Predicting updated geometry of dental components

Abstract

Methods, systems, and apparatuses for updating the geometry of an initial 3D model of a dental aid or dental appliance to conform to the engagement surface of a corresponding dental component to provide a better force system as part of orthodontic treatment. The methods can include predicting an updated geometry of the initial 3D model data.

Description

[0001] Priority requirements

[0002] This patent application claims priority to U.S. Provisional Application No. 63 / 627,745, filed January 31, 2024, entitled “DENTAL COMPONENT UPDATEDGEOMETRY PREDICTION”, which is incorporated herein by reference in its entirety.

[0003] By incorporating references

[0004] All publications and patent applications mentioned in this specification are incorporated herein by reference to the extent that each individual publication or patent application is specifically and individually indicated to be incorporated herein by reference. Background Technology

[0005] Dental appliances (“appliances”) used as part of orthodontic treatment may be adapted to be worn on one or more patient teeth. Appliances may be configured to engage with one or more dental aids (“aids” or “tools”) that are fastened or secured to one or more patient teeth. The aids and appliances may be designed such that engagement between corresponding structures of the aids and appliances results in the application of one or more forces (retention forces, tooth movement forces, lateral expansion forces, etc.) to the patient’s dentition to facilitate orthodontic treatment. Optimal engagement between the appliance and the aid translates into optimal forces to facilitate orthodontic treatment.

[0006] Insufficient engagement between the fabricated geometry of an accessory and its corresponding engagement surface on the appliance can have various causes, resulting in suboptimal forces. As an example only, different fabrication or manufacturing techniques used for accessories and appliances can lead to less-than-ideal engagement geometries. Solutions are needed that can provide conformal geometry between the fabricated accessory and the corresponding engagement surface of the fabricated dental appliance to generate the desired force system for orthodontic treatment. Summary of the Invention

[0007] One aspect disclosed herein relates to updating at least one surface of a 3D model of an accessory or appliance to create an updated geometry such that the manufactured mating surfaces will fit more closely together, thereby creating a better engagement and / or force system to facilitate orthodontic treatment. The disclosure herein can be applied to updating the surfaces of accessories or appliances. The disclosure herein can be used to update various surfaces of dental components to more closely conform to the geometry of different dental component surfaces.

[0008] One aspect of this disclosure is a method for forming a dental accessory. The method may include: receiving or generating an initial 3D model of the dental accessory by a processor; predicting an updated geometry of the initial 3D model of the dental accessory by the processor to conform to the accessory well of a dental appliance; and generating a digital representation of the dental accessory based on the updated geometry.

[0009] In this respect, predicting the updated geometry may include identifying error surfaces on the initial 3D model of the dental aid, where the error surfaces correspond to surfaces of the aid wells that are predicted to deviate from the original design of the dental appliance; and modifying the error surfaces of the 3D model of the dental aid to create the updated surfaces. The updated geometry defines a modified geometry that differs from the initial geometry of the 3D model of the dental aid.

[0010] One aspect of this disclosure is a method for forming a dental appliance. The method may include: receiving or generating an initial 3D model of the dental appliance by a processor; predicting an updated geometry of the 3D model of the dental appliance by the processor to conform to a dental accessory; and generating a digital representation of the dental appliance based on the updated geometry.

[0011] In this respect, predicting the updated geometry may include: identifying error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental appliance that are predicted to deviate from the original design of the dental appliance; and modifying the error surfaces of the 3D model of the dental appliance to create the updated surfaces. The updated geometry defines a modified geometry that differs from the initial 3D model of the dental appliance.

[0012] The prediction method for predicting the updated geometry of dental components in this paper can be performed using a model that has been trained to predict the updated geometry, such as a supervised machine learning algorithm trained with inputs and targets.

[0013] One aspect of this disclosure is a method for training a machine learning prediction model to predict an updated geometry of a 3D model of a dental aid to conform to an aid well of a dental appliance. The method may include: providing 3D models of a plurality of dental aids, each of the plurality of 3D models including an error surface; providing 3D models of a plurality of dental appliances, each of the plurality of 3D models including an aid receiving well; identifying a plurality of sampling points on each error surface; identifying a plurality of training features associated with each of the plurality of sampling points; and providing one or more target distances from each of the plurality of sampling points to a surface of the aid receiving well, to train the prediction model using the plurality of features associated with each of the plurality of sampling points and the target distances. Once trained, the trained prediction model is adapted to receive an initial 3D model of a dental aid as input and, based on the initial 3D model of the dental aid, predict an updated geometry of the 3D model of the dental aid to conform to an aid well of a dental appliance.

