JP7692582B2 - Identification System - Google Patents

Description

The present invention relates to an identification system, and more particularly to a technique for performing personal identification based on two-dimensional images of teeth or tooth models, etc.

It is common to create dental prostheses (hereinafter, simply referred to as prostheses) based on a patient's dental impressions. Typically, a dental clinic takes an impression of the patient's teeth, and a plaster model of the teeth is created based on the impression. The plaster model is then sent to the dental laboratory (hereinafter, simply referred to as the "dental prostheses") along with information that can identify the patient.
The plaster model is then sent to a dental laboratory, where the dental technician builds the dental prosthesis out of wax on top of the plaster model, then takes an impression of the wax model to create a mold. The dental prosthesis is then obtained by pouring metal or other materials into the mold.

During this process, the plaster models that the laboratory receives from the dental clinic are often damaged. As a result, it can become difficult to know which patient the dental prosthesis was made for, especially when dental prostheses for multiple patients are being made simultaneously. In such cases, the correspondence between the patient and the dental prosthesis was traditionally determined by intuition and experience. This was a very time-consuming task, and there was a risk of errors. It would be ideal if there was some way to record identification information that identifies the individual patient on the dental prosthesis itself, but since dental prostheses are worn inside the patient's body and there are high demands for safety, this is not a realistic method.

Similarly, in dental clinics, there may be a problem where the relationship between the completed dental prosthesis and the patient is not clear. This causes a loss of treatment time. Therefore, there is a need to develop a method to link the dental prosthesis and the patient without recording information on the dental prosthesis itself.

In addition, the characteristics of the dental prosthesis are considered to be common to the characteristics of the dental mold, plaster model, and the patient's teeth. Therefore, the above-mentioned method is also useful for matching dental molds and plaster models with patients, and for identifying unidentified people using dental characteristics.

Related techniques include Patent Document 1 and Patent Document 2. Patent Document 1 describes a method for detecting a tooth of an unidentified person by X-ray photography, a method for detecting a tooth of the unidentified person by X-ray photography, and a method for detecting a tooth of the unidentified person by X-ray photography.
Patent Document 2 describes a system for identifying an individual by comparing the data. Patent Document 2 describes the creation of a feature amount database of dental impression scan data (three-dimensional polygon data).

Patent No. 5125324 International Publication No. 2016/143022 Patent No. 6216024

However, the X-ray images and dental impression scan data disclosed in Patent Documents 1 and 2 are difficult to obtain without using dedicated equipment at a dental clinic. In addition, there are problems with the cost and time required to obtain the data, and the risk of exposure to radiation from X-ray photography.

In addition, X-ray images, dental scan data, and the like are rarely provided to dental laboratories separately from plaster models. Therefore, it is not appropriate to apply these conventional techniques to solving problems in dental laboratories.

Therefore, it is desirable to provide a system that can easily associate patient information using information that is easily obtained by anyone at a dental clinic, dental laboratory, etc. The present invention has been made to solve such problems, and has an object to provide an identification system that can easily identify individuals based on two-dimensional images of teeth or tooth models, etc.

An identification system according to one embodiment of the present invention comprises an imaging unit that acquires image data of teeth, dental impressions, dental models, dental prostheses, or derivatives generated based on teeth, a feature extraction unit that extracts features of the image data, a feature-patient information storage unit that stores patient information and the features related to the patient in association with each other, and a search unit that searches the feature-patient information storage unit for patient information corresponding to the features extracted by the feature extraction unit.
In an identification system according to one embodiment of the present invention, the feature-patient information storage unit stores the patient information in association with a learning model that has been trained for each patient to determine which of the features do not change over time, and the search unit searches for the patient information from the feature-patient information storage unit by inputting the features extracted by the feature extraction unit into the learning model.
In an identification system according to one embodiment of the present invention, the photographing unit is provided in a mobile terminal device equipped with a camera, and the image data is acquired by the camera.

According to the present invention, it is possible to provide an identification system that can easily perform personal identification based on two-dimensional images of teeth or tooth models, etc.

