Identification system

Abstract

To provide an identification system that can easily perform personal identification on the basis of a two-dimensional image of a tooth or a model, etc. of the tooth.SOLUTION: An identification system 100 comprises: a photographing unit 101 for acquiring image data of a tooth, an impression, a dental model, a dental product, or a derivative generated on the basis of the tooth; a feature extraction unit 102 for extracting a feature quantity of the image data; a feature-patient information storage unit 103 for associating information of a patient with the feature quantity related to the patient, and storing them; and a search unit 104 for searching for the information of the patient associated with the feature quantity extracted by the feature extraction unit, from the feature-patient information storage unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an identification system, and particularly to a technique for performing personal identification based on a two-dimensional image such as a tooth or a dental model.

Background Art

[0002] It is widely practiced to create dental prostheses (hereinafter simply referred to as prostheses) based on the tooth shape of a patient. Typically, in a dental clinic, the tooth shape of a patient is taken, and a dental plaster model is created based on the tooth shape. The dental plaster model is sent to a dental laboratory (hereinafter simply referred to as a laboratory) together with information that can identify the patient. The laboratory constructs a prosthesis on the dental plaster model with wax, takes a mold of this wax prosthesis, and creates a casting mold. By pouring a material such as metal into this casting mold, a prosthesis is obtained.

[0003] In this process, the dental plaster model received by the laboratory from the dental clinic is often damaged. Therefore, it may become unclear which patient the created prosthesis belongs to, especially when creating prostheses for multiple patients in parallel. In such cases, conventionally, the correspondence between the patient and the prosthesis has been specified based on intuition and experience. This is a very laborious task and there is also a risk of errors. If identification information for identifying the individual patient could be recorded on the prosthesis itself by some method, it would be fine, but since the prosthesis is to be worn inside the patient's body and has high requirements regarding safety and the like, this is not a practical method.

[0004] Similarly, in a dental clinic, a problem may occur where the correspondence between the completed prosthesis and the patient becomes unclear. This causes a loss of medical treatment time. Therefore, information on the prosthesis itself ​​​​​​​​​​​​​There is a long-awaited development of a method for associating dental prostheses with the patient themselves without recording them.

[0005] Also, the characteristics of dental prostheses are considered to be common to the tooth shape, plaster model, and the characteristics of the patient's teeth. Therefore, the above method is also useful for associating tooth shapes and plaster models with patients, and for identifying unknown persons using tooth characteristics.

[0006] As related technologies, there are Patent Document 1 and Patent Document 2. Patent Document 1 describes a system for identifying a person by comparing an image of teeth obtained by X-ray photographing an unknown person with an image of teeth obtained by X-ray photographing the unknown person during their lifetime. Patent Document 2 describes creating a feature amount database of tooth shape scan data (3D polygon data). An image of teeth obtained by X-ray photographing an unknown person and an image of teeth obtained by X-ray photographing the unknown person during their lifetime are compared to identify the person. Patent Document 2 describes creating a feature amount database of tooth shape scan data (3D polygon data).

Prior Art Documents

Patent Documents

[0007]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0008] However, X-ray images, tooth shape scan data, etc. disclosed in Patent Document 1 and Patent Document 2 are difficult to obtain without using dedicated equipment in a dental hospital. Also, it is a problem that it takes cost and time to acquire data, and there is a risk of radiation exposure due to X-ray photographing. It is difficult to obtain without using dedicated equipment in a dental hospital. Also, it takes cost and time to acquire data, and there is a risk of radiation exposure due to X-ray photographing. This is also a problem.

[0009] ​​​In addition, it is rare for X-ray images, dental scan data, etc. to be provided to the dental laboratory separately from the plaster model. Therefore, it is not appropriate to apply these conventional techniques to solve problems in the dental laboratory. Therefore, it is desired to provide a system that can easily associate with patient information using information that can be easily obtained by anyone in a dental clinic, dental laboratory, etc. The present invention has been made to solve such problems, and an object thereof is to provide an identification system that can easily perform personal identification based on a two-dimensional image of a tooth, a dental model, etc.

[0010]

Means for Solving the Problems

[0011] ​​​​​​​​​​​​​​

Advantages of the Invention

[0012] According to the present invention, an identification system that can easily perform personal identification based on a two-dimensional image of a tooth or a dental model or the like can be provided.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Embodiments for Carrying Out the Invention

[0014] Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. First, the configuration of the identification system 100 according to the embodiment of the present invention will be described using the block diagrams of FIGS. 1 and 2.