[0014] One aspect of this disclosure is a method for training a machine learning prediction model to predict an updated geometry of a 3D model of a dental appliance to conform to an accessory. The method may include: providing 3D models of a plurality of dental appliances, each of the plurality of 3D models including an error surface in an accessory well; providing 3D models of a plurality of dental accessories; identifying a plurality of sampling points on each error surface; identifying a plurality of features associated with each of the plurality of sampling points; and providing one or more target distances from each of the plurality of sampling points to a surface of the accessory, to train the prediction model using the plurality of features associated with each of the plurality of sampling points and the target distances. Once trained, the trained prediction model is adapted to receive an initial 3D model of the dental appliance as input and, based on the initial 3D model of the dental appliance, predict an updated geometry of the 3D model of the dental appliance to conform to the accessory.

[0015] One aspect of this disclosure is a system comprising: one or more processors; and a memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method. The computer-implemented method can be any method described herein, including those that incorporate a trained model to predict any updated geometry described herein.

[0016] In this aspect, the computer-implemented method may include: receiving or generating an initial 3D model of a dental accessory by a processor; predicting an updated geometry of the 3D model of the dental accessory by the processor to conform to the accessory well of the dental appliance; and generating a digital representation of the dental accessory based on the updated geometry. Predicting the updated geometry may include: identifying error surfaces on the initial 3D model of the dental accessory, wherein the error surfaces correspond to surfaces of the accessory well that are predicted to deviate from the original design of the dental appliance; and modifying the error surfaces of the 3D model of the dental accessory to create the updated surfaces. The updated geometry defines a modified geometry that differs from the initial geometry of the 3D model of the dental accessory.

[0017] In this aspect, the computer-implemented method may include: receiving or generating an initial 3D model of a dental appliance by a processor; predicting an updated geometry of the 3D model of the dental appliance by the processor to conform to a dental aid; and generating a digital representation of the dental appliance based on the updated geometry. Predicting the updated geometry may include: identifying error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental aid that are predicted to deviate from the original design of the dental aid; and modifying the error surfaces of the 3D model of the dental appliance to create the updated surfaces. The updated geometry defines a modified geometry that differs from the initial 3D model of the dental appliance. Attached Figure Description

[0018] A better understanding of the features and advantages of the methods and apparatus described herein will be obtained by referring to the following detailed description and accompanying drawings, which illustrate illustrative embodiments, in which: Figure 1 An exemplary 3D model of the auxiliary component is shown.

[0019] Figure 2 An exemplary physical model of the dental arch and accessories is shown.

[0020] Figure 3 An exemplary process for indirectly forming an appliance is shown.

[0021] Figure 4A and Figure 4B Model data for the teeth and accessories are shown.

[0022] Figure 5A , Figure 5B and Figure 5C An exemplary printing process is shown that leads to over-curing in a portion of the physical model.

[0023] Figure 6A , Figure 6B and Figure 6CExemplary different manufacturing techniques are shown and illustrated, including exemplary different manufacturing orientations that may result in geometric mismatches between the interface surfaces of different dental components.

[0024] Figure 7 A comparison is shown between the initial 3D model of the auxiliary component and the physical model, which includes over-cured areas of the auxiliary component due to the manufacturing process.

[0025] Figure 8 A comparison is shown between the initial 3D model of the auxiliary component and the physical model, which includes over-cured areas of the auxiliary component due to the manufacturing process.

[0026] Figure 9A and Figure 9B A comparison is shown between the shape of the initial 3D model of the attachment and the shape of the indirectly formed template attachment.

[0027] Figure 10 The predicted updated geometry is shown, which includes modifying the error surface of the 3D model of the auxiliary part to create the updated offset surface.

[0028] Figure 11 An exemplary method is shown as part of forming a dental accessory.

[0029] Figure 12 An exemplary method for predicting the updated geometry of an initial 3D model of an auxiliary component is shown.

[0030] Figure 13A and Figure 13B A method for predicting the updated geometry of an initial 3D model of an auxiliary component is shown.

[0031] Figure 14 An exemplary general method for training a machine learning algorithm or model is shown.

[0032] Figure 15 An exemplary process for training a machine learning algorithm or model is shown.

[0033] Figure 16A and Figure 16B This shows a portion of an exemplary process for training a machine learning algorithm or model.

[0034] Figure 16C An exemplary coordinate system is shown in the examples and figures used with reference to this document.

[0035] Figure 17 An exemplary method is shown that uses a trained model to predict the updated geometry of an initial 3D model of a dental aid.

[0036] Figure 18 A composite or flash layer is shown that can be used to predict the updated geometry of auxiliary components.

[0037] Figure 19 An exemplary directly manufactured auxiliary component with a support structure is shown.

[0038] Figure 20 An exemplary dental appliance is shown, which may include one or more auxiliary components as described herein.

[0039] Figure 21 An exemplary method for forming a dental appliance is shown.

[0040] Figure 22 An exemplary method for predicting the updated geometry of an initial 3D model of a dental appliance is shown.

[0041] Figure 23 An exemplary general method for training a machine learning algorithm or model is shown.

[0042] Figure 24 An exemplary process for training a machine learning algorithm or model is shown.

[0043] Figure 25 , Figure 26 and Figure 27 An updated geometry of a predicted dental appliance is shown, which includes modifying the error surface of the 3D model of the appliance to create an updated offset appliance surface.

