Oral Condition Evaluation System

Abstract

To provide an oral cavity state evaluation system capable of suitable analysis and estimation of an oral cavity image.SOLUTION: The oral cavity state evaluation system includes an information analysis part which analyzes an oral cavity image included in an input image with first analysis means. The information analysis part classifies the oral cavity image into a first oral cavity image which can be analyzed with the first analysis means and a second oral cavity image which cannot be analyzed with the first analysis means. The first oral cavity image is analyzed with the first analysis means by the information analysis part and in a case where the oral cavity image is the second oral cavity image, the oral cavity image is analyzed with second analysis means different from the first analysis means.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an oral cavity condition evaluation system that evaluates a user's oral cavity condition. [Background technology]

[0002] There is known a system that analyzes the oral cavity condition from an oral cavity image including the entire oral cavity and assists a dentist or other specialist in making a judgment. Patent Document 1 discloses a dental analysis system that extracts lesions from an X-ray image of the entire oral cavity of a user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-208831 A Summary of the Invention [Problem to be solved by the invention]

[0004] The oral condition of each user varies as the user ages. For example, the variation is caused by acquired tooth loss, caries, and treatment. Oral images reflecting the varied oral conditions may not be able to be appropriately analyzed and evaluated by a single means. [Means for solving the problem]

[0005] The oral condition evaluation system of the present invention is an oral condition evaluation system including an information analysis unit that analyzes oral images included in an input image using a first analysis means, and the information analysis unit classifies the oral images into first oral images that can be analyzed by the first analysis means and second oral images that cannot be analyzed by the first analysis means, and the first oral images are analyzed by the information analysis unit using the first analysis means, and if the oral image is the second oral image, it is analyzed by a second analysis means different from the first analysis means. Effect of the Invention

[0006] According to the oral cavity condition evaluation system of the present invention, appropriate analysis and evaluation of oral cavity images can be performed. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing the configuration of an oral cavity condition evaluation system according to an embodiment. [Diagram 2] FIG. 4 is a diagram showing an example of a first intraoral image. [Diagram 3] FIG. 13 is a diagram showing an example of a second intraoral image. [Figure 4] 11 is a flowchart showing an example of an analysis of an oral cavity image executed by an information analysis unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] (An example of the form that an oral condition evaluation system can take) (1) According to the oral condition evaluation system of the present disclosure, there is provided an oral condition evaluation system including an information analysis unit that analyzes an oral image included in an input image by a first analysis means, wherein the information analysis unit classifies the oral image into a first oral image that can be analyzed by the first analysis means and a second oral image that cannot be analyzed by the first analysis means, and the first oral image is analyzed by the information analysis unit by the first analysis means, and if the oral image is the second oral image, it is analyzed by a second analysis means different from the first analysis means. According to the above-mentioned oral cavity condition evaluation system, the oral cavity images are classified into the first oral cavity images and the second oral cavity images, the first oral cavity images are analyzed by the first analysis means, and the second oral cavity images are analyzed by the second analysis means, so that the oral cavity images are appropriately analyzed and evaluated.

[0009] (2) According to one example of the oral cavity condition evaluation system, the first analysis means includes analysis using an analytical learning model that has been pre-trained on images related to the oral cavity, and a first analysis result, which is the analysis result of the first oral cavity image by the first analysis means, is output. According to the above-described oral cavity condition evaluation system, the user can appropriately recognize the oral cavity condition based on the first analysis result by the first analysis means.

[0010] (3) According to one example of the oral cavity condition evaluation system, the second analysis means includes analysis by at least one of an expert, an examination device, and an examination instrument, and a second analysis result, which is the analysis result of the second oral cavity image by the second analysis means, is output. According to the above-described oral cavity condition evaluation system, the user can appropriately recognize the oral cavity condition based on the second analysis result by the second analysis means.

[0011] (4) According to an example of the oral cavity condition evaluation system, at least one of the second oral cavity image and the second analysis result is stored in a database. According to the above-described oral cavity condition evaluation system, information relating to the second oral cavity image is suitably stored.

[0012] (5) According to an example of the oral cavity condition evaluation system, the information analysis unit classifies the first oral cavity image and the second oral cavity image using a classification learning model that has learned images related to the oral cavity. According to the above-described intraoral condition evaluation system, the first intraoral image and the second intraoral image can be suitably classified.

