Prediction and mitigation of aligner damage

Abstract

The embodiments relate to solutions for aligner damage. One method includes: obtaining a digital design of a polymer aligner for a patient's dental arch. The polymer aligner is shaped to apply force to the teeth of the dental arch. The method further includes performing an analysis on the digital design of the polymer aligner using at least one of: a) a trained machine learning model; b) numerical simulation; c) a geometric evaluator; or d) a rule engine. The method may further include determining, based on the analysis, whether the digital design of the polymer aligner includes potential damage points, wherein for a potential damage point, there exists a threshold probability that breakage, deformation, or warping will occur. The method may further include: in response to determining that the digital design of the polymer aligner includes potential damage points, performing corrective measures based on the potential damage points.

Description

[0001] This divisional application is directed to the national phase application filed on September 27, 2019, with national application number 202310510605.4. The latter divisional application is a divisional application of the PCT national phase application filed on September 27, 2019, with national application number 201980078384.X. Technical Field

[0002] This disclosure relates to the field of designing dental appliances (e.g., polymer orthodontic aligners), and in particular to designing the physical properties of polymer aligners based on the desired or acceptable manufacturing or clinical outcomes that those polymer aligners can achieve, and predicting the failure of such polymer aligners. Background Technology

[0003] The goal of orthodontics is to move a patient's teeth into a position that optimizes function and / or aesthetics. Typically, an orthodontist or dentist applies appliances such as braces to the patient's teeth, and groups of braces apply continuous force to the teeth, gradually pushing them towards the desired position. Over time, and through a series of clinical visits and adjustments to the braces, the orthodontist adjusts the appliances to move the teeth toward their final position.

[0004] Alternatives to conventional orthodontic treatment using conventional fixed appliances (e.g., braces) include systems comprising a series of prefabricated aligners. In these systems, multiple aligners, and sometimes all aligners, may be designed and / or fabricated to be worn by the patient before the aligners are applied to the patient and / or the aligners reposition the patient's teeth (e.g., at the start of treatment). The design and / or planning of patient-specific treatment can utilize computer-based three-dimensional (3D) planning / design tools. Aligner design may rely on computer modeling of a series of planned sequential tooth arrangements, with each aligner designed to be worn on the teeth and flexibly reposition the teeth to the tooth arrangement of each plan.

[0005] Once the design and / or planning are complete, a series of prefabricated aligners can be made from a material that applies force to the patient's teeth, either alone or in combination with attachments on the patient's teeth. Example materials include one or more polymeric materials. Manufacturing may involve thermoforming the aligners using a series of molds (e.g., 3D-printed molds) and / or directly manufacturing the aligners. For some thermoforming manufacturing techniques, a shell is formed around the mold to achieve the negative side of the mold. The shell is then removed from the mold for use in various applications. An example application where a shell is formed around a mold and then used later is orthodontic dentistry or orthodontic treatment. In this application, the mold may be a positive mold of the patient's dental arch, and the shell may be an aligner for aligning one or more of the patient's teeth. When using attachments (e.g., planned orthodontic attachments), the mold may also include features associated with the attachments.

[0006] The mold can be formed using a variety of techniques, such as casting or rapid prototyping equipment. For example, a 3D printer can use additive manufacturing techniques (e.g., stereolithography) or subtractive manufacturing techniques (e.g., milling) to create a mold for the aligner. The aligner can then be formed on the mold using thermoforming techniques. Once the aligner is formed, it can be trimmed manually or automatically. In some cases, a computer-controlled 4-axis or 5-axis trimmer (e.g., a laser trimmer or grinder) is used to trim the aligner along the cut lines. The trimmer uses electronic data identifying the cut lines to trim the aligner. The aligner can then be removed from the mold and delivered to the patient. As another example, the aligner can be directly fabricated using, for example, stereolithography (SLA), digital light processing (DLP), and / or other 3D printing techniques.

[0007] While it may be desirable to identify specific portions of the aligner that are prone to deformation, warping, and / or breakage during manufacturing (e.g., in response to removal from the mold) and / or during use (e.g., in response to removal from the patient's dentition), this is difficult to achieve with existing technologies. Attached Figure Description

[0008] This disclosure is illustrated by way of example and not limitation in the figures of the accompanying drawings.

[0009] Figure 1A A flowchart is shown of a method for performing correction analysis on the digital design of a polymer aligner according to one embodiment.

[0010] Figure 1B A flowchart illustrating a manufacturing process for selecting one or more aligners based on damage prediction of one or more aligners, according to one embodiment, is shown.

[0011] Figure 2AA method for training a machine learning model according to one embodiment to predict whether an orthodontic aligner will be damaged during the manufacturing process of an orthodontic aligner is illustrated.

[0012] Figure 2B A flowchart is shown of a method for performing analysis on the digital design of an orthodontic aligner using a trained machine learning model, according to one embodiment.

[0013] Figure 2C A flowchart is shown illustrating a method, according to one embodiment, for using a trained machine learning model to determine whether an orthodontic aligner will become damaged (e.g., break) during or after the manufacture of the orthodontic aligner.

[0014] Figure 2D A flowchart illustrating a method, according to one embodiment, for determining whether any of the orthodontic aligners in a set of orthodontic aligners associated with a patient's treatment plan will become damaged (e.g., broken) using a trained machine learning model.

[0015] Figure 3A A flowchart is shown illustrating a method for performing analysis on the digital design of a polymer aligner using numerical simulation, according to one embodiment.

[0016] Figure 3B An example numerical simulation is shown that relates to the removal of a polymer aligner from a dental arch structure according to one embodiment.

[0017] Figure 4A A flowchart illustrating a method for performing analysis on the digital design of a polymer aligner using numerical simulation by modeling the teeth of the dental arch and the adhesive attachments as springs, according to one embodiment, is shown.

[0018] Figure 4B An example numerical simulation of modeling the teeth of a patient's dental arch as springs is shown according to one embodiment.

[0019] Figure 5A A flowchart illustrating a method for performing analysis on the digital design of a polymer aligner using numerical simulation by modeling a subset of the teeth of the dental arch and the adhesive attachments as springs, according to one embodiment, is shown.

[0020] Figure 5B An example numerical simulation is shown, which models a subset of the teeth of a patient's dental arch as springs according to one embodiment.

[0021] Figure 6A A flowchart illustrating a method for performing analysis on the digital design of an aligner (e.g., a polymer aligner) using numerical simulation according to one embodiment is shown.

[0022] Figure 6BA bending load is applied to the area around the aligner according to one embodiment.

[0023] Figure 6C A torsional load is applied to the region surrounding the aligner according to one embodiment.

[0024] Figure 6D A uniaxial tensile load is applied to the region around the aligner according to one embodiment.

[0025] Figure 6E A shear load is applied to the region surrounding the aligner according to one embodiment.

[0026] Figure 6F A weakness of the aligner according to one embodiment is shown.

[0027] Figure 7A A flowchart illustrating a method for performing analysis on the digital design of an aligner (e.g., a polymer aligner) using a geometric evaluator according to one embodiment is shown.

[0028] Figure 7B An aligner comprising a tooth receiving cavity and an adjacent region between a pair of tooth receiving cavities is shown according to one embodiment.

[0029] Figure 7C A cross-sectional slice obtained from an aligner according to one embodiment is shown.

[0030] Figure 7D An illustration of a surrounding according to one embodiment is shown. Figure 7C The bending load applied to the first axis of the cross-sectional slice.

[0031] Figure 7E An illustration of a surrounding according to one embodiment is shown. Figure 7C The bending load is applied to the second axis of the cross-sectional slice.

[0032] Figure 7F An illustration shows a perimeter perpendicular to one embodiment. Figure 7C The torsional load applied to the third axis of the cross-sectional slice.

[0033] Figure 7G The illustration shows a superposition of three different aligners for a dental arch according to one embodiment, wherein each aligner is associated with a different treatment stage of the dental arch.

[0034] Figure 8A A flowchart of a method 800 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation according to one embodiment is shown, the numerical simulation simulating a series of loads on the aligner.

[0035] Figure 8BThe stress-strain curve of an aligner according to one embodiment is shown. Stress (σ) can represent force, while strain (ε) can represent displacement.

[0036] Figure 8C A flowchart is shown illustrating a method for performing analysis on the digital design of an aligner (e.g., a polymer aligner) using numerical simulations associated with chewing and / or grinding of teeth, according to one embodiment.

[0037] Figure 9 A flowchart is shown for a method of applying one or more corrective measures to a polymer aligner based on a simulated removal of the polymer aligner from the dental arch.

[0038] Figure 10 A flowchart is shown, according to one embodiment, of a method for performing analysis on a digital design of a polymer aligner using a rules engine.

[0039] Figure 11 A flowchart is shown for a method of generating a set of possible treatment plans after output filtering according to one embodiment.

[0040] Figure 12 A flowchart is shown of a method for performing numerical simulations on a digital design of a polymer aligner according to one embodiment to generate rules for a rule engine.

[0041] Figure 13 A flowchart is shown illustrating a method for using a rule engine to identify potential damage points in the digital design of a polymer aligner according to one embodiment, and then performing numerical simulation on the digital design of the polymer aligner.

[0042] Figure 14 A block diagram of an example computing device according to an embodiment of the present disclosure is shown.

[0043] Figure 15A A tooth repositioning appliance according to an embodiment is shown.

[0044] Figure 15B A tooth repositioning system according to an embodiment is shown.

[0045] Figure 15C An orthodontic treatment method using multiple appliances according to an embodiment is shown.

[0046] Figure 16 A method for designing orthodontic appliances according to an embodiment is shown.

[0047] Figure 17 A method for digitally planning orthodontic treatment is illustrated according to an embodiment.

[0048] Figure 18Another method is shown for applying one or more corrective measures to a polymer aligner based on a simulated removal of the polymer aligner from the dental arch. Detailed Implementation

[0049] An aligner (also referred to herein as an "orthodontic aligner") can be a type of dental appliance (also referred to herein as an "instrument") applied to a patient's dentition and used to treat malocclusion. Examples of aligners and aligner systems can be found in [the document / reference needed]. Figure 15A and 15B Found it. Figure 15C The image illustrates an example treatment method using an aligner. The aligner can be formed from polymer materials using indirect or direct manufacturing techniques, examples of which can be combined. Figure 15A , 15B The discussion with 15C is relevant. As further noted in this article, many aligners may experience strain / stress during indirect manufacturing due to removal from the mold. Additionally, during use (whether indirect or direct aligners), many aligners may experience strain / stress due to prolonged residence in the oral environment (e.g., up to 23 hours daily for weeks) or repeated removal from the patient's dentition (e.g., several times daily for weeks). Strain / stress can lead to physical damage to the aligner (deformation (permanent or other forms), warping, cracking, breakage, damage, etc.). Physical damage during manufacturing can cause serious problems, including material waste, supply chain issues, and failure to meet customer requirements. Physical damage during use can also cause serious problems, such as adversely affecting the effectiveness of staged protocols and / or treatment plans.

[0050] The embodiments described herein relate to systems, methods, and / or computer-readable media suitable for predicting deformation, warping, and / or breakage of custom-manufactured products (e.g., aligners) before or during manufacturing (e.g., in response to removal from a mold) and / or before or during use (e.g., in response to removal from a patient's dentition). Embodiments covering addressing and / or mitigating predicted points of damage are also discussed. The embodiments described herein also cover techniques for optimizing aligner characteristics (e.g., thickness) by predicting portions of the aligner that are prone to deformation, warping, breakage, etc., and by identifying the degree to which these characteristics align with desired and / or actual clinical goals. Various embodiments may also use optimized aligner characteristics as a basis for effective aligner manufacturing processes, customized and / or optimized treatment plans, etc. These characteristics may be considered individually or together as one or more solutions to aligner damage, e.g., solutions to accommodate potential physical damage to the aligner during manufacturing, use, etc.

[0051] More specifically, in some embodiments, systems and methods for resolving aligner damage can be implemented during the design phase of orthodontic aligners, prior to and / or during manufacturing. Designing custom-manufactured products can be particularly challenging, especially in the context of orthodontic aligner manufacturing, where aligners are individually tailored for each individual patient. Furthermore, many orthodontic treatment plans specify treatment through a series of aligners manufactured for the patient. Each aligner in a series can fulfill a specific phase of the treatment plan and / or possess unique characteristics (e.g., shape) compared to other aligners in the series. Additionally, many orthodontic treatment plans can provide paired aligners for each phase of treatment for the patient, with a unique upper aligner for treating the upper dental arch and a unique lower aligner for treating the lower dental arch. Therefore, in some cases, a single treatment may include 50-60 phases for treating complex cases, implying the design and manufacture of 100-120 unique aligners for a single patient.

[0052] Furthermore, for aligners manufactured using indirect manufacturing techniques (e.g., thermoforming), removing the aligner from the mold may result in the application of forces and / or torques to the aligner. In some cases, due to the applied forces, the polymer material of the aligner may crack, warp, and / or deform during removal. Additionally, removing the aligner from a patient's teeth may result in the application of forces and / or torques to the aligner, which can also cause it to crack, warp, or deform. If the aligner cracks, the patient may request a replacement. Therefore, another aligner is manufactured and delivered to the patient. As can be imagined, manufacturing costs increase with the number of replacement aligners. In some cases, replacement aligners may be manually modified post-manufacturing to attempt to address potential cracking. For example, if a cracked interproximal area of ​​the aligner is identified, filling material may be added to the aligner to strengthen it. Manually modifying aligners post-manufacturing can be cumbersome and slow, especially when hundreds, thousands, or more replacement aligners are required. Furthermore, modifying replacement aligners is a reactive process performed after the original aligner has malfunctioned. Therefore, embodiments of this disclosure can provide a more scalable, automated, and / or proactive solution that can detect potential damage points during the design of the aligner and perform one or more corrective measures before the aligner is manufactured. The embodiments can reduce the occurrence of aligner damage, and thus also reduce the number of replacement aligners manufactured. This reduction in damage can lower the overall cost of manufacturing aligners and can reduce the amount of time technicians spend troubleshooting aligner damage.

[0053] As described herein, aligners can be formed from a polymer housing configured to receive a patient's upper or lower dental arch during a specific treatment phase. Each aligner can be configured to apply force to the patient's teeth during a specific phase of orthodontic treatment. Each aligner has a tooth-receiving cavity that receives and resiliently repositions a tooth according to the specific treatment phase. Each tooth-receiving cavity may be referred to as a "cap". Teeth can be repositioned by the aligner by, for example, vertically moving one or more teeth (e.g., squeezing or pushing teeth), rotating one or more teeth (e.g., by applying torque to the teeth, by secondary / tertiary rotation, etc.), moving one or more teeth laterally relative to the dental arch, and / or moving one or more teeth anteroposteriorly relative to the dental arch. Additionally, each aligner may include the shape of a receiving feature attached to the patient's dentition to facilitate tooth repositioning and / or rotation.

[0054] Implementations may identify individual aligners that include potential points of failure, and / or may identify a set of aligners that includes another aligner with potential points of failure (e.g., for a patient or a specific dental arch of a patient). The manufacturing process for aligners may be determined based on the probability that those aligners will become damaged (e.g., develop points of failure). The manufacturing process for a set of aligners (e.g., all aligners associated with a patient's treatment plan, or all aligners associated with a patient's upper or lower dental arch treatment plan) may also be determined based on the probability that any aligner in the set will become damaged or experience failure.

[0055] As described above, for a given set of digital designs for an alignment device, embodiments can identify various possible points of failure. One or more possible points of failure may include one or more of cracking, warping, deformation, malfunction, etc. Detecting possible points of failure can enable the modification or fixation of the digital design of the alignment device to remove possible points of failure before the alignment device is manufactured, thereby improving the yield of successfully manufactured alignment devices, reducing the number of patient complaints related to alignment device failure, reducing the manufacturing cost of replacement alignment devices, and / or preventing the manufacture of alignment devices that include possible points of failure. It should be noted that, as used herein, a “probable” point of failure (used interchangeably with a “likely” point of failure) can refer to the probability that a given area of ​​the alignment device will be damaged by, for example, manufacturing or use. A possible point of failure need not be represented by, for example, a majority. A possible point of failure may indicate that the probability of damage exceeds any specified threshold, including by a majority.

[0056] In some embodiments, potential damage points can be determined based on the digital design of the aligner. The digital design of the aligner can refer to a digital model of the aligner that includes its geometry. In some embodiments, the digital model of each aligner can be included in a digital file associated with the aligner. In some embodiments, a digital model of the aligner can be generated based on scanning the aligner (e.g., using an intraoral scanner or other 3D scanner) and generating the digital model of the aligner according to the scan results. In other embodiments, a digital model of the aligner can be generated using a digital model of a mold of the patient's dental arch. The digital model of the mold can be offset (e.g., magnified) to generate the digital model of the aligner. The terms "digital design of the aligner" and "digital model of the aligner" are used interchangeably herein. Analysis can be performed on the digital design of the aligner using at least one of the following: a) a trained machine learning model trained to identify aligners with potential points of damage; b) a numerical simulation associated with the removal of the aligner from the mold of the patient's dental arch; c) a numerical simulation associated with progressive damage to the aligner; d) a numerical simulation simulating the load around weak points (e.g., interproximal regions) in the aligner; e) a geometric evaluator (e.g., evaluating parameters associated with the geometry of the aligner) that calculates and evaluates geometry-related parameters (e.g., cross-sectional parameters); or f) a rule engine that includes one or more rules associated with parameters of the aligner indicating points of damage. Based on this analysis, it can be determined whether the digital design of the aligner includes one or more potential points of damage. For a potential point of damage, there is at least a threshold probability that cracking, deformation, warping, failure, etc., will occur. In response to determining that the digital design of the aligner includes one or more potential points of damage, one or more corrective actions (e.g., modifying the digital design of the aligner, modifying attachments in the digital design of the aligner, providing notification to a dental practitioner, etc.) can be performed based on the one or more potential points of damage. Some advantages of the disclosed embodiments may include: automatic detection of various possible damage points in the aligner; automatic correction of possible damage points in the aligner; and / or automatic selection of the aligner manufacturing process based on the presence of possible fault points / damage points in the aligner. The embodiments may also reduce the number of replacement aligners manufactured, thereby reducing manufacturing costs and increasing customer satisfaction. In some implementations, the determination of possible damage points can form the basis for the design of aligners with variable thicknesses to accommodate those damage points. Such variable thicknesses to accommodate damage points can be formed through direct manufacturing techniques and / or other techniques. Furthermore, the embodiments can increase the number of aligners manufactured without cracks, warping, or deformation.

[0057] Various software and / or hardware components can be used to achieve, for example Figure 14The disclosed embodiments are shown. For example, software components may include computer instructions stored in a tangible, non-transitory computer-readable medium, which are executed by one or more processing means to perform an alignment failure solution on the digital design of the alignment. Hardware components may include processing means, storage means, networking means, etc.

[0058] The shape of an aligner, including the shape of each tooth-receiving cavity (cap) within the aligner, the shape of the interproximal regions between tooth-receiving cavities, the shape of the cutting line, the shape of any additional cavities formed to accommodate attachments on the patient's teeth, and so on, can affect whether a particular aligner will break, warp, deform, or be damaged during removal from an arch-like structure (e.g., a mold and / or the patient's dentition). As described herein, the shape of an aligner can be modified to accommodate potential points of damage, and the shape of the aligner can form the basis for an aligner with variable thickness. Aligners with modified shapes can be formed using various techniques, including but not limited to direct manufacturing techniques.

[0059] In the embodiments disclosed herein, the digital design of each aligner used in a treatment plan or in a specific stage of a treatment plan can be analyzed to determine whether one or more potential points of damage exist at any location in the digital design of the aligner. Each digital design of the aligner can be associated with the digital design of the patient's dental arch at the stage of treatment. If one or more potential points of damage are detected against the digital design of the aligner, corrective measures can be performed based on the potential points of damage.

[0060] The embodiments are described with reference to aligners and orthodontic aligners (e.g., polymer aligners and polymer orthodontic aligners). An aligner is a form of dental appliance (also simply referred to as an appliance for convenience). In particular, as described above and in more detail below, an aligner can be of the type of polymer housing used to correct, for example, malocclusion. It should be understood that the embodiments described herein with reference to aligners are also applicable to other types of dental appliances and housings, and particularly to other types of polymer dental appliances, including but not limited to sleep apnea treatment devices, night braces, etc.

[0061] Once the design is complete, each aligner can be manufactured using, for example, indirect or direct manufacturing techniques to form the polymer material and implement one or more stages of the treatment plan on the patient's dentition. This article is about Figure 15A , 15B Article 15C further describes examples of indirect manufacturing techniques and direct manufacturing techniques. For example, Figure 1AA flowchart is shown of a method 100 for performing correction analysis on a digital design of a polymer aligner according to one embodiment. One or more operations of method 100 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 100 may be performed by executing... Figure 14 The processing device of the alignment design analysis module 1450 is used to perform the analysis. It should be noted that method 100 can be performed for each unique alignment for each patient's treatment plan, or for each unique alignment under one or more stages (e.g., key stages) of the treatment plan.

[0062] At box 102, the processing logic can obtain a digital design of an aligner for a patient's dental arch. The aligner in the digital design (e.g., a polymer aligner) is shaped to apply force to one or more teeth of the dental arch. In some embodiments, the processing logic can receive a file including a digital model of a mold used to create a particular aligner. The processing logic can manipulate (e.g., zoom in) the geometry of the digital model of the mold to dynamically generate the digital design of the aligner. In some embodiments, the processing logic can receive the digital design of the aligner from another system or by scanning an aligner manufactured in a scan. In some embodiments, the digital design of the aligner is a virtual three-dimensional (3D) model of the aligner, generated based on a virtual 3D model of the dental arch at the treatment stage.

[0063] In box 104, the processing logic may perform analysis on the digital design of the polymer aligner using at least one of the following: a) a trained machine learning model trained to identify polymer aligners with potential points of damage; b) a numerical simulation associated with the removal of the polymer aligner from the mold of the patient's dental arch; c) a numerical simulation associated with progressive damage to the aligner; d) a numerical simulation simulating the load around weak points (e.g., interproximal regions) in the aligner; e) a geometric evaluator that evaluates parameters associated with the geometry of the polymer aligner; or f) a rule engine comprising one or more rules associated with parameters of the polymer aligner indicating points of damage. (See below for reference.) Figure 2A-2D Additional details are discussed regarding the analysis performed on the digital design of polymer aligners using a trained machine learning model. (See below for reference.) Figure 3A-5B Additional details are discussed regarding the analysis performed on the digital design of the aligner using numerical simulation, which is related to the removal of the aligner from the mold. (Refer to...) Figures 8A-8C Additional details are discussed regarding the analysis of the digital design of the aligner using numerical simulations associated with progressive damage to the aligner. (See also...) Figure 6A-7GAdditional details are discussed regarding the analysis of the digital design of the aligner using numerical simulation and / or geometric evaluators (which simulate the load around the weak points of the aligner). See below for reference. Figure 10 Additional details are discussed regarding the use of a rules engine to perform analysis on the digital design of the aligner.

[0064] At box 106, the processing logic may determine, based on analysis, whether the digital design of the aligner includes one or more potential points of failure. A potential point of failure may be a point with at least a threshold probability of cracking, deformation, or warping due to removal of the aligner from the mold, removal of the aligner from the teeth, use of the aligner, etc. At box 107, the processing logic determines whether any potential points of failure are identified. If at least one potential point of failure is identified, the method proceeds to box 108. Otherwise, the method may terminate.

[0065] At block 108, the processing logic may perform one or more corrective actions and / or select a manufacturing process based on one or more possible damage points. In some embodiments, performing one or more corrective actions includes modifying the digital design of the aligner to generate a modified digital design of the aligner. In some embodiments, performing one or more corrective actions includes modifying the digital design of the dental arch associated with the digital design of the aligner. Due to the change in the digital design of the dental arch, the digital design of the aligner may also be changed to accommodate the change in the digital design of the dental arch.

