Artificial tooth dimension evaluation system and program thereof

Abstract

To provide an artificial tooth dimension evaluation system, an artificial tooth dimension evaluation method, and an artificial tooth dimension evaluation program that enable the conversion of qualitative and ambiguous instructions contained in dental technician instruction books created by a dentist into objective and quantitative manufacturing dimensions for artificial teeth, thereby making the production of artificial teeth possible.SOLUTION: An artificial tooth dimension evaluation system 1 comprises artificial tooth dimension evaluation models 25a, 25b trained using teacher data sets 8a to 8c to convert the artificial tooth production level indicated in the dental technician instruction book created by dentists into an artificial tooth production dimension, and has an evaluation unit 5 that inputs dental arch data 15a to 15c, contact data 16a to 16c, bite data 17a to 17c, and fit data 18a to 18c extracted by a feature extraction unit 4a into the evaluation model, and outputs the evaluated artificial tooth dimensions as output data sets 20a to 20c.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a denture dimension evaluation system, a method thereof, and a program thereof, which enable the production of dentures by converting the instruction content described in a dental laboratory instruction created by a dentist into the production dimensions of the dentures.

Background Art

[0002] Conventionally, in dental treatment, for the production of dental laboratory work such as prostheses required for treatment, a dental clinic first takes an impression of a patient's dental arch and sends a written document called a dental laboratory instruction together with the impression to a dental laboratory to request the production of dentures. The dental laboratory instruction contains instructions by a dentist necessary for the production of the patient's prosthesis, and the dental laboratory produces a dental model based on the impression and the instructions described in the dental laboratory instruction. Then, the dental laboratory constructs a laboratory work with wax on the dental model, takes a mold of the wax laboratory work to produce a casting mold, and then pours a material such as metal into the casting mold to obtain the laboratory work. However, dental laboratories often have multiple dental clinics as customers, and they have to manage the dental laboratory instructions sent from dental clinics for each dentist and each patient, which is complicated. In addition, the completed laboratory work also needs to be managed for each dental clinic and each patient, which is also a factor that complicates the management. Therefore, for example, Patent Document 1 discloses an invention called "Dental Laboratory Work Order Receiving and Ordering System, Dental Laboratory Work Order Receiving and Ordering Program, and Dental Laboratory Work Order Receiving and Ordering Method". In this invention, the creation and reception of instructions are performed via the respective terminals of a dental clinic and a dental laboratory. The instruction contains, as instruction information, the type information, treatment position information, and material information of the dental laboratory work. The storage unit of the system stores these instruction information in a storage unit DB, and also stores master data regarding the laboratory fees corresponding to these information. Then, the calculation unit of the system calculates the laboratory fees while referring to the instruction information and the master data, creates a dental laboratory instruction using a terminal, and performs the order receiving and ordering of the laboratory work using the data, thereby reducing the complexity of management. In addition, Patent Document 2 discloses an instruction management system named "Instruction Management System, Instruction Management Program, and Instruction Management Method" that electronically manages dental laboratory work instructions on paper. In this invention, since it is possible to update the instruction information described in the dental laboratory work instructions, the communication between the dental clinic and the dental laboratory can also be transmitted and received via the laboratory terminal and the dental clinic terminal, and it is possible to eliminate the complexity of management. Furthermore, Patent Document 3 discloses an invention named "Dental Laboratory Workpiece Identification System, Dental Laboratory Workpiece Identification Method, and Program". This invention relates to a technique for identifying which patient a completed dental laboratory workpiece belongs to. Specifically, a technique for determining the similarity between a feature quantity based on reference shape data, which is STL data associated with a dental laboratory work instruction, and a feature quantity based on the shape data of the dental laboratory workpiece to be identified is disclosed. In this invention, by determining the similarity between these two feature quantities, it is possible to identify which patient's dental laboratory workpiece it is.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the inventions disclosed in these patent documents, although the complexity of managing dental laboratory work instructions and the workpieces produced thereby is reduced, the complexity regarding grasping the instruction content reflecting the instruction characteristics of the dentist described in the dental laboratory work instructions before management cannot be eliminated. For example, conventionally, many dentists who fill out dental laboratory instructions are extremely busy, and they often need to complete the instructions in a short time, so the instructions may not be clearly written. Moreover, the content of the instructions may also be ambiguous due to variations in the dentists' instruction characteristics. Therefore, there have been cases where it is difficult to understand the content of the dental laboratory instructions in the first place, apart from management issues. Specifically, in dental laboratory instructions, while indicating the position of the patient's treated tooth in the dental arch, instructions regarding the gap dimension between the treated tooth and the adjacent tooth, called contact, instructions regarding the gap dimension between the treated tooth and the opposing tooth, called bite, and instructions regarding the gap dimension between the treated tooth and the prosthesis, called fit, are subjective, qualitative, and ambiguous terms such as "tight" or "loose" based on the dentists' own instruction characteristics. As a result, it is difficult to objectively and quantitatively determine the manufacturing dimensions of dentures at the dental laboratory. At the same time, even if the fabricated dental work is delivered to the dental clinic, it may not match the dentist's intention, leading to complexities such as the need to modify or remanufacture at the dental laboratory and inefficiencies in terms of yield.

[0005] The present invention has been made to address such conventional circumstances, and aims to provide a denture dimension evaluation system, a denture dimension evaluation method, and a denture dimension evaluation program that enable denture manufacturing by converting the subjective, qualitative, and ambiguous instruction content based on instruction characteristics described in the dental laboratory instructions created by dentists into objective, quantitative, and clear manufacturing dimensions for dentures.

