Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
AUTOMATIC CREATION OF A VIRTUAL MODEL OF AT LEAST A BONDING PART OF AN ORTHODONTIC BRACKET
Document Type and Number:
WIPO Patent Application WO/2022/135717
Kind Code:
A1
Abstract:
A computer-implemented method and a system are provided to create a virtual model of at least a bonding part of an orthodontic bracket. A process for manufacturing at least a bonding part of an orthodontic bracket is described.

Inventors:
HIRSCH MARKUS (CH)
Application Number:
PCT/EP2020/087803
Publication Date:
June 30, 2022
Filing Date:
December 23, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HIRSCH DYNAMICS HOLDING AG (CH)
International Classes:
A61C7/00; A61C7/14; A61C7/16
Domestic Patent References:
WO2019241251A12019-12-19
Foreign References:
US20030152884A12003-08-14
US20160199154A12016-07-14
US20180303581A12018-10-25
US20090191503A12009-07-30
US20160361142A12016-12-15
Attorney, Agent or Firm:
TORGGLER & HOFMANN PATENTANWÄLTE GMBH & CO KG et al. (AT)
Download PDF:
Claims:
CLAIMS

22 What is claimed:

1. A computer- implemented method for creating a virtual model of at least a bonding part of an orthodontic bracket, comprising at least the following steps:

• providing a virtual tooth model of a patient’s tooth, the virtual tooth model modeling at least one surface of the patient’s tooth to which the orthodontic bracket is to be bonded

• determining a bonding area of the at least one surface of the virtual tooth model to which the orthodontic bracket is to be bonded

• using at least one artificial neuronal network to create, on basis of said bonding area of the virtual tooth model, at least the virtual model of the bonding part of the orthodontic bracket, the virtual model of the boding part having a bonding surface which is modeled in such a way that said bonding surface matches the bonding area of the virtual tooth model

2. The method of the preceding claim wherein the virtual model of the bonding part of the orthodontic bracket is created by the at least one artificial neuronal network such that the bonding part has a pre-defined connecting surface for connecting the bonding part to an archwire part of an orthodontic bracket.

3. The method of the preceding claim wherein the pre-defined connecting surface of the virtual model of the bonding part of the orthodontic bracket has at least one protrusion and/or at least one recess.

4. The method of at least one of the preceding claims wherein the virtual model of the bonding part of the orthodontic bracket models, on the bonding surface, an alphanumeric code to identify the tooth to which the bonding surface is to be bonded to, preferably in the form of human-readable recesses and/or protrusions which form alphanumeric symbols. The method of at least one of the preceding claims, wherein:

• a virtual model of an archwire part of an orthodontic bracket is provided which models at least one archwire slot running in a mesial-distal direction

• based on the virtual model of the bonding part of the orthodontic bracket and on the virtual model of an archwire part of an orthodontic bracket a virtual model of a complete orthodontic bracket modeling at least both, the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket is created The method of at least one of claim 2 to claim 5 wherein the virtual model of the archwire part of an orthodontic bracket models a connecting surface in such a way that it matches the pre-defined connecting surface of the bonding part of the orthodontic bracket. The method of the preceding claim wherein the step of creating the virtual model of the complete orthodontic bracket is done by connecting

• the connecting surface of the virtual model of the archwire part of an orthodontic bracket and

• the pre-defined connecting surface of the bonding part of the orthodontic bracket The method of at least one of claim 5 to claim 7 wherein the virtual model of the archwire part of an orthodontic bracket is provided in the form of a template having a pre-defined shape. A computer-implemented method for creating virtual models of a plurality of orthodontic brackets, in particular virtual models of a plurality of orthodontic brackets for a complete mandibular and/or maxillary dentition of a patient, comprising at least the following steps:

• for each of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, an individual virtual model of at least a bonding part of an orthodontic bracket is created with the method of at least one of the preceding claims, wherein the individual virtual models of the bonding parts of different orthodontic brackets of the plurality of orthodontic brackets differ from each other with respect to their bonding surfaces

• for all of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, a virtual model of the archwire part of an orthodontic bracket is chosen, wherein it is preferred that the chosen virtual model of the archwire part of an orthodontic bracket is the same for all of the orthodontic brackets of the plurality of orthodontic brackets

• for each orthodontic bracket of the plurality of orthodontic brackets the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket are combined to form a virtual model of the complete orthodontic bracket modeling at least both, the individual virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part The method of the preceding claim wherein a plurality of artificial neuronal networks which work in parallel is used to create the individual virtual models

