[0028] S102, extracting status information of multiple teeth from the three-dimensional model of the oral cavity, where the status information includes tooth size, displacement distance, and torsion angle.

[0029] In the above steps S101 to S102, the oral three-dimensional model generated by the oral scan data contains not only the point cloud data constituting the oral three-dimensional model, but also the RGB space data of the oral three-dimensional model. In the process of extracting the status information of multiple teeth from the oral three-dimensional model, the status information of multiple teeth is defined using a standardized scale. The standardized scale can be understood as a normal oral control model, which ensures that the multiple reference tooth models selected subsequently have a better growth morphology. Specifically, the patient's oral three-dimensional model is matched with a preset standard three-dimensional oral model library to obtain a comparative oral three-dimensional model similar to the target patient's oral three-dimensional model, and then based on the comparative oral three-dimensional model, the status information of each tooth in the target patient's oral three-dimensional model is calculated.

[0030] In a possible implementation, the oral scan data may contain other dental diseases (severe caries, periodontal disease, and dental trauma, etc.) in the target patient, which may result in the oral 3D model not being able to provide a good description of some of the patient's teeth, causing the generated oral 3D model to be distorted, with multiple teeth sticking together and incomplete description of teeth. Based on this, the present application constructs the oral 3D model in the RGB color space, and uses the distinct and significant color characteristics of the gums, teeth, and oral mucosa in the oral cavity to depict the edge feature points of each tooth, thereby determining the size, shape, and position of multiple teeth. Specifically: First, the reference coordinate system in the comparison oral 3D model similar to the target patient's oral 3D model is transplanted into the target patient's oral 3D model. Then, the reference coordinate system is used to define the point cloud dataset of the oral 3D model. The point cloud dataset contains multiple oral feature points, each of which stores defined point coordinates and RGB values. The point coordinates are used to calculate the size, shape, and position of each tooth. The teeth, gums, and oral mucosa are distinguished by combining the RGB values ​​at each point coordinate, so as to determine multiple edge feature points of each tooth. Finally, the status information of each tooth is calculated based on the multiple edge feature points of each tooth.

[0031] In one possible implementation, due to the complex oral environment, the oral scanning device is difficult to detect and the detection conditions are poor, so the constructed oral 3D model is often fuzzy, which may cause the edge feature points of the teeth to be inaccurate. In order to solve this problem, the present application constructs an RGB oral model in the RGB color space using the RGB values ​​stored in each oral feature point; then, the RGB tooth model in the RGB oral model is extracted. This step can be understood as extracting the teeth and oral mucosa in the oral cavity to facilitate the subsequent segmentation of the RGB tooth model between each tooth; then, the RGB tooth model is converted into a grayscale image, and then the gradient amplitude of each RGB point in the grayscale image is calculated to generate a gradient image. The calculation method can be performed using gradient operators such as Sobel operator, Prewitt operator, Roberts operator, Laplacian operator, etc.; it can be understood that the gradient image reflects the degree of color change, and the oral cavity is a kind of image with a gradient value of 0.0447mm. In the cavity tooth model, the gaps between teeth, teeth, and gums have great differences in color. Therefore, image segmentation of the gradient image can well distinguish the gaps between teeth, teeth, and gums. The watershed algorithm can be used for image segmentation. The watershed algorithm regards the image as a terrain surface, and the change in color is equivalent to the change in height of the terrain. By selecting the minimum gradient amplitude point in the gradient image as the water injection point, and then executing the watershed algorithm at the water injection point to simulate the water injection operation, when the water injection reaches a certain level, a water area will be formed. At this time, the junction of the water areas formed by each water injection point is the boundary area. Therefore, the watershed algorithm can clearly define the boundary of the gap area, so as to find the edge feature points of each tooth. Specifically, multiple local minimum gradient amplitudes are first marked in the gradient image, and then each local minimum gradient amplitude is used as a seed point to execute the watershed algorithm. When the watershed algorithm converges, the gradient image is traversed to obtain a segmented image. At this time, the multiple gradient points extracted from the segmentation line of the segmented image are edge feature points.