[0015] FIG. 1 is a diagram showing the functional configuration of the identification system 100. The identification system 100 includes a photographing unit 101, a feature extraction unit 102, a feature - patient information storage unit 103, a search unit 104, an output unit 105, and a registration unit 106.

[0016] FIG. 2 is a diagram showing an example of the hardware configuration of the identification system 100. The identification system 100 includes a CPU 11, a ROM 12, a RAM 13, a non - volatile memory 14, a bus 10, and an input / output device 60. ​​

[0017] The CPU 11 is a processor that controls the entire identification system 100. The CPU 11 reads out the system program stored in the ROM 12 via the bus 10, and controls the entire identification system 100 according to the system program.

[0018] The ROM 12 stores in advance a system program for executing various processes. The RAM 13 temporarily stores temporary calculation data, display data, data input by the user via the input / output device 60, programs, and the like.

[0019] The non-volatile memory 14 is backed up by, for example, a battery (not shown), and retains the storage state even when the power supply of the identification system 100 is cut off. The non-volatile memory 14 stores data, programs, and the like input from the input / output device 60. Programs and data stored in the non-volatile memory 14 may be expanded to the RAM 13 during execution and use.

[0020] The input / output device 60 is a data input / output device including a display, a key input interface, and the like. The input / output device 60 displays the information received from the CPU 11 via the interface 18 on the display. The input / output device 60 passes commands, data, and the like input from the key input interface and the like to the CPU 11 via the interface 18.

[0021] Each processing unit shown in FIG. 1 is logically realized by these hardware executing software. Note that the identification system 100 may be configured by a single information processing device, or may be configured by a plurality of information processing devices cooperating with each other. For example Then, the photographing unit 101 and the feature extraction unit 102 can be implemented in a mobile terminal device such as a smartphone equipped with a camera, and the feature-patient information storage unit 103, the search unit 104, and the output unit 105 can be separately implemented in a server computer accessible from the smartphone. The server computer can be provided by a known technology such as cloud computing, fog computing, edge computing, etc. The photographing unit 101 photographs a dental model of a patient to obtain image data. Alternatively, it may photograph a dental mold, dental prosthesis, or the patient's teeth themselves to obtain image data. The image data can be either a still image or a moving image. Also, the image data may include color information, depth information, etc. The feature extraction unit 102 extracts the feature amounts of the image data obtained by the photographing unit 101. Preferably, only the feature amounts related to the dental model, dental mold, dental prosthesis, or the patient's teeth included in the image are selectively extracted. In addition, feature amounts related to the dental root may be extracted. Feature amounts related to the shape and color of teeth and dental roots reflect information unique to each individual, such as the state of tooth wear and the condition of the gums (such as periodontal abscess), and thus can be used for highly accurate individual identification. In particular, the positional relationship of each groove in the fossa fissures of the molar teeth changes little even if the teeth are worn, making it suitable for individual identification. Since the extraction process of feature amounts from a two-dimensional image is well-known, detailed description is omitted in this paper. The feature-patient information storage unit 103 stores the feature amounts extracted by the feature extraction unit 102 and the patient information.

[0022]

[0023]

[0024] ​​​​​​​​​​​​​​It is a database that stores by association (see Fig. 3). Patient information includes at least identifying information that can uniquely identify a patient, the profile of the patient, treatment records, ordering information for dental prostheses (prescription forms), delivery information (delivery notes), etc. Alternatively, the identification system 100 may be communicably connected to external systems such as a medical record system and a prescription issuing system (not shown), and may be associated with information such as treatment records managed by the medical record system, prescriptions managed by the prescription issuing system, and delivery notes via the identification information.

[0025] The search unit 104 searches the feature-patient information storage unit 103 using a given search condition. For example, the search unit 104 searches the feature-patient information storage unit 103 using the feature quantity extracted by the feature extraction unit 102 from the image data of a certain dental prosthesis as a search key, and extracts patients associated with the feature quantity whose similarity exceeds a predetermined similarity. That is, the similarity between the feature quantity input as the search key and the feature quantity registered in the feature-patient information storage unit 103 is calculated, and when the similarity between the two exceeds a predetermined threshold value, the identification information of the patient associated with the registered feature quantity is output, etc. Since the calculation process of the similarity of the feature quantity is well-known, detailed description thereof is omitted in this article. Thereby, the identification information, profile, etc. of the patient corresponding to the dental prosthesis can be obtained. When the identification system 100 is in cooperation with an external system, it may search and obtain the information managed by the external system using the obtained identification information of the patient, etc. For example, using the identification information as a search key, treatment records managed by the medical record system, prescriptions managed by the prescription issuing system, and delivery notes can be obtained.

