Method, apparatus, system, and program product for predicting oral state

Abstract

The application provides a method, device, system and program product for predicting oral cavity state, the method comprising: acquiring first three-dimensional scanning images of the oral cavity of the same patient at different times, the first three-dimensional scanning images being used to reflect the oral cavity state of the patient; extracting one or more characteristic parameters for characterizing the oral cavity state from the plurality of first three-dimensional scanning images; and predicting evolution information of the oral cavity state by a prediction model according to the one or more characteristic parameters of the oral cavity state, the evolution information being used to evaluate the oral health condition of the patient. The application can accurately predict the evolution information of the oral cavity state, providing a more reliable basis for diagnosis. Since the patient can intuitively understand the evolution information of the disease, the patient's understanding and cooperation of the treatment can be enhanced. For patients with special conditions, doctors can more accurately determine the treatment opportunity, develop a more reasonable treatment plan, and improve the treatment effect by predicting the evolution information of the oral cavity state.

Description

Technical Field

[0001] This application belongs to the field of data analysis technology, and in particular relates to a method, device, system and program product for predicting oral cavity status. Background Technology

[0002] Currently, the diagnosis and treatment of oral diseases mainly rely on the experience of dentists and visual observation. Traditional diagnostic methods have some limitations; dentists often rely on subjective judgment, leading to inaccurate treatment plans. Patients often lack a comprehensive understanding of their oral health status and its changes, lacking necessary objective data to support their treatment, which affects their understanding and cooperation. Furthermore, for patients with special circumstances who cannot be treated immediately, the timing of treatment needs to be determined based on the dentist's experience; however, the timeframe determined by the dentist is often approximate, making it difficult to pinpoint the exact timing. Summary of the Invention

[0003] This application provides a method, device, system, and program product for predicting oral health, which can solve the problem that current oral health treatment mainly relies on subjective judgment, resulting in inaccurate treatment plans and patients having difficulty fully understanding their own oral health status and changes due to a lack of objective data, thus affecting their understanding and cooperation with treatment.

[0004] In a first aspect, embodiments of this application provide a method for predicting oral cavity status, applied to an electronic device, including:

[0005] Acquire first three-dimensional scan images of the oral cavity of the same patient at different times, the first three-dimensional scan images being used to reflect the oral cavity status of the patient;

[0006] Extract one or more feature parameters from multiple first three-dimensional scan images to characterize the oral cavity state;

[0007] Based on one or more characteristic parameters of the oral cavity state, an evolutionary information of the oral cavity state is predicted by a predictive model, and the evolutionary information is used to assess the patient's oral health status.

[0008] In one possible implementation of the first aspect, when the oral cavity condition involves missing teeth, the extraction of one or more feature parameters characterizing the oral cavity condition from a plurality of the first three-dimensional scan images includes:

[0009] Determine the time interval between adjacent first three-dimensional scan images;

[0010] One or more feature parameters for characterizing the missing tooth are extracted from multiple first three-dimensional scan images; the feature parameters of the missing tooth include: the type and location of the missing tooth, the long axis of the adjacent tooth of the missing tooth, and the height and morphology of the alveolar bone surrounding the missing tooth;

[0011] The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes:

[0012] Based on the time interval between adjacent first three-dimensional scan images and one or more feature parameters of the missing tooth, change information of feature parameters around the missing tooth is determined; the change information of feature parameters around the missing tooth includes at least one of: tilting velocity of adjacent teeth of the missing tooth, displacement velocity of adjacent teeth of the missing tooth, and alveolar bone resorption velocity around the missing tooth.

[0013] Based on the changes in characteristic parameters around the missing tooth, the evolutionary information around the missing tooth is predicted by the prediction model; the evolutionary information around the missing tooth includes at least one of the following: the future tilting velocity of the adjacent tooth of the missing tooth, the future displacement velocity of the adjacent tooth of the missing tooth, and the future alveolar bone resorption velocity around the missing tooth.

[0014] In one possible implementation of the first aspect, if mucosal abnormalities also exist in the oral cavity, the method further includes:

[0015] Determine the location and area of ​​the abnormal mucosal regions in multiple first three-dimensional scan images;

[0016] Based on the time interval between adjacent first three-dimensional scan images and the location and area of ​​the mucosal abnormality region, the evolution information of the mucosal abnormality region is determined;

[0017] The timing of dental implantation is determined based on the evolutionary information of the abnormal mucosal area and the evolutionary information around the missing tooth.

[0018] In one possible implementation of the first aspect, the method further includes:

[0019] Before implanting the missing tooth, a three-dimensional model of the implantation effect is determined.

[0020] Acquire a second three-dimensional scan image of the patient's oral cavity after tooth implantation;

[0021] Based on the three-dimensional model of the implantation effect and the second three-dimensional scan image, the degree of restoration after implantation of the missing tooth is determined.

[0022] In one possible implementation of the first aspect, the method further includes:

[0023] Acquire third three-dimensional scan images of the face of the same patient at different times; the acquisition time of the third three-dimensional scan image corresponds to that of the first three-dimensional scan image.

[0024] The third 3D scan image corresponding to the acquisition time is stitched together with the first 3D scan image to obtain a comprehensive model;

[0025] Based on the changes in characteristic parameters around the missing teeth and the integrated model, the predictive model predicts facial change parameters of the patient.

[0026] Based on the comprehensive model and the facial change parameters, a video of the patient's facial evolution is generated.

[0027] In one possible implementation of the first aspect, when the oral condition presents with gingival recession, tartar buildup, tooth cracks, occlusal wear, or periodontitis; the extraction of one or more feature parameters characterizing the oral condition from a plurality of the first three-dimensional scan images includes:

[0028] Determine the time interval between adjacent first three-dimensional scan images;

[0029] One or more feature parameters are extracted from multiple first three-dimensional scan images to characterize the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis; wherein, the feature parameters for gingival recession include: gingival margin line and gingival volume; the feature parameters for dental calculus include: at least one of calculus coverage area and average calculus thickness; the feature parameters for tooth crack include: at least one of crack length, crack depth, and crack orientation; the feature parameters for occlusal surface wear include: at least one of: cusp height reduction, occlusal surface concavity area / depth, and tooth volume loss; the feature parameters for periodontitis include: periodontal pocket depth, clinical attachment loss, and alveolar bone resorption height.

[0030] The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes:

[0031] Based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis, the change information of characteristic parameters of the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis is determined; wherein, the change information of characteristic parameters of the gingival recession includes at least one of the following: the speed of gingival margin movement and the speed of gingival volume reduction; the change information of characteristic parameters of dental calculus includes at least one of the following: the speed of calculus coverage area expansion and the speed of calculus average thickness increase; the change information of characteristic parameters of tooth crack includes at least one of the following: the speed of crack length extension and the speed of crack depth deepening; the change information of characteristic parameters of occlusal surface wear includes at least one of the following: the speed of cusp height reduction, the speed of occlusal surface concavity area expansion / depth deepening, and the speed of tooth volume loss; the change information of characteristic parameters of periodontitis includes at least one of the following: the speed of periodontal pocket deepening, the speed of clinical attachment loss, and the speed of alveolar bone resorption acceleration.