[0032] However, since the original detection data of the RGB dental model may not be accurate, the image quality of the gradient image cannot well represent the situation of the teeth in the oral cavity. Therefore, it is necessary to further determine whether the image quality of the current RGB dental model can accurately reflect the arrangement of the teeth in the oral cavity. Specifically, the gradient image is first segmented to obtain a point cloud data set corresponding to multiple tooth edges and a point cloud data set corresponding to multiple teeth; then, a first center point corresponding to each of the multiple teeth is determined from the point cloud data set corresponding to each of the multiple tooth edges, and a second center point corresponding to each of the multiple teeth is determined from the point cloud data set corresponding to each of the multiple teeth. It should be noted that the first center point and the second center point can both represent the morphological center point (geometric center point) of the tooth. When the original detection data of the RGB dental model is accurate enough, the first center point and the second center point should be consistent. Therefore, the first center point corresponding to each of the multiple teeth is constructed as the first center point. A tooth arrangement curve is constructed, and the second center points corresponding to the multiple teeth are constructed as a second tooth arrangement curve; then the first tooth arrangement curve is compared with the second tooth arrangement curve to obtain the overlap between the two. If the overlap is greater than or equal to the preset overlap, it means that the original detection data of the RGB tooth model is accurate enough, that is, the current gradient image can well describe the edge features of the teeth in the oral cavity. At this time, the feature points in the point cloud data set corresponding to the edges of the multiple teeth can be directly used as the edge feature points of the multiple teeth; if the overlap is less than the preset overlap, it means that the current gradient image cannot make a good description of the edge features of the teeth in the oral cavity. At this time, image enhancement algorithms such as contrast enhancement and bilateral filtering can be used for the gradient image to amplify the gradient differences between the tooth gaps, teeth and gums, and then repeat the above steps until the enhanced gradient image can better describe the edge features of the teeth in the oral cavity, thereby obtaining multiple edge feature points of the multiple teeth with relatively accurate accuracy.

[0033] After the edge feature points are identified, the point coordinates of the edge feature points are queried from the point cloud data set of the oral three-dimensional model, and then the point coordinates are converted into a tooth model. Finally, the tooth model is compared with the preset standard tooth model to calculate the corresponding state information of the tooth model, where the preset standard tooth model can be understood as the tooth model in the comparison oral three-dimensional model.

[0034] S103, performing a pathological analysis on the status information of a plurality of teeth, and determining a plurality of reference tooth models therefrom.

[0035] In the above steps, the reference tooth model can be understood as a relatively healthy tooth model in the oral cavity, and the state information of healthy teeth is generally within the normal range, which indicates that normal teeth are more stable and adaptable under multiple influencing factors in the same oral cavity than deformed teeth. Therefore, this application determines whether a tooth is a reference tooth model by analyzing the performance of multiple teeth under multiple influencing factors, specifically: An influencing factor analysis is performed on multiple state data of teeth (tooth size, displacement distance, and torsion angle) to obtain multiple influence values ​​corresponding to each of the multiple state data. For example, the tooth displacement distance may be affected by multiple factors such as adjacent tooth extrusion, occlusal force, and periodontal tissue health status. The influence value of the influencing factor can be understood as a quantitative score of the current state data of the tooth based on a pre-established quantitative scoring table of influencing factors. Then, the influence values ​​of the multiple state data of the tooth are constructed into an influence matrix. At this time, in order to further test the stability and adaptability of the tooth, multiple sets of preset interference matrices are applied to the influence matrix. The preset interference matrix can be understood as an influence matrix randomly generated for multiple state data based on the patient's current oral environment. Then, the eigenvalues ​​of the influence matrix under multiple sets of preset interference matrices are calculated, and the eigenvalue variation ranges of multiple eigenvalues ​​are calculated. If a tooth's eigenvalue variation range under the action of multiple preset interference matrices can still be within the preset eigenvalue range, it means that the tooth has better robustness in a complex and changeable oral environment and is more likely to meet the requirements of the benchmark tooth model under the patient's real oral environment.

[0036] S104: Generate an initial oral diagnosis report for the target patient based on multiple reference tooth models.