[0013] (6) According to an example of the oral cavity condition evaluation system, at least one of the analysis learning model and the classification learning model is updated based on analysis of the second oral cavity image. According to the above-described intraoral condition evaluation system, the learning model is updated based on information relating to the second intraoral image, thereby improving the accuracy of the learning model.

[0014] (7) According to an example of the oral cavity condition evaluation system, the system further includes an external terminal that displays the second oral cavity image and inputs an analysis result of the second oral cavity image. According to the above-described oral cavity condition evaluation system, analysis can be easily performed by, for example, an expert using an external terminal different from the interface unit.

[0015] (8) According to one example of the oral condition evaluation system, the information analysis unit further classifies the input image into an oral image and a non-oral image that does not include the oral cavity, and outputs a third analysis result if the input image is a non-oral image. According to the above-described oral cavity condition evaluation system, the user can easily recognize from the third analysis result that the input image is not appropriate.

[0016] (9) An example of the oral cavity condition evaluation system further includes an interface unit for acquiring the input image. According to the above-described oral cavity condition evaluation system, the user can preferably input an input image.

[0017] (10) According to one example of the oral cavity condition evaluation system, the interface unit includes a display unit, and the display unit displays at least one of the first analysis result, the second analysis result, and the third analysis result. According to the above-described oral cavity condition evaluation system, the user can easily recognize at least one of the first analysis result, the second analysis result, and the third analysis result.

[0018] (Embodiment) An oral cavity condition evaluation system 10 of this embodiment will be described with reference to Figs. 1 to 4. The oral cavity condition evaluation system 10 is a system that acquires and analyzes input information I related to an oral cavity condition and outputs output information O. A main element constituting the oral cavity condition evaluation system 10 is a server 30. Preferably, the oral cavity condition evaluation system 10 includes an interface unit 20 for executing information exchange with the server 30. In one example, the interface unit 20 is a smart device configured to be portable by a user. The smart device includes a tablet terminal or a smartphone. In another example, the interface unit 20 is a personal computer. The personal computer is installed in the user's residence, a store, or a dental clinic. The store includes a store that sells oral care items or a store that sells other products. The interface unit 20 and the server 30 are configured to be able to communicate with each other using, for example, an Internet line N. In another example, the interface unit 20 and the server 30 are configured as a single unit.

[0019] The interface unit 20 includes a control unit 21, a storage unit 22, an acquisition unit 23, a communication unit 24, and a display unit 25. The control unit 21 includes a processor that executes a predetermined control program. The processor includes, for example, a CPU, a GPU, or an MPU.

[0020] The storage unit 22 stores various control programs executed by the control unit 21 and information used for various control processes. The storage unit 22 includes, for example, a non-volatile memory and a volatile memory. The non-volatile memory includes, for example, at least one of a ROM, an EPROM, an EEPROM, and a flash memory. The volatile memory includes, for example, a RAM.

[0021] The acquisition unit 23 acquires input information I from the user. The acquisition unit 23 has any configuration for acquiring the input information I of the user. In one example, the input information I is a camera that can acquire an oral cavity image P of the user's oral cavity as an input image. The input image includes a still image and a video. The input image includes a three-dimensional image having depth information or a panoramic image formed by pasting together a plurality of images. The camera may be a camera mounted on a smart device, or may be a separate independent camera. The independent camera is, for example, a pen-shaped camera with a camera at the tip that is suitable for photographing the oral cavity, or a camera capable of photographing a 360° range. The independent camera is configured to be capable of wired or wireless communication with the control unit 21. The input image photographed by the independent camera is transmitted to the control unit 21 by wired or wireless communication.

[0022] The communication unit 24 is configured to be able to communicate with the outside of the interface unit 20 under the control of the control unit 21. The communication unit 24 is configured to be able to communicate via an Internet line N. The communication unit 24 may be configured to be able to communicate with the server 30 of the interface unit 20 by wired communication or wireless communication. The communication unit 24 transmits, for example, the user's input information I acquired by the acquisition unit 23 under the control of the control unit 21, and receives information from the server 30.

[0023] The display unit 25 displays various information under the control of the control unit 21. The various information is, for example, information related to the user's input information I and information from the server 30. In one example, the display unit 25 is configured with a display. The display of the display unit 25 may be configured with a touch panel. When a part of the display unit 25 is configured with a touch panel, a part of the touch panel may also function as a user interface of the acquisition unit 23.

