Mold arch reinforcement and marking for dental appliance manufacture
By introducing arch and beam designs into dental instrument molds, combined with marking and identifier features, the problems of mold damage and identifier errors are solved, enabling efficient and low-consumption dental instrument production.
Patent Information
- Application Number
- CN202380032399.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-01-30
- Filing Date
- 2023-01-31
- Publication Date
- 2024-11-22
AI Technical Summary
Existing dental instrument molds are prone to damage during manufacturing, leading to production failures, defective dental instruments and equipment, and conventional identification methods are material and time-consuming and prone to errors.
The design employs a mold that includes the dental arch and beams. The beams are equipped with marking sections and identifier features. By combining machine learning models to read the identifiers, material consumption is reduced and production efficiency is improved.
Significantly reduces mold damage, increases production volume and quality, reduces material consumption, avoids reading errors, provides machine- and human-readable markings, and enhances the freedom of mold placement on equipment.
Smart Images

Figure CN119012982A_ABST
Abstract
Description
[0001] The technical field is related to the field of manufacturing, and in particular, to mold arch reinforcement and marking for dental appliance manufacturing. Background Art
[0002] The system produces a mold for forming a dental appliance to be used in corrective dentistry or orthodontic treatment. Dental appliances (such as palatal expanders, dental braces, and accessory forming templates) are used to perform specific functions according to a corresponding treatment plan. For example, an incremental palatal expander may include a set of dental appliances that fit into the patient's palate and are used to expand the patient's palate according to a treatment plan. The braces may include a polymer dental appliance that includes a tooth receiving cavity to receive and reposition the patient's teeth to correct a malocclusion. A dental accessory template may include a dental appliance that is shaped to fit the patient's dentition and allow an accessory (e.g., an incorporated accessory, a preformed accessory, etc.) to be placed into the patient's dentition. Summary of the invention
[0003] Some example implementations of the disclosure are summarized herein.
[0004] In a first embodiment, a mold is used for a dental appliance. The mold includes: a dental arch portion associated with a plurality of teeth of a user, the dental arch portion including a first distal portion, a second distal portion, and an incisor portion arranged between the first distal portion and the second distal portion; and a beam extending from the first distal portion to the second distal portion to reinforce the mold, wherein the beam includes a marking portion forming a mark for identifying the mold.
[0005] The second embodiment may further expand the first embodiment. In the second embodiment, the marking comprises through holes from the upper surface of the marking portion to the lower surface of the marking portion, wherein the through holes form digits of the identifier of the marking.
[0006] The third embodiment may further expand upon the first or second embodiment. In the third embodiment, the mold further comprises: a pick and place component coupled to the beam, wherein the pick and place component is configured to be fixed by the dental appliance manufacturing apparatus.
[0007] The fourth embodiment may further expand any one of the first to third embodiments. In the fourth embodiment, the beam comprises a flat portion configured to engage with a locking mechanism of the plate to secure the mould to the plate in the z-direction.
[0008] The fifth embodiment may further expand any one of the first to fourth embodiments. In the fifth embodiment, the mold further comprises a plurality of identifier features extending from one or more side walls of the beam for automatically identifying the mold.
[0009] The sixth embodiment can further expand any one of the first to fifth embodiments. In the sixth embodiment, the beam includes a reinforcement portion extending from a first distal portion of the dental arch portion to a second distal portion of the dental arch portion, wherein the reinforcement portion is configured to reinforce the beam, and wherein the reinforcement portion has a greater thickness than the marking portion.
[0010] The seventh embodiment may further expand any one of the first to sixth embodiments. In the seventh embodiment, the mold further includes: a first chamfer disposed between the marking portion and the first distal end portion of the dental arch portion; and a second chamfer disposed between the marking portion and the second distal end portion of the dental arch portion.
[0011] In an eighth embodiment, a method includes: determining a position of a beam of a mold relative to a dental arch portion of the mold, the dental arch portion including a first distal portion, a second distal portion, and an incisor portion arranged between the first distal portion and the second distal portion, wherein the beam extends from the first distal portion to the second distal portion; determining a layout of identifiers to be formed on the beam between the first distal portion and the second distal portion; and determining a shape of the beam to be attached to the dental arch portion of the mold, wherein the mold is formed based on the position of the beam, the layout of the identifiers, and the shape of the beam.
[0012] The ninth embodiment may further expand the eighth embodiment. In the ninth embodiment, determining the position of the beam includes: identifying a plurality of transformations of the mold, wherein each of the plurality of transformations includes a corresponding position of the beam relative to the dental arch portion; slicing a three-dimensional (3D) model of the dental arch portion to generate a two-dimensional (2D) contour of the 3D model; and selecting a first transformation of the plurality of transformations based on the 2D contour, wherein the first transformation includes the position of the beam relative to the dental arch portion.
[0013] The tenth embodiment may further expand the eighth or ninth embodiment. In the tenth embodiment, selecting the first transformation includes determining that a width distance between distal ends of the beam from the first distal portion to the second distal portion in the first transformation satisfies a threshold distance.
[0014] The eleventh embodiment can further expand any one of the eighth to tenth embodiments. In the eleventh embodiment, selecting the first transformation includes: determining that in the first transformation the beam is located between the incisor portion of the dental arch portion and a line intersecting the first distal end of the first distal portion and the second distal end of the second distal portion; and determining that in the first transformation a length distance between the beam and the line satisfies a threshold distance.
[0015] A twelfth embodiment can further expand any one of the eighth to eleventh embodiments. In the twelfth embodiment, selecting the first transformation includes: determining that a feature offset distance between a pick and place component of the beam and a corresponding identifier feature extending from the beam in the first transformation satisfies a threshold distance, wherein the feature offset distance provides clearance for the dental appliance manufacturing equipment to fix the pick and place component to move the mold.
[0016] The thirteenth embodiment may further expand any one of the eighth to twelfth embodiments. In the thirteenth embodiment, selecting the first transformation includes determining that the identifier to be formed in the beam is not blocked by the geometry of the mold.
[0017] The fourteenth embodiment may further expand any one of the eighth to thirteenth embodiments. In the fourteenth embodiment, the selection of the first transformation is further based on determining that a gap distance between a trimming line of the dental arch portion and a connection between the dental arch portion and the beam in the first transformation satisfies a threshold distance.
[0018] The fifteenth embodiment can further expand any one of the eighth to fourteenth embodiments. In the fifteenth embodiment, determining the layout of the identifier to be formed on the beam includes: identifying a predefined format of a marking portion of the beam; determining a number of marks to be formed in the marking portion of the beam based on the identifier; and determining a plurality of identifier features to extend from a side wall of the beam based on the identifier, wherein the identifier features form a binary code to be decoded to verify the identifier determined from the number of marks.
[0019] The sixteenth embodiment can further expand any one of the eighth to fifteenth embodiments. In the sixteenth embodiment, the shape of the beam includes: a substantially flat marking portion of the beam, the substantially flat marking portion forming stencil digits cut through the beam based on the identifier; and a plurality of identifier features extending from the side wall of the beam.
[0020] The seventeenth embodiment may further expand any one of the eighth to sixteenth embodiments. In the seventeenth embodiment, the shape of the beam includes: a reinforcement portion of the beam configured to prevent deformation of the beam, wherein the reinforcement portion of the beam has a greater thickness than the substantially flat marking portion of the beam.
[0021] The eighteenth embodiment can further expand any one of the eighth to seventeenth embodiments. In the eighteenth embodiment, the shape of the beam includes a chamfer between the marked portion and the dental arch portion of the beam to prevent the beam from breaking, wherein the chamfer is used to provide a gap distance between the beam and the trimming line of the mold.
[0022] In a nineteenth embodiment, a non-transitory machine-readable storage medium stores instructions that, when executed, cause a processing device to perform a method according to any one of the eighth to eighteenth embodiments.
[0023] In a twentieth embodiment, a system includes: a memory; and a processing device coupled to the memory, the processing device being configured to execute the method according to any one of the eighth to eighteenth embodiments.
[0024] In a twenty-first embodiment, a method for designing a virtual three-dimensional (3D) model of a mold for a dental appliance includes: determining an identifier associated with the mold, wherein the mold includes a dental arch portion associated with a plurality of teeth of a user, wherein the dental arch portion includes a first distal portion, a second distal portion, and an incisor portion disposed between the first distal portion and the second distal portion; determining a mark to be formed in a mark portion of a beam of the mold based on the identifier; and determining placement of the beam, wherein the beam extends from the first distal portion to the second distal portion in the virtual 3D model of the mold.
[0025] The twenty-second embodiment can further expand the twenty-first embodiment. In the twenty-second embodiment, determining the identifier includes: determining a patient identifier associated with the mold; determining control information associated with the mold; determining a material of a dental appliance to be formed by the mold; determining a jaw associated with the mold; determining a material-jaw identifier based on the material and the jaw; and determining a phase identifier associated with the mold, wherein the identifier is based on the patient identifier, the control information, the material-jaw identifier, and the phase identifier.
[0026] The twenty-third embodiment can further expand the twenty-first or twenty-second embodiment. In the twenty-third embodiment: the mark is a cutting mark including a plurality of numbers; a first subset of the plurality of numbers is associated with a patient identifier; a second subset of the plurality of numbers is associated with control information; a third subset of the plurality of numbers is associated with a material-jaw identifier; and a fourth subset of the plurality of numbers is associated with a stage identifier.
[0027] The twenty-fourth embodiment can further expand any one of the twenty-first to twenty-third embodiments. In the twenty-fourth embodiment, the method further includes: determining a plurality of identifier features based on the patient identifier, the material-jaw identifier, and the stage identifier; and dividing the plurality of identifier features into a first subset and a second subset, wherein the first subset of the plurality of identifier features is to be placed on the first side wall of the beam, and the second subset of the plurality of identifier features is to be formed on the second side wall of the beam.
[0028] The twenty-fifth embodiment can further expand any one of the twenty-first to twenty-fourth embodiments. In the twenty-fifth embodiment, the method further includes: determining a location of a pick-and-place component on the beam of the mold within a threshold distance of the center of the beam; and determining a feature offset associated with the location of the pick-and-place component, wherein the first subset and the second subset are to be formed based on the feature offset.
[0029] The twenty-sixth embodiment can further expand any one of the twenty-first to twenty-fifth embodiments. In the twenty-sixth embodiment: a first control pin and a second control pin will be formed on the first side wall of the beam; a first subset of the plurality of identifier features will extend from the first side wall of the beam between the first control pin and the second control pin; a third control pin and a fourth control pin will be formed on the second side wall of the beam; and a second subset of the plurality of identifier features will extend from the second side wall of the beam between the third control pin and the fourth control pin.
[0030] The twenty-seventh embodiment may further expand any one of the twenty-first to twenty-sixth embodiments. In the twenty-seventh embodiment, the method further comprises: determining a type of dental appliance to be formed by the mold, wherein a type mark is formed on a pick and place component of the mold based on the type of dental appliance.
[0031] In a twenty-eighth embodiment, a non-transitory machine-readable storage medium stores instructions that, when executed, cause a processing device to perform a method according to any one of the twenty-first to twenty-seventh embodiments.
[0032] In a twenty-ninth embodiment, a system includes: a memory; and a processing device coupled to the memory, the processing device being configured to execute a method according to any one of the twenty-first to twenty-seventh embodiments.
[0033] In a thirtieth embodiment, a method of identifying a mold of a dental arch includes receiving an image of the mold of the dental arch, performing a first analysis of the image, determining, based on the first analysis, an area of the image corresponding to a mark formed by a marking portion of a beam of the mold, the mark forming an identifier having a plurality of digits, performing a second analysis of the area of the image, and identifying each of the plurality of digits of the identifier based on the second analysis of the area of the image.
[0034] The thirty-first embodiment may further extend the thirtieth embodiment. In the thirty-first embodiment, performing the first analysis includes matching the template with the marked portion in the image.
[0035] The thirty-second embodiment can further expand the thirtieth or thirty-first embodiment. In the thirty-second embodiment, the method further includes: receiving a historical image of a historical mark of a historical mold, each of the historical marks being formed in a corresponding mark portion of a corresponding beam of a corresponding historical mold; receiving a historical region associated with the historical image; and training a machine learning model using a training input including the historical image and a target output including the historical region to generate a trained machine learning model, wherein performing the first analysis includes providing the image as an input to the trained machine learning model.
[0036] The thirty-third embodiment can further expand any one of the thirtieth to thirty-second embodiments. In the thirty-third embodiment, performing a first analysis on the image includes: providing the image as an input to a trained machine learning model, the trained machine learning model being trained to output the boundary of the region; and receiving an output indicating the region of the image from the trained machine learning model.
[0037] The thirty-fourth embodiment can further expand any one of the thirtieth to thirty-third embodiments. In the thirty-fourth embodiment, the method further includes: receiving a historical sub-region of a historical image of a historical mark of a historical mold, each of the historical marks being formed in a corresponding mark portion of a corresponding beam of a corresponding historical mold, each of the historical sub-regions corresponding to a historical number of the historical mark; receiving a historical number of a historical identifier associated with the historical sub-region; and training a machine learning model using a training input including the historical sub-region and a target output including the historical number to generate a trained machine learning model, wherein performing the second analysis includes providing a sub-region of the region of the image as an input to the trained machine learning model.
[0038] The thirty-fifth embodiment can further expand any one of the thirtieth to thirty-fourth embodiments. In the thirty-fourth embodiment, performing the second analysis includes: identifying sub-regions of the image based on the region, wherein each sub-region corresponds to a corresponding digit of the identifier of the mold; providing the sub-regions of the image as input to a trained machine learning model, the trained machine learning model being trained to output multiple digits of the identifier; and receiving an output indicating the multiple digits of the identifier from the trained machine learning model.
[0039] The thirty-sixth embodiment can further expand any one of the thirtieth to thirty-fifth embodiments. In the thirty-sixth embodiment, the method further includes: performing a third analysis of the region of the image; based on the third analysis of the region of the image, identifying the identifier feature presence data of the beam; and verifying the identifier based on the identifier feature presence data of the beam.
[0040] The thirty-seventh embodiment can further expand the thirty-sixth embodiment. In the thirty-seventh embodiment, the method further includes: receiving historical sub-regions of the historical image of the historical beam of the historical mold, each of the historical sub-regions corresponding to the historical potential identifier beam of the historical mold; receiving historical identifier feature presence data associated with the historical sub-region of the historical image; and training the machine learning model using the training input including the historical sub-region and the target output including the historical identifier feature presence data to generate a trained machine learning model, wherein performing the third analysis includes providing the sub-region of the image as input to the trained machine learning model.
[0041] The thirty-eighth embodiment can further expand the thirty-sixth or thirty-seventh embodiment. In the thirty-eighth embodiment, performing the third analysis includes: identifying a portion of the image corresponding to a pick-and-place component of a beam of the mold; identifying a control feature on a side wall of the beam in the image; identifying an area between the control features on either side of the portion of the image; identifying sub-regions of the image based on the area, wherein each sub-region corresponds to a potential identifier feature of the beam; providing the sub-regions of the image as input to a trained machine learning model, the trained machine learning model being trained to output identifier feature presence data; and receiving an output indicating the identifier feature presence data from the trained machine learning model.
[0042] In a thirty-ninth embodiment, a non-transitory machine-readable storage medium stores instructions that, when executed, cause a processing device to perform a method according to any one of the thirtieth to thirty-eighth embodiments.
[0043] In a fortieth embodiment, a system includes: a memory; and a processing device coupled to the memory, the processing device being configured to execute the method according to any one of the thirtieth to thirty-eighth embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The invention is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings.
[0045] Figures 1A to 1E A mold for producing a dental appliance is shown according to some embodiments.
[0046] FIG. 2A to FIG. 2B A mold for producing a dental appliance is shown according to some embodiments.
[0047] FIG. 3A to FIG. 3C Shown is a portion of a mold for producing a dental appliance according to some embodiments.
[0048] Figure 4A is a block diagram illustrating an exemplary system architecture in accordance with certain embodiments.
[0049] Figure 4B is an example dataset generator for creating a dataset for a machine learning model according to certain embodiments.
[0050] Figure 4C is a block diagram illustrating determining prediction data according to certain embodiments.
[0051] FIG. 5A to FIG. 5K is a flow chart of a method associated with a mold for producing a dental appliance, according to certain embodiments.
[0052] Figure 6 A block diagram of an example computing device is shown in accordance with some embodiments.
[0053] Fig. 7A A tooth repositioning appliance according to certain embodiments is shown.
[0054] Figure 7B A tooth repositioning system according to certain embodiments is shown.
[0055] Figure 7C A method of orthodontic treatment using multiple appliances is shown in accordance with certain embodiments.
[0056] Figure 8 A method for designing an orthodontic appliance according to certain embodiments is shown.
[0057] Fig. 9 A method for digitally planning orthodontic treatment according to certain embodiments is shown. DETAILED DESCRIPTION
[0058] This article describes techniques related to mold arch reinforcement and marking for dental appliance manufacturing.
[0059] Manufacturing systems are used to produce products. Some manufacturing systems use molds to produce products. For example, some dental appliance systems use molds (e.g., molds of jaws, molds associated with a user's teeth, molds associated with a user's dental arch, etc.) to form dental appliances. Dental appliances can include one or more incremental palatal expanders, orthodontic appliances (e.g., dental appliances with or without mandibular advancement structures and / or other structures), sleep apnea treatment devices, dental attachment templates, attachment forming templates (e.g., appliances for placing attachments that engage with attachment wells and / or other structures in an appliance to apply repositioning forces on a patient's dentition), including areas containing prefabricated (e.g., 3D printed) attachments, and / or other dental appliances.
[0060] During the manufacture of dental appliances, molds may be made and the molds may go through several production stages. Some molds become damaged during this process. Damaged molds lead to failed dental appliance production, defective dental appliances, damage to dental appliance manufacturing equipment, and / or a shortened dental appliance life.
[0061] The mold may go through several production stages to produce a dental appliance. The mold may include several alignment and support features, each of which may be used for mold reinforcement, for pick and place processing of the mold, as a fixture used by a trimming and thermoforming machine, and to provide one of a machine-readable mark and a human-readable mark. These multiple features included in conventional molds consume material and processing time in their manufacture. In addition, these features limit the possible placement of the mold on the dental appliance manufacturing equipment.
[0062] In addition, the mold is identified at different stages of production. Conventional systems add human-readable identifiers to the mold by adding additional materials to the sides of the mold to form a protruding identifier and adding a coating (e.g., ink, paint, etc.) to the protruding identifier so that the protruding identifier can be read by a user. Conventional systems can also add machine-readable identifiers to the mold by adding additional materials and coatings (e.g., ink, paint, etc.) to the mold in the form of a digital matrix to be read by a machine. Conventional techniques for adding human and machine-readable identifiers to molds use additional materials and coatings other than those used for the mold body, use additive manufacturing processes, and are prone to errors. Conventional identifiers may be partially blocked by the mold and / or dental appliance. Conventional solutions may interfere with dental appliance manufacturing and result in defective dental appliances. Conventional solutions may cause errors in the reading of identifiers.
[0063] Embodiments of the devices, systems, components, and methods described herein address at least some of the above-noted deficiencies of conventional systems.
[0064] In some embodiments, the mold includes a dental arch portion and a beam. The dental arch portion is associated with the user's teeth (e.g., the user's dental arch, the user's upper jaw or lower jaw). The dental arch portion may include a first distal portion (e.g., a first molar), a second distal portion (e.g., a second molar), and an incisor portion (e.g., an incisor) arranged between the first distal portion and the second distal portion. The beam extends from the first distal portion to the second distal portion. The beam includes a marking portion arranged between the first distal portion and the second distal portion. The marking portion forms a mark (e.g., a cutting mark) for identifying the mold. In some embodiments, pins, protrusions, pits, recesses, and / or other features extend from the beam and / or are included in the beam to form a machine-readable identifier for identifying or verifying an identifier of the mold.
[0065] In embodiments, the beams can be configured to perform functions that are traditionally performed by a number of different features. For example, the beams can provide mold reinforcement, allow for pick and place processing of the mold via the beams, serve as a fixture for use by trimming and thermoforming machines, and provide machine-readable and human-readable markings. Each mold can be designed with a custom beam that is sized and / or positioned on the mold to provide both a threshold level of reinforcement for the mold and sufficient area to accommodate machine- and human-readable markings, and / or maximize placement options for the mold on dental appliance manufacturing equipment.
[0066] A method may include determining an identifier for a mold. A method may include determining locations of components of a mold to manufacture the mold. A method may include forming a mold including an identifier (e.g., in the form of a cut mark, in the form of a pin). A method may include reading the identifier from the mold. In some embodiments, the identifier may be read from the mold using one or more trained machine learning models.