[0037] In the above steps, after determining the multiple reference tooth models in the target patient's mouth, a second personalized diagnosis is adopted at this time, and the degree of pathological changes of other remaining teeth is determined based on the reference tooth model. This application is based on the principle of single analysis, and generates multiple diagnostic reports as much as possible on the premise of retaining the patient's original teeth in good growth state, and then selects the diagnostic scheme with the highest coverage of the reference tooth model from the multiple diagnostic reports as the treatment diagnostic scheme. Specifically: calibrate the multiple reference tooth models in the oral three-dimensional model to obtain multiple calibrated oral three-dimensional models, wherein one reference tooth model corresponds to one calibrated oral three-dimensional model. It should be explained that, except for the calibrated reference tooth model in the calibrated oral three-dimensional model, the remaining other tooth models are all non-calibrated reference tooth models that can be diagnosed and treated; then, input the multiple calibrated oral three-dimensional models into the tooth diagnosis model to obtain the standard oral three-dimensional models corresponding to the multiple calibrated oral three-dimensional models. The standard oral three-dimensional model can be understood as the oral three-dimensional model after simulated orthodontic treatment, and the standard oral three-dimensional model contains its corresponding calibrated reference tooth model. Then, multiple reference tooth models are matched with multiple standard oral 3D models, and the coverage rate of each standard oral 3D model on multiple reference tooth models is found. Then, the standard oral 3D model with the highest coverage rate is selected from multiple standard oral 3D models as the personalized orthodontic oral model of the target patient. Finally, based on the personalized orthodontic oral model as the control model, the disease data of multiple teeth in the current 3D oral model of the target patient are diagnosed, and the disease data are generated into an initial diagnosis report.

[0038] When generating the initial diagnosis report, since the condition of each tooth is different, the description method in the initial diagnosis report will also be different. For example, for teeth with milder symptoms, the description in the initial diagnosis report is more simplified, while for teeth with more serious symptoms, a more detailed description may be required in combination with images. Based on this, the present application classifies the symptom data of multiple teeth to obtain the description levels of multiple teeth, specifically: according to the symptom data of multiple teeth, multiple treatment data corresponding to each of the multiple teeth are generated, wherein the multiple treatment data include treatment cycles, treatment processes, and treatment costs, etc. Then, the weight values ​​of the multiple treatment data are determined by the hierarchical analysis method, and the treatment difficulty score is scored for each treatment data of each tooth according to the preset treatment difficulty score, and then the weighted sum of the multiple teeth on the multiple treatment data is calculated to obtain the description scores of the multiple teeth, and finally, the description score of each tooth is evaluated according to the preset description level rating table, wherein different description levels are different in description methods, description contents, and description order, so as to generate a personalized initial diagnosis report for each patient, thereby improving the reference value of the initial diagnosis report.

[0039] Reference Figure 2 The present application also provides an oral orthodontic digital intelligent diagnosis system, which is an oral digital diagnosis system. The system includes an acquisition module 1, a processing module 2 and an output module 3, wherein: Acquisition module 1, used to acquire oral scan data of a target patient and generate an oral 3D model; Processing module 2, used to extract status information of multiple teeth from the three-dimensional model of the oral cavity, the status information including tooth size, displacement distance and torsion angle; Performing pathological analysis on status information of a plurality of teeth, and determining a plurality of reference tooth models therefrom; The output module 3 is used to generate an initial oral diagnosis report of the target patient based on multiple reference tooth models.

[0040] In a possible implementation, the processing module 2 is also used to construct a reference coordinate system of the oral three-dimensional model; obtain a point cloud data set of the oral three-dimensional model, the point cloud data set comprising a plurality of oral feature points, wherein each oral feature point stores point coordinates and RGB values; based on the point cloud data set, determine a plurality of edge feature points corresponding to each of the plurality of teeth; calculate the state information of the first tooth in the reference coordinate system based on the plurality of edge feature points of the first tooth and a preset standard tooth model, the first tooth being any one of the plurality of teeth.

[0041] In a possible implementation, the processing module 2 is also used to construct the point cloud data set into an RGB oral model in the RGB color space; extract the RGB tooth model in the RGB oral model, and convert the RGB tooth model into a grayscale image; calculate the gradient amplitude of each RGB point in the grayscale image, and generate a gradient image; perform image segmentation on the gradient image to obtain point cloud data sets corresponding to multiple tooth edges and point cloud data sets corresponding to multiple teeth; determine the first center points corresponding to multiple teeth from the point cloud data sets corresponding to the multiple tooth edges, and determine the second center points corresponding to multiple teeth from the point cloud data sets corresponding to the multiple teeth; construct the first center points corresponding to the multiple teeth into a first tooth arrangement curve, and construct the second center points corresponding to the multiple teeth into a second tooth arrangement curve; compare the first tooth arrangement curve with the second tooth arrangement curve to obtain the overlap between the two; if the overlap is greater than or equal to the preset overlap, the feature points in the point cloud data sets corresponding to the multiple tooth edges are used as the edge feature points of the multiple teeth.