[0066] If a potential point of damage is determined to be at or near a cut line in the digital design of the aligner, modifying the digital design of the aligner may include modifying the radius of the cut line. For example, in the digital design of the aligner, the cut line may be lowered to be straighter rather than sharper (weakening the strength of the aligner at that point). Straightening the cut line can increase the strength of the aligner at that location and can remove the potential point of damage from the digital design of the aligner. If a potential point of damage is determined to be at or near the interproximal region between two teeth, modifying the digital design of the aligner may include modifying the thickness of a portion of the digital design of the aligner. For example, increasing the thickness of that portion of the digital design of the aligner makes the outer surface of the digital design of the aligner flatter. Thickening that portion of the digital design can strengthen that portion of the aligner and can remove the potential point of damage from the digital design of the aligner. In some embodiments, the thickness of the aligner is controllable for aligners manufactured directly using 3D printing technology, but is not controllable for aligners manufactured by thermoforming processes.

[0067] In some embodiments, modifying the digital design of the aligner may include inserting an indicator into the digital design of the aligner. The indicator indicates a recommended location for initiating removal of the aligner. The location for placing the indicator may be determined during analysis of the digital design. For example, the analysis may identify that applying force at a specific location on the digital design of the aligner to remove the aligner's digital design is less likely to cause damage compared to applying force at any other location on the aligner's digital design. Therefore, the indicator may be placed at that specific location.

[0068] In some embodiments, if a potential point of damage is determined to exist at or near a location associated with an attachment to a tooth in the digital design of the aligner, corrective measures may include modifying one or more attachments associated with the potential point of damage on one or more teeth in a virtual 3D model of the dental arch. Modifying the 3D model of the dental arch may result in the generation of a modified virtual 3D model of the aligner based on changes to the attachments. For example, the cavity of the aligner that houses the attachments may be moved, increased, or decreased in size, or may have a modified shape in the modified virtual 3D model of the aligner based on changes to the attachments in the 3D model of the dental arch.

[0069] In some embodiments, if a potential damage point is determined to exist at or near a location between two teeth, corrective measures may include adding new virtual fillers or extending existing virtual fillers to one or more locations on a virtual 3D model of the dental arch associated with one or more potential damage points. Virtual fillers may refer to digital features of a virtual model (e.g., a virtual model of the dental arch) or digital features added to a virtual model that presents an additional object between two or more adjacent teeth. In embodiments, virtual fillers in a virtual model alter the geometry of the corresponding physical mold and reduce the likelihood of manufacturing problems. A modified virtual 3D model of the aligner may be generated based on a modified virtual 3D model of the dental arch that includes virtual fillers. Virtual fillers can result in the aligner having a flatter surface between the two teeth to accommodate the virtual filler. A flatter surface between the teeth can increase the strength of the aligner and remove potential damage points from the digital design of the aligner.

[0070] After any modifications are made to the digital design of the aligner, a modified virtual 3D model of the aligner can be generated based on these modifications. The processing logic can determine whether the modified digital design of the aligner includes one or more potential defects. In response to determining that the modified digital design of the aligner includes one or more potential defects, the processing logic can perform one or more second corrective actions based on these potential defects. This process can be repeated until all potential defects have been removed from the digital design of the aligner, or until only a threshold number of potential defects remain in the digital design of the aligner, and so on.

[0071] In some embodiments, a digital design of the aligner is received during the treatment planning phase of orthodontic treatment. In some embodiments, when one or more potential points of failure are identified in the digital design of the aligner, corrective measures may include recommending modifications to one or more attachments on one or more teeth of the patient to reduce the probability that the potential points will fail below a threshold probability. In some embodiments, corrective measures may include recommending modifications to the digital design of the aligner to move one or more teeth using another digital design of another aligner at a different stage of the patient's treatment plan to reduce the probability that the potential points will fail below a threshold probability. For example, a specific tooth rotation may be specified in the first stage of the treatment plan, and a specific attachment may be used to achieve that specific tooth rotation. The treatment plan may be modified to move the specific tooth rotation to a later treatment stage, thereby also moving the use of the specific attachment to a later treatment stage.

[0072] In some embodiments, corrective measures may include recommending one or more procedures to properly remove the aligner from the patient's dental arch to reduce the probability that a potential point of failure will occur below a threshold probability. In some embodiments, corrective measures may include informing the dental practitioner during the treatment planning phase that the digital design of the aligner has a potential point of failure. For example, if a potential point of failure cannot be removed by modifying the digital design of the aligner, the processing logic may inform the dental practitioner of the potential point of failure.

[0073] In some embodiments, performing corrective measures based on one or more potential damage points may include setting a flag associated with the aligner to indicate that a quality inspection should be performed on the aligner after manufacturing. This flag may target the quality inspection at one or more potential damage points. In some embodiments, corrective measures may include recommending targeted inspections by sending notifications to an inspector's system.

[0074] In some embodiments, performing corrective measures based on one or more possible points of damage may include setting markers to use a fragile mold or a mold with weak areas during manufacturing. A fragile mold may refer to a mold that breaks so that the aligner can be removed from the fragile mold. While the mold is breaking, a smaller force can be applied to the aligner, and therefore, the likelihood of the aligner failing during removal can be reduced.

[0075] In some embodiments, performing corrective measures based on one or more possible points of damage may include altering the geometry of a virtual 3D model of the mold. For example, a portion of the virtual 3D model of the mold may be bubbled or thickened. A modified virtual 3D model of the aligner can be generated based on the modified virtual 3D model of the mold, and the shape of the modified virtual 3D model can be altered from the original virtual 3D model of the aligner due to the portion of the modified 3D model of the mold. By bubbling, thickening, or expanding the digital model (and thus the aligner) at one or more locations, the amount of force required to remove the aligner from the mold (or dental arch) at that location is reduced. Therefore, cracking, warping, etc., at that location can be mitigated.

[0076] In some embodiments, a manufacturing process can be selected for the aligner at block 108 based on predictions of possible points of damage or failure in the aligner, or based on the assumption that the aligner has no possible points of damage or failure.

[0077] Figure 1B A method 110 for selecting a manufacturing process for one or more aligners is illustrated. One or more operations of method 110 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, special-purpose logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 110 may be performed by executing… Figure 14 The method 110 is executed by the processing device of the alignment design analysis module 1450. It should be noted that method 110 is described with reference to a set of alignments (e.g., alignments as part of a patient's treatment plan, or alignments associated with a treatment plan for a specific dental arch of a patient). However, in embodiments, method 110 may be executed for each unique alignment for each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. In embodiments, method 110 may be executed at block 108 of method 100.

[0078] At block 112 of method 110, the processing logic receives data on possible failure points of multiple aligners. This data may be for aligners associated with one or more orthodontic treatment plans for one or more patients. The data on the probability of failure points may have been output via: a) a trained machine learning model trained to identify aligners with possible failure points, b) a numerical simulation associated with the removal of the aligner from the mold of the patient's dental arch, c) a numerical simulation associated with progressive damage to the aligner, d) a numerical simulation simulating the load around a weak point in the aligner, e) a geometric evaluator evaluating parameters associated with the geometry of the polymer aligner, or f) a rule engine including one or more rules associated with parameters indicating failure points of the aligner. In some embodiments, the data on the probability of failure points may have been generated by two or more of the simulator, rule engine, and / or machine learning model described above.

[0079] At box 114, the processing logic aggregates data from aligners associated with the same treatment plan into one or more sets. In one embodiment, failure probability data for all aligners associated with a treatment plan is aggregated into a single set. Alternatively, failure probability data for aligners associated with the same treatment plan can be aggregated into two or more sets. For example, data associated with the patient's lower dental arch (e.g., data from each treatment phase of the lower dental arch) can be combined into a first dataset, and data associated with the patient's upper dental arch can be combined into a second dataset.

[0080] If the probability of a point on the aligner being damaged is provided through two or more different techniques (e.g., through a machine learning model and simulation output, or through two simulation outputs, or through geometric evaluation), the predictions from multiple techniques can be combined to improve the accuracy of the prediction. For example, data from a single aligner can be received, wherein the data includes a first probability of aligner failure output by a machine learning model, and also includes a second probability of aligner failure output by a numerical simulation.

[0081] At box 116, each of one or more datasets is evaluated to determine whether all aligners in any dataset have a probability of damage / failure below a lower bound probability threshold. The lower bound threshold may have a value, for example, a probability of 2%, 5%, 10%, 15%, or 20% for a point of damage / failure. A set of aligners excluding those with a probability of damage / failure reaching or exceeding the lower bound threshold can be identified as a particularly low-risk set of aligners. Such a low-risk set of aligners can be rapidly tracked with minimal manufacturing steps, which can reduce the cost of manufacturing such a set and accelerate the manufacturing process. Therefore, if the probability of failure for all aligners in the set is below the lower bound threshold, the method proceeds to box 118 and determines a first manufacturing process for that set of aligners. The first manufacturing process may be, for example, a fast-track manufacturing process. In embodiments, a fast-track manufacturing process may operate under the assumption that no anomalies will occur, no aligners will be reworked during the manufacturing process, and manufacturing can be completed with minimal waiting time. However, if any aligner in the aligner set has a probability of failure / damage that reaches or exceeds the lower threshold at any point, the method may continue to box 120.

[0082] In some embodiments, the processing logic selects from two possible manufacturing processes, and the operation of block 116 is skipped, wherein the method proceeds from block 114 to block 120.

[0083] At box 120, each of one or more datasets is evaluated to determine whether any aligner in any dataset has a probability of damage / failure equal to or greater than an upper probability threshold. The upper threshold may have a value, for example, a probability of 45%, 50%, 55%, 60%, or 65% for a point of damage / failure. A set of aligners that includes at least one aligner with at least one point having a probability of damage / failure equal to or greater than the upper threshold can be identified as a particularly high-risk set of aligners. Such a high-risk set of aligners may undergo more inspection, slower manufacturing, increased quality control steps, etc., which can reduce the chance of aligners in the set becoming damaged and / or increase the chance of detecting any damage in such a set of aligners. Therefore, if no aligner in the set has any point with a probability of damage / failure equal to or greater than the upper threshold, the method proceeds to box 122, and a second manufacturing process can be selected. If the probability of a failure point for one or more aligners in the set is higher than the upper threshold, the method proceeds to box 124, and a third manufacturing process is determined for that set of aligners. The second manufacturing process can be a standard manufacturing process for aligners. The third manufacturing process can be a quality control manufacturing process (e.g., it uses image-based quality control inspection stations to inspect some or all of the aligners in the aligner set). In embodiments, the third manufacturing process can be performed by the most experienced technician or operator. In one embodiment, the cycle time of the third manufacturing process is increased to provide the operator with additional time to carefully handle the aligners (e.g., remove the aligners from the mold). The first manufacturing workflow at box 118 can be a workflow with the lowest complexity. The second manufacturing workflow at box 122 can be a workflow with medium complexity. The third manufacturing workflow at box 124 can be a workflow with the highest complexity.

[0084] Figure 2A A flowchart of a method 200 for training a machine learning model to perform analysis on the digital design of an orthodontic aligner, according to one embodiment, is shown. According to one embodiment, the machine learning model can be trained to predict whether the orthodontic aligner will be damaged during manufacturing.

[0085] One or more operations of method 200 are executed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, special-purpose logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 200 may be executed by processing logic of a computing device. Figure 14 The alignment design analysis module 1450 is processed by the processing unit.

[0086] In block 202 of method 200, the processing logic may preprocess digital designs of multiple orthodontic aligners, making the digital designs usable as training data for training a machine learning model. Some digital designs of orthodontic aligners may be associated with orthodontic aligners that have already been manufactured. For such digital designs, a clinical data storage device may store information indicating whether each associated corresponding orthodontic aligner was damaged during manufacturing. Other digital designs of orthodontic aligners may be associated with orthodontic aligners that have not yet been manufactured. Therefore, there may be no information regarding whether the orthodontic aligner associated with such a digital design was damaged during manufacturing.

[0087] In one embodiment, blocks 204-208 relate to preparing a digital design for an orthodontic aligner that has not yet been manufactured (or for which there is no information about damage), for use in training a machine learning model. At block 204, processing logic can use one or more numerical simulations to process the digital design of one or more orthodontic aligners to determine possible points of failure for the respective aligner. Any numerical simulations described herein can be used to determine possible points of failure / damage. Therefore, in embodiments, by using... Figure 3A-8C One or more methods described herein can be used to process the digital design of a model, which can identify possible points of failure in the digital design of the aligner.

[0088] As discussed above and referenced below Figure 3A-5B Further discussion suggests that numerical simulations can be performed on the digital design of the aligner to simulate one or more forces and / or displacements on the aligner. In some embodiments, these force simulations involve removing the aligner from a dental arch structure (e.g., a tooth or mold). The numerical simulation can determine when the magnitude of the force required to remove the aligner from the dental arch structure reaches a value of stress or strain / stress or deformation energy, or when the deformation energy level at any point on the aligner exceeds a threshold, which may indicate that failure will occur at that particular point. Strain can be determined based on displacement, motion, or geometric changes at these points, and stress can be determined based on the forces applied to the aligner. In some embodiments, strain or stress thresholds can be used during the numerical simulation to determine when points on the digital design of the aligner are likely to fail. In this way, the numerical simulation can serve as a predictive model that predicts possible failure points on the digital design of the aligner. These simulations can be run multiple times on multiple digital designs of the aligner, and the digital designs can include labels to indicate whether the digital design includes one or more possible failure points.

[0089] In block 206, the processing logic may determine for each digital design whether a potential failure point has been predicted for the associated corresponding orthodontic aligner. At block 208, the processing logic may add information about potential failure points to the digital design of the corresponding orthodontic aligner. In some cases, this may include adding information about the location of potential failure points and / or information about the probability of failure / damage at each potential failure point. Alternatively, the processing logic may add information about the absence of potential failure points to the digital design of an orthodontic aligner that does not have any potential failure points. In embodiments, potential failure points may be those points on the orthodontic aligner that have a probability of failure exceeding a probability threshold (e.g., 50%, 60%, or some other value). Potential failure points and the absence of potential failure points can be used as labels for the digital design of the orthodontic aligner. For example, a digital design that identifies one or more potential failure points may be assigned label 1, indicating that the associated aligner is predicted to be damaged during manufacturing. A digital design that does not identify any potential failure points may be assigned label 0, indicating that the associated aligner is predicted not to be damaged during manufacturing.

[0090] In one embodiment, blocks 210-216 relate to preparing a digital design for an orthodontic aligner that has been manufactured and for which there is information about damage, for use in training a machine learning model. At block 210, the processing logic may receive the digital design of one or more orthodontic aligners. At block 212, the processing logic may receive information indicating one or more orthodontic aligners that were damaged during manufacturing. Additionally, the processing logic may receive information indicating one or more locations of damage occurring in the manufactured aligner and / or the type of damage occurring (e.g., warping, cracking, deformation, etc.). In some embodiments, the actual damage points of the aligner may be reported by manufacturing technicians, by automated manufacturing systems, and / or by patients.

[0091] Information about whether an aligner has suffered damage can also be obtained from historical patient feedback. For example, a patient may provide a report specifying an aligner malfunction and / or the location of the damage may be determined (e.g., from the report, by scanning the aligner, etc.). Furthermore, the patient may specify which aligner (e.g., top or bottom) malfunctioned at a particular stage of the treatment plan. In some cases, the patient may return the broken aligner to a site where it can be scanned to obtain an image of the polymer aligner's digital design, including the location of the damage point. This allows images of broken aligners to be collected for an image corpus (a collection of images that may include a large set of images) and used as part of the training data. Information provided by the patient about the broken aligner, or information determined via scanned images, can be correlated to determine the aligner's ID, which can then be used to obtain the digital design of that specific aligner. The location of the damage point can be placed in the aligner's digital design and labeled to indicate the location of the damage.

[0092] At box 216, the processing logic can add information about whether damage has occurred (e.g., about the point of damage) to the digital design of the corresponding orthodontic aligner. In some cases, this may include adding information about the location of detected fault points / damage points. Additionally, the processing logic can add information about the digital design of orthodontic aligners that were not damaged during manufacturing. Possible damage points and no-damage points can be used as labels for the digital design of the orthodontic aligner. For example, a damaged digital design can be assigned label 1, indicating that the associated aligner was damaged during manufacturing. A non-damaged digital design can be assigned label 0, indicating that the associated aligner was not damaged during manufacturing. Therefore, the actual damage points on the physical aligner can be added as labels or metadata to the digital design associated with the aligner. In some cases, the digital aligner is labeled with information indicating whether the associated physical aligner has one or more damaged points, but not indicating the actual location of the damaged points.

[0093] At box 218, the processing logic can extract at least one of geometric, treatment-related, or clinical characteristics from the digital design of the orthodontic aligner. In one embodiment, characteristics are extracted via a software module that analyzes a three-dimensional virtual model of the dental arch and / or aligner and determines the associated characteristics of the dental arch and / or aligner based on that analysis. The extracted characteristics can include a variety of features, including those unrelated to whether the aligner will become damaged, and those that may influence whether the aligner will become damaged. Examples of geometric characteristics include the shape of a single tooth of one or more teeth, the position of teeth on the dental arch relative to other teeth, jaw shape, etc. Examples of treatment-related characteristics include the number of treatment stages, the number and location of dental attachments, whether the aligner is an active or passive aligner, etc. Examples of clinical characteristics include the amount of tooth crowding, deep occlusion, degree of malocclusion, etc. In an embodiment, the characteristics extracted by the processing logic can be formatted as structured data or tabular data. Therefore, characteristics of the aligner associated with the digital design can be represented as structured data or tabular data.

[0094] At box 220, a subset of characteristics for each digital design can be selected. In one embodiment, the same characteristics are included in the subset of each digital design. The selected subset of characteristics may be those related to damage or manufacturing defects in the aligner.

[0095] According to one embodiment, Table 1 below identifies numerous features that can be extracted from the digital model of the dental arch or the digital model of the alignment device. For one embodiment, Table 1 also indicates whether each feature is included in a subset at box 220. Table 1 shows only a small sample of the many different types of features that can be extracted from the digital model of the dental arch or the digital model of the alignment device. Although most of the features shown are included in subsets, in some embodiments, the subset may include fewer than half the total number of extracted features (e.g., only a small fraction).

[0096]

[0097] One possible feature to extract is the Spee curve (also known as the curve of Spee's line), which is the curvature of the mandibular occlusal surface that begins at the premolars, continues through the buccal cusps of the posterior teeth, and extends to the terminal molars. In other words, the Spee curve is the anatomical curvature of the occlusal alignment of the teeth that begins at the ends of the lower incisors, continues through the buccal cusps of the natural premolars and molars, and extends to the anterior boundary of the ramus. The idea behind measuring this curvature is to find a circle in the sagittal plane in 2D space, or a sphere in 3D space that best represents the set of cusps that best fit the mandible. The radius and angle between the center of this circle and the line segment connecting the cusp of the terminal molar and the first incisor can be a measure of curvature. It can be assumed that the larger the radius of the circle and the smaller the angle, the less pronounced the curvature of the jaw.

[0098] To find the Spee curve in 2D space, the curvature of each side of the jaw arch can be measured separately. Each cusp can be projected onto the midline plane (e.g., the plane with x-coordinate equal to zero). The problem of finding the center and radius of the circle that best fits all points can be solved as follows: 1) Calculate the initial guess by averaging the x and y coordinates of all points; 2) For example, improving the initial guess by using a least-squares estimator (e.g., based on the Euclidean distance between the point and the circle); and 3) Given the calculated residuals and cost function, use the least squares method to finally determine the local minimum of the cost function (e.g., using the Levenberg-Marquardt method), and then return the radius and coordinates of the center of the circle.

[0099] Then, the processing logic can find the angle between the line segment connecting the center of the circle to the tip of the terminal molar and the first incisor.

[0100] At box 222, the processing logic may generate an embedding for each digital design of the orthodontic aligner based on a subset of characteristics determined for that digital design. In some embodiments, the embedding may have a structured or tabular data format.

[0101] In an alternative embodiment, the operations at boxes 218 and 220 may be omitted. Instead, one or more height maps may be generated from the digital design of the aligner (e.g., from a dental arch or a 3D digital model of the aligner). Height maps can be generated by projecting the 3D digital model onto multiple different planes from multiple different angles. In such an embodiment, at box 222, an embedding may be generated by combining multiple height maps associated with the digital design of the aligner.

[0102] At box 224, the processing logic collects a training dataset comprising digital designs of multiple orthodontic aligners. In an embodiment, the training dataset may include embeddings generated at box 222. Each embedding may be associated with metadata indicating whether the aligner associated with the embedding is marked as a damaged aligner or an undamaged aligner. Preferably, the training dataset contains thousands, tens of thousands, hundreds of thousands, or more data points, where each data point is data (e.g., an embedding) associated with a different aligner. In some embodiments, digital designs of aligners with associated damage points (provided by real-world data) and digital designs of aligners with associated potential damage points (provided by the output of numerical simulations) may be used together to generate a robust machine learning model that can predict potential damage points of new aligners from the digital models of those aligners. In an embodiment, the machine learning model or statistical model may also classify the type of damage, the extent of damage, and / or other information related to the aligner.

[0103] At box 226, the processing logic trains a machine learning model using a training dataset. The machine learning model can be trained to process data (e.g., embeddings) from a digital design of an orthodontic aligner and output the probability associated with the digital design that the aligner will be damaged during the manufacturing process, during clinical use, during transport and disposal, and so on. In this embodiment, the machine learning model is trained to have a false positive rate of, for example, 2% or less, for the desired target.

[0104] A machine learning model can refer to a model artifact created by a training engine using a training dataset (e.g., training inputs and corresponding target outputs or labels). Training can be performed using a training dataset that includes at least one of the following: a) a digital design of aligners for a first set, with labels indicating whether each of the plurality of first aligners has undergone one or more damage points; or b) a digital design of aligners for a second set, with labels indicating whether each of the second set of aligners includes one or more possible damage points. A machine learning model can consist of a single level of linear or nonlinear operations (e.g., a support vector machine (SVM) or a single level of neural network), or it can be a deep neural network consisting of multiple levels of nonlinear operations. Examples of deep networks and neural networks include convolutional neural networks and / or recurrent neural networks with one or more hidden layers. Some neural networks may consist of interconnected nodes, where each node receives input from a previous node, performs one or more operations, and sends the resulting output to one or more other connected nodes for future processing.

[0105] Convolutional neural networks (CNNs) encompass architectures that can provide efficient image recognition. A CNN may include several convolutional layers and subsampling layers that apply filters to image portions of text to detect certain features (e.g., damaged points). Specifically, a CNN includes a convolution operation that element-wise multiplies each image segment by a filter (e.g., a matrix) and sums the results at similar locations in the output image.

[0106] Recurrent neural networks (RNNs) can propagate data forward and backward from later processing stages to earlier ones. RNNs include the ability to process sequences of information and store information about previous computations in the context of hidden layers. Thus, RNNs may possess a kind of "memory."

[0107] In some embodiments, the machine learning model may be a random forest classifier. A random forest classifier applies an ensemble learning approach to classify data by constructing multiple decision trees (e.g., hundreds to thousands of decision trees) that output classification decisions based on input data during training. The random forest classifier averages the decisions of the multiple decision trees and produces an output based on the average. In embodiments, different decision trees in the random forest classifier may be trained on different portions of the training dataset. Each decision tree may be a predictive model that uses observations about the input data (represented by branches of the decision tree) to draw conclusions about the input data (represented by leaves of the decision tree). For example, each decision tree may be trained to determine the classification for a digital design of an alignment tool. In embodiments, the random forest classifier may be trained using a training algorithm such as feature bagging (also known as bootstrap aggregating), which selects a random subset of features at each candidate split during the learning process. An advantage of a trained random forest classifier is that, after classification, processing logic or the user can accurately determine why a classification was made by tracking the branches of one or more decision trees that reached the classification decision.