25 of at least the bonding parts of different orthodontic brackets. The method of at least one of the preceding claims wherein the virtual tooth model of a patient’s tooth is provided in the form of a scan file, preferably obtained by scanning a dental imprint or an intraoral scan. The method of the preceding claim wherein the scan file is provided in the form of at least one CAD file, preferably at least one STL file or at least one object file, and wherein the at least one artificial neuronal network is trained to read the at least one CAD file. The method of at least one of the preceding claims wherein the virtual model of at least the bonding part of the orthodontic bracket(s) and/or of the archwire part of an orthodontic bracket and/or of a complete orthodontic bracket is provided in the form of at least one CAD file, preferably at least one STL file or at least one object file. A system for creating a virtual model of at least a bonding part of an orthodontic bracket, comprising at least:

• at least one input configured to receive a virtual tooth model of a patient’s tooth, the virtual tooth model modeling at least one surface of the patient’s tooth to which the orthodontic bracket is to be bonded

• at least one computing device which is configured to execute at least one artificial neuronal network which is trained to

— accept, as input, a bonding area of the at least one surface of the virtual tooth model to which the orthodontic bracket is to be bonded or, preferably, determine a bonding area of the at least one surface

26 of the virtual tooth model to which the orthodontic bracket is to be bonded

— create, on basis of said bonding area of the virtual tooth model, the virtual model of at least the bonding part of the orthodontic bracket, the virtual model of the bonding part having a bonding surface which is modeled in such a way that said bonding surface matches the bonding area of the virtual tooth model The system according to the preceding claim wherein the at least one artificial neuronal network is trained to create the virtual model of the bonding part of the orthodontic bracket having a pre-defined connecting surface for connecting the bonding part to an archwire part of an orthodontic bracket. The system according to the preceding claim wherein the pre-defined connecting surface of the virtual model of the bonding part of the orthodontic bracket has at least one protrusion and/or at least one recess. The system according to least one of claim 14 to claim 16 wherein the virtual model of the bonding part of the orthodontic bracket models, on the bonding surface, an alphanumeric code to identify the tooth to which the bonding surface is to be bonded to, preferably in the form of human-readable recesses and/or protrusions which form alphanumeric symbols. The system according to at least one of claim 14 to claim 17, wherein: the at least one input is configured to receive a virtual model of an archwire part of an orthodontic bracket which models at least one archwire slot running in a mesial-distal direction

27 • based on the virtual model of the bonding part of the orthodontic bracket and on the virtual model of an archwire part of an orthodontic bracket a virtual model of a complete orthodontic bracket modeling at least both, the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket is created by the system, preferably using at least one artificial neuronal network executed by the computing device of the system or an algorithm stored in a memory which is part of the system or which the system can connect to The system according to at least one of claim 15 to claim 18 wherein the virtual model of the archwire part of an orthodontic bracket models a connecting surface in such a way that it matches the pre-defined connecting surface of the bonding part of the orthodontic bracket. The system according to the preceding claim wherein the system creates the virtual model of the complete orthodontic bracket by connecting

• the connecting surface of the virtual model of the archwire part of an orthodontic bracket and

• the pre-defined connecting surface of the bonding part of the orthodontic bracket The system according to at least one of claim 18 to claim 20 wherein the virtual model of the archwire part of an orthodontic bracket is provided in the form of a template having a pre-defined shape. The system according to at least one of claim 14 to claim 21, wherein the system is additionally configured to create virtual models of a plurality of orthodontic

28 brackets, in particular virtual models of a plurality of orthodontic brackets for a complete mandibular and/or maxillary dentition of a patient, wherein:

• the at least one artificial neuronal network is trained to create, for each of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, an individual virtual model of at least a bonding part of an orthodontic bracket, wherein the individual virtual models of the bonding parts of different orthodontic brackets of the plurality of orthodontic brackets differ from each other with respect to their bonding surfaces

• for all of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, a virtual model of the archwire part of an orthodontic bracket is chosen, wherein it is preferred that the chosen virtual model of the archwire part of an orthodontic bracket is the same for all of the orthodontic brackets of the plurality of orthodontic brackets

• for each orthodontic bracket of the plurality of orthodontic brackets the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket are combined by the system to form a virtual model of the complete orthodontic bracket modeling at least both, the individual virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part The system according to the preceding claim wherein a plurality of artificial neuronal networks is provided which are configured to be executed in parallel by the system to create the individual virtual models of the bonding parts of different orthodontic brackets.