[0067] Compared with traditional dental appliance manufacturing systems, various aspects of the present disclosure produce technical advantages of significantly reducing wasted materials, significantly increasing production volume and significantly improving quality. The mold of the present disclosure includes a beam that provides reinforcement of the mold compared to conventional molds. This allows the mold of the present disclosure to avoid failures in dental appliance production, defective dental appliances, damage to dental appliance equipment, and reduced life of dental appliances of conventional solutions. The identifier of the present disclosure (e.g., cutting marks and / or pins) avoids additional materials, additional processing, and additional errors of the identifier of the conventional solution. The method of determining an identifier for a mold, the method of determining the position of a component of a mold, the method of forming a mold, and the method of reading an identifier from a mold of the present disclosure avoid errors in reading identifiers, manufacturing errors, consumption of additional materials, consumption of additional time, and additional processing of performing conventional solutions. Compared to conventional molds for dental appliances, the molds of the present disclosure reduce the percentage of damaged molds, reduce material consumption, provide additional degrees of freedom for mold placement, provide a secure grip for pick and place robots to grasp the mold, provide fixtures for use by trimming and thermoforming machines, and provide a surface for mold marking (e.g., both human-readable and machine-readable).
[0068] While some embodiments of the present disclosure describe molds for producing dental appliances, in other embodiments, other types of objects may be formed and other processes may be performed by the methods of the present disclosure.
[0069] Figures 1A to 1EA mold 100 for producing a dental appliance according to some embodiments is shown. The mold 100 can be produced using a rapid prototyping device (e.g., a 3D printer), which can employ additive manufacturing techniques (e.g., stereolithography) and / or subtractive manufacturing techniques (e.g., milling). The printing of a mold for a dental appliance is discussed in more detail below.
[0070] The mold 100 may be placed on a plate 180 (eg, a platform). The plate 180 may have a substantially horizontal upper surface, and the mold 100 may have a substantially horizontal lower surface (eg, placed on the substantially horizontal upper surface of the plate 180). Figure 1A 180. The mold 100 may be lifted from the plate 180 and placed onto the plate 180 in the positive z-direction and the negative z-direction. The plate 180 may include one or more protruding members 182 and a locking mechanism 184.
[0071] The mold 100 includes a dental arch portion 110. The dental arch portion 110 can be associated with the patient's teeth (e.g., is a representation of the teeth and a portion of the gums of the patient's dental arch). A dental appliance can be formed on the dental arch portion 110, and then the dental appliance can be used on the patient's dental arch at a later time. The dental arch portion 110 includes a distal portion 112A, a distal portion 112B, and an incisor portion 114. The incisor portion 114 is located between the distal portions 112A-B. The distal portions 112A-B may include the molars of the dental arch, and the incisor portion 114 may include the incisors of the dental arch.
[0072] The mold 100 includes a beam 120. The beam 120 extends between the distal portion 112A and the distal portion 112B. The beam 120 includes a marking portion 122 (e.g., a substantially flat marking portion) placed between the distal portion 112A and the distal portion 112B. The marking portion 122 forms a mark for identifying the mold 100. In some embodiments, the mark is a cutting mark extending through the marking portion 122 (e.g., the mark includes a through hole from the upper surface of the marking portion to the lower surface of the marking portion, wherein the through hole forms a number). In some embodiments, the mark is recessed in the marking portion 122. The mark (e.g., the cutting mark) is human-readable and / or machine-readable. The mark can be a series of numbers (e.g., a number) that form an identifier or include a series of numbers (e.g., a number) that form an identifier. In some embodiments, the beam 120 combines fixtures for pick and place operations (e.g., pick and place components 130), fixtures used by trimming and thermoforming machines (e.g., cut marks and / or identifier features 140 formed in the marking portion 122), surfaces for human and / or machine readable markings (e.g., cut marks), and mold reinforcements in one piece or component. The beam can additionally or alternatively be adapted for different purposes, such as additional identifier components 132 (e.g., data matrix portions). The beam 120 can be parameterized and adjusted for use by dental appliance manufacturing equipment, as described in more detail below.
[0073] In an embodiment, when the mold 100 of the jaw is manufactured (e.g., 3D printed), the mold 100 of the jaw is marked with a patient identifier (PIN) and a stage identifier (e.g., a stage number). In subsequent operations (e.g., thermoforming and edge cutting of dental appliances), the mold 100 can be appropriately identified to perform corresponding patient ID and stage number related processing operations, such as to determine appropriate trimming instructions for trimming the mold. In some embodiments, the mark (e.g., cut mark) can be formed by an engraved font symbol. The mark (e.g., cut mark) can be readable by both a human and a machine vision system, or only by a human or only by a machine vision system. Additional control information can be provided in the form of additional symbols in the mark (e.g., cut mark) and pins, pits, or other features that can be identified by a machine vision system. The mark (e.g., cut mark) and / or identifier feature 140 can replace the numbers printed on the side of a conventional mold and the data matrix code coupled to the mold for a conventional machine vision system. The identifier feature 140 may include one or more pins, protrusions, recesses, grooves, and / or other types of features that can be read by a machine to determine a value (e.g., an identifier for the mold 100). The mold 100 may have reduced material consumption compared to conventional solutions. The mold 100 may combine both human-readable indicia and machine-readable indicia in one component of the mold 100 (e.g., the beam 120).
[0074] In some embodiments, the mold 100 includes a pick-and-place component 130 configured to be fixed by a dental appliance manufacturing device. The dental appliance manufacturing device (e.g., a robot) can fix the mold 100 via the pick-and-place component 130 to lift the mold 100 and place the mold 100 in a position for a dental appliance manufacturing process. The pick-and-place component 130 can be coupled to the beam 120 (e.g., fixed to the beam 120, adjacent to the beam 120, integral with the beam 120, as a part of the beam 120). The height of the pick-and-place component 130 (e.g., along the z-direction) is greater than the height of the beam 120, so that the dental appliance manufacturing device can fix the pick-and-place component 130. In some embodiments, the height of the pick-and-place component 130 (e.g., along the z-direction) is greater than the height of the protruding component 182 of the plate 180.
[0075] In some embodiments, the beam 120 includes one or more reinforcement portions 124 extending from the distal portion 112A to the distal portion 112B to reinforce the beam 120 (e.g., between the distal portion 112A and the distal portion 112B along the x-direction). Each reinforcement portion 124 may have a greater thickness (e.g., height along the z-direction) than the marking portion 122. In some embodiments, each reinforcement portion 124 may include a stronger material (e.g., metal) than the marking portion 122. In some embodiments, each reinforcement portion 124 may be made of the same material as the marking portion 122. The reinforcement portion 124A may include a first side wall of the beam 120, and the reinforcement portion 124B may include a second side wall of the beam 120. The reinforcement portion 124 may reinforce the mold 100 while minimizing the material used to manufacture the beam 120 and while minimizing the material to be removed from the marking portion 122 to form a mark (e.g., a cutting mark).
[0076] In some embodiments, the beam 120 includes a flat portion 126 (e.g., a flat portion of the reinforcing portion 124A) that is configured to engage with a locking mechanism 184 of the plate 180. The locking mechanism 184 can have a fixed portion 186 fixed to the plate 180 and a pivoting portion 188 pivotally coupled to the fixed portion 186. The pivoting portion 188 can pivot to overlap with the flat portion 126 of the beam 120 of the mold 100. The fixed portion 186 and the protruding members 182A-B of the locking mechanism 184 can fix the mold 100 in the x-direction and the y-direction, and the pivoting portion 188 of the locking mechanism 184 can fix the mold 100 in the z-direction (e.g., in a thermoforming chamber). Figure 1B and Figure 1E The unlocked position of the pivot portion 188 is shown, which does not overlap the beam 120 and allows the mold 100 to be placed on and / or removed from the plate 180 . Figure 1B and Figure 1E Also shown is the locked position of the pivot portion 188, which overlaps the beam 120 to prevent the mold 100 from being removed from the plate 180. Figure 1E As shown, the fixed portion 186 can include a thicker portion (e.g., closer to the distal portion 112B) that prevents the pivot portion 188 from pivoting in a first direction (e.g., to the right from the locked position), and can have a thinner portion (e.g., closer to the distal portion 112A) that allows the pivot portion 188 to pivot in a second direction (e.g., to the left from the locked position). The dental appliance manufacturing device (e.g., a robot) can be configured to move the pivot portion 188 to the locked position and the unlocked position.
[0077] In some embodiments, mold 100 (e.g., beam 120) includes an identifier feature 140 for automatic identification (e.g., machine-readable identification) of mold 100. In one embodiment, identifier feature 140 extends from a side wall of beam 120 (e.g., from reinforcement portion 124). In some embodiments, beam 120 includes: control pin 142A (or other control feature), which may be a pin or other feature proximate reinforcement portion 124A closest to distal portion 112A; control pin 142B (or other control feature), which is a pin or feature proximate reinforcement portion 124A closest to distal portion 112B; control pin 142C (or other control feature), which is a pin or other feature proximate reinforcement portion 124B closest to distal portion 112A; and control pin 142D (or other control feature), which is a pin or other feature proximate reinforcement portion 124B closest to distal portion 112B. The identifier features 140 may be identified based on the control pins 142 or features (e.g., a first subset of the identifier features 140 are located between control pins 142A-B, and a second subset of the identifier features 140 are located between control pins 142C-D). The identifier features 140 may form a bar code (e.g., 0 for no pin, 1 for a pin) that is machine readable to determine an identifier for the mold 100 (which may be the same identifier as in a mark (e.g., a cut mark) formed by the marking portion 122).
[0078] In some embodiments, mold 100 includes chamfer 128A disposed between marking portion 122 and distal portion 112A and chamfer 128B disposed between marking portion 122 and distal portion 112B. Each chamfer 128 can be inclined (e.g., increase in thickness) from marking portion 122 toward distal portion 112. Each chamfer 128 can be shaped to provide a gap between chamfer 128 and a cut line along mold 100 (e.g., a trim line for trimming a dental appliance from mold 100).
[0079] In some embodiments, the mold 100 (e.g., the beam 120) includes an identifier component 132 coupled to the beam 120 (e.g., attached to a pick and place component 130 that is attached to or integral with the beam 120). In some embodiments, the identifier component 132 can be a digital matrix. The identifier component 132 can be used to verify the markings (e.g., cut marks) formed in the marking portion 122 and the identifier feature 140. The identifier component 132 can be removed before performing the dental appliance manufacturing process.
[0080] like Figure 1C As shown, the mold 100 can have a cut line 190 at which a dental appliance device (e.g., a cutting device, a trimming device) cuts (e.g., trims) the dental appliance from the mold 100. A clearance line 192 is located at a threshold distance 194 from the cut line 190. The chamfer 128 can be formed not to pass through the clearance line 192 to provide a safe clearance for trimming the dental appliance from the mold 100.
[0081] FIG. 2A to FIG. 2B A mold 100 for producing a dental appliance is shown according to some embodiments.
[0082] Figure 2A A two-dimensional (2D) outline 200 of a three-dimensional (3D) model of a dental arch portion 110 of a mold 100 is shown according to some embodiments. Figure 5A As described in, the translation of the mold can include a corresponding position of the beam 120 relative to the dental arch portion 110. In different transformations, the dental arch portion 110 can be at different distances or angles from the beam 120. The dental arch portion 110 can have different heights in different transformations (e.g., the dental arch portion 110 includes different amounts of gingival area in different transformations). The bottom surface of the dental arch portion 110 can be at different angles relative to the upper surface of the dental arch portion 110 in different transformations (e.g., the gingival area is cut at different angles to form the bottom surface of the dental arch portion 110 in different transformations). In some embodiments, the beam has different lengths or different chamfers 128 in different transformations of the mold. A 2D profile can be created for different transformations of the mold 100 (e.g., the mold 100 of the dental arch portion 110).
[0083] Figure 2B Threshold distances 210-230 of the mold 100 are shown according to some embodiments. The 2D profile 200 of the mold 100 is used to determine different transformations of the mold 100 (e.g., the configuration of the beam 120 and the dental arch portion 110). The distance of each of the transformations can be compared to the threshold distance, such as Figure 5B Described in .
[0084] The width distance between the distal ends of the beams 120 of the mold 100 (e.g., each of the variations of the mold) can be compared to a threshold distance 210 (e.g., the width distance of the marking portion 122 of the beam 120). The threshold distance 210 can be the minimum width of the beam to fit the marking formed by the marking portion 122 of the beam 120.
[0085] The length distance between the beam 120 and the line 240 is compared to the threshold distance 220, where the line 240 intersects the first distal end of the first distal portion 112A of the dental arch portion 110 (e.g., corresponding to the posterior molars on the first side of the dental arch) and the second distal end of the second distal portion 112B (e.g., corresponding to the posterior molars on the second side of the dental arch). The threshold distance 220 can be about 0 to about 15 mm. The beam 120 is located between the incisor portion 112C and the line 240.
[0086] The feature offset distance between the identifier features 140 on either side of the pick and place component 130 meets the threshold distance 230 (e.g., about 4.5 mm). This provides an offset for the dental appliance device to secure the pick and place component 130 so that the mold 100 can be moved without contacting the identifier features 140.
[0087] like Figure 5A As described, the translation of the mold is selected based on the 2D contours of the 3D model (e.g., the position of the beam relative to the dental arch position). Figure 5B As shown, the translation of the mold (eg, the position of the beam relative to the dental arch position) is further selected based on the distance of the mold satisfying a threshold distance (eg, threshold distances 210 - 230 ).
[0088] FIG. 3A to FIG. 3C A portion of a mold 100 for producing a dental appliance is shown according to some embodiments.
[0089] Figure 3AA block diagram of a beam 120 and a pick and place component 130 of a mold 100 according to certain embodiments is shown. The beam 120 includes a marking portion 122 that forms a mark (e.g., a cut mark). The mark (e.g., a cut mark) includes an identifier consisting of a number. In some embodiments, the first 7-8 digits of the mark (e.g., a cut mark) are a patient identifier (PIN) 310, the next 1-2 digits are control information 312, the next digit is a material-jaw identifier 314, and the last 2 digits are a stage identifier 316. Each patient can have a specific PIN 310 (e.g., a specific number unique to that patient). The patient can have different molds, each with a corresponding stage (e.g., the patient first uses an appliance made using a first mold of a first stage, after a first predetermined amount of time, the patient uses a second appliance made using a second mold of a second stage, and so on, to move teeth). Each stage corresponds to a corresponding stage identifier 315. The material-jaw identifier 314 can identify what type of mold and whether the mold is for the upper jaw or the lower jaw. In some embodiments, the marking (eg, cutting mark) formed by the marking portion 122 may include 11-13 digits. Alternatively, the marking (eg, cutting mark) may include a different number of digits.
[0090] The material-jaw identifier 314 can be selected according to the following table:
[0091] The material-jaw identifier 314 can be a single number (e.g., 0-5). Each material-jaw identifier 314 can correspond to N (e.g., which can indicate the material of the appliance), T (e.g., which can indicate the material of the template), or R (e.g., which can indicate the material of the retainer). Each material-jaw identifier 314 can correspond to the upper jaw (U) or the lower jaw (L). In an embodiment where there are three possible materials (N, T, and R) and two possible jaw options (U and L), there can be five possible combinations, each of which can be represented by a material-jaw identifier value (e.g., ranging from 0 to 5).
[0092] In some embodiments, the pick and place component 130 forms a type marking 318. The type marking 318 may be "T" (template) if a template is to be formed, "R" (retainer) if a retainer is to be formed, or none (retainer) if an appliance is to be formed. The type marking 318 may allow for quick manual identification of whether the mold 100 is to be used to form an appliance, a template, or a retainer.
[0093] Figure 3BA beam 120 of mold 100 is shown according to some embodiments.
[0094] The beam 120 can be passed through Figure 5A , 5B and / or 5D. A transformation of the mold 100 is determined, the transformation including the position of the beam 120 relative to the dental arch portion 110. A shape of the chamfer 128 is determined to attach the beam 120 to the dental arch portion.
[0095] The beam 120 can be formed based on a design (eg, a 3D model) and can be used to form a dental appliance by method 500C. The beam 120 can be used to identify a mold by one or more of the methods of 500E-K.
[0096] The beam 120 has a marking portion 122, control pins 142A-D (or other control features), and an identifier feature 140. The control pin 142 is a feature (e.g., a pin) that is closest to the distal portion 112A-B of the dental arch portion 110. The control pin 142 is used to identify the beginning of the identifier feature 140 (e.g., all pins between the control pin 142 are identifier features 140).
[0097] The pick and place component 130 can be located within a threshold distance of the center of the beam 120. The pick and place component 130 can be positioned to provide clearance for a dental appliance manufacturing device (e.g., a robot) to fix the pick and place component 130 without contacting other parts of the mold 100 (e.g., without contacting the teeth of the mold). A portion 320 of the beam 120 corresponding to the pick and place component 130 can be positioned. In one embodiment, an imaging system of the dental appliance manufacturing device generates an image of the mold 100 or a portion of the mold 100 (e.g., the beam 120). The processing device can process the image using conventional image processing techniques to determine the location of the portion 320. The portion 320 may include an area without control pins / features and / or identifier features. In an embodiment, the portion includes an exposed area (without control pins / features and / or identifier features) such that the closest control pins / features and / or identifier features are a threshold distance from either side of the pick and place component 130. Thus, portion 320 provides space to accommodate a gripper and / or other device for grasping, holding and / or securing mold 100 .
[0098] The beam 120 of the mold 100 may include a region 326. The processing device may process the image using conventional image processing techniques and / or one or more trained machine learning models to determine the location of the region 326 of the mold 100. The region 326 corresponds to a mark (e.g., a cut mark) formed in the mark portion 122 of the beam 120. Figure 3B The area 326 shown in FIG. 1 is divided into Figure 3C. Twelve sub-regions 328 may be located on the beam. Each sub-region 328 may include a number of identifiers.
[0099] The beam 120 of the mold 100 may include control pins 142A-B on a first sidewall of the beam 120 and control pins 142C-D on a second sidewall of the beam 120. The processing device may process the image using conventional image processing techniques and / or one or more trained machine learning models to determine the location of the control pins 142. The area 322A-B between the control pins 142A-B and the area 322C-D between the control pins 142C-D (excluding the portion 320) are identified (e.g., by the processing device processing the image using conventional image processing techniques and / or one or more trained machine learning models). Figure 3B The area 322 shown in FIG. 1 is divided into Figure 3C . Eight sub-regions 324 can be located on the first side wall of the beam 120, and eight sub-regions 324 can be located on the second side wall of the beam. A sub-region 324 containing an identifier feature 140 (e.g., an identifier pin) can be considered to be "1", and a sub-region 324 not containing an identifier feature 140 can be considered to be "0". The 1s and 0s from the sub-regions 324 (e.g., identifier feature presence data) can be used to determine (e.g., verify) the identifier. The marking (e.g., a cut mark) of the marking portion 122 can be used to determine the same identifier. The identifier can be determined by the marking (e.g., a cut mark), and the identifier can be determined solely by the identifier feature 140 to have redundancy in determining the identifier. If the identifier determined via the marking (e.g., a cut mark) and the identifier determined via the identifier feature 140 do not match, a corrective action can be performed (e.g., providing an alarm, not using the mold 100 to form a dental appliance, etc.).
[0100] Figure 4A 400A is a block diagram illustrating an exemplary system architecture of a system 400A according to some embodiments. The system 400A can perform one or more processes associated with mold and / or dental appliance production. For example, the system 400A can perform mold design, mold formation, mold identification, dental appliance production, etc. In some embodiments, the processes associated with mold and / or dental appliance production are controlled by a controller 402 or a client device 404.
[0101] In some embodiments, the controller 402 and / or the client device 404 may perform mold design (eg, see Figure 5A , Figure 5B and Figure 5D). The controller 402 and / or the client device may determine the position of the beam, the layout of the identifier to be formed on the beam, and / or the shape of the beam, and may cause the dental appliance manufacturing apparatus 406 to form a mold. The controller 402 and / or the client device may determine the identifier for the mold, the marking to be formed on the mold, the placement of the beam relative to the dental arch portion of the mold, the position of the pick and place component of the mold, the feature offset associated with the position of the pick and place component, the identifier feature to be formed on the beam, and / or the layout of the identifier feature on the beam, and may cause the dental appliance manufacturing apparatus 406 to form the mold.
[0102] In some embodiments, the controller 402 and / or the client device 404 can perform mold and / or dental appliance production (e.g., see Figure 5B ). The controller 402 and / or the client device may receive a digital model of the mold, form the mold, cause a plastic sheet to be heated, cause the heated plastic sheet to be thermoformed on the mold, and cause the thermoformed plastic sheet to be trimmed to form the dental appliance.
[0103] In some embodiments, the controller 402 and / or the client device 404 may perform mold identification (e.g., see FIG. 5E to FIG. 5K ). In some embodiments, the controller 402 and / or the client device 404 receives prediction data from the prediction system 410 to perform mold identification. The prediction system 410 can train and use machine learning models to provide prediction data (see Figure 5F to Figure 5K ). For example, prediction system 410 can predict an area of the mold image corresponding to a mark, can predict a number of marks from the image, and / or can determine feature presence data based on the image of an identifier feature of the mold.
[0104] System 400A includes controller 402, client device 404, dental appliance manufacturing equipment 406, imaging device 408, prediction server 412, and data storage 450. Prediction server 412 can be part of prediction system 410 (e.g., to predict image areas corresponding to mold markings, predict numbers of markings from images, predict identifier feature presence data from images). Prediction system 410 can also include server machines 470 and 480.