[0108] In some embodiments, the machine learning model may be an XGBoost classifier. XGBoost is an implementation of gradient boosting decision trees. In other embodiments, other gradient boosting decision trees may be used to implement the machine learning model. Boosting is an ensemble technique in which new models are added to correct errors produced by existing models. Models are added sequentially until no further improvement can be made. Gradient boosting is a method of creating new models that predict the residuals or errors of previous models. The results of multiple models are then summed together to make a final prediction. It is called gradient boosting because it uses the gradient descent algorithm to minimize the overhead of adding new models. In some embodiments, the machine learning model may be a logistic regression model.

[0109] In embodiments where a random forest classifier or gradient boosting decision tree classifier (e.g., an XGBoost classifier) ​​is trained on features extracted from a digital model of a dental arch or aligner, the machine learning model can be trained to express the joint effects of the features and identify aligners that may be damaged or broken.

[0110] In some embodiments, the machine learning model can be periodically retrained using an updated training dataset. For example, as new patients are treated, additional data about the manufactured aligners can be continuously generated. On a periodic or recurring basis (e.g., every six months), the processing logic can repeat the training of the machine learning model. By periodically retraining the machine learning model, new information, techniques, and / or processes can be captured and reflected in the model, such as updated software, updated manufacturing processes, etc. In some embodiments, the training of the machine learning model can be continuous or sequential based on the continuous inflow of new data. In some embodiments, different machine learning models are trained for aligners formed from different materials, aligners manufactured using different manufacturing processes, and / or aligners with other parameters (e.g., direct manufacturing versus thermoforming). For example, a first machine learning model can be trained to predict potential damage points on aligners manufactured by thermoforming them on a mold, and a second machine learning model can be trained to predict potential damage points on aligners directly manufactured using 3D printing or other rapid prototyping techniques.

[0111] Figure 2B A flowchart of a method 230 for performing analysis on a digital design of an alignmentr using a trained machine learning model, according to one embodiment, is shown. One or more operations of method 230 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 230 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 230 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 230 includes... Figure 1A The operations performed during box 104.

[0112] At block 232 of method 230, the processing logic may perform analysis on the digital design of an orthodontic aligner (e.g., a polymer orthodontic aligner) using a trained machine learning model, which may have been trained according to method 200. Performing analysis on the digital design of the aligner using the trained machine learning model may include applying (block 234) the digital design of the aligner as input to the trained machine learning model. Furthermore, performing analysis on the digital design of the aligner using the trained machine learning model may include generating (block 236) an output indicating whether the digital design of the aligner includes one or more potential damage points, using the trained machine learning model. In some embodiments, if the digital design of the aligner includes one or more potential damage points, the output of the trained machine learning model may identify the location of one or more damage points. Additionally, the output of the trained machine learning model may include recommendations for one or more of the aforementioned corrective measures. Alternatively, the output of the trained machine learning model, along with the digital design of the aligner, may be input into another system or module (e.g., another trained machine learning model). This other system or module may then determine recommended corrective measures based on the digital design of the aligner and the predicted damage points.

[0113] In some embodiments, after a trained machine learning model determines that one or more potential damage points have been predicted, the digital design of the aligner, which includes one or more potential damage points, can be further processed by performing numerical simulations on the digital design of the polymer aligner to verify the presence of one or more potential damage points. The numerical simulation can be any numerical simulation described herein. For example, in embodiments, the numerical simulation can be: a) simulating the removal of the orthodontic aligner from a mold of the patient's dental arch, or b) simulating the load around a weak point in the orthodontic aligner. Using numerical simulation to process the digital model of the aligner can be computationally expensive and require more resources compared to using a trained machine learning model to process the digital model of the aligner. Therefore, resource utilization (e.g., memory and / or processor utilization) can be minimized by first processing the digital model of the aligner with a trained machine learning model, and then limiting the use of numerical simulation to test the digital model of the aligner against which the trained machine learning model predicted damage points. Additionally, in some embodiments, the trained machine learning model determines the presence of one or more potential damage points but does not identify the location of such potential damage points. In some embodiments, by using numerical simulation to process a trained machine learning model already configured with a digital model of the aligner to predict damage points, the location of one or more damage points can be identified, and corrective measures can be determined.

[0114] Figure 2CA flowchart of method 240, according to one embodiment, is shown to determine whether an orthodontic aligner will become damaged (e.g., break) during or after the manufacture of the orthodontic aligner. Examples of post-manufacturing damage include damage during clinical use of the aligner, damage during transport and disposal of the aligner, etc. The machine learning model may have been trained according to method 200. One or more operations of method 240 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 240 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 240 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 230 includes... Figure 1A The operations performed during box 104.

[0115] At box 242 of method 240, the processing logic may extract geometric, treatment-related, and / or clinical features from the digital design of the orthodontic aligner in the manner described above with reference to method 200. At box 244, the processing logic may select a subset of features. The selected subset of features may correspond to the same subset of features used to train the machine learning model. At box 246, the processing logic may generate an embedding for the digital design based on the subset of features.

[0116] At box 248, the processing logic uses a trained machine learning model to process data from the digital design of the orthodontic aligner. In an embodiment, the data from the digital design may include the embedding generated at box 246. Alternatively or additionally, the data from the digital design may include a three-dimensional digital model of the aligner or a three-dimensional digital model of the dental arch or mold used to manufacture the aligner. Alternatively or additionally, the data from the digital design may include one or more height maps generated by projecting the three-dimensional digital model of the dental arch or aligner onto one or more planes.

[0117] At box 250, the trained machine learning model outputs the probability that the orthodontic aligner, associated with the digital model, will be damaged during the aligner's manufacturing process or during subsequent use. This probability can be a value ranging from 0 to 1, where 1 represents a 100% chance of the aligner being damaged, and 0 represents a 0% chance of the aligner being damaged.

[0118] In one embodiment, at box 252, the machine learning model also outputs information identifying the probability that a specific point or location on the orthodontic aligner will be damaged. For example, it could output a separate probability value from 0 to 1 for each of multiple points on the orthodontic aligner.

[0119] In one embodiment, at block 254, the processing logic determines whether the probability of the orthodontic aligner being damaged is below a first threshold (or whether the probability of all points on the orthodontic aligner being damaged is below a first threshold). If the probability of the orthodontic aligner being damaged is below the first threshold, the method continues to block 256, and the aligner can be determined to be a low-risk aligner. Figure 1B Then, a first manufacturing process for a low-risk aligner can be selected for the aligner.

[0120] If the probability of the orthodontic aligner being damaged is determined to be higher than a first threshold at box 254, the method proceeds to box 256. At box 256, the processing logic determines whether the probability of the orthodontic aligner being damaged is higher than a second threshold (or whether the probability of any point on the orthodontic aligner being damaged is higher than a second threshold). The second threshold can be higher than the first threshold. For example, the first threshold can be 0.2%, 0.5%, 1%, 2%, 5%, or 10%, while the second threshold can be 15%, 20%, 25%, 30%, 40%, or 50%. If the probability of the orthodontic aligner being damaged is higher than the second threshold, the method proceeds to box 260. Otherwise, the method proceeds to box 258.

[0121] At box 258, it can be determined that the aligner is a standard risk aligner. For example... Figure 1B As shown in the diagram, a second manufacturing process for a standard risk aligner can then be selected for the aligner.

[0122] At box 260, the processing logic determines that the aligner is a high-risk aligner. (As in...) Figure 1B Then, a third manufacturing process can be selected for the aligner for high-risk aligners. In one embodiment, at block 262, the processing logic can output a notification including the location of at least one point that has a probability of failure equal to or greater than a second threshold. For example, such a notification could be output if a machine learning model outputs data indicating the locations of points on the aligner and the associated probabilities that those points become failures.

[0123] In some embodiments, such as Figure 2CAs shown, the aligner can be classified into three different categories based on the probability that it will be damaged during or after manufacturing. These classifications can include low-risk, medium-risk or standard-risk, and high-risk categories. In other embodiments, the aligner can be classified into a binary category, which includes standard risk (or no damage predicted) and high risk (or damage predicted). In such embodiments, the operations of blocks 254 and 256 can be omitted.

[0124] Figure 2D A flowchart illustrating method 264, according to one embodiment, uses a trained machine learning model to determine whether any orthodontic aligners in a set of orthodontic aligners associated with a patient's treatment plan will be damaged (e.g., broken) during or after the manufacture of the set of orthodontic aligners. The machine learning model may have been trained according to method 200. One or more operations of method 264 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 264 may be performed by executing... Figure 14 The alignment design analysis module 1450 is used for processing. It should be noted that method 264 can be performed for each treatment plan, or for the upper and lower dental arches of each treatment plan.

[0125] At block 266 of method 264, the processing logic determines a set of aligners, which includes digital designs of orthodontic aligners associated with the patient's treatment plan. For example, the treatment plan may divide the patient's orthodontic treatment into a series of phases, and different orthodontic aligners may be designed for each treatment phase. A single treatment plan may include any number of phases and associated digital designs of orthodontic aligners (e.g., up to 50 phases), and separate digital designs may be generated for the upper and lower dental arches for each phase. In one embodiment, the set of aligners includes all digital designs of the upper or lower dental arches associated with the patient's treatment plan. In another embodiment, the set of aligners includes all digital designs of the upper and lower dental arches associated with the patient's treatment plan.

[0126] At box 268, the processing logic may extract geometric, treatment-related, and / or clinical features from the digital design of each orthodontic aligner in the aligner set in the manner described in reference method 200 above. At box 270, the processing logic may select a subset of features. The selected subset of features may correspond to the same subset of features used to train the machine learning model. At box 272, the processing logic may generate an embedding for each digital design in the aligner set based on the corresponding subset of features.

[0127] At box 274, the processing logic uses a trained machine learning model to process data from the digital design of the orthodontic aligner. In an embodiment, the data from the digital design may include the embedding generated at box 246. Alternatively or additionally, the data from the digital design may include a three-dimensional digital model of the aligner or a three-dimensional digital model of the dental arch or mold used to manufacture the aligner. Alternatively or additionally, the data from the digital design may include one or more height maps generated by projecting the three-dimensional digital model of the dental arch or aligner onto one or more planes.

[0128] At box 276, for each digital design of the aligners in the aligner set, the trained machine learning model outputs the probability that the aligner associated with the corresponding digital model (e.g., during the manufacture of the aligner or during subsequent use of the aligner) will be damaged. This probability can be a value ranging from 0 to 1, where 1 represents a 100% chance that the aligner will be damaged, and 0 represents a 0% chance that the aligner will be damaged.

[0129] In one embodiment, at block 278, the processing logic determines whether the probability of any orthodontic aligner being damaged is below a first threshold (or whether the probability of all points on the orthodontic aligner being damaged is below a first threshold). If the probability of all orthodontic aligners being damaged is below the first threshold, the method continues to block 280, and it can be determined that the set of aligners is a low-risk aligner set. Figure 1B Then, a first manufacturing process can be selected for the low-risk aligner set.

[0130] If, at box 278, the probability that one or more orthodontic aligners are damaged is determined to be higher than a first threshold, the method proceeds to box 282. At box 282, the processing logic determines whether the probability that at least one orthodontic aligner is damaged is equal to or greater than a second probability threshold (or whether the probability that any point on at least one orthodontic aligner is damaged is equal to or greater than a second threshold). The second threshold can be higher than the first threshold. For example, the first threshold can be 0.2%, 0.5%, 1%, 2%, 5%, or 10%, while the second threshold can be 15%, 20%, 25%, 30%, 40%, or 50%. If the probability that any orthodontic aligner in the aligner set is damaged is equal to or greater than the second threshold, the method proceeds to box 286. Otherwise, the method proceeds to box 284.

[0131] At box 284, it can be determined that this set of aligners is a standard risk aligner set. For example... Figure 1B As shown in the diagram, a second manufacturing process for the standard risk aligner set can then be selected for the aligner set.

[0132] At box 286, the processing logic determines that the aligner set is a high-risk aligner set. (As in...) Figure 1B Then, a third manufacturing process can be selected for the high-risk aligner set.

[0133] In some embodiments, such as Figure 2D As shown, the aligner set can be classified into three different categories based on the probability that an aligner in the set will be damaged during or after manufacturing. These categories may include a low-risk category, a medium-risk or standard-risk category, and a high-risk category. In other embodiments, the aligner set may be classified into a binary category, which includes standard risk (or no damage predicted) and high risk (or damage predicted). In such embodiments, the operations of blocks 254 and 256 may be omitted.

[0134] Figure 3A A flowchart of a method 300 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation according to one embodiment is shown. One or more operations of method 300 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 300 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 300 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 300 includes... Figure 1A The operations performed during box 104.

[0135] At box 302, the processing logic can perform an analysis of the digital design of the aligner using numerical simulations associated with the removal of the polymer aligner from a tooth-like or arch-like structure (e.g., a mold or patient's dentition). Numerical simulations can include finite element methods, finite difference methods, finite volume methods, meshless methods, smoothed particle methods, combinations of these methods, etc. The finite element method (also known as finite element analysis) can refer to a numerical method used to solve partial differential equations, and can also be used to perform structural analysis of the aligner. The geometry of the structure (in this case, the aligner) is discretized into multiple points or elements on a domain to solve a set of partial differential equations characterizing the constitutive relations of the aligner material, and the solution is performed in a finite-dimensional functional space. The finite difference method can refer to a numerical method used to solve differential equations by approximating them with difference equations and calculating approximate values ​​at discrete points. The finite volume method can refer to a method of representing and evaluating partial differential equations in the form of algebraic equations. The finite volume method can also calculate values ​​(e.g., strain, stress, force) at discrete locations on the mesh geometry of the digital design of the aligner. "Finite volume" can refer to a small volume surrounding each point on a mesh. Meshless methods can refer to methods based on the interaction between nodes or points and all their neighboring nodes or points. In other words, meshless methods do not require connections between nodes in the simulation domain. Smooth particle Galerkin or hydrodynamic methods can be forms of meshless methods.

[0136] At block 304, the processing logic may simulate one or more forces and / or displacements on the digital design of the aligner that are associated with the removal of the aligner from a dental arch structure (e.g., a mold or a patient's dental arch). Simulating one or more forces and / or displacements on the digital design of the aligner may include performing the operations at blocks 306, 308, 310, 312, and 314. At block 306, the processing logic may collect one or more material properties of the aligner (also referred to as material property information). Material properties may include the amount or value of stress and / or strain that the material can withstand before breakage, fracture, deformation, warping, etc. An example of a material property is the Young's modulus of the material. In some embodiments, since the aligner will be made of the same material (e.g., a polymer), the material properties may not change between different digital designs of the aligner. In embodiments, the material properties may be included in the configuration of the aligner design analysis module 1450.

[0137] At box 308, the processing logic can collect a first geometry of the aligner from the digital design of the aligner. The first geometry can be specific to each patient (and each stage of treatment) and can be determined based on the patient's dental arch. The first geometry is obtained by generating the digital design of the aligner by manipulating a digital model of the arch-like structure (e.g., a mold or the patient's dental arch). The digital model of the arch-like structure can represent the patient's dental arch. The digital model of the mold can be compensated to approximate the surface of the aligner and generate the digital design of the aligner. Thus, the digital design of the aligner can include cavities (referred to as tooth-receiving cavities or covers) configured to accommodate the patient's teeth and / or attachments on the teeth.

[0138] At box 310, the processing logic can collect a second geometry of the dental arch structure from a digital model of the arch structure (e.g., a mold). The digital model of the dental arch structure can be generated from information obtained through intraoral scanning of the patient during consultation and / or from the treatment plan. For example, the patient's dental arch can be digitized via scanning and modeled as a dental arch for mold fabrication. The second geometry may include information related to the patient's dental arch, such as tooth size, tooth shape, tooth orientation, interdental distances, attachments on the teeth, upper dental arch, lower dental arch, etc.

[0139] At box 312, the processing logic can simulate the removal of an aligner with one or more material properties and a first geometry from a toothed arch structure with a second geometry by applying one or more loads (e.g., one or more forces and / or displacements) to a set of points on the digital design of the aligner. The performed numerical simulation may include solving a series of partial differential equations that model the application of one or more loads (e.g., forces and / or displacements) to the aligner with the material properties and first geometry to remove the aligner from the toothed arch structure with the second geometry. Furthermore, the partial differential equations can calculate stress or strain values ​​at each point in the set of points on the digital design of the aligner, and can determine whether a point is a potential point of failure based on the calculated stress or strain values ​​and the amount of force applied. The partial differential equations can be elastostatic or elastostatic partial differential equations that calculate the stress or strain state in the digital design of the aligner and thus predict rupture, warping, deformation, etc. Polymer strain / stress can be a factor leading to crack initiation and rupture, as well as warping, deformation, etc., in polymer aligners. The partial differential equations can be expressed as follows: Find ( ), so that: in ,

[0140] Under boundary conditions: exist Place,

[0141] exist Place,

[0142] And initial conditions: exist Place,

[0143] exist Place,

[0144] Given , , , , , , , , ,

[0145] in, It is a 3D displacement field. It is a Dirichlet boundary condition. It is a Neumann boundary condition. It is the applied force (body force). , It is the initial displacement and velocity. and It is the stress and strain tensor. It is the elastic tensor. It is the density of the material. This refers to the domains of interest. Note that settings can be configured. Furthermore, it can solve problems related to elastic statics.

[0146] At box 314, for each point in the point set, the processing logic can perform the operations at boxes 316 and 318. At box 316, the processing logic can determine whether the values ​​of stress and / or strain meet the damage criteria for each point by solving the partial differential equations described above. The damage criteria are met when the values ​​of stress and / or strain exceed a threshold. The partial differential equations can be used to calculate the values ​​of strain / stress or deformation energy at each point in the point set, as well as the amount of resistance involved in removing the alignment device from the mold at that point. Because a second geometry of the dental arch structure is used in the numerical simulation, information related to the attachment may be related to the amount of resistance. In some embodiments, information related to the resistance associated with the digital design of removing the alignment device at that point, and information related to the second geometry of the dental arch structure associated with the point and resistance (tooth size, tooth shape, number of teeth, distance between teeth, attachment type, attachment size, attachment number, etc.) can be stored in a lookup table. This lookup table can later be referenced by a simplified model that does not take into account the second geometry of the dental arch structure. Therefore, as described below, the lookup table can be filled before running a simplified model that depends on resistance as part of its calculation.

[0147] At box 318, in response to determining that the values ​​of strain and / or stress meet damage criteria (e.g., the value of local deformation (strain and stress) exceeds a threshold (e.g., 1-20% strain or 0.5-20 MPa stress)), the processing logic can determine that this point is a potential failure point. If the strain and / or stress values ​​calculated at this point exceed the threshold, cracks may initiate and lead to rupture; strain / stress or deformation energy may cause warping, deformation, etc., of the alignment device. The threshold defined for strain / stress or deformation energy may be related to a yield criterion (e.g., von Mises) or maximum / minimum principal stress / strain or deformation energy, such that when the strain / stress or deformation energy value reaches the criterion value, the polymer material will fail, or it may be any suitable configurable threshold.

[0148] Figure 3BAn example numerical simulation 350 is illustrated, relating to the removal of a digital design of an aligner 352 from a digital model of a dental arch structure 354 according to one embodiment. The numerical simulation 350 graphically represents the solution of partial differential equations when one or more forces and / or displacements are applied to the digital design of the aligner 352 to remove the digital design of the aligner 352 from the digital model of the dental arch structure 354. As shown, a set of points (represented as triangles in the digital model of the aligner 352) is included in the digital design of the aligner 352, and the partial differential equations calculate the stress or strain value at each point, and the amount of resistance involved in removing the digital design of the aligner 352 from the digital model of the dental arch structure (e.g., mold) 354 at that point. The numerical simulation 350 may use color-coded shading associated with strain or stress values. A first color, shading, or hash may represent stress or strain values ​​below a threshold, while a second color, shading, or hash may represent stress or strain values ​​exceeding a threshold. Any number of colors, shades, and / or hashes can be used to represent various strain / stress or deformation energy values ​​along a scale. For example, processing logic can calculate the strain value of point 356 below a threshold and thus shade these points with a first color (e.g., blue) or a first hash, indicating that point 356 is not a potential failure point because its strain or stress value does not exceed the threshold. In some embodiments, the shading can be based on the amount of resistance involved in removing the digital design of the aligner 352 from a digital model of the arch-shaped structure (e.g., mold) 354. If the amount of resistance exceeds a threshold, it can be identified as a potential failure point, and those points can be shaded with a second color (e.g., red) or hash.

[0149] Figure 4A A flowchart illustrating a method 400 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation by modeling the teeth of a dental arch and adhesive attachments as springs, according to one embodiment, is shown. One or more operations of method 400 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 400 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 400 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 400 includes... Figure 1A The operations performed during box 104.

[0150] At box 402, the processing logic can perform an analysis of the digital design of the aligner using numerical simulations associated with the removal of the aligner from a tooth-like or arch-like structure (e.g., a mold or patient's dentition). Numerical simulations can include finite element analysis, finite element methods, finite difference methods, finite volume methods, meshless methods, smoothed particle methods, etc.

[0151] At box 404, the processing logic can simulate one or more forces and / or displacements on the digital design of the aligner that are associated with the removal of the aligner from the dental arch structure. Simulating one or more forces and / or displacements on the digital design of the aligner may include performing the operations at boxes 406 and 408. At box 406, the processing logic can model each tooth of the patient's dental arch as a potentially fragile connector (e.g., a spring) attached to a corresponding cavity in the digital design of the polymer aligner. Modeling each tooth as a spring is computationally cheaper and more time-efficient than using a second geometry of a digital model with a mold. The modeled springs can be used to determine reactive strains and stresses, and to determine the effects of these strains and stresses at various parts of the digital design of the polymer aligner. Calibration of the spring parameters can be determined using various techniques, such as experiments and more detailed computational models.

[0152] At box 408, for each spring, the processing logic can perform the operations at boxes 410, 412, 414, and 416. At box 410, the processing logic can determine the spring stiffness based on the resistance associated with the modeled tooth and the geometry of the tooth and / or any attachments associated with the tooth modeling the spring. In some embodiments, a reference can be run without... Figure 3A The resistance is obtained from the aforementioned lookup table in the described numerical simulation, which uses a second geometry of the dental arch represented by a digital model of the dental arch. For example, the lookup table could store information such as: a digital design of a polymer aligner removed from a specific tooth with 0 attachments breaks when a force of 1 Newton (N) is applied; a digital design of a polymer aligner removed from a specific tooth with 1 attachment breaks when a force of 3 N is applied; a digital design of a polymer aligner removed from a specific tooth with 2 attachments breaks when a force of 5 N is applied, and so on. In some embodiments, a reference can be used. Figure 3A The described numerical simulation is used to dynamically calculate the resistance. The geometry of the attachment and associated tooth may include the undercut of the attachment and / or tooth. The undercut of the attachment may refer to the height of the lower surface of the attachment. The height of the undercut of the attachment can be used to determine the distance that the digital design of the polymer aligner needs to move to disengage from the attachment on the tooth. Stiffness can be determined by dividing the resistance by the undercut distance. The determined stiffness can be measured in Newtons per millimeter (N / mm). For example, the stiffness of the connector may be 30 N / mm (3 N of resistance divided by an undercut distance of 0.1 mm).