FIG. 2 is a block diagram showing a functional configuration of the identification system 100. FIG. 2 is a block diagram showing a hardware configuration of the identification system 100. FIG. 10 is a diagram showing an example of a feature-patient information storage unit 103. FIG. 2 is a diagram illustrating an example of the operation of the identification system 100. FIG. 2 is a diagram illustrating an example of the operation of the identification system 100.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A specific embodiment to which the present invention is applied will be described in detail below with reference to the drawings. First, the configuration of an identification system 100 according to an embodiment of the present invention will be described with reference to the block diagrams of FIG. 1 and FIG.

1 is a diagram showing the functional configuration of an identification system 100. The identification system 100 includes an imaging unit 101, a feature extraction unit 102, a feature-patient information storage unit 103, a search unit 104, and an output unit 105.
5. A registration unit 106 is provided.

2 is a diagram showing an example of a 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.

The CPU 11 is a processor that controls the entire identification system 100.
reads a system program stored in a ROM 12 via the bus 10, and controls the entire identification system 100 in accordance with the system program.

The ROM 12 prestores system programs 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.

The non-volatile memory 14 is backed up by, for example, a battery (not shown), and retains its stored state even if the power to the identification system 100 is cut off. The non-volatile memory 14 stores data, programs, etc. input from the input/output device 60. The programs and data stored in the non-volatile memory 14 may be expanded in the RAM 13 when executed and used.

The input/output device 60 is a data input/output device equipped with a display, a key input interface, etc. The input/output device 60 displays information received from the CPU 11 via the interface 18 on the display. The input/output device 60 passes commands, data, etc. input from the key input interface, etc., to the CPU 11 via the interface 18.

Each processing unit shown in FIG. 1 is logically realized by executing software on these hardware devices. The identification system 100 may be configured by a single information processing device, or may be configured by linking multiple information processing devices. For example, the imaging unit 101 and the feature extraction unit 102 may 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 may be separately implemented in a server computer accessible from the smartphone. The server computer may be provided by a known technology such as cloud computing, fog computing, edge computing, etc.

The photographing unit 101 photographs a model of the patient's teeth to obtain image data. Alternatively, the image data may be obtained by photographing a dental mold, a dental prosthesis, or the patient's teeth themselves. The image data may be either a still image or a video. The image data may also include color information, depth information, and the like.

The feature extraction unit 102 extracts features from the image data obtained by the imaging unit 101. Preferably, only features related to the tooth model, dental mold, dental prosthesis, or the patient's teeth included in the image are selectively extracted. In addition, features related to the gums may be extracted. Features related to the shape and color of the teeth and gums reflect information that differs from person to person, such as the wear state of the teeth and the condition of the gums (pyorrhea, etc.), like fingerprints, and can be used for highly accurate personal identification. In particular, the positional relationship of each groove in the pits and fissures of molars is suitable for personal identification because it does not change much even if the teeth are worn down. Note that the process of extracting features from two-dimensional images is publicly known, so a detailed description will be omitted in this paper.

The feature-patient information storage unit 103 is a database that stores the features extracted by the feature extraction unit 102 in association with patient information (see FIG. 3). The patient information may include at least identification information that can uniquely identify a patient, a profile of the patient, treatment records, ordering information (instructions) for technical products, and delivery information (delivery notes). Alternatively, the identification system 100 may be communicably connected to external systems such as a medical record system and an instruction issuing system (not shown), and may be associated with information such as treatment records managed by the medical record system and instructions and delivery notes managed by the instruction issuing system via the identification information.

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 a feature extracted by the feature extraction unit 102 from image data of a certain dental prosthesis as a search key, and extracts patients associated with the feature whose similarity exceeds a predetermined similarity. That is, the search unit 104 calculates the similarity between the feature input as the search key and the feature registered in the feature-patient information storage unit 103, and outputs the identification information, etc. of the patient associated with the registered feature when the similarity between the two exceeds a predetermined threshold value. Note that the calculation process of the similarity of the feature is publicly known, so a detailed description will be omitted in this paper. This makes it possible to obtain the identification information, profile, etc. of the patient corresponding to the dental prosthesis. When the identification system 100 is linked to an external system, the obtained identification information, etc. of the patient may be used to search and obtain information managed by the external system. For example, the identification information can be used as a search key to obtain treatment records managed by a medical record system, instructions and delivery notes managed by an instruction issuing system, etc.