[0105] The controller 402, the client device 404, the dental appliance manufacturing equipment 406, the imaging device 408, the prediction server 412, the data storage 450, the server machine 470, and the server machine 480 may be coupled to each other via a network 416. In some embodiments, the network 416 is a public network that provides the client device 404 with access to the prediction server 412, the data storage 450, and other publicly available computing devices. In some embodiments, the network 416 is a private network that provides the controller 402 with access to the dental appliance manufacturing equipment 406, the imaging device 408, the data storage 450, and other privately available computing devices, and provides the client device 404 with access to the prediction server 412, the data storage 450, and other privately available computing devices. The network 116 may include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.
[0106] The client device 404 may include a computing device, such as a personal computer (PC), a desktop computer, a laptop computer, a mobile phone, a smart phone, a tablet computer, a netbook computer, etc. The client device 404 may include a dental appliance generator 420. The dental appliance generator 420 may receive user input of a mold 100 to be generated and / or a dental appliance to be formed using the mold 100 (e.g., through a graphical user interface (GUI) displayed via the client device 404). In some embodiments, the dental appliance generator 420 sends data to the prediction system 410, receives output (e.g., prediction data 468) from the prediction system 410, and / or causes the mold 100 and / or dental appliance to be generated. The client device 404 may include an operating system that allows a user to generate, view, or edit one or more of the data. In some embodiments, the dental appliance generator 420 may cause the mold and / or dental appliance to be generated.
[0107] Controller 402, prediction server 412, server machine 470, and server machine 480 may each include one or more computing devices, such as a rack server, a router computer, a server computer, a PC, a mainframe computer, a laptop computer, a tablet computer, a desktop computer, a graphics processing unit (GPU), an accelerator application-specific integrated circuit (ASIC) (e.g., a tensor processing unit (TPU)), and the like.
[0108] The controller 402 and / or the client device 404 may include a dental appliance generator 420. The dental appliance generator 420 may perform processes associated with mold and / or dental appliance production (e.g., FIG. 5A to FIG. 5K For example, dental appliance generator 420 may receive image 452 (e.g., from imaging device 408, from data storage 450) and store a set of image 452 and information 462 in data storage 450. Prediction system 410 may use at least a portion of image 452 and / or information 462 to determine prediction data 468.
[0109] The prediction server 412 may include a prediction component 414. In some embodiments, the prediction component 414 may retrieve at least a portion of the image 452 from the data storage 450 and generate an output (e.g., prediction data 468) for the production of the mold 100 and / or the dental appliance. In some embodiments, the prediction component 414 may use a trained machine learning model 490 to determine the output for producing the mold 100 and / or the dental appliance. The trained machine learning model 490 may be trained using historical images 454 and / or historical information 464 to learn key processing and hardware parameters.
[0110] Data storage 150 may be a memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or another type of component or device capable of storing data. Data storage 150 may include multiple storage components (e.g., multiple drives or multiple databases) that may span multiple computing devices (e.g., multiple server computers). Data storage 450 may store images 452, information 462, prediction data 468, etc.
[0111] Image 452 may include an image of the entire mold 100, an image of the beam 120 of the mold 100, an image of the marking portion 122 of the beam, an image of the number of the marking portion 122, an image of the control pin 142 and / or identifier feature 140, an image of a single control pin and / or identifier feature 140, and the like.
[0112] The information 462 may include an area of the mold 100 corresponding to the marking, a number of the marking of the mold 100, identifier feature presence data, and the like.
[0113] The predicted data 468 may include predicted information for the mold 100. For example, the predicted data 468 may include a predicted area of the mold 100 corresponding to a marking, a predicted number of markings for the mold, predicted identifier presence data, and the like.
[0114] In some embodiments, the client device 404 may store the image 452 and / or the information 462 in the data storage 450, and the prediction server 412 may retrieve the image 452 and / or the information 462 from the data storage 450. In some embodiments, the prediction server 412 may store the output of the trained machine learning model 490 (e.g., prediction data 468) in the data storage 450, and the client device 404 may retrieve the output from the data storage 450.
[0115] In some embodiments, prediction system 410 also includes server machine 470 and server machine 480. Server machine 470 includes a data set generator 472 that can generate a data set (e.g., a set of data inputs, a collection of data inputs, and a set of target outputs) to train, validate, and / or test machine learning model 490. Figure 4B and Figure 5E Some operations of the dataset generator 472 are described in detail. In some embodiments, the dataset generator 472 can divide the images 452 and the information 462 into a training set (e.g., sixty percent of the images 452 and the information 462), a validation set (e.g., twenty percent of the images 452 and the information 462), and a test set (e.g., twenty percent of the images 452 and the information 462). In some embodiments, the prediction system 410 (e.g., via the prediction component 414) generates multiple sets of features. For example, a first set of features can be a first set of data corresponding to each dataset (e.g., a training set, a validation set, and a test set) (e.g., a first portion of the image 452, etc.), and a second set of features can be a second set of data types corresponding to each dataset (e.g., a second portion of the image 452).
[0116] The server machine 480 includes a training engine 482, a validation engine 484, a selection engine, and / or a test engine 486. The engines (e.g., the training engine 482, the validation engine 484, the selection engine 485, and the test engine 486) may refer to hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (such as instructions running on a processing device, a general purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 482 may be capable of training a machine learning model 490 using one or more feature sets associated with a training set from the data set generator 472. The training engine 482 may generate a plurality of trained machine learning models 490, wherein each trained machine learning model 490 corresponds to a different feature set of the training set (e.g., a portion of the image 452). For example, a first trained machine learning model may have been trained using all features (e.g., X1-X5), a second trained machine learning model may have been trained using a first subset of features (e.g., X1, X2, X4), and a third trained machine learning model may have been trained using a second subset of features (e.g., X1, X3, X4, and X5) that may partially overlap with the first subset of features.
[0117] The validation engine 484 may be capable of validating the trained machine learning models 490 using a corresponding feature set of a validation set from the dataset generator 472. For example, a first feature set of the validation set may be used to validate a first trained machine learning model 490 trained using a first feature set of the training set. The validation engine 484 may determine the accuracy of each of the trained machine learning models 490 based on the corresponding feature set of the validation set. The validation engine 484 may discard trained machine learning models 490 whose accuracy does not meet a threshold accuracy. In some embodiments, the selection engine 485 may be capable of selecting one or more trained machine learning models 490 whose accuracy meets a threshold accuracy. In some embodiments, the selection engine 485 may be capable of selecting a trained machine learning model 490 with the highest accuracy of the trained machine learning models 490.
[0118] The testing engine 486 may be able to test the trained machine learning model 490 using a corresponding feature set of the test set from the dataset generator 472. For example, a first trained machine learning model 490 trained using a first feature set of the training set may be tested using a first feature set of the test set. The testing engine 486 may determine a trained machine learning model 490 having the highest accuracy among all trained machine learning models based on the test set.
[0119] The machine learning model 490 may refer to a model artifact created by the training engine 482 using a training set that includes data inputs and, in some embodiments, corresponding target outputs (correct answers for the corresponding training inputs). Patterns in the data set that cluster the data inputs and / or map the data inputs to target outputs (correct answers) may be found, and mappings that capture these patterns are provided to the machine learning model 490. The machine learning model 490 may use one or more of linear regression, random forests, neural networks (e.g., artificial neural networks), and the like.
[0120] The prediction component 414 can provide the current image 456 of the mold to the trained machine learning model 490, and can run the trained machine learning model 490 on the input to obtain one or more outputs. The prediction component 414 can be capable of determining (e.g., extracting) prediction data 468 associated with the identification mold (e.g., a predicted area corresponding to the marked current image 456, a predicted number from the mark, predicted identifier feature presence data) from the output of the trained machine learning model 490, and can determine (e.g., extract) confidence data from the output, the confidence data indicating a confidence level that the prediction data 468 corresponds to the information 462 of the mold 100. The prediction component 414 or the dental appliance generator 420 can use the confidence data to decide whether to cause the mold 100 or the dental appliance to be produced and / or cause a corrective action to be performed based on the prediction data 468. For example, in response to determining that the confidence data does not meet a threshold amount (e.g., a low confidence in the identifier of the mold), the dental appliance generator 420 can cause the dental appliance not to be produced on the mold.
[0121] The confidence data may include or indicate a confidence level that the predicted data 468 corresponds to the current image 456 (e.g., to the mold 100). In one example, the confidence level is a real number between 0 and 1, inclusive, where 0 indicates no confidence that the predicted data 468 corresponds to the current image 456, and 1 indicates absolute confidence that the predicted data 468 corresponds to the current image 456. In some embodiments, the system 400A may use the prediction system 410 to determine the predicted data 468, rather than manually inspecting the mold 100. In some embodiments, in response to the confidence data indicating a confidence level below a threshold level, the system 400A may cause a corrective action to provide an alert to not use the mold 100, to stop production of the mold 100, to inspect the equipment, to manually inspect the mold 100, etc. In response to the confidence data indicating that the confidence level of a predetermined number of instances (e.g., a percentage of instances, a frequency of instances, a total number of instances, etc.) is below a threshold level, the prediction component 414 can cause the trained machine learning model 490 to be retrained (e.g., based on the current image 456 and the current information 466 corresponding to the current image 456, etc.).
[0122] For purposes of illustration and not limitation, aspects of the present disclosure describe training a machine learning model using image 452 and information 462 and inputting current image 452 into the trained machine learning model to determine prediction data 468. In other embodiments, a heuristic model or a rule-based model is used to determine prediction data 468 (e.g., without using a trained machine learning model). Prediction component 414 can monitor image 452 and information 462. Information about the current image 452 can be monitored or otherwise used in a heuristic model or a rule-based model. Figure 4B The data input 401 describes any information.
[0123] In some embodiments, the functionality of controller 402, client device 404, prediction server 412, server machine 470, and server machine 480 may be provided by a smaller number of machines. For example, in some embodiments, server machines 470 and 480 may be integrated into a single machine, while in some other embodiments, server machine 470, server machine 480, and prediction server 412 may be integrated into a single machine. In some embodiments, controller 402 and client device 404 may be integrated into a single machine.
[0124] In general, functions described as being performed by controller 402, client device 404, prediction server 412, server machine 470, and server machine 480 in one embodiment can also be performed on prediction server 412 in other embodiments, if appropriate. In addition, functions attributed to a particular component can be performed by different or multiple components operating together. For example, in some embodiments, prediction server 412 can determine whether to cause production of mold 100 or dental appliance or perform corrective action based on prediction data 468. In another example, client device 404 can determine prediction data 468 based on output from a trained machine learning model.
[0125] Additionally, the functionality of a particular component may be performed by different or multiple components operating together.One or more of prediction server 412, server machine 470, or server machine 480 may be accessed as a service provided to other systems or devices through an appropriate application programming interface (API).
[0126] In an embodiment, a "user" may be represented as a single individual. However, other embodiments of the present disclosure encompass a "user" that is an entity controlled by multiple users and / or automation sources. For example, a group of individual users united as a group of administrators may be considered a "user."
[0127] Although embodiments of the present disclosure are discussed in terms of determining prediction data 468 based on images 452 to produce a mold 100 and / or a dental appliance or to perform corrective actions in dental appliance manufacturing, embodiments may also be generally applicable to determining prediction data to perform actions.
[0128] Figure 4B is an example dataset generator 472 for creating a dataset for a machine learning model 490 according to certain embodiments. Figure 4B System 400B shows a data set generator 472, a data input 401 and a target output 403.
[0129] In some embodiments, the data set generator 472 generates a data set including one or more data inputs 401 In some embodiments, the dataset includes one or more target outputs 403 corresponding to the data input 401. The dataset may also include mapping data that maps the data input 401 to the target output 403. The data input 401 may also be referred to as "features," "attributes," or "information." In some embodiments, the dataset generator 472 may provide the dataset to a training engine 482, a validation engine 484, or a testing engine 486, where the dataset is used to train, validate, or test the machine learning model 490. Figure 5E Some embodiments of generating a training set are further described.
[0130] In some embodiments, dataset generator 472 generates data input 401 based on historical images 454 and generates target output 403 based on historical information 464 associated with historical images 454. Dataset generator 472 may determine a mapping from each set of historical images 454 to historical information 464.
[0131] In some embodiments, data input 401 may include one or more feature sets of historical images 454. Each instance of historical image 454 may be an image of the entire mold 100, an image of a beam 120 of a mold 100, an image of a marking portion 122 of a beam, an image of a number of a marking portion 122, an image of a control pin 142 and / or an identifier feature 140, an image of a single control pin and / or identifier feature 140, etc.
[0132] In some embodiments, the dataset generator 272 may generate a first data input corresponding to a first feature set to train, validate, or test a first machine learning model, and the dataset generator 272 may generate a second data input corresponding to a second feature set to train, validate, or test a second machine learning model.
[0133] In some embodiments, the data set generator 272 may discretize one or more of the data input 401 or the target output 403 (e.g., for use in a classification algorithm for a regression problem). The discretization of the data input 401 or the target output 403 may transform the continuous value of the variable into a discrete value. In some embodiments, the discrete values of the data input 401 indicate discrete portions of an image to obtain the target output 403 (e.g., discrete information about a number in a portion of an image or whether a pin is present in a portion of an image).
[0134] The data input 401 and target output 403 for training, validating, or testing a machine learning model may include information for a specific facility (e.g., for a specific dental appliance manufacturing facility). For example, the historical images 454 and the historical information 464 may be for the same dental appliance manufacturing facility.
[0135] In some embodiments, the information used to train the machine learning model can come from a particular type of manufacturing equipment (e.g., an imaging device 408 associated with a dental appliance manufacturing equipment 406) at a dental appliance manufacturing facility having particular characteristics, and allow the trained machine learning model to determine results for a particular set of dental appliance manufacturing equipment. In some embodiments, the information used to train the machine learning model can be for parts from two or more manufacturing facilities, and can allow the trained machine learning model to determine results for a mold 100 based on input from one manufacturing facility.
[0136] In some embodiments, after a dataset is generated and used to train, validate, or test the machine learning model 490, the machine learning model 490 can be further trained, validated, or tested (e.g., further images 452 and information 462) or adjusted (e.g., adjusting weights associated with the input data of the machine learning model 490, such as connection weights in a neural network).
[0137] Figure 4C 468. The system 400C may be used to determine whether to produce a mold 100 and / or a dental appliance or to perform a corrective action (e.g., associated with the mold 100, the dental appliance manufacturing apparatus 406, etc.) based on historical data (e.g., historical images 454 and historical information 464).
[0138] At block 430, the system 400C (eg, Figure 4AThe prediction system 410 of FIG. 1 performs data partitioning of the historical data (e.g., historical images 454 and historical information 464) (e.g., via the data set generator 472 of the server machine 470 of FIG. 1) to generate a training set 422, a validation set 424, and a test set 426. For example, the training set may be 60% of the historical data, the validation set may be 20% of the historical data, and the validation set may be 20% of the historical data. The system 400C may generate multiple feature sets for each of the training set, the validation set, and the test set. For example, if the historical data is associated with 20 imaging devices 408 and 100 molds 100 (e.g., molds 100 corresponding to images 452 from the 20 imaging devices 408), the first feature set may be imaging devices 1-10, the second feature set may be imaging devices 11-20, the training set may be molds 1-60, the validation set may be molds 61-80, and the test set may be molds 81-100. In this example, a first feature set of the training set would be associated with image 452 and information 462 associated with imaging device 1-10 and mold 1-60.
[0139] At box 432, system 400C performs model training using training set 422 (e.g., via training engine 482 of FIG. 1). System 400C can train multiple models using multiple feature sets of training set 422 (e.g., a first feature set of training set 422, a second feature set of training set 422, etc.). For example, system 400C can train machine learning models to generate a first trained machine learning model using a first feature set in the training set (e.g., images from imaging device 1-10 for mold 1-60) and generate a second trained machine learning model using a second feature set in the training set (e.g., images from imaging device 11-20 for mold 1-60). In some embodiments, the first trained machine learning model and the second trained machine learning model can be combined to generate a third trained machine learning model (e.g., which can be a better predictor than the first or second trained machine learning model itself). In some embodiments, the feature sets used to compare models can overlap (e.g., a first feature set from imaging device 1-15 and a second feature set from imaging device 5-20). In some embodiments, hundreds of models may be generated, including models with various feature permutations and model combinations.
[0140] At box 434, the system 400C performs model validation using the validation set 424 (e.g., via the validation engine 484 of FIG. 1 ). The system 400C may validate each of the trained models using the corresponding feature set of the validation set 424. For example, the system 400C may validate a first trained machine learning model using a first feature set in the validation set (e.g., images from imaging devices 1-10 for molds 61-80), and validate a second trained machine learning model using a second feature set in the validation set (e.g., images from imaging devices 11-20 for molds 61-80). In some embodiments, the system 400C may validate hundreds of models generated at box 432 (e.g., models with various arrangements of features, combinations of models, etc.). At box 434, the system 400C may determine the accuracy of each of the one or more trained models (e.g., via model validation), and may determine whether one or more of the trained models have an accuracy that satisfies a threshold accuracy. In response to determining that none of the trained models have an accuracy that satisfies the threshold accuracy, flow returns to block 432, where system 400C performs model training using a different feature set of the training set. In response to determining that one or more of the trained models have an accuracy that satisfies the threshold accuracy, flow continues to block 436. System 400C can discard trained machine learning models (e.g., based on a validation set) that have an accuracy below the threshold accuracy.
[0141] At block 436, the system 400C performs model selection (e.g., via the selection engine 485 of FIG. 1 ) to determine which of the one or more trained models that meet the threshold accuracy has the highest accuracy (e.g., the selected model 428, based on the validation of block 434). In response to determining that two or more of the trained models that meet the threshold accuracy have the same accuracy, the flow can return to block 432, where the system 400C performs model training using a further refined training set corresponding to the further refined feature set to determine the trained model with the highest accuracy.
[0142] At block 438, the system 400C performs model testing (e.g., via the testing engine 486 of FIG. 1 ) using the test set 426 to test the selected model 428. The system 400C may test the first trained machine learning model using a first feature set in the test set (e.g., images from the imaging device 1-10 for the mold 81-100) to determine that the first trained machine learning model meets the threshold accuracy (e.g., based on the first feature set of the test set 426). In response to the accuracy of the selected model 428 not meeting the threshold accuracy (e.g., the selected model 428 is overfit to the training set 422 and / or the validation set 424 and is not applicable to other data sets such as the test set 426), the process continues to block 432, where the system 400C performs model training (e.g., retraining) using a different training set corresponding to a different feature set. In response to determining that the selected model 428 has an accuracy that meets the threshold accuracy based on the test set 426, the process continues to block 440. In at least block 432 , the model may learn patterns in the historical images 454 to make predictions, and in block 438 , the system 400C may apply the model to the remaining data (eg, the test set 426 ) to test the predictions.
[0143] At box 440, the system 400C uses a training model (e.g., the selected model 428) to receive the current image 456 and determine (e.g., extract) prediction data 468 based on the output of the training model to produce the mold 100 and / or dental appliance or perform corrective actions associated with mold or dental appliance production.
[0144] In some embodiments, current information 466 corresponding to the current image 456 is received, and the model is retrained based on the current image 456 and the current information 466 .
[0145] In some embodiments, one or more of the operations in blocks 430-440 may occur in various orders and / or with other operations not presented and described herein. In some embodiments, one or more of the operations in blocks 430-440 may not be performed. For example, in some embodiments, one or more of the data partitioning of block 430, the model validation of block 434, the model selection of block 436, or the model testing of block 438 may not be performed.
[0146] FIG. 5A to FIG. 5K is a flow chart of methods 500A-K associated with mold and / or dental appliance production according to certain embodiments. In some embodiments, one or more operations of methods 500A-K are performed by a computing device (e.g., Figure 4A Controller 402, Figure 4A Client device 404, Figure 4AThe processing logic may include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (e.g., instructions executed by a processing device, a general purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. For example, one or more operations of the methods 500A-K may be performed by a processing device executing a program or module, such as Figure 4A and Figure 6 A dental appliance generator 420 is provided.
[0147] It can be noted that regarding FIG. 4A to FIG. 4C One or more of the components described may be used to illustrate FIG. 5A to FIG. 5K In some embodiments, a non-transitory machine-readable storage medium stores instructions that are executed by a processing device (e.g., Figure 4A Controller 402, Figure 4A Client device 404, Figure 4A Prediction server 412, Figure 4A When executed by the prediction system 410, etc., the processing device executes the method 500A-K.
[0148] For simplicity of illustration, methods 500A-K are depicted and described as a series of actions. However, actions according to the present disclosure may occur in various orders and / or simultaneously, and with other actions not presented and described herein. Furthermore, not all of the actions shown may be performed to implement methods 500A-K according to the disclosed subject matter. Additionally, those skilled in the art will understand and appreciate that methods 500A-K may alternatively be represented as a series of interrelated states via state diagrams or events.
[0149] refer to Figure 5A According to some embodiments, method 500A is associated with producing a mold for forming a dental appliance (eg, forming a digital model for the mold).
[0150] At block 501, processing logic determines a position of a beam of a mold relative to a dental arch portion of the mold (e.g., processing logic finds an appropriate position for the beam). The dental arch portion includes a first distal portion (e.g., including molars on a first side of the jaw), a second distal portion (e.g., including molars on a second side of the jaw), and an incisor portion disposed between the first distal portion and the second distal portion (e.g., including incisors at the front of the jaw). The beam extends from the first distal portion to the second distal portion (e.g., offset from a distal end of the distal portion of the dental arch portion). In some embodiments, the beam is substantially parallel to Figure 2B line 240).