[0153] At box 412, the processing logic can determine the amount of force required to break the spring by performing a numerical simulation of the digital design for removing the aligner from the spring. In some embodiments, the partial differential equations described above can be used to perform the numerical simulation of the digital design for removing the aligner from the spring. In some cases, the vertical force associated with the spring is used in the partial differential equations, and linear operations can be used, which is consistent with the reference... Figure 3A The nonlinear operations used in the partial differential equations described by Method 300 are the opposite. The partial differential equations can take the spring stiffness and / or the material properties of the aligner as inputs to determine the required force. Furthermore, while simulating the digital design of the aligner by removing it from the spring, the partial differential equations can calculate the values ​​of strain / stress or deformation energy at various points in the digital design of the aligner associated with the spring.

[0154] At box 414, the processing logic can determine whether the force on the spring is greater than a threshold force during the transfer process. If the force is greater than the threshold force, the spring may break. If the force is greater than the threshold force, the value of one or more strain / stress or deformation energy at one or more points on the digital design of the aligner may exceed the threshold strain / stress or deformation energy value caused by excessive force.

[0155] At block 416, in response to determining whether the stress / strain or deformation energy on the aligner meets a damage criterion, the processing logic may determine that a point in the digital design of the aligner is a potential damage point. The stress / strain or deformation energy may meet a damage criterion when its value exceeds a threshold. In an embodiment, in response to determining that the amount of force required to break the spring associated with that point exceeds a threshold amount of force, the processing logic may determine that a point in the digital design of the aligner is a potential damage point. In response to determining the presence of a potential damage point, one or more corrective measures may be performed. In some embodiments, the digital design of the aligner may be fed into a trained machine learning model to verify potential damage points.

[0156] Figure 4BAn example numerical simulation 450 is shown, modeling the teeth of a patient's dental arch as springs 452 according to one embodiment. As shown, each spring 452 is inserted into a corresponding cavity of a digitally designed polymer aligner 454, just as a tooth would be when the aligner is worn or attached to a mold. Each spring 452 may have a stiffness determined based on resistance and the geometry of the undercut of the attachment on the tooth, which is associated with the digitally designed removal of the aligner from the corresponding tooth, which may have an attachment. The numerical simulation can model the removal of the digitally designed aligner from each spring by applying one or more forces and / or displacements to lift the digitally designed aligner from the spring. If the force required to break the spring is greater than a threshold amount of force, the processing logic can determine that a potential point of failure exists at a portion of the digitally designed aligner associated with that spring. It should be understood that the numerical simulation is calculated simultaneously for each spring 452 while the digitally designed aligner is being removed.

[0157] Figure 5A A flowchart illustrating a method 500 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation by modeling a subset of teeth and adhesive attachments of a dental arch as springs, according to one embodiment, is shown. One or more operations of method 500 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 500 may be performed by executing… Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 500 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 500 includes... Figure 1A The operations performed during box 104.

[0158] At box 502, the processing logic can perform an analysis of the digital design of the aligner using numerical simulations associated with the removal of the aligner from the arch-shaped structure. Numerical simulations can include finite element analysis, finite element methods, finite difference methods, finite volume methods, meshless methods, smooth grain Galerkin methods, etc.

[0159] At block 504, the processing logic may simulate one or more forces and / or displacements in the digital design of the aligner associated with the removal of the aligner from the arch-like structure (e.g., a mold or the patient's dental arch). Simulating one or more forces and / or displacements in the digital design of the aligner may include performing the operations at blocks 506, 508, and 510. At block 506, the processing logic may model a subset of the teeth in the patient's dental arch as a subset of springs. Each spring in the subset of springs may be attached to a corresponding cavity in the digital design of the aligner. It should be understood that, in this embodiment, not every tooth in the patient's dental arch is modeled as a spring. Each subset of springs may model at least one different tooth that is different from another subset of springs. The subset of springs is used in different numerical simulations of removing the aligner from the arch-like structure. By performing numerical simulations using only a subset of springs, fewer calculations can be performed simultaneously, and the numerical simulation is performed faster than performing a numerical simulation for each spring modeled for each tooth in the dental arch. Method 500 can be iterated by performing numerical analysis on different subsets of the springs until each spring is involved in the numerical simulation of the digital design of the move aligner.

[0160] At box 508, the processing logic can determine the tooth model connected to another spring (e.g., reference). Figure 4A The method described in method 400 describes the force required to move the aligner. At block 510, for each spring in the subset of springs in the simulation, the processing logic may perform the operations at blocks 512 and 514. At block 512, the processing logic may determine the force required to move the aligner from the tooth model connected to another spring and apply that force to the aligner. At block 514, the processing logic may determine whether the aligner under this load meets a damage criterion. The damage criterion may involve a value of stress / strain or deformation energy exceeding a threshold. In an embodiment, in response to determining that the amount of force required to break the spring associated with that point exceeds a threshold amount of force, the processing logic may determine that the point on the digital design of the aligner is a possible damage point. One or more corrective measures may be performed in response to determining the presence of a possible damage point. In some embodiments, the digital design of the aligner may be fed into a trained machine learning model to verify possible damage points.

[0161] Figure 5BAn example numerical simulation 550 is shown, modeling a subset of teeth of a patient's dental arch as springs 552 according to one embodiment. As shown, the subset of springs 552 is inserted into corresponding cavities of a digitally designed aligner 554, just as with teeth when the aligner is worn or attached to a mold. In the depicted numerical simulation 550, springs are not included in some cavities of the digitally designed aligner 554. Different subsets of springs can be modeled in different numerical simulations until the numerical simulation of removing the digitally designed aligner 554 involves each modeled spring for each tooth. Each spring 552 may have a stiffness determined based on resistance and the geometry of the undercut of the attachment on the tooth, which is associated with the digitally designed aligner removal from the corresponding tooth, which may have an attachment. The numerical simulation can model the digitally designed aligner removal from the subset of springs by applying one or more forces to lift the digitally designed polymer aligner from the subset of springs. If the stress / strain or deformation energy value at any point on the spring exceeds a threshold to meet the damage criterion, the processing logic can determine that the possible damage point exists in a portion of the digital design of the aligner associated with the first spring. It should be understood that while retrieving the digital design of the aligner, a numerical simulation is simultaneously performed for each spring 552 in the spring subset.

[0162] Figure 6A A flowchart of a method 600 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation according to one embodiment is shown. One or more operations of method 600 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 600 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 600 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 600 includes... Figure 1A The operations performed during box 104.

[0163] At box 602, the processing logic can use numerical simulation to perform analysis on the digital design of the aligner to determine the overall strength of the aligner under one or more load conditions. Numerical simulations can include finite element methods, finite difference methods, finite volume methods, meshless methods, smoothed grain methods, combinations of these methods, etc.

[0164] At block 604, the processing logic may collect one or more material properties (also referred to as material property information) of the aligner. Material properties may include the amount or value of stress and / or strain that the material can withstand before breakage, cracking, deformation, warping, etc. An example of a material property is the Young's modulus of the material. In some embodiments, since the aligner will be made of the same material (e.g., a polymer), the material properties may not change between different digital designs of the aligner. In embodiments, the material properties may be included in the configuration of the aligner design analysis module 1450.

[0165] At box 606, the processing logic can collect the geometry of the aligner from the digital design of the aligner. The geometry can be specific to each patient (and each stage of treatment) and can be determined based on the patient's dental arch. The geometry is obtained by generating the digital design of the aligner by manipulating a digital model of the arch-like structure (e.g., a mold or the patient's dental arch). The digital model of the arch-like structure can represent the patient's dental arch. The digital model of the arch-like structure can be compensated to approximate the surface of the aligner and generate the digital design of the aligner. Thus, the digital design of the aligner can include cavities (referred to as tooth-receiving cavities or covers) configured to accommodate the patient's teeth and / or attachments on the teeth.

[0166] At box 607, the processing logic may collect clinical and / or treatment-related information associated with the aligner (and its digital design). For example, clinical information may include at least one of tooth crowding information, undercut information, tooth geometry information, tooth size, tooth shape, number of teeth, or distance between teeth. Treatment-related information may include at least one of the following: the number of attachments associated with one or more of the multiple tooth cavities, the type of attachments associated with one or more of the multiple tooth cavities, the placement of the attachments on the teeth, or precise cutting information associated with one or more interproximal regions. In some embodiments, such information is included in a lookup table that may be referenced by the processing logic and / or simulation.

[0167] At block 608, the processing logic can simulate one or more loads on the digital design of the aligner (e.g., the geometry of the digital design of the aligner). The simulated loads can include one or more of bending loads, torsional loads, uniaxial tensile loads, uniaxial compressive loads, shear loads, and / or another load. In embodiments, the simulated loads can be simulated forces, moments, or displacements (e.g., translation and / or rotation). Simulating one or more loads on the digital design of the aligner can include performing the operations at blocks 610, 614, 616, and 618.

[0168] At box 610, the processing logic can select a region of the digital design of the aligner, and can then proceed to perform the operations of boxes 614-618 to test the strength associated with the selected region. At box 610, each of the set of regions can be selected, and the operations of boxes 614-618 can be repeated for each region. The selected regions can all be weak points of the aligner, such as adjacent regions of the aligner.

[0169] Figure 6F Weak points 655, 660, 665 of an aligner 626 according to one embodiment are shown. The weak points may correspond to adjacent regions of the aligner.

[0170] Return to Figure 6A At box 614, the processing logic applies one or more load conditions around a selected region (e.g., around a weak point or adjacent region). As described above, the load conditions may include bending loads, torsional loads, uniaxial tensile loads, uniaxial compressive loads, and / or shear loads, which may be applied individually or together. In one embodiment, the load is a moment or force, such as a lifting force, bending force, torsional force, shear force, tensile force, or compressive force. In this embodiment where a force or moment is applied, strain and / or strain energy can be calculated. In one embodiment, the load is a displacement (e.g., translational displacement and / or rotational displacement), and stress can be calculated.

[0171] Load conditions around a region can be simulated by applying a first boundary condition to one or more regions on a first side of the region and by applying a second boundary condition to one or more additional regions on a second side of the region. For example, load conditions around an interproximal region can be simulated by fixing one or more first tooth receptacles on the first side of the interproximal region in place and applying a load to one or more second tooth receptacles on the second side of the interproximal region. In one embodiment, the load is applied to the occlusal surface of one or more second tooth receptacles.

[0172] Clinical and / or treatment-related information can be correlated with the magnitude of the load required to remove the aligner from the associated dentition (e.g., the tooth cavity of the aligner) in the region. For example, the number of attachments on one or more dentitions adjacent to the tooth cavity can affect the resistance associated with removing the aligner from the dental arch at the tooth cavity. To account for this interaction in a simulation, the amount of load applied around a region (e.g., around an interproximal region) can be based on the number of attachments associated with one or more teeth adjacent to that region. Other clinical and / or treatment-related information can also be used to adjust the magnitude of the applied load. Such information may include, for example, jaw shape, tooth size, tooth shape, tooth number, tooth position, attachment type, attachment size, attachment number, etc.

[0173] Figure 6B A bending load 634 is shown applied around a region 633 of an aligner 626 according to one embodiment. Region 633 may be an adjacent region connecting a first tooth receiving cavity (cap) 628 and a second tooth receiving cavity (cap) 635. The bending load 634 may be applied about an axis 632 passing through region 633. For example, the bending load 634 at the adjacent region 633 can be simulated by fixing the first tooth receiving cavity 628 and / or the third tooth receiving cavity 627 on a first side of the adjacent region 633 in place (e.g., by setting a zero displacement boundary condition) and applying a load to the second tooth receiving cavity 630 on a second side of the adjacent region 633 (e.g., by setting a force boundary condition or a displacement boundary condition for the second tooth receiving cavity). In one embodiment, the load is applied to the tooth receiving cavity 630, which may be the tooth receiving cavity at the far end of the aligner 626. In another embodiment, the bending load 634 is applied to the tooth receiving cavity 635 adjacent to the tooth receiving cavity 628. To simulate applying a load to the next adjacent region 629, the boundary conditions on the tooth cavity 628 can be removed, and boundary conditions can be set for the tooth cavity 627. The load can then be applied to the tooth cavity 630 again.

[0174] As mentioned, the magnitude of the load (which may include force, moment, torque, displacement, rotation, etc.) applied to a defined region (e.g., the interproximal region) to impart strain, stress, and / or strain energy can be based on clinical and / or treatment-related information. In one embodiment, the amount of load applied around the interproximal region 633 is based at least in part on the number of attachments associated with the tooth receptacle 628 (e.g., the number of attachments placed on the tooth that will mate with the tooth receptacle 628) and / or the number of attachments associated with the tooth receptacle 627. The presence of attachments on the teeth associated with these tooth receptacles 627, 628 may increase the amount of force required to remove the alignment device from the mold. Therefore, the amount of load simulated for the interproximal region 633 can be increased based on the number of attachments associated with the tooth receptacle 627 and / or the tooth receptacle 628. In one embodiment, if there are no attachments associated with the tooth receptacle 627 and / or if there are no attachments associated with the tooth receptacle 628, a force of 1 Newton (N) is applied to simulate the load around the interproximal region 633. In one embodiment, for each attachment associated with tooth cavity 627, the applied force is increased by 1 Newton or other amount to test strain at interproximal region 633. In one embodiment, for each attachment associated with tooth cavity 628, the force is increased by 1 Newton or other amount to test strain at interproximal region 633.

[0175] Figure 6C A torsional load 638 is shown applied around a region of aligner 626 according to one embodiment. Region 633 may be an adjacent region connecting a first tooth receiving cavity (cap) 628 and a second tooth receiving cavity (cap) 635. The torsional load 638 may be applied about an axis 636 passing through region 633. For example, the torsional load 638 at the adjacent region 633 can be simulated by fixing the first tooth receiving cavity 628 and / or the third tooth receiving cavity 627 on a first side of the adjacent region 633 in place (e.g., by setting a zero displacement boundary condition) and applying a load or displacement to the second tooth receiving cavity 630 on a second side of the adjacent region 633 (e.g., by setting a force boundary condition or a displacement boundary condition for the second tooth receiving cavity). In one embodiment, the load is applied to the tooth receiving cavity 630, which may be the tooth receiving cavity at the far end of aligner 626. In another embodiment, the torsional load 638 is applied to the tooth receiving cavity 635 adjacent to the tooth receiving cavity 628.

[0176] Figure 6DA uniaxial tensile load 642 is shown applied to a region 633 surrounding an aligner 626 according to one embodiment. Region 633 may be an adjacent region connecting a first tooth receiving cavity (cap) 628 and a second tooth receiving cavity (cap) 635. The uniaxial tensile load 642 may be applied along an axis passing through region 633. For example, the uniaxial tensile load 642 at the adjacent region 633 can be simulated by fixing the first tooth receiving cavity 628 and / or the third tooth receiving cavity 627 on a first side of the adjacent region 633 in place (e.g., by setting a zero displacement boundary condition) and applying a load to the second tooth receiving cavity 630 on a second side of the adjacent region 633 (e.g., by setting a force boundary condition or a displacement boundary condition for the second tooth receiving cavity). In one embodiment, the load is applied to the tooth receiving cavity 630, which may be the distal tooth receiving cavity of the aligner 626. In another embodiment, the uniaxial tensile load 642 is applied to the tooth receiving cavity 635 adjacent to the tooth receiving cavity 628.

[0177] Figure 6E A shear load 646 is shown applied around region 633 of the aligner according to one embodiment. Region 633 may be an adjacent region connecting a first tooth receiving cavity (cap) 628 and a second tooth receiving cavity (cap) 635. In the example, the shear load 646 at the adjacent region 633 can be simulated by fixing the first tooth receiving cavity 628 and / or the third tooth receiving cavity 627 on a first side of the adjacent region 633 in place (e.g., by setting a zero displacement boundary condition) and applying a load to the second tooth receiving cavity 630 on a second side of the adjacent region 633 (e.g., by setting a force boundary condition or a displacement boundary condition for the second tooth receiving cavity). In one embodiment, the load is applied to the tooth receiving cavity 630, which may be the tooth receiving cavity at the far end of the aligner 626. In another embodiment, the shear load 646 is applied to the tooth receiving cavity 635 adjacent to the tooth receiving cavity 628.

[0178] In embodiments, some loads that can be applied may include combinations of bending, twisting, lifting, shearing, compression, and / or stretching. For example, a load applied to one or more regions of the alignment device may include a first magnitude along the x-axis (e.g., in the cheek direction), a second magnitude along the y-axis (e.g., in the mesial direction), and / or a third magnitude along the z-axis (e.g., in the vertical direction). For example, the load may include a force of 0 N along the x-axis, a force of 0.2 N along the y-axis, and a force of 1 N along the z-axis. Additionally or alternatively, example loads may include rotational forces about one or more of the x-axis, y-axis, and / or z-axis. For example, an example load may include a force of 0 N around the x-axis, a force of 0.2-1.0 N around the y-axis, and a force of 0 N around the z-axis.

[0179] Return to Figure 6A At box 616, numerical simulations are used to determine the quantities of strain, stress, and / or strain energy (e.g., strain energy density) for each simulated load condition. The quantities of strain, stress, and / or stress energy can be determined based on load conditions and material property information. Additionally, one or more derived values ​​can be derived from the strain, stress, and / or strain energy density. The performed numerical simulations may include solving a series of partial differential equations that model the application of one or more loads (e.g., forces and / or displacements) to an aligner having material properties and geometry. Furthermore, the partial differential equations can calculate stress or strain values ​​at selected regions (e.g., at weak points or adjacent regions). The partial differential equations can be elastic or elastomechanical partial differential equations that calculate the stress, strain energy, and / or strain states within the digital design of the aligner, which can be used to predict rupture, warping, deformation, etc. In one embodiment, the quantities of strain, stress, and / or strain energy are determined for the edge of the aligner at that region (e.g., at the edge where the region aligns with the aligner's cut line).

[0180] At block 618, the processing logic calculates a strength value for the region (e.g., a weak point or adjacent region) based on the amount of strain, stress, and / or strain energy (e.g., strain energy density) determined for one or more simulated loads. Additionally or alternatively, the strength value may be based on one or more derived values ​​derived from at least one of the strain, stress, and / or strain energy density. In one embodiment, the strength value for the region is based on the strain, stress, and / or strain energy density calculated for each of a plurality of different load conditions. For example, the strength value for the region may be based on the maximum strain, stress, and / or strain energy density from the strain, stress, and / or strain energy density values ​​calculated for the region.

[0181] The strength values ​​of the region can be used to determine whether the region is a potential failure point or includes potential failure points. For example, if the maximum calculated stress, strain, and / or strain energy density of the region exceeds a threshold, the region can be identified as a potential failure point of the aligner.

[0182] At block 620, the processing logic can determine the overall intensity value for the entire aligner. The overall intensity value can be based on the intensity value determined for each test area. In one embodiment, the intensity value corresponds to the minimum intensity value for the test area.

[0183] At box 622, the processing logic determines whether the strength value meets the damage criterion or standard. A damage criterion is met when the values ​​of stress and / or strain and / or strain energy density exceed a threshold. Partial differential equations can be used to calculate the values ​​of strain / stress, strain energy density, and / or deformation energy at each test region.

[0184] At box 622, in response to determining that the strength value meets the damage criteria (e.g., the value of local deformation (strain and stress) exceeds a threshold (e.g., 1-20% strain or 0.5-20 MPa stress)), the processing logic can determine that the aligner includes one or more possible failure points. If the strain and / or stress values ​​calculated at this point exceed the threshold, cracks may initiate and could lead to fracture; strain / stress or deformation energy may cause warping, deformation, etc., of the aligner. The thresholds defined for strain / stress, strain energy density, and / or deformation energy may be related to yield criteria (e.g., von Mises) such that the polymer material will fail when the strain / stress or deformation energy values ​​reach a critical value, or may be any suitable configurable threshold.

[0185] If the aligner has an overall strength value that meets the damage criteria (e.g., one or more regions of the aligner have strain, stress, and / or strain energy exceeding a threshold), then the aligner can be determined to include one or more potential failure points. In response to determining that the aligner includes one or more potential failure points, the processing logic can select a manufacturing process for the aligner that includes one or more potential failure points, such as referring to... Figure 1B As described above. Alternatively, in response to determining that the aligner includes one or more potential points of damage, the processing logic may perform one or more corrective measures as described above to generate a modified digital model of the aligner. Some examples of modifying the digital model of the aligner include: modifying the tangent radius of the digital model of the aligner (e.g., in the interdental region for potential points of damage), modifying the thickness of a portion of the digital model of the aligner (e.g., in the interdental region for potential points of damage), modifying the geometry of the digital model of the aligner (e.g., in or around the interdental region for potential points of damage), and inserting an indicator in the digital model of the aligner, wherein the indicator indicates a recommended location for initiating removal of the aligner from the dental arch mold. In another example, the processing logic may generate a modified digital model of the dental arch by modifying one or more attachments on one or more teeth in the digital model of the dental arch, and may then generate a modified digital model of the aligner based on the modified digital model of the dental arch. In another example, by adding new virtual fillers to a location on the digital model of the dental arch or expanding existing virtual fillers to a location on the digital model of the dental arch (which is associated with an adjacent region as a possible point of damage), the processing logic can generate a modified digital model of the dental arch, and then a modified digital model of the aligner can be generated based on the modified digital model of the dental arch.

[0186] Figure 7AA flowchart illustrates a method 700 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using a geometric estimator according to one embodiment. In this embodiment, the geometric estimator can be considered a type of numerical simulation. One or more operations of method 700 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 700 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 700 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 600 includes... Figure 1A The operations performed during box 104.

[0187] At block 702, the processing logic can use a geometric evaluator (e.g., numerical simulation) to perform an analysis on the digital design of the aligner to determine the overall strength of the aligner. In an embodiment, the geometric evaluator can determine one or more geometric properties of the digital design of the aligner at one or more regions of the aligner (e.g., at one or more adjacent regions and / or other weak points of the digital design of the aligner), and can calculate stress or stiffness or strength based on one or more geometric properties and the material properties of the material used to manufacture the aligner.

[0188] At block 704, the processing logic may collect one or more material properties (also referred to as material property information) of the aligner. Material properties may include the amount or value of stress and / or strain that the material can withstand before breakage, cracking, deformation, warping, etc. An example of a material property is the Young's modulus of the material. In some embodiments, since the aligner will be made of the same material (e.g., a polymer), the material properties may not change between different digital designs of the aligner. In embodiments, the material properties may be included in the configuration of the aligner design analysis module 1450.

[0189] At box 706, the processing logic can collect the geometry of the aligner from the digital design of the aligner. The geometry can be specific to each patient (and each stage of treatment) and can be determined based on the patient's dental arch. The geometry is obtained by generating the digital design of the aligner by manipulating a digital model of the arch-like structure (e.g., a mold or the patient's dental arch). The digital model of the arch-like structure can represent the patient's dental arch. The digital model of the arch-like structure can be compensated to approximate the surface of the aligner and generate the digital design of the aligner. Thus, the digital design of the aligner can include cavities (referred to as tooth-accommodating cavities or covers) configured to receive the patient's teeth and / or attachments on the teeth.

[0190] At box 707, the processing logic can determine the location of potential weak points (e.g., inter-dental regions of the aligner). It's important to note that potential weak points typically appear in inter-dental regions due to weak connections. However, they can exist in other locations in different dentitions. In one embodiment, the location of the inter-dental regions is determined by first determining the center of the tooth-receiving cavity of the aligner. A line between the centers of each pair of adjacent tooth-receiving cavities can then be calculated. For each pair of adjacent tooth-receiving cavities, the midpoint of the line drawn between the centers of the tooth-receiving cavities can be the midpoint of the inter-dental region connecting the two tooth-receiving cavities. The inter-dental region connecting two adjacent tooth-receiving cavities can include a region surrounding the midpoint of the line (e.g., from a first offset along a first direction from the midpoint along the line to a second offset along a second direction from the midpoint along the line).