Means for Solving the Problems

[0006] In order to achieve the above object, a denture dimension evaluation system according to a first invention converts a production level for a denture shown in a dental laboratory work instruction created by a dentist into production dimensions, and enables the dropping down to the production dimensions according to the instruction characteristics of the dentist and denture production based thereon. The denture dimension evaluation system includes a feature amount formed by adding dentition data of the production level for a learning denture by the dentist, and at least one of three types of data, i.e., contact data, bite data, and fit data of the production level; a denture dimension evaluation model learned using, as teacher data, a combination of the feature amount and production dimensions preliminarily assigned corresponding to the feature amount of the learning denture; a feature amount extraction unit that extracts the feature amount of the production level for the denture shown in the dental laboratory work instruction; an evaluation unit that evaluates the production dimensions for the denture by applying the feature amount extracted by the feature amount extraction unit to the denture dimension evaluation model; and an output unit that outputs the production dimensions for the denture evaluated by the evaluation unit. In the denture dimension evaluation system having the above configuration, the feature amount extraction unit acts to extract a feature amount formed by adding dentition data of the production level for the denture entered by the dentist in the dental laboratory work instruction, and at least one of three types of data, i.e., contact data, bite data, and fit data of the production level. Further, the evaluation unit acts to evaluate the production dimensions of the denture by inputting the feature amount for the extracted denture to the learned denture dimension evaluation model, and the output unit acts to output the evaluated production dimensions. In the present application, the "production level" means the instruction content regarding the production of a denture or a learning denture indicated by a dentist. Specifically, it means the content (data) of each of an instruction regarding a gap dimension between a treatment tooth called contact and an adjacent tooth, an instruction regarding a gap dimension between a treatment tooth called bite and an opposing tooth, and an instruction regarding a gap dimension between a treatment tooth called fit and a prosthesis. Further, since it is also necessary to indicate the specification of the treatment tooth, adjacent tooth, and opposing tooth by dentition data, for convenience, the "production level" includes dentition data.

[0007] Moreover, the denture dimension evaluation system, which is the second invention, is characterized in that in the first invention, it has a learned model generation unit that generates the denture dimension evaluation model using the teacher data. In the denture dimension evaluation system with the above configuration, the learned model generation unit adds at least one of the contact data, bite data, and fit data at the production level to the tooth alignment data at the production level for the learning denture, and uses the resulting feature amount and the production dimension pre-assigned as the correct label corresponding to the feature amount of the learning denture as teacher data to generate a learned denture dimension evaluation model.

[0008] The denture dimension evaluation method, which is the third invention, is a denture dimension evaluation method for converting the production level for a denture shown in a dental technician's instruction sheet created by a dentist into a production dimension, enabling the dropping down to the production dimension according to the instruction characteristics of the dentist and denture production based thereon. The method includes a feature amount extraction step of extracting a feature amount composed of at least one of the tooth alignment data at the production level for the denture shown in the dental technician's instruction sheet and the contact data, bite data, and fit data at the production level; a denture dimension evaluation step of evaluating the production dimension for the denture by applying the feature amount to a denture dimension evaluation model; and an output step of outputting the production dimension for the denture evaluated in the denture dimension evaluation step. The denture dimension evaluation model is a denture dimension evaluation model learned using, as teacher data, a combination of the feature amount at the production level for the learning denture by the dentist and the production dimension of the learning denture pre-assigned corresponding to the feature amount of the learning denture. In the denture dimension evaluation method with the above configuration, the feature quantity extraction step adds the dental arch data at the production level for the denture entered by the dentist in the dental technician's instruction sheet and at least one of the three data of the contact data, bite data, and fit data at the production level, and acts to extract the feature quantity composed thereof. Further, the denture dimension evaluation step acts to evaluate the production dimension of the denture by inputting the feature quantity for the extracted denture into the learned denture dimension evaluation model, and the output step acts to output the evaluated production dimension.

[0009] The denture dimension evaluation method which is the fourth invention is characterized in that, in the third invention, it has a learned model generation step of generating the denture dimension evaluation model learned using the teacher data. In the denture dimension evaluation method with the above configuration, the learned model generation step uses, as teacher data, the feature quantity composed of the dental arch data at the production level for the learning denture and at least one of the three data of the contact data, bite data, and fit data at the production level, and the production dimension previously given as the correct label corresponding to the feature quantity of the learning denture, and acts to generate a learned denture dimension evaluation model.

[0010] The denture dimension evaluation program according to the fifth invention is a denture dimension evaluation program executed by a computer to convert the production level for a denture indicated in a dental technician's instruction manual created by a dentist into production dimensions, and to enable the conversion into the production dimensions according to the instruction characteristics of the dentist and denture production based thereon. The program includes a feature quantity composed of the dental arch data of the production level for a learning denture by the dentist, and at least one of the three data of the contact data, bite data, and fit data of the production level, and a denture dimension evaluation model learned using, as teacher data, a combination of the feature quantity and the production dimensions of the learning denture previously assigned corresponding to the feature quantity of the learning denture. The program has a feature quantity extraction step of extracting the feature quantity of the production level for the denture indicated in the dental technician's instruction manual, a denture dimension evaluation step of evaluating the production dimensions for the denture by applying the feature quantity to the denture dimension evaluation model, and an output step of outputting the production dimensions for the denture evaluated in the denture dimension evaluation step. In the denture dimension evaluation program having the above configuration, the feature quantity extraction step acts to extract a feature quantity composed of the dental arch data of the production level for a denture entered by a dentist in a dental technician's instruction manual, and at least one of the three data of the contact data, bite data, and fit data of the production level. Further, the denture dimension evaluation step acts to evaluate the production dimensions of a denture by inputting the feature quantity of the extracted denture into the learned denture dimension evaluation model, and the output step acts to output the evaluated production dimensions.

[0011] The denture dimension evaluation program according to the sixth invention is characterized in that, in the fifth invention, it has a learned model generation step of generating the denture dimension evaluation model learned using the teacher data. In the denture dimension evaluation program with the above configuration, the learned model generation step adds a feature amount composed of dental arch data at the production level for the learning denture and at least one of the three types of data, i.e., contact data, bite data, and fit data, at the production level, and the production dimensions pre-assigned as the correct label corresponding to the feature amount of the learning denture, and acts to generate a learned denture dimension evaluation model using them as teacher data.