[0151] In some embodiments, block 501 includes one or more of blocks 502 - 504 .
[0152] At block 502, processing logic identifies transformations of the mold. Each transformation includes a corresponding position of the beam relative to the dental arch portion. In some embodiments, the transformations are pre-computed transformations (e.g., different orientations and / or sizes of the beam). Each transformation may include a corresponding position of the beam 120 relative to the dental arch portion 110. In some examples, in different transformations of the mold 100, the beam 120 is located at different distances from the distal end of the distal portion of the dental arch portion 110 (e.g., at different distances from the distal end of the distal portion of the dental arch portion 110). Figure 2B In some examples, the beam 120 and the dental arch portion 110 are at different angles relative to each other. In some examples, the beam 120 and / or the dental arch portion 110 have different heights in different variations of the mold 100 (e.g., the dental arch portion 110 includes different amounts of gingival area). In some examples, in different variations of the mold 100, the substantially horizontal lower surface of the dental arch portion 110 is at different angles relative to the upper surface of the dental arch portion 110 (e.g., the teeth) (e.g., the gingival portion of the dental arch portion 110 forms a substantially horizontal lower surface at different angles relative to the upper surface in different variations of the mold 100). In some examples, the beam 120 has different lengths or different chamfers 128 in different variations of the mold 100.
[0153] At block 503 , processing logic slices the 3D model of the dental arch portion to generate a 2D outline of the 3D mold. Figure 2A 2D contours of the 3D model are shown. In some embodiments, 2D contours are created for different transformations of the dental arch portion 110. The 2D contours can be generated for one or more heights of the dental arch portion 110 that include or are parallel to the lower surface of the dental arch portion 110. In some embodiments, the 2D contours are generated for one or more heights corresponding to the thickness of the beam 120 (e.g., the chamfer 128 of the beam).
[0154] At block 504, processing logic selects a first transformation in the transformations based on the 2D contour. The transformations include the position of the beam 120 relative to the dental arch portion 110. The transformations may include the shape of the dental arch portion (e.g., how much gingival area is included in the dental arch portion 110). In some embodiments, processing logic examines each transformation from the pre-computed list of transformations and selects the first transformation that satisfies several conditions (e.g., see Figure 5B ).
[0155] At block 505, processing logic determines a layout of identifiers to be formed on the beam between the first distal portion and the second distal portion (eg, processing logic generates a label).
[0156] Block 505 may include one or more of blocks 506 - 508 .
[0157] At block 506, processing logic identifies a predefined format for the marked portion of the beam (eg, generates a label in the predefined format). For example, the predefined format may be a marked portion of the beam of a first threshold length.
[0158] At block 507, processing logic determines a number of marks (e.g., cut marks) to be formed in the marked portion of the beam based on the identifier (e.g., generates control information including a control number for the cut mark). Processing logic may determine an 11-13 digit mark based on the identifier. The mark may include a number of cutout shapes to be formed in the beam. Each number may form a numbered void in the material (e.g., a through hole through the beam). The number of the mark may be human-readable and machine-readable.
[0159] At block 508, processing logic determines an identifier feature of the beam based on the identifier (e.g., generates control information including a pin, such as 16 bits of control information). Processing logic may determine a pattern of 0s and 1s, where 0 corresponds to the absence of an identifier feature and 1 corresponds to an identifier feature. The pattern of 0s and 1s is configured to be read as identifier feature presence data. The identifier feature presence data may be used to verify the identifier displayed by the tag. In some embodiments, the identifier feature forms a binary code to be decoded to verify the identifier determined from the number of the tag.
[0160] At block 509, processing logic determines the shape of the beam to be attached to the dental arch portion of the mold (e.g., processing logic builds the beam shape). The mold is formed based on the position of the beam (from block 501), the identifier (from block 505), and the shape of the beam (from block 509).
[0161] Block 509 may include one or more of blocks 510 - 513 .
[0162] At block 510, processing logic determines a shape of a marking portion that forms a mark (e.g., a cut mark) based on the identifier (e.g., creating a flat beam with engraved numbers). The marking portion is used to provide a threshold area for each digit of the identifier. Processing logic can determine a threshold length of the marking portion based on the number of digits of the identifier.
[0163] At block 511, processing logic determines a location of an identifier feature (e.g., a control pin, an identifier feature) on the beam based on the identifier (e.g., creating a flat beam with a binary identifier feature). To determine the location of the pin, processing logic may determine the location of the pick and place component (e.g., a pick and place robot has a gap to fix the location of the pick and place component), and then position the pin at a threshold distance from the pick and place component. Each of the sub-regions along the sidewall of the beam corresponding to the identifier feature (e.g., "1") or the lack of the identifier feature (e.g., "0") may have a predetermined area.
[0164] At block 512, processing logic determines a reinforcement portion of the beam (e.g., creates a reinforcement portion to prevent deformation of the beam). The reinforcement portion of the beam may extend from chamfer to chamfer. The reinforcement portion of the beam may be configured to extend from a first distal portion of the dental arch portion to a second distal portion of the dental arch portion.
[0165] At block 513, processing logic determines the chamfer of the beam (e.g., creating a chamfer between the beam and the mold to prevent the beam from breaking, adapting the chamfer shape to the cut line to provide a safety gap). The reinforcement portion may have a greater thickness than the marked portion. The chamfered portion may start with the same thickness as the marked portion, and the thickness may be increased until it has the same thickness as the reinforcement portion.
[0166] refer to Figure 5B According to some embodiments, method 500B is associated with selecting a transformation of a mold for dental appliance production.
[0167] At block 515, processing logic selects a transformation of the mold. Multiple potential transformations of the mold may be generated, and method 500B may be repeated until a transformation satisfies all of the conditions of method 500B. In some embodiments, method 500B is repeated for each transformation of the mold, and then the transformations that satisfy all of the conditions of method 500B are compared to each other.
[0168] At box 516, processing logic determines (e.g., measures) a width distance between the distal ends of the beams of the mold from a first distal portion of the dental arch portion of the mold to a second distal portion of the dental arch portion of the mold in the transformation of the mold selected in box 515.
[0169] At block 517, processing logic determines whether the width distance of block 516 satisfies a threshold distance (e.g., the length of the marking portion, the combined length of the marking portion and the chamfer) (e.g., there is enough space between the distal portions 112A-B to form a mark in the marking portion 122). In response to the width distance not satisfying the threshold distance, the flow returns to block 515, where another transformation of the mold is selected. In response to the width distance satisfying the threshold distance, the flow continues to block 518.
[0170] At block 518, processing logic determines (e.g., measures) the distance between the beam and the line (e.g., Figure 2B The length distance between the lines 240).
[0171] At block 519, processing logic determines whether the length distance of block 518 satisfies a threshold distance (e.g., about 0 mm to about 15 mm) (e.g., the distance between the farthest point of the molar and the beam is less than about 15 mm). In response to the width distance not satisfying the threshold distance, the flow returns to block 515, where another transformation of the mold is selected. In response to the length distance satisfying the threshold distance, the flow continues to block 520.
[0172] At box 520, processing logic determines (e.g., measures) a feature offset distance between a pick and place component of the beam and a corresponding identifier feature of the beam (e.g., the closest identifier pin extending from a side wall of the beam) in the transformation of the mold selected in box 515.
[0173] At block 521, processing logic determines whether the feature offset distance of block 520 satisfies a threshold distance. In some embodiments, processing logic determines whether the feature offset distance on a first side wall of the beam (e.g., which is aligned with the pick and place component) satisfies a threshold distance (e.g., approximately 4.5 mm), and whether the feature offset distance on a second side wall of the beam (e.g., which is attached to the pick and place component) satisfies a threshold distance (e.g., approximately 4.5 mm) (e.g., see Figure 2B The feature offset distance provides clearance for a dental appliance manufacturing device (e.g., a robot) to secure the pick and place component 130 to move the mold 100. In response to the feature offset distance not satisfying the threshold distance, the process returns to block 515 where another transformation of the mold is selected. In response to the feature offset distance satisfying the threshold distance, the process continues to block 522.
[0174] At box 522, processing logic determines (e.g., measures) the gap distance between the trim line of the mold (e.g., the trim line of the arch portion where the thermoformed plastic sheet will be trimmed from the mold) and the connection (e.g., chamfer) between the arch portion and the beam in the transformation selected in box 515.
[0175] At block 523, processing logic determines whether the gap distance of block 522 satisfies a threshold distance. In response to the gap distance not satisfying the threshold distance, flow returns to block 515 where another transformation of the mold is selected. In response to the gap distance satisfying the threshold distance, flow continues to block 518.
[0176] At block 524, processing logic determines whether the beam is located between the incisor portion of the dental arch and a line intersecting the distal end of the distal portion of the dental arch in the transformation (e.g., Figure 2B In response to the beam not being between the incisor portion and the line, the flow returns to block 515 where another transformation of the mold is selected. In response to the beam being between the incisor portion and the line, the flow continues to block 525.
[0177] At block 525, processing logic determines whether the identifier (e.g., indicia and / or identifier feature) of the mold is not blocked by the geometry of the mold (e.g., tilted teeth). In response to the identifier being blocked, the flow returns to block 515, where another transformation of the mold is selected. In response to the identifier being not blocked, the flow continues to block 526.
[0178] At block 526, processing logic determines whether the beam will create a production issue. For example, processing logic determines whether webbing (e.g., additional material between the beam and the dental arch portion, gaps in the material between the beam and the dental arch portion) is present. In response to determining that the beam will create a production issue, the flow returns to block 515, where another change in the mold is selected. In response to determining that the beam will not create a production issue, the flow continues to block 527.
[0179] At block 527, processing logic applies the transformation of the mold selected at block 515 to the position of the beam relative to the dental arch portion (e.g., see Figure 5A In some embodiments, the processing logic uses Figure 5B In some embodiments, the processing logic identifies the condition that satisfies Figure 5B The processing logic may rank the transformations based on the amount of material used (e.g., less material ranks higher), the distance from the line between the distal end of the distal portion of the dental arch portion (e.g., closer to the line ranks higher, closer to 15mm from the line ranks higher, etc.), etc.
[0180] refer to Figure 5C According to some embodiments, method 500C is associated with dental appliance production using a mold.
[0181] At block 530, processing logic receives the digital model of the mold. In some embodiments, the mold is associated with a dental arch of a user, such as a mold that can be used to form a dental appliance. In some embodiments, the mold is used to form a dental appliance (e.g., for use in association with a dental arch of a user), such as an augmented palatal expander, an appliance (e.g., with or without a mandibular advancement feature and / or other feature), a dental attachment template, and / or other dental appliance.
[0182] The shape of the patient's dental arch at the treatment stage can be determined based on the treatment plan to generate a digital model of the mold. In the example of orthodontics, a treatment plan can be generated based on an intraoral scan of a dental arch (e.g., a dental arch for receiving dental appliances, a dental arch to be modeled). An intraoral scan of the patient's dental arch can be performed to generate a 3D virtual model of the patient's dental arch. For example, a full scan of the patient's mandibular arch and / or maxillary arch can be performed to generate a 3D virtual model thereof. Intraoral scanning can be performed by creating multiple overlapping intraoral images from different scanning stations and then stitching the intraoral images together to provide a composite 3D virtual model. In other applications, a virtual 3D model can also be generated based on a scan of an object to be modeled or based on the use of computer-aided drawing technology (e.g., to design a virtual 3D mold). Alternatively, an initial negative mold can be generated from the actual object to be modeled. The negative mold can then be scanned to determine the shape of the positive mold to be produced.
[0183] Once a virtual 3D model of the patient's dental arch is generated, the dentist can determine the desired treatment outcome, including the final position and orientation of the patient's teeth. The processing logic can then determine multiple treatment stages so that the teeth are gradually moved from the starting position and orientation to the target final position and orientation. The shape of the final virtual 3D model and each intermediate virtual 3D model can be determined by calculating the progression of tooth movement throughout the orthodontic treatment from the initial tooth placement and orientation to the final corrected tooth placement and orientation. For each treatment stage, a separate virtual 3D model of the patient's dental arch at that treatment stage can be generated. The shape of each virtual 3D model will be different. The original virtual 3D model, the final virtual 3D model, and each intermediate virtual 3D model are unique and customized for the patient.
[0184] The processing logic may determine an initial shape of the mold of the patient's dental arch at the treatment stage based on the digital model of the dental arch at the treatment stage.The processing logic may additionally determine one or more features to add to the object.
[0185] The processing logic may determine the final shape of the mold and may generate a digital model of the mold. Alternatively, the digital model may have already been generated. In this case, the processing logic may update the already generated digital model to include one or more determined features of the mold. The digital model may be represented by a file, such as a computer-aided drawing (CAD) file or a 3D printable file, such as a stereolithography (STL) file. The digital model may include instructions that will control a manufacturing system or device to produce a mold having a specified geometry.
[0186] At block 531, processing logic forms a mold. Block 521 may include one or more of blocks 532-537. In an embodiment, the mold is formed via three-dimensional printing, such as by using a rapid prototyping machine.
[0187] At block 532, processing logic causes the dental arch portion of the mold to be formed.
[0188] At block 533, processing logic causes the marked portion of the beam of the mold to be formed.
[0189] At block 534, processing logic causes a mark (eg, a cut mark) to be formed in the mark portion.
[0190] At block 535, processing logic causes a pin (eg, an identifier feature, a control pin) to be formed on the beam.
[0191] At block 536 , processing logic causes a reinforcement portion of the beam to be formed.
[0192] At block 537 , processing logic causes the chamfer of the beam to be formed.
[0193] In an embodiment, some or all of the options of blocks 532-537 may be performed in parallel during the formation of the mold (e.g., the mold is formed layer by layer). In some embodiments, one or more of blocks 532-537 are performed in series. For example, the dental arch portion may be formed at block 532, then the marking portion of the mold may be formed at block 533, then the marking of block 534 may be formed (e.g., removing material from the marking portion to form the marking), etc.
[0194] The mold can be generated based on the digital model of frame 530. The virtual 3D model of the patient's dental arch can be used to generate a unique customized mold associated with the dental arch at a specific stage of treatment. The shape of the mold can be based at least in part on the shape of the virtual 3D model used for the treatment stage. The mold can correspond to the patient's dental arch, and the mold can include an inclined portion that starts below the gum line of the dental arch and extends away from the dental arch to the lower part of the mold. In some embodiments, a mold is generated in which the inclined portion starts below the gum line (e.g., to help release a thermoformed plastic sheet from the mold). The mold can be formed using a rapid prototyping device (e.g., a 3D printer) to manufacture the mold using additive manufacturing technology (e.g., stereolithography) or subtractive manufacturing technology (e.g., milling). The digital model can be input into a rapid prototyping machine. Then, the rapid prototyping machine manufactures the mold using the digital model. An example of a rapid prototyping machine is a 3D printer. 3D printing includes any layer-based additive manufacturing process. 3D printing can be implemented using an additive process, in which continuous layers of material are formed in a specified shape. 3D printing can be performed using extrusion deposition, particulate material bonding, lamination, photopolymerization, continuous liquid interface production (CLIP), or other techniques. 3D printing can also be achieved using subtractive processes such as milling.
[0195] In one embodiment, stereolithography (SLA) (also referred to as optical manufacturing solid imaging) is used to manufacture SLA molds. In SLA, molds are manufactured by continuously printing thin layers of photocurable materials (e.g., polymer resins) on top of each other. The platform is located in a bath of liquid photopolymer or resin, just below the surface of the bath. A light source (e.g., an ultraviolet laser) depicts a pattern on the platform, curing the photopolymer pointed to by the light source to form the first layer of the mold. The platform is incrementally lowered, and the light source tracks the new pattern on the platform to form another layer of the mold at each increment. Repeat this process until the mold is fully made. Once all layers of the mold are formed, the mold can be cleaned and cured. In one embodiment, a system such as that described above herein (e.g., system 400A, dental appliance manufacturing equipment 406) is used to print the mold.
[0196] Materials such as polyesters, copolyesters, polycarbonates, polycarbonates, thermoplastic polyurethanes, polypropylene, polyethylene, polypropylene and polyethylene copolymers, acrylic acid, cyclic block copolymers, polyetheretherketones, polyamides, polyethylene terephthalate, polybutylene terephthalate, polyetherimides, polyethersulfones, polytrimethylene terephthalate, styrene block copolymers (SBC), silicone rubber, elastomeric alloys, thermoplastic elastomers (TPE), thermoplastic vulcanizates (TPV) elastomers, polyurethane elastomers, block copolymer elastomers, polyolefin blend elastomers, thermoplastic copolyester elastomers, thermoplastic polyamide elastomers, or combinations thereof, can be used to directly form the mold. The material used to make the mold can be provided in an uncured form (e.g., as a liquid, resin, powder, etc.) and can be cured (e.g., by photopolymerization, photocuring, gas curing, laser curing, crosslinking, etc.). The properties of the material before curing can be different from the properties of the material after curing.
[0197] Optionally, the rapid prototyping techniques described herein allow for the manufacture of molds comprising multiple materials, referred to herein as "multi-material direct manufacturing". In some embodiments, the multi-material direct manufacturing method involves forming a mold simultaneously from multiple materials in a single manufacturing step. For example, a multi-tip extrusion device can be used to selectively distribute multiple types of materials (e.g., resins, liquids, solids, or combinations thereof) from different material supply sources so as to manufacture a mold from multiple different materials. Alternatively or in combination, the multi-material direct manufacturing method can involve forming a mold from multiple materials in multiple sequential manufacturing steps. For example, the first portion of the mold (e.g., the main portion of the mold) can be formed from a first material according to any direct manufacturing method herein, and then the second portion of the mold (e.g., a complex feature added to the mold) can be formed from a second material according to the method herein, and so on, until the entire mold has been formed. The relative arrangement of the first portion and the second portion can be varied as desired. In one embodiment, multi-material direct manufacturing is used to make a first material for marking a cutting line on the mold, and to make one or more additional materials for the rest of the mold.
[0198] In some embodiments, the dental appliance can be formed from a mold (e.g., by thermoforming the dental appliance on the mold). The dental appliance can be configured to provide force to move the patient's teeth, or can be configured to perform other actions, such as protecting the patient's teeth from bruxism. The shape of each dental appliance is unique and customized for a specific patient and a specific stage of treatment. In an example, the dental appliance can be pressure molded or thermoformed on a printed mold. Each mold can be used to make a dental appliance that will apply force to the patient's teeth at a specific stage of orthodontic treatment. The dental appliance has a tooth receiving cavity that receives the teeth and resiliently repositions the teeth according to the specific stage of treatment.
[0199] In response to forming the mold, the mold is removed from the build platform. The mold can then be secured to a plate (e.g., Figure 1A , Figure 1B and Figure 1D The mold can be fixed to the plate via fasteners such as pins, keyways, and / or locking mechanisms (e.g., locking mechanisms 184). The mold can be fixed to the plate to prevent movement of the mold in the x-direction, y-direction, and / or z-direction, and to prevent rotation (e.g., angular change) of the mold during further processing.
[0200] The processing logic may identify the mold via a mark (e.g., a cut mark) and / or a pin of a beam prior to moving the mold (e.g., a pick and place operation). The processing logic may identify the mold via an imaging system (e.g., a portion of an imaging station, a portion of a thermoforming station, a portion of a trimming station, a portion of a robot for moving the mold, etc.). In response to identifying the mold via the mark (e.g., a cut mark) and / or a pin of a beam, the processing logic may move the mold (e.g., a pick and place operation) by securing the mold via a pick and place component coupled to (e.g., integrated into) the beam. The mold may be moved to the thermoforming station via a robotic arm, a conveyor belt, or other transport mechanism. The mold may be secured at the thermoforming station via a locking mechanism of a plate that secures a flat portion of the mold.
[0201] At box 538, processing logic causes the plastic sheet to be heated. The plastic sheet can be fixed to the tray, and the plastic sheet fixed to the tray can be surrounded by a mask before the plastic sheet is heated. The plastic sheet can be an elastic thermoplastic, a polymer material sheet, etc. The plastic sheet can be lowered onto the tray so that the retaining pins of the tray pierce the plastic sheet to fix the plastic sheet to the tray. A pressurized cylinder can lower the mask onto the plastic sheet fixed to the tray. The plastic sheet can be heated to a temperature at which the plastic sheet becomes pliable. A ceramic heater, a convection oven, or an infrared heater can be used to heat the plastic sheet. The mask can allow the plastic sheet to be heated to 336°F without hanging to avoid air leakage.
[0202] At block 539, processing logic identifies the mold (e.g., see FIG. 5E to FIG. 5K ). The processing logic may receive an image of the mold and determine an identifier of the mold based on the image (e.g., see FIG. 5E to FIG. 5K ), and retrieve thermoforming instructions based on the identifier.