[0044] Figure 28 An exemplary method is shown that uses a trained model to predict the updated geometry of an initial 3D model of a dental appliance.

[0045] Figure 29 This is a diagram showing a variant of the computing environment 2900. Detailed Implementation

[0046] Dental appliances (“appliances”) for dental treatment (e.g., orthodontic treatment) may be adapted to be worn on one or more patient teeth. Appliances may be configured to engage with one or more dental aids (“aids” or “tools”) that are fastened or secured to one or more patient teeth. One or more aids, as used herein, may be referred to as a single aid. Aids and appliances may be designed such that engagement between corresponding engagement structures of the aid and appliance results in the application of one or more forces (retention, tooth movement, lateral expansion) to the patient’s dentition to facilitate orthodontic treatment. Therefore, orthodontic treatment is generally more effective when the manufactured components engage when worn to generate preferred forces to facilitate orthodontic treatment.

[0047] While a variety of reasons may lead to inadequate bonding, the innovative solutions described herein can be applied to these reasons, manufacturing appliances and accessories to facilitate the desired treatment, where different manufacturing techniques may result in insufficient, suboptimal, or less-than-ideal bonding of the geometry of the corresponding bonding surfaces. For example, using different manufacturing processes (e.g., direct manufacturing vs. indirect manufacturing) to manufacture accessories and applications is an example of different manufacturing techniques described herein, which may result in corresponding surface geometries that could lead to smaller or unwanted force systems between the appliance and accessory, or may otherwise result in suboptimal bonding of the appliance and accessory. Additionally, for example, manufacturing appliances and accessories with different orientations (e.g., top-down vs. bottom-up) to facilitate the desired treatment is an example of different manufacturing techniques described herein, which may result in insufficient, suboptimal, or less-than-ideal bonding of the geometry of the corresponding bonding surfaces. Furthermore, for example, using different types of 3D printing processes to manufacture appliances and accessories to facilitate the desired treatment is an example of different manufacturing techniques described herein, which may result in insufficient, suboptimal, or less-than-ideal bonding of the geometry of the corresponding bonding surfaces. This article describes additional examples of different types of manufacturing techniques used for auxiliary parts and appliances.

[0048] One aspect disclosed herein relates to updating at least one surface of a 3D model of an accessory or appliance to create an updated geometry such that the manufactured mating surfaces will fit more closely together, thereby achieving a better force system to facilitate orthodontic treatment. The disclosure herein can be applied to updating the surfaces of accessories, or updating the surfaces of appliances, such as the surfaces of appliances designed to engage with the surfaces of accessories.

[0049] The aids described herein may include dental attachments, buttons, power arms, brackets, or any other fixation devices attached to one or more teeth for engagement with dental appliances (e.g., clear aligners, palatal expanders, mouth protectors, retainers) to facilitate orthodontic treatment. While some examples of aids described herein may include dental attachments, the methods and systems described herein may include other types of aids.

[0050] Orthodontic treatment may include generating or receiving a 3D model of the patient's dentition, which may include using Figure 29 The intraoral scanning system 2910. Treatment may include determining the geometry of an accessory to be fixed to one or more teeth, thereby engaging the appliance to apply a force system to facilitate treatment, which may include using Figure 29 The treatment planning system 2930 in the text. Treatment may include generating 3D models of the dentition and accessories, such as CAD models. Figure 1A portion of an exemplary 3D model 100 is shown, which includes a tooth model 104 and an accessory model 102 in a position and configuration designed to apply force when engaged with an appliance. In this example, the accessory 102 is a dental attachment adapted to engage with an attachment or appendage of an appliance. The model may include a complete model of a patient's dentition and one or more accessories (e.g., attachments).

[0051] As used in this article, the term "3D model" can refer to data configured to represent or render a 3D model, or it can refer to the 3D model itself.

[0052] Common techniques used to manufacture articles (e.g., appliances and accessories for dental applications) involve additive manufacturing techniques, such as 3D printing. As will be discussed further in detail here, certain 3D printing methods involving the use of energy (e.g., light) to cure materials (e.g., stereolithography (SLA), digital light processing (DLP), volumetric printing) can be prone to over-curing due to, for example, energy (e.g., light) penetrating beyond the intended target area. That is, at least some of the energy can penetrate the material further than optimally, and thus cure additional areas (referred to herein as “over-cured areas”), resulting in a deviation from the initial 3D model on which the article is based. This deviation can be particularly problematic in the case of articles manufactured individually but requiring physical interaction with each other, as deviations in one or both articles can lead to suboptimal interactions.

[0053] Some dental applications (e.g., orthodontics) require the use of separate artifacts that interact with each other. For example, some dental treatments require the use of appliances configured to physically engage with accessories (e.g., attachments, power arms, buttons). In this example, one or more accessories (e.g., attachments, buttons) can be fabricated and attached to the patient's teeth, and appliances (e.g., orthodontic appliances, palatal expanders) can be fabricated to be placed on the patient's teeth and one or more accessories, wherein the appliance includes one or more corresponding receiving wells that mate with one or more accessories.