Advantages of the Invention

[0012] In the denture dimension evaluation system according to the first invention, the feature extraction unit extracts a feature amount composed of dental arch data at the production level for the denture entered by a dentist in a dental laboratory work order and at least one of the three types of data, i.e., subjective contact data, bite data, and fit data, expressed by the dentist himself / herself. In the evaluation unit, the feature amount related to the denture extracted by the learned denture dimension evaluation model is input, and the objective production dimensions of the denture can be evaluated according to the instruction characteristics of the dentist. Therefore, for each dentist, it is possible to convert the feature amount for a subjective and ambiguous denture based on the instruction characteristics into objective and clear production dimensions that can be produced in a dental laboratory, improve the quality of denture production, and increase the yield. Furthermore, since the request for correction or re-production of the denture is also reduced, it is also possible to promote the improvement of the yield and working environment of the dental laboratory.

[0013] The denture dimension evaluation system according to the second invention can generate a learned denture dimension evaluation model, and it is also possible to further learn the feature amount of the dental laboratory work order used for evaluation and the actual production dimensions as teacher data for the once-generated denture dimension evaluation model, and construct a denture dimension evaluation model with higher accuracy. By constructing a denture dimension evaluation model with higher accuracy, it is possible to further enhance the effects described in the first invention.

[0014] The denture dimension evaluation method according to the third invention is an invention that regards the denture dimension evaluation system according to the first invention as a method invention. Therefore, the effects obtained by implementing the method invention are the same as those of the first invention.

[0015] The method for evaluating the dimensions of a denture according to the fourth invention is an invention that regards the denture dimension evaluation system according to the second invention as a method invention. Therefore, the effects obtained by implementing this method invention are the same as those of the second invention.

[0016] The denture dimension evaluation program according to the fifth invention is an invention that regards the denture dimension evaluation method according to the third invention as a program invention to be executed using a computer. Therefore, the effects obtained by implementing this program invention are the same as those of the first and third inventions.

[0017] The denture dimension evaluation program according to the sixth invention is an invention that regards the denture dimension evaluation method according to the fourth invention as a program invention to be executed using a computer. Therefore, the effects obtained by implementing this program invention are the same as those of the second and fourth inventions.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5A

Figure 5B

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0019] FIG. 1 is a block diagram of a denture dimension evaluation system according to an embodiment of the present invention. In FIG. 1, the denture dimension evaluation system 1 includes a processing unit 2 composed of an input unit 3, a feature amount extraction unit 4a, a learned model generation unit 4b, an evaluation unit 5, and an output unit 6, and a teacher data database 7, an input data database 13, an output data database 19, and a learned model database 24 connected to the processing unit 2. This denture dimension evaluation system 1 can be assumed to be a system provided with arithmetic circuits and storage devices capable of exhibiting respective functions within a computer server. The input unit 3 functions as a data input unit or a data reception unit, and corresponds to a reception device for data related to learning dental technician instructions, dental technician instructions, etc., and a keyboard, mouse, tablet, optical reading device, etc. used when an administrator or user of the denture dimension evaluation system 1 inputs data. Further, as the output unit 6, a display device, a transmission device to an information communication network, or a transmitter that transfers data to other devices as a data transmission unit can be considered. That is, even if the components in FIG. 1 are not integrated, the input unit 3 and the output unit 6 can be separated and provided separately, and data and information can be transmitted and received between the processing unit 2, the databases 7, 13, 19, 24, or a portable terminal (not shown) or a browsing terminal (not shown) provided as necessary. It is also possible to adopt a system configuration.

[0020] In the process of generating the denture dimension evaluation models 25a and 25b as the learned models, the feature extraction unit 4a of the processing unit 2 functions as a device that extracts a feature amount composed of tooth row data and at least one of the three types of data, i.e., contact data, bite data, and fit data, from the content of the manufacturing level described in the learning dental laboratory instruction sheet input from the input unit 3.

[0021] Here, with reference to FIGS. 2(a) to 2(d), the tooth row data, contact data, bite data, and fit data will be described. FIG. 2(a) is a conceptual diagram showing a human tooth row, (b) is a conceptual diagram showing contact, which is one of the feature amounts, (c) is a conceptual diagram showing bite, which is one of the feature amounts, and (d) is a conceptual diagram showing fit, which is one of the feature amounts. As shown in FIG. 2(a), the tooth row indicates the position of the arrangement of human teeth. A human has eight teeth on each left and right side of the upper tooth row 26 and the lower tooth row 27. Therefore, a dentist assigns the numbers "1" to "8" for each upper and lower left and right to identify the location of the teeth, and indicates the treated tooth 30 (FIGS. 2(b) to 2(d)), the adjacent tooth 31 (FIG. 2(b)), and the opposing tooth 33 (FIG. 2(c)) in the dental laboratory instruction sheet. Therefore, the tooth row data means the numbers for identifying the location of the teeth indicated by the dentist and the data indicated by the icon position of the teeth. Next, the contact data means the instruction content regarding the gap dimension (contact 32) between the treated tooth 30 and the adjacent tooth 31 as shown in FIG. 2(b), the bite data means the instruction content regarding the gap dimension (bite 34) between the treated tooth 30 and the opposing tooth 33 as shown in FIG. 2(c), and the fit data means the instruction content regarding the gap dimension (fit 36) between the treated tooth 30 and the covering (prosthesis) 35 as shown in FIG. 2(d). Note that not only the treated tooth 30 which is a cut tooth, but also in the case of a false tooth, the mucosa is used instead of the treated tooth 30 in FIG. 2(d), the false tooth is used instead of the covering 35, and the wearing feeling is expressed as the fit 36.