[0032] Based on the changes in the characteristic parameters of gingival recession, the prediction model predicts the evolution information of gingival recession, tartar, tooth cracks, occlusal surface wear, or periodontitis. The evolution information of gingival recession includes at least one of: the future movement rate of the gingival margin and the future decrease rate of gingival volume. The evolution information of tartar includes at least one of: the future expansion rate of tartar coverage area, the future increase rate of average tartar thickness, and the risk of tartar accumulation in specific locations. The evolution information of tooth cracks includes: the future rate of crack length extension, the future rate of crack thickness increase, and the future rate of crack accumulation. The information on the evolution of tooth occlusal surface wear includes at least one of the following: the rate of future cusp height reduction, the rate of future expansion / deepening of occlusal surface concavity area, the rate of future tooth volume loss, the probability of increased dentin hypersensitivity risk, the probability of increased tooth crack risk, and the prediction of decreased occlusal vertical distance. The information on the evolution of periodontitis includes at least one of the following: the rate of future periodontal pocket deepening, the rate of future attachment loss, the rate of future bone resorption acceleration, the prediction of active lesion sites, and the probability of tooth loosening risk.

[0033] In one possible implementation of the first aspect, the method further includes:

[0034] Obtain at least one of the following patient data: dietary data, oral hygiene habits data, age data, gender data, unhealthy habits data, systemic disease data, and genetic data;

[0035] The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes:

[0036] The weight parameters of the prediction model are adjusted based on at least one of the patient's dietary data, oral hygiene habits data, age data, gender data, bad habits data, systemic disease data, and genetic data.

[0037] Based on the adjusted prediction model and one or more feature parameters of the oral cavity state, the evolution information of the oral cavity state is predicted.

[0038] In one possible implementation of the first aspect, the method further includes:

[0039] Based on the evolution information of the oral cavity state and the first three-dimensional scan image, an evolution video of the oral cavity state is generated.

[0040] Secondly, embodiments of this application provide an oral cavity state prediction device, comprising:

[0041] The first acquisition module is used to acquire first three-dimensional scan images of the oral cavity of the same patient at different times, and the first three-dimensional scan images are used to reflect the oral cavity status of the patient.

[0042] An extraction module is used to extract one or more feature parameters from a plurality of the first three-dimensional scan images to characterize the oral cavity state;

[0043] The prediction module is used to predict the evolution information of the oral cavity state based on one or more feature parameters of the oral cavity state through a prediction model. The evolution information is used to assess the patient's oral health status.

[0044] Thirdly, embodiments of this application provide an oral cavity state prediction system, including:

[0045] An oral scanner is used to scan a patient's oral cavity multiple times to obtain multiple first-dimensional scan images;

[0046] An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of the first aspects.

[0047] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of the first aspects.

[0048] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any one of the first aspects above.

[0049] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0050] The beneficial effects of this application embodiment compared to the prior art are as follows: This embodiment acquires first three-dimensional scan images at multiple time points and extracts one or more feature parameters to characterize the oral cavity state. Analyzing these parameters using a predictive model allows for accurate prediction of the evolution of the oral cavity state, providing a more reliable basis for diagnosis. Because patients can intuitively understand the evolution of the disease, their understanding and cooperation with treatment are enhanced. For patients with special circumstances, by predicting the evolution of the oral cavity state, doctors can more accurately determine the timing of treatment, formulate more reasonable treatment plans, and improve treatment outcomes. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a method for predicting oral cavity status according to an embodiment of this application;

[0053] Figure 2 This is a schematic diagram of the oral cavity state prediction device provided in one embodiment of this application. Detailed Implementation

[0054] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0055] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0056] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0057] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0058] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0059] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0060] Traditional diagnosis and treatment of oral diseases rely primarily on the experience of dentists and visual observation. This traditional method has the following problems:

[0061] (1) It is difficult to accurately assess the specific conditions of the oral cavity (such as the degree of tilt of adjacent teeth with missing teeth, the degree of gingival recession, etc.), which leads to inaccurate treatment plans.

[0062] (2) The evolution of oral condition cannot be predicted, and patients have difficulty understanding the necessity of treatment.

[0063] (3) Lack of objective data support makes it difficult to effectively educate and communicate with patients.

[0064] (4) For some oral conditions, treatment cannot be performed immediately due to the patient's own condition (such as gingivitis, periodontitis, severe tilting of adjacent teeth with missing teeth, or systemic diseases). In this case, the timing of treatment needs to be determined based on the doctor's experience. However, the doctor often determines a general time range and it is difficult to accurately determine the timing of treatment.

[0065] In recent years, dental scanner technology has matured, enabling the acquisition of 3D images of the patient's oral cavity and providing new tools for the diagnosis and treatment of oral conditions. However, existing dental scanner technology is primarily used for diagnosis and lacks the ability to predict the evolution of oral conditions. This makes it difficult to effectively help patients understand the necessity of treatment, to conduct effective patient education and communication, and to accurately determine the timing of treatment.

[0066] to this end Figure 1 This illustration shows a flowchart of a method for predicting oral cavity status according to an embodiment of this application. The method is applied to electronic devices such as mobile phones, computers, tablets, and televisions. Alternatively, the electronic device can be an oral scanner (intraoral or extraoral scanner), or a mobile phone, computer, tablet, or television connected to the oral scanner via wired or wireless means. The method can also be applied to a cloud server. The method includes steps S110-S130.

[0067] S110: Acquire first three-dimensional scan images of the oral cavity of the same patient at different times. The first three-dimensional scan images are used to reflect the oral cavity condition of the patient.

[0068] For example, the first three-dimensional scan image is a three-dimensional model obtained by scanning the oral cavity surface of the same patient using an oral three-dimensional scanner. The first three-dimensional scan image is colored and can reflect the specific condition of the patient's oral cavity, such as whether there are missing teeth, whether there are mucosal abnormalities, whether there are dentition, whether there is tartar, whether there is periodontitis, whether there is wear on the occlusal surface of the teeth, whether there is gingival recession, etc.

[0069] Specifically, an oral scanner is used to periodically perform three-dimensional scans of the patient's oral cavity. Each scan generates one or more first three-dimensional scan images. When multiple first three-dimensional scan images are obtained, the best one can be selected. The time interval between two adjacent scans is determined by the doctor based on the specific oral cavity condition, or the prediction model determines the time of the next scan based on the current first three-dimensional scan image.

[0070] For example, gum recession usually occurs slowly, and when a doctor notices signs of gum recession, the patient can be asked to have a check-up every three months. If the patient has a systemic disease, such as diabetes, the gum recession will accelerate, and the patient can be advised to have a check-up every few months.

[0071] For patients with missing teeth, if there is inflammation in the area of ​​the missing tooth (such as periodontitis, gingivitis, periodontal abscess, or periapical periodontitis) or significant alveolar bone resorption, the infection needs to be controlled or bone grafting should be performed before dental implantation. On the other hand, if missing teeth are not restored in time, it can cause adjacent teeth to tilt. Therefore, scans can be performed monthly or even weekly to provide data for determining the appropriate timing for dental implantation.

[0072] For patients without obvious oral diseases, oral scans can be performed during regular teeth cleaning to establish oral health records and detect potential oral diseases in a timely manner.

[0073] It's easy to understand that patients can have their mouths scanned by a doctor during each visit, or they can scan themselves at home using a mouth scanner.

[0074] By recording the scanning time when scanning the patient's oral cavity, a first three-dimensional scan image based on time series can be obtained.

[0075] S120: Extract one or more feature parameters from multiple three-dimensional scan images to characterize the oral cavity state.

[0076] It's easy to understand that different oral diseases have different characteristic parameters. These characteristic parameters can be one or multiple.

[0077] S130: Based on one or more characteristic parameters of oral condition, predict the evolutionary information of oral condition using a predictive model. This evolutionary information is used to assess the patient's oral health status.

[0078] Optionally, the predictive model can employ long short-term memory networks, convolutional neural networks, recurrent neural networks, etc. After being trained on a large amount of data, the predictive model can learn the patterns and laws governing the development of oral health, thereby providing doctors and patients with more accurate information on disease evolution and allowing them to anticipate the rate of progression of oral health conditions and changes in severity over a future period.