[0191] At box 708, the processing logic can analyze potential weak points (e.g., adjacent regions) identified in the aligner. Analysis of potential weak points may include calculating the geometric values ​​(e.g., area moment of inertia) of the potential weak points and / or calculating stress based on one or more loads applied to the potential weak points. Analyzing potential weak points in the aligner may include performing the operations at boxes 710, 712, 714, 716, and 718.

[0192] At block 710, the processing logic can select potential weaknesses in the digital design of the aligner (e.g., neighboring regions), and can then proceed to the operations of blocks 712-718 to test the strength associated with the selected potential weaknesses. At block 710, each of the set of potential weaknesses can be selected, and the operations of blocks 712-718 can be repeated for each potential weakness. In some embodiments, the selected potential weaknesses can be neighboring regions of the aligner.

[0193] Figure 7BAn aligner 724 according to one embodiment is shown, which includes tooth receiving cavities and adjacent regions 730A-M between pairs of tooth receiving cavities. The position of each adjacent region 730A-M may have been determined as described above. For example, the center of the first tooth receiving cavity 726 and the center of the second tooth receiving cavity 728 may be determined. A line 732 may then be drawn between the center of the first tooth receiving cavity 726 and the center of the second tooth receiving cavity 728. The adjacent region 730D may then be determined to be near the midpoint of line 732. The positions of other adjacent regions may be determined similarly.

[0194] Return to Figure 7A At box 712, the processing logic determines one or more cross-sectional slices of the selected potential weak point. In one embodiment, one or more cross-sectional slices pass through the midpoint of the potential weak point (e.g., through the midpoint of an adjacent region). Additional cross-sectional slices can then be taken along the line at locations offset from the midpoint. In one embodiment, 5, 10, 15, or 20 cross-sectional slices are generated. Alternatively, other numbers of cross-sectional slices can be generated.

[0195] Each cross-sectional slice can define a plane comprising a first axis and a second axis. The first axis of each plane can be perpendicular to a line drawn between the centers of the tooth receptacles separated in the interproximal regions under discussion, and can also be perpendicular to the z-axis (where the z-axis is a vertical axis and / or an axis perpendicular to the occlusal surface defined by the aligner). The second axis of the plane defined by the cross-sectional slice can be the z-axis. Alternatively, the second axis of one or more planes defined by the cross-sectional slice can be at an angle to the z-axis. To determine the cross-sectional slice, processing logic can determine an additional line perpendicular to the line connecting the centers of the tooth receptacles and perpendicular to the z-axis. A plane can then be determined having a first axis defined by the additional line and a second axis parallel to or at an angle to the z-axis. The digital model of the aligner can then be sliced ​​by the planes to generate the cross-sectional slices.

[0196] Figure 7C A cross-sectional slice 740 cut from an aligner 734 according to one embodiment is shown. The cross-sectional slice 740 is cut at adjacent regions of the aligner 734 by cutting through the aligner at a plane 736 defined by a first axis 738 and a second axis 737.

[0197] Return to Figure 7AAt box 714, for each defined cross-sectional slice, one or more strength values ​​are calculated. Such values ​​may be based, for example, on stress, strain, strain energy, or one or more derived values ​​from stress, strain, and / or strain energy. In one embodiment, one or more area moments of inertia are calculated for each slice. For each axis of interest, the area moment of inertia of the aligner's cross-section is calculated separately. For example, the area moment of inertia of the cross-section may be determined with reference to a first axis (e.g., the x-axis or cheek axis) of the plane defined by the cross-sectional slice, a second axis (e.g., the z-axis or bite line axis) of the plane defined by the cross-sectional slice, a third axis perpendicular to the plane defined by the cross-sectional slice (e.g., the y-axis), and / or a line on the plane defined by the cross-sectional slice (e.g., a line defined by the equation x = z). The area moment of inertia of the aligner's cross-sectional slice relative to the axis can be calculated by the following formula:

[0198] Where I is the area moment of inertia, x is the perpendicular distance from the axis to the element dA, dA is the area of ​​the element, and R is an arbitrary shape.

[0199] For each area moment of inertia I, one or more stress values ​​σ can then be determined. The stress σ associated with the area moment of inertia can be calculated using the following formula:

[0200] Where d is the distance from a point on the aligner to the axis, and M is the torque or force applied at that point.

[0201] The maximum stress can be calculated for each area moment of inertia using the following formula. :

[0202] in, d max This is the maximum distance from any point on the aligner to the axis. In some embodiments, the material properties of the material used to manufacture the aligner can also be used in the calculation of stress and maximum stress.

[0203] Figure 7D An illustration of a surrounding according to one embodiment is shown. Figure 7C A bending load 742 is applied to the first axis 738 of the cross-sectional slice 740. As shown, the area moment of inertia of the cross-sectional slice 740 is calculated at the first axis 738. Then, the area moment of inertia is used at the first axis 738 to calculate the bending force or moment about the axis 738.

[0204] Figure 7E An illustration shows a surrounding (e.g., according to one embodiment) Figure 7CA bending load 744 is applied to the second axis 737 of the cross-sectional slice 740. As shown, the area moment of inertia of the cross-sectional slice 740 is calculated at the second axis 737. Then, the area moment of inertia is used at the second axis 737 to calculate the bending force or moment about the axis 737.

[0205] Figure 7F An illustration shows a perimeter perpendicular to one embodiment. Figure 7C A torsional load 746 is applied to the third axis 748 of the cross-sectional slice 740. As shown, the area moment of inertia of the cross-sectional slice 740 is calculated at the third axis 748. Then, the area moment of inertia is used at the third axis 748 to calculate the bending force or moment about the axis 748.

[0206] Return to Figure 7A At block 716, the processing logic calculates the minimum strength value of the potential weak point. In one embodiment, the minimum strength value is calculated based on the minimum area moment of inertia and / or the maximum stress calculated for the potential weak point. As described above, multiple cross-sectional slices are generated for the potential weak point, and multiple area moments of inertia are calculated for each cross-sectional slice. Additionally, a maximum stress value can be determined for each area moment of inertia. The minimum area moment of inertia and / or the maximum stress can be determined from multiple area moments of inertia and / or multiple stress values ​​calculated for the potential weak point. The minimum strength value can be or can be based on the minimum area moment of inertia and / or the maximum stress calculated for the potential weak point. In one embodiment, a minimum strength value and / or a maximum stress value is selected for each type of calculated area moment of inertia. Thus, if four different area moments of inertia are calculated, the minimum strength value can be based on a combination of four different minimum area moments of inertia (e.g., for four different axes) and / or a combination of four different maximum stresses (e.g., for four different axes).

[0207] At box 718, the processing logic can determine whether the minimum strength value of a potential weak point (e.g., an adjacent region) meets one or more damage criteria. Damage criteria may include a stress threshold and / or an area moment of inertia threshold. If the minimum area moment of inertia is lower than the area moment of inertia threshold and / or if the maximum stress is equal to or greater than the stress threshold, the damage criteria can be met. If the damage criteria are met, the processing logic can determine that the potential weak point is a possible damage point.

[0208] At box 720, the processing logic can determine the overall strength value of the entire aligner. The overall strength value can be a determined strength value based on each potential weak point being tested. In one embodiment, the strength value corresponds to the minimum strength value of the adjacent regions being tested.

[0209] At box 722, the processing logic can determine whether the strength value meets one or more damage criteria or standards. A damage criterion is met when the maximum stress value at any potential weak point exceeds a stress threshold, and / or when the minimum area moment of inertia at any potential weak point is below an area moment of inertia threshold.

[0210] If the aligner has an overall strength value that meets the damage criteria, it can be determined that the aligner includes one or more potential points of failure. In response to determining that the aligner includes one or more potential points of failure, the processing logic can select a manufacturing process for the aligner that includes one or more potential points of failure, for example, referring to... Figure 1B As described above. Alternatively, in response to determining that the aligner includes one or more potential points of damage, the processing logic may perform one or more corrective measures as described above to generate a modified digital model of the aligner. Some examples of modifying the digital model of the aligner include: modifying the tangent radius of the digital model of the aligner (e.g., in the interdental region for potential points of damage), modifying the thickness of a portion of the digital model of the aligner (e.g., in the interdental region for potential points of damage), modifying the geometry of the digital model of the aligner (e.g., in or around the interdental region for potential points of damage), and inserting an indicator in the digital model of the aligner, wherein the indicator indicates a recommended location for initiating removal of the aligner from the dental arch mold. In another example, the processing logic may generate a modified digital model of the dental arch by modifying one or more attachments on one or more teeth in the digital model of the dental arch, and may then generate a modified digital model of the aligner based on the modified digital model of the dental arch. In another example, the processing logic can generate a modified digital model of the dental arch by adding new virtual fillers to locations on the digital model of the dental arch or by expanding existing virtual fillers to locations on the digital model of the dental arch (which are associated with adjacent regions as potential points of damage), and then generate a modified digital model of the aligner based on the modified digital model of the dental arch.

[0211] The metrics used in method 700 can be used to directly predict the probability of aligner / retainer failure (as described above), or they can be used as features to train a machine learning model. For example, as discussed above, the area moment of inertia and / or strain values ​​determined for each neighboring region can be used as input to train a machine learning model to predict possible failure points. These metrics can be used in conjunction with or in lieu of the metrics discussed in the previous reference machine learning model training. For example, embeddings in the training dataset can each include a set of area moments of inertia and / or strain values ​​associated with one or more neighboring regions of the aligner, and may include labels indicating whether the aligner has experienced a failure point and / or indicating the location of the failure point (e.g., the specific neighboring region that was damaged).

[0212] Figure 7G A superposition 750 of three different aligners for a dental arch according to one embodiment is shown, wherein each aligner is associated with a different treatment stage of the dental arch. The first section 752 of the first aligner associated with the first treatment stage has a relatively wide base and a short peak. In contrast, the second section 754 of the second aligner associated with the thirteenth treatment stage has a narrower base and a higher peak. In a further comparison, the third section 756 of the third aligner associated with the twenty-sixth treatment stage has an even narrower base and an even higher peak. Analysis of the three different sections will yield the highest area moment of inertia and lowest stress of the first section 752, and the lowest area moment of inertia and highest stress of the third section 756. Therefore, in this example, the third aligner can be identified as including potential points of damage, while the first aligner can be identified as not including potential points of damage.

[0213] Several different loads are applied to an aligner during its lifespan. These loads include those caused by the single removal of the aligner from the mold used to form it, those caused by insertion into and removal from the patient's dental arch, those caused by chewing and / or grinding the patient's teeth while wearing the aligner, and those caused by handling and transport. For example, during the removal of the aligner from the mold, one or more points on the aligner may or may not experience some damage (e.g., permanent deformation or strain). During the intended use, the patient may need to insert and remove the aligner several times a day for a specific number of days, ranging from one day to three weeks. Similarly, although it is not recommended for patients to wear the aligner while eating, they may still do so. Furthermore, patients may grind their teeth while wearing the aligner. Each of the aforementioned loads can cause minor damage to the aligner, depending on its intensity and amount. The initiation and evolution of damage at points / areas can eventually lead to crack initiation and propagation, and ultimately, failure / breakage. To predict whether a particular aligner design is likely to break or to optimize the shape of the aligner to reduce the probability of damage and / or failure, the following can be performed: Figure 8A Method 800.

[0214] Figure 8AA flowchart of a method 800 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using numerical simulation according to one embodiment is shown, the numerical simulation simulating a series of loads on the aligner. One or more operations of method 800 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, special-purpose logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 800 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 800 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 800 includes... Figure 1A The operations performed during block 104. Method 800 can simulate sequential loading and any associated induced damage from the initial manufacturing of the aligner to its final use. This simulation allows the processing logic to predict the onset of damage, the evolution of damage, and / or failure / fracture.

[0215] At box 802, the processing logic can use numerical simulation to perform analysis on the digital design of the aligner. Numerical simulation can include finite element methods, finite difference methods, finite volume methods, meshless methods, smooth grain methods, combinations of these methods, etc.

[0216] At block 804, the processing logic may collect one or more material properties (also referred to as material property information) of the aligner. Material properties may include the amount or value of stress and / or strain that the material can withstand before breakage, cracking, deformation, warping, etc., such as elastic modulus, Poisson's ratio, yield strength, strain-stress curve, etc. In one embodiment, material properties include undamaged response curves and / or progressive damage curves associated with the material. In another embodiment, material properties may be included in the configuration of the aligner design analysis module 1450.

[0217] At box 806, the processing logic can collect a first geometry of the aligner from the digital design of the aligner. In an embodiment, this may include collecting the digital design of the aligner. The first geometry may be specific to each patient (and to each stage of treatment) and may be determined based on the patient's dental arch. The first geometry can be obtained by generating the digital design of the aligner by manipulating a digital model of the dental arch structure (e.g., a mold or the patient's dental arch). The digital model of the dental arch structure may represent the patient's dental arch. The digital model of the dental arch structure can be compensated to approximate the surface of the aligner and generate the digital design of the aligner. Thus, the digital design of the aligner may include a cavity (referred to as a tooth-receiving cavity or cap) configured to receive the patient's teeth and / or attachments on the teeth.

[0218] At box 808, the processing logic can collect a second geometry of the dental arch structure from a digital model of the arch structure (e.g., a mold). In an embodiment, this may include collecting a digital model of the dental arch structure. The digital model of the dental arch structure can be generated from information obtained by performing an intraoral scan of the patient during a consultation and / or from a treatment plan. For example, the patient's dental arch can be digitized via scan and modeled as a dental arch for fabricating a mold. The second geometry may include information related to the patient's dental arch, such as tooth size, tooth shape, tooth orientation, distance between teeth, attachments on teeth, upper dental arch, lower dental arch, etc. The dental arch structure may represent the upper or lower dental arch of a patient at the stage of treatment.

[0219] At box 808, the processing logic may additionally collect a third geometry of the opposing dental arch from a digital model of the opposing dental arch (e.g., a mold). In an embodiment, this may include collecting a digital model of the opposing dental arch. The digital model of the opposing dental arch may be generated from information obtained by performing an intraoral scan of the patient during a consultation and / or from a treatment plan. The third geometry may include information related to the patient's opposing dental arch, such as tooth size, tooth shape, tooth orientation, distance between teeth, attachments on teeth, upper dental arch, lower dental arch, etc. The opposing dental arch may represent the upper or lower dental arch of a patient at the stage of treatment.

[0220] At box 809, the processing logic can simulate progressive damage to the aligner to determine the total amount of damage to each of one or more regions of the aligner. The processing logic can simulate a series of one or more forces and / or displacements on the digital design of the aligner, which are associated with the removal of the aligner from a dental arch structure (e.g., a mold or the patient's dental arch), placement of the aligner on the dental arch structure, chewing, etc. Simulating one or more forces and / or displacements on the digital design of the aligner may include performing the operations at boxes 810, 812, 814, 816, and 818.

[0221] At box 810, the processing logic can simulate a load on the aligner. The simulated load can be any load previously discussed (e.g., reference...). Figure 3A-7G Additionally, any techniques and / or numerical simulations previously discussed can be used (e.g., refer to...). Figure 3A-7G The load is simulated by applying one or more loads (e.g., one or more forces and / or displacements) to a set of points on the digital design of the aligner. The simulated load can simulate the removal of an aligner with one or more material properties and a first geometry from a dental arch structure with a second geometry (e.g., as referenced). Figures 3A-3B , Figures 4A-4B , Figures 5A-5B or Figures 6A-6F (As discussed). In one embodiment, the simulated load simulation places the aligner on the dental arch structure. This simulation of the load can be performed, for example, using the reverse of forces applied to remove the aligner from the dental arch structure. In one embodiment, the simulated load simulates chewing forces on the aligner, which is referred to below. Figure 8C A more detailed discussion follows. In the embodiments, the applied load includes one or more forces or moments.

[0222] At box 812, the processing logic determines the amount of damage to each of one or more regions of the aligner. This may include determining the amount of damage to each region and / or point of the aligner. Damage to a region / point can be determined first as described above (e.g., referring to...). Figure 3A-6F The amount of strain at each region / point is determined to determine this. A point on the aligner may be able to withstand strain up to a threshold amount without damage or permanent deformation. However, strain at a point exceeding the threshold amount may cause damage to that point on the aligner. Therefore, the strain measured at a point / region of the aligner can be classified as elastic strain and plastic strain. Elastic strain can be temporary strain that decreases to zero after no force is applied to the aligner. Plastic strain can be permanent strain that may cause permanent deformation of the aligner. Any amount of plastic strain at a point / region of the aligner may cause a certain amount of damage to the aligner at that point / region. The amount of damage may be based on the magnitude of the plastic strain. In one embodiment, the value of the amount of damage is from 0 to 1, where 0 represents no damage and 1 represents fracture. A damage value of 0 can represent 0% damage, while a damage value of 1 can represent 100% damage.

[0223] At box 814, the processing logic can update the digital model of the aligner based on the amount of damage (e.g., plastic strain) at the corresponding points on the aligner. For each point / region on the aligner, the amount of damage can be recorded. This can be referred to as the initial damage value applied to that point. Ideally, most or all regions / points on the aligner will have zero damage. The digital model can be updated such that a subsequent simulation of another load on the aligner will be applied to a modified digital model of the aligner, where any damage that has occurred (e.g., plastic strain) has been accounted for in the initial conditions of the aligner, as included in the modified digital model of the aligner. Additionally, the digital model can be updated by adjusting the geometry of the digital model to account for plastic strain and reflect any permanent deformation of the aligner associated with plastic strain.

[0224] At block 816, the processing logic determines whether to simulate any additional loads on the aligner. If no additional loads on the aligner will be simulated, the method continues to block 818, and the processing logic stops simulating loads on the aligner. If another load on the aligner is to be simulated, the method returns to block 810, and another load on the aligner is simulated. In an embodiment, a series of many different loads can be simulated on the aligner. In each simulation, the amount of damage caused by the simulated loads can be used to update the digital model of the aligner. This can cause plastic strain to accumulate at certain points on the aligner, which may eventually cause those points on the aligner to crack or deform to a size that prevents the aligner from achieving its intended purpose. In one embodiment, a series of simulations of loads on the aligner includes: 1) Simulate the previous removal of the aligner from the mold used to form the dental arch; 2) Repeated simulations of removing the retractor from the patient's dental arch and inserting the retractor into the patient's dental arch (e.g., continuous simulations of retracting and inserting the retractor 10-200 times); and / or 3) Repeatedly simulate the chewing load on the alignment device.

[0225] The different simulation techniques described in this article can be used sequentially. For example, refer to... Figures 3A to 3B The described technique can be initially used to simulate the removal of the aligner from a dental arch mold, and references... Figures 4A to 4B or Figures 6A to 6F The described technique can then be used to simulate applying an aligner to and / or removing an aligner from a patient's dental arch.

[0226] At block 820, the processing logic determines whether at least one region / point of the aligner meets a damage criterion based on the total amount of damage to each of one or more regions. In one embodiment, the damage criterion is the total cumulative strain. In one embodiment, the damage criterion is 0 damage (e.g., any amount of damage at any point on the aligner causes the aligner to meet the damage criterion). In one embodiment, the damage criterion is 2% damage, 5% damage, 10% damage, 15% damage, or 20% damage. If the damage criterion is met, the processing logic may initiate one or more corrective actions and / or may select a specific manufacturing process associated with the aligner having potential damage points, as discussed in detail previously in this application.

[0227] In some embodiments, the operation of block 820 can be performed after each load on the aligner is simulated. If the aligner meets the failure criteria at any time, further simulation of the aligner may not be possible. This may enable the processing logic to track the failure evolution path of the aligner and determine when it is likely to fail during the aligner's lifespan, and which loads are most detrimental to the aligner.

[0228] Figure 8B A stress / strain curve 822 for an aligner according to one embodiment is shown. Stress (σ) can represent force, while strain (ε) can represent displacement. The stress / strain curve 822 can include an undamaged response curve 824 (between points A, B, D, and J) and a damaged response curve (also known as a progressive damage curve) 826 (between points D and F). As a force is applied to the points of the aligner, the stress increases and the strain also increases according to the undamaged response curve 824 until the strain reaches a quantity sufficient to cause damage initiation (marked as D on the stress / strain curve 822). Between points A and B, the strain increases linearly with increasing stress according to the material properties of the aligner at a rate associated with the elastic modulus or Young's modulus (E), which is also the slope of the strain-stress curve between points A and B. If the amount of strain is equal to or less than the strain at point B, the strain returns to point A (zero strain) after the load causing the strain is removed from the aligner. The region between point A and point B is called the plastic region, and any strain between point A and point B is elastic strain.

[0229] When the strain exceeds point B, the slope varies according to the undamaged response curve 824 until the strain reaches the initial damage value at point D. Any strain exceeding point B represents plastic strain. Therefore, the region between points B and D is the plastic region. If the strain is between points B and D (e.g., at point C), then when stress is no longer applied to the aligner, the strain is based on the elastic modulus or Young's modulus. (And the initial slope) decreases to non-zero strain. In the example shown, after the stress causes the strain to no longer reach point C, the strain decreases to point H, which represents the plastic strain or permanent deformation at the point of the aligner. If further stress is then applied, the strain increases from point H to point C, and then continues to increase along the undamaged response curve 824 as the strain increases to point D.

[0230] The portion of the undamaged response curve 824 between points D and J represents what the curve would look like if damage had not occurred. However, the aligner was damaged at point D, and its response follows the damaged response curve 826 between points D and F. Any strain after point D will cause changes in the material properties of the aligner material at the point of damage, including reduced elasticity at that point. This is reflected in a less steep slope in the strain-stress response.

[0231] In the example shown, strain is displayed as an increase up to point I. Once the load is removed and the stress decreases to zero, the strain decreases from point I to point G according to the new slope. The new slope can be calculated using the following equation:

[0232] Where S is the new slope of the strain-stress curve, d is the amount of damage (from 0 to 1), and E is the elastic modulus. This reflects the deterioration of the elasticity of the alignment material at the point of damage. If further stress is applied, the strain will increase from point G according to the new slope S until it reaches point I. Further increases in strain will cause the strain to continue following the damage response curve 826. If the strain has ever reached point F, the alignment will break or fracture at that point.

[0233] Figure 8C A flowchart of method 830, according to one embodiment, is shown, which uses numerical simulations associated with chewing and / or tooth grinding to perform analysis on a digital design of an aligner (e.g., a polymer aligner). One or more operations of method 830 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 830 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 830 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 830 includes... Figure 1A The operations performed during box 104.

[0234] At box 832, the processing logic can perform analysis on the digital design of the aligner using numerical simulations associated with chewing and / or tooth grinding. Numerical simulations can include finite element methods, finite difference methods, finite volume methods, meshless methods, smooth grain methods, combinations of these methods, etc.

[0235] At box 834, the processing logic may collect one or more material properties (also referred to as material property information) of the aligner. Material properties may include the amount or value of stress and / or strain that the material can withstand before breakage, cracking, deformation, warping, etc. An example of a material property is the Young's modulus of the material. In some embodiments, since the aligner will be made of the same material (e.g., a polymer), the material properties may not change between different digital designs of the aligner.

[0236] At box 836, the processing logic can collect a first geometry of the aligner from the digital design of the aligner. In an embodiment, this may include collecting the digital design of the aligner. The first geometry may be specific to each patient (and to each treatment stage) and may be determined based on the patient's dental arch. The first geometry can be obtained by generating the digital design of the aligner by manipulating a digital model of the dental arch-like structure (e.g., a mold or the patient's dental arch). The digital model of the dental arch-like structure may represent the patient's dental arch. The digital model of the dental arch-like structure can be compensated to approximate the surface of the aligner and generate the digital design of the aligner. Thus, the digital design of the aligner may include cavities (referred to as tooth-receiving cavities or covers) configured to accommodate the patient's teeth and / or attachments on the teeth.