[0026] The output unit 105 outputs the information acquired by the search unit 104. For example, the identification information, profile, treatment record, instructions, delivery note, etc. of the patient acquired from the feature-patient information storage unit 103 or an external system are displayed on a display of a mobile terminal device or the like. Alternatively, the result may be output by printing, voice, or the like.

[0027] The registration unit 106 performs a process of associating the feature amount extracted by the feature extraction unit 102 with patient information and storing it in the feature-patient information storage unit 103. The patient information is provided to the registration unit 106 by means not shown. Typically, the patient information is input by input means such as a keyboard. Also, for example, when an instruction (printed matter or display screen) with the patient's identification information is simultaneously copied into image data, the feature extraction unit 102 can recognize the identification information and provide it to the registration unit 106. The identification information may be a character or information encoded therefrom (such as a barcode or a two-dimensional code). Since the technology for recognizing the identification information is well known, detailed description thereof is omitted in this article. Further, the registration unit 106 may search for and acquire information managed by an external system using the provided identification information or the like, and store it in the feature-patient information storage unit 1003. For example, using the identification information as a search key, treatment records managed by an EMR system, instructions and delivery notes managed by an instruction issuance system, etc. can be acquired.

[0028] <Example 1> As Example 1, an example of applying the identification system 100 to the business of a dental laboratory creating dental prostheses in response to a request from a dental hospital will be described. In this example, the photographing unit 101, the feature extraction unit 102, and the output unit 105 are included in applications for mobile terminal devices for both the dental hospital and the dental laboratory. ​​​​​​​​​​​​​​It is assumed that they are each implemented. Also, a feature - patient information storage unit 103, a search unit 104, and a registration unit 106 are implemented in the server computer.

[0029] (1) The dental clinic creates a dental model of the patient. Also, using an instruction - issuing system (not shown), it creates an instruction for the dental laboratory. The instruction contains the identification information of the patient. The dental clinic photographs the model and the image data of the printed instruction written into the photographing unit 101 of the mobile - terminal device application.

[0030] (2) The feature extraction unit 102 extracts the feature amount of the dental model from the image data obtained in (1). Also, it recognizes the identification information of the patient described in the instruction. The feature extraction unit 102 transmits the feature amount and the identification information as a set to the registration unit 106 of the server computer.

[0031] (3) The registration unit 106 associates the received feature amount and identification information and registers them in the feature - patient information storage unit 103.

[0032] (4) The dental clinic sends the dental model and the printed instruction to the dental laboratory. The dental laboratory photographs the received dental model by the photographing unit 101 of the mobile - terminal application.

[0033] (5) The feature extraction unit 102 extracts the feature amount of the dental model from the image data obtained in (4) and transmits it to the search unit 104 of the server computer.

[0034] (6) The search unit 104 searches the feature - patient information storage unit 103 and acquires the identification information corresponding to the received feature amount (see FIG. 4). Also, the search unit 104 searches an instruction - issuing system (not shown) and acquires the instruction corresponding to the identification information. ​​

[0035] (7) The output unit 105 displays the obtained instruction sheet on the mobile terminal application. The dental laboratory compares the content described in the printed instruction sheet received in (4) with the content described in the instruction sheet displayed on the mobile terminal application and confirms that the two match. In addition, the output unit 105 can display the image captured by the imaging unit 101 on the same screen as the instruction sheet or save it in association with the instruction sheet. This can leave evidence of receiving the model and the instruction sheet.

[0036] (8) The dental laboratory creates a dental prosthesis. During the creation process, for example, if the correspondence between the tooth model and the printed instruction sheet becomes unclear, or the tooth model is lost due to damage, etc., it may become unclear which patient's work in progress dental prosthesis or the final dental prosthesis is. In this case, the dental laboratory photographs the dental prosthesis with the imaging unit 101 of the mobile terminal application.

[0037] (9) The feature extraction unit 102 extracts the feature amount of the dental prosthesis from the image data obtained in (8) and transmits it to the search unit 104 of the server computer.

[0038] (10) The search unit 104 searches the feature - patient information storage unit 103 and obtains the identification information corresponding to the received feature amount. In addition, the search unit 104 searches an instruction sheet issuance system (not shown) and obtains the instruction sheet corresponding to the identification information.

[0039] (11) The output unit 105 displays the obtained instruction sheet on the mobile terminal application. . By checking this instruction sheet, the dental technician can identify the patient corresponding to the dental work. This is possible.