[0079] This embodiment acquires first three-dimensional scan images at multiple time points and extracts one or more feature parameters to characterize the oral cavity state. Analyzing these parameters using a predictive model allows for accurate prediction of the oral cavity's evolutionary information, providing a more reliable basis for diagnosis. Because patients can intuitively understand the disease's evolution, their understanding and cooperation with treatment are enhanced. For patients with special circumstances, predicting the evolution of the oral cavity state allows doctors to more accurately determine the timing of treatment, develop more reasonable treatment plans, and improve treatment outcomes.

[0080] As an optional implementation, in the case of missing teeth in the oral cavity: S120: Extract one or more feature parameters for characterizing the oral cavity state from multiple first three-dimensional scan images, including S121-S122.

[0081] S121: Determine the time interval between adjacent first three-dimensional scan images.

[0082] It's easy to understand that although patients are advised to have a follow-up visit / self-scan at preset intervals, they often find it difficult to strictly adhere to these intervals. Therefore, the acquisition times of two adjacent first 3D scan images are not always at equal time intervals. By examining the recording times of multiple first 3D scan images, the time interval between two adjacent first 3D scan images can be calculated.

[0083] For example, assuming there are 3 first three-dimensional scan images, acquired at times t0, t1, and t2 respectively, the time interval between adjacent first three-dimensional scan images is △T1 and △T2, where △T1 = t1 - t0 and △T2 = t2 - t1.

[0084] S122: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize the missing tooth; the feature parameters of the missing tooth include: the type and location of the missing tooth, the long axis of the adjacent tooth of the missing tooth, and the height and morphology of the alveolar bone around the missing tooth.

[0085] If a missing tooth is left unreplaced for a long time, the adjacent teeth will move closer to the gap in the middle, and the position of the adjacent teeth will change. The rate at which the adjacent teeth tilt varies significantly depending on the type of missing tooth.

[0086] By analyzing multiple first-dimensional 3D scan images, the type and location of missing teeth can be identified. Optionally, the type and location of missing teeth can be identified as follows: each tooth in the 3D scan image is segmented to form an independent individual. The tooth position number and location of each tooth are identified to obtain the patient's dentition. A standard dentition model is established based on normal dentition data. The patient's dentition is compared with the normal dentition model to identify the type and location of missing teeth, where the tooth position number determines the tooth type.

[0087] The adjacent teeth of a missing tooth include the teeth on either side of the missing tooth. This may be one tooth, for example, the third molar at the very back of the dentition may be adjacent to only one tooth; or it may be two teeth, for example, all teeth except the third molar may be adjacent to two teeth. The long axis of the tooth is the geometric axis that runs longitudinally through the tooth and passes through its center.

[0088] By analyzing multiple first-dimensional scan images and using region segmentation models or geometric feature recognition models, the alveolar bone region can be identified. Then, the height of the alveolar bone is measured, and its morphological characteristics are analyzed to determine whether the patient has bone resorption, bone defects, or other conditions.

[0089] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S131-S132.

[0090] S131: Based on the time interval between adjacent first three-dimensional scan images and one or more feature parameters of the missing tooth, determine the change information of feature parameters around the missing tooth; the change information of feature parameters around the missing tooth includes at least one of the following: tilting velocity of adjacent teeth of the missing tooth, displacement velocity of adjacent teeth of the missing tooth, and alveolar bone resorption velocity around the missing tooth.

[0091] For adjacent teeth with missing teeth, by comparing the long axis direction of the adjacent tooth in two adjacent first three-dimensional scan images (assuming a time interval of ΔT1), the change in the angle of the long axis direction within ΔT1 can be calculated. This change in angle is the tilt angle of the adjacent tooth within ΔT1. By combining ΔT1 and the tilt angle of the tooth's long axis, the tilt velocity of the adjacent tooth within ΔT1 can be accurately calculated. If there are more than three first three-dimensional scan images based on the time series, it can also be determined whether the tilt velocity of the adjacent tooth is uniform, accelerating, or decelerating.

[0092] By marking specific points of adjacent teeth in multiple first three-dimensional scan images, comparing the positional changes of these points in adjacent first three-dimensional scan images, calculating the displacement, and then dividing by the time interval, the displacement velocity of the adjacent teeth can be obtained.

[0093] By comparing the height and morphological changes of the alveolar bone around the missing tooth in adjacent images, the alveolar bone resorption rate is obtained by dividing the amount of height and morphological change by the time interval.

[0094] S132: Based on the changes in characteristic parameters around the missing tooth, predict the evolutionary information around the missing tooth using a prediction model; the evolutionary information around the missing tooth includes at least one of the following: the future tilting velocity of the adjacent tooth, the future displacement velocity of the adjacent tooth, and the future alveolar bone resorption velocity around the missing tooth.

[0095] Because the predictive model learns the patterns and regularities of tooth tilting in the oral cavity, it can predict the future tilting speed of adjacent teeth, the future displacement speed of adjacent teeth, and the future alveolar bone resorption speed around the missing tooth by using the currently calculated tilting speed of adjacent teeth, the future displacement speed of adjacent teeth, and the future alveolar bone resorption speed around the missing tooth as inputs. This helps doctors to develop treatment plans in advance and avoid excessive tilting of adjacent teeth, which could lead to more serious oral problems.

[0096] Addressing the common oral health issue of missing teeth, this embodiment extracts one or more characteristic parameters of the missing tooth and calculates changes in surrounding characteristic parameters. This allows for an accurate assessment of the impact of the missing tooth on adjacent teeth and alveolar bone, providing a scientific basis for developing personalized treatment plans. For patients who do not prioritize missing teeth, learning about the future tilting trend of their teeth will increase their awareness of oral health, leading to better cooperation with their doctor's treatment and oral care recommendations, thereby improving the quality of oral health management.

[0097] As an optional implementation, the oral cavity condition may also include mucosal abnormalities. The method for predicting the oral cavity condition further includes steps S140-S160.

[0098] S140: Determine the location and area of ​​abnormal mucosal regions in multiple first three-dimensional scan images.

[0099] Healthy gums appear smooth and continuous in 3D scans, fitting snugly against the teeth. When a patient's mucosa is abnormal, the gums may become swollen and red, or develop white / red patches. On imaging, this manifests as thickened and irregular gum margins, blunted gingival papillae, and may even show gum recession, exposing the tooth roots. The location and extent of oral inflammation can be determined by observing the color and shape of the gums.

[0100] Mucosal abnormalities usually indicate that the patient has oral inflammation, including gingivitis, periodontitis, periodontal abscess, periapical periodontitis, etc.

[0101] Specifically, by analyzing the mucosal region of the first three-dimensional scan image using analysis software, abnormal mucosal regions can be identified through color and shape. Through classification models, it can be determined whether the abnormal mucosal region is oral inflammation, as well as the location and area of ​​the oral inflammation.

[0102] S150: Determine the evolution information of the mucosal abnormality region based on the time interval between adjacent first three-dimensional scan images and the location and area of ​​the mucosal abnormality region.

[0103] Compare the position and area of ​​the abnormal mucosal region in two adjacent first 3D scan images. If the position of the abnormal mucosal region changes, record its direction and distance of movement; for changes in area, calculate the difference in area. Divide the change in area by the time interval between adjacent images to obtain the rate of change of the abnormal mucosal region's area.

[0104] Based on the rate and location of area change, the evolution of abnormal mucosal regions can be determined. If the area continues to increase and shows signs of spreading, the mucosal abnormality is considered to be in the development stage; if the area gradually decreases, the mucosal abnormality is considered to be in the improvement stage.