[0054] As will be explained in further detail below, in some cases, an appliance (or physical mold for ultimately forming the appliance) can be manufactured in a first orientation, while an accessory (or mold for ultimately forming the accessory) can be manufactured in a second orientation. For example, an appliance can be 3D printed with its gingival portion at the bottom, and a corresponding accessory can be 3D printed with its gingival portion at the top. That is, one can be printed upside down, while the other can be printed face up. In many cases, this difference in manufacturing techniques may be necessary or at least optimal (e.g., the first manufacturing method may be feasible for forming the appliance, but not for forming the accessory). Overcuring is particularly problematic in such cases, for example, because the receiving well of an appliance printed in the first orientation may include an overcured area in the first direction (e.g., in the gingival direction), while the corresponding accessory printed in a different orientation may not include the corresponding overcured area in that first direction. Therefore, a mismatch exists, such that the accessory may not conform properly to its corresponding receiving well, and therefore may not engage properly with its corresponding receiving well. This can lead to suboptimal performance. In some cases, mismatch can even prevent auxiliary components from fitting into their corresponding receiving wells, rendering the appliance or auxiliary component ineffective or unusable. This is illustrated in this document by reference, for example. Figure 6A , Figure 6B and Figure 6C To show and describe in more detail.

[0055] One aspect of the methods and systems disclosed herein aims to address this problem by predicting overcuring and / or other deviations that may be caused by manufacturing techniques, and adjusting the geometry of either or both of the 3D models of the appliance and one or more accessories to address such deviations so that the appliance and accessories fit together properly.

[0056] In some examples, dental appliances can be formed based on a physical model (e.g., a mold) corresponding to a patient's dentition and any existing or planned accessories (e.g., attachments), where the physical model can be manufactured based on 3D model data. For example, the appliance can be thermoformed on the physical model or manufactured based on the physical model in other ways (e.g., injection molding). Figure 2 An example of a portion of a mold 200 created based on a 3D model of the dentition and accessories is shown. The mold 200 is adapted to engage with an appliance as part of orthodontic treatment. The mold 200 includes teeth 204 and accessories 202, which are dental attachments in this case.

[0057] Figure 3An exemplary process is illustrated in which multiple molds (including mold 302) have been manufactured. Multiple molds can be manufactured at once using additive manufacturing techniques (e.g., 3D printing techniques such as stereolithography, digital light processing, powder sintering, volumetric printing). A sheet of material 304 is thermoformed on mold 302 to form a corresponding appliance 306. The appliance can be a dental appliance, such as an orthodontic appliance, palatal expander, retainer, mouth guard, sports protector, etc. The configuration of the thermoformed appliance, including auxiliary parts wells, depends on the shape of the mold. Appliances formed using molds as intermediates (rather than directly formed, e.g., by directly 3D printing a 3D model of the appliance) may be referred to herein as having been "indirectly" formed.

[0058] Molds 200 and 302 can be manufactured using direct manufacturing techniques (such as layer-by-layer printing) and based on 3D models corresponding to the patient's dentition and planned / existing accessories on such dentition (such as... Figure 1 It is manufactured using a 3D model (100). Figure 4A and Figure 4B The model data 400 is represented, including tooth representation 404 and auxiliary component representation 402. Figure 4A and Figure 4B The accessory designation 402 reflects an initial geometry (referred to herein as the "initial geometry") designed for the patient based on the treatment plan and / or the patient's characteristics to achieve specific outcomes for the patient when the accessory is fastened to the patient's teeth and engaged with the final appliance to be manufactured. Includes Figure 4B The dashed lines in the figure are to illustrate that the mold in this example (which includes the auxiliary part corresponding to auxiliary part representation 402) is manufactured directly layer by layer based on 3D model data (e.g., photocured).

[0059] For example, stereolithography (SLA) can be used to print molds layer by layer. Figures 5A-5C The diagram shows an auxiliary part 502 designed by layer-by-layer 3D printing (SLA) from an initial 3D model of the auxiliary part. As shown in these figures, due to over-curing, the geometry of the final manufactured auxiliary part differs from the initial geometry of the designed auxiliary part 502, and in this case, is larger. During SLA mold printing, the mold is printed layer by layer. When printing the upper layers, light energy passes through the already printed portions and causes over-curing near the bottom surface, such as... Figure 5C As shown. Figure 5B and Figure 5CAs shown, the translucent material allows some UV light to pass through and forms an over-cured region 512 near the bottom surface of the initial geometry designed for the patient. Therefore, this over-cured region 512 extends beyond the initial geometry of the initial 3D model 502 of the accessory, and as a result may cause problems or at least may not be optimal. During mold printing, in some cases, the printed accessory may be larger than the initial 3D model of the accessory in one or more directions (e.g., approximately 0-500 μm). Figure 5C As shown, the amount of over-curing can vary along the length of the bottom surface. In some cases, other unintended deviations may occur (e.g., shape differences). Therefore, the mold includes one or more auxiliary parts, each with a geometry different from the geometry of the initial 3D model of the auxiliary part. Although this disclosure focuses on methods for addressing geometrical variations caused by over-curing, it envisions that geometrical variations may originate from any other manufacturing process effects, and that similar methods can be used to address such variations.