[0024] The user communicates with the server 30, for example, by inputting a specific URL into the interface unit 20 or by reading a QR code (registered trademark) with the interface unit 20. The user may also start communication with the server 30 by selecting an icon displayed on the display unit 25.

[0025] The server 30 includes an information acquisition unit 31, an information output unit 32, an information analysis unit 33, and an information storage unit 34. The information acquisition unit 31 is configured to be able to acquire information. In one example, the information acquisition unit 31 acquires information from the communication unit 24 of the interface unit 20. The information output unit 32 is configured to be able to output information. In one example, the information output unit 32 outputs information to the communication unit 24 of the interface unit 20.

[0026] The information analysis unit 33 executes various analyses and controls. The information analysis unit 33 includes a calculation processing unit that executes a predetermined control program. The calculation processing unit includes, for example, a CPU or an MPU. The information analysis unit 33 is configured to be able to analyze input information I from a user. In one example, the information analysis unit 33 analyzes an oral cavity image P included in the input information I using a first analysis means. The first analysis means includes an analysis using a learning model based on machine learning. In one example, the learning model is a supervised learning model, which is one of the machine learning models. In another example, the learning model is an unsupervised learning model or a reinforcement learning model.

[0027] The information storage unit 34 stores at least one of the learning model and various pieces of information. The information analysis unit 33 refers to the learning model and various pieces of information stored in the information storage unit 34 as necessary.

[0028] The oral cavity condition evaluation system 10 further includes a database 40 and an external terminal 50. The database 40 stores at least one of the second oral cavity image P2 and the second analysis result. The database 40 is configured to be able to communicate with at least one of the interface unit 20, the server 30, and the external terminal 50.

[0029] The external terminal 50 is used to analyze the second intraoral image P2 by the second analysis means. The external terminal 50 is, for example, a smart device or a personal computer. The external terminal 50 includes a control unit 51, a storage unit 52, a communication unit 53, and a display unit 54. The control unit 51 includes a calculation processing unit that executes a predetermined control program. The calculation processing unit includes, for example, a CPU, a GPU, or an MPU.

[0030] The storage unit 52 stores various control programs executed by the control unit 51 and information used for various control processes. The storage unit 52 includes, for example, a non-volatile memory and a volatile memory. The non-volatile memory includes, for example, at least one of a ROM, an EPROM, an EEPROM, and a flash memory. The volatile memory includes, for example, a RAM.

[0031] The communication unit 53 is configured to be able to communicate with elements other than the external terminal 50 under the control of the control unit 51. In one example, the communication unit 53 is configured to be able to communicate via the Internet line N. The communication targets are at least one of the interface unit 20, the server 30, and the database 40.

[0032] The display unit 54 displays information under the control of the control unit 51. The information to be displayed is, for example, the second oral cavity image P2. In one example, the display unit 25 is configured with a display. The display of the display unit 25 may be configured with a touch panel.

[0033] The information analysis unit 33 classifies the input image into an oral cavity image P or a non-oral cavity image. In one example, a trained model suitable for detecting a face is used to determine whether the oral cavity image P is an oral cavity image or a non-oral cavity image depending on whether the oral cavity region R can be detected from the input image. The oral cavity region R includes a first oral cavity region R1 including the user's upper jaw teeth and a second oral cavity region R2 including the user's lower jaw teeth. The trained model for detecting faces is introduced into the information analysis unit 33 by, for example, an API. The non-oral cavity image includes an image in which the oral cavity region R cannot be recognized due to, for example, not including the oral cavity region R, being blurred, or having inappropriate brightness.

[0034] When the input image is a non-oral image, the information analysis unit 33 outputs information to the display unit 25 of the interface unit 20 requesting the user to re-input the input information I including the oral cavity image P. When one of the first oral cavity region R1 and the second oral cavity region R2 can be acquired but the other cannot be acquired, the information analysis unit 33 may be configured to determine that the input image is an oral cavity image P or a non-oral cavity image.

[0035] The oral cavity image P includes a first oral cavity image P1 and a second oral cavity image P2. FIG. 2 shows an example of the first oral cavity image P1. The first oral cavity image P1 is an image that is determined to be analyzable by the analytical learning model MA. FIG. 3 shows an example of the second oral cavity image P2. The second oral cavity image P2 is an image that is determined to be unanalyzable by the analytical learning model MA. The second oral cavity image P2 includes, for example, missing teeth, recession, caries, and fillings in the oral cavity region R. The second oral cavity image P2 shown in FIG. 3 is missing some teeth. The first oral cavity image P1 is analyzed by a first analysis means.