[0105] S160: Determine the timing of dental implantation based on the evolutionary information of the abnormal mucosal area and the evolutionary information around the missing tooth.

[0106] Dental implant surgery requires a stable oral environment. Abnormal development of the oral mucosa and structural changes around the missing tooth can both affect the success rate of the implant surgery. Taking both factors into account allows for the determination of an optimal implant timing, improving the success rate and reducing postoperative complications.

[0107] Taking into account both the evolutionary information of the mucosal abnormality and the evolutionary information around the missing tooth, if the mucosal abnormality is in its developmental stage, and the adjacent teeth are tilting rapidly and the alveolar bone resorption rate is also high, it indicates an unstable oral environment. In this case, dental implant surgery is not suitable, and the mucosal abnormality needs to be treated first. For example, if the mucosal inflammation is gingivitis, the inflammation needs to be controlled first, and dental implant surgery should be considered only after the oral inflammation has entered a stable phase. When the oral inflammation enters a stable phase, meaning the area no longer increases or even shows a decreasing trend, and the tilting rate of adjacent teeth and the alveolar bone resorption rate around the missing tooth slow down to a certain extent (e.g., adjacent tooth tilting rate less than 1° / month, alveolar bone resorption rate less than 0.5 mm / month), the oral environment can be considered relatively stable, and dental implant surgery can be considered at this time.

[0108] Based on the evolutionary information of the abnormal mucosal area and the area surrounding the missing tooth, a predictive model can be used to determine the specific timing of dental implantation. For example, the implantation surgery may be scheduled one month after the gingivitis has stabilized. In another embodiment, the dentist can also determine the specific timing of dental implantation based on the evolutionary information of the gingivitis and the area surrounding the missing tooth.

[0109] This embodiment accurately assesses the evolutionary information of abnormal mucosal areas and the area surrounding missing teeth, allowing for the selection of a stable oral environment for dental implant surgery. This reduces surgical risks and improves implant stability and success rates. Furthermore, this embodiment determines the timing of implantation based on each patient's specific condition and oral health, achieving personalized treatment plans that better meet patient needs.

[0110] As an optional implementation, the method for predicting oral cavity status further includes S170-S190.

[0111] S170: Before implanting a missing tooth, determine the 3D model of the implantation effect.

[0112] Specifically, before the patient receives dental implants, the first three-dimensional scan image is adjusted. This includes filling in missing teeth (i.e., the implant) in the first three-dimensional scan image, adjusting the position of adjacent teeth, and grinding adjacent teeth according to the occlusal relationship to obtain a three-dimensional model of the implant effect. Among these adjustments, an implant that matches the size, shape, and color of the adjacent teeth is designed.

[0113] S180: Acquire a second three-dimensional scan image of the oral cavity of a patient after tooth implantation.

[0114] In dental implant surgery, the dentist first makes an incision in the gums to expose the alveolar bone. A socket is then prepared in the alveolar bone, and the implant is placed inside. Afterward, the incised gum tissue is repositioned and sutured. Immediately after the implant surgery or after a certain healing period, the patient's mouth is scanned again using an oral scanner to obtain a second, three-dimensional image.

[0115] S190: Determine the degree of restoration after implantation of missing teeth based on the 3D model of the implantation effect and the second 3D scan image.

[0116] For example, the 3D model of the implant outcome and the second 3D scan image are precisely registered to achieve optimal spatial alignment. A 3D comparison algorithm is used to compare and analyze the registered model and image. For instance, the deviations of the position, angle, and height of the implant and adjacent teeth in the second 3D scan image from the 3D model of the implant outcome are calculated; the similarity of the implant's shape and color to the 3D model of the implant outcome is calculated; and the similarity of the actual wear volume and morphology of adjacent teeth to the wear volume and morphology of adjacent teeth in the 3D model of the implant outcome is calculated. Based on the results of the comparative analysis, the degree of restoration after implantation of the missing tooth is quantified and expressed as a percentage of the degree of conformity between the implant outcome and the ideal model.

[0117] This embodiment establishes a 3D model of the implantation effect before surgery, providing doctors with a visual reference to help them more accurately plan the implant's position and orientation during the procedure. Simultaneously, it allows patients to have a clear understanding of the implantation outcome before surgery, increasing their willingness to undergo treatment. After tooth implantation, doctors can determine the success of the surgery based on the degree of restoration and whether further adjustments are needed; patients can also intuitively understand the implantation effect, improving their satisfaction with the treatment.

[0118] As an optional implementation, in cases where the oral cavity condition includes gingival recession; S120: extract one or more feature parameters for characterizing the oral cavity condition from multiple first three-dimensional scan images, including S123-S124.

[0119] S123: Determine the time interval between adjacent first three-dimensional scan images.

[0120] S124: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize gingival recession; the feature parameters of gingival recession include at least one of the following: gingival margin line and gingival volume.

[0121] Specifically, the gingival margin is identified and marked in multiple first-dimensional 3D scan images. Using image segmentation algorithms, the gingival margin line is accurately extracted based on the differences in features such as color between the gingival tissue and surrounding tissue in the images.

[0122] A 3D model of the gingival region is extracted from the first 3D scan image. The gingival volume data is obtained by calculating the space occupied by the 3D model of the gingival region. For example, the gingival region can be divided into multiple small 3D voxels, and then the total volume of these voxels can be calculated.

[0123] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S133-S134.

[0124] S133: Based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of gingival recession, determine the change information of characteristic parameters of gingival recession; the change information of characteristic parameters of gingival recession includes at least one of the following: the movement speed of the gingival margin line and the rate of decrease in gingival volume.

[0125] Compare the positions of the gingival margin extracted from two adjacent first 3D scan images. Measure the distance the gingival margin moves between these two images, and then divide the distance by the time interval between the adjacent images to obtain the gingival margin movement velocity. Similarly, the rate of gingival volume reduction can be obtained.

[0126] S134: Based on the changes in characteristic parameters of gingival recession, predict the evolution information of gingival recession using a predictive model; the evolution information of gingival recession includes at least one of the following: the future movement speed of the gingival margin and the future reduction speed of gingival volume.

[0127] The calculated data on the movement speed of the gingival margin and the rate of decrease in gingival volume are input into the prediction model to obtain the movement speed of the gingival margin and the rate of decrease in gingival volume over a future period.

[0128] This embodiment extracts data on the gingival margin and gingival volume, and calculates the movement speed of the gingival margin and the shrinkage speed of the gingival volume. This allows for accurate quantification of the degree and evolution of gingival recession, avoiding errors in subjective judgment. Doctors can then develop personalized treatment plans for each patient, improving the targetedness and effectiveness of treatment.

[0129] As an optional implementation, when the oral cavity condition includes dental calculus, S120: extract one or more feature parameters for characterizing the oral cavity condition from multiple first three-dimensional scan images, including S1251-S1252.

[0130] S1251: Determine the time interval between adjacent first three-dimensional scan images.

[0131] S1252: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize dental calculus.

[0132] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S1351-S1352.

[0133] S1351: Determine the change information of the characteristic parameters of the dental calculus based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of the dental calculus.

[0134] S1352: Based on the changes in the characteristic parameters of dental calculus, predict the evolution information of dental calculus using a prediction model.

[0135] The characteristic parameters of dental calculus include at least one of the following: calculus coverage area and average calculus thickness. Specifically, the calculus region is identified and marked in multiple first three-dimensional scan images. Using an image segmentation algorithm, the calculus region is accurately segmented based on the differences in color, texture, height, and other characteristics between the calculus (usually appearing as yellowish-white, brownish-black, or black clumps / sheets) and tooth tissue in the images. The tooth surface area covered by the calculus is calculated, and its average thickness (e.g., calculating the average bulge height of the calculus region relative to the underlying tooth surface) is calculated by analyzing the three-dimensional height data of the calculus region.