[0022] Returning to FIG. 1, in the operation process of the denture dimension evaluation models 25a and 25b, it functions as a device that extracts a feature amount composed of dentition data and at least one of the three types of data, i.e., contact data, bite data, and fit data, from the content of the production level described in the dental laboratory instruction sheet input from the input unit 3 for manufacturing the denture used in the treatment. The learned model generation unit 4b is a device that generates a learned denture dimension evaluation model using, as teacher data, a feature amount composed of dentition data at the production level for the learning denture extracted from the dental laboratory instruction sheet for learning and at least one of the three types of data, i.e., contact data, bite data, and fit data, at the production level, and the production dimension pre - assigned as the correct label corresponding to the feature amount of the learning denture. Hereinafter, a pair of data of contact data, bite data, and fit data of the feature amount of the learning denture in the teacher data and the production dimension pre - assigned as the correct label corresponding to each of them are respectively referred to as contact teacher data, bite teacher data, and fit teacher data. The evaluation unit 5 is a device that evaluates the production dimension of the denture by applying the feature amount extracted from the dental laboratory instruction sheet for manufacturing the denture, which is extracted by the feature amount extraction unit 4a, to the denture dimension evaluation model.

[0023] The teacher data database 7 is a database that stores in a readable manner contact teacher data 10a - 10c composed of dentition data 9a - 9c at the production level for the learning denture extracted from the dental laboratory instruction sheet for learning and contact data of the production level and the production dimension pre - assigned as the correct label corresponding thereto, bite teacher data 11a - 11c composed of bite data at the production level and the production dimension pre - assigned as the correct label corresponding thereto, and fit teacher data 12a - 12c composed of fit data at the production level and the production dimension pre - assigned as the correct label corresponding thereto. Note that the symbols "a" to "c" are attached to assume that there are three dentists when operating the denture dimension evaluation system 1 according to the present embodiment, and they are stored as teacher data sets 8a to 8c for each dentist. As described above, since it is a denture dimension evaluation system for the purpose of reducing variations due to the individuality of dentists, it is desirable to store the data sets in the teacher database 7 for each dentist. Therefore, even when there are dentists other than the three, it is desirable to operate while storing the data sets for each dentist.

[0024] Next, the input database 13 is a database that can read and store the dental arch data 15a to 15c at the production level for the dentures extracted from the dental technician's instructions when utilizing the denture dimension evaluation system 1, the contact data 16a to 16c at the production level, the bite data 17a to 17c at the production level, and the fit data 18a to 18c at the production level. Also in this input database 13, assuming three dentists, they are stored as three input data sets 14a to 14c.

[0025] Finally, the output database 19 is a database that can read the denture dimension evaluation models 25a and 25b generated by the learned model generation unit 4b by the evaluation unit 5, input the input data sets 14a to 14c stored in the input database 13 thereto, and read and store the data of the results of evaluating the production dimensions of the dentures to be created based on the dental technician's instructions. Specifically, similar to the teacher database 7 and the input database 13, assuming three dentists, in addition to the contact evaluation data 21a to 21c, the bite evaluation data 22a to 22c, and the fit evaluation data 23a to 23c, the same dental arch data 15a to 15c as at the time of input are also stored as output data sets 20a to 20c so that they can be read.

[0026] Next, in addition to FIG. 1, with reference to FIGS. 3 to 5A and 5B, the generation of the denture dimension evaluation models 25a and 25b in the denture dimension evaluation system 1 and the flow of denture dimension evaluation using the learned denture dimension evaluation models 25a and 25b will be described. FIG. 3 is a flowchart showing the flow of generating a denture dimension evaluation model by learning and the flow of denture dimension evaluation using the learned denture dimension evaluation model, which is executed by the denture dimension evaluation system according to the embodiment of the present invention. This FIG. 3 also represents the execution process for the denture dimension evaluation method and the denture dimension evaluation program of the present invention. Explaining the flow of generating the denture dimension evaluation model in the denture dimension evaluation system 1 and the flow of denture dimension evaluation using the learned denture dimension evaluation model with reference to this figure is synonymous with explaining the embodiment of the denture dimension evaluation method and the denture dimension evaluation program using a computer. In FIG. 3, the components connected to the broken line that covers the symbols and descriptions related to the steps indicated by the drawn lines from the descriptions related to the steps indicated by "S" are the components of the denture dimension evaluation system 1 shown in FIG. 1, and the symbols are the same.

[0027] In FIG. 3, step S1 of the upper learned model generation process is a process of inputting information on the feature amounts shown in the dental technician's instruction for the learning denture, that is, dentition data, contact data at the production level, bite data at the production level, and fit data at the production level, from the input unit 3. The information on the feature amounts in this step S1 is a concept including the above data themselves or the dental technician's instruction including those data. Also, when inputting the information on the feature amounts to the input unit 3, in the case of inputting the data themselves, it may be input based on the characters and numbers representing the dentition data described in the dental technician's instruction and the numbers (indices) such as 1 to 7 representing the production levels of the contact data, bite data, and fit data, which will be described with reference to FIG. 4 later. On the other hand, when the input unit 3 is a scanner device or the like, the dental technician's instruction itself may be scanned to input information other than the feature amounts.

[0028] Here, an explanation of the dental laboratory instruction will be added while referring to FIG. 4. FIG. 4 is a conceptual diagram of the dental laboratory instruction created by a dentist. In FIG. 4, the dental laboratory instruction 40 is provided with a name and dental clinic name display column 41 and a location display column 42 of the dental clinic, and information regarding the dentist who created the dental laboratory instruction 40 is shown. Icons regarding the upper dental arch 26 and the lower dental arch 27 are shown together with numbers representing the positions of the teeth. For example, assuming that the hatched tooth indicated by "5" in "lower left" (lower right in the figure) is the treatment tooth 30, it is indicated by the dentist check 48 by the dentist that it is the fifth tooth in the "lower left" dental arch. In the present embodiment, the dentist check 48 is shown at the "lower left" of the dental arch and the number "5" of the tooth number 43 as an entry by the dentist, but it may be specified by the dentist check 48 for the icon of the tooth shape itself below or the tooth number 43 attached to the tooth shape. Note that in the present embodiment, the dentist check 48 is represented by a figure like the katakana character "re", but the actual shape of the dentist check 48 is not limited to a figure like "re", and any figure, number, character, or symbol may be used as long as the tooth is specified. On the left side of the area showing the dental arch, there are a contact entry column 45, a bite entry column 46, and a fit entry column 47. These are represented by characters indicating the degrees of "loose", "normal", and "tight" and the numbers "1" to "7" and "scale" corresponding to those degrees as an index 44, and the dentist expresses the contact data, bite data, or fit data at the production level by marking the dentist check 48 on the "scale". The subjective instruction characteristics of the dentist will appear when expressing the index 44. Note that this dental laboratory instruction 40 is common for both learning dentures and therapeutic dentures. Also, the dental laboratory instruction 40 is not limited to that shown in FIG. 4, and it suffices if at least one of the display of the dentist's name, the instruction regarding the dental arch, and the instruction regarding the production contact data, bite data, and fit data is shown. For example, while indicating the index 44, the entry by the dentist may be shown as the number itself instead of the dentist check 48.