[0237] At box 838, the processing logic can collect a second geometry of the dental arch structure from a digital model of the arch structure (e.g., a mold). In an embodiment, this may include collecting a digital model of the dental arch structure. The digital model of the dental arch structure can be generated from information obtained by performing an intraoral scan of the patient during a consultation and / or from a treatment plan. For example, the patient's dental arch can be digitized via scan and modeled as a dental arch for fabricating a mold. The second geometry may include information related to the patient's dental arch, such as tooth size, tooth shape, tooth orientation, distance between teeth, attachments on teeth, upper dental arch, lower dental arch, etc. The dental arch structure may represent the upper or lower dental arch of a patient at the stage of treatment.

[0238] At box 840, the processing logic may additionally collect a third geometry of the relative dental arch structure from a digital model of the relative dental arch structure (e.g., a mold). In an embodiment, this may include collecting a digital model of the relative dental arch structure. The digital model of the relative dental arch structure may be generated from information obtained by performing an intraoral scan of the patient during a consultation and / or from a treatment plan. The third geometry may include information related to the patient's relative dental arch, such as tooth size, tooth shape, tooth orientation, distance between teeth, attachments on teeth, upper dental arch, lower dental arch, etc. The relative dental arch structure may represent the upper or lower dental arch of a patient at the stage of treatment.

[0239] At box 842, the processing logic can apply boundary conditions associated with masticatory load (or molar load) to both the patient's upper and lower dental arches (e.g., to a second geometry of the digital model of the dental arch and a third geometry of the digital model of the opposing dental arch). In one embodiment, the boundary condition for the upper dental arch is a fixed location (e.g., zero displacement), while the boundary condition for the lower dental arch is applying a load (e.g., force) to one or more points on the lower dental arch. In another embodiment, the boundary condition for the lower dental arch is a fixed location (zero displacement), while the boundary condition for the upper dental arch is applying a load to one or more points on the upper dental arch. These applied boundary conditions can simulate the compression of the aligner between the upper and lower dental arches. In one embodiment, a force of approximately 0-2000 Newtons can be applied to one dental arch in the direction relative to the arch. Depending on the shape, size, height of the teeth, the patient's sex, age, etc., the compressive force and the resulting strain may be unevenly distributed among the various points of the aligner.

[0240] At box 844, the processing logic can measure the strain at various regions or points on the aligner. This strain can then be used to assess whether any point on the aligner is a potential point of damage.

[0241] Figure 9 A flowchart of a method 900 for implementing one or more correction measures on an aligner (e.g., a polymer aligner) based on the results of one or more loads on the aligner is shown. One or more operations of method 900 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 900 may be performed by executing… Figure 14 The alignment design analysis module 1450 is processed by the processing device. It should be noted that method 900 can be executed for each unique alignment in each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 900 includes... Figure 1A The operations performed during box 104.

[0242] At box 902, the processing logic may use any of the techniques described above to simulate the load on the aligner. For example, the processing logic may use a first digital model and a second digital model to simulate the removal of the polymer aligner from the dental arch structure (e.g., a mold or the patient's dental arch). The first digital model represents the patient's digital dental arch structure, and the second digital model represents the polymer aligner to be supported by the dental arch structure, specifying one or more physical shapes of the polymer aligner at one or more regions of the polymer aligner.

[0243] At box 904, the processing logic determines the probability that one or more values ​​at one or more regions will meet one or more damage criteria. This value may represent strain and / or stress, or any other quantity derived from those determined at one or more regions during simulated loading on the aligner (e.g., during simulated removal of the polymer aligner from the dental arch using a first digital model and a second digital model). A damage criterion may be met when one or more values ​​exceed a threshold. In one embodiment, the threshold may have been determined based on fracture data using a trained machine learning model. In one embodiment, the determination at box 904 may be based on the interaction between the dental arch structure and one or more physical properties of the polymer aligner, and this interaction is due to simulated removal.

[0244] At box 906, in response to analyzing the digital model of the aligner to obtain one or more possible physical damage points based on the probability that one or more values ​​meet one or more damage criteria, the processing logic may determine whether to apply one or more corrective measures to the aligner. If it is determined that one or more corrective measures should be applied, the processing logic may apply one or more corrective measures to the aligner.

[0245] Figure 10 A flowchart illustrates a method 1000 for performing analysis on a digital design of an aligner (e.g., a polymer aligner) using a rule engine according to one embodiment. One or more operations of method 1000 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 1000 may be performed by executing... Figure 14 The alignment design analysis module 1450 is used for processing. It should be noted that method 1000 can be executed for each unique alignment for each patient's treatment plan, or for each unique alignment under a key stage of the treatment plan. Furthermore, method 1000 includes... Figure 1A The operations performed during box 104.

[0246] The rule engine can use one or more rules determined based on observations, numerical simulation outputs, etc. For example, a customer might provide a report describing damage to an aligner during removal; a manufacturing technician might observe damage to an aligner during removal from a mold, and so on. Hundreds or thousands of observations of aligners damaged due to applied forces can be used to identify patterns or combinations of features included in the damaged aligner that could lead to breakage. Rules can be determined specifying potential damage points when such patterns or combinations of features are present in subsequent designs. Furthermore, numerical simulations can be performed and potential damage points can be identified as outputs. Outputs from hundreds or thousands of numerical simulations can be aggregated, and patterns or combinations of features associated with potential damage points can be identified. Rules can be determined specifying potential damage points when such patterns or combinations of features are present in subsequent designs.

[0247] At box 1002, the processing logic may perform analysis on the digital design of the aligner using a rule engine, which may include performing the operations at boxes 1004 and 1006. This rule engine includes one or more rules associated with parameters of the aligner that indicate points of damage. Rules may include a set of parameters (e.g., multiple features near a threshold) and / or rules associated with individual parameters. At box 1004, the processing logic may determine the parameters of the aligner based on the digital design of the polymer aligner. Parameters may include at least one of the following: the angle of the incision line at the aligner's location associated with the interproximal region of the patient's dental arch; the curvature of the aligner; the thickness of the aligner; the undercut height associated with attachments to teeth in the patient's dental arch; the presence of features in the aligner; the distance between features of the aligner associated with attachments to teeth in the patient's dental arch; the number of features of the aligner; and / or a combination of features of the aligner. Any one or more of these parameters may indicate potential points of damage in the digital design of the aligner, as determined based on historical patient feedback, a trained machine learning model, and / or running any of the numerical simulations described above. Rules may be created based on one or more parameters.

[0248] At box 1006, for each parameter in the parameters, the processing logic can perform the operations at boxes 1008 and 1010. Additionally, the processing logic can perform the operations at boxes 1008 and 1010 based on one or more combinations of parameters and / or based on all identified parameters. At box 1008, the processing logic can determine whether one or more rules indicate that a parameter (or set of parameters) meets a criterion. This criterion can relate to a parameter exceeding a threshold or the presence of certain features indicated by one or more parameters. For example, if an attachment is present on a tooth and another attachment is present on an adjacent tooth, a rule can indicate a possible point of damage between the two teeth. In another example, if the angle of the cleavage line is greater than a threshold angle, a rule can indicate a possible point of damage at the location of the cleavage line. Rules can also be associated with specific teeth. For example, different threshold angles for the cleavage line can be associated with adjacent regions between different pairs of teeth.

[0249] Therefore, at block 1010, in response to determining that the parameters meet one or more rule criteria, the processing logic can determine that the location of the digital design of the aligner associated with the parameters is a potential point of failure. One or more corrective actions can be performed in response to determining the presence of a potential point of failure. In some embodiments, the digital design of the aligner can be input into a trained machine learning model to verify potential points of failure, any of the numerical simulations described above can be performed on the digital design of the aligner, or both.

[0250] Figure 11 A flowchart of a method 1100 for outputting a filtered set of possible treatment plans is shown according to one embodiment. One or more operations of method 1100 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 1100 may be performed by an execution... Figure 14 The alignment design analysis module 1450 is processed by the processing unit.

[0251] At box 1102, the processing logic can determine a set of possible treatment plans, each including a set of digital designs of aligners (e.g., polymer aligners) within a set of treatment stages. The set of possible treatment plans may include dynamically generated plans based on intraoral scans of the patient's mouth provided by the physician, modified by the physician (e.g., the physician adding attachments to teeth at a specific stage), and so on.

[0252] At block 1104, for each digital design of an aligner in the set of digital designs of aligners for a set of possible treatment plans, the processing logic may perform the operations at blocks 1106 and 1108. At block 1106, the processing logic may perform analysis on the digital design of the aligner. This analysis may include using at least one of: a) a trained machine learning model; b) any one or more numerical simulations; or c) a rule engine. In some embodiments, the analysis may include using a rule engine to identify possible malfunctions, and then feeding the digital design of the aligner into a trained machine learning model and / or running any of the above numerical simulations on the digital design of the aligner to verify the possible malfunctions. In another embodiment, the digital design of the aligner may be fed into a trained machine learning model that may output the presence of possible malfunctions in the digital design of the aligner (and optionally, the location of the possible malfunctions), and numerical simulations may be performed on the digital design of the aligner to verify the presence and / or location of the possible malfunctions. In another embodiment, any one or more of the above numerical simulations can be performed on the digital design of the aligner to determine the presence of potential damage points, and the digital design of the aligner can be fed into a trained machine learning model to verify the potential damage points.

[0253] At box 1108, the processing logic can determine, based on analysis, whether the digital design of the aligner includes one or more potential points of failure.

[0254] At box 1110, the processing logic can filter out treatment plans associated with the digital design of one or more aligners with possible damage points from the set of possible treatment plans to create a filtered set of possible treatment plans.

[0255] At box 1112, the processing logic may output at least one possible treatment plan from a filtered set of possible treatment plans. The filtered set of possible treatment plans may not include a digital design of the aligner that includes potential damage points. In some embodiments, if a potential damage point cannot be addressed, the physician may be informed that one or more digital designs of the aligner include potential damage points, and may be advised to provide instructions on how to properly remove the aligner to reduce the chance of damage, instructions on how to move an attachment on a tooth to a later stage of the treatment plan, and so on.

[0256] Figure 12A flowchart illustrates a method 1200 for performing numerical simulations on a digital design of an aligner (e.g., a polymer aligner) to generate a rule engine, according to one embodiment. One or more operations of method 1200 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 1200 may be performed by executing... Figure 14 The alignment design analysis module 1450 is processed by the processing unit.

[0257] At box 1202, the processing logic may perform analysis multiple times on the set of digital designs of the aligner using any of the numerical simulations described above to determine patterns or combinations of features or parameters of the aligner associated with one or more possible points of failure. Patterns or combinations of features or parameters may include overcrowded attachments, overcrowded teeth, cutting line angles exceeding thresholds, aligner thickness being too thin, etc.

[0258] At box 1204, the processing logic can use patterns or combinations of features or parameters to generate a rule engine to create one or more rules obtained from performing analysis on a set of digital designs of the aligner multiple times using numerical simulations. In some embodiments, once the rule engine is generated, the digital design of the aligner can be processed by the rule engine before any numerical simulations are performed or fed into a trained machine learning model. If the rule engine indicates that the digital design of the aligner includes potential defects, further analysis can be performed on the digital design of the aligner, performing numerical simulations and / or feeding the digital design of the aligner into a trained machine learning model.

[0259] Figure 13 A flowchart of method 1300 according to one embodiment is shown. Method 1300 uses a rule engine and / or a trained machine learning model on the digital design of an aligner (e.g., a polymer aligner) to identify potential defects, and then performs a numerical simulation of the digital design of the aligner. One or more operations of method 1300 are performed by processing logic of a computing device. The processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations of method 1300 may be performed by executing… Figure 14 The alignment design analysis module 1450 is processed by the processing unit.

[0260] At box 1302, the processing logic can perform analysis on the digital design of the aligner using a rule engine that includes one or more rules associated with parameters of the aligner indicating potential damage points. The rule engine can indicate the presence of possible damage points included in the digital design of the aligner based on the parameters of the aligner's digital design.

[0261] At box 1303, the processing logic may determine whether one or more potential defects are detected using a rule engine and / or a trained machine learning model. If no one or more potential defects are detected in the aligner, method 1300 may terminate. If one or more potential defects are detected in the aligner, at box 1304, the processing logic may perform an analysis of the digital design of the aligner using numerical simulation to confirm the presence of one or more potential defects included in the aligner.

[0262] At box 1305, the processing logic can determine whether one or more possible points exist, as confirmed by numerical simulation. If not, method 1300 can terminate. If the processing logic confirms the existence of one or more possible damage points using numerical simulation, at box 1306, the processing logic can perform one or more corrective actions based on the one or more possible damage points.

[0263] Figure 14 A graphical representation of a machine in the example form of a computing device 1400 is shown, in which a set of instructions causes the machine to perform any or more methods discussed herein (e.g., the methods of Figures 1-13). In some embodiments, the machine may be part of or communicatively coupled to a design site. In alternative embodiments, the machine may be connected (e.g., networked) to other machines in a local area network (LAN), intranet, extranet, or the Internet. For example, the machine may be networked to a design site and / or a rapid prototyping device, such as a 3D printer or SLA device. The machine may operate as a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), cellular phone, network device, server, network router, switch, or bridge, or any machine capable of executing a set of instructions (sequentially or otherwise) specifying the actions to be taken by the machine. Furthermore, although only a single machine is shown, the term "machine" should also be considered as any collection of machines (e.g., computers) that individually or jointly execute a set (or more) of instructions to perform any one or more methods discussed herein.

[0264] Example computing device 1400 (also referred to as computing device) includes processing device 1402, main memory 1404 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), static memory 1406 (e.g., flash memory, static random access memory (SRAM), etc.) and auxiliary memory (e.g., data storage device 1428), which communicate with each other via bus 1408.

[0265] Processing device 1402 represents one or more general-purpose processors such as microprocessors, central processing units, etc. More specifically, processing device 1402 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 1402 may also be one or more special-purpose processing devices, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, etc. Processing device 1402 is configured to execute processing logic (instructions 1426) for performing the operations and steps discussed herein.

[0266] The computing device 1400 may also include a network interface device 1422 for communicating with the network 1464. The computing device 1400 may also include a video display unit 1410 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 1412 (e.g., a keyboard), a cursor control device 1414 (e.g., a mouse), and a signal generation device 1420 (e.g., a speaker).

[0267] Data storage device 1428 may include machine-readable storage medium (or more specifically, non-transitory computer-readable storage medium) 1424 thereon storing one or more sets of instructions 1426 embodying any one or more methods or functions described herein. Non-transitory storage medium refers to storage medium other than a carrier wave. During execution of instructions 1426 by computer device 1400, instructions 1426 may also reside wholly or at least partially in main memory 1404 and / or processing device 1402, which also constitute computer-readable storage media.

[0268] The computer-readable storage medium 1424 may also be used to store one or more digital models (also referred to as electronic models) of an aligner and / or dental arch and / or an aligner design analysis module 1450, which can perform one or more operations of the methods described herein. The computer-readable storage medium 1424 may also store a software library containing methods for invoking the aligner design analysis module 1450. Although the computer-readable storage medium 1424 is shown as a single medium in the example embodiment, the term "computer-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) storing one or more sets of instructions. The term "computer-readable storage medium" should also be considered to include any medium capable of storing or encoding a set of instructions for machine execution and causing the machine to perform any one or more methods of this disclosure. Therefore, the term "computer-readable storage medium" should be considered to include, but is not limited to, solid-state memory, as well as optical and magnetic media.

[0269] Figure 15AAn exemplary tooth repositioning appliance or aligner 1500 is shown, which can be worn by a patient to achieve stepwise repositioning of individual teeth 1502 in the jaw. The appliance may include a housing (e.g., a continuous polymer housing or a segmented housing) having a tooth-receiving cavity that accommodates and resiliently repositions the teeth. The appliance or portions thereof may be fabricated indirectly using a physical model of a tooth. For example, an appliance (e.g., a polymer appliance) may be formed using a physical model of a tooth and sheets of polymer material of a suitable number of layers. As used herein, “polymer material” may include any material formed of a polymer. As used herein, “polymer” may refer to a molecule composed of repeating structural units linked by covalent chemical bonds, typically characterized by a substantial 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, and 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). Polymers are typically polymers of one or more monomer precursors. The term polymer includes homopolymers, or polymers consisting essentially of a single repeating monomer subunit. The term polymer also includes copolymers formed when two or more different types of monomers are linked in the same polymer. Useful polymers include organic or inorganic polymers that can be in an amorphous, semi-amorphous, crystalline, or semi-crystalline state. Polymers can include polyolefins, polyesters, polyacrylates, polymethacrylates, polystyrene, polypropylene, polyethylene, polyethylene terephthalate, polylactic acid, polyurethane, epoxy polymers, polyethers, poly(vinyl chloride), polysiloxanes, polycarbonates, polyamides, polyacrylonitrile, polybutadiene, poly(cycloolefins), and copolymers. The systems and / or methods provided herein are compatible with a range of plastics and / or polymers. Therefore, this list is not entirely inclusive but exemplary. Plastics can be thermosetting or thermoplastic. The plastic can be thermoplastic.

[0270] Examples of materials applicable to the embodiments disclosed herein include, but are not limited to, those described in the following published and provisional patent applications filed by Align Technology: “MULTIMATERIAL ALIGNERS”, U.S. Publication No. 2017 / 0007361, published January 12, 2017; “DIRECT FABRICATION OF ALIGNERS WITH INTERPROXIMAL FORCE COUPLING”, U.S. Publication No. 2017 / 0007365, published January 12, 2017; and “DIRECT FABRICATION OF ORTHODONTIC APPLIANCES WITH VARIABLE”, U.S. Publication No. 2017 / 0007359, published January 12, 2017. PROPERTIES (Direct fabrication of dental alignment instruments with variable properties); U.S. Publication No. 2017 / 0007366, published on January 12, 2017, entitled "DIRECT FABRICATION OF ALIGNERSFOR ARCH EXPANSION"; U.S. Publication No. 2017 / 0007368, published on January 12, 2017, entitled "DIRECT FABRICATION OF ATTACHMENT TEMPLATES WITH ADHESIVE"; U.S. Publication No. 2017 / 0007367, published on January 12, 2017, entitled "DIRECT FABRICATION OF ALIGNERS FOR PALATE EXPANSION AND OTHER". APPLICATIONS (Direct fabrication of aligners and other instruments for palatal expansion); U.S. Publication No. 2017 / 0007360, published January 12, 2017, entitled "SYSTEMS, APPARATUSES AND METHODS FOR DENTAL APPLIANCES WITH INTEGRALLY FORMED FEATURES"; U.S. Publication No. 2017 / 0007363, published January 12, 2017, entitled "DIRECT FABRICATION OF POWER ARMS";U.S. Publication No. 2017 / 0007386, published January 12, 2017, entitled "Systems, Apparatuses and Methods for Substance Delivery from Dental Appliance"; U.S. Publication No. 2017 / 0008333, published January 12, 2017, entitled "Dental Appliance Having Ornamental Design"; U.S. Publication No. 2017 / 0007362, published January 12, 2017, entitled "Dental Materials Using Thermoset Polymers"; and U.S. Provisional Application No. 62 / 667,354, filed May 4, 2018, entitled "Curable Composition for Use in a High Temperature." "LITHOGRAPHY-BASED PHOTOPOLYMERIZATION PROCESS AND METHOD OF PRODUCING CROSSLINKEDPOLYMERS THEREFROM"; U.S. Provisional Application Serial No. 62 / 667,364, filed May 4, 2018, "POL YMERIZABLE MONOMERRS AND METHOD OF POLYMERIZING THE SAME"; and any conversion applications (including publications and granted patents), including any divisional, continuation, or partial continuation thereof.

[0271] Although polymer aligners are discussed herein, the disclosed techniques can also be applied to aligners made of different materials. Some embodiments are discussed herein with reference to orthodontic aligners (also simply aligners). However, the embodiments are also extended to other types of housings formed on a mold, such as orthodontic retainers, orthodontic splints, oral insertion sleep appliances (e.g., for minimizing snoring, sleep apnea, etc.) and / or housings for non-dental applications. Therefore, it should be understood that the embodiments relating to aligners herein are also applicable to other types of housings. For example, the principles, features, and methods discussed can be applied to any application or process in which image-based quality control is useful for any suitable type of housing, whether it is a suitably shaped device (such as an eyeglass frame, contact lens or glass lens, hearing aid or plug, artificial knee, prosthesis and device, orthodontic insert) or protective device (such as knee braces, mobile cups, or elbow, chin, and calf braces, and other similar motion / protective devices).

[0272] The aligner 1500 can be adapted to all or fewer teeth present in the maxilla or mandible. The appliance can be specifically designed to accommodate the patient's teeth (e.g., the morphology of the tooth-accommodating cavity matches the morphology of the patient's teeth) and can be manufactured based on a positive or negative model of the patient's teeth generated by molding, scanning, etc. Optionally, the appliance can be a general-purpose appliance configured to accommodate teeth, but not necessarily shaped to match the morphology of the patient's teeth. In some cases, only certain teeth accommodated by the appliance can be repositioned by the appliance, while other teeth can provide a base or anchor area to hold the appliance in place when the appliance applies force to one or more teeth targeted for repositioning. In some cases, at certain points during treatment, some, most, or even all of the teeth may need to be repositioned. The moved teeth can also serve as a base or anchor point to hold the appliance in place while the patient wears it. Typically, no wires or other devices will be provided for holding the appliance in place above the teeth. However, in some cases, it may be necessary or required to provide a corresponding receptacle or hole 1506 in the aligner 1500 for a separate attachment or other anchoring element 1504 on the tooth 1502, so that the appliance can apply selected forces on the tooth. Example appliances (including those used in the Invisalign® system) have been described in numerous patents and patent applications of Align Technology, including, for example, U.S. Patent Nos. 6,450,807 and 5,975,893, and on the company’s website, which is accessible on the Internet (see, for example, the URL “invisalign.com”). Examples of dental attachments suitable for use with orthodontic appliances are also described in Align Technology’s patents and patent applications, including, for example, U.S. Patent Nos. 6,309,215 and 6,830,450.

[0273] Figure 15BA tooth repositioning system 1510 is illustrated, comprising multiple appliances 1512, 1514, and 1516. Any appliance described herein may be designed and / or provided as part of a set of multiple appliances for use in a tooth repositioning system. Each appliance may be configured such that the tooth receiving cavity has a geometry corresponding to an intermediate or final tooth arrangement intended for use with the appliance. By placing a series of progressively positional adjustment appliances on the patient's teeth, the patient's teeth can be progressively repositioned from an initial tooth arrangement to a target tooth arrangement. For example, the tooth repositioning system 1510 may include a first appliance 1512 corresponding to the initial tooth arrangement, one or more intermediate appliances 1514 corresponding to one or more intermediate arrangements, and a final appliance 1516 corresponding to the target arrangement. The target tooth arrangement may be the planned final tooth arrangement selected for the patient's teeth at the end of all planned orthodontic treatment. Alternatively, the target alignment can be one of several intermediate alignments of the patient's teeth during orthodontic treatment, which may include a variety of different treatment options, including but not limited to: recommendations for surgery, suitability for interproximal enamel reduction (IPR), scheduling of progress checks, optimal anchoring positions, desired maxillary expansion, and involvement of restorative dentistry (e.g., inlays, onlays, crowns, bridges, implants, veneers, etc.). Thus, it can be understood that the target tooth alignment can be the result of any planned alignment of the patient's teeth following one or more progressive repositioning phases. Similarly, the initial tooth alignment can be any initial alignment of the patient's teeth followed by one or more progressive repositioning phases.