The output unit 105 outputs the information acquired by the search unit 104. For example, the information includes patient identification information, profile, and treatment records acquired from the feature-patient information storage unit 103 or an external system.
The instruction sheet, delivery note, etc. are displayed on the display of a mobile terminal device, etc. Alternatively, the results may be output as printouts or audio.

The registration unit 106 performs a process of associating the features extracted by the feature extraction unit 102 with patient information and storing them 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 an input means such as a keyboard. In addition, for example, when an instruction sheet (printed matter or display screen) or the like containing the patient's identification information is simultaneously imprinted on the 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 characters, or may be information obtained by encoding the identification information (such as a barcode or two-dimensional code). Since the technology for recognizing identification information is well known, a detailed description will be omitted in this paper. In addition, the registration unit 106 uses the provided identification information, etc. to search for and acquire information managed by an external system, and registers the information in the feature-patient information storage unit 103.
For example, the identification information may be used as a search key to retrieve medical records managed by the medical record system, instructions and delivery notes managed by the instruction issuing system, and the like.

Example 1
As a first embodiment, an example will be described in which the identification system 100 is applied to a task in which a dental laboratory creates a dental prosthesis at the request of a dental clinic. In this example, the imaging unit 101, the feature extraction unit 102, and the output unit 105 are installed in an application for a mobile terminal device for a dental clinic and a dental laboratory.
It is also assumed that the server computer is equipped with a feature-patient information storage unit 103, a search unit 104, and a registration unit 106.

(1) The dental clinic creates a model of the patient's teeth. In addition, the dental clinic creates an instruction sheet for the dental laboratory using an instruction sheet issuing system (not shown). The instruction sheet contains identification information of the patient. The dental clinic photographs image data including the model and the printed instruction sheet using the photographing unit 101 of the mobile terminal device application.

(2) The feature extraction unit 102 extracts features of the tooth model from the image data acquired in (1). It also recognizes the patient's identification information written on the prescription. The feature extraction unit 102 transmits the features and the identification information as a set to the registration unit 106 of the server computer.

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

(4) The dental clinic sends the tooth model and the printed instruction sheet to the dental laboratory. The dental laboratory photographs the received tooth model using the photographing unit 101 of the mobile terminal application.

(5) The feature extraction unit 102 extracts features of the tooth model from the image data acquired in (4) and transmits them to the search unit 104 of the server computer.

(6) The search unit 104 searches the feature-patient information storage unit 103 to obtain identification information corresponding to the received feature amount (see FIG. 4). The search unit 104 also searches an instruction issuing system (not shown) to obtain an instruction corresponding to the identification information.

(7) The output unit 105 displays the acquired instruction sheet on the mobile terminal application.
The laboratory compares the contents of the printed instructions received in (4) with the contents of the instructions displayed on the mobile device application and confirms that the two match.
Furthermore, the output unit 105 can display the image captured by the image capturing unit 101 on the same screen as the instruction sheet, or store the image in association with the instruction sheet. This makes it possible to leave evidence that the model and the instruction sheet have been received.

(8) The dental laboratory creates a dental prosthesis. During the creation process, for example, if the correspondence between the tooth model and the printed instructions becomes unclear, or if the tooth model is lost due to damage, it may become impossible to identify which patient the wax dental prosthesis or the final dental prosthesis belongs to. In this case, the dental laboratory photographs the dental prosthesis using the photographing unit 101 of the mobile terminal application.

(9) The feature extraction unit 102 extracts features of the technical work from the image data acquired in (8) and transmits them to the search unit 104 of the server computer.

(10) The search unit 104 searches the feature-patient information storage unit 103 to acquire identification information corresponding to the received feature amount. The search unit 104 also searches an instruction book issuing system (not shown) to acquire an instruction book corresponding to the identification information.

(11) The output unit 105 displays the acquired instruction sheet on the mobile terminal application.
By checking this instruction sheet, the laboratory can identify the patient for whom the dental prosthesis is to be produced.