[0203] At box 540, processing logic causes the heated plastic sheet to be thermoformed to the mold (e.g., based on an identifier of the mold and / or thermoforming instructions). Processing logic may execute box 540 after identifying the mold in box 539. In order to thermoform the heated plastic sheet onto the mold, pressure may be simultaneously applied to the plastic sheet to form the now pliable plastic sheet around the mold (e.g., with features that will emboss markings and / or elements in the dental appliance formed on the mold). Once the sheet cools, it will have a shape that conforms to the mold. In one embodiment, a release agent (e.g., a non-stick material) is applied to the mold before forming the dental appliance (e.g., a shell). This may facilitate removal of the mold from the shell later.
[0204] At block 541, processing logic identifies the mold (e.g., see FIG. 5E to FIG. 5K ). The processing logic may receive an image of the mold and determine an identifier of the mold based on the image (e.g., see FIG. 5E to FIG. 5K ), and retrieve the trimming instruction based on the identifier.
[0205] At box 542, processing logic causes the thermoformed plastic sheet to be trimmed to form a dental appliance (e.g., based on an identifier of the mold and / or thermoforming instructions). The mold with the thermoformed plastic sheet can be moved to a trimming station, and image identification can be performed to verify that the correct mold and trimming instructions are being used. Processing logic can perform box 542 after identifying the mold in box 539 or 541. The thermoformed plastic sheet can be removed from the mold before or after being trimmed (e.g., using a shell removal device). The thermoformed plastic sheet can be trimmed to generate a dental appliance. In some embodiments, during the trimming of the thermoformed plastic sheet to generate the dental appliance, a portion of the thermoformed plastic sheet placed on a portion of the mold is removed, and the portion of the mold is tilted outwardly below the gum line. Before or after the thermoformed plastic sheet is removed from the mold for the treatment stage, the thermoformed plastic sheet is trimmed along one or more cutting lines (also referred to as trimming lines). The cutting line can be a gingival cutting line representing the interface between the dental appliance and the patient's gums. In one embodiment, the dental appliance is cut manually by a technician using scissors, a drill, a cutting wheel, a scalpel, or any other cutting instrument. In another embodiment, the dental appliance is cut by a computer-controlled trimmer (such as a CNC machine or a laser trimmer). The computer-controlled trimmer can control the angle and position of the trimmer's cutting tool to trim the thermoformed plastic sheet.
[0206] In some embodiments, the transfer of the fixed mold and / or the plate of plastic sheet material is carried out via a conveyor system (e.g., via lateral movement). In some embodiments, the transfer of the fixed mold and / or the plate of plastic sheet material is carried out via a turntable system (e.g., via rotational movement).
[0207] In some embodiments, the mold is transferred to be located below the thermoforming station and lifted to allow the heated sheet to be thermoformed on the first mold and the second mold. In some embodiments, the first mold is transferred to be located below the thermoforming station via lateral movement (e.g., a conveyor system). In some embodiments, the mold is transferred to be located below the thermoforming station via rotational movement (e.g., a turntable system).
[0208] In some embodiments, the technology herein can be used to form molds, such as thermoforming molds. Examples of these can be found in: U.S. Patent No. 9,943,991, entitled "Mold with separable features" by inventors Tanugula et al.; U.S. Patent No. 9,943,386, entitled "Mold with weakened areas" by inventors Webber et al.; and U.S. Patent No. 8,776,391, entitled "System for post-processing orthodontic appliance molds" by inventors Kaza et al.; and any continuation or divisional applications claiming priority and any invention or provisional applications from which priority is claimed. These patents / applications are incorporated herein by reference as if fully set forth herein.
[0209] In some embodiments, the technology herein can be used to form an appliance with a mandibular repositioning feature. Examples of these can be found in the following patents: U.S. Patent No. 9,844,424, entitled "Dental appliance with repositioning jaw elements" by inventor Wu et al.; U.S. Patent Publication No. 2015 / 0238280, entitled "Dental appliance with repositioning jaw elements" by inventor Wu et al.; U.S. Patent No. 10,213,277, entitled "Dental appliance binding structure" by inventor Webber et al.; and any continuation or divisional application claiming priority and any invention or provisional application claiming priority therefrom. These patents / applications are incorporated herein by reference as if fully set forth herein.
[0210] In some embodiments, the technology herein can be used to form a palatal expander. Examples can be found in: U.S. Patent No. 9,610,141, entitled "Arch expanding appliance" by inventor Kopelman et al.; U.S. Patent No. 7,192,273, entitled "System and method for palatal expansion" by inventor McSurdy; U.S. Patent No. 7,874,836, entitled "System and method for palatal expansion" by inventor McSurdy; and any continuation or divisional application claiming priority and any invention or provisional application claiming priority therefrom. These patents / applications are incorporated herein by reference as if fully set forth herein.
[0211] In some embodiments, the technology herein can be used to form attachment forming templates. Examples can be found in: U.S. Patent Publication No. 2017 / 0007368, entitled “Direct fabrication of attachment templates with adhesive” to Boronkay; U.S. Patent Publication No. 2017 / 0165032, entitled “Dental attachment placement structure” to Webber et al.; U.S. Patent Publication No. 2017 / 0319296, entitled “Dental attachment placement structure” to Webber et al.; the contents of U.S. Patent Application Serial No. 16 / 366,686, entitled “Dental attachment placement structure” to Webber et al.; and any continuation or divisional applications claiming priority and any invention or provisional applications claiming priority therefrom. These patents / applications are incorporated herein by reference as if fully set forth herein.
[0212] In some embodiments, the technology herein can be used to form directly manufactured aligners. Examples can be found in: U.S. Patent Application Publication No. 2016 / 0310236 entitled “Direct fabrication of orthodontic appliances with elastics” by inventors Kopelman et al.; U.S. Patent Application Publication No. 2017 / 0007365 entitled “Direct fabrication of aligners with interproximal force coupling” by Kopelman et al.; U.S. Patent Application Publication No. 2017 / 0007359 entitled “Direct fabrication of orthodontic appliances with variable properties” by Kopelman et al.; U.S. Patent Application Publication No. 2017 / 0007366 entitled “Direct fabrication of orthodontic appliances with interproximal force coupling” by Kopelman et al.; U.S. Patent Application Publication No. 2017 / 0007359 entitled “Systems, apparatuses and methods for dental appliances with integrally U.S. Patent Application Publication No. 2017 / 0007360, entitled “Systems, apparatus, and methods for dental appliances with integrally formed features”; U.S. Patent No. 10,363,116, entitled “Direct fabrication of power arms” to Boronkay; U.S. Patent Application Publication No. 2017 / 0007366, entitled “Direct fabrication of aligners for arch expansion” to Kopeleman et al.; U.S. Patent Application Publication No. 2017 / 0007367, entitled “Direct fabrication of palate expansion and other applications” to Li et al.; and any continuation or divisional applications claiming priority and any invention or provisional applications claiming priority therefrom. These patents / applications are incorporated herein by reference as if fully set forth herein.
[0213] Examples of materials that can be used with the embodiments discussed herein include the following subject matter: U.S. Patent Publication No. 2017 / 0007362, entitled “Dental Materials Using Thermoset Polymers” by inventors Yan CHEN et al.; International Patent Application No. PCT / US2019 / 030683, entitled “Curable Composition for Use in a High Temperature Lithography-Based Photopolymerization Process and Method of Producing Crosslinked Polymers Therefrom” by Alleyne Technologies, Inc.; and International Patent Application No. PCT / US2019 / 030687, entitled “Polymerizable Monomers and Method of Polymerizing the Same” by Alleyne Technologies, Inc. These patents / applications are incorporated herein by reference as if fully set forth herein. As described in this article, hybrid 3D printing technology can combine the advantages of SLA, DLP, and FDM into a single technology that can be used as the basis for mass-produced 3D printed objects (dental appliances, hearing aids, medical implants, etc.).
[0214] refer to Figure 5D According to some embodiments, method 500D is associated with generating a digital model of a mold for forming a dental appliance (eg, adding features to a digital model of a dental arch).
[0215] At block 545, processing logic determines an identifier to be associated with the mold. Block 540 may include determining a patient identifier (e.g., an 8-digit number) associated with the mold, control information associated with the mold (e.g., a control number used to verify label identification correctness, notify identification errors, and / or correct identification errors), a material-jaw identifier based on the material of the dental appliance to be formed by the mold and the jaw associated with the mold, and / or a phase identifier (e.g., 1-99) associated with the mold. In some embodiments, determining the material-jaw identifier includes: determining the material of the dental appliance to be formed by the mold (e.g., an appliance, template, or retainer); and determining the jaw associated with the mold (e.g., mandibular or maxillary). In some embodiments, the identifier is based on the patient identifier, the control information, the material-jaw identifier, and the phase identifier.
[0216] In some embodiments, the control information (eg, control number) may overlay the last three symbols of the identifier (eg, material / jaw and stage).
[0217] Control information may be calculated for numbers (eg, cutting marks) and for identifier features.
[0218] At block 546, processing logic determines a mark (e.g., a cutting mark) to be formed by a marking portion of the beam of the mold based on the identifier to identify the mold. The mold may include a dental arch portion associated with a plurality of teeth of the user. The dental arch portion may include: a first distal portion; a second distal portion; and an incisor portion disposed between the first distal portion and the second distal portion. The beam extends from the first distal portion to the second distal portion.
[0219] The markings (e.g., cut markings) may include numbers, wherein a first subset of the numbers are associated with a patient identifier, a second subset of the numbers are associated with control information, a third subset of the numbers are associated with a material-jaw identifier, and a fourth subset of the numbers are associated with a stage identifier. The control information may be used to verify the identifier. For example, a sum of all the numbers of at least a portion of the identifier may be performed and then an algorithm (e.g., a modulus 10 algorithm, a modulus 10 algorithm, a (mod 10 algorithm, Luhn algorithm, Luhn formula) is applied to the sum, and a permutation is then applied to the algorithm result (e.g., applying permutation 1246395078). The result (e.g., the permutation of the modulo 10 result applied to the sum of the number) can be compared to the control information number. If the result matches the control information number, then the number can be verified to be correct.
[0220] For example, if at least part of the identifier is 123456, then:
[0221] The sum of each number 123456: 1+2+3+4+5+6=21
[0222] Apply modulo 10 to the sum: 21 mod 10 = 1
[0223] Apply permutation: Apply permutation 1246395078 to 1=2 (second number, indexed from zero)
[0224] 2 is used as a control information number on the mark formed in the mark portion of the beam.
[0225] At block 547, processing logic determines placement of the beam within a first threshold distance of the distal end of the dental arch portion.
[0226] At block 548, processing logic determines that the position of the pick and place part of the mold is a threshold distance (e.g., Figure 2B The processing logic can determine a position closest to the center of the beam where a dental appliance manufacturing device (e.g., a robot) is not blocked by the geometry of the mold (e.g., a tooth) when fixing a pick and place component.
[0227] In some embodiments, processing logic determines a type of dental appliance to be formed by the mold and determines a type indicia to be formed on a pick and place component of the mold based on the type of dental appliance.
[0228] At block 549, processing logic determines a characteristic offset associated with the location of the pick and place component. In some embodiments, the characteristic offset is a block from a negative maximum block offset (e.g., approximately -4.5 mm from the center of the pick and place component) to a positive block offset (e.g., approximately +4.5 mm from the center of the pick and place component) on either side of the beam (e.g., along both side walls of the beam).
[0229] At block 550, processing logic determines an identifier feature to be formed on the beam based on the identifier. The identifier feature may form a bar code (e.g., a 16-digit bar code). The identifier feature may extend from a side wall of the beam. The bar code may be formed based on at least a portion (e.g., 11 digits) of the identifier (e.g., label) other than the control number (e.g., including the PID plus the last three symbols of the identifier: material / jaw and stage).
[0230] At block 551, processing logic determines the layout of the identifier features on the sidewalls of the beam based on the feature offsets. Processing logic can generate control information (e.g., 16 bits per row) and divide the control information into two bytes. The first byte can be located on the first sidewall (e.g., the top side or first side of the beam), and the second byte can be located on the second sidewall (e.g., the bottom side or second side of the beam). In one embodiment, processing logic calculates the right offset from the center of portion 320 to the pin (e.g., based on the top fixture size and bottom fixture size parameters, which can be equal to about 13 mm, so that there is about 6.5 mm on each side along the x-direction (right and left)). Processing logic can fill the identifier features on the right side of the beam (e.g., position as many pins as possible on the right side). Then processing logic can calculate the left offset (e.g., similar to calculating the right offset) and fill the identifier features on the left side of the beam (e.g., similar to filling the identifier features on the right side).
[0231] The identifier characteristic may be represented in a decimal positional number system and thereafter XOR'd with all $16-bit$ parts, starting with the least significant bit.
[0232] For example, if at least part of the identifier is 123456, then:
[0233] Convert from decimal to binary: 123456 becomes 11110001001000000 (or 1E240 in hexadecimal)
[0234] Apply XOR all to the result: 1110001001000000 XOR 1 = 1110001001000001 (or E241 in hex).
[0235] The result can then be displayed on the beam as an identifier feature. Half of the numbers (e.g., the first 8 numbers) are shown along the first side wall, and half of the numbers (e.g., the last 8 numbers) are shown along the second side wall. Each 0 is shown as lacking an identifier feature (e.g., lacking a protruding pin), and each 1 is shown as an identifier (e.g., a protruding pin).
[0236] In some embodiments, processing logic determines the identifier features based on the patient identifier, the material-jaw identifier, and / or the stage identifier. Processing logic may separate the identifier features into a first subset and a second subset, and may cause the first subset of identifier features to be formed on the first side wall of the beam and cause the second subset of identifier features to be formed on the second side wall.
[0237] In some embodiments, processing logic causes a first control pin and a second control pin to be formed on a first sidewall of the beam, wherein a first subset of identifier features extends from the first sidewall of the beam between the first control pin and the second control pin. Processing logic may cause a third control pin and a fourth control pin to be formed on a second sidewall of the beam, wherein a second subset of identifier features extends from the second sidewall of the beam between the third control pin and the fourth control pin.
[0238] refer to Figure 5E According to some embodiments, method 500E is used to identify a mold for forming a dental appliance.
[0239] At block 555, processing logic receives an image of a mold of a patient's dental arch. The image may be captured by an imaging device of the dental appliance manufacturing apparatus, or by an imaging device separate from the dental appliance manufacturing apparatus. The image may be captured before the mold is used in a station of the dental appliance manufacturing apparatus (e.g., a thermoforming station, a trimming station, etc.).
[0240] At block 556, processing logic performs a first analysis on the image. Figure 5F to Figure 5G In some embodiments, block 556 is performed by processing logic without using machine learning.
[0241] At box 557, processing logic determines, based on the first analysis, an area of the image corresponding to a mark (e.g., a cut mark) formed by the marked portion of the beam of the mold. The mark (e.g., a cut mark) can form an identifier. In some embodiments, performing the first analysis on the image (e.g., determining the area) can include matching a template to the marked portion in the image. For example, the template can be a rectangle with a width-to-length ratio that matches the marked portion of the beam. The template can be enlarged or reduced (e.g., while matching the width-to-length ratio) to match the marked portion of the beam. In some embodiments, performing the first analysis on the image includes using a trained machine learning model (e.g., see Figure 5F to Figure 5K ) to determine the region. For example, a machine learning model may be trained using an input of historical images and a target output of historical regions (e.g., an indication of historical regions of historical images). The image of block 555 may be input into the trained machine learning model, and the output may then indicate the region for the labeled portion of the image.
[0242] At block 558, processing logic performs a second analysis on the region of the image. FIG. 5H to FIG. 5I In some embodiments, block 558 is performed by processing logic without using machine learning.
[0243] At block 559, processing logic identifies each digit of an identifier of a mark (e.g., a cut mark) based on a second analysis of the region of the image. The identifier is to be used in producing a dental appliance using the mold. In some embodiments, the second analysis includes using a trained machine learning model (e.g., see FIG. 5H to FIG. 5I ).
[0244] At block 560, processing logic performs a third analysis of the image. Figure 5J to Figure 5K In some embodiments, block 560 is performed by processing logic without using machine learning.
[0245] At box 561, processing logic determines identifier feature presence data based on a third analysis of the image. The identifier feature presence data may indicate whether an identifier feature is present in each potential identifier feature location between control pins. In some embodiments, box 561 includes identifying a portion of the image corresponding to a pick and place component of a beam of a mold. Box 561 may also include identifying in the image a first control pin and a second control pin extending from a first side wall of the beam and a third control pin and a fourth control pin extending from a second side wall of the beam. Box 561 may also include identifying sub-areas of the image between the control pins on either side of the portion of the image corresponding to the pick and place component, a first subset of the sub-areas of the image being between the first control pin and the second control pin along the first side wall of the beam, and a second subset of the sub-areas of the image being between the third control pin and the fourth control pin along the second side wall of the beam. Box 561 may also include determining whether each of the sub-areas of the image corresponds to a corresponding pin extending from the beam. In some embodiments, the third analysis includes using a trained machine learning model (e.g., see Figure 5J to Figure 5K ).
[0246] At box 562, processing logic verifies the identifier determined at box 559 based on the identifier feature presence data of the beam determined at box 561. At box 562, processing logic can compare the identifier based on the mark (e.g., the cut mark) with the identifier based on the identifier feature. In response to the identifier matching, processing logic can cause the mold to be used to form the dental appliance. In response to the identifier not matching, processing logic can cause corrective action to be performed (e.g., providing an alarm, causing manual inspection of the mold, stopping dental appliance manufacturing, etc.).
[0247] refer to Fig. 5F According to certain embodiments, method 500F is associated with training a machine learning model associated with identifying a mold (e.g., determining an area of an image corresponding to a mark formed by a marked portion of a beam of the mold).
[0248] At block 565, processing logic identifies a historical image of a historical marker of a historical mold. The historical image may be Figure 5E The mold of the frame 555 is similar to the mold or a different mold.
[0249] At block 566, processing logic identifies a historical region associated with the historical image. The historical region may be manually identified. The historical region may be determined by one of the methods disclosed herein (e.g., method 500G) and manually verified. The historical region indicates a historical boundary of a marked portion of the beam that forms a mark (e.g., a cut mark) of the beam.
[0250] At box 567, processing logic trains a machine learning model using data inputs including historical images and target outputs including historical regions to generate a trained machine learning model that is configured to generate an output associated with a region of a marked portion of a beam of a predicted mold in response to an image of an input mold.
[0251] refer to Figure 5G In accordance with certain embodiments, method 500G is associated with using a machine learning model associated with identifying a mold (eg, determining an area of an image corresponding to a mark formed by a marked portion of a beam of the mold).
[0252] At block 568, processing logic will (e.g., Figure 5E The image of box 555 is provided as input to the trained machine learning model. The trained machine learning model can be trained by method 500F.
[0253] At block 569, processing logic obtains one or more outputs from the trained machine learning model indicating prediction data, the prediction data including a predicted region of the image corresponding to the marked portion of the beam. The predicted region can be used to identify the marked number of the beam of the mold.
[0254] refer to Figure 5H In accordance with certain embodiments, method 500H is associated with training a machine learning model associated with identifying a mold (e.g., determining a number of marks formed by a marked portion of a beam of a mold).
[0255] At block 570, processing logic identifies a historical sub-region of the historical image of the historical mark of the historical mold. The historical sub-region may be determined by the methods disclosed herein (e.g., method 500I) and manually verified. The historical sub-region may be determined by Figure 5E Box 557 or Figure 5G The area determined by method 500G is divided by the number of digits of the historical marker (eg, determined via user input).
[0256] At block 571, processing logic identifies a historical number associated with the historical sub-region. The historical number may be identified manually. The historical number may be determined by one of the methods disclosed herein (eg, method 5001) and manually verified.
[0257] At box 572, processing logic trains a machine learning model using data inputs including historical sub-regions and target outputs including historical numbers to generate a trained machine learning model that is configured to generate outputs associated with predicting labeled numbers in an image.
[0258] refer to Fig.5IAccording to certain embodiments, method 500I is associated with using a machine learning model associated with identifying a mold (e.g., determining a number of marks formed by a marked portion of a beam of the mold).
[0259] At block 580, processing logic identifies sub-regions of the image based on the region of the marked portion, where each sub-region corresponds to a digit of the identifier of the mold. In some embodiments, processing logic divides the region into equal sub-regions based on a predetermined number of digits (e.g., received via user input, the identifiers of all molds have the same number of digits).
[0260] At block 581, processing logic provides the current sub-region of the image to a trained machine learning model. The trained machine learning model may be trained by method 500H.
[0261] At block 582, processing logic obtains one or more outputs from the trained machine learning model indicating predicted data including a predicted number of an identifier of the mold. The predicted number (eg, identifier) may be used to identify the mold.
[0262] refer to Figure 5J According to certain embodiments, method 500J is associated with training a machine learning model associated with identifying a mold (eg, determining that identifier feature presence data for a beam of the mold).
[0263] At block 580, processing logic identifies a historical sub-region of the historical image associated with the mold. The historical sub-region may be manually identified. The historical sub-region may be determined by a method disclosed herein (e.g., method 500K) and manually verified. The historical sub-region may be a Figure 5K The area determined by blocks 585-587 is divided by the number of potential identifier features of the historical beam (eg, determined via user input).
[0264] At block 581, processing logic identifies historical identifier feature presence data associated with the historical sub-region. The historical identifier feature presence data may be identified manually. The historical identifier feature presence data may be determined by a method disclosed herein (eg, method 500K) and manually verified.