[0274] In some embodiments, appliances 1512, 1514, 1516, or a portion thereof, may be manufactured using indirect manufacturing techniques, such as thermoforming on a male or female mold. Indirect manufacturing of orthodontic appliances may involve: manufacturing a male or female mold of a patient's dentition in a targeted arrangement (e.g., through rapid prototyping, milling, etc.), and thermoforming one or more sheets on a mold to produce an appliance housing.

[0275] In an example of indirect manufacturing, a mold for the patient's dental arch can be manufactured from a digital model of the dental arch, and the shell can be formed on the mold (e.g., by thermoforming a polymer sheet on the mold of the dental arch and then trimming the thermoformed polymer sheet). Mold manufacturing can be performed using a rapid prototyping machine (e.g., a stereolithography (SLA) 3D printer). This can be achieved using a computing device (e.g., Figure 14After the processing logic of the computing device processes the digital models of instruments 1512, 1514, and 1516, the rapid prototyping machine can receive the digital model of the dental arch mold and / or the digital models of instruments 1512, 1514, and 1516. The processing logic may include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed by the processing device), firmware, or a combination thereof. For example, one or more operations may be performed by the processing device executing the instrument design analysis program or module 1450.

[0276] To create a mold, the shape of the patient's dental arch during the treatment phase is determined based on the treatment plan. In an orthodontic example, a treatment plan can be generated based on an intraoral scan of the dental arch to be modeled. An intraoral scan of the patient's dental arch can be performed to generate a three-dimensional (3D) virtual model (mold) of the patient's dental arch. For example, a full scan of the patient's mandibular and / or maxillary arch can be performed to generate its 3D virtual model. 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, virtual 3D models can also be generated based on scans of the object to be modeled or based on the use of computer-aided drawing techniques (e.g., for designing virtual 3D molds). Alternatively, an initial negative mold (e.g., dental impressions, etc.) 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.

[0277] 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 phases to advance the teeth from their initial position and orientation to their target final position and orientation. By calculating the progression of tooth movement throughout the entire 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 phase, a separate virtual 3D model of the patient's dental arch can be generated for that phase. The shape of each virtual 3D model will differ. The original virtual 3D model, the final virtual 3D model, and each intermediate virtual 3D model are unique and customized for the patient.

[0278] Therefore, multiple distinct virtual 3D models (digital designs) of the dental arch can be generated for a single patient. The first virtual 3D model can be a unique model of the patient's currently presented dental arch and / or teeth, and the final virtual 3D model can be a model of the patient's dental arch and / or teeth after orthodontic treatment of one or more teeth and / or jaws. Multiple intermediate virtual 3D models can be modeled, each progressively different from the previous virtual 3D models.

[0279] Each virtual 3D model of a patient's dental arch can be used to generate a unique, customized physical mold of the arch for a specific treatment phase. The shape of the mold can be at least partially based on the shape of the virtual 3D model for that treatment phase. The virtual 3D model can be represented in a file such as a computer-aided drafting (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, laboratory, manufacturing plant, or other entity). The virtual 3D model may include instructions that control a manufacturing system or apparatus to produce a mold with the specified geometry.

[0280] Clinicians' offices, laboratories, manufacturing plants, or other entities can receive virtual 3D models of a mold (i.e., digital models already created as described above). The entity can then 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 machine is a 3D printer. 3D printing encompasses any layer-based additive manufacturing process. 3D printing can be achieved using additive processes, where continuous layers of material are formed in a prescribed 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.

[0281] In some cases, stereolithography (SLA) (also known as optical fabrication solid imaging) is used to create SLA molds. In SLA, a mold is created by sequentially printing thin layers of a photocurable material (e.g., a polymeric resin) onto one mold layer at a time. A platform is placed in a bath of liquid photopolymer or resin, just below the surface of the bath. A light source (e.g., an ultraviolet laser) tracks a pattern on the platform, curing the photopolymer as the light source points to it, forming the first layer of the mold. The platform is gradually lowered, and the light source tracks a new pattern on the platform to form another layer of the mold with each descent. This process is repeated until the mold is completely fabricated. Once all the layers of the mold have been formed, the mold can be cleaned and cured.

[0282] Materials such as polyesters, copolyesters, polycarbonates, polycarbonates, thermopolymerized polyurethanes, polypropylene, polyethylene, polypropylene and polyethylene copolymers, acrylic acid, cyclic block copolymers, polyetheretherketones, polyamides, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, polypropylene terephthalate, styrene block copolymers (SBCs), silicone rubber, elastomer alloys, thermopolymerized elastomers (TPEs), thermopolymerized vulcanized rubber (TPV) elastomers, polyurethane elastomers, block copolymer elastomers, polyolefin blend elastomers, thermopolymerized copolyester elastomers, thermopolymerized polyamide elastomers, or combinations thereof, can be used to directly form molds. Materials used to manufacture molds can be provided in uncured form (e.g., as liquids, resins, powders, etc.) and can be cured (e.g., by photopolymerization, light curing, gas curing, laser curing, crosslinking, etc.). The properties of the material before curing may differ from the properties of the material after curing.

[0283] The appliances can be formed from each mold and, when applied to a patient's teeth, can provide force to move the patient's teeth as specified in the treatment plan. Each appliance is uniquely shaped and tailored to the specific patient and stage of treatment. In the examples, appliances 1515, 1514, and 1516 can be pressure-formed or thermoformed on a mold. Each mold can be used to manufacture the appliance that will apply force to the patient's teeth at a specific stage of orthodontic treatment. Each appliance 1515, 1514, and 1516 has a tooth-receiving cavity that accommodates the tooth and resiliently repositions the tooth according to the specific stage of treatment.

[0284] In one embodiment, a sheet of material is pressed or thermoformed on a mold. This sheet can be, for example, a polymer sheet (e.g., an elastic thermopolymer, a polymer material sheet, etc.). To thermoform the shell on the mold, the sheet can be heated to a temperature at which it becomes pliable. Pressure can be applied simultaneously to the sheet to form the now-pliable sheet around the mold. Once cooled, the sheet will have a shape conforming to the mold. In one embodiment, a release agent (e.g., a non-stick material) is applied to the mold prior to shell formation. This facilitates subsequent removal of the mold from the shell. Force can be applied to lift the appliance from the mold. In some cases, the removal force may cause cracking, warping, or deformation. Therefore, the embodiments disclosed herein can identify potential points of damage in the digital design of the appliance prior to manufacturing and can perform corrective measures.

[0285] Additional information can be added to the device. This additional information can be any information relating to the device. Examples of such additional information include part number identifiers, patient names, patient identifiers, case numbers, sequence identifiers (e.g., indicating which device in a treatment sequence a specific liner belongs to), manufacturing dates, clinician names, logos, etc. For example, after determining that a potential point of failure exists in the digital design of the device, an indicator can be inserted into the device's digital design. In some embodiments, the indicator may indicate a recommended location for initiating the removal of the polymer device to prevent the formation of a point of failure during removal.

[0286] In some embodiments, a library of removal methods / patterns can be established and referenced when simulating the removal of the aligner in a numerical simulation. Different patients or manufacturing technicians may prefer to remove the aligner in different ways, and there may be some typical patterns. For example: 1) Some patients first lift from the posterior lingual side (left then right, or vice versa) and then move around the dental arch from the left / right posterior to the right / left posterior; 2) Similar to #1, but some other patients lift only one posterior side and then move around the dental arch; 3) Similar to #1, but some patients lift from the buccal side instead of the posterior lingual side; 4) Some patients lift from the anterior incisors and pull forcefully to remove the aligner; 5) Some other patients grasp the lingual and buccal sides of the posterior position and pull out both sides simultaneously; 6) Some other patients grasp random teeth in the middle. The library may also include removal guidelines provided by the aligner manufacturer. The removal method may also depend on the presence of attachments on the teeth, as some of the methods described above may lead to a more comfortable removal approach. Based on the attachments on each tooth, it is possible to determine how the aligner can be removed for each patient, and to adjust the removal process for that patient in that specific simulation.

[0287] After an appliance is formed on a mold for a specific treatment phase, it is then trimmed along a cutting line (also called a trimming line) and removed from the mold. The processing logic determines the cutting line of the appliance. The cutting line can be determined based on a virtual 3D model of the dental arch at the specific treatment phase, a virtual 3D model of the appliance to be formed on the dental arch, or a combination of virtual 3D models of the dental arch and the appliance. The location and shape of the cutting line are important for the appliance's function (e.g., its ability to apply desired forces to the patient's teeth) and its fit and comfort. For housings such as orthodontic appliances, orthodontic retainers, and orthodontic splints, the trimming of the housing plays a significant role in the housing's effectiveness for its intended purpose (e.g., aligning, retaining, or positioning one or more of the patient's teeth) and its fit on the patient's dental arch. For example, if the housing is trimmed too much, it may lose rigidity and its ability to apply forces to the patient's teeth may be impaired. If the housing is over-trimmed, it may become thinner in that location and could become a point of damage when the patient removes the housing from their teeth or from the mold. In some embodiments, as one of the corrective measures taken when a potential point of damage is identified in the digital design of the appliance, the cut lines may be modified in the digital design of the appliance.

[0288] On the other hand, if the housing is under-trimmed, some parts of the housing may impact the patient's gums and cause discomfort, swelling, and / or other dental problems. Additionally, if the housing is under-trimmed in one location, the housing may be too rigid at that location. In some embodiments, the cutting line can be a straight line passing through the instrument at, below, or above the gingival line. In some embodiments, the cutting line can be a gingival cutting line, which represents the interface between the instrument and the patient's gums. In such embodiments, the cutting line controls the distance between the edge of the instrument and the patient's gingival line or gingival surface.

[0289] In this embodiment, virtual filler can be used to reduce the likelihood of potential damage points occurring. When a potential damage point is identified, virtual filler can be added to the area associated with the potential damage point, or existing virtual filler in that area can be expanded. For example, virtual filler in adjacent areas can be added or expanded.

[0290] Each patient has a unique dental arch with unique gingiva. Therefore, the shape and position of the incision line can be unique and customized for each patient and each stage of treatment. For example, the incision line is customized to run along the gingival line (also known as the gum line). In some embodiments, the incision line may be off the gingival line in some areas and on the gingival line in others. For example, in some cases, it may be desirable for the incision line to be off the gingival line (e.g., not touching the gum), where, in the interproximal region between teeth, the shell will touch the teeth and be on the gingival line (e.g., touching the gum). Therefore, it is important to trim the shell along the predetermined incision line.

[0291] In some embodiments, orthodontic appliances (or portions thereof) described herein may be manufactured using direct manufacturing techniques, such as additive manufacturing (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 physical templates (e.g., molds, masks, etc.) to define the object's geometry. Additive manufacturing technologies can be categorized as follows: (1) vat photopolymerization (e.g., stereolithography), in which objects are constructed layer by layer from a vat of liquid photopolymer resin; (2) material spraying, in which materials are sprayed onto a build platform using a continuous or drop-on-demand (DOD) method; (3) binder spraying, in which alternating layers of build material (e.g., powder-based materials) and binder material (e.g., liquid binder) are deposited through a printhead; (4) fused deposition modeling (FDM), in which materials are extracted 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 thermal sintering (SHS), selective laser melting (SLM), and selective laser sintering (SLS); (6) sheet lamination, including but not limited to layered solid fabrication (LOM) and ultrasonic additive manufacturing (UAM); and (7) directional energy deposition, including but not limited to laser engineered mesh forming, directional light fabrication, direct metal deposition, and 3D laser cladding. For example, stereolithography can be used to directly manufacture one or more of appliances 1515, 1514, and 1516. 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, an object geometry can be built up layer by layer. As another example, appliances 1512, 1514, and 1516 can be directly manufactured using selective laser sintering. In some embodiments, selective laser sintering involves selectively melting and fusing layers of powder material using a laser beam according to a desired cross-sectional shape to build up the object geometry. As yet another example, appliances 1512, 1514, and 1516 are directly manufactured by fused deposition modeling. In some embodiments, fused deposition modeling involves melting and selectively depositing filaments of a thermoplastic polymer layer by layer to form an object. In yet another example, material spraying can be used to directly manufacture appliances 1512, 1514, and 1516. In some embodiments, material spraying involves spraying or extruding one or more materials onto a construction surface to form a continuous layer of the object geometry.

[0292] In some embodiments, the direct manufacturing methods provided herein build the geometry of an object layer by layer, wherein successive layers are formed in discrete build-up steps. Alternatively or in combination, direct manufacturing methods that allow for the continuous building up of the object's geometry may 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-phase printing" is used to manufacture appliances 1512, 1514, and 1516, wherein the object is continuously built from a reservoir of photopolymerizable resin by forming a gradient of partially cured resin between the object's build surface and a "dead zone" that inhibits polymerization. In some embodiments, a semi-permeable membrane is used to control the delivery of photopolymerization inhibitors (e.g., oxygen) into the dead zone to form a polymerization gradient. Continuous liquid-phase printing can achieve manufacturing speeds approximately 25 to approximately 100 times faster than other direct manufacturing methods, and approximately 1000 times faster by incorporating a cooling system. Continuous liquid phase printing is described in the following documents: U.S. Patents with publication numbers 2015 / 0097315, 2015 / 0097316 and 2015 / 0102532, the contents of each of which are incorporated herein by reference in their entirety.

[0293] As another example, by constructing a platform that moves continuously during the irradiation phase (e.g., along the vertical or Z-direction), thereby controlling the curing depth of the irradiated photopolymer with the speed of movement, a continuous direct manufacturing method can achieve the continuous construction of the object's geometry. Thus, continuous polymerization of the material on the construction 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.

[0294] In another example, a continuous direct manufacturing method may involve extruding a composite material consisting of a curable liquid material surrounding a solid strand. The composite material can 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 entire disclosure of which is incorporated herein by reference.

[0295] In yet another example, the continuous direct manufacturing method utilizes heliolithography, in which a liquid photopolymer is cured using focused radiation while the build platform is continuously rotated and raised. Thus, the geometry of an object can be continuously built along a helical 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.

[0296] The direct manufacturing method described herein is compatible with a wide range of materials, including but not limited to one or more of the following: polyesters, copolyesters, polycarbonates, thermoplastic polyurethanes, polypropylene, polyethylene, copolymers of polypropylene and polyethylene, acrylic acid, cyclic block copolymers, polyetheretherketones, polyamides, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, polypropylene terephthalate, styrene block copolymers (SBCs), silicone rubber, elastomer alloys, thermoplastic elastomers (TPEs), thermoplastic vulcanizate (TPV) elastomers, polyurethane elastomers, block copolymer elastomers, polyolefin blend elastomers, thermoplastic copolyester elastomers, thermoplastic polyamide elastomers, thermosetting materials, or combinations thereof. Materials used for direct manufacturing may be provided in uncured form (e.g., as liquids, resins, powders, etc.) and may be cured (e.g., by photopolymerization, photocuring, gas curing, laser curing, crosslinking, etc.) to form orthodontic appliances or portions thereof. The properties of the material before curing may differ from those after curing. Once cured, the materials described in this article exhibit sufficient strength, stiffness, durability, and biocompatibility for use in orthodontic appliances. The properties of the cured material can be selected based on the required properties of the corresponding part of the appliance.

[0297] In some embodiments, the relatively rigid portions of the 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 acid, cyclic block copolymers, polyetheretherketone, polyamide, polyethylene terephthalate, polybutylene terephthalate, polyetherimide, polyethersulfone, and / or polypropylene terephthalate.

[0298] In some embodiments, the relatively elastic portion of the orthodontic appliance may be formed by direct manufacturing using one or more of the following materials: styrene block copolymer (SBC), silicone rubber, elastomer alloy, thermoplastic elastomer (TPE), thermoplastic vulcanized rubber (TPV) elastomer, polyurethane elastomer, block copolymer elastomer, polyolefin blend elastomer, thermoplastic copolyester elastomer, and / or thermoplastic polyamide elastomer.

[0299] Machine parameters can include curing parameters. For digital light processing (DLP) based curing systems, curing parameters can include power, curing time, and / or the grayscale of the entire image. For laser-based curing systems, curing parameters can include power, speed, beam size, beam shape, and / or beam power distribution. For printing systems, curing parameters can include material droplet size, viscosity, and / or curing power. These machine parameters (e.g., certain parameters per 1-x layers and certain parameters after each build) can be periodically monitored and adjusted as part of process control on the manufacturing machine. Process control can 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 via feedback loops. For DLP machines, depending on system stability, grayscale, etc., can be measured and calibrated before, during, and / or at the end of each build and / or at predetermined time intervals (e.g., every n builds, once per hour, once per day, once per week, etc.). Additionally, material properties and / or optical properties can be provided to the manufacturing machine, and the machine process control module can use these parameters to adjust machine parameters (e.g., power, time, grayscale, etc.) to compensate for variations in material properties. By implementing process control on manufacturing machines, variations in tool precision and residual stress can be reduced.

[0300] Optionally, the direct manufacturing method described herein allows for the manufacture of appliances comprising multiple materials, referred to herein as "multimaterial direct manufacturing." In some embodiments, the multimaterial direct manufacturing method involves simultaneously forming an object from multiple materials in a single manufacturing step. For example, a multi-tip extrusion apparatus can be used to selectively dispense multiple types of materials from different material supply sources 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 multimaterial direct manufacturing method may involve forming an object from multiple materials in multiple sequential manufacturing steps. For example, a first portion of the object may be formed from a first material according to any direct manufacturing method herein, then a second portion of the object may be formed from a second material according to a method herein, and so on, until the entire object has been formed.

[0301] Direct manufacturing offers various advantages compared to other manufacturing methods. For example, compared to indirect manufacturing, direct manufacturing allows for the production of orthodontic appliances without the use of any molds or templates to shape the appliance, thereby reducing the number of manufacturing steps involved and improving the resolution and accuracy of the final appliance geometry. Additionally, direct manufacturing allows for precise control over the three-dimensional geometry of the appliance, such as its thickness. Complex structures and / or auxiliary components can be integrally formed as a monolith with the appliance housing in a single manufacturing step, rather than being added to the housing in separate manufacturing steps. 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, adjacent structures, and housings with variable thickness and / or internal structures (e.g., increasing strength by reducing weight and material usage). For example, in some embodiments, the direct manufacturing method described herein allows for the manufacture of orthodontic appliances with feature dimensions 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.

[0302] 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 method described herein allows the production of orthodontic appliances with strength variations in all directions not exceeding about 25%, about 20%, about 15%, about 10%, about 5%, about 1%, or about 0.5%. Furthermore, the direct manufacturing method described herein can be used to manufacture orthodontic appliances at a faster rate compared to other manufacturing techniques. In some embodiments, the direct manufacturing method described herein allows the production of orthodontic appliances within time intervals 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 rapid “chairside” production of custom-made appliances, for example, during regular appointments or checkups.

[0303] In some embodiments, the direct manufacturing methods described herein implement process control over various machine parameters for the direct manufacturing system or apparatus to ensure the manufacture of the resulting appliance with high precision. Such precision is advantageous for ensuring that the desired force system is accurately delivered to the teeth to effectively induce tooth movement. Process control can 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.

[0304] Material properties can vary depending on the properties of the raw materials, their purity, and / or process variables during mixing. In many embodiments, resins or other materials intended for direct manufacturing should be manufactured under strict process control to ensure minimal variation in 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 distortion temperature). Process control for material manufacturing processes can be achieved by screening the physical properties of raw materials during mixing and / or controlling temperature, humidity, and / or other process parameters. By controlling the material manufacturing process, the variability of process parameters can be reduced, resulting in more uniform material properties for each batch. As further discussed herein, residual variability in material properties can be compensated for through on-machine process control.

[0305] Machine parameters can include curing parameters. For digital light processing (DLP) based curing systems, curing parameters can include power, curing time, and / or the grayscale of the entire image. For laser-based curing systems, curing parameters can include power, speed, beam size, beam shape, and / or beam power distribution. For printing systems, curing parameters can include material droplet size, viscosity, and / or curing power. These machine parameters (e.g., certain parameters per 1-x layers and certain parameters after each build) can be periodically monitored and adjusted as part of process control on the manufacturing machine. Process control can 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 via feedback loops. For DLP machines, grayscale can be measured and calibrated at the end of each build. Additionally, material properties and / or optical characteristics can be provided to the manufacturing machine, and the machine process control module can use these parameters to adjust machine parameters (e.g., power, time, grayscale, etc.) to compensate for variations in material properties. By controlling the manufacturing machine, variations in instrument accuracy and residual stress can be reduced.

[0306] In many embodiments, environmental variables (e.g., temperature, humidity, sunlight, or exposure to other energy / curing sources) are kept within a narrow range to reduce variations in appliance thickness and / or other characteristics. Optionally, machine parameters may be adjusted to compensate for environmental variables.

[0307] In many embodiments, post-treatment of the appliance includes cleaning, post-curing, and / or support removal processes. Relevant post-treatment parameters may 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 part of a process control scheme. Furthermore, the physical properties of the appliance can be altered by modifying post-treatment parameters. Adjusting post-treatment machine parameters can provide another way to compensate for variations in material properties and / or machine properties.

[0308] The configuration of orthodontic appliances described herein can be determined based on the patient's treatment plan (e.g., a treatment plan involving the successive application of multiple appliances to progressively reposition teeth). Computer-based treatment planning and / or appliance manufacturing methods can be used to facilitate the design and manufacture of appliances. For example, one or more appliance components described herein can be digitally designed and manufactured using computer-controlled manufacturing equipment (e.g., computer numerical control (CNC) milling, computer-controlled rapid prototyping (e.g., 3D printing), etc.). The computer-based methods presented herein can improve the accuracy, flexibility, and convenience of appliance manufacturing.

[0309] Figure 15CA method 1550 for orthodontic treatment using multiple appliances (e.g., multiple aligners) according to an embodiment is illustrated. Method 1550 can be practiced using any of the appliances or sets of appliances described herein. In box 1560, a first orthodontic appliance is applied to the patient's teeth to reposition the teeth from a first dental alignment to a second dental alignment. In box 1570, a second orthodontic appliance is applied to the patient's teeth to reposition the teeth from a second dental alignment to a third dental alignment. Method 1550 can be repeated as needed using any suitable number and combination of sequential appliances to progressively reposition the patient's teeth from the initial alignment to the target alignment. All of these appliances can be fabricated in the same phase, in groups, or in batches (e.g., at the beginning of a treatment phase), or one appliance can be fabricated at a time, and the patient can wear each appliance until the teeth no longer feel pressure from each appliance, or until the maximum amount of tooth movement presented at that given phase has been reached. Multiple different appliances (e.g., a set of appliances) can be designed and even fabricated before the patient wears any of the multiple appliances. After an appliance has been worn for an appropriate period of time, the patient can replace the current appliance with the next appliance in the series until no appliances remain. The appliances are typically not fixed to the teeth, and the patient can place and change appliances at any time during treatment (e.g., patient-removable appliances). The final appliance, or several appliances in the series, may have one or more geometries selected for overcorrecting tooth alignment. For example, one or more appliances may have geometries that (if fully realized) move individual teeth beyond the alignment already selected as “final.” This overcorrection may be desirable to counteract potential relapse after the repositioning method has ended (e.g., allowing individual teeth to move in the opposite direction to their pre-corrected position). Overcorrection may also be beneficial for accelerating correction (e.g., an appliance with a geometry positioned beyond the desired intermediate or final position may move individual teeth toward that position at a greater rate). In this case, the use of the appliance can be terminated before the teeth reach the position determined by the appliance. Furthermore, overcorrection can be intentionally performed to compensate for any inaccuracies or limitations of the appliance.

[0310] Figure 16 A method 1600 for designing orthodontic appliances to be manufactured by direct fabrication, according to an embodiment, is illustrated. Method 1600 can be applied to any embodiment of the orthodontic appliances described herein. Some or all of the blocks of method 1600 can be performed by any suitable data processing system or apparatus (e.g., one or more processors configured with suitable instructions).