[0036] The first oral cavity image P1 includes at least a first specific part in the oral cavity. The first specific part includes a central incisor T1, a gum corresponding to the central incisor T1, a lateral incisor T2, a gum corresponding to the lateral incisor T2, a canine T3, and a gum corresponding to the canine T3. The first oral cavity image P1 includes a tooth image and a gum image in the oral cavity. The tooth image includes a central incisor T1 image, a lateral incisor T2 image, and a canine T3 image in the oral cavity. The gum image includes an image of the gum corresponding to the central incisor T1, the lateral incisor T2, and the canine T3. The first oral cavity image P1 includes at least one of the four first specific parts in the upper, lower, left, and right of the user's oral cavity. The analysis result of the first oral cavity image P1 by the first analysis means is output as a first analysis result.

[0037] The following describes the analysis of the oral cavity image P using the learning model executed by the information analysis unit 33. The learning model includes at least an analysis learning model MA that analyzes the oral cavity region R of the first oral cavity image P1, and a classification learning model MC that classifies the oral cavity image P into the first oral cavity image P1 and the second oral cavity image P2.

[0038] Each learning model was developed based on approximately 10,000 oral cavity images P. The developer classified the oral cavity images P into learning images, validation images, and test images. The learning images are supervised data used when creating the learning model. The validation images are images used to correct the operation of the learning model based on the learning images. The test images are images used to finally confirm the operation of the learning model. The test images are used, for example, to confirm whether the learning model is overfitting. The learning images make up approximately 56 percent of the total. The validation images make up approximately 24% of the total. The test images make up 20% of the total.

[0039] The first oral cavity image P1 for creating the analysis learning model MA was supervised by an expert. The expert is, for example, a dentist, a dental hygienist, a researcher who studies oral conditions, or a developer who develops oral care products. The expert who analyzes the oral cavity judged the degree of crowding, the degree of gingival recession, and the degree of interdental space for at least the first oral cavity region R1 and the second oral cavity region R2 of the first oral cavity image P1. The expert who analyzes the oral cavity judged the degree of crowding based on the type of crowding. The expert who analyzes the oral cavity judged the gingival recession in multiple stages, from no gingival recession to total gingival recession. The expert who analyzes the oral cavity judged the interdental space in multiple stages, from no interdental space to severe interdental space, for each of the upper and lower jaws.

[0040] The analysis learning model MA includes a plurality of trained models. The analysis learning model MA includes a first trained model M1 that determines whether the oral cavity region R can be evaluated and a second trained model M2 that actually evaluates the oral cavity region R.

[0041] The first trained model M1 includes at least one of a learning model M11 that determines whether the oral cavity region R of the oral cavity image P has an analyzable image quality, a learning model M12 that determines whether crowding evaluation is possible, a learning model M13 that determines whether interdental space evaluation is possible for the teeth of the upper jaw, a learning model M14 that determines whether interdental space evaluation is possible for the teeth of the lower jaw, and a learning model M15 that determines whether gingival recession evaluation is possible.

[0042] The second trained model M2 includes at least one of a learning model M21 for determining whether or not there is crowding in the upper jaw teeth, a learning model M22 for determining whether or not there is crowding in the lower jaw teeth, a learning model M23 for determining whether or not there is interdental space in the upper jaw teeth, a learning model M24 for determining whether or not there is interdental space in the lower jaw teeth, and a learning model M25 for determining whether or not there is interdental recession.

[0043] The analysis learning model MA that analyzes the first oral cavity image P1 outputs the result of the classification. The analysis learning model MA outputs information on the presence or the degree of interdental gaps, gingival recession, crowding, gingival inflammation, unbrushed areas, bruxism, caries, hypersensitivity, halitosis, and staining in the first specific area, information on the presence or the degree of periodontal disease in the user's oral cavity, information on whether the chewing function is normal, information on whether the occlusion is normal, and information on whether the swallowing function is normal.

[0044] In one example, the classification learning model MC is created by learning the first intraoral image P1. In this case, the classification learning model MC makes a judgment based on whether the intraoral image P has features that are similar to the first intraoral image P1. In another example, the classification learning model MC is created by learning the second intraoral image P2. In this case, the classification learning model MC makes a judgment based on whether the intraoral image P has features that are similar to the second intraoral image P2. The classification learning model MC may be created by learning both the first intraoral image P1 and the second intraoral image P2. Classification of the intraoral images P used for learning into the first intraoral image P1 and the second intraoral image P2 is performed by an expert.