[0136] The characteristic parameters of dental calculus include at least one of the following: the rate of expansion of calculus coverage area and the rate of increase in average calculus thickness. Specifically, the calculus coverage area of ​​the same tooth position extracted from two adjacent first three-dimensional scan images is compared. The area difference is calculated, and this difference is divided by the time interval between the adjacent images to obtain the rate of expansion of calculus coverage area. Similarly, the average thickness data of the same calculus region is compared, the difference is calculated, and divided by the time interval to obtain the rate of increase in average calculus thickness.

[0137] Information on the evolution of dental calculus includes at least one of the following: the future rate of expansion of calculus coverage area, the future rate of increase in average calculus thickness, and the risk of calculus accumulation in specific locations. Specifically, the calculated dynamic data on the rate of expansion of calculus coverage area and the rate of increase in average calculus thickness are combined with the patient's individual oral hygiene habits (such as brushing frequency and whether dental floss / water flosser is used) and input into the predictive model. The model analyzes these data and risk factors to predict the rate of expansion and thickness increase of dental calculus on specific teeth (such as the lingual side of the lower anterior teeth and the buccal side of the maxillary molars) over a future period, and assesses its cumulative risk.

[0138] As an optional implementation, in the case where the oral cavity condition includes a tooth crack, S120: extract one or more feature parameters for characterizing the oral cavity condition from multiple first three-dimensional scan images, including S1261-S1262.

[0139] S1261: Determine the time interval between adjacent first three-dimensional scan images.

[0140] S1262: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize tooth fracture.

[0141] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S1361-S1362.

[0142] S1361: Determine the change information of the characteristic parameters of the tooth fracture based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of the tooth fracture.

[0143] S1362: Based on the changes in the characteristic parameters of tooth cracks, predict the evolution information of tooth cracks using a prediction model.

[0144] The characteristic parameters of tooth cracks include at least one of the following: crack length, crack depth, and crack orientation (relative to the long axis of the tooth or the occlusal surface). Specifically, tooth cracks are identified and marked in multiple first-dimensional scan images. Utilizing the high-resolution characteristics of 3D scan images for minute surface defects, combined with edge detection and morphological analysis algorithms, linear fracture features on the tooth surface (especially the occlusal surface, pits and fissures, cusp bevels, and stress concentration areas at the cervical region) are identified. The spatial length of the identified cracks is measured, their orientation (e.g., parallel to the long axis of the tooth, perpendicular to the long axis of the tooth, oblique, or arc-shaped around the cervical region) is analyzed, and their depth is estimated based on the depth of the crack's depression in the 3D model.

[0145] The characteristic parameter changes of tooth cracks include at least one of the following: crack length extension rate and crack depth deepening rate. Specifically, the length and depth data of the same crack extracted from two adjacent first 3D scan images are compared. The length difference and depth difference are calculated and divided by the time interval between adjacent images to obtain the crack length extension rate and crack depth deepening rate. For newly appearing cracks, their initial position, length, and depth are marked.

[0146] The evolutionary information of a tooth crack includes at least one of the following: the future rate of crack length extension, the future rate of crack depth increase, the predicted direction of crack propagation, and the probability of tooth fracture. Specifically, the calculated dynamic change data, such as the rate of crack length extension and the rate of crack depth increase, are combined with the patient's individual bad habits data (such as bruxism, the intensity and frequency of clenching), occlusal relationship data, and dietary habit data (such as the frequency of chewing hard objects) and input into the prediction model. The model analyzes this dynamic change data, predicts the rate of existing crack length extension and depth increase over a future period, predicts its possible propagation direction (such as whether it will extend towards the root or pulp chamber), and calculates the probability that the crack will lead to complete tooth fracture in the future.

[0147] As an optional implementation, in cases where the oral cavity condition includes wear on the occlusal surfaces of teeth, S120: extract one or more feature parameters for characterizing the oral cavity condition from multiple first three-dimensional scan images, including S1271-S1272.

[0148] S1271: Determine the time interval between adjacent first three-dimensional scan images.

[0149] S1272: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize wear on the occlusal surface of teeth.

[0150] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S1371-S1372.

[0151] S1371: Determine the change information of the characteristic parameters of tooth occlusal surface wear based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of tooth occlusal surface wear.

[0152] S1372: Based on the changes in characteristic parameters of tooth occlusal surface wear, predict the evolution of tooth occlusal surface wear using a predictive model.

[0153] The characteristic parameters of tooth occlusal surface wear include at least one of the following: cusp height reduction, occlusal surface concavity area / depth, and tooth volume loss. Specifically, occlusal surface wear is quantitatively analyzed in multiple first-dimensional scan images: by comparing the current occlusal surface 3D morphology with a preset tooth anatomical reference model or a scan image of the patient in an early, unworn (or slightly worn) state, the height reduction of a specific cusp apex or ridge relative to a reference point is accurately measured. The area and average depth (or maximum depth) of concave areas formed by wear on the occlusal surface (such as flattening of pits and fissures, or platforms formed by cusp wear) are identified and calculated. The volume loss of tooth hard tissue in the occlusal surface region is obtained by calculating the volume difference between the current occlusal surface 3D model and the reference model.

[0154] The characteristic parameters of tooth occlusal surface wear include at least one of the following: the rate of decrease in cusp height, the rate of expansion / deepening of the occlusal surface concavity area, and the rate of tooth volume loss. Specifically, the data on the decrease in cusp height, the occlusal surface concavity area / depth, and the tooth volume loss of the same tooth surface are compared in two adjacent first three-dimensional scan images. The differences of each parameter are calculated and divided by the time interval between adjacent images to obtain the corresponding rates of decrease in cusp height, expansion / deepening of the occlusal surface concavity area, and tooth volume loss.

[0155] The evolutionary information of occlusal wear includes at least one of the following: the future rate of cusp height reduction, the future rate of expansion / deepening of occlusal surface concavity area, the future rate of tooth volume loss, the probability of increased risk of dentin sensitivity, the probability of increased risk of tooth crack, and the predicted reduction in occlusal vertical distance. Specifically, the calculated dynamic change data of cusp height reduction rate, concavity area expansion / deepening rate, and tooth volume loss rate are combined with the patient's individual bad habits data (such as bruxism, intensity and frequency of clenching), dietary habits data (such as frequency of acidic beverages and hard foods), and occlusal relationship data, and input into the prediction model. The model analyzes these data and risk factors to predict the future rate of cusp height reduction, concavity area expansion / deepening rate, and tooth volume loss rate due to occlusal wear. It assesses the probability of increased wear leading to dentin exposure and sensitivity symptoms, as well as the probability of new or worsened tooth cracks due to decreased tooth strength and stress concentration. For patients with severe wear across the entire dentition, the potential reduction in the overall occlusal vertical distance can also be predicted.

[0156] As an optional implementation, in cases where the oral condition includes periodontitis, S120: extract one or more feature parameters for characterizing the oral condition from multiple first three-dimensional scan images, including S1281-S1282.

[0157] S1281: Determine the time interval between adjacent first three-dimensional scan images.

[0158] S1282: Extract one or more feature parameters from multiple first three-dimensional scan images to characterize periodontitis.

[0159] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S1381-S1382.

[0160] S1381: Determine the change information of periodontal disease characteristic parameters based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of periodontitis.