[0029] Returning to FIG. 3, step S2 is a step in which the feature amount extraction unit 4a extracts the feature amount of the production level from the information regarding the production level input via the input unit 3 in step S1. When the information in step S1 is the production level data itself (hereinafter, this case is referred to as pattern 1), the feature amount as a combination of the dental arch data, contact data, bite data, and fit data of the production level required from the information is extracted. Also, when the information input in step S1 is the entire dental laboratory instruction 40 or a part thereof (hereinafter, this case is referred to as pattern 2), the feature amount as a combination of the dental arch data, contact data, bite data, and fit data of the production level required is read and extracted therefrom. In this case, for the extraction of the feature amount of the production level, the feature amount extraction unit 4a is an apparatus equipped with an OCR (Optical Character Recognition) function and an image recognition function, etc., so that it is possible to read characters, numbers, figures, or symbols described in the dental laboratory instruction 40. The extracted feature amount of the production level of the learning denture is stored by the feature amount extraction unit 4a in the teacher data database 7 so as to be readable as dental arch data 9a to 9c, contact teacher data 10a to 10c, bite teacher data 11a to 11c, and fit teacher data 12a to 12c.

[0030] In step S3, the manufacturing dimensions of the learning denture as the correct label are input via the input unit 3, and the input unit 3 stores the contact teacher data 10a to 10c, the bite teacher data 11a to 11c, and the fit teacher data 12a to 12c in the teacher data database 7 so that they can be read out. As described above, since each teacher data means a pair of data of the feature amount at the manufacturing level of the learning denture and the manufacturing dimensions as the correct label, they are stored as a pair of data. Step S4 is a process in which the learned model generation unit 4b reads out the contact teacher data 10a to 10c, the bite teacher data 11a to 11c, and the fit teacher data 12a to 12c from the teacher data database 7 and performs machine learning.

[0031] Here, while referring to FIGS. 5A and 5B, an explanation will be added to the machine learning process by the learned model generation unit 4b in step S4. FIG. 5A is a conceptual diagram showing the configuration in the case of pattern 1 of the denture dimension evaluation model according to the present embodiment, and FIG. 5B is a conceptual diagram showing the tooth row of the input layer in the case of pattern 1 of the denture dimension evaluation model expressed by numbers based on international standards. In FIG. 5A, in the input layer 50a of the denture dimension evaluation model 25a, in addition to the tooth row data 9a extracted from the dental technician's instruction 40 regarding the learning denture, among the contact teacher data 10a, the bite teacher data 11a, and the fit teacher data 12a, the contact data 53a, the bite data 54a, and the fit data 55a at the manufacturing level described by the dentist in the dental technician's instruction 40 are input. In pattern 1, they are extracted as data, and the contact data 53a is 2.3, the bite data 54a is 4.5, and the fit data 55a is 4.8, respectively. These numbers are either directly described by the dentist in the dental technician's instruction 40 or are extracted in some way in advance from the dentist check 48 attached to the scale or the like displayed and expressed numerically without a unit.

[0032] On the other hand, in the output layer 52a, the dentition data 9a is output as the dentition data 9a as it is from the input layer 50a via the intermediate layer 51a. However, for the contact data 53a of 2.3, the bite data 54a of 4.5, and the fit data 55a of 4.8 of the learning denture with respect to the manufacturing level input to the input layer 50a, as the manufacturing dimensions of the learning denture, the contact manufacturing dimension 53b of 0.23 mm, the bite manufacturing dimension 54b of 0.05 mm, and the fit manufacturing dimension 55b of 0.012 mm of the correct label are output respectively. These manufacturing dimensions of the correct label are objective and quantitative manufacturing dimensions obtained corresponding to the contact data 53a etc. of the manufacturing level obtained according to the instruction characteristics of the dentist. And these constitute a pair of contact teacher data 10a, bite teacher data 11a, and fit teacher data 12a. Regarding the dentition data 9a, in FIG. 5A, it is described as data with a dentist check 48 attached to the tooth number 43 and the position of the dentition. However, these are pre-assigned numbers based on international standards with "upper right" being 1, "upper left" being 2, "lower left" being 3, and "lower right" being 4. Along with the tooth number 43 that becomes 1 to 8 starting from the anterior teeth, for example, if it is the fourth tooth from the lower right anterior tooth where the dentist check 48 is shown in the dentition of FIG. 5A, as shown in FIG. 5B, it is expressed as "44" etc. Then, the input in the input unit 3 and the extraction in the feature quantity extraction unit 4a can also be handled as numerical data itself. In that case, it is advisable to instruct to also write the numbers based on international standards together with the tooth number 43 in the dentition display column of the dental technician's instruction sheet 40 shown in FIG. 4. In that case, it may be written together with the tooth number 43 such as "upper right (1)" etc., and further, it may be made to have the dentist check 48. Also, when "44" is input in the dentition data 9a of the input layer 50a, the dentition data 9a is also output as "44" in the output layer 52a of FIG. 5A. In this way, since the dentition data 9a is output as it is from the input layer 50a and is not input to the denture dimension evaluation model function 56a of the intermediate layer 51a, if the position of the treatment tooth 30 in the dentition is specified and there are no problems in the input unit 3 and the feature quantity extraction unit 4a, it is not necessary to be restricted by the data format.