[0045] When the oral cavity image P is the second oral cavity image P2, it is analyzed by a second analysis means different from the first analysis means. The second analysis means includes an analysis means that does not use a learning model. In one example, the second analysis means is an analysis of the second oral cavity image P2 by an expert. The analysis by the expert is performed in a similar manner to the teaching of the first oral cavity image P1. The expert performs the analysis by referring to the second oral cavity image P2 displayed on the external terminal 50, for example. The second analysis means may include an analysis by at least one of an inspection device and an inspection tool. The analysis by the inspection device is, for example, an X-ray of the oral cavity of the user shown in the second oral cavity image P2. The analysis by the inspection tool is, for example, an inspection using a probe on the oral cavity of the user shown in the second oral cavity image P2.

[0046] The information analysis unit 33 outputs the second analysis result, which is the analysis result by the second analysis means, and the second intraoral image P2 to the outside of the server 30. In one example, the information analysis unit 33 outputs to at least one of the database 40 and the external terminal 50.

[0047] The information analysis unit 33 outputs the output information O based on the input information I. The output information O includes at least one of the first analysis result, the second analysis result, and the third analysis result. The first analysis result and the second analysis result include information on at least one of the presence or absence, the degree, and the occurrence probability of a predetermined state. The first analysis result and the second analysis result include at least one of information on the presence or absence or the degree of interdental gaps, gingival recession, crowding, gingival inflammation, unbrushed areas, bruxism, caries, hypersensitivity, halitosis, and staining in the first specific area, or information on the state of the teeth, gums, and oral mucosa. The information on the state of the teeth, gums, and oral mucosa includes at least one of, for example, tooth wear, tooth loss, the presence or the degree of tooth fracture, blood color, dryness, and texture. The texture includes a plurality of textures including, for example, a hard texture that feels firm when touched with a finger, and a soft texture that feels squishy when touched with a finger. The first analysis result and the second analysis result may include at least one of information on whether periodontal disease exists in the user's oral cavity, information on whether the chewing function is normal, information on whether the occlusion is normal, and information on whether the swallowing function is normal. The information on whether periodontal disease exists is information on at least one of the size, depth, and number of so-called periodontal pockets that occur between the gums and the teeth. The information on whether the chewing function is normal is, for example, information on chewing force, the presence or absence of biased chewing, and chewing sounds. The information on whether the occlusion is normal is, for example, information on the bite force and the bite of the upper and lower jaw teeth. The information on whether the swallowing function is normal is, for example, information on the presence or absence of swallowing disorders. The third analysis result includes information that the input image is a non-oral image.

[0048] The analysis learning model MA is periodically updated by the second intraoral images P2 and the second analysis results stored in the database 40. In one example, this is the case when a predetermined number or more of the second intraoral images P2 are stored in the database 40. The predetermined number is, for example, within a range of 100 to 1000. Specifically, the predetermined number of the second intraoral images P2 associated with the second analysis results are classified into learning images, verification images, and test images, and the steps of learning, verification, and testing are performed to update the analysis learning model MA.

[0049] The classification learning model MC is periodically updated by the second intraoral cavity images P2 and the second analysis results stored in the database 40. In one example, this is the case when a predetermined number or more of the second intraoral cavity images P2 are stored in the database 40. The predetermined number is, for example, within a range of 100 to 1000. Specifically, the second intraoral cavity images P2 associated with the second analysis results are used as learning images, verification images, and test images, and the steps of learning, verification, and testing are executed to update the classification learning model MC.

[0050] An example of an analysis procedure executed by the information analysis unit 33 will be described with reference to Fig. 4. The information analysis unit 33 executes the following steps periodically or every time an input image is input.

[0051] In step S11, the information analysis unit 33 determines whether or not an oral cavity image P has been input. If the determination is affirmative, the information analysis unit 33 executes the process of step S12. If the determination is negative, the information analysis unit 33 executes the process of step S17.

[0052] In step S12, the information analysis unit 33 classifies the oral cavity image P into a first oral cavity image P1 or a second oral cavity image P2 using the classification learning model MC.

[0053] In step S13, the information analysis unit 33 determines whether the oral cavity image P is the first oral cavity image P1. If the determination is affirmative, the information analysis unit 33 executes the process of step S14. If the determination is negative, the information analysis unit 33 executes the process of step S16.