[0161] S1382: Based on the changes in characteristic parameters of periodontitis, predict the evolution of periodontitis using a predictive model.

[0162] Characteristic parameters of periodontitis include at least one of the following: periodontal pocket depth, clinical attachment loss (CAL), and alveolar bone resorption height. Specifically, in multiple first-stage 3D scan images: the gingival sulcus / periodontal pocket boundary is identified using 3D image segmentation technology, and the vertical distance from the pocket floor to the gingival margin is measured as the periodontal pocket depth. The cementoenamel junction (CEJ) is positioned as a reference point, and the distance from the gingival margin to the CEJ (gingival recession) and the distance from the pocket floor to the CEJ are measured to calculate the clinical attachment loss (CAL = recession + probing depth). The alveolar bone resorption height is determined by combining the first-stage 3D scan images.

[0163] The characteristic parameters of periodontitis include at least one of the following: the rate of periodontal pocket deepening, the rate of clinical attachment loss, and the rate of alveolar bone resorption. Specifically, the rate of periodontal pocket deepening is obtained by comparing the difference in periodontal pocket depth at the same location in two adjacent images and dividing by the time interval. The rate of clinical attachment loss is obtained by comparing the difference in clinical attachment loss at the same location and dividing by the time interval. The rate of alveolar bone resorption is obtained by comparing the difference in alveolar bone resorption height in the same region and dividing by the time interval.

[0164] The evolutionary information of periodontitis includes at least one of the following: the future rate of periodontal pocket deepening, the future rate of attachment loss, the future rate of bone resorption, prediction of active lesion sites, and the probability of tooth loosening. Specifically, the calculated dynamic data such as the rate of periodontal pocket deepening, the rate of clinical attachment loss, and the rate of alveolar bone resorption are combined with the patient's individual systemic disease data (such as diabetes control level), genetic data (family history of periodontitis), oral hygiene data (plaque control level), and smoking data, and input into the prediction model. The model comprehensively analyzes the dynamic progression trend and risk factors to predict: the future rate of periodontal pocket deepening, the rate of attachment loss, and the rate of bone resorption at specific sites; high-risk active lesion sites (i.e., areas that may deteriorate rapidly in the future); and the probability of tooth loosening / loss calculated based on the degree and rate of bone resorption.

[0165] As an optional implementation, the method for predicting oral cavity status further includes S200.

[0166] S200: Obtain at least one of the following patient data: dietary data, oral hygiene habit data, age data, gender data, bad habit data, systemic disease data, and genetic data.

[0167] Factors such as a patient's diet (e.g., frequency of consumption of sweets, colored drinks, and coffee per week), oral hygiene habits (e.g., brushing frequency and flossing), age, gender, unhealthy habits (e.g., smoking, excessive alcohol consumption, biting hard objects), systemic diseases (e.g., diabetes, hypertension, cardiovascular disease), and genetics (e.g., family history of oral health conditions) can all influence the occurrence, development, and evolution of oral health conditions. Obtaining this data can provide a more comprehensive understanding of each patient's individual situation and offer richer evidence for accurately predicting the evolution of oral health conditions.

[0168] The above data can be obtained by asking patients or designing questionnaires for them to fill out.

[0169] Correspondingly, S130: Based on one or more characteristic parameters of the oral cavity state, predict the evolution information of the oral cavity state through a prediction model, including S1391 and S1392.

[0170] S1391: Adjust the weight parameters of the prediction model based on at least one of the patient's dietary data, oral hygiene habits data, age data, gender data, bad habits data, systemic disease data, and genetic data.

[0171] For example, since patient dietary data, oral hygiene habits, and unhealthy habits can lead to pigment deposition, if the frequency of consumption of colored beverages (such as coffee, tea, and red wine) is too high, the predictive model will have a greater weight in identifying pigment deposition and tartar. If oral hygiene habits show that brushing frequency is too low or the method is improper, the predictive model will have a greater weight in identifying plaque buildup, gingival inflammation (such as redness and swelling, bleeding on probing), and interproximal caries. If the age data is too high, the predictive model will have a greater weight in identifying the degree of gingival recession and alveolar bone resorption, caries, and tooth wear. If the gender data shows male, the predictive model will have a greater weight in identifying the rate of tartar deposition and the depth of periodontal pockets. If unhealthy habits data show a high frequency of smoking, the predictive model will have a greater weight in identifying tooth pigment deposition, the rate of tartar formation, and oral mucosal abnormalities (such as leukoplakia / erythema). If unhealthy habits data show nocturnal teeth grinding or clenching, the predictive model will have a greater weight in identifying tooth tilt, tooth wear, tooth cracks, and periodontal tissue trauma. If systemic disease data indicates diabetes, the predictive power for the degree of oral inflammation, periodontal pocket depth, and alveolar bone resorption rate in the predictive model is significantly increased. If systemic disease data indicates a blood disorder (such as leukemia) or the use of anticoagulants, the predictive power for abnormal gingival swelling in the predictive model is significantly increased. If systemic disease data indicates gastroesophageal reflux disease, the predictive power for dental caries or lingual erosion of the teeth in the predictive model is significantly increased. If genetic data indicates a family history of dental caries, the predictive power for dental caries in the predictive model is significantly increased. If genetic data indicates a family history of periodontitis, the predictive power for signs of aggressive periodontitis or oral gingival inflammation in the predictive model is significantly increased.

[0172] S1392: Predict the evolution information of oral cavity state based on the adjusted prediction model and one or more feature parameters of oral cavity state.

[0173] A single feature parameter of an oral condition may not be able to fully and accurately reflect the evolution of a disease. This embodiment combines multiple relevant patient data and adjusts the weight parameters of the prediction model. The adjusted prediction model can comprehensively consider the influence of various factors on the oral condition, enabling it to more accurately predict the evolution of the oral condition and thus providing strong support for doctors to develop more reasonable treatment and prevention plans.

[0174] As an optional implementation, the method for predicting oral cavity status further includes S210.

[0175] S210: Generate an evolution video of the oral cavity state based on the evolution information of the oral cavity state and the first three-dimensional scan image.

[0176] The first three-dimensional scan images based on time series record the state of the patient's oral cavity at different time points. These first three-dimensional scan images can be used as keyframes in the evolution video. Combined with the evolution information of the oral cavity state, the evolution video of the oral cavity state is generated by frame interpolation.

[0177] Evolutionary videos can visually demonstrate the changes in oral health, helping doctors and patients better understand the evolution of diseases, and also increasing patients' awareness of their oral health and their willingness to receive treatment.

[0178] As an optional implementation, the method for predicting oral cavity status further includes S220-S250.

[0179] S220: Acquire third three-dimensional scan images of the face of the same patient at different times; the acquisition time of the third three-dimensional scan image corresponds to that of the first three-dimensional scan image.

[0180] Optionally, each time the patient's mouth is scanned by an oral scanner, the patient's face is scanned by a facial scanner to obtain a time-series-based third-dimensional scan image.

[0181] S230: The third 3D scan image corresponding to the acquisition time is stitched together with the first 3D scan image to obtain a composite model.

[0182] Specifically, the composite model is obtained by stitching together the third-dimensional scan image and the first-dimensional scan image in a unified coordinate system based on the overlapping area. In this model, the tooth region in the third-dimensional scan image is replaced by the first-dimensional scan image, or the tooth region in the third-dimensional scan image is hidden, while the first-dimensional scan image displays the tooth region.

[0183] S240: Based on the changes in characteristic parameters around the missing teeth and the comprehensive model, the predictive model predicts the patient's facial change parameters.