[0060] When dental instruments are formed (e.g., thermoforming) on ​​a mold (e.g., mold 302), such as Figure 3 As shown, the dental appliance will be formed with one or more auxiliary wells, which are configured to more closely conform to or match the shape of the mold auxiliary part, rather than the initial geometry of the initial 3D model of the auxiliary part.

[0061] In some cases, a mold (e.g., mold 302) can also be used to form an accessory template (e.g., by thermoforming on the mold) having one or more accessory wells, which can then be used to form one or more corresponding accessories on a patient's dentition. For example, the accessory template can be positioned on a patient's dentition, and then a curable material can flow into the accessory wells and then cure on the patient's dentition. Similar to appliances formed using a mold, accessories formed using a mold may be referred to herein as "indirectly" formed.

[0062] When the auxiliary component template is thus indirectly formed on the same mold on which the dental appliance is formed, the auxiliary component template will have a geometry that fully conforms to the auxiliary component in the dental appliance, because they are both indirectly formed on the same mold. That is, even if there are deviations in the mold (e.g., due to...) Figures 5A-5C (caused by over-curing in the mold), if both the appliance and the auxiliary part template are formed on the mold, the resulting auxiliary part can fully conform to the auxiliary part joint well in the appliance, so that there may be no problem.

[0063] However, in some examples, instead of using the same manufacturing techniques to create the accessory, the dental accessory described herein can be manufactured in an orientation different from the orientation in which the mold is printed. Different manufacturing orientations in this document refer to the relative manufacturing orientations between two objects that are at an angle greater than zero, such as 180° (opposite orientation), 90°, 45°, or 25°, or other angles. Different manufacturing orientations can form an accessory with a geometry different from the receiving well of a dental appliance (e.g., an appliance already formed by thermoforming on a mold), because in this example, the receiving well of the dental appliance is formed based on the mold shape of the accessory, which may include, for example, Figure 5C The over-cured region 512 is shown. An auxiliary component manufactured directly in a different orientation can have a geometry different from the geometry of the well and can be closer to the geometry of the designed initial 3D model. Therefore, if over-curing or other deviations (e.g., shape, volume, etc.) already exist in the formation of the mold used to create the corresponding appliance, and the auxiliary component is manufactured in a different orientation (e.g., 3D printing), the auxiliary component may have a different geometry from the receiving well, resulting in a suboptimal interaction between the two components. In one example, the dental appliance can be manufactured in a first orientation, where the gingival side of the receiving well is downward (e.g., using an indirect manufacturing technique as described above, using a direct manufacturing technique such as 3D printing, etc.), and the associated dental auxiliary component can be manufactured in a second orientation (e.g., using an indirect manufacturing technique as described above, using a direct manufacturing technique such as 3D printing, etc.), where the gingival side of the dental auxiliary component is upward. In some examples, the dental appliance can be manufactured using an indirect manufacturing technique, and the dental auxiliary component can be manufactured using a direct manufacturing technique (and in a different orientation).

[0064] Figure 6A The printout is shown Figures 5A-5C The orientation of the mold shown. Figure 6B Exemplary different manufacturing techniques are illustrated, which include a printing direction or orientation different from the orientation of the mold forming. In this example, the auxiliary part 600 is manufactured from top to bottom, wherein the top region 602 of the auxiliary part is formed before the bottom region 604. In this manufacturing process, the bottom region 604, including the gingival surface 610, is not easily formed with the mold. Figure 6A The same areas, if any, are over-cured during the orientation printing shown, with the gingival surface at the bottom. In this example, the printed gingival surface 610 will have a shape closer to the gingival surface of the initial 3D model of the accessory than the molded shape. Figure 6B The printed auxiliary part 600 (including the gingival surface 610) will not conform to the shape of the receiving well of the appliance formed on the mold, wherein the mold includes an over-cured gingival area.

[0065] While the disclosure herein may provide examples of indirectly forming (e.g., thermoforming) fixtures and directly forming (e.g., 3D printing) one or more auxiliary parts, different manufacturing techniques that may result in suboptimal geometric consistency between surfaces may include directly manufacturing both fixtures and auxiliary parts, but at different angles or orientations. In this case, different angles or orientations are examples of the different manufacturing techniques described herein. For example, Figure 6A and Figure 6B The opposite orientations (180° difference) of the prints are shown. However, at non-zero angles other than 180°, the orientations may differ, leading to a lack of sufficient consistency. For example, Figure 6A and Figure 6C The difference shown is a 90° (or approximately 90°) difference in orientation when printing the accessory 620, which will also result in insufficient consistency between the well and gingival surfaces of the 3D-printed accessory 620 based on the initial 3D model of the accessory. The predicted updated geometry in this paper adjusts the error surfaces of the initial 3D model of the accessory and creates an updated surface that conforms to the corresponding mating surface of the corresponding dental component.