29 The system according to at least one of claim 14 to claim 23 wherein the at least one input is configured to receive the virtual tooth model of a patient’s tooth in the form of a scan file, preferably obtained by scanning a dental imprint or an intraoral scan. The system according to the preceding claim wherein the at least one input is configured to receive the scan file in the form of at least one CAD file, preferably at least one STL file or at least one object file, and wherein the at least one artificial neuronal network is trained to read the at least one CAD file. The system according to at least one of claim 14 to claim 25 wherein the system has at least one output which, preferably, is configured to provide the virtual model of at least the bonding part of the orthodontic bracket (s) and/or of the archwire part of an orthodontic bracket and/or of the complete orthodontic bracket in the form of at least one CAD file, preferably at least one STL file or at least one object file. A process for manufacturing at least a bonding part of an orthodontic bracket by using a virtual model of the bonding part of the orthodontic bracket created by a method of at least one of claim 1 to claim 13 or by a system according to at least one of claim 14 to claim 26. The process of the preceding claim wherein the bonding part of the orthodontic bracket is manufactured by additive manufacturing or by removal of material of a blank. The process of one of claim 27 and claim 28 wherein an archwire part of an orthodontic bracket is manufactured based on the virtual model created by a

30 method of one of claim 5 and claim 6 or by a system according to claim 18 and claim 19. The process of the preceding claim wherein the archwire part of the orthodontic bracket is manufactured by at least one of the group comprising: injection molding, additive manufacturing and removal of material of a blank. The process of one of claim 29 and claim 30 wherein a complete orthodontic bracket is manufactured by mechanically joining the bonding part of the orthodontic bracket and the archwire part of the orthodontic bracket. The process of claim 27 wherein a complete orthodontic bracket is manufactured based on the virtual model of a complete orthodontic bracket created by a method of at least one of claim 5 to claim 13 or by a system according to at least one of claim 18 to claim 26. A computer program which, when the program is executed by a computer causes the computer to carry out the method of at least one of claim 1 to claim 13 or to be configured as a system according to at least one of claim 14 to claim 26. A computer-readable medium comprising instructions which, when executed by a computer, causes the computer to carry out the method of at least one of claim 1 to claim 13 or to be configured as a system according to at least one of claim 14 to claim 26. A data carrier signal carrying:

• at least one virtual model created by a method of at least one of claim 1 to claim 13 or by a system according to at least one of claim 14 to claim 26 and/or

31 • the computer program of claim 33

32

Description:
AUTOMATIC CREATION OF A VIRTUAL MODEL OF AT LEAST

A BONDING PART OF AN ORTHODONTIC BRACKET

TECHNICAL FIELD

[0001] In one aspect, the present invention relates to a (computer-implemented) method and a system for creating a virtual model of at least a bonding part of an orthodontic bracket. In another aspect, the present invention relates to a process for manufacturing at least a bonding part of an orthodontic bracket.

BACKGROUND

[0002] A computer-implemented method and a system for creating a virtual model of a complete orthodontic bracket having a lingually situated bonding area for bonding the orthodontic bracket to a specific tooth and a labially situated archwire slot running in a mesial-distal direction is taught in WO 2019/241251 Al. The bonding area of the orthodontic bracket matches a bonding surface of the tooth. A virtual model of the complete bracket including the matching bonding area is created by use of a CAD program. The degree of matching between the bonding area of the orthodontic bracket and the bonding surface of the tooth depends on the skill of a human operator of the CAD program and is time consuming. The only way to manufacture the orthodontic bracket is additive manufacturing which is costly and time consuming. [0003] Another computer-implemented method and a system for creating a virtual model of a complete orthodontic bracket is taught in US 2016/361142 Al. The virtual model of the orthodontic bracket has two parts: One part models a lingual bonding area for bonding the orthodontic bracket to a specific tooth and the other part models the rest of the orthodontic bracket comprising an archwire slot running in a mesial- distal direction. Both virtual model parts are combined electronically to create a virtual model of the complete bracket. The degree of matching between the bonding area of the orthodontic bracket and the bonding surface of the tooth depends on the skill of a human operator of the CAD program and is time consuming.

[0004] What is needed is a method and a system which are able to create a virtual model of at least a bonding part of an orthodontic bracket in a more reliable and faster way, a computer program to cause a computer to carry out such a method or to embody such a system and a process which is able to manufacture at least a bonding part of an orthodontic bracket or a complete orthodontic bracket faster, more cost-efficient and more reliable than the methods and systems of the prior art, as well as a computer-readable medium and a data carrier signal.

SUMMARY OF INVENTION

[0005] It is an object of the invention to provide a method and a system which are able to create a virtual model of at least a bonding part of an orthodontic bracket in a more reliable and faster way.

[0006] It is another object of the invention to provide a process which is able to manufacture at least a bonding part of an orthodontic bracket faster, more costefficient and more reliable than the processes of the prior art. [0007] Still other objects and advantages of the invention will in part be obvious and will in part be apparent from the specification and drawings.