Example 2
As a second embodiment, an example in which the identification system 100 is applied to the task of identifying an unidentified person will be described. In this example, it is assumed that the imaging unit 101, the feature extraction unit 102, and the output unit 105 are implemented in an application for a mobile terminal of a user such as a judicial official. It is also assumed that the feature-patient information storage unit 103, the search unit 104, and the registration unit 106 are implemented in a server computer. It is also assumed that a database of correspondence between the identification information and feature amounts of a large number of patients has already been built in the feature-patient information storage unit 103 through the tasks as shown in the first embodiment.

(1) A user photographs the teeth of an unidentified person using the photographing unit 101 of a mobile terminal application.

(2) The feature extraction unit 102 extracts tooth features from the image data acquired in (1) and transmits them to the search unit 104 of the server computer.

(3) The search unit 104 searches the feature-patient information storage unit 103 to acquire identification information corresponding to the received feature amount. The search unit 104 also searches an instruction issuing system, a medical record system, etc. (not shown) to acquire an instruction, a medical record, etc. corresponding to the identification information.

(4) The output unit 105 displays the acquired instructions, medical records, etc. on a mobile terminal application. By checking the instructions, medical records, etc., the user can identify the patient corresponding to the dental prosthesis, i.e., the unidentified person.

Example 3
As a third embodiment, an example in which the identification system 100 is applied to improve the quality of medical care in a dental clinic will be described. In this example, the imaging unit 101, the feature extraction unit 102, and the output unit 105 are implemented in an application for a mobile terminal of a user such as a dentist. Also, the feature-patient information storage unit 103, the search unit 104, and the like are implemented in a server computer.
4 and a registration unit 106 are implemented. The identification system 100 is also assumed to be linked to a medical record system (not shown) via the patient's identification information. The medical record system is capable of managing medical records from multiple dental clinics, and in the case where a patient has visited multiple dental clinics in the past, the medical records created at each dental clinic are assumed to be stored.

(1) A dentist photographs a patient's teeth, a dental model, or a dental impression, etc., using the photographing unit 101 of a mobile terminal application.

(2) The feature extraction unit 102 extracts features of the teeth, tooth models, tooth impressions, etc. from the image data acquired in (1) and transmits them to the search unit 104 of the server computer.

(3) The search unit 104 searches the feature-patient information storage unit 103 to obtain identification information corresponding to the received feature amount. The search unit 104 also searches the medical record system to obtain a medical record corresponding to the identification information. If the patient has visited multiple dental clinics in the past, the medical records created at each dental clinic are obtained.

(4) The output unit 105 displays the acquired medical record on a mobile terminal application.
Dentists can refer to the patient's past treatment records in these charts to
In particular, in this embodiment, the dental clinic can refer to chart information created at dental clinics other than the dental clinic in question, which enables the dental clinic to provide high-quality treatment that takes into account the long-term treatment history.

Example 4
As a fourth embodiment, the search unit 104 searches the feature-patient information storage unit 103 using the feature amount as a search key.
In this search process, the search unit 104 searches for a feature amount given as a search key and the feature-patient information storage unit 10
3 (i.e., the similarity exceeds a predetermined threshold).
It is necessary to determine whether or not the feature amount is correct. However, since the condition of a person's teeth and gums changes with age and condition, the feature amount may change accordingly. In this embodiment, a trained model that has been trained on the tendency of this change through machine learning is used to enable more accurate search processing. To perform this machine learning processing, the identification system 100 has a machine learning unit 107.

(1) Learning stage The machine learning unit 107 uses feature amounts extracted from images of the teeth, dental models, dental impressions, or dental prostheses of the same patient taken at multiple times as learning data, and constructs a learning model that estimates the identity of the patient based on the feature amounts. For example, a method such as that disclosed in Patent Document 3, which combines a difference detection method and machine learning, can be used for learning.