[0033] In the intermediate layer 51a, a denture dimension evaluation model function 56a for machine learning is arranged so that contact manufacturing dimensions 53b, etc. of the learning denture as the correct label output from the output layer 52a can be derived from contact data 53a, etc. of the manufacturing level of the learning denture input in the input layer 50a. When the contact data 53a, etc. of the manufacturing level are expressed numerically in the input layer 50a as in Pattern 1, as this model function, it is desirable to perform regression analysis using the least squares method or the like, and the function obtained as a result is desirable. However, the type of the denture dimension evaluation model function 56a is not particularly limited, and as long as the causal relationship or correlation between the contact data 53a, etc. as input values and the contact manufacturing dimensions 53b, etc. as output values is clarified, any function other than a linear function may be used. Therefore, in the case of Pattern 1, the machine learning process by the learned model generation unit 4b in step S4 is a process of obtaining a function in which the causal relationship or correlation between the contact data 53a, etc. of the manufacturing level as input values and the contact manufacturing dimensions 53b, etc. of the correct label as output values is obtained while performing regression analysis. In this way, the learned model generation unit 4b generates a learned denture dimension evaluation model function 56a by regression analysis or the like for outputting contact manufacturing dimensions, etc. in response to the input of contact data 53a, etc. of the manufacturing level of the learning denture, uses this as the intermediate layer 51a, and stores it in the learned model database 24 in a readable manner as a learned denture dimension evaluation model 25a including the front and rear input layer 50a and output layer 52a.

[0034] Next, with reference to FIG. 6, an explanation of the machine learning process by the learned model generation unit 4b in step S4 will be added for the case of Pattern 2. FIG. 6 is a conceptual diagram showing the configuration in the case of Pattern 2 of the denture dimension evaluation model according to the present embodiment. In the denture dimension evaluation model 25b of FIG. 6, in the case of Pattern 2, what is different from Pattern 1 is that neither what is input in the input unit 3 nor what is extracted by the feature extraction unit 4a is numerical data, but the dental laboratory instruction 40 for learning itself. It is the index 44 and the dentist check 48 image in the dental laboratory instruction 40 as shown in the input layer 50b, and this is input as the contact data image 57a, the bite data image 58a, and the fit data image 59a at the production level of the learning denture. In the case of Pattern 2, as shown in the input layer 50b of FIG. 6, even when the dentist check 48 is attached to the position of the dental arch and the tooth number 43 as the dental arch data 9a, there is no problem because a device equipped with a scanning and character and graphic recognition function is used in the input unit 3 and the feature extraction unit 4a. Also, similar to Pattern 1, it is not necessary to input to the denture dimension evaluation model function 56b of the intermediate layer 51b. In the output layer 52b, the dental arch data 9a is output as it is, similar to Pattern 1, and the contact production dimension 53b, etc. as the correct label are also the same as in Pattern 1. As such a machine learning method in the case of Pattern 2, it is conceivable to use a denture dimension evaluation model function 56b using a neural network that inputs the contact data image 57a, the bite data image 58a, and the fit data image 59a of the index 44 and the dentist check 48 in the dental laboratory instruction 40 as shown in the input layer 50b of FIG. 6, respectively, and outputs the contact production dimension 53b, the bite production dimension 54b, and the fit production dimension 55b of the denture.

[0035] In the machine learning process in this case, the contact production dimensions of the denture output by inputting the index 44 in the dental technician's instruction 40 and the contact data image 57a of the dentist's check 48 are compared with the contact production dimensions 53b of the correct label, etc., and the parameters of the denture dimension evaluation model function 56b using the neural network of the intermediate layer 51b are optimized so that the contact production dimensions of the output denture approach the contact production dimensions 53b of the correct label. Examples of these parameters include weights (coupling coefficients) between neurons and coefficients used in activation functions. Regarding the optimization method of these parameters, for example, it is executed using the error backpropagation method or the like. In this way, the learned model generation unit 4b generates a learned denture dimension evaluation model function 56b that uses a neural network that receives the input of the index 44 in the dental technician's instruction 40 and the contact data image 57a of the dentist's check 48 and outputs the contact production dimensions, etc., uses this as the intermediate layer 51b, and includes the input layer 50b and the output layer 52b before and after, and stores it in the learned model database 24 so that it can be read out as the learned denture dimension evaluation model 25b. Note that as the neural network, in this embodiment, a convolutional neural network (CNN) that is considered suitable for image processing is used. However, as long as the correct correlation between the input and output can be maintained, other learning algorithms such as a support vector machine (SVM) may be used.

[0036] Also, in FIGS. 5A, 5B and 6, data at the production level by dentist "a" is used as the input, and furthermore, as the feature quantities, all three types of data, namely dentition data, contact data, bite data, and fit data at the production level, are used. However, the data regarding the production level may include at least one of the three types of data. This is because in the trained model generation unit 4b in step S4, the contact data, bite data, and fit data at the production level in the feature quantities are independently learned with respect to the dentition data. Furthermore, the target dentists are not only "a", but may also include "b", "c", or others. However, in order to reflect the individuality of each dentist, in the trained model generation unit 4b, it is necessary to independently learn for each individual dentist.

[0037] Returning to FIG. 3, step S5 is a step of obtaining the denture dimension evaluation models 25a and 25b that have been learned by the machine learning executed by the trained model generation unit 4b in step S4. The obtained denture dimension evaluation models 25a and 25b are stored in the trained model database 24 in a manner that can be read by the trained model generation unit 4b. By this step S5, the learned denture dimension evaluation models 25a and 25b are obtained, and the process of generating the learned model is completed.