[0054] In step S14, the information analysis unit 33 analyzes the first intraoral image P1 by the first analysis unit. Specifically, the first intraoral image P1 is analyzed by the analytical learning model MA. After step S14, the information analysis unit 33 executes the process of step S15.

[0055] In step S15, the information analysis unit 33 outputs the first analysis result. Specifically, it outputs the first analysis result to the interface unit 20. The control unit 21 of the interface unit 20 causes the display unit 25 to display the first analysis result.

[0056] In step S16, the information analysis unit 33 outputs the second intraoral image P2 to at least one of the database 40 and the external terminal 50. The external terminal 50 displays the second intraoral image P2 on the display unit 54, and the expert analyzes the second intraoral image P2 using the second analysis means. The expert outputs a second analysis result, which is an analysis result of the second intraoral image P2, to at least one of the server 30 and the database 40.

[0057] In step S17, the information analysis unit 33 outputs a third analysis result including information indicating that an oral cavity image has not been input and a non-oral cavity image has been input. Specifically, the information analysis unit 33 outputs the third analysis result to the interface unit 20.

[0058] In step S18, the information analysis unit 33 determines whether or not the second analysis result has been received. Specifically, the information analysis unit 33 determines whether or not the second analysis result corresponding to the oral cavity image P has been received from the external terminal 50. If the determination is positive, the information analysis unit 33 executes the process of step S19. If the determination is negative, the information analysis unit 33 ends the analysis.

[0059] In step S19, the information analysis unit 33 outputs the second analysis result. Specifically, it outputs the second analysis result to the interface unit 20. The control unit 21 of the interface unit 20 causes the display unit 25 to display the second analysis result.

[0060] The operation of the oral cavity condition evaluation system 10 of this embodiment will be described. A user inputs an input image to the acquisition unit 23 of the interface unit 20. The interface unit 20 outputs the input image to the server 30. The information analysis unit 33 of the server 30 analyzes the input image. When the input image is the first oral cavity image P1, the information analysis unit 33 outputs a first analysis result to the interface unit 20. When the input image is the second oral cavity image P2, the information analysis unit 33 outputs to the outside. The output destinations are the database 40 and the external terminal 50. When the input image is a non-oral cavity image other than the oral cavity image P, the third analysis result is output to the interface unit 20. The second oral cavity image is analyzed by an expert via the external terminal 50. The external terminal 50 outputs the second analysis result to the server 30. The information analysis unit 33 outputs the second analysis result to the interface unit 20. The user recognizes the oral cavity condition by referring to the analysis result displayed on the display unit 25 of the interface unit 20.

[0061] According to the oral cavity condition evaluating system 10 of the present embodiment, the following effects can be further obtained. The second analysis result by the second analysis means is output, for example, to the interface unit 20. Therefore, even in the case of input information I that cannot be analyzed by the first analysis means, the user can easily recognize the state of the oral cavity by referring to the second analysis result.

[0062] At least one of the analysis learning model MA and the classification learning model MC is updated in response to the second analysis result, and thus the accuracy of the analysis learning model MA and the classification learning model MC is improved as the second intraoral image and the second analysis result are stored in the database.

[0063] (Modification) The description of the embodiments is merely an example of the form that the oral cavity condition evaluation system of the present invention may take, and is not intended to limit the form. In addition to the embodiments, the present invention may take the form of, for example, modified examples of the embodiments shown below, or a combination of at least two modified examples that are not mutually contradictory.

[0064] The analytical learning model MA may be configured to output the results of the regression analysis, in which case the analytical learning model MA outputs a numerical value of at least one of the degree of crowding, the degree of interdental space, and the degree of gingival recession.

[0065] At least one of the trained model M1 and the trained model M2 may be a model trained by unsupervised learning or reinforcement learning. At least one of the trained models M11 to M15 and the trained models M21 to M25 may be a model trained by unsupervised learning or reinforcement learning.

[0066] The analysis-learning model MA may determine whether or not evaluation is possible without distinguishing between the first oral cavity region R1 and the second oral cavity region R2 in the oral cavity image P. The analysis-learning model MA may recognize a set of teeth and gums in the oral cavity image P and determine whether or not evaluation is possible. The analysis-learning model MA may also recognize each set of teeth and gums in the oral cavity region R and perform analysis if the majority of them are evaluable.