[0008] One object of the disclosure relates to a method of claim 1 and a system according to claim 14 which are able to create a virtual model of at least a bonding part of an orthodontic bracket in a more reliable and faster way than in the prior art due to the use of at least one artificial neuronal network (in the following called in short: ANN) to create the virtual model of at least the bonding part of the orthodontic bracket. This makes the inventive method and system independent of a human operator’s skill, at least with respect to the creation of the virtual model of the bonding part of an orthodontic bracket, and allows for a faster creation of the virtual model.

[0009] Another object of the disclosure relates to a process according to claim 27 which is able to manufacture at least a bonding part of an orthodontic bracket faster, more cost-efficient and more reliable than the processes of the prior art.

[0010] Yet another object of the disclosure relates to a computer program according to claim 33 which, when the program is executed by a computer, causes the computer to carry out the method of claim 1 or any claim dependent thereon or to be configured as a system according to claim 14 or any claim dependent thereon.

[0011] Still another object of the disclosure relates to a computer-readable medium comprising instructions which, when executed by a computer, causes the computer to carry out the method of claim 1 or any claim dependent thereon or to be configured as a system according to claim 14 or any claim dependent thereon.

[0012] Still another object of the disclosure relates to a data carrier signal carrying: at least one virtual model created by a method of at least one of claim 1 to claim 13 or by a system according to at least one of claim 14 to claim 26 and/or the computer program of claim 33

[0013] Embodiments of the invention are defined in the dependent claims.

DESCRIPTION OF EMBODIMENTS

[0014] A computing device suitable for the system can be chosen as is known in the prior art. It can comprise, e.g., one or more CPUs according to the art and a digital memory for saving data necessary for operation of the system. The term CPU encompasses any processor which performs operations on some data such as a central processing unit of a system, a co-processor, a Graphics Processing Unit, a Vision Processing Unit, a Tensor Processing Unit, an FPGA, an ASIC, a Neural Processing Unit, . . .

[0015] Artificial neuronal networks can be of any type known in the art (such as a MfNN, R.NN, LSTM, . . . ). An ANN comprises a plurality of artificial neurons. Each artificial neuron (in the following in short: "neuron") has at least one (usually a plurality of) synapse for obtaining a signal and at least one axon for sending a signal (in some embodiments a single axon can have a plurality of branchings). Usually, each neuron obtains a plurality of signals from other neurons or from an input interface of the neuronal network via a plurality of synapses and sends a single signal to a plurality of other neurons or to an output interface of the neuronal network. A neuron body is arranged between the synapse(s) and the axon(s) and comprises at least an integration function (according to the art) for integrating the obtained signals and an activation function (according to the art) to decide whether a signal is to be sent by this neuron in reaction to the obtained signals. Any activation function of the art can be used such as a step- function, a sigmoid function, . . .

[0016] As is known in the art, the signals obtained via the synapses can be weighted by weight factors (synaptic weights). Individual weight factors can be provided by a weight storage. The weights can be determined as known in the art, e.g., during a training phase by modifying a pre-given set of weights such that a desired result is given by the ANN with a required accuracy. Other known techniques could be used.

[0017] As is known in the art, input signals and weights and output signals do not have to be in the format of scalars but can be defined as vectors or higher-dimensional tensors.

[0018] The term "real time" is defined pursuant to the norm DIN ISO/IEC 2382 as the operation of a computing system in which programs for processing data are always ready for operation in such a way that the processing results are available within a predetermined period of time.

[0019] The computer-implemented method for creating a virtual model of at least a bonding part of an orthodontic bracket, can comprise at least the following steps:

• providing a virtual tooth model of a patient’s tooth, the virtual tooth model modeling at least one surface of the patient’s tooth to which the orthodontic bracket is to be bonded

• determining a bonding area (i.e. , determine a sub-area of the at least one surface of the virtual tooth) of the at least one surface of the virtual tooth model to which the orthodontic bracket is to be bonded

• using at least one artificial neuronal network to create, on basis of said bonding area of the virtual tooth model, at least the virtual model of the bonding part of the orthodontic bracket, the virtual model of the bonding part having a bonding surface which is modeled in such a way that said bonding surface matches the bonding area of the virtual tooth model

[0020] The system for creating a virtual model of at least a bonding part of an orthodontic bracket, can comprise at least:

• at least one input which is configured to receive a virtual tooth model of a patient’s tooth, the virtual tooth model modeling at least one surface of the patient’s tooth to which the orthodontic bracket is to be bonded

• at least one computing device which is configured to execute at least one artificial neuronal network which is trained to

- accept, as input, a bonding area (i.e., a selected sub-area of the at least one surface of the tooth) of the at least one surface of the virtual tooth model to which the orthodontic bracket is to be bonded or, preferably, determine a bonding area (i.e., determine a sub-area of the at least one surface of the virtual tooth) of the at least one surface of the virtual tooth model to which the orthodontic bracket is to be bonded

- create, on basis of said bonding area of the virtual tooth model, the virtual model of at least the bonding part of the orthodontic bracket, the virtual model of the bonding part having a bonding surface which is modeled in such a wav that said bonding surface matches the bonding area of the virtual tooth model

[0021] The method and system allow a very fast creation of the virtual model of at least a bonding part of an orthodontic bracket and/or of a complete orthodontic bracket, preferably in real time.