[0040] <Example 2> As Example 2, an example of applying the identification system 100 to the identification work of an unknown person will be described. In this example, it is assumed that the photographing unit 101, the feature extraction unit 102, and the output unit 105 are respectively implemented in an application for a user's mobile terminal such as a judicial officer. Also, it is assumed that the feature-patient information storage unit 103, the search unit 104, and the registration unit 106 are implemented in the server computer. Also, by the operations as shown in Example 1, it is assumed that a correspondence database between the identification information and the feature amounts of a large number of patients has already been constructed in the feature-patient information storage unit 103.

[0041] (1) The user photographs the teeth of the unknown person with the photographing unit 101 of the application for the mobile terminal.

[0042] (2) The feature extraction unit 102 extracts the feature amounts of the teeth from the image data obtained in (1) and transmits them to the search unit 104 of the server computer.

[0043] (3) The search unit 104 searches the feature-patient information storage unit 103 and acquires the identification information corresponding to the received feature amounts. Also, the search unit 104 searches an instruction sheet issuing system or a medical record system (not shown) etc. and acquires the instruction sheet or medical record etc. corresponding to the identification information.

[0044] (4) The output unit 105 displays the acquired instruction sheet or medical record etc. on the application for the mobile terminal. By checking this instruction sheet or medical record etc., the user can identify the patient corresponding to the dental work, that is, the unknown person. ​​​​​​​​​​​

[0045] <Example 3> As Example 3, an example of applying the identification system 100 for improving the quality of medical services in a dental clinic will be described. In this example, it is assumed that a photographing unit 101, a feature extraction unit 102, and an output unit 105 are respectively implemented in an application for a user's mobile terminal such as a dentist. Also, it is assumed that a feature-patient information storage unit 103, a search unit 104, and a registration unit 106 are implemented in a server computer. Further, it is assumed that the identification system 100 is linked via a medical record system (not shown) and the identification information of the patient. The medical record system can manage the medical records of a plurality of dental clinics, and it is assumed that the medical records created at each dental clinic are stored when the patient has visited a plurality of dental clinics in the past. For example, a dentist photographs the patient's teeth, dental models, or dental casts, etc. with the photographing unit 101 of the application for the mobile terminal.

[0046] (1) The dentist photographs the patient's teeth, dental models, or dental casts, etc. with the photographing unit 101 of the application for the mobile terminal.

[0047] (2) The feature extraction unit 102 extracts the feature amounts of the teeth, dental models, or dental casts, etc. from the image data obtained in (1), and transmits them to the search unit 104 of the server computer.

[0048] (3) The search unit 104 searches the feature-patient information storage unit 103 and acquires the identification information corresponding to the received feature amounts. Also, the search unit 104 searches the medical record system and acquires the medical record corresponding to the identification information. When the patient has visited a plurality of dental clinics in the past, the medical records created at each dental clinic are acquired.

[0049] (4) The output unit 105 displays the acquired medical record on the application for the mobile terminal. ​​​​​By referring to the past treatment records of the patient described in these medical records, a dentist can formulate an optimal treatment plan based on the treatment process. In particular, in this embodiment, since the dentist can also refer to the medical record information created at dental clinics other than the dental hospital, the dental hospital can provide high-quality treatment considering the long-term treatment process.

[0050] <Example 4> As Example 4, a method for improving the accuracy of the process in which the search unit 104 searches the feature-patient information storage unit 103 using a feature amount as a search key will be described. In this search process, the search unit 104 needs to determine whether the feature amount given as the search key matches the feature amount stored in the feature-patient information storage unit 103 (that is, the similarity exceeds a predetermined threshold). However, since the state of a person's teeth and gums changes over time and depending on the condition, the feature amount can also change accordingly. In this embodiment, by using a learned model obtained by machine learning the tendency of this change, more accurate search processing becomes possible. To perform this machine learning process, the identification system 100 has a machine learning unit 107.

[0051] (1) Learning stage The machine learning unit 107 uses, as learning data, feature amounts extracted from images of the teeth, dental models, dental molds, or dental artifacts of the same patient taken at multiple times, and constructs a learning model for estimating the same-person property based on the feature amounts. For learning, for example, a method as disclosed in Patent Document 3, which combines differential detection method and machine learning, can be adopted.