[0066] In such Figure 5C In the examples of over-curing shown, the receiving well of the appliance formed using the mold may be larger than the corresponding accessory in one or more dimensions. This difference in geometry may result in less contact between the appliance receiving well and the accessory, which could lead to a smaller and / or unwanted force system, and thus less than ideal orthodontic treatment. In another example, deviations along one or more surfaces in the mold corresponding to the receiving well may result in the receiving well being smaller than a directly manufactured accessory. In yet another example, one or more surfaces in the mold corresponding to the receiving well may have deviations in shape, slope, etc., and such deviations may not be present in the directly manufactured accessory. In these examples, the engagement between the accessory and the appliance may similarly be suboptimal.

[0067] Figure 7 The initial geometry of the initial 3D model of the tooth model 604, including surfaces 606 and 607 of the designed accessory, and the predicted geometry of the accessory including surfaces 606 and 608 are shown, wherein the predicted accessory is expected to be formed based on a mold with deviations (e.g., including over-cured areas) as described above. Figure 7 The molded auxiliary parts are larger than the initial 3D model due to the over-cured areas, where the outer surface defines a volume larger than that defined by the geometry of the initial 3D model.

[0068] Figure 8The figure shows an overlay of an initial 3D model of the auxiliary part 712 (in this case, an accessory) and a scan of the template accessory 710 thermoformed on an SLA mold. As shown, the geometry of the initial 3D model 712 is different from (in this case smaller than) the geometry of the template accessory 710, and the volume defined by the geometry of the template accessory 710 is larger than the volume defined by the geometry of the initial 3D model 712.

[0069] Figure 9A and Figure 9B Additional examples of the initial 3D model design geometry for auxiliary parts are shown. Figure 9A ), and the predicted geometry used to adjust for deviations caused, for example, over-curing. Figure 9B ). Figure 9A and Figure 9B The differences in geometry are shown, with the template attachment being larger because it was formed using a mold that includes an over-cured area.

[0070] One aspect disclosed herein relates to adjusting at least one surface of a 3D model of an accessory or a corresponding appliance to create an updated geometry (e.g., by predicting deviations as described above and then adjusting surfaces on an initial 3D model based on the predicted deviations to generate an updated or adjusted 3D model), particularly in cases where the accessory and appliance are manufactured differently (e.g., manufactured in different orientations) resulting in a mismatch between them. By adjusting the 3D model, predicted over-curing / deviations can be taken into account, and the ultimately manufactured appliance and corresponding accessory will fit more closely to each other, thereby achieving a better force system to facilitate orthodontic treatment. The disclosure herein can be applied to correct the surfaces of a 3D model of an accessory to conform to the surfaces of an appliance (e.g., a receiving well of an appliance configured to engage with the surface of an accessory), or to correct the surfaces of a 3D model of an appliance to conform to the surfaces of an accessory.

[0071] One of the technical solutions provided by the methods and systems described herein is to achieve a desired force system while allowing greater flexibility in manufacturing options for producing dental components that work together (e.g., dental appliances and corresponding dental aids). For example, printing the appliance or mold in a first orientation (e.g., gingival portion down) may be more feasible or better, and printing the aid in a second orientation (e.g., gingival portion up) may be more feasible or better. As another example, indirectly manufacturing the appliance (e.g., thermoforming on a mold that may have already been formed by 3D printing) may be more feasible or better, and directly manufacturing the aid (e.g., direct 3D printing, e.g., using DLP) may be more feasible or better, and vice versa. As yet another example, manufacturing the appliance (or the mold used to form the appliance) using a first 3D printing technology (e.g., SLA) may be more feasible or better, and manufacturing the aid (or the mold used to form the template of the aid) using a second 3D printing technology (e.g., DLP) may be more feasible or better. By adjusting the geometry of the 3D model to account for the mismatch between the fixtures and accessories due to the use of different manufacturing techniques, compatibility of these different technologies can be achieved, thereby realizing the optimal combination of manufacturing techniques.

[0072] One aspect of this disclosure is a method for directly forming a dental accessory (e.g., an attachment) that takes into account the difference between the geometry of a 3D model of the dental accessory and the geometry of an accessory well indirectly formed from a dental appliance, which engages with the dental accessory when the dental accessory is attached to a tooth and the dental appliance is worn by a patient. The method includes predicting an updated geometry of an initial 3D model to conform to the geometry of the appliance accessory well, thereby achieving a better force system based on orthodontic treatment.