[0022] The virtual model of the bonding part can be used in a process to manufacture a physical embodiment of at least the bonding part of an orthodontic bracket, preferably at the site of a user (e.g., a dentist or orthodontist) of the method and system, provided there is a manufacturing device for manufacturing a physical embodiment of the bonding part provided at the site. If the user has a physical embodiment of an archwire part of an orthodontic bracket at hand, the user can mechanically combine the archwire part and the bonding part (e.g., glue them together) to obtain a physical embodiment of a complete orthodontic bracket. Alternatively, a virtual model of a complete orthodontic bracket could be used to manufacture a physical embodiment of the complete orthodontic bracket.

[0023] It should be noted that data used as input for the method and system can represent a virtual tooth model of an individual tooth in isolation or can represent a plurality of virtual models of teeth (forming, e.g., at least part of a dental arch). If a plurality of virtual models of teeth is provided as input and the individual teeth are not already marked up as such in the input, the at least one ANN can be trained to recognize which teeth are present in the input.

[0024] The method can use a single ANN or a plurality of ANNs and the computing device can be configured to execute a single ANN or it could be configured to parallelly execute a plurality of ANNs. If a plurality of ANNs is used by the method or configured in the system, in some embodiments, for each tooth present in a human dentition at least one ANN can be trained to recognize that tooth and to create the virtual model of the bonding part of an orthodontic bracket based on the virtual tooth model of that tooth. As each of the ANNs works solely on the virtual model of a single tooth operation of the method and system can be faster which shortens the time necessary to create a plurality of virtual models of orthodontic brackets.

[0025] In some embodiments of the method and system the virtual model of the bonding part of the orthodontic bracket is created by the at least one ANN such that the bonding part has a pre-defined connecting surface. This connecting surface can be use to connect the virtual model of the bonding part of the orthodontic bracket to a virtual model of an archwire part of the orthodontic bracket, as described below, such that the connecting surface can also be present in a manufactured physical embodiment of the bonding part of the orthodontic bracket and can be used to physically connect the manufactured physical embodiment of the bonding part of the orthodontic bracket to a manufactured physical embodiment of an archwire part of the orthodontic bracket.

[0026] In these embodiments of the method and system it can be provided that the pre-defined connecting surface of the virtual model of the bonding part of the orthodontic bracket has at least one protrusion and/or at least one recess which serves to facilitate a physical connection between a manufactured physical embodiment of the bonding part of the orthodontic bracket to a manufactured physical embodiment of the archwire part of the orthodontic bracket, wherein a connecting surface of the virtual model of the archwire part has at least one correspondig recess and/or protrusion.

[0027] In some embodiments of the method and system the virtual model of the bonding part of the orthodontic bracket models, on the bonding surface, an alphanumeric code to identify the tooth to which the bonding surface is to be bonded to, preferably in the form of human- readable recesses and/or protrusions which form alphanumeric symbols. This allows a dentist or orthodondist to see on the manufactured orthodontic bracket itself on which tooth the orthodontic bracket is to be placed.

[0028] In some embodiments of the method and system: a virtual model of an archwire part of an orthodontic bracket is provided (with regard to the system via at least one input which is configured to receive the virtual model) which models at least one archwire slot running in a mesial-distal direction based on the virtual model of the bonding part of the orthodontic bracket and on the virtual model of an archwire part of an orthodontic bracket a virtual model of a complete orthodontic bracket modeling at least both, the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket is created (by the system)

[0029] The virtual model of the archwire part of an orthodontic bracket can, e.g., be obtained from a database in which a single template or different templates for the virtual model of the archwire part of an orthodontic bracket.

[0030] In these embodiments, creation of a virtual model of a complete orthodontic bracket is possible in a very quick way, preferably in real time. In some embodiments the connection can be done in such a way that there is an overlap between the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket. Alternatively, the connection can be done in such a way that the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket directly abut (without an overlap).

[0031] The virtual model of the complete orthodontic bracket can be used in a process to create a physical embodiment of the orthodontic bracket, preferably at the site of a user of the method and system, e.g., a dentist or orthodontist, provided there is a manufacturing device for manufacturing a physical embodiment of the complete orthodontic bracket.

[0032] It is preferred that the virtual model of the archwire part of an orthodontic bracket models a connecting surface in such a way that it matches the pre-defined connecting surface of the bonding part of the orthodontic bracket. This allows easy combination of physical embodiments of an archwire part of an orthodontic bracket and a bonding part of an orthodontic bracket.