[0052] For example, for the feature amounts obtained from the same patient at various times such as in their teens, thirties, and fifties, is given a "normal" teacher signal, and the feature amounts obtained from other randomly selected patients are given an "abnormal" teacher signal, and then the distance map is corrected so that the distance values between the "normal" feature amounts are equal to or less than a predetermined threshold value. As a result, a learning model that can determine whether the input feature amount is from the same patient without being affected by aging or the like can be generated. That is, features that do not change over time can be extracted from the image data, and a learning model for determining the identity based on the features can be generated.

[0053] The machine learning unit 107 can generate such a learning model for each patient. Here as the learning data, feature amounts extracted from images of a patient's teeth, dental models, tooth forms, or prosthetic appliances stored in an electronic medical record system or an instruction issuance system in the past may be used and so on.

[0054] (2) Determination stage When the search unit 104 searches the feature-patient information storage unit 103, instead of the conventional known similarity determination processing, the feature amounts as search keys are sequentially input to the learning models generated by the machine learning unit 107 for each patient (see FIG. 5). Here, if there is a learning model that outputs "normal" as the determination result the search unit 104 outputs the patient associated with the learning model as the search result In this case, the feature-patient information storage unit 103 can hold the learning models related to patients and the patient information in association with each other, instead of the correspondence between the feature amounts and the patient information

[0055] According to the present embodiment, images such as teeth, tooth forms, models, and prosthetic appliances are relatively easy to obtain ​​​​The characteristic amount of data can be used as personal identification data. As a result, it becomes possible to identify a patient corresponding to teeth, tooth shapes, models , dental prostheses, etc. by a simple operation. In particular, since the model circulates between the dental clinic and the dental laboratory and serves as the basis for fabricating dental prostheses, it is convenient that the appearance of the model itself can be used as personal identification data.

[0056] Further, according to the present embodiment, it is not information that is generally difficult to obtain like a dental X-ray image that has been conventionally used for personal identification, but two-dimensional images of teeth, tooth shapes, models, dental prostheses, etc. It is possible to identify a patient individual from easily obtainable data. As a result, it becomes possible to easily access patient information in a much wider range of scenarios than before.

[0057] Note that the present invention is not limited to the above-described embodiment, and may be arbitrarily changed as long as the gist of the present invention is not impaired. For example, the characteristic amount is not limited to those obtained from teeth, tooth shapes, models, dental prostheses, etc., and may be those obtained from derivatives of teeth, including replicas or images of these.

[0058] Further, in the above-described embodiment, an example of using a two-dimensional image as image data is mainly shown However, the present invention is not limited to this, and for example, a three-dimensional image may be used.

[0059] Further, in the above-described embodiment, the machine learning unit 107 extracts features that do not change over time from the image data and generates a learning model for determining authenticity based on the features. However the present invention is not limited to this. For example, the machine learning unit 107 uses image data of various ages of a large number of patients as learning data, and the features of a certain patient after aging A learning model for estimation may be generated. In this case, the search unit 104 inputs, as a search key, the current tooth feature amount of the patient to be input, and the feature amount after aging estimated by the learning model based on the patient's past teeth, and can determine the individuality by comparing them. Alternatively, the machine learning unit 107 may use image data of various ages of a large number of patients as learning data, and generate a learning model for estimating the features of a certain patient before aging. In this case, the search unit 104 estimates, based on the current tooth feature amount of the patient input as a search key, the feature amount before aging by the learning model, and the feature amount of the patient's past teeth stored in the database, and can determine the individuality by comparing them.

Explanation of Signs

[0060] 100 Identification system 101 Photographing unit 102 Feature extraction unit 103 Feature - Patient information storage unit 104 Search unit 105 Output unit 106 Registration unit 107 Machine learning unit

Claims

1. An imaging unit that acquires image data, A feature extraction unit that extracts feature amounts of the image data, A feature-patient information storage unit that stores the patient information and the feature amounts in association with each other, A search unit that searches the feature-patient information storage unit for the patient information corresponding to the feature amounts, and has: In a first step before mixing prostheses of a plurality of patients, the imaging unit acquires first image data of the teeth of the patient, the feature extraction unit extracts the feature amounts of the first image data, and the feature-patient information storage unit stores the patient information and the feature amounts of the first image data in association with each other; In a second step after mixing the prostheses of the plurality of patients, the imaging unit acquires second image data of the dental prosthesis, the feature extraction unit extracts the feature amounts of the second image data, and the search unit searches the feature-patient information storage unit for the patient information associated with the feature amounts of the first image data corresponding to the feature amounts of the second image data. Identification system.

2. The imaging unit is provided in a mobile terminal device equipped with a camera, and the image data is acquired by the camera. The identification system according to Claim 1.

Images