[0042] In a possible implementation, the processing module 2 is also used to perform influencing factor analysis on multiple state data of the second tooth to obtain multiple influence values ​​corresponding to each of the multiple state data, wherein the multiple state data constitute information of the second tooth, and the second tooth is any one of the multiple teeth; construct the influence values ​​corresponding to the multiple state data into an influence matrix; apply multiple groups of preset interference matrices to the influence matrix, and calculate the eigenvalues ​​of the influence matrix under the multiple groups of preset interference matrices; calculate the eigenvalue change interval of multiple eigenvalues; if the eigenvalue change interval is within the preset eigenvalue interval, determine that the second tooth is a reference tooth model.

[0043] In a possible implementation, the output module 3 is also used to perform influencing factor analysis on multiple state data of the second tooth to obtain multiple influence values ​​corresponding to each of the multiple state data, wherein the multiple state data constitute information of the second tooth, and the second tooth is any one of the multiple teeth; construct the influence values ​​corresponding to the multiple state data into an influence matrix; apply multiple groups of preset interference matrices to the influence matrix, and calculate the eigenvalues ​​of the influence matrix under the multiple groups of preset interference matrices; calculate the eigenvalue variation interval of multiple eigenvalues; if the eigenvalue variation interval is within the preset eigenvalue interval, determine that the second tooth is a reference tooth model.

[0044] In a possible implementation, the output module 3 is also used to calibrate multiple reference tooth models in the oral three-dimensional model to obtain multiple calibrated oral three-dimensional models, wherein one reference tooth model corresponds to one calibrated oral three-dimensional model; input the multiple calibrated oral three-dimensional models into the dental diagnostic model to obtain standard oral three-dimensional models corresponding to the multiple calibrated oral three-dimensional models; match the multiple reference tooth models with the multiple standard oral three-dimensional models to obtain a target standard oral three-dimensional model; and use the target standard oral three-dimensional model as a personalized orthodontic oral model.

[0045] In a possible implementation, the output module 3 is also used to obtain multiple treatment data corresponding to each of the multiple teeth based on the disease data of the multiple teeth, and the multiple treatment data include treatment cycles, treatment procedures, and treatment costs; based on preset weights of the multiple treatment data and treatment difficulty scores of the multiple teeth on the multiple treatment data, calculate description scores of the multiple teeth; and determine description levels of the multiple teeth based on the description scores of the multiple teeth.

[0046] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0047] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0048] The communication bus 302 is used to realize the connection and communication between these components.

[0049] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0050] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0051] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0052] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of an orthodontic digital intelligent diagnosis method.

[0053] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing a method for digital intelligent diagnosis of orthodontics in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0054] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0055] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0056] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0058] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0059] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0060] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A digital intelligent diagnosis method for orthodontics, characterized in that: Applied to an oral digital diagnosis system, the method comprises: Obtain oral scan data of the target patient and generate a three-dimensional oral model; Extracting status information of multiple teeth from the three-dimensional model of the oral cavity, wherein the status information includes tooth size, displacement distance, and torsion angle; Performing pathological analysis on the status information of the plurality of teeth, and determining a plurality of reference tooth models therefrom; Based on the multiple reference tooth models, an initial oral diagnosis report of the target patient is generated.

2. The method according to claim 1, characterized in that Extracting the status information of multiple teeth from the three-dimensional model of the oral cavity is specifically as follows: Constructing a reference coordinate system of the oral three-dimensional model; Acquire a point cloud data set of the oral cavity three-dimensional model, wherein the point cloud data set includes a plurality of oral cavity feature points, wherein each oral cavity feature point stores a point coordinate and an RGB value; Based on the point cloud data set, determining a plurality of edge feature points corresponding to each of the plurality of teeth; According to a plurality of edge feature points of a first tooth and a preset standard tooth model, state information of the first tooth in the reference coordinate system is calculated, and the first tooth is any one of the plurality of teeth.