[0033] In some embodiments of the method and system creation of the virtual model of the complete orthodontic bracket is done by connecting: the connecting surface of the virtual model of the archwire part of an orthodontic bracket and the pre-defined connecting surface of the bonding part of the orthodontic bracket

[0034] In some embodiments of the method and system the virtual model of the archwire part of an orthodontic bracket is provided in the form of a template having a pre-defined shape (which can, e.g., be accessed via a database). This is preferred if the virtual model of the archwire part and the virtual model of the bonding part are to be connected in such a way that they abut.

[0035] In some embodiments virtual models of a plurality of orthodontic brackets (in particular virtual models of a plurality of orthodontic brackets for a complete mandibular and/or maxillary dentition of a patient) are created by the method and system wherein: for each of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, an individual virtual model of at least a bonding part of an orthodontic bracket is created with the method of at least one of the embodiments described above, wherein the individual virtual models of the bonding parts of different orthodontic brackets of the plurality of orthodontic brackets differ from each other with respect to their bonding surfaces for all of the orthodontic brackets of the plurality of orthodontic brackets, for which virtual models are to be created, a virtual model of the archwire part of an orthodontic bracket is chosen, wherein it is preferred that the chosen virtual model of the archwire part of an orthodontic bracket is the same for all of the orthodontic brackets of the plurality of orthodontic brackets for each orthodontic bracket of the plurality of orthodontic brackets the virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part of an orthodontic bracket are combined to form a virtual model of the complete orthodontic bracket modeling at least both, the individual virtual model of the bonding part of the orthodontic bracket and the virtual model of the archwire part

[0036] This allows for parallel creation of the virtual models of which a virtual model of the complete orthodontic bracket is composed, e.g., for all of the teeth that are to be provided with orthodontic brackets in a dentition of a single patient.

[0037] In these embodiments it is preferred that a plurality of ANNs which work in parallel is used to create the individual virtual models of the bonding parts of different orthodontic brackets to speed up creation of the individual virtual models of the bonding parts of different orthodontic brackets.

[0038] In some embodiments of the method and system the virtual tooth model of a patient’s tooth is provided to the method and the at least one input of the system in the form of a scan file, preferably obtained by scanning a dental imprint or an intraoral scan of a patient’s dentition. [0039] In these embodiments of the method and system the scan file can be provided to the method and the at least one input of the system in the form of at least one CAD file, preferably at least one STL file or at least one object file, and the at least one ANN reads the at least one CAD file. The ANN can be trained to directly recognize the spatial information represented by the at least one CAD file, i.e., without help of a dedicated pre-determined algorithm.

[0040] In some embodiments of the method and system the virtual model of the bonding part of the orthodontic bracket (s) and/or of the archwire part of an orthodontic bracket is provided by the method and an at least one output of the system in the form of at least one CAD file, preferably at least one STL file or at least one object file. The at least one CAD file can be viewed by a human operator using one of the available CAD programs and, if deemed necessary, can be modified by the human operator.

[0041] In some embodiments of the process for manufacturing, at least a bonding part of an orthodontic bracket by using a virtual model of the bonding part of the orthodontic bracket created by a method according to one of the embodiments described above or by a system according to one of the embodiments described above, the bonding part of the orthodontic bracket is manufactured by additive manufacturing or by removal of material of a blank.

[0042] In some embodiments of the process for manufacturing, an archwire part of an orthodontic bracket is manufactured based on the virtual model created by a method of at least one of the embodiments described above or by a system according to at least one of the embodiments described above, or as retrieved from a database.

[0043] In these embodiments it can be provided that the archwire part of the orthodontic bracket is manufactured by at least one of the group comprising: injection molding (this allows cheap mass manufacturing since a plurality of injection molded archwire parts, all having the same shape, can be used for connection with individual bonding parts), additive manufacturing and removal of material of a blank.

[0044] In some embodiments of the process a complete orthodontic bracket is manufactured by mechanically joining the bonding part of the orthodontic bracket and the archwire part of the orthodontic bracket.

[0045] In some embodiments of the process a complete orthodontic bracket is manufactured based on the virtual model of a complete orthodontic bracket created by at least one embodiment of a method as described above or by at least one embodiment of a system as described above.

[0046] The complete orthodontic bracket, or any part thereof, can be formed of ceramic, composite, or metal and is preferably translucent, opaque or fully transparent ceramic or composite material (e.g., aluminium oxide or zirconium oxide ceramics).