[0265] At box 582, processing logic trains a machine learning model using data inputs comprising historical sub-regions of historical images and target outputs comprising historical identifier feature presence data to generate a trained machine learning model that is configured to generate outputs associated with the identifier feature presence data of the predicted mold.
[0266] refer to Figure 5KAccording to certain embodiments, method 500K is associated with using a machine learning model associated with (eg, determining that identifier feature presence data of a beam of a mold).
[0267] At block 585, processing logic identifies (e.g., Figure 5E A portion of the image of the frame 555 of the mold corresponds to a pick and place component of the beam of the mold. The portion of the image may include a threshold distance around the pick and place component (e.g., a box of 4.5 mm in length centered on the center of the pick and place component).
[0268] At block 586, processing logic identifies in the image a controlling feature of the side wall of the beam (e.g., a Figure 1A The control feature may be a feature (e.g., a pin) on a side wall of the beam that is closest to a distal portion of the dental arch portion of the mold. For example, a first control feature may be a feature on the first side wall that is closest to the first distal portion of the dental arch portion, a second control feature may be a feature on the first side wall that is closest to the second distal portion of the dental arch portion, a third control feature may be a feature on the second side wall that is closest to the first distal portion of the dental arch portion, and a fourth control feature may be a feature on the second side wall that is closest to the second distal portion of the dental arch portion.
[0269] At block 587, processing logic identifies regions between control features on either side of the partial image. The regions may include a first region along a first sidewall between a first control pin and the partial image, a second region along the first sidewall between a second control pin and the partial image, a third region along the second sidewall between a third control pin and the partial image, and a fourth region along the second sidewall between a fourth control pin and the partial image.
[0270] At block 588, processing logic identifies sub-regions of the image based on the regions. Processing logic may determine the sub-regions based on a predetermined amount of spacing of the identifier features along the sidewalls of the beam. For example, for eight potential identifier features along the first sidewall and eight potential identifier features along the second sidewall, processing logic may take the sum of the lengths of the first region and the second region (e.g., the lengths along the sidewalls) and divide the sum by eight, and processing logic may do the same for the third region and the fourth region (e.g., divide the sum of their lengths by eight). Each sub-region corresponds to a potential identifier feature of the beam.
[0271] At block 589, processing logic provides the sub-region to a trained machine learning model. The trained machine learning model may be trained by method 500J.
[0272] At block 590, processing logic obtains one or more outputs from the trained machine learning model indicating prediction data indicating identifier feature presence data for the mold. The identifier feature presence data may be used to identify the mold (eg, or verify an identifier of the mold).
[0273] Figure 6 A diagrammatic representation of a machine in the example form of a computing device 600 is shown within which a set of instructions for causing the machine to execute a program referenced FIG. 5A to FIG. 5K Any one or more methods discussed in the method of. In alternative embodiments, the machine can be connected (e.g., networked) to other machines in a local area network (LAN), an intranet, an extranet, or the Internet. For example, the machine can be networked to a rapid prototyping device, such as a 3D printer or SLA device. The machine can operate with the ability of a server or client machine in a client-server network environment, or as a peer machine operation in a peer-to-peer (or distributed) network environment. The machine can be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a network device, a server, a network router, a switch or a bridge, or any machine capable of executing a set of instructions (sequential or otherwise) specifying the action to be taken by the machine. In addition, although only a single machine is shown, the term "machine" should also be considered to include any collection of machines (e.g., computers) that execute a set (or multiple sets) of instructions to execute any one or more methods discussed herein, either individually or jointly.
[0274] In some embodiments, the computing device 600 is one or more of the controller 402, the client device 404, the dental appliance manufacturing apparatus 406, the imaging device 408, the prediction server 412, the server machine 470, or the server machine 480. In some embodiments, the computing device 600 includes Figure 6 One or more of the components shown.
[0275] The example computing device 600 includes a processing device 602, a main memory 604 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), etc.), a static memory 606 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., a data storage device 628), which communicate with each other via a bus 608.
[0276] Processing device 602 represents one or more general-purpose processors, such as a microprocessor, a central processing unit, etc. More specifically, processing device 602 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor implementing a combination of instruction sets. Processing device 602 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. Processing device 602 is configured to execute processing logic (instructions 626) for performing the operations and steps discussed herein.
[0277] The computing device 600 may also include a network interface device 622 for communicating with a network 664. The computing device 600 may also include a video display unit 610 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 612 (e.g., a keyboard), a cursor control device 614 (e.g., a mouse), and a signal generating device 620 (e.g., a speaker).
[0278] The data storage device 628 may include a machine-readable storage medium (or more specifically, a non-transitory machine-readable storage medium) 624 on which is stored one or more sets of instructions 626 implementing any one or more of the methods or functions described herein. A non-transitory machine-readable storage medium refers to a storage medium other than a carrier wave. The instructions 626 may also reside completely or at least partially within the main memory 604 and / or within the processing device 602 during execution thereof by the computing device 600, the main memory 604 and the processing device 602 also constituting computer-readable storage media.
[0279] The computer readable storage medium 624 may also be used to store one or more instructions for dental appliance production and / or the dental appliance generator 420, which may execute reference FIG. 5A to FIG. 5K The computer-readable storage medium 624 may also store a software library containing methods for invoking the dental appliance generator 420. Although the computer-readable storage medium 624 is shown as a single medium in the example embodiment, the term "non-transitory machine-readable storage medium" should be considered to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store one or more sets of instructions. The term "non-transitory machine-readable storage medium" should also be considered to include any medium that is capable of storing or encoding a set of instructions for execution by a machine and causing the machine to perform any one or more of the methods of the present disclosure. Therefore, the term "non-transitory machine-readable storage medium" should be considered to include, but is not limited to, solid-state memory and optical and magnetic media.
[0280] Fig. 7A An exemplary tooth repositioning dental appliance or brace 700 is shown that can be worn by a patient to achieve progressive repositioning of individual teeth 702 in a jaw. The brace 700 can be formed from a mold 100 that includes a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein. The brace can include a shell (e.g., a continuous polymer shell or a segmented shell) having a tooth receiving cavity that receives and elastically repositions the teeth. The brace or a portion thereof can be indirectly manufactured using a physical model of the teeth. For example, a physical model of the teeth and a sheet of a suitable polymer material layer can be used to form an appliance (e.g., a polymer appliance). As used herein, a "polymer material" can include any material formed from a polymer. As used herein, "polymer" may refer to a molecule consisting of repeating structural units connected by covalent chemical bonds, characterized by a large number of repeating units (e.g., equal to or greater than 3 repeating units, optionally, equal to or greater than 10 repeating units in some embodiments, greater than or equal to 30 repeating units in some embodiments) and a high molecular weight (e.g., greater than or equal to 10,000 Da, greater than or equal to 50,000 Da or greater than or equal to 100,000 Da in some embodiments). A polymer is typically the polymerization product of one or more monomer precursors. The term polymer includes homopolymers, or polymers that are substantially composed of a single repeating monomer subunit. The term polymer also includes copolymers formed when two or more different types of monomers are connected in the same polymer. Useful polymers include organic polymers or inorganic polymers, which can be in an amorphous, semi-amorphous, crystalline or semi-crystalline state. Polymers can include polyolefins, polyesters, polyacrylates, polymethacrylates, polystyrenes, polypropylene, polyethylene, polyethylene terephthalate, polylactic acid, polyurethanes, epoxy polymers, polyethers, polyvinyl chloride, polysiloxanes, polycarbonates, polyamides, polyacrylonitrile, polybutadiene, polycycloolefins, and copolymers. The systems and / or methods provided herein are compatible with a range of plastics and / or polymers. Therefore, this list is not all inclusive, but exemplary. Plastics can be thermosetting plastics or thermoplastics. Plastics can be thermoplastics.
[0281] Examples of materials suitable for use with the embodiments disclosed herein include, but are not limited to, those described in the following patent applications filed by Alleyne Technologies, Inc.: “MULTILAYER DENTAL APPLIANCES AND RELATEDMETHODS AND SYSTEMS,” U.S. Pat. No. 9,655,691, filed May 14, 2012, by Li et al.; “SYSTEMS AND METHODS FOR VARYING ELASTIC MODULUS APPLIANCES,” U.S. Pat. No. 6,964,564, filed July 26, 2002, by Phan et al.; “METHODS OF MAKING ORTHODONTIC APPLIANCES,” U.S. Pat. No. 7,641,828, filed October 12, 2004, by DeSimone et al.; “TREATMENT OF TEETH BY ALIGNERS (Treating Teeth with Aligners),” U.S. Patent No. 8,740,614 to Wen et al., filed on July 29, 2009; and any applications (including published and issued patents) claiming or providing the benefit of the same, including any divisional, continuation, or continuation-in-part thereof, the contents of which are incorporated herein by reference.
[0282] Examples of materials suitable for embodiments disclosed herein include a hard polymer layer disposed between two soft polymer layers. In some embodiments, the hard inner polymer layer includes a copolyester and has a polymer layer elastic modulus. In some embodiments, the first soft outer polymer layer and the second soft outer polymer layer both include a thermoplastic polyurethane elastomer, and both have a soft polymer elastic modulus less than the elastic modulus of the hard polymer layer, a flexural modulus greater than about 35,000 psi, a hardness of about 60A to about 85D, and a thickness in the range of 25 microns to 100 microns. In some embodiments, the hard inner polymer layer is disposed between the first soft outer polymer layer and the second soft outer polymer layer to reduce the drop in the elastic positioning force applied to the teeth when the appliance is worn. The hard polymer layer may include polyester, copolyester, polycarbonate, thermoplastic polyurethane, polypropylene, polyethylene, polypropylene and polyethylene copolymer, acrylic acid, cyclic block copolymer, polyetheretherketone, polyamide, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, polytrimethylene terephthalate, or a combination thereof (e.g., a mixture of at least two of the listed hard polymer materials). In some embodiments, the hard polymer layer includes two or more hard polymer layers. The soft outer polymer material may include styrene block copolymer (SBC), silicone rubber, elastomeric alloy, thermoplastic elastomer (TPE), thermoplastic vulcanized rubber (TPV) elastomer, polyurethane elastomer, block copolymer elastomer, polyolefin blend elastomer, thermoplastic copolyester elastomer, thermoplastic polyamide elastomer, or a combination thereof (e.g., a mixture of at least two of the listed soft polymer materials). The soft polymer layer may be the same material or different materials.
[0283] Examples of materials suitable for the embodiments disclosed herein include an intermediate layer arranged between two layers. The two layers individually include a thermoplastic polymer having a flexural modulus of about 1,000 MPa to 2,500 MPa and a glass transition temperature and / or melting point of about 80°C to 180°C. The intermediate layer includes a polyurethane elastomer having a flexural modulus of about 50 MPa to about 500 MPa and a glass transition temperature and / or melting point of about 90°C to about 220°C. The combined thickness of the intermediate layer and the outer layer of the polymer sheet composition is 250 microns to 2000 microns, and the flexural modulus is 500 MPa to 1500 MPa. In some embodiments, the outer layer includes one or more of a copolyester, a polycarbonate, a polyester polycarbonate blend, a polyurethane, a polyamide, or a polyolefin. The intermediate layer may have a Shore hardness of A90 to D55 and a compression setting of less than 35% after 22 hours at 25°C. In some embodiments, the outer layers have a lateral restoring force of less than 100 Newtons (N) / square centimeter when displayed at 0.05 mm to 0.1 mm relative to each other. In some embodiments, the interaction peel strength between the outer layer and the intermediate layer is greater than 50 N / 2.5 cm. In some embodiments, the combined thickness of the outer layers is 50 microns to 1,000 microns. In some embodiments, one or more of the outer layers includes a microcrystalline polyamide comprising 50 to 100 mole % of a C6 to C14 aliphatic diacid moiety and about 50 to 100 mole % of 4,4'-methylene-bis(cyclohexylamine), having a glass transition temperature between about 100°C and 180°C, a heat of fusion of less than 20 J / g, and a light transmittance greater than 80%. In some embodiments, one or more of the outer layers comprises a copolyester comprising: a dicarboxylic acid component comprising 70 mol% to 100 mol% of terephthalic acid residues; and a diol component comprising (i) 0 mol% to 90 mol% of ethylene glycol, (ii) 5 mol% to 50 mol% of 2,2,4,4-tetramethyl-1,3-cyclobutanediol residues, (iii) 50 mol% to 95 mol% of 1,4-cyclohexanedimethanol residues, and (iv) 0 mol% to 1 mol% of a polyol having three or more hydroxyl groups, wherein the sum of the mole % of diol residues (i), (ii), (iii) and (iv) is 100 mol%, and the copolyester exhibits a glass transition temperature Tg of 80°C to 150°C. In some embodiments, the middle layer comprises an aromatic polyether polyurethane having a Shore hardness of A90 to D55 and a compression setting of less than 35%, wherein the interlayer peel strength between the outer layer and the middle layer is greater than 50 N / 2.5 cm.In some embodiments, one or more of the outer layers comprises a polyurethane comprising: a diisocyanate comprising 80 mol % to 100 mol % of methylene diphenyl diisocyanate residues and / or hydrogenated methylene diphenyl diisocyanate; and a diol component comprising: (i) 0 mol % to 100 mol % of hexamethylene glycol; and (ii) 0 mol % to 50 mol % of 1,4-cyclohexanedimethanol, wherein the sum of (i) and (ii) is greater than 90 mol %, and the polyurethane has a glass transition temperature, Tg, of about 85°C to about 150°C.
[0284] Although polymer braces are discussed herein, the disclosed technology can also be applied to braces with different materials. Some embodiments are discussed herein with reference to orthodontic braces (also referred to as braces). However, the embodiments also extend to other types of shells formed on molds, such as orthodontic retainers, orthodontic splints, sleeping appliances for oral insertion (e.g., for minimizing snoring, sleep apnea, etc.) and / or shells for non-dental applications. Therefore, it should be understood that the embodiments of the braces herein are also applicable to other types of shells. For example, the principles, features and methods discussed can be applied to any application or process, wherein it is useful to perform simultaneous formation of multiple shells, wherein the multiple shells are shells of any suitable type forming an adapter, such as eyeglass frames, contact lenses or glass lenses, hearing aids or earplugs, artificial kneecaps, prostheses and devices, orthopedic inserts, and protective equipment, such as knee pads, sports crotch guards, or elbow, chin and shin guards and other similar sports / protective devices.
[0285] The appliance 700 can be fitted on all teeth present in the maxilla or mandible, or on less than all teeth. The appliance can be specially designed to accommodate the patient's teeth (e.g., the topography of the tooth receiving cavity matches the topography of the patient's teeth), and can be manufactured based on a positive or negative mold of the patient's teeth generated by an impression, a scan, etc. Alternatively, the appliance can be a universal appliance configured to accommodate teeth, but is not necessarily shaped to match the topography of the patient's teeth. In some cases, only some teeth accommodated by the appliance will be repositioned by the appliance, while other teeth can provide a base or anchoring area for holding the appliance in place when the appliance applies force to one or more teeth that are the target of repositioning. In some cases, during treatment, some, most, or even all teeth will be repositioned at a certain point. The teeth that are moved can also be used as a base or anchor for holding the appliance when the appliance is worn by the patient. Typically, wires or other devices for holding the appliance in place on the teeth will not be provided. However, in some cases, it may be desirable or necessary to provide a separate attachment or other anchoring element 704 on the tooth 702, with a corresponding receptacle or hole 706 in the appliance 700 so that the appliance can exert a selected force on the tooth. The apparatus used in the system) is described in many patents and patent applications of Alleyne Technologies, Inc. (including, for example, U.S. Patent Nos. 6,450,807 and 5,975,893) and on the company's website (which can be accessed on the Internet (see, for example, URL Examples of tooth-mounted attachments suitable for use with orthodontic appliances are also described in patents and patent applications assigned to Alleyne Technologies, Inc., including, for example, U.S. Patent Nos. 6,309,215 and 6,830,450.
[0286] Figure 7BA tooth repositioning system 710 including a plurality of appliances 712, 714, 716 is shown. The appliances 712, 714, 716 may be formed from a mold 100 including a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein. Alternatively, the appliances 712, 714, 716 may be directly manufactured using a rapid prototyping machine such as discussed above. Any appliance described herein may be designed and / or provided as part of a set of multiple appliances used in a tooth repositioning system. Each appliance may be configured such that a tooth receiving cavity has a geometry corresponding to an intermediate or final tooth arrangement intended for the appliance. By placing a series of incremental position adjustment appliances on the patient's teeth, the patient's teeth may be progressively repositioned from an initial tooth arrangement to a target tooth arrangement. For example, the tooth repositioning system 710 may include: a first appliance 712 corresponding to an initial tooth arrangement; one or more intermediate appliances 714 corresponding to one or more intermediate arrangements; and a final appliance 716 corresponding to a target arrangement. The target tooth arrangement can be the planned final tooth arrangement selected for the patient's teeth at the end of all planned orthodontic treatment. Alternatively, the target tooth arrangement can be one of a number of intermediate arrangements for the patient's teeth during the course of orthodontic treatment, which can include a variety of different treatment scenarios, including but not limited to situations where surgery is recommended, situations where interproximal reduction (IPR) is appropriate, situations where a progress check is scheduled, situations where anchor placement is optimal, situations where palatal expansion is desired, situations involving restorative dentistry (e.g., inlays, onlays, crowns, bridges, implants, veneers, etc.), etc. Therefore, it should be understood that the target tooth arrangement can be any planned resulting arrangement of the patient's teeth following one or more incremental repositioning stages. Likewise, the initial tooth arrangement can be any initial arrangement of the patient's teeth followed by one or more incremental repositioning stages.
[0287] In some embodiments, the appliances 712, 714, 716 (or a portion thereof) can be produced using indirect manufacturing techniques, such as by thermoforming on a male or female mold. Indirect manufacturing of orthodontic appliances can involve making a male or female mold of the patient's dentition in a target arrangement (e.g., by rapid prototyping, milling, etc.), and thermoforming one or more sheets of material on the mold to produce the appliance housing.
[0288] In an example of indirect manufacturing, a mold of the patient's dental arch can be made from a digital model of the dental arch, and the shell can be formed on the mold (e.g., by thermoforming a polymer sheet over the mold of the dental arch and then trimming the thermoformed polymer sheet). The manufacturing of the mold can be performed by a rapid prototyping machine (e.g., a stereolithography (SLA) 3D printer). After the digital model of the appliance 712, 714, 716 has been generated by a computing device (such as Figure 6 The rapid prototyping machine may receive the digital model of the mold of the dental arch and / or the digital model of the appliance 712, 714, 716 after processing by processing logic of a computing device in the rapid prototyping machine. The processing logic may include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by a processing device), firmware, or a combination thereof. For example, one or more operations may be performed by a processing device executing the dental appliance generator 420.
[0289] In order to make the mold, the shape of the dental arch used for the patient during the treatment stage is determined based on the treatment plan. In the example of orthodontics, the treatment plan can be generated based on the intraoral scan of the dental arch to be modeled. An intraoral scan of the patient's dental arch can be performed to generate a 3D virtual model (mold) of the patient's dental arch. For example, a full scan of the patient's mandibular arch and / or maxillary arch can be performed to generate its 3D virtual model. The intraoral scan can be performed by creating multiple overlapping intraoral images from different scanning stations and then stitching the intraoral images together to provide a composite 3D virtual model. In other applications, a virtual 3D model can also be generated based on a scan of the object to be modeled or based on the use of computer-aided drawing technology (e.g., for designing a virtual 3D mold). Alternatively, an initial negative film (e.g., a dental impression, etc.) can be generated from the actual object to be modeled. The negative film can then be scanned to determine the shape of the positive film to be produced.
[0290] Once a virtual 3D model of the patient's dental arch is generated, the dentist can determine the desired treatment outcome including the final position and orientation of the patient's teeth. The processing logic can then determine multiple treatment stages to gradually move the teeth from the starting position and orientation to the target final position and orientation. By calculating the progression of tooth movement throughout the orthodontic treatment from the initial tooth placement and orientation to the final corrected tooth placement and orientation, the shape of the final virtual 3D model and each intermediate virtual 3D model can be determined. For each treatment stage, a separate virtual 3D model of the patient's dental arch at that treatment stage can be generated. The shape of each virtual 3D model will be different. The original virtual 3D model, the final virtual 3D model, and each intermediate virtual 3D model are all unique and customized for the patient.
[0291] Thus, multiple different virtual 3D models (digital designs) of a dental arch can be generated for a single patient. The first virtual 3D model can be a unique model of the patient's dental arch and / or teeth as currently presented by the patient, and the final virtual 3D model can be a model of the patient's dental arch and / or teeth after correction of one or more teeth and / or jaws. Multiple intermediate virtual 3D models can be modeled, each of which can be progressively different from the previous virtual 3D model.
[0292] Each virtual 3D model of a patient's dental arch can be used to generate a uniquely customized physical mold of the dental arch at a specific treatment stage. The shape of the mold can be based at least in part on the shape of the virtual 3D model of the treatment stage. The virtual 3D model can be represented in a file such as a computer-aided drawing (CAD) file or a 3D printable file such as a stereolithography (STL) file. The virtual 3D model of the mold can be sent to a third party (e.g., a clinician's office, a laboratory, a manufacturing plant, or other entity). The virtual 3D model may include instructions that will control a manufacturing system or device to produce a mold with a specified geometry.