[0038] Next, the operation process of the learned model will be described with reference to FIG. 3 and FIG. 7. FIG. 7 is a conceptual diagram showing the denture dimension evaluation model used in the evaluation unit of the denture dimension evaluation system according to the embodiment of the present invention. In this FIG. 7, both the case of pattern 1 and the case of pattern 2 are described as the dentition data 15a to 15c, contact data 16a to 16c, bite data 17a to 17c, and fit data 18a to 18c shown in the input layer 50c of the denture dimension evaluation models 25a and 25b. In the input layer 50c, in pattern 1, the dental arch data 15a to 15c indicating that the tooth number 43 in the lower right is the tooth numbered "4", the contact data 16a to 16c of "3.2", the bite data 17a to 17c of "3.7", and the fit data 18a to 18c of "4.6" are input as the extracted numerical values. However, in pattern 2, an image is input that is extracted from the dental technician's instruction 40 regarding the data and shows the dentist check 48 with the index 44 reflecting the instruction characteristics of the dentist. Note that the denture dimension evaluation model 25a is for pattern 1, and the denture dimension evaluation model 25b is for pattern 2. Regarding the dental arch data 15a to 15c, in FIG. 7, it is described as data with the dentist check 48 attached to the tooth number 43 and the position of the dental arch. Similar to the dental arch data 9a described with reference to FIGS. 5A and 5B, it may be expressed as numerical data. By doing so, the input in the input unit 3 and the extraction in the feature extraction unit 4a can also be handled as the numerical data itself. However, since the dental arch data 15a to 15c are output as they are from the input layer 50c and are not input to the denture dimension evaluation model functions 56a and 56b in the intermediate layer 51c, if the position of the treatment tooth 30 in the dental arch is specified and there are no problems in the input unit 3 and the feature extraction unit 4a, the data format does not have to be restricted. In FIG. 3, step S6 is the input process of the dental technician's instruction 40 for the denture. From the dental technician's instruction 40, the data at the production level like in pattern 1 may be extracted and input as numerical data in some way, or the description of the dental technician's instruction 40 itself like in pattern 2 may be input. The input is performed for the input unit 3.

[0039] Step S7 is a step in which the feature quantity extraction unit 4a extracts the feature quantity of the manufacturing level from the information regarding the manufacturing level input via the input unit 3 in step S6. When extracting the feature quantity of the manufacturing level, if the information in step S6 is pattern 1, the feature quantity is extracted as a combination with at least one of the three types of data, namely, the dentition data 15a to 15c, the contact data 16a to 16c, the bite data 17a to 17c, and the fit data 18a to 18c, of the required denture manufacturing level from the information. When only the numerical data of the required manufacturing dimensions is input in advance in step S6, the input numerical data is directly extracted in step S7. On the other hand, if the information input in step S6 is pattern 2, an image regarding the feature quantity as a combination with at least one of these three types of data and the dentition data 15a to 15c is read and extracted from among the dentition data 15a to 15c of the required denture manufacturing level from the dental laboratory instruction 40, the contact data image 57b as the contact data 16a to 16c, the bite data image 58b as the bite data 17a to 17c, and the fit data image 59b as the fit data 18a to 18c. The feature quantity extraction unit 4a stores the extracted feature quantity in the input data database 13 so that it can be read out as the input data sets 14a to 14c of the dentition data 15a to 15c, the contact data 16a to 16c, the bite data 17a to 17c, and the fit data 18a to 18c in both cases of pattern 1 and pattern 2.

[0040] Step S8 is a step of inputting the feature amounts extracted in step S7 into the denture dimension evaluation models 25a and 25b. In this step, the evaluation unit 5 reads out either of the denture dimension evaluation models 25a and 25b from the learned model database 24 according to the pattern of the feature amounts extracted by the feature amount extraction unit 4a. Further, the evaluation unit 5 inputs, to the input layer 50c of the denture dimension evaluation models 25a and 25b, a data set as shown as pattern 1 in FIG. 7 if it is pattern 1, and inputs a data set as shown as pattern 2 if it is pattern 2, by reading them out from the input data database 13. Note that FIG. 7 shows both data sets in the case of pattern 1 and pattern 2 in the input layer 50c, and also shows a data set including all of the contact data 16a to 16c, the bite data 17a to 17c, and the fit data 18a to 18c. However, as the feature amounts to be extracted, a combination with at least one of the three data related to the production level such as the contact data 16a to 16c with respect to the dental arch data 15a to 15c necessary as production dimensions may be sufficient. Also, although it seems that the data of three dentists with the signs "a" to "c" are input simultaneously, the data of each dentist may be input one by one, or the data of a plurality of dentists may be input simultaneously.

[0041] Step S9 is a step of evaluating the denture dimensions, that is, the production dimensions of the denture. In this step, the evaluation unit 5 evaluates the production dimensions of the denture using the denture dimension evaluation model functions 56a and 56b of the intermediate layer 51c according to the feature amounts input to the input layer 50c. That is, it is a step of evaluating the objective and quantitative production dimensions of the denture according to the feature amounts reflecting the subjective and qualitative instruction characteristics of the dentist. Note that in step S8, an explanation has been given that the data of a plurality of dentists may be input simultaneously. However, since the denture dimension evaluation model functions 56a and 56b are learned using the teacher data for each dentist, it is necessary to use individual functions for each dentist. Step S10 is a step of outputting the production dimensions of the denture. In this step, the evaluation unit 5 outputs, as the production dimensions related to the denture evaluated by the denture dimension evaluation model functions 56a and 56b of the intermediate layer 51c, a set of tooth row data 15a to 15c, contact evaluation data 21a to 21c, bite evaluation data 22a to 22c, and fit evaluation data 23a to 23c to the output layer 52c, and further, the evaluation unit 5 stores these data in the output database 19 so that they can be read out as output data sets 20a to 20c. At the dental laboratory, the necessary output data sets 20a to 20c can be read from the output database 19 via the output unit 6 of the processing unit 2, and the denture can be manufactured based on the objectively, specifically, and quantitatively obtained production dimensions of the denture.