[0047] The method, system and process of the invention work in the same way whether: an orthodontic bracket is to be arranged on a lingual side of a tooth (such that the bonding part is a labial part and the archwire part is a lingual part of the orthodontic bracket) or an orthodontic bracket is to be arranged on a labial side of a tooth (such that the bonding part is a lingual part and the archwire part is a labial part of the orthodontic bracket)

[0048] Training of the at least one artificial neuronal network: [0049] Training of the system (training of the method can be done analogously) can be done as is known in the art regarding ANNs, e.g., using supervised training.

[0050] The supervised training can be done in the usual way by providing training data, comparing the output created on the basis of the training data with a target output and adapting the ANNs to better approximate the target output by the created output, e.g., with back-propagation, until a desired degree of accuracy is reached. This is usually done before inference operation of the system. As is known in the art, supervised training can encompass, e.g., supervised learning based on a known outcome where a model is using a labeled set of training data and a known outcome variable or reinforcement learning (reward system).

[0051] In order to train an ANN to recognize a virtual tooth model, in particular different shapes of surfaces of teeth that might be present in a dentition of a patient, provided for example in the form of at least one CAD file, during supervised training, training data can be provided to the system, comprising:

3d representations of teeth of a human dentition; for each tooth a plurality of different possible shapes in different orientations is given, preferably examples having different possible scan defects and/or colors are also given preferably 3d representations showing different (parts of) dentitions, i.e., showing which teeth are adjacent to another are given, preferably (parts of) dentitions having gaps due to missing teeth are also given

[0052] Once an ANN has been trained to recognize a shape of a surface of a tooth it is easy for the ANN to create a matching bonding surface of the bonding part because the shape of a matching bonding surface is simply the negative shape of the surface of the tooth in the area where the bonding part is intended to be bonded to. With exception of the bonding surface, a bonding part can always have the same shape and can, e.g., be loaded from a database.

[0053] The same logic can be used in order to train an ANN to be able to automatically create a virtual model of a complete orthodontic bracket based on the virtual model of the bonding part and a virtual model of an archwire part (stored, e.g., in a database): The ANN can be provided with files showing different bonding parts and files showing different archwire parts as well as files showing complete orthodontic brackets and can then, in a supervised way, be taught to combine bonding parts and archwire parts to obtain the complete orthodontic brackets. Alternatively, as the archwire part and the bonding part can be determined to always have the same connecting surfaces, instead of using an ANN, the creation of the complete orthodontic bracket based on the virtual model of the bonding part and a virtual model of an archwire part could be done by an algorithm, devised by a human programmer, which accepts, as input, a virtual model of a bonding part and a virtual model of an archwire part and provides, as output, a virtual model of the combined virtual models, i.e., a virtual model of a complete orthodontic bracket consisting of the archwire part and the bonding part.

[0054] Supervised training can be stopped once a desired accuracy is achieved by the system.

BRIEF DESCRIPTION OF DRAWINGS

[0055] The Figures show schematic views of:

Figure 1: a system and method according to a first embodiment of the invention

Figure 2: a system and method according to a second embodiment of the invention

Figure 3a and 3b: (a virtual model of) a first orthodontic bracket created by a sys- tem or method according to the invention or manufactured by a process according to an embodiment of the invention on a first tooth and (a virtual model of) a second orthodontic bracket created by a system or method according to the invention or manufactured by a process according to an embodiment of the invention on a second tooth, respectively

Figure 4: an embodiment of (a virtual model of) an orthodontic bracket according to an embodiment of the invention

Figure 5: another embodiment of (a virtual model of) an orthodontic bracket according to an embodiment of the invention

Figure 6: a top view onto a bonding surface of (a virtual model of) an orthodontic bracket according to an embodiment of the invention

Figure 7: a side view of (a virtual model of) an orthodontic bracket according to an embodiment of the invention

Nb., although in the figures orthodontic brackets 1 are shown to be arranged on a labial side of a tooth (such that the bonding part 3 is a lingual part and the archwire part 2 is a labial part of the orthodontic bracket 1), the method, system 1 and process of the invention work in the same way if an orthodontic bracket 1 is to be arranged on a lingual side of a tooth (such that the bonding part 3 is a labial part and the archwire part 2 is a lingual part of the orthodontic bracket 1).

[0056] Figure 1 shows a system 1 and the steps of a method according to a first embodiment of the invention.