[0067] The analysis learning model MA may be configured to display the oral cavity image P in false color. In one example, the areas in the oral cavity image P that the learning model used for analysis, or areas where interdental gaps, gingival recession, and crowding occur, are displayed in red. The user can easily recognize the areas used for analysis and areas where problems occur in the oral cavity condition.

[0068] The configuration of the acquisition unit 23 is not limited to the embodiment. In one example, the acquisition unit 23 is a user interface configured to allow the user to input or select characters, etc. The input information I of the user may further include at least one of information on the user's lifestyle, information on the user's oral secretions, information on the user's oral flora, answer information to a predetermined question, and information on the user's own attributes. The information on the user's lifestyle includes information on the user's diet, oral care behavior, and wake-up or sleep time. The information on the user's oral secretions includes information on the amount, viscosity, hydrogen ion concentration, amount of antibacterial components, and amount of components related to tooth remineralization. The information on the user's oral flora includes information on the amount and type of main bacteria present in the saliva, dental plaque, or mucosa, and information on the type and amount of antibodies to the main bacteria. The information on the user's oral secretions and the information on the user's oral flora may be the result of a medical interview with the user, or may be information on the result of an examination of the oral secretions, etc. present in the user's oral cavity by a predetermined means. The answer information for the predetermined question includes questions about the state of the user's gums, a preferred brushing method for oral care, the number of times the user brushes his / her teeth per day, the time spent brushing each time, the time of day when the user brushes his / her teeth, and whether the user has dentures. The questions about the state of the user's gums include, for example, whether the user's gums bleed when brushing or eating. The information about the user's attributes is, for example, the user's age, sex, height, weight, dominant arm, and medical history. In another example, the acquisition unit 23 is a sensor that detects the state of the oral cavity. The sensor is, for example, a fluorescent sensor and a temperature sensor. The fluorescent sensor irradiates light of a predetermined wavelength and measures the amount of light to measure the distribution and amount of a predetermined substance in the oral cavity. The predetermined substance is, for example, stain or plaque. The temperature sensor measures the temperature in the oral cavity. The sensor is configured to be capable of wired or wireless communication with the control unit 21. The information obtained by the sensor is transmitted to the control unit 21 by wired or wireless communication. The sensor may be further configured to be capable of measuring at least one of chewing force, bite force, blood flow in the gums, bad breath, strength of brushing pressure during brushing, or toothbrush movement during brushing.The information analysis unit 33 may analyze the oral cavity image P by taking into account the information acquired from the acquisition unit 23.

[0069] The input information I may be acquired via an IoT device. In one example, the input information I is acquired by connecting an IoT device to an oral care item used for brushing. In one example, the input information I includes information on the number of times teeth are brushed per day and the frequency of use of the oral care item. The IoT device may transmit the input information I to the acquisition unit 23 or may transmit the input information I to the server 30.

[0070] The input information I may include first input information I1 including the user's current state information and second input information I2 being the user's past state information. When the first input information I1 and the second input information I2 include the user's oral cavity image P, the oral cavity image P included in the second input information I2 is an image of the user's oral cavity a predetermined time before the first input information I1 is acquired. When the first input information I1 and the second input information I2 include information on the user's oral care, the information on the oral care included in the second input information I2 is information on the oral care a predetermined time before the first input information I1 is acquired. In one example, the predetermined time is one month or more. In another example, the predetermined time is one year or more. The second input information I2 may be transmitted to the server 30 via the communication unit 24 before the acquisition unit 23 acquires the first input information I1, or may be transmitted to the server 30 via the communication unit 24 simultaneously with the transmission of the first input information I1. In this case, the interface unit 20 further includes a storage unit that stores at least the second input information I2. The input information I may further include a third input information I3 acquired a predetermined time before the second input information I2. The information analysis unit 33 calculates the estimated information E using at least one of the first input information I1 to the third input information I3. The accuracy is further improved by adding the third input information I3. The predetermined time interval may be changed for each piece of input information I. The input information I may further include a fourth input information or subsequent pieces of input information I.

[0071] The database 40 may be provided in the server 30. In one example, the database 40 is provided in the information storage unit 34. At least one of the learning models and the various pieces of information may be stored in a location other than the information storage unit 34 of the server 30. In one example, they are stored in a storage unit provided in the interface unit 20. In another example, they are stored in the database 40.