[0293] A clinician's office, laboratory, manufacturing plant, or other entity can receive a virtual 3D model of the mold (i.e., a digital model that has been created as described above). The entity can input the digital model into a rapid prototyping machine. The rapid prototyping machine then uses the digital model to manufacture the mold. An example of a rapid prototyping manufacturing machine is a 3D printer. 3D printing includes any layer-based additive manufacturing process. 3D printing can be achieved using additive processes, in which continuous layers of material are formed in a specified shape. 3D printing can be performed using extrusion deposition, granular material bonding, lamination, photopolymerization, continuous liquid interface production (CLIP), or other techniques. 3D printing can also be achieved using subtractive processes (such as milling).
[0294] An appliance can be formed from each mold and, when applied to the patient's teeth, can provide force to move the patient's teeth as prescribed by the treatment plan. The shape of each appliance is unique and customized for a specific patient and a specific stage of treatment. In one example, the appliances 712, 714, 716 can be pressure molded or thermoformed on the mold. Each mold can be used to make an appliance that will apply force to the patient's teeth at a specific stage of orthodontic treatment. Each appliance 712, 714, 716 has a tooth receiving cavity that receives a tooth and resiliently repositions the tooth according to the specific stage of treatment.
[0295] In one embodiment, a sheet of material is formed or thermoformed on a mold. For example, the sheet can be a polymer sheet (e.g., an elastic thermopolymer, a sheet of polymer material, etc.). In order to thermoform the shell on the mold, the sheet of material can be heated to a temperature at which the sheet becomes soft. Pressure can be applied to the sheet at the same time to form the now soft sheet around the mold. Once the sheet cools, it will have a shape that conforms to the mold. In one embodiment, a release agent (e.g., a non-stick material) is applied to the mold before forming the shell. This can facilitate the subsequent removal of the mold from the shell. Force can be applied to lift the utensil from the mold. In some cases, cracking, warping, or deformation may be caused by the removal force. Therefore, embodiments disclosed herein can determine one or more possible damage points that may occur in the digital design of the utensil before manufacturing, and corrective actions can be performed.
[0296] Additional information may be added to the appliance. The additional information may be any information related to the appliance. Examples of such additional information include a part number identifier, a patient name, a patient identifier, a case number, a sequence identifier (e.g., indicating which appliance in a treatment sequence a particular liner is), a manufacturing date, a clinician's name, a logo, etc. For example, after determining that there is a possible damage point in the digital design of the appliance, an indicator may be inserted into the digital design of the appliance. In some embodiments, the indicator may represent a recommended location to begin removing the polymer appliance to prevent damage points from occurring during removal.
[0297] In some embodiments, a library of removal methods / patterns can be established and referenced when simulating the removal of an appliance in a numerical simulation. Different patients or production technicians may tend to remove the appliance differently, and there may be some typical patterns. For example: 1) Some patients first lift from the lingual side of the posterior (first to the left, then to the right, and vice versa), then go around the dental arch from the left / right posterior segment to the right / left posterior segment; 2) Similar to #1, but some other patients only lift one side of the posterior side, then go around the dental arch; 3) Similar to #1, but some patients lift from the buccal side instead of the lingual side of the posterior side; 4) Some patients lift from the anterior incisor and pull hard to remove the appliance; 5) Some other patients grab the lingual and buccal sides of the posterior position and pull out both sides at the same time; 6) Some other patients grab a random tooth in the middle. The library may also include removal guidelines provided by the manufacturer of the appliance. The removal method may also depend on the presence or absence of attachments on the teeth, as some of the above methods may make the removal method more comfortable. Based on the attachment situation on each tooth, it can be determined how each patient is likely to remove the appliance, and the removal process adjusted for that patient in that particular simulation.
[0298] After the appliance is formed on the mold for the treatment stage, the appliance is removed from the mold (e.g., the appliance is automatically removed from the mold), and then the appliance is trimmed along the cutting line (also called the trimming line). The processing logic can determine the cutting line for the appliance. The determination of the cutting line can be based on a virtual 3D model of the dental arch at a specific treatment stage, based on a virtual 3D model of the appliance to be formed on the dental arch, or based on a combination of a virtual 3D model of the dental arch and a virtual 3D model of the appliance. The position and shape of the cutting line can be important for the function of the appliance (e.g., the ability of the appliance to apply the desired force to the patient's teeth) and the fit and comfort of the appliance. For shells such as orthodontic appliances, orthodontic retainers, and orthodontic splints, the trimming of the shell may play an important role in the efficacy of the shell for its intended purpose (e.g., aligning, retaining, or positioning one or more teeth of the patient) and the fit of the shell on the patient's dental arch. For example, if the shell is trimmed too much, the shell may lose rigidity and the ability of the shell to apply force to the patient's teeth may be impaired. If the shell is trimmed too much, the shell may become weak at that location and may become a point of failure when the patient removes the shell from their teeth or removes the shell from the mold. In some embodiments, as one of the corrective measures taken when it is determined that there is a possible point of failure in the digital design of the appliance, the cut line can be modified in the digital design of the appliance.
[0299] On the other hand, if the shell is trimmed too little, some parts of the shell may hit the patient's gums and cause discomfort, swelling and / or other dental problems. In addition, if the shell is trimmed too little in one position, the shell may be too hard in that position. In some embodiments, the cutting line can be a straight line through the appliance at the gum line, below the gum line, or above the gum line. In some embodiments, the cutting line can be a gum cutting line, which represents the interface between the appliance and the patient's gums. In such an embodiment, the cutting line controls the distance between the edge of the appliance and the patient's gum line or gum surface.
[0300] Each patient has a unique dental arch with unique gums. Therefore, the shape and position of the cutting line can be unique and customized for each patient and each treatment stage. For example, the cutting line is customized to be along the gum line (also called the gingival line). In some embodiments, the cutting line can be away from the gum line in some areas and on the gum line in other areas. For example, in some cases, it may be desirable for the cutting line to be away from the gum line (e.g., not contacting the gums), wherein in the interproximal area between the teeth, the shell will contact the teeth and be on the gum line (e.g., contacting the gums). Therefore, it is important to trim the shell along the predetermined cutting line.
[0301] In some embodiments, the dental appliances (e.g., orthodontic appliances) herein (or portions thereof) can be produced using direct manufacturing, such as additive manufacturing techniques (also referred to herein as "3D printing") or subtractive manufacturing techniques (e.g., milling). In some embodiments, direct manufacturing involves forming an object (e.g., an orthodontic appliance or a portion thereof) without using a physical template (e.g., a mold, a mask, etc.) to define the geometry of the object. Additive manufacturing techniques can be categorized as follows: (1) vat photopolymerization (e.g., stereolithography), in which an object is constructed layer by layer from a vat of liquid photopolymer resin; (2) material jetting, in which material is sprayed onto a build platform using a continuous or drop-on-demand (DOD) process; (3) binder jetting, in which alternating layers of build material (e.g., powder-based material) and binder material (e.g., liquid binder) are deposited by a print head; (4) fused deposition modeling (FDM), in which material is pumped through a nozzle, heated, and deposited layer by layer; (5) powder bed fusion, including but not limited to direct metal laser sintering (DMLS), electron beam melting (EBM), selective heat sintering (SHS), selective laser melting (SLM), and selective laser sintering (SLS); (6) sheet lamination, including but not limited to layered object manufacturing (LOM) and ultrasonic additive manufacturing (UAM); and (7) directed energy deposition, including but not limited to laser engineered mesh forming, directed light manufacturing, direct metal deposition, and 3D laser cladding. For example, stereolithography can be used to directly manufacture one or more of the utensils 712, 714, and 716. In some embodiments, stereolithography involves selectively polymerizing a photosensitive resin (e.g., a photopolymer) using light (e.g., ultraviolet light) according to a desired cross-sectional shape. By sequentially polymerizing multiple object cross sections, the object geometry can be established in a layer-by-layer manner. As another example, selective laser sintering can be used to directly manufacture the utensils 712, 714, and 716. In some embodiments, selective laser sintering involves selectively melting and fusing layers of powdered materials using a laser beam according to a desired cross-sectional shape to establish the object geometry. As yet another example, the utensils 712, 714, and 716 can be directly manufactured by fused deposition molding. In some embodiments, fused deposition molding involves melting and selectively depositing filaments of thermoplastic polymers in a layer-by-layer manner to form an object. In yet another example, material spraying can be used to directly manufacture the utensils 712, 714, and 716. In some embodiments, material spraying involves spraying or extruding one or more materials onto a build surface to form a continuous layer of the object geometry.
[0302] In some embodiments, the direct manufacturing method provided herein establishes the geometry of the object in a layer-by-layer manner, wherein continuous layers are formed in discrete building steps. Alternatively or in combination, a direct manufacturing method that allows the continuous establishment of the geometry of the object can be used, referred to herein as "continuous direct manufacturing". Various types of continuous direct manufacturing methods can be used. As an example, in some embodiments, "continuous liquid interphase printing" is used to manufacture apparatus 712, 714 and 716, wherein, by forming a gradient of partially cured resin between the building surface of the object and the "dead zone" that inhibits polymerization, the object is continuously built from a reservoir of a photopolymerizable resin. In some embodiments, a semipermeable membrane is used to control the delivery of a photopolymerization inhibitor (e.g., oxygen) into the dead zone to form a polymerization gradient. Continuous liquid interphase printing can achieve a manufacturing speed that is about 25 times to about 100 times faster than other direct manufacturing methods, and can achieve a speed that is about 1000 times faster by combining a cooling system. Continuous liquid interphase printing is described in U.S. Patent Publication Nos. 2015 / 0097315, 2015 / 0097316, and 2015 / 0102532, the disclosures of each of which are incorporated herein by reference in their entirety.
[0303] As another example, a continuous direct manufacturing method can achieve continuous construction of object geometry by continuous movement of the build platform during the irradiation phase (e.g., along the vertical or Z direction), so that the hardening depth of the irradiated photopolymer is controlled by the movement speed. Thus, continuous polymerization of material on the build surface can be achieved. Such methods are described in U.S. Patent No. 7,892,474, the disclosure of which is incorporated herein by reference in its entirety.
[0304] In another example, a continuous direct manufacturing method may involve extruding a composite material consisting of a curable liquid material around a solid strand. The composite material may be extruded along a continuous three-dimensional path to form an object. Such methods are described in U.S. Patent Publication No. 2014 / 0061974, the disclosure of which is incorporated herein by reference in its entirety.
[0305] In yet another example, a continuous direct manufacturing method utilizes a "heliolithography" method, in which a liquid photopolymer is cured using focused radiation while the build platform is continuously rotated and raised. Thus, object geometry can be continuously built along a spiral construction path. Such methods are described in U.S. Patent Publication No. 2014 / 0265034, the disclosure of which is incorporated herein by reference in its entirety.
[0306] Direct manufacturing method provided herein can be compatible with a variety of materials, including but not limited to one or more of the following: polyester, copolyester, polycarbonate, thermoplastic polyurethane, polypropylene, polyethylene, copolymer of polypropylene and polyethylene, acrylic acid, cyclic block copolymer, polyetheretherketone, polyamide, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, polytrimethylene terephthalate, styrene block copolymer (SBC), silicone rubber, elastomer alloy, thermoplastic elastomer (TPE), thermoplastic vulcanizate (TPV) elastomer, polyurethane elastomer, block copolymer elastomer, polyolefin blended elastomer, thermoplastic copolyester elastomer, thermoplastic polyamide elastomer, thermosetting material or its combination. Material for direct manufacturing can be provided in uncured form (for example, as liquid, resin, powder, etc.), and can be cured (for example, by photopolymerization, light curing, gas curing, laser curing, crosslinking, etc.), so as to form orthodontic appliance or a part thereof. The characteristic of material before curing may be different from the characteristic of material after curing. Once cured, the materials herein may exhibit sufficient strength, rigidity, durability, biocompatibility, etc., for use in orthodontic appliances. The properties of the materials used after curing may be selected based on the desired properties of the corresponding part of the appliance.
[0307] In some embodiments, relatively rigid portions of an orthodontic appliance may be formed by direct manufacturing using one or more of the following materials: polyester, copolyester, polycarbonate, thermoplastic polyurethane, polypropylene, polyethylene, copolymers of polypropylene and polyethylene, acrylic, cyclic block copolymers, polyetheretherketone, polyamide, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, and / or polytrimethylene terephthalate.
[0308] In some embodiments, the relatively elastic portion of the orthodontic appliance can be formed by direct manufacturing using one or more of the following materials: styrene block copolymers (SBC), silicone rubber, elastomeric alloys, thermoplastic elastomers (TPE), thermoplastic vulcanizate (TPV) elastomers, polyurethane elastomers, block copolymer elastomers, polyolefin blend elastomers, thermoplastic copolyester elastomers and / or thermoplastic polyamide elastomers.
[0309] Optionally, the direct manufacturing methods described herein allow for the manufacture of appliances comprising multiple materials, referred to herein as "multi-material direct manufacturing". In some embodiments, the multi-material direct manufacturing methods involve the simultaneous formation of an object from multiple materials in a single manufacturing step. For example, a multi-tip extrusion device can be used to selectively dispense multiple types of materials from different material supply sources so as to manufacture an object from multiple different materials. Such a method is described in U.S. Patent No. 6,749,414, the disclosure of which is incorporated herein by reference in its entirety. Alternatively or in combination, the multi-material direct manufacturing methods may involve the formation of an object from multiple materials in multiple sequential manufacturing steps. For example, a first portion of an object may be formed from a first material according to any direct manufacturing method herein, and then a second portion of the object may be formed from a second material according to the methods herein, and so on until the entire object has been formed.
[0310] Direct manufacturing can provide various advantages compared to other manufacturing methods. For example, in contrast to indirect manufacturing, direct manufacturing allows orthodontic appliances to be produced without using any molds or templates to shape the appliances, thereby reducing the number of manufacturing steps involved and improving the resolution and accuracy of the final appliance geometry. In addition, direct manufacturing allows precise control of the three-dimensional geometry of the appliance, such as the thickness of the appliance. Complex structures and / or auxiliary components can be formed as a single piece with the appliance housing in a single manufacturing step, rather than being added to the housing in a separate manufacturing step. In some embodiments, direct manufacturing is used to produce appliance geometries that are difficult to create using alternative manufacturing techniques, such as appliances with very small or fine features, complex geometries, undercuts, interproximal structures, and shells with variable thickness and / or internal structures (e.g., to improve strength by reducing weight and reducing material usage). For example, in some embodiments, the direct manufacturing method of the present invention allows the manufacture of orthodontic appliances with feature sizes less than or equal to about 5 μm, or in the range of about 5 μm to about 50 μm, or in the range of about 20 μm to about 50 μm.
[0311] The direct manufacturing techniques described herein can be used to produce appliances with substantially isotropic material properties (e.g., substantially the same or similar strength in all directions). In some embodiments, the direct manufacturing methods herein allow the production of orthodontic appliances whose strength varies no more than about 25%, about 20%, about 15%, about 10%, about 5%, about 1%, or about 0.5% in all directions. In addition, the direct manufacturing methods herein can be used to manufacture orthodontic appliances at a faster rate than other manufacturing techniques. In some embodiments, the direct manufacturing methods herein allow the production of orthodontic appliances in a time interval of less than or equal to about 1 hour, about 30 minutes, about 25 minutes, about 20 minutes, about 15 minutes, about 10 minutes, about 5 minutes, about 4 minutes, about 3 minutes, about 2 minutes, about 1 minute, or about 30 seconds. Such manufacturing speeds allow, for example, rapid "chairside" production of custom appliances during routine appointments or examinations.
[0312] In some embodiments, the direct manufacturing methods described herein implement process control of various machine parameters for the direct manufacturing system or device to ensure that the resulting appliance is manufactured with high precision. Such precision may be advantageous for ensuring that the desired force system is accurately delivered to the teeth in order to effectively cause tooth movement. Process control may be implemented to account for process variations caused by a variety of sources, such as material properties, machine parameters, environmental variables, and / or post-processing parameters.
[0313] Material properties may vary depending on the properties of the raw materials, the purity of the raw materials, and / or process variables during the mixing of the raw materials. In many embodiments, the resin or other material for direct manufacturing should be manufactured under strict process control to ensure that the optical properties, material properties (e.g., viscosity, surface tension), physical properties (e.g., modulus, strength, elongation), and / or thermal properties (e.g., glass transition temperature, heat deformation temperature) are small. Process control for material manufacturing processes can be achieved by screening the physical properties of the raw materials and / or controlling temperature, humidity, and / or other process parameters during the mixing process. By performing process control on the material manufacturing process, the variability of the process parameters can be reduced and the material properties of each batch of materials can be made more uniform. As further discussed herein, the residual variability in material properties can be compensated by process control on the machine.
[0314] The machine parameters may include curing parameters. For curing systems based on digital light processing (DLP), the curing parameters may include power, curing time, and / or grayscale of the entire image. For laser-based curing systems, the curing parameters may include power, speed, beam size, beam shape, and / or power distribution of the beam. For printing systems, the curing parameters may include material drop size, viscosity, and / or curing power. These machine parameters (e.g., certain parameters for each 1-x layer and certain parameters after each build) may be regularly monitored and adjusted as part of process control on the manufacturing machine. Process control may be achieved by including sensors on the machine that measure power and other beam parameters per layer or every few seconds and automatically adjust them through a feedback loop. For DLP machines, grayscale may be measured and calibrated at the end of each build. In addition, material properties and / or light properties may be provided to the manufacturing machine, and the machine process control module may use these parameters to adjust machine parameters (e.g., power, time, grayscale, etc.) to compensate for changes in material properties. By performing process control on the manufacturing machine, changes in tool accuracy and residual stress may be reduced.
[0315] In many embodiments, environmental variables (eg, temperature, humidity, sunlight, or exposure to other energy / curing sources) are maintained within narrow ranges to reduce variations in tool thickness and / or other properties. Optionally, machine parameters may be adjusted to compensate for environmental variables.
[0316] In many embodiments, the post-processing of the utensil includes cleaning, post-curing and / or support removal processes. Relevant post-processing parameters can include the purity of the cleaning agent, cleaning pressure and / or temperature, cleaning time, post-curing energy and / or time, and / or the consistency of the support removal process. These parameters can be measured and adjusted as a part of the process control scheme. In addition, the physical properties of the utensil can be changed by modifying the post-processing parameters. Adjusting the post-processing machine parameters can provide another way to compensate for the changes in material properties and / or machine characteristics.
[0317] Once a device (eg, an appliance) is manufactured, it may be inspected using the systems and / or methods described above.
[0318] The configuration of the orthodontic appliances herein can be determined based on the patient's treatment plan (e.g., a treatment plan involving the sequential application of multiple appliances to gradually reposition the teeth). Computer-based treatment planning and / or appliance manufacturing methods can be used to facilitate the design and manufacture of the appliances. For example, one or more appliance components described herein can be digitally designed and manufactured with the aid of a computer-controlled manufacturing device (e.g., computer numerical control (CNC) milling, computer-controlled rapid prototyping (such as 3D printing), etc.). The computer-based methods proposed herein can improve the accuracy, flexibility, and convenience of appliance manufacturing.
[0319] Figure 7CA method 750 of orthodontic treatment using multiple appliances is shown according to an embodiment. One or more of the multiple appliances can be formed by a mold 100 that includes a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein. The method 750 can be practiced using any appliance or set of appliances described herein. In box 760, a first orthodontic appliance is applied to the patient's teeth to reposition the teeth from a first dental arrangement to a second dental arrangement. In box 770, a second orthodontic appliance is applied to the patient's teeth to reposition the teeth from the second dental arrangement to a third dental arrangement. The method 750 can be repeated as needed using any suitable number and combination of sequential appliances to progressively reposition the patient's teeth from an initial arrangement to a target arrangement. All of these appliances can be generated at the same stage or in groups or batches (e.g., at the beginning of a treatment stage), or these appliances can be manufactured at once, and the patient can wear each appliance until the teeth no longer feel the pressure of each appliance, or until the maximum tooth movement presented in the given stage has been reached. Before the patient wears any of the multiple appliances, multiple different appliances (e.g., a set of appliances) can be designed and even manufactured. After wearing the appliance for an appropriate period of time, the patient can replace the current appliance with the next appliance in the series until no more appliances remain. The appliance is usually not fixed to the teeth, and the patient can place and replace the appliance (e.g., a patient-removable appliance) at any time during treatment. The final appliance or several appliances in the series can have one or more geometries selected for overcorrecting the tooth arrangement. For example, one or more appliances can have the following geometry, which (if fully realized) moves each tooth beyond the tooth arrangement that has been selected as the "final". Such overcorrection may be desirable to counteract potential relapse after the repositioning method has concluded (e.g., to allow individual teeth to move back to their pre-corrected positions). Overcorrection may also be beneficial to speed up correction (e.g., an appliance having a geometry that is located beyond a desired intermediate or final position may move individual teeth toward that position at a greater rate). In such cases, use of the appliance may be terminated before the teeth reach the position defined by the appliance. In addition, overcorrection may be intentionally performed to compensate for any inaccuracies or limitations of the appliance.