[0057] The system 1 comprises at least one input 13 which is configured to receive a virtual tooth model 15, e.g., in the form of at least one CAD file. The input 13 is connected to a computing device 14 which, in this embodiment, is configured to execute in parallel (i.e., are executed at the same time) at least two ANNs arranged sequentially (i.e., the ANN shown at a lower position in Figure 1 receives information from the ANN shown at a higher position in Figure 1). The first ANN is trained to create a virtual model 16 of the bonding part 3 of an orthodontic bracket 1 and to provide this virtual model 16 of the bonding part 3 to the sequentially arranged ANN. This ANN receives as input (e.g., via another input 13 - not shown - or the input 13 shown in the top of the figure) a virtual model 17 of an archwire part 2 of an orthodontic bracket 1 and is trained to create, based on the virtual model 16 of the bonding part and the virtual model 17 of the archwire part 2, a virtual model 18 of a complete orthodontic bracket 1 which can be made available via at least one output 19 of the system 1, e.g., in the form of a CAD file. The virtual model 18 of the complete orthodontic bracket 1 can either: be directly provided to a manufacturing device to manufacture a physical embodiment of the complete orthodontic bracket 1 or can be modified by a human operator using one of the computer programs known in the art and then be provided to a manufacturing device to manufacture a physical embodiment of the complete orthodontic bracket 1

[0058] The system 1 shown in Figure 1 could have a computing device 14 which, in this embodiment, is configured to execute in parallel (i.e., execute at the same time) at least two ANNs arranged sequentially wherein the upper ANN in Figure 1 is trained to create virtual models 16 of different bonding parts 3 in parallel when provided with a virtual tooth model 15 showing a plurality of teeth; and the lower ANN in Figure 1 is trained to create virtual models 18 of different complete orthodontic brackets 1 when provided with different of, which is preferred, the same virtual model 17 of an archwire part 2.

[0059] Figure 2 shows a system 1 and the steps of a method according to a second embodiment of the invention.

[0060] The only difference between the first embodiment shown in Figure 1 and the second embodiment shown in Figure 2 consists in the variation that in the second embodiment the computing device 14 is configured to be executed in parallel (i.e., at the same time) a plurality of ANNs, both, with respect to the upper position in Figure 2 and with respect to the lower position in Figure 2.

[0061] Figure 3a shows an orthodontic bracket 1 (the virtual model 18 looks the same) bonded to a surface of a tooth via its bonding area 3. As can be seen, the bonding area 3 matches a bonding surface 5 of the tooth. Although, in Figure 3a, this can only be seen for the drawing plane of the figure, the match is given with respect to the complete bonding area 3 and the complete bonding surface 5. Comparing Figure 3a and Figure 3b it can be seen that, naturally, the shape of the bonding area 3 is different for a different tooth because the shape of the bonding surface 5 of that tooth is different. Also, it can be seen that for both teeth (which can belong to the dentition of one patient) the same archwire part 2 of the orthodontic brackets 1 can be used. In both orthodontic brackets 1 the archwire part 2 is physically connected to the bonding part 3 by a connecting surface 7 of the archwire part 2 and a connecting surface 8 of the bonding part 3.

[0062] Figure 4 shows a virtual model 1 of a complete orthodontic bracket 1 (a physical embodiment of the orthodontic bracket 1 looks the same) in which the archwire slot 6 modelled in the archwire part 2 can be seen. In this embodiment the connecting surface 7 of the archwire part 2 and the connecting surface 8 of the bonding part 3 are formed as plane areas.

[0063] The embodiment of Figure 5 differs from the one of Figure 4 only in that in this embodiment the connecting surface 7 of the archwire part 2 has a protrusion 9 and the connecting surface 8 of the bonding part 3 has a corresponding recess 10 for facilitating connecting the archwire part 2 and the boinding part 3. Other than shown, there could be a plurality of protrusions 9 and corresponding recesses 10.

[0064] The embodiment of Figure 6 (which can be seen as a top view on the bonding surface 4 of one of the orthodontic brackets 1 of the previous figures or could be a different embodiment) has, as is known in the art, a plurality of recesses 12 for bonding material to facilitate bonding of the orthodontic bracket 1 to a tooth. Of more interest is the alphanumeric code 11 shown inside a dotted line which identifies the orthodontic bracket 1 as being intended to be bonded to tooth number 31 (in this example using the ISO 3950 notation).

[0065] In the embodiment of Figure 7 (which can be seen as a top view on the bonding surface 4 of one of the orthodontic brackets 1 of the previous figures or could be a different embodiment) a curvature of the bonding surface 4 of the bonding part 3 of the orthodontic bracket 1 can be seen. REFERENCE SIGNS LIST orthodontic bracket archwire part of orthodontic bracket bonding part of orthodontic bracket bonding surface of bonding part of orthodontic bracket bonding area of virtual tooth model or real tooth archwire slot connecting surface of (virtual model of) archwire part of orthodontic bracket connecting surface of (virtual model of) bonding part of orthodontic bracket protrusion recess corresponding to protrusion alphanumeric code recess for bonding material input of system computing device virtual tooth model virtual model of bonding part of orthodontic bracket virtual model of archwire part of orthodontic bracket virtual model of complete orthodontic bracket output of system