[0072] The first analysis result and the second analysis result may include estimated information that is information other than the first specific site included in the oral cavity image P. In one example, the first analysis result and the second analysis result include information on the second specific site. The second specific site includes at least one of premolars and molars in the oral cavity. The estimated information includes at least one of premolars and molars in the oral cavity. The condition of the first specific site in the oral cavity is correlated with the condition of the second specific site different from the first specific site in the oral cavity. In one example, in a test targeting 75 women in their 40s to 70s, the condition of the gums in the anterior teeth is highly correlated with the condition of the gums in the molars. That is, when gingival recession occurs in the first specific site, gingival recession also occurs in the second specific site. The same is true for the degree of interdental space and crowding.

[0073] The first analysis result and the second analysis result may include at least one of information on a prediction of the user's future oral condition, information on an oral care method for the user, and information on the user's health condition affected by the user's oral condition. The information on the prediction of the user's future oral condition includes an estimated image showing the user's oral condition after a predetermined period of time has passed. The information on the oral care method for the user includes information on oral care products suitable for the user's oral condition and how to use them. The information on the user's health condition affected by the user's oral condition includes, for example, information on periodontal disease or a non-oral health condition related to the oral condition.

[0074] When the learning of the analysis learning model MA and the classification learning model MC is completed, the processes of steps S13, S16, S18, and S19 executed by the information analysis unit 33 may be omitted. In this case, all the oral cavity images P are analyzed by the first analysis means. Therefore, the user can recognize the oral cavity state by referring to the first analysis result.

[0075] Instead of or in addition to the external terminal 50, another terminal locally connected to the server 30 may be provided. The other terminal is used to analyze the second intraoral image P2 by the second analysis means. The other terminal may be a smart device or a personal computer. Instead of or in addition to the external terminal 50, the interface unit 20 may analyze the second intraoral image P2 by the second analysis means. [Explanation of symbols]

[0076] 10: Oral condition evaluation system 20: Interface section 30: Server 31: Information acquisition department 32: Information output section 33: Information analysis department 34: Information storage section 40: Database 50: External terminal I: Input information O : Output information MA: Analytical Learning Model MC: Classification learning model

Claims

1. An oral cavity condition evaluation system including an information analysis unit that analyzes an oral cavity image included in an input image by a first analysis means, The information analysis unit classifies the intraoral images into first intraoral images that can be analyzed by the first analysis means and second intraoral images that cannot be analyzed by the first analysis means, The first intraoral image is analyzed by the first analysis means through the information analysis unit, When the intraoral image is the second intraoral image, the information analysis unit outputs the second intraoral image to an external terminal used for analysis of the second intraoral image by a second analysis unit different from the first analysis unit. Oral condition assessment system.

2. The first analysis means includes an analysis using an analysis learning model that has previously learned images related to the oral cavity, A first analysis result, which is the analysis result of the first intraoral image by the first analysis means, is output. The oral cavity condition evaluation system according to claim 1 .

3. the second analysis means includes at least one of analysis by an expert, analysis by a testing device, and analysis by a testing instrument; The oral cavity condition evaluation system further includes the external terminal, The external terminal is configured to output a second analysis result which is an analysis result of the second intraoral image by the second analysis means. The oral cavity condition evaluation system according to claim 2 .

4. The external terminal is configured to display the second intraoral image. The oral cavity condition evaluation system according to claim 3 .

5. At least one of the second intraoral image and the second analysis result is stored in a database. The oral cavity condition evaluation system according to claim 3 or 4.

6. The information analysis unit classifies the first intraoral image and the second intraoral image using a classification learning model that has learned images related to the intraoral cavity. The oral cavity condition evaluation system according to any one of claims 1 to 5.

7. The information analysis unit further classifies the input image into the oral cavity image and a non-oral cavity image that does not include an oral cavity, If the input image is the non-oral image, output a third analysis result. The oral cavity condition evaluation system according to any one of claims 1 to 6.

8. The input image is further provided with an interface unit for acquiring the input image. The oral cavity condition evaluation system according to any one of claims 1 to 7.

9. The interface unit includes a display unit. The oral cavity condition evaluation system according to claim 8.

10. The display unit displays the first analysis result. The oral cavity condition evaluation system according to claim 9, which indirectly relies on claim 2.

11. The display unit displays the second analysis result. The oral cavity condition evaluation system according to claim 9 or 10, which indirectly relies on claim 3.

12. The display unit displays the third analysis result. An oral cavity condition evaluation system according to any one of claims 9 to 11, which indirectly cites claim 7.

Images