[0184] Specifically, after tooth loss, especially when multiple teeth are missing, the cheek muscles lose their support and gradually sink inward. This is because the alveolar bone around the teeth is gradually absorbed as teeth are lost, leading to changes in the facial bone structure. This makes the cheeks appear less full, resulting in noticeable hollowing, an uneven facial contour, and an aged appearance. Furthermore, tooth loss affects chewing function, preventing patients from fully utilizing their chewing muscles when chewing food. Over time, the chewing muscles atrophy due to insufficient exercise and stimulation. This atrophy of the chewing muscles makes the facial contours less full, causing the cheeks to appear smaller, thus altering the overall appearance of the face.

[0185] Among them, the information on changes in characteristic parameters around missing teeth includes at least the occlusal height and the degree of alveolar bone resorption, and the facial change parameters include at least the contour change parameters of both sides of the face.

[0186] During the prediction process, the patient's mandibular movement trajectory can also be obtained. Based on the mandibular movement trajectory, the movement trajectory of the muscles on both sides of the face can be determined, thereby determining the contour change parameters on both sides of the face.

[0187] S250: Generates a video of the patient's facial evolution based on the comprehensive model and facial change parameters.

[0188] Facial deformation processing is performed based on facial change parameters to generate a facial simulation model, which presents the patient's facial changes.

[0189] The patient's facial evolution video can intuitively show the facial changes caused by tooth loss, making the patient more willing to cooperate with the doctor and accept treatment.

[0190] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0191] Corresponding to the method for predicting oral cavity status described in the above embodiments, Figure 2 A structural block diagram of the oral cavity state prediction device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0192] Reference Figure 2 The device includes:

[0193] The first acquisition module 10 is used to acquire first three-dimensional scan images of the oral cavity of the same patient at different times, and the first three-dimensional scan images are used to reflect the oral cavity status of the patient.

[0194] Extraction module 20 is used to extract one or more feature parameters from a plurality of the first three-dimensional scan images to characterize the oral cavity state;

[0195] The prediction module 30 is used to predict the evolution information of the oral cavity state based on one or more feature parameters of the oral cavity state through a prediction model. The evolution information is used to assess the patient's oral health status.

[0196] As an optional implementation, in the case of missing teeth in the oral cavity, the extraction module includes:

[0197] The first determining module is used to determine the time interval between adjacent first three-dimensional scan images;

[0198] The first extraction submodule is used to extract one or more feature parameters from multiple first three-dimensional scan images to characterize the missing tooth; the feature parameters of the missing tooth include: the type and location of the missing tooth, the long axis of the adjacent tooth of the missing tooth, and the height and morphology of the alveolar bone around the missing tooth;

[0199] Correspondingly, the prediction module includes:

[0200] The second determining module is used to determine the change information of the feature parameters around the missing tooth based on the time interval between adjacent first three-dimensional scan images and one or more feature parameters of the missing tooth; the change information of the feature parameters around the missing tooth includes at least one of: the tilting velocity of the adjacent tooth of the missing tooth, the displacement velocity of the adjacent tooth of the missing tooth, and the alveolar bone resorption velocity around the missing tooth.

[0201] The first prediction submodule is used to predict the evolutionary information around the missing tooth based on the change information of the characteristic parameters around the missing tooth through the prediction model; the evolutionary information around the missing tooth includes at least one of the following: the future tilting velocity of the adjacent tooth of the missing tooth, the future displacement velocity of the adjacent tooth of the missing tooth, and the future alveolar bone resorption velocity around the missing tooth.

[0202] As an optional implementation, if oral mucosal abnormalities also exist, the oral condition prediction device further includes:

[0203] The third determining module is used to determine the location and area of ​​the abnormal mucosal regions in the multiple first three-dimensional scan images;

[0204] The fourth determining module is used to determine the evolution information of the mucosal abnormal region based on the time interval between adjacent first three-dimensional scan images and the location and area of ​​the mucosal abnormal region.

[0205] The fifth determining module is used to determine the timing of dental implantation based on the evolutionary information of the abnormal mucosal region and the evolutionary information around the missing tooth.

[0206] As an optional implementation, the oral cavity state prediction device further includes:

[0207] The sixth determining module is used to determine a three-dimensional model of the implantation effect of the missing tooth before implantation.

[0208] The second acquisition module is used to acquire a second three-dimensional scan image of the patient's oral cavity after tooth implantation;

[0209] The seventh determining module is used to determine the degree of restoration of the missing tooth after implantation based on the three-dimensional model of the implantation effect and the second three-dimensional scan image.

[0210] As an optional implementation, when the oral cavity condition includes the presence of gingival recession, the extraction module includes:

[0211] The second extraction submodule is used to extract one or more feature parameters from multiple first three-dimensional scan images to characterize the gingival recession; the feature parameters of the gingival recession include: gingival margin line and gingival volume;

[0212] Correspondingly, the prediction module includes:

[0213] The eighth determining module is used to determine the change information of the characteristic parameters of gingival recession based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of gingival recession; the change information of the characteristic parameters of gingival recession includes at least one of: the movement speed of the gingival margin line and the rate of decrease in gingival volume;

[0214] The second prediction submodule is used to predict the evolution information of gingival recession based on the change information of the characteristic parameters of gingival recession through the prediction model; the evolution information of gingival recession includes at least one of the future movement speed of the gingival margin line and the future reduction speed of the gingival volume.

[0215] As an optional implementation, the oral cavity state prediction device further includes:

[0216] The third acquisition module is used to acquire at least one of the following: patient's dietary data, oral hygiene habit data, age data, gender data, bad habit data, systemic disease data, and genetic data;

[0217] Correspondingly, the prediction module includes:

[0218] The weight adjustment module is used to adjust the weight parameters of the prediction model based on at least one of the patient's dietary data, oral hygiene habit data, age data, gender data, bad habit data, systemic disease data, and genetic data.

[0219] The third prediction submodule predicts the evolution information of the oral cavity state based on the adjusted prediction model and one or more feature parameters of the oral cavity state.

[0220] As an optional implementation, the oral cavity state prediction device further includes:

[0221] The video generation module is used to generate an evolution video of the oral cavity state based on the evolution information of the oral cavity state and the first three-dimensional scan image.

[0222] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0223] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0224] This application also provides an oral cavity state prediction system, including: an oral scanner for scanning a patient's oral cavity multiple times to obtain multiple first three-dimensional scan images; and an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the above embodiments.

[0225] Optionally, the electronic device can be a computer, mobile phone, television, etc.

[0226] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0227] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0228] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0229] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0230] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Python, Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0231] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0232] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0233] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0234] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0235] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for predicting oral cavity status, applied to electronic devices, characterized in that, include: Acquire first three-dimensional scan images of the oral cavity of the same patient at different times, the first three-dimensional scan images being used to reflect the oral cavity status of the patient; Extract one or more feature parameters from multiple first three-dimensional scan images to characterize the oral cavity state; Based on one or more characteristic parameters of the oral cavity state, an evolutionary information of the oral cavity state is predicted by a predictive model, and the evolutionary information is used to assess the patient's oral health status. In cases where mucosal abnormalities also exist in the oral cavity, the method further includes: Determine the location and area of ​​multiple abnormal mucosal regions in the first three-dimensional scan images; Based on the time interval between adjacent first three-dimensional scan images and the location and area of ​​the mucosal abnormality region, the evolution information of the mucosal abnormality region is determined; The timing of dental implantation is determined based on the evolutionary information of the abnormal mucosal area and the evolutionary information around the missing tooth; the evolutionary information around the missing tooth includes at least one of the following: the future tilting velocity of the adjacent tooth of the missing tooth, the future displacement velocity of the adjacent tooth of the missing tooth, and the future alveolar bone resorption velocity around the missing tooth.