3. The method according to claim 2, characterized in that Based on the point cloud data set, a plurality of edge feature points corresponding to each of the plurality of teeth are determined, specifically: In RGB color space, constructing the point cloud data set into an RGB oral model; Extracting an RGB tooth model from the RGB oral model, and converting the RGB tooth model into a grayscale image; Calculate the gradient amplitude of each RGB point in the grayscale image and generate a gradient image; Performing image segmentation on the gradient image to obtain a plurality of point cloud data sets corresponding to the tooth edges and a plurality of point cloud data sets corresponding to the teeth; Determine a plurality of first center points corresponding to each of the teeth from a plurality of point cloud data sets corresponding to each of the tooth edges, and determine a plurality of second center points corresponding to each of the teeth from a plurality of point cloud data sets corresponding to each of the teeth; Constructing a first tooth arrangement curve based on the first center points corresponding to the plurality of teeth, and constructing a second tooth arrangement curve based on the second center points corresponding to the plurality of teeth; Comparing the first tooth arrangement curve with the second tooth arrangement curve to obtain a degree of overlap between the two; If the overlap degree is greater than or equal to a preset overlap degree, the feature points in the point cloud data sets corresponding to the multiple tooth edges are used as the edge feature points of the multiple teeth.

4. The method according to claim 1, characterized in that: The step of performing pathological analysis on the status information of the plurality of teeth and determining a plurality of reference tooth models therefrom specifically includes: Performing influencing factor analysis on a plurality of state data of the second tooth to obtain a plurality of influencing values ​​corresponding to each of the plurality of state data, wherein the plurality of state data constitutes information of the second tooth, and the second tooth is any one of the plurality of teeth; Constructing an influence matrix by using influence values ​​corresponding to the plurality of state data; Applying multiple sets of preset interference matrices to the influence matrix, and calculating eigenvalues ​​of the influence matrix under the multiple sets of the preset interference matrices; Calculate the characteristic value variation interval of a plurality of the characteristic values; If the characteristic value variation interval is within the preset characteristic value interval, the second tooth is determined to be the reference tooth model.

5. The method according to claim 1, characterized in that The generating of the oral initial diagnosis report of the target patient based on the plurality of reference tooth models is specifically as follows: Based on the multiple reference tooth models, construct a personalized orthodontic oral model of the target patient; Comparing the personalized oral three-dimensional model with the oral three-dimensional model to obtain disease data of the plurality of teeth; Classifying the disease data of the plurality of teeth into different levels to obtain description levels of the plurality of teeth; An initial oral diagnosis report of the target patient is generated based on the description levels of the multiple teeth.

6. The method according to claim 5, characterized in that The step of constructing the personalized orthodontic oral model of the target patient based on the plurality of reference tooth models is specifically as follows: Calibrate the multiple reference tooth models in the oral three-dimensional model to obtain multiple calibrated oral three-dimensional models, wherein one reference tooth model corresponds to one calibrated oral three-dimensional model; Inputting the plurality of calibrated oral cavity three-dimensional models into a dental diagnosis model to obtain standard oral cavity three-dimensional models corresponding to the plurality of calibrated oral cavity three-dimensional models; Matching the plurality of reference tooth models with the plurality of standard oral cavity three-dimensional models to obtain a target standard oral cavity three-dimensional model; The target standard oral cavity three-dimensional model is used as the personalized orthodontic oral cavity model.

7. The method according to claim 5, characterized in that The step of classifying the disease data of the plurality of teeth to obtain description levels of the plurality of teeth specifically includes: According to the disease data of the plurality of teeth, obtaining a plurality of treatment data corresponding to each of the plurality of teeth, wherein the plurality of treatment data includes a treatment cycle, a treatment process and a treatment cost; Based on the preset weights of the plurality of treatment data and the treatment difficulty scores of the plurality of teeth on the plurality of treatment data, the description scores of the plurality of teeth are calculated; Determine description levels of the plurality of teeth according to the description scores of the plurality of teeth.

8. An orthodontic digital intelligent diagnosis system, characterized in that: The system is an oral digital diagnosis system, comprising an acquisition module (1), a processing module (2) and an output module (3), wherein: The acquisition module (1) is used to acquire oral scan data of a target patient and generate a three-dimensional oral model; The processing module (2) is used to extract status information of multiple teeth from the three-dimensional model of the oral cavity, wherein the status information includes tooth size, displacement distance and torsion angle; Performing pathological analysis on the status information of the plurality of teeth, and determining a plurality of reference tooth models therefrom; The output module (3) is used to generate an initial oral diagnosis report of the target patient based on the multiple reference tooth models.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images