For example, a teacher signal of "normal" is assigned to features acquired from the same patient at various times, such as when the patient was in their teens, thirties, fifties, etc., and a teacher signal of "abnormal" is assigned to features acquired from other randomly selected patients, and the distance map is then corrected so that the distance between "normal" features is equal to or less than a predetermined threshold value. This makes it possible to generate a learning model that can determine whether input features are from the same patient, without being affected by aging or other factors. In other words, features that do not change over time are extracted from image data,
A learning model can be generated to determine identity based on the features.

The machine learning unit 107 can generate such a learning model for each patient. Here, as the learning data, features extracted from images of the patient's teeth, dental models, dental impressions, dental prostheses, etc., previously stored in an electronic medical record system, an instruction issuing system, etc., may be used.

(2) Judgment stage When searching the feature-patient information storage unit 103, the search unit 104 sequentially inputs features as search keys to a learning model generated for each patient by the machine learning unit 107, instead of a conventional known similarity judgment process (see FIG. 5). If there is a learning model that outputs "normal" as a judgment result, the search unit 104 outputs the patient linked to the learning model as a search result.
In this case, the feature-patient information storage unit 103 stores the following information instead of the correspondence between the feature amount and the patient information:
A learning model relating to a patient can be stored in association with patient information.

According to this embodiment, the feature quantities of data that are relatively easy to obtain, such as images of teeth, dental impressions, models, dental prostheses, etc., can be used as personal identification data. This makes it possible to identify patients corresponding to teeth, dental impressions, models, dental prostheses, etc., through simple operations. In particular, since models are circulated between dental clinics and dental laboratories and serve as the basis for creating dental prostheses, it is convenient to be able to use the appearance of the model itself as personal identification data.

Furthermore, according to this embodiment, it is possible to identify individual patients not from information that is generally difficult to obtain, such as dental X-ray images that have been used for personal identification in the past, but from easily obtainable data such as two-dimensional images of teeth, dental impressions, models, dental prostheses, etc. This makes it possible to easily access patient information in a much wider range of situations than before.

The present invention is not limited to the above-described embodiment, and may be modified as desired without departing from the spirit of the present invention. For example, the feature amount is not limited to those obtained from teeth, dental impressions, models, dental prostheses, etc., and may be those obtained from derivatives of teeth, including copies or images of these.

Furthermore, in the above-described embodiment, examples have been mainly shown in which two-dimensional images are used as image data, but the present invention is not limited to this, and for example, three-dimensional images may also be used.

In the above embodiment, the machine learning unit 107 extracts features that do not change over time from the image data, and generates a learning model that determines the identity based on the features. However, the present invention is not limited to this, and for example, the machine learning unit 107 may use image data of many patients of various ages as learning data to generate a learning model that estimates the features of a certain patient after aging. In this case, the search unit 104 can determine the identity by comparing the current dental feature amount of the patient input as a search key with the feature amount after aging estimated by the above learning model based on the patient's past teeth. Alternatively, the machine learning unit 107 uses image data of many patients of various ages as learning data,
A learning model for estimating the characteristics of a certain patient before aging may be generated. In this case, the search unit 104 can determine the identity of the patient by comparing the characteristics before aging estimated by the learning model based on the patient's current tooth characteristics input as a search key with the past tooth characteristics of the patient stored in the database.

100 Identification system 101 Imaging 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 (2)

An imaging unit that acquires image data;
A feature extraction unit that extracts a feature amount of the image data;
a feature-patient information storage unit that stores patient information and the feature amount in association with each other;
a search unit that searches the patient information corresponding to the feature amount from the feature-patient information storage unit,
In a first step before mixing dental prostheses of a plurality of patients, the photographing unit acquires first image data of the teeth of the patients, the feature extracting unit extracts feature amounts of the first image data, and the feature-patient information storing unit stores the patient information and the feature amounts of the first image data in association with each other;
an identification system, characterized in that in a second step after the dental prostheses of the plurality of patients are mixed, the photographing unit acquires second image data relating to the dental prostheses, the feature extraction unit extracts features of the second image data, and the search unit searches the feature-patient information storage unit for the patient information associated with features of the first image data that correspond to the features of the second image data . The identification system according to claim 1 , wherein the photographing unit is provided in a mobile terminal device equipped with a camera, and the image data is acquired by the camera.

Images