2. The method for predicting oral cavity status as described in claim 1, characterized in that, In the case of missing teeth in the oral cavity, the extraction of one or more feature parameters characterizing the oral cavity from multiple first three-dimensional scan images includes: Determine the time interval between adjacent first three-dimensional scan images; One or more feature parameters for characterizing the missing tooth are extracted from multiple first three-dimensional scan images; the feature parameters of the missing tooth include: the type and location of the missing tooth, the long axis of the adjacent tooth of the missing tooth, and the height and morphology of the alveolar bone surrounding the missing tooth; The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes: Based on the time interval between adjacent first three-dimensional scan images and one or more feature parameters of the missing tooth, change information of feature parameters around the missing tooth is determined; the change information of feature parameters around the missing tooth includes at least one of: tilting velocity of adjacent teeth of the missing tooth, displacement velocity of adjacent teeth of the missing tooth, and alveolar bone resorption velocity around the missing tooth. Based on the changes in characteristic parameters around the missing tooth, the evolutionary information around the missing tooth is predicted using the prediction model.

3. The method for predicting oral cavity status as described in claim 1, characterized in that, The method further includes: Before implanting the missing tooth, a three-dimensional model of the implantation effect is determined. Acquire a second three-dimensional scan image of the patient's oral cavity after tooth implantation; Based on the three-dimensional model of the implantation effect and the second three-dimensional scan image, the degree of restoration after implantation of the missing tooth is determined.

4. The method for predicting oral cavity status as described in claim 1, characterized in that, The method further includes: Acquire third three-dimensional scan images of the face of the same patient at different times; the acquisition time of the third three-dimensional scan image corresponds to that of the first three-dimensional scan image. The third 3D scan image corresponding to the acquisition time is stitched together with the first 3D scan image to obtain a comprehensive model; Based on the changes in characteristic parameters around the missing teeth and the integrated model, the predictive model predicts facial change parameters of the patient. Based on the comprehensive model and the facial change parameters, a video of the patient's facial evolution is generated.

5. The method for predicting oral cavity status as described in claim 1, characterized in that, In cases where the oral cavity exhibits gingival recession, tartar buildup, tooth cracks, wear on the occlusal surfaces of teeth, or periodontitis; The step of extracting one or more feature parameters from multiple first three-dimensional scan images to characterize the oral cavity state includes: Determine the time interval between adjacent first three-dimensional scan images; One or more feature parameters are extracted from multiple first three-dimensional scan images to characterize the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis; wherein, the feature parameters for gingival recession include: gingival margin line and gingival volume; the feature parameters for dental calculus include: at least one of calculus coverage area and average calculus thickness; the feature parameters for tooth crack include: at least one of crack length, crack depth, and crack orientation; the feature parameters for occlusal surface wear include: at least one of: cusp height reduction, occlusal surface concavity area / depth, and tooth volume loss; the feature parameters for periodontitis include: periodontal pocket depth, clinical attachment loss, and alveolar bone resorption height. The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes: Based on the time interval between adjacent first three-dimensional scan images and one or more characteristic parameters of the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis, the change information of characteristic parameters of the gingival recession, dental calculus, tooth crack, occlusal surface wear, or periodontitis is determined; wherein, the change information of characteristic parameters of the gingival recession includes at least one of the following: the speed of gingival margin movement and the speed of gingival volume reduction; the change information of characteristic parameters of dental calculus includes at least one of the following: the speed of calculus coverage area expansion and the speed of calculus average thickness increase; the change information of characteristic parameters of tooth crack includes at least one of the following: the speed of crack length extension and the speed of crack depth deepening; the change information of characteristic parameters of occlusal surface wear includes at least one of the following: the speed of cusp height reduction, the speed of occlusal surface concavity area expansion / depth deepening, and the speed of tooth volume loss; the change information of characteristic parameters of periodontitis includes at least one of the following: the speed of periodontal pocket deepening, the speed of clinical attachment loss, and the speed of alveolar bone resorption acceleration. Based on the changes in the characteristic parameters of gingival recession, the prediction model predicts the evolution information of gingival recession, tartar, tooth cracks, occlusal surface wear, or periodontitis. The evolution information of gingival recession includes at least one of: the future movement rate of the gingival margin and the future decrease rate of gingival volume. The evolution information of tartar includes at least one of: the future expansion rate of tartar coverage area, the future increase rate of average tartar thickness, and the risk of tartar accumulation in specific locations. The evolution information of tooth cracks includes: the future rate of crack length extension, the future rate of crack thickness increase, and the future rate of crack accumulation. The information on the evolution of tooth occlusal surface wear includes at least one of the following: the rate of future cusp height reduction, the rate of future expansion / deepening of occlusal surface concavity area, the rate of future tooth volume loss, the probability of increased dentin hypersensitivity risk, the probability of increased tooth crack risk, and the prediction of decreased occlusal vertical distance. The information on the evolution of periodontitis includes at least one of the following: the rate of future periodontal pocket deepening, the rate of future attachment loss, the rate of future bone resorption acceleration, the prediction of active lesion sites, and the probability of tooth loosening risk.

6. The method for predicting oral cavity status as described in claim 1, characterized in that, The method further includes: Obtain at least one of the following patient data: dietary data, oral hygiene habits data, age data, gender data, unhealthy habits data, systemic disease data, and genetic data; The step of predicting the evolution information of the oral cavity state using a prediction model based on one or more feature parameters of the oral cavity state includes: The weight parameters of the prediction model are adjusted based on at least one of the patient's dietary data, oral hygiene habits data, age data, gender data, bad habits data, systemic disease data, and genetic data. Based on the adjusted prediction model and one or more feature parameters of the oral cavity state, the evolution information of the oral cavity state is predicted.

7. The method for predicting oral cavity status as described in any one of claims 1-6, characterized in that, The method further includes: Based on the evolution information of the oral cavity state and the first three-dimensional scan image, an evolution video of the oral cavity state is generated.

8. An oral cavity state prediction device, characterized in that, include: The first acquisition module is used to acquire first three-dimensional scan images of the oral cavity of the same patient at different times, and the first three-dimensional scan images are used to reflect the oral cavity status of the patient. An extraction module is used to extract one or more feature parameters from a plurality of the first three-dimensional scan images to characterize the oral cavity state; The prediction module is used to predict the evolution information of the oral cavity state based on one or more feature parameters of the oral cavity state through a prediction model, and the evolution information is used to assess the oral health status of the patient. In cases where mucosal abnormalities also exist in the oral cavity; The prediction module also includes: The first determining module is used to determine the location and area of ​​multiple mucosal abnormalities in the first three-dimensional scan images; The second determining module is used to determine the evolution information of the mucosal abnormal region based on the time interval between adjacent first three-dimensional scan images and the location and area of ​​the mucosal abnormal region. The third determining module is used to determine the timing of dental implantation based on the evolutionary information of the abnormal mucosal region and the evolutionary information around the missing tooth; the evolutionary information around the missing tooth includes at least one of the following: the future tilting velocity of the adjacent tooth of the missing tooth, the future displacement velocity of the adjacent tooth of the missing tooth, and the future alveolar bone resorption velocity around the missing tooth.

9. An oral cavity state prediction system, characterized in that, include: An oral scanner is used to scan a patient's oral cavity multiple times to obtain multiple first-dimensional scan images; An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 7; Alternatively, the oral cavity state prediction system includes: an oral scanner for scanning the patient's oral cavity multiple times to obtain multiple first three-dimensional scan images, and for performing the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, When the computer program product is run on an electronic device, it causes the electronic device to perform the method as described in any one of claims 1 to 7.

Images