[0311] In box 1610, a movement path is determined to move one or more teeth from an initial alignment to a target alignment. The initial alignment can be determined by a mold or by scanning of the patient's teeth or oral tissues, such as using wax bite, direct contact scanning, X-ray imaging, tomography, ultrasound imaging, and other techniques for acquiring information about the location and structure of teeth, jawbone, gingiva, and other orthodontic-related tissues. From the acquired data, a digital dataset representing the initial (e.g., pre-treatment) alignment of the patient's teeth and other tissues can be derived. Optionally, the initial digital dataset can be processed to segment the tissue components to each other. For example, a data structure digitally representing the individual crowns can be generated. Advantageously, a digital model of the entire tooth can be generated, including measured or extrapolated hidden surfaces and root structures, as well as the surrounding bone and soft tissues.

[0312] The target alignment of teeth (e.g., the orthodontic treatment expectation and anticipated end result) can be received from the clinician in the form of a prescription, calculated based on basic orthodontic principles, and / or calculated from an outpatient prescription. By specifying the expected final position of the teeth and a digital representation of the teeth themselves, the final position and surface geometry of each tooth can be specified to form a complete model of the tooth alignment at the end of the desired treatment.

[0313] With the initial and target positions of 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 fewest round trips to bring the tooth from its initial position to its desired target position. Optionally, the tooth path can be segmented, and the segments can be calculated such that the movement of each tooth within a segment remains within threshold limits of linearity and rotational translation. In this way, the endpoints of each path segment can constitute a clinically feasible repositioning, and the set of segment endpoints can constitute a clinically feasible sequence of tooth positions, so that moving from one point in the sequence to the next does not result in tooth conflict.

[0314] In box 1620, a force system is defined to produce movement of one or more teeth along a movement path. The force system may include one or more forces and / or one or more torques. Different force systems 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 orthodontic treatment) can be used to determine the appropriate force system to be applied to the teeth to accomplish tooth movement. Sources may be considered when determining the force system to be applied, including literature, force systems determined through experimental or virtual modeling, computer-based modeling, clinical experience, minimization of unwanted forces, etc.

[0315] Determining the force system can include constraints on permissible forces, such as permissible direction and magnitude, and the desired movement induced by the applied forces. For example, different movement strategies may be required for different patients when fabricating a palatal expander. For instance, since very young patients may not have a fully-formed suture, the amount of force required to separate the palate may depend on the patient's age. Therefore, in juvenile patients and other patients without a fully closed mid-palatal suture, palatal expansion can be achieved with smaller forces. Slow palatal movement can also facilitate bone growth to fill the expanding suture. For other patients, faster expansion may be required, which can be achieved by applying greater forces. These requirements can be combined as needed to select the structure and materials of the appliance; for example, by selecting a palatal expander capable of applying greater forces to break the mid-palatal suture and / or induce rapid palatal expansion. Subsequent appliance stages can be designed to apply forces of varying magnitudes, for example, initially applying a larger force to break the suture and then applying smaller forces to maintain suture separation or gradually expand the palate and / or dental arch.

[0316] Determining the force system may also involve 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 arch (e.g., 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, thereby determining the force sufficient to provide the desired expansion of the palate and / or dental arch. In some embodiments, the thickness and / or density of the palatal suture can be measured or input by a treatment specialist. In other embodiments, the treatment professional can select appropriate treatment based on the patient's physiological characteristics. For example, the nature of the palate can also be assessed based on factors such as the patient's age—for instance, younger adolescent patients typically require less force to expand the sutures than older patients because the sutures have not yet fully formed.

[0317] In box 1630, an orthodontic appliance configured to generate a force system is identified. The determination of the orthodontic appliance, its geometry, material composition, and / or properties can be performed using a treatment or force application simulation environment. The simulation environment may include, for example, a computer modeling system, a biomechanical system, or a device. Optionally, a digital model of the appliance and / or teeth, such as a finite element model, can be generated. Finite element models can be created using computer program applications from various vendors. To create a solid geometry model, computer-aided engineering (CAE) or computer-aided design (CAD) programs can be used, such as AutoCAD® software products available from Autodesk, Inc., San Rafael, California. To create and analyze a finite element model, program products from many vendors can be used, including the finite element analysis software package from ANSYS, Inc., Fort Cannes, Pennsylvania, and the SIMULIA (Abaqus) software product from Dassault Systèmes, Inc., Waltham, Massachusetts.

[0318] Optionally, one or more orthodontic appliances can be selected for testing or force modeling. As described above, the desired tooth movement and the force system required or anticipated to cause the desired tooth movement can be identified. Using a simulation environment, candidate orthodontic appliances can be analyzed or modeled to determine the actual force system resulting from the use of the candidate appliances. Optionally, one or more modifications can be made to the candidate appliances, and the force modeling can be further analyzed as described, for example, to iteratively determine the appliance design that produces the desired force system.

[0319] In block 1640, instructions are generated for manufacturing an orthodontic appliance incorporating the specified orthodontic appliance. These instructions can be configured to control a manufacturing system or equipment to produce an orthodontic appliance having the specified orthodontic appliance. In some embodiments, the instructions are configured to manufacture the orthodontic appliance using direct manufacturing methods (e.g., stereolithography, selective laser sintering, fused deposition modeling, 3D printing, continuous direct manufacturing, multimaterial direct manufacturing, etc.) according to the various methods presented herein. In alternative embodiments, the instructions can be configured to manufacture the appliance indirectly, for example, by thermoforming.

[0320] Method 1600 may include additional boxes: 1) scanning the patient’s maxillary arch and palate intraorally to generate three-dimensional data of the palate and maxillary arch; 2) determining the three-dimensional shape profile of the appliance to provide the gap and tooth occlusion structure as described herein.

[0321] Although the above boxes illustrate a method 1600 for designing orthodontic appliances according to some embodiments, those skilled in the art will recognize some variations based on the teachings described herein. Some boxes may include sub-boxes. Certain boxes may typically be performed repeatedly as needed. One or more boxes of method 1600 can be performed using any suitable manufacturing system or apparatus, such as those described herein. Some boxes may be optional, and the order of the boxes may be changed as needed.

[0322] Figure 17 A method 1700 for digitally planning the design or manufacture of orthodontic treatment and / or appliances is illustrated according to embodiments. This method 1700 can be applied to any treatment procedure described herein and can be performed by any suitable data processing system.

[0323] In box 1710, a digital representation of the patient's dental arch is received. This digital representation may include surface topographic data of the patient's intraoral cavity (including teeth, gingival tissue, etc.). Surface topographic data can be generated by directly scanning the intraoral cavity, a physical model (positive or negative) of the intraoral cavity, or an indentation of the intraoral cavity using a suitable scanning device (e.g., a handheld scanner, a desktop scanner).

[0324] In box 1720, one or more treatment phases are generated based on the digital representation of the dental arch. A treatment phase can be a progressive repositioning phase of an orthodontic treatment procedure designed to move one or more of the patient's teeth from an initial tooth arrangement to a target arrangement. For example, a treatment phase can be generated by: determining the initial tooth arrangement indicated by the digital representation, determining the target tooth arrangement, and determining the movement path of one or more teeth in the initial arrangement required to achieve the target tooth arrangement. The movement path can be optimized based on: minimizing the total distance moved, preventing conflicts between teeth, avoiding more difficult tooth movements, or any other suitable criteria.

[0325] In box 1730, at least one orthodontic appliance (e.g., at least one aligner) is manufactured based on the generated treatment stage. For example, a set of appliances may be manufactured, each shaped according to the tooth alignment specified by one of the treatment stages, so that the patient can wear these appliances sequentially to progressively reposition the teeth from the initial alignment to the target alignment. The appliance set may include one or more orthodontic appliances described herein. The manufacture of the appliance may include creating a digital model of the appliance to serve as input to a computer-controlled manufacturing system. The appliance may be formed using direct manufacturing methods, indirect manufacturing methods, or a combination thereof, as needed.

[0326] In some cases, planning various arrangement or treatment phases may not be necessary for the design and / or manufacture of the apparatus. For example... Figure 17As shown by the dashed lines, the design and / or manufacture of orthodontic appliances, and possibly specific orthodontic treatments, may include using a representation of the patient's teeth (e.g., receiving a digital representation of the patient's teeth at box 1710), and then designing / or manufacturing the orthodontic appliance based on the representation of the patient's teeth in the arrangement represented by the received representation.

[0327] Figure 18 A method 1800 is shown for applying one or more corrective measures to a polymer aligner based on a simulated removal of the aligner from the dental arch. Method 1800 can be applied to any process described herein and can be performed by, among others... Figure 14 Any suitable data processing system can be used to perform this task.

[0328] At box 1802, a first digital model representing the patient's dental arch structure can be collected. The dental arch structure may include one or more tooth structures of the patient that are mated to the polymer aligner. As used herein, "dental arch structure" may include structures corresponding to structures corresponding to the patient's dentition. In some implementations, the dental arch structure includes a physical mold for forming the polymer aligner. The dental arch structure may include areas for attachments, bubbles, and / or other structures adhered (e.g., bonded) to the teeth and / or tooth structures; and / or pressure areas, dynamic bridges, and / or other structures subtracted from / removed from the teeth and / or tooth structures. In various implementations, the dental arch structure may include the patient's actual dentition. The dental arch structure can be identified by using physical impressions, scanning, and / or techniques for indirectly manufacturing the polymer aligner by forming the physical mold. Thus, in some implementations, the first digital model represents a physical mold (predictive, actual, etc.) used as the basis for indirectly manufacturing the aligner. The first digital model may include a 3D representation of the physical mold and / or may correspond to a file (e.g., an STL file) for manufacturing (e.g., 3D printing) the physical mold of the aligner. The first digital model may specify one or more material properties of the physical mold, such as one or more surface properties of the material of the physical mold, which will cause friction with the aligner coupled to the physical mold. In various implementations, the first model of the dental arch structure may include one or more physical properties that can be specified in relation to the patient's dentition and / or the patient wearing a polymer aligner on their dental arch, such as biomechanical resistance, friction, other surface properties, etc.

[0329] At box 1804, a second digital model representing the polymer aligner to be supported by the dental arch structure can be collected. The second digital model may include a 3D representation of the polymer aligner and / or may include data relating to forces, torques, and / or other orthodontic repositioning elements to be applied to the dental arch. In some implementations, the polymer aligner may include one or more tooth-receiving cavities configured to apply repositioning forces to one or more tooth structures of the dental arch structure. The second digital model may specify at least some physical properties of the polymer aligner at one or more regions of the polymer aligner. As described herein, physical properties may correspond to material properties of the polymer aligner, such as acceptable material strain at each region. The second digital model may specify for each region whether the polymer aligner is susceptible to physical damage (e.g., deformation, warping, failure, and / or breakage). In some implementations, the second digital model may subdivide the aligner into finite element units and may associate physical properties with those finite elements. As described herein, one or more finite elements may be characterized by specific material properties associated with specific material strains.

[0330] At box 1806, a first digital model and a second digital model are used to simulate the interaction between the polymer aligner and the dental arch structure. An example of this interaction is coupling; however, it should be noted that the polymer aligner and the dental arch structure can physically interact with each other without being coupled. One or more spatial points of the first digital model can be aligned with corresponding spatial points of the second digital model to simulate the placement of the polymer aligner onto the dental arch structure. In some implementations, virtual spring forces can be used to model the interaction between the cavity of the polymer aligner and the corresponding tooth structure in the dental arch structure. In various implementations, the interaction can be modeled by aligning the finite element of the second digital model with the corresponding spatial elements of the first digital model.

[0331] At box 1808, a first digital model and a second digital model can be used to simulate the removal of a polymer aligner from the arch structure. In some implementations, the interaction between the physical properties of the aligner and the second physical properties of the physical mold can be simulated. As an example, the interaction between the material properties of the aligner and the material properties of the physical mold at various regions in space can be simulated. In various implementations, the interaction between the physical properties of the aligner and the physical properties associated with the patient wearing the aligner on the arch (e.g., properties associated with biomechanical forces applied to the teeth and / or properties associated with the intraoral environment) can be simulated. Additionally, simulating the removal of the polymer aligner from the arch structure can include simulating a spring-loaded removal force between the cavity of the polymer aligner and the corresponding tooth structure. As described herein, the spring-loaded removal force can correspond to a force sufficient to exceed a virtual spring force (e.g., a modeling force on the polymer aligner via the mold or arch). Simulating the removal of the polymer aligner from the arch structure can include simulating the sequential removal of the polymer aligner from a first posterior tooth structure of the arch structure to a second opposing posterior tooth structure of the arch structure. It should be noted that simulating the removal of a polymer aligner from a dental arch structure may include: simulating removal from the anterior dental arch structure, followed by the posterior dental arch structure; simulating removal from an appendage-like structure on the dental arch structure, followed by other structures, and so on.

[0332] At box 1810, based on the interaction between the arch-like structure and one or more first physical properties, the probability that one or more physical strains at one or more regions will satisfy one or more strain / stress or deformation energy-based damage criteria can be determined, wherein the interaction is caused by simulation removal. As used herein, “strain / stress or deformation energy-based damage criteria” can include a set of criteria for determining whether the strain / stress of a region of the structure will satisfy, exceed, or otherwise specify a threshold. The strain / stress or deformation energy-based criteria can include numerical fractions (e.g., Boolean and / or decimal values) or can be implemented using various techniques. One or more values ​​representing the interaction between the physical properties of the aligner and the physical properties of the arch-like structure can be determined. These values ​​can represent the probability of physical strain (structural strain, material strain, etc.) at various regions of the aligner due to removal. As described herein, each region (e.g., each finite element) can have values ​​associated with it. Box 1810 may involve reducing the thickness of the polymer aligner represented in the second digital model until one or more first physical properties of the polymer aligner satisfy, exceed, or otherwise satisfy the strain / stress or deformation energy-based damage criteria at one or more regions of the polymer aligner.

[0333] At box 1812, a second digital model is analyzed based on the probability of one or more physical strains at one or more regions to obtain one or more possible structural failure points. In some implementations, the values ​​of physical strains at each region are compared with individual thresholds (e.g., strain thresholds) for those regions. Regions with values ​​below / reaching / exceeding those thresholds can be identified.

[0334] At box 1814, in response to analyzing the second digital model to obtain one or more possible structural damage points, it can be determined whether to implement one or more corrective measures on the polymer aligner. In some implementations, the one or more corrective measures include modifying the aligner geometry of the polymer aligner to accommodate one or more possible structural damage points. As various examples, the one or more corrective measures may guide the placement of cutting lines, occlusal ramps, dynamic bridges, attachments, etc., at locations other than those specified in the second digital model. The corrective measures may guide modifications to the thickness or density of the aligner at various regions of the aligner. The corrective measures may include, for example, instructions to modify the manufacture of the aligner as described herein and / or instructions to modify the treatment regimen as further indicated herein.

[0335] At box 1816, a third digital model representing the polymer aligner can be generated. The third digital model can be based on the second digital model and one or more correction measures of the polymer aligner. The third digital model can represent a modified aligner with, for example, modified aligner geometry (modified cutting lines, occlusal ramps, power bridges, attachments, aligner thickness in various regions, etc.). The modified aligner can serve as the basis for modified manufacturing processes and / or modified treatment plans.

[0336] In some implementations, manufacturing instructions may be provided to fabricate the modified polymer aligner based on a third digital model. In some implementations, the manufacturing instructions may include: a mold-forming instruction for forming a physical aligner mold for the polymer aligner using the third digital model; and / or a thermoforming instruction for thermoforming the polymer aligner from a sheet of polymer material placed on the physical aligner mold. As described herein, the third digital model may include one or more structural features at points corresponding to corresponding points of the second digital model, the one or more structural features being configured to accommodate one or more correction measures. In various implementations, the manufacturing instructions include direct manufacturing instructions for directly manufacturing the polymer aligner using the third digital model. As described herein, the third digital model may include one or more regions with modified thicknesses relative to corresponding regions of the second digital model, the one or more regions with modified thicknesses being configured to accommodate one or more correction measures.

[0337] It should be understood that the above description is intended to be illustrative and not restrictive. Many other embodiments will become apparent upon reading and understanding the above description. Although embodiments of this disclosure have been described with reference to specific example embodiments, it should be recognized that this disclosure is not limited to the described embodiments but can be practiced with modifications and variations within the spirit and scope of the appended claims. Therefore, the specification and drawings should be considered illustrative and not restrictive. Consequently, the scope of this disclosure should be determined by reference to the appended claims and the full scope of their equivalents.

Claims

1. A method comprising: Data from the digital design of the orthodontic aligner is processed to determine the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner or during subsequent use of the orthodontic aligner; The probability that the orthodontic aligner associated with the digital design will be damaged is compared with a probability threshold; Based on the comparison results, it is determined whether the orthodontic aligner is a high-risk orthodontic aligner; and In response to determining that the orthodontic aligner is a high-risk orthodontic aligner, perform at least one of the following: a) corrective measures, or b) select a manufacturing process for the high-risk orthodontic aligner to reduce the probability that the orthodontic aligner associated with the digital design will be damaged.

2. A method comprising: Collect digital models representing an aligner for a patient's dental arch, wherein the aligner includes multiple tooth receptacles and multiple interproximal regions, wherein each of the multiple tooth receptacles is spaced apart from adjacent tooth receptacles in the multiple tooth receptacles by an interproximal region in the multiple interproximal regions; Receive material property information of the material used to manufacture the alignment device; Analyzing one or more regions of the aligner, wherein analyzing the regions of the aligner includes: Simulate the application of loads around the area; Based on the material property information and the load, determine at least one of stress, strain, or strain energy density at the region caused by the applied load around the region; The strength of the aligner in the region is evaluated at least in part based on at least one of the stress, strain, strain energy density determined for the region, or a derived value derived from at least one of the stress, strain, or strain energy density; and Based on the strength of the aligner in the region, it is determined whether the region meets the damage criteria.

3. A method comprising: Collect digital models representing an aligner for a patient's dental arch, wherein the aligner includes multiple tooth-receiving cavities and multiple interproximal regions, wherein each of the multiple tooth-receiving cavities is spaced apart from adjacent tooth-receiving cavities by interproximal regions within the multiple interproximal regions; and Analyzing one or more neighboring regions among the plurality of neighboring regions of the aligner, wherein analyzing the neighboring regions among the plurality of neighboring regions of the aligner includes: Determine multiple cross-sectional slices of the adjacent regions; For each of the plurality of cross-sectional slices, calculate one or more strength values; From the one or more intensity values ​​calculated for the plurality of cross-sectional slices, determine the minimum intensity value of the adjacent region; and Based on the minimum intensity value of the aligner in the adjacent region, it is determined whether the adjacent region meets the damage criterion.

4. A method comprising: At least a first digital model representing a aligner for a patient’s dental arch is collected, wherein the aligner includes a plurality of tooth-receiving cavities, wherein the dental arch includes a plurality of tooth structures, and wherein each of the plurality of tooth-receiving cavities is configured to fit onto one of the plurality of tooth structures; Simulating progressive damage to the aligner to determine the total amount of damage to each of one or more regions of the aligner, wherein simulating progressive damage to the regions of the aligner includes: At least the first digital model is used to simulate a series of multiple loads on the aligner; For each simulation of the load among the plurality of loads on the aligner, determine the amount of damage to a region of the aligner; and After each simulation of the load on the aligner, the first digital model is updated based on the amount of damage to the region of the aligner; Based on the total amount of damage to each of the one or more regions of the aligner, determine whether at least one region of the one or more regions of the aligner meets the damage criterion; and In response to determining whether the damage criteria are met, it is determined whether one or more corrective measures should be implemented for the aligner.

5. A computing device, comprising: A data storage device for storing at least a first digital model representing an aligner for a patient's dental arch, wherein the aligner includes a plurality of tooth-receiving cavities, wherein the dental arch includes a plurality of tooth structures, and wherein each of the plurality of tooth-receiving cavities is configured to fit onto one of the plurality of tooth structures; and A processing device, operatively coupled to the data storage, the processing device being used for: Collect at least the first digital model from the data storage; Simulating progressive damage to the aligner to determine the total amount of damage to each of one or more regions of the aligner, wherein simulating progressive damage to the regions of the aligner includes: At least the first digital model is used to simulate a series of multiple loads on the aligner; For each simulation of the load among the plurality of loads on the aligner, determine the amount of damage to a region of the aligner; and After each simulation of the load on the aligner, the first digital model is updated based on the amount of damage to the area of ​​the aligner. Based on the total amount of damage to each of the one or more regions of the aligner, determine whether at least one region of the one or more regions of the aligner meets the damage criterion; and In response to determining whether the damage criterion is met, it is determined whether to implement one or more corrective measures on the aligner.

6. A non-transitory computer-readable medium comprising instructions that, when executed by a processing means, cause the processing means to perform operations including: At least a first digital model representing the aligner of the patient's dental arch should be collected, wherein, The aligner includes a plurality of tooth receiving cavities, wherein the dental arch includes a plurality of tooth structures, and wherein each of the plurality of tooth receiving cavities is configured to fit onto one of the plurality of tooth structures; Simulating progressive damage to the aligner to determine the total amount of damage to each of one or more regions of the aligner, wherein simulating progressive damage to the regions of the aligner includes: At least the first digital model is used to simulate a series of multiple loads on the aligner; For each simulation of the load among the plurality of loads on the aligner, determine the amount of damage to a region of the aligner; and After each simulation of the load on the aligner, the first digital model is updated based on the amount of damage to the area of ​​the aligner. Based on the total amount of damage to each of the one or more regions of the aligner, determine whether at least one region of the one or more regions of the aligner meets the damage criterion; and In response to determining whether the damage criterion is met, it is determined whether to implement one or more corrective measures on the aligner.

7. A method comprising: Data from the digital design of orthodontic aligners is processed through a trained machine learning model; The trained machine learning model outputs the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner. The probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner is compared with a probability threshold. Based on the comparison results, it is determined whether the orthodontic aligner is a high-risk orthodontic aligner; and In response to determining that the orthodontic aligner is a high-risk orthodontic aligner, perform at least one of the following: a) corrective measures, or b) select a manufacturing process for the high-risk orthodontic aligner to reduce the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner.

8. A method for training a machine learning model to predict damage to orthodontic alignment devices, the method comprising: A training dataset is collected comprising digital designs of multiple orthodontic aligners, wherein each digital design is associated with a corresponding orthodontic aligner among the plurality of orthodontic aligners, and wherein each digital design includes metadata indicating whether the associated corresponding orthodontic aligner was damaged during the manufacturing process of the associated corresponding orthodontic aligner; and The machine learning model is trained using the training dataset, wherein the machine learning model is trained to process data from a digital design of an orthodontic aligner and output the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacture of the orthodontic aligner.

9. A computer-readable storage medium including instructions, which, when executed by a processing means, cause the processing means to perform operations including: For each digital design of the orthodontic alignment in a digital design of multiple orthodontic alignments, perform the following: Data from the digital design of the orthodontic aligner is processed using a trained machine learning model; The trained machine learning model outputs the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner. as well as Based on a comparison of the probability that the orthodontic aligner associated with the digital design will be damaged during the manufacturing process of the orthodontic aligner with a first probability threshold, it is determined whether the orthodontic aligner is a high-risk orthodontic aligner. Determine an aligner set comprising digital designs of the plurality of orthodontic aligners, wherein the digital designs of the plurality of orthodontic aligners are all associated with the patient’s treatment plan; Determine whether any orthodontic aligner represented in the set of aligners is a high-risk orthodontic aligner; and In response to determining that at least one orthodontic aligner represented in the aligner set is a high-risk orthodontic aligner, a manufacturing process for the high-risk orthodontic aligner is selected for the aligner set to reduce the probability that the orthodontic aligners in the aligner set will be damaged during manufacturing.

Images