[0073] Figure 10 A portion of the prediction process is illustrated, which includes adjusting the geometry of an initial 3D model of an accessory, represented by surfaces 902 and 904. This process adjusts the geometry of the initial 3D model to create an updated geometry that includes surfaces 902 and 906. In this example, the error surface 904 is adjusted to create an updated surface 906 that compensates for over-cured areas of the mold accessory as described above. Adjusting the geometry to include the updated surface 906 creates an updated geometry for the accessory that more closely conforms to the geometry of the accessory well of the dental appliance than the geometry of the initial 3D model of the accessory, because in this example, the appliance including the accessory well is indirectly formed on the mold.

[0074] In some embodiments, the 3D model of an appliance receiving well or accessory can be adapted to have an updated geometry that actively uses predicted over-curing to form the desired shape. That is, the desired appliance or accessory can be manufactured using controlled amounts of over-curing. For example, refer to... Figure 10 Instead of allowing the formation of over-cured regions (i.e., the portion between surfaces 904 and 906), the 3D model of the auxiliary part can be adjusted by modifying surface 904 of the 3D model to give it a geometry dependent on over-curing, thereby ultimately producing an auxiliary part with a geometry similar to the initial 3D model. For example, this could involve "extrusion" (i.e., in...). Figure 10 The method and system disclosed herein can be used to predict the dimensions of overcuring and to adjust surface 904 accordingly in the updated 3D model, such that when the accessory is actually printed, the result is an accessory that conforms to the initial 3D model (due to controlled overcuring). Similar controlled overcuring methods can be used to manufacture appliances.

[0075] Figure 11 An exemplary method for forming a dental accessory is shown, which can at least partially occur in Figure 29 In the treatment planning system 2930, method 1000 includes, at step 1002, receiving or generating an initial 3D model of a dental aid. The initial 3D model of the dental aid includes data configured to represent or render a 3D model. The initial 3D model can be... Figure 29 The treatment plan system 2930 is generated in the system and is based on the use of Figure 29 Oral scan generated by the intraoral scanning system 2910. Figure 1 A portion of the initial 3D model of the dental aid is shown.

[0076] At step 1004, method 1000 includes predicting an updated geometry of the 3D model of the dental aid to conform to the aid's well. As described herein, the updated geometry includes any type of adjustment to the geometry of the initial 3D model. Examples of the updated geometry (e.g., provided by...) Figure 10 Surfaces 902 and 906 in the diagram represent the conformation of the appliance accessory well, because in this example, the appliance is indirectly formed on the mold (e.g., thermoforming), thereby creating a better force system as part of the orthodontic treatment plan when the accessory is fixed to the teeth and the appliance is worn by the patient. Method 1000 includes, at step 1006, generating a digital representation of the dental accessory based on the updated geometry, which can be... Figure 29The treatment planning system 2930 occurs within the system. Method 1000 may also optionally include, at step 1008, receiving direct manufacturing instructions based on the updated geometry via a direct manufacturing machine, and in response to the received instructions, directly manufacturing the dental accessory using the manufacturing machine according to the direct manufacturing instructions, which can be performed... Figure 29 This occurs in the auxiliary parts and / or appliance manufacturing system 2950.

[0077] Figure 12 from Figure 11 Step 1004 in the diagram illustrates an exemplary method 1100 for predicting the updated geometry of a dental aid. Method 1100 includes, at step 1102, identifying error surfaces on the initial 3D model of the dental aid, such as... Figure 10 Error surface 904 in the document refers to the surface of the attachment well that is predicted to deviate from the original design of the dental appliance. The predicted surface of the attachment well from the original design may be due to deviations based on the manufacturing process. For example, as described herein, predicted deviations can occur as a result of manufacturing techniques that include (e.g., layer-by-layer) printing a physical model of a patient's dentition, such as any mold described herein. As mentioned above, deviations may result from over-curing in a portion of the mold's auxiliary parts during 3D printing, an example of which is... Figures 5A-5C As shown in the image.

[0078] Method 1100 further includes, at step 1104, modifying the error surface of the 3D model of the dental aid to create an updated surface, an example of which is... Figure 10 The updated surface 906 is shown in the diagram. As described herein, adjusting the error surface refers to any type of adjustment to the error surface. Similarly, as described herein, an updated surface refers to a surface that has been adjusted relative to and compared to the error surface.

[0079] As described herein, adjusting an error surface includes changing the shape, profile, volume, and / or geometry of the error surface, which are not necessarily exclusive characteristics of the surface as used herein. For example, the shape, profile, and geometry of surfaces may have similar characteristics. Changing the geometry of an error surface of an initial model (of an accessory or appliance) can refer to any adjustment to the geometry, shape, and / or profile of the error surface. For example, changing the geometry of an error surface may include adjusting the geometry of one or more portions of the error surface without adjusting the geometry of one or more other portions of the error surface. Additionally, for example, changing the geometry of an error surface may include adjusting a first portion of the surface to a greater extent than a second portion, examples of which are shown and described herein.