[0320] Figure 8A method 800 for designing an orthodontic appliance to be produced by direct manufacturing is shown according to an embodiment. The method 800 can be applied to any embodiment of an orthodontic appliance that can be formed by a mold 100 including a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein. Some or all of the blocks of the method 800 can be executed by any suitable data processing system or device (e.g., one or more processors configured with suitable instructions).
[0321] In box 810, a movement path for moving one or more teeth from an initial arrangement to a target arrangement is determined. The initial arrangement can be determined from a mold or scan of the patient's teeth or oral tissue, for example, using wax articulation, direct contact scanning, x-ray imaging, tomography, ultrasound imaging, and other techniques for obtaining information about the position and structure of teeth, jaws, gums, and other orthodontically relevant tissues. A digital data set representing the initial (e.g., before treatment) arrangement of the patient's teeth and other tissues can be derived from the acquired data. Optionally, the initial digital data set is processed to segment tissue components from each other. For example, a data structure that digitally represents each crown can be generated. Advantageously, a digital model of the entire tooth can be generated, including measured or inferred hidden surfaces and root structures and surrounding bone and soft tissue.
[0322] The target arrangement of teeth (e.g., the desired and expected end result of orthodontic treatment) can be received from a clinician in the form of a prescription, can be calculated based on basic orthodontic principles, and / or can be computationally inferred from the clinical prescription. By specifying the desired final positions of the teeth and digital representations of the teeth themselves, the final position and surface geometry of each tooth can be specified to form a complete model of the dental arrangement at the desired end of treatment.
[0323] Having both an initial position and a target position for each tooth, a movement path can be defined for the movement of each tooth. In some embodiments, the movement path is configured to move the tooth in the fastest manner, with the least amount of round trips, to move the tooth from its initial position to its desired target position. The tooth path can optionally be segmented, and the segments can be calculated so that the movement of each tooth within the segment remains within threshold limits for linear and rotational translation. In this way, the endpoints of each path segment can constitute a clinically feasible repositioning, and the collection of segment endpoints can constitute a clinically feasible sequence of tooth positions, so that moving from one point to the next in the sequence does not result in tooth collision.
[0324] In box 820, a force system is determined to produce movement of one or more teeth along the movement path. The force system may include one or more forces and / or one or more torques. Different force systems may result in different types of tooth movement, such as tilting, translation, rotation, extrusion, intrusion, root movement, etc. Biomechanical principles, modeling techniques, force calculation / measurement techniques, etc. (including knowledge and methods commonly used in orthodontics) can be used to determine the appropriate force system to be applied to the teeth to achieve tooth movement. When determining the force system to be applied, sources may be considered, including literature, force systems determined by experiments or virtual modeling, computer-based modeling, clinical experience, minimization of unnecessary forces, etc.
[0325] Determination of the force system can include constraints on the forces allowed, for example, constraints on the directions and magnitudes allowed and the desired movement caused by the applied forces. For example, when manufacturing a palatal expander, different patients may require different movement strategies. For example, the amount of force required to separate the palate can depend on the age of the patient, because very young patients may not have a fully formed suture. Therefore, in adolescent patients and others who do not have a fully closed palatal suture, palatal expansion can be accomplished with a lower force level. Slower palatal movement can also help bone growth to fill the expanded suture. For other patients, faster expansion may be required, which can be achieved by applying greater force. The structure and material of the device can be selected as needed in combination with these requirements; for example, by selecting a palatal expander that can apply a large force to destroy the palatal suture and / or cause rapid expansion of the palate. Subsequent stages of the device can be designed to apply different amounts of force, such as first applying a large force to destroy the suture, and then applying a smaller force to keep the suture separated or gradually expand the palate and / or dental arch.
[0326] Determination of the force system can also include modeling the patient's facial structures, such as the skeletal structure of the jaw and palate. For example, scan data of the palate and dental arches, such as X-ray data or 3D optical scan data, can be used to determine parameters of the skeletal and muscular systems of the patient's oral cavity in order to determine a force sufficient to provide the desired expansion of the palate and / or dental arches. In some embodiments, the thickness and / or density of the mid-palatal suture can be measured or input by a treating professional. In other embodiments, the treating professional can select an appropriate treatment based on the patient's physiological characteristics. For example, the characteristics of the palate can also be estimated based on factors such as the patient's age, for example, a young adolescent patient will typically require less force to expand the suture than an elderly patient because the suture has not yet been fully formed.
[0327] In box 830, an orthodontic appliance configured to generate a force system is determined. The determination of the orthodontic appliance, the geometry, material composition and / or characteristics of the appliance can be performed using a treatment or force simulation environment. The simulation environment can include, for example, a computer modeling system, a biomechanical system or device, etc. Optionally, a digital model of the appliance and / or teeth, such as a finite element model, can be generated. The finite element model can be created using computer program application software available from various suppliers. To create a solid geometry model, a computer-aided engineering (CAE) or computer-aided design (CAD) program can be used, such as available from Autodesk, Inc. of San Rafael, California Software Products. To create finite element models and analyze them, program products from several vendors may be used, including the finite element analysis package from ANSYS, Inc., Canonsburg, Pennsylvania, and the SIMULIA (Abaqus) software product from Dassault Systèmes, Inc., Waltham, Massachusetts.
[0328] Optionally, one or more orthodontic appliances may be selected for testing or force modeling. As described above, desired tooth movement and the force system required or desired to induce the desired tooth movement may be identified. Using the simulation environment, candidate orthodontic appliances may be analyzed or modeled to determine the actual force system produced by using the candidate appliances. One or more modifications may optionally be made to the candidate appliances, and the force modeling may be further analyzed as described, for example, to iteratively determine an appliance design that produces the desired force system.
[0329] In box 840, instructions for manufacturing an orthodontic appliance (including an appliance design) are generated. The instructions can be configured to control a manufacturing system or device to produce an orthodontic appliance having a specified orthodontic appliance. In some embodiments, the instructions are configured to manufacture an orthodontic appliance using direct manufacturing (e.g., stereolithography, selective laser sintering, fused deposition modeling, 3D printing, continuous direct manufacturing, multi-material direct manufacturing, etc.) according to the various methods presented herein. In alternative embodiments, the instructions can be configured to indirectly manufacture the appliance, such as by thermoforming. In some embodiments, the instructions for manufacturing an orthodontic appliance include instructions for forming a mold 100, the mold 100 including a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein.
[0330] Method 800 may include additional blocks: 1) intraorally scanning the patient's upper dental arch and palate to generate three-dimensional data of the palate and upper dental arch; and / or 2) determining a three-dimensional shape profile of the appliance to provide the spacing and tooth engagement structure as described herein.
[0331] Although the above blocks illustrate a method 800 for designing an orthodontic appliance according to some embodiments, those skilled in the art will recognize some variations based on the teachings described herein. Some blocks may include sub-blocks. Certain blocks may generally be repeated as needed. One or more blocks of method 800 may be performed with any suitable manufacturing system or device, such as the embodiments described herein. Some blocks may be optional, and the order of the blocks may be changed as needed.
[0332] Fig. 9 A method 900 for digitally planning orthodontic treatment and / or design or manufacture of appliances according to an embodiment is shown. The method 900 may be applied to any treatment procedure described herein and may be performed by any suitable data processing system.
[0333] In block 910, a digital representation of the patient's teeth is received. The digital representation may include surface topography data of the patient's oral cavity (including teeth, gum tissue, etc.). The surface topography data may be generated by directly scanning the oral cavity, a physical model (positive or negative) of the oral cavity, or an impression of the oral cavity using a suitable scanning device (e.g., a handheld scanner, a desktop scanner, etc.).
[0334] In block 920, one or more treatment phases are generated based on the digital representation of the teeth. The treatment phases may be incremental repositioning phases of an orthodontic treatment process designed to move one or more of the patient's teeth from an initial tooth arrangement to a target arrangement. For example, the treatment phases may be generated by determining an initial tooth arrangement indicated by the digital representation, determining a target tooth arrangement, and determining a movement path of one or more teeth in the initial arrangement required to achieve the target tooth arrangement. The movement path may be optimized based on minimizing the total movement distance, preventing collisions between teeth, avoiding tooth movements that are more difficult to achieve, or any other suitable criteria.
[0335] In box 930, at least one orthodontic appliance is manufactured based on the generated treatment stages. For example, a set of appliances can be manufactured, each appliance is formed according to the tooth arrangement specified by one of the treatment stages, so that the appliances can be worn sequentially by the patient to incrementally reposition the teeth from an initial arrangement to a target arrangement. The appliance set may include one or more orthodontic appliances described herein. The manufacture of the appliance may involve creating a digital model of the appliance for use as an input to a computer-controlled manufacturing system. As desired, the appliance may be formed using a direct manufacturing method, an indirect manufacturing method, or a combination thereof. The manufacture of the appliance can be performed via a mold 100, which includes a beam 120 extending between distal portions 112A-B of the mold 100, as disclosed herein.
[0336] In some cases, the design and / or manufacture of the device may not require staging of the various arrangements or treatment phases. Fig. 9 As shown by the dashed lines in , the design and / or manufacture of orthodontic appliances and possibly specific orthodontic treatments may include using a representation of a patient's teeth (e.g., receiving a digital representation of the patient's teeth at box 910), and then designing and / or manufacturing the orthodontic appliance based on the representation of the patient's teeth in an arrangement represented by the received representation.
[0337] Other examples of appliances that include features that may be formed to be more rigid than the tooth engagement area may include devices with bite blocks, such as those described in US20210169617, the entire contents of which are incorporated herein by reference.
[0338] Generally, any appliance described herein can have variable properties, including a mixture of regions of different stiffness / compliance (e.g., Young's modulus). For example, the methods and features described herein can be used with and / or modified from the apparatus shown and described in US20170007359A1, the entire contents of which are incorporated herein by reference. For example, the methods described herein can be used to prepare any of the dental appliances shown and described in US20170007359A1.
[0339] It should be understood that the above description is intended to be illustrative rather than restrictive. After reading and understanding the above description, many other embodiments will be apparent. Although the embodiments of the present disclosure have been described with reference to specific example embodiments, it will be appreciated that the present invention is not limited to the described embodiments, but can be practiced by modification and change within the spirit and scope of the appended claims. Therefore, the description and the accompanying drawings should be regarded as illustrative rather than restrictive. Therefore, the scope of the present invention should be determined with reference to the appended claims and the full scope of equivalents given by these claims.
Claims
1. A mold for a dental appliance, the mold include: a dental arch portion associated with a plurality of teeth of a user, the dental arch portion comprising a first distal portion, a second distal portion, and an incisor portion disposed between the first distal portion and the second distal portion; as well as A beam extends from the first distal end portion to the second distal end portion to reinforce the mold, wherein the beam includes a marking portion forming a mark for identifying the mold.
2. The mold according to claim 1, in, The marking includes a through hole from an upper surface of the marking portion to a lower surface of the marking portion, wherein the through hole forms a number of an identifier of the marking.
3. The mold according to claim 1, further comprising: include: A pick and place component is coupled to the beam, wherein the pick and place component is configured to be secured by a dental appliance manufacturing apparatus.
4. The mold according to claim 1, in, The beam includes a flat portion configured to engage with a locking mechanism of a plate to secure the mold to the plate in the z-direction.
5. The mold of claim 1 further comprising a plurality of identifier features extending from one or more side walls of the beam for automatically identifying the mold.
6. The mold according to claim 1, in, The beam includes a reinforcement portion extending from the first distal portion of the dental arch portion to the second distal portion of the dental arch portion, wherein the reinforcement portion is configured to reinforce the beam, and wherein the reinforcement portion has a greater thickness than the marking portion.
7. The mold according to claim 1, further comprising: include: a first chamfer disposed between the marking portion and the first distal portion of the dental arch portion; as well as A second chamfer is disposed between the marking portion and the second distal end portion of the dental arch portion.
8. A method, include: determining a position of a beam of the mold relative to a dental arch portion of the mold, the dental arch portion comprising a first distal portion, a second distal portion, and an incisor portion disposed between the first distal portion and the second distal portion, wherein the beam extends from the first distal portion to the second distal portion; determining a layout of identifiers to be formed on the beam between the first distal portion and the second distal portion; and A shape of the beam to be attached to the dental arch portion of the mold is determined, wherein the mold is formed based on the position of the beam, the layout of the identifiers, and the shape of the beam.
9. The method according to claim 8, in, Determining the position of the beam includes: identifying a plurality of transformations of the mold, wherein each of the plurality of transformations comprises a corresponding position of the beam relative to the dental arch portion; Slicing a three-dimensional (3D) model of the dental arch portion to generate a two-dimensional (2D) contour of the 3D model; and A first transformation of the plurality of transformations is selected based on the 2D contour, wherein the first transformation includes a position of the beam relative to the dental arch portion.
10. The method according to claim 9, in, Selecting the first transformation comprises: It is determined that a width distance between a distal end of the beam from the first distal portion to the second distal portion in the first transformation satisfies a threshold distance.
11. The method according to claim 9, in, Selecting the first transformation comprises: determining that in the first transformation the beam is located between the incisor portion of the dental arch portion and a line intersecting a first distal end of the first distal portion and a second distal end of the second distal portion; and It is determined that a length distance between the beam and the line in the first transformation satisfies a threshold distance.
12. The method according to claim 9, in, Selecting the first transformation comprises: A determination is made that a feature offset distance between a pick and place component of the beam and a corresponding identifier feature extending from the beam in the first transformation satisfies a threshold distance, wherein the feature offset distance provides clearance for a dental appliance manufacturing machine to secure the pick and place component to move the mold.
13. The method according to claim 9, in, Selecting the first transformation comprises: It is determined that the identifier to be formed in the beam is not obstructed by the geometry of the mold.
14. The method according to claim 9, in, The selection of the first transformation is further based on determining that a gap distance between a trimming line of the arch portion and a connection between the arch portion and the beam in the first transformation satisfies a threshold distance.
15. The method according to claim 8, in, Determining a layout of the identifiers to be formed on the beam includes: a predefined format identifying a marked portion of the beam; determining a number of marks to be formed in the marked portion of the beam based on the identifier; and A plurality of identifier features are determined to extend from a side wall of the beam based on the identifier, wherein the identifier features form a binary code to be decoded to verify the identifier determined from the indicia's digits.
16. The method according to claim 8, in, The shapes of the beams include: a substantially flat marking portion of the beam, the substantially flat marking portion forming an engraved number cut through the beam based on the identifier; and A plurality of identifier features extend from a side wall of the beam.
17. The method according to claim 16, in, The shapes of the beams include: The reinforcement portion of the beam is configured to prevent deformation of the beam, wherein the reinforcement portion of the beam has a greater thickness than the substantially flat marking portion of the beam.
18. The method according to claim 8, in, The shapes of the beams include: A chamfer is located between the marked portion of the beam and the dental arch portion to prevent the beam from breaking, wherein the chamfer is used to provide a clearance distance between the beam and a trim line of the mold.
19. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform the method according to any one of claims 8 to 18.
20. A system, include: Memory; as well as A processing device is coupled to the memory, the processing device is configured to execute the method according to any one of claims 8 to 18.
21. A method of designing a virtual three-dimensional (3D) model of a mold for a dental appliance, include: determining an identifier associated with the mold, wherein the mold includes a dental arch portion associated with a plurality of teeth of a user, wherein the dental arch portion includes a first distal portion, a second distal portion, and an incisor portion disposed between the first distal portion and the second distal portion; determining a mark to be formed in a marked portion of the beam of the mold based on the identifier; and A placement of the beam is determined, wherein the beam extends from the first distal portion to the second distal portion in the virtual 3D model of the mold.
22. The method according to claim 21, in, Determining the identifier includes: determining a patient identifier associated with the mold; determining control information associated with the mold; determining a material of the dental appliance to be formed from the mold; determining a jaw associated with the mold; determining a material-jaw identifier based on the material and the jaw; and A phase identifier associated with the mold is determined, wherein the identifier is based on the patient identifier, the control information, the material-jaw identifier, and the phase identifier.
23. The method according to claim 22, in: The mark is a cutting mark including a plurality of numbers; A first subset of the plurality of digits is associated with the patient identifier; a second subset of the plurality of numbers being associated with the control information; a third subset of the plurality of digits being associated with the material-jaw identifier; and A fourth subset of the plurality of numbers is associated with the phase identifier.
24. The method according to claim 22, further comprising: include: determining a plurality of identifier features based on the patient identifier, the material-jaw identifier, and the stage identifier; as well as The plurality of identifier features are divided into a first subset and a second subset, wherein the first subset of the plurality of identifier features is to be placed on a first side wall of the beam and the second subset of the plurality of identifier features is to be formed on a second side wall of the beam.
25. The method according to claim 24, further comprising: include: determining a position of a pick and place component on the beam of the mold within a threshold distance of a center of the beam; as well as A feature offset associated with a location of the pick and place component is determined, wherein the first subset and the second subset are to be formed based on the feature offset.
26. The method according to claim 24, in: A first control pin and a second control pin are to be formed on the first side wall of the beam; said first subset of said plurality of identifier features to extend from said first sidewall of said beam between said first control pin and said second control pin; A third control pin and a fourth control pin are to be formed on the second side wall of the beam; and The second subset of the plurality of identifier features will extend from the second side wall of the beam between the third control pin and the fourth control pin.
27. The method according to claim 21, further comprising: include: A type of dental appliance to be formed from the mold is determined, wherein based on the type of dental appliance, type indicia are formed on a pick and place component of the mold.
28. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform the method according to any one of claims 21 to 27.
29. A system, include: Memory; as well as A processing device, coupled to the memory, for executing the method according to any one of claims 21 to 27.
30. A method for marking a mold of a dental arch, the method include: receiving an image of the mold of the dental arch; performing a first analysis of the image; determining, based on the first analysis, an area of the image corresponding to a mark formed by a marked portion of a beam of the mold, the mark forming an identifier having a plurality of digits; performing a second analysis of the region of the image; as well as Based on the second analysis of the region of the image, each digit of the plurality of digits of the identifier is identified.
31. The method according to claim 30, in, Performing the first analysis includes matching a template to the marked portion in the image.
32. The method according to claim 30, further comprising: include: receiving a historical image of historical markings of a historical mold, each of the historical markings being formed in a corresponding marking portion of a corresponding beam of a corresponding historical mold; receiving a historical region associated with the historical image; as well as A machine learning model is trained using a training input comprising the historical image and a target output comprising the historical area to generate a trained machine learning model, wherein performing the first analysis comprises providing the image as an input to the trained machine learning model.
33. The method according to claim 30, in, Performing a first analysis of the image comprises: providing the image as input to a trained machine learning model, the trained machine learning model being trained to output the boundary of the region; and An output is received from the trained machine learning model indicating the region of the image.
34. The method according to claim 30, further comprising: include: receiving a history sub-region of a history image of a history mark of a history mold, each of the history marks being formed in a corresponding mark portion of a corresponding beam of a corresponding history mold, each of the history sub-regions corresponding to a history number of the history mark; receiving a history number for a history identifier associated with the history sub-region; and A machine learning model is trained using a training input comprising the historical sub-region and a target output comprising the historical numbers to generate a trained machine learning model, wherein performing the second analysis comprises providing a sub-region of the region of the image as input to the trained machine learning model.
35. The method according to claim 30, in, Performing the second analysis includes: identifying sub-regions of the image based on the region, wherein each sub-region corresponds to a respective digit of the identifier of the mold; providing the sub-region of the image as input to a trained machine learning model, the trained machine learning model being trained to output the plurality of digits of the identifier; and An output is received from the trained machine learning model indicating the plurality of digits of the identifier.
36. The method according to claim 30, further comprising: include: performing a third analysis of the region of the image; identifying an identifier feature presence data for the beam based on the third analysis of the region of the image; as well as The identifier is verified based on the identifier characteristic presence data of the beam.
37. The method according to claim 36, further comprising: include: receiving historical sub-regions of a historical image of a historical beam of a historical mold, each of the historical sub-regions corresponding to a historical potential identifier beam of the historical mold; receiving historical identifier feature presence data associated with said historical sub-region of said historical image; as well as A machine learning model is trained using a training input comprising the historical sub-region and a target output comprising the historical identifier feature presence data to generate a trained machine learning model, wherein performing the third analysis comprises providing the sub-region of the image as input to the trained machine learning model.
38. The method according to claim 36, in, Performing the third analysis includes: identifying a portion of the image corresponding to a pick and place feature of the beam of the mold; identifying, in the image, a control feature on a sidewall of the beam; identifying an area between the control features on either side of the portion of the image; identifying sub-regions of the image based on the region, wherein each sub-region corresponds to a potential identifier feature of the beam; providing the sub-region of the image as input to a trained machine learning model, the trained machine learning model being trained to output the identifier feature presence data; and An output is received from the trained machine learning model indicating presence data of the identifier feature.
39. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform the method according to any one of claims 30 to 38.
40. A system, include: Memory; as well as A processing device, coupled to the memory, for executing the method according to any one of claims 30 to 38.
Citation Information
Cited By
Oral cross-sectional image scanning method and system based on machine vision
CN121549950A
Digital segmentation line design method, dental appliance forming method, dental appliance, apparatus, electronic device, and storage medium
WO2026145594A1