[0042] Therefore, in the denture dimension evaluation system 1 according to the present embodiment, for each dentist, it is possible to convert the subjective, qualitative, and ambiguous features of the denture that reflect the instruction characteristics in the dental laboratory instruction sheet into objective, quantitative, and clear production dimensions that can be manufactured at the dental laboratory, and it is possible to improve the quality and yield of denture production. Furthermore, since the request for modification and re-production of the denture from the dentist is also reduced, it is possible to contribute to the improvement of the work efficiency of the dental laboratory, and ultimately, it is also possible to promote the improvement of the working environment. Furthermore, in the denture dimension evaluation system 1, by providing the learned model generation unit 4b and the teacher database 7, it is possible to update the teacher data sets 8a to 8c over time when generating the denture dimension evaluation models 25a and 25b. Therefore, it is possible to update the denture dimension evaluation models 25a and 25b using the learned model generation unit 4b according to the accumulation of the tooth row data 9a to 9c, the contact teacher data 10a to 10c, the bite teacher data 11a to 11c, and the fit teacher data 12a to 12c to construct a more accurate learned model, and it is possible to further enhance the above-described effects. In addition, in the denture dimension evaluation method that regards the denture dimension evaluation system 1 as a method invention and the denture dimension evaluation program that regards it as a program invention, it is possible to exhibit the same effects as those that the denture dimension evaluation system 1 can exhibit.

Industrial Applicability

[0043] The invention of the present application can be used in a denture dimension evaluation system, a method thereof, and a program thereof that can evaluate the denture dimensions required for manufacturing a denture at a denture manufacturing facility based on a dental laboratory instruction sheet exchanged between a dentist and a dental laboratory.

Explanation of Signs

[0044] 1…Denture dimension evaluation system 2…Processing unit 3…Input unit 4a…Feature extraction unit 4b…Trained model generation unit 5…Evaluation unit 6…Output unit 7…Teacher database 8a~8c…Teacher dataset 9a~9c…Dental arch data 10a~10c…Contact teacher data 11a~11c…Bite teacher data 12a~12c…Fit teacher data 13…Input data database 14a~14c…Input dataset 15a~15c…Dental arch data 16a~16c…Contact data 17a~17c…Bite data 18a~18c…Fit data 19…Output data database 20a~20c…Output dataset 21a~21c…Contact evaluation data 22a~22c…Bite evaluation data 23a~23c…Fit evaluation data 24…Trained model database 25a,25b…Denture dimension evaluation model 26…Upper dental arch 27…Lower dental arch 30…Treatment tooth 31…Adjacent tooth 32…Contact 33…Opposing tooth 34…Bite 35…Overlay 36…Fit 40…Dental technician's instruction 41…Name and hospital name display column 42…Location display column 43…Tooth number 44…Index 45…Contact entry column 46…Bite entry column 47…Fit entry column 48…Dentist's check 50a~50c…Input layer 51a~51c…Intermediate layer 52a~52c…Output layer 53a…Contact data 53b…Contact production dimension 54a…Bite data 54b…Bite production dimension 55a…Fit data 55b…Fit production dimension 56a,56b…Denture dimension evaluation model function 57a,57b…Contact data image 58a,58b…Bite data image 59a,59b…Fit data image

Claims

1. A denture dimension evaluation system for converting the production level indicated for a denture in a dental technician's instruction sheet created by a dentist into production dimensions and enabling the reduction of the production dimensions according to the instruction characteristics of the dentist and the production of a denture based thereon, comprising: A feature quantity formed by adding the dental arch data of the production level for a learning denture by the dentist and at least one of the three data of contact data, bite data, and fit data of the production level, and a production dimension preliminarily assigned corresponding to the feature quantity of the learning denture, a denture dimension evaluation model learned with the combination as teacher data; A feature quantity extraction unit that extracts the feature quantity of the production level for the denture indicated in the dental technician's instruction sheet; An evaluation unit that evaluates the production dimension for the denture by applying the feature quantity extracted by the feature quantity extraction unit to the denture dimension evaluation model; An output unit that outputs the production dimension for the denture evaluated by the evaluation unit, a denture dimension evaluation system characterized by comprising the above.

2. The denture dimension evaluation system according to Claim 1, further comprising a learned model generation unit that generates the denture dimension evaluation model using the teacher data.

3. A denture dimension evaluation method for converting the production level indicated for a denture in a dental technician's instruction sheet created by a dentist into production dimensions and enabling the reduction of the production dimensions according to the instruction characteristics of the dentist and the production of a denture based thereon, comprising: A feature quantity extraction step of extracting a feature quantity formed by adding the dental arch data of the production level for the denture indicated in the dental technician's instruction sheet and at least one of the three data of contact data, bite data, and fit data of the production level; A denture dimension evaluation step of evaluating the production dimension for the denture by applying the feature quantity to a denture dimension evaluation model; An output step of outputting the production dimension for the denture evaluated in the denture dimension evaluation step, and having: The denture dimension evaluation model is a denture dimension evaluation model learned with a combination of the feature quantity of the production level for a learning denture by the dentist and the production dimension of the learning denture preliminarily assigned corresponding to the feature quantity of the learning denture as teacher data, a denture dimension evaluation method characterized by this.

4. The denture dimension evaluation method according to claim 3, comprising a trained model generation step of generating the denture dimension evaluation model trained using the teacher data.

5. A denture dimension evaluation program executed by a computer to convert the production level for a denture shown in a dental technician's instruction sheet created by a dentist into production dimensions, and to enable the dropping down to the production dimensions and denture production based on the instruction characteristics of the dentist, comprising a denture dimension evaluation model trained using, as teacher data, a combination of a feature amount obtained by adding at least one of the tooth alignment data of the production level for a learning denture by the dentist, and the three data of the contact data, bite data, and fit data of the production level, and the production dimensions of the learning denture pre-assigned corresponding to the feature amount of the learning denture, a feature amount extraction step of extracting the feature amount of the production level for the denture shown in the dental technician's instruction sheet, a denture dimension evaluation step of evaluating the production dimensions for the denture by applying the feature amount to the denture dimension evaluation model, and an output step of outputting the production dimensions for the denture evaluated in this denture dimension evaluation step. The denture dimension evaluation program is characterized by having these steps.

6. The denture dimension evaluation program according to claim 5, comprising a trained model generation step of generating the denture dimension evaluation model trained using the teacher data.

Images