[0080] In some embodiments, adjusting the error surface includes extruding at least a portion of the error surface outward in a direction perpendicular to at least a portion of the error surface. For example, Figure 10 An adjustment error surface 904 is shown, comprising extruding the error surface 904 outward in a direction E perpendicular to the error surface 904. Extruding at least a portion of the error surface in the "E" direction does not require adjusting or moving all points on the surface the same distance in one direction (e.g., along the long axis of the auxiliary member). Figure 10 As shown, for example, the degree to which error surface 904 is adjusted in direction E is generally greater in regions closer to the tooth surface than in regions farther from the tooth surface (relative to the "H" direction perpendicular to the tooth surface, as shown in the figure, and in...). Figure 18 (Cited in Chinese).

[0081] In some embodiments, adjusting the error surface may include squeezing at least a portion of the error surface inward in a direction perpendicular to at least a portion of the error surface. For example, Figure 10 The intrusion direction "I" perpendicular to the error surface 904 is shown.

[0082] In some implementations, the updated geometry can define a larger volume than the volume defined by the initial 3D model of the dental aid. For example, as Figure 10 As shown, the updated geometry includes surfaces 902 and 906, and defines a larger volume than that defined by the geometry of the initial 3D model, which includes surface 902 and error surface 904. In other embodiments, the volumes of the initial and updated geometries may be the same after the error surface is adjusted to the updated surface.

[0083] The method for forming dental aids described herein may include predicting an updated geometry of a 3D model of the dental aid to conform to an accessory well of a dental appliance. The updated geometry conforming to the accessory well is a geometry that more closely conforms to or matches the geometry of the corresponding accessory well of the dental appliance compared to the geometry of an initial 3D model of the dental aid. In this example, the term conforming includes corresponding accessory surfaces and well surfaces that are more similar to or match each other compared to the corresponding initial accessory 3D model and well surfaces.

[0084] Figure 13A and Figure 13B The updated geometry of the initial 3D model of the predicted dental aid 1202 is shown to conform to the aid well of the dental appliance 1204.

[0085] Figure 13A An initial 3D model of the auxiliary component 1202, including the error surface 1206, and the dental appliance auxiliary component well 1204 are shown. Figure 13B The diagram shows the predicted updated geometry 1212 of the initial 3D model of the auxiliary component 1202, where the error surface 1206 has been adjusted to create the updated surface 1216, wherein the updated geometry better conforms to the auxiliary component well 1204 of the dental appliance than the initial 3D model of the auxiliary component. Figure 13A and Figure 13B As shown.

[0086] The methods described herein suitable for predicting the updated geometry of an initial 3D model of a dental accessory may include a trained model (algorithm), which is a trained machine learning algorithm (learning algorithm). The trained model may be described herein as a predictive model (“PM”), and specifically, if the trained model is suitable for predicting the updated geometry of the accessory (or the appliance described below), then the trained model is an over-curing predictive model (“OPM”) that compensates for over-curing of the accessory during the physical model manufacturing process (e.g., in the physical model).

[0087] One aspect of this disclosure relates to a method for training a machine learning model such that, once trained, the model is adapted to receive a new or initial 3D model of a dental aid as input and predict an updated geometry of the initial 3D model of the dental aid to conform to the aid well of the dental appliance.

[0088] Figure 14 An exemplary method 1300 is shown for training a machine learning (“ML”) algorithm to create a trained model that, once trained, is adapted to predict updated geometry of a 3D model of a dental accessory to conform to the attachment well of the dental appliance. Method 1300 includes, at step 1302, training the ML algorithm using input features and a training objective. Once trained, at step 1304, the trained model is adapted to predict updated geometry of an initial 3D model of the accessory.

[0089] The training model may include providing input features, including an initial 3D model of the accessory and a 3D model of the dental appliance, which has been indirectly manufactured on a 3D-printed physical model of the dental arch (e.g., a mold) based on the initial 3D model of the accessory. In this example, the geometry of the appliance well does not conform to the geometry of the initial 3D model of the accessory because the appliance is indirectly formed on a mold that includes an over-cured area of ​​the accessory. A machine learning algorithm can be trained using the input of the initial 3D model of the accessory and data (e.g., scans) of the indirectly manufactured 3D model of the dental appliance. Once trained, the model is adapted to receive the initial 3D model of the accessory and predict an updated geometry of the 3D model of the accessory to conform to the accessory well of the dental appliance. Thus, the trained model can predict the updated geometry, which will provide a better force system as part of orthodontic treatment.

[0090] Figure 15 An exemplary method 1400 for training an ML algorithm to create a trained model, once trained, is shown, which is adapted to predict updated geometry of an initial 3D model of a dental accessory to conform to the attachment well of a dental appliance. Method 1400 includes, at step 1402, providing multiple 3D models of the accessory and multiple 3D models of the indirectly formed dental appliance, each dental appliance corresponding to one of the multiple initial 3D models of the accessory. For example, step 1402 may include providing a 3D model of accessory 1202 from FIG. 13 and a corresponding 3D model of dental appliance 1204.

[0091] Method 1400 includes, at step 1404, identifying multiple sampling points on the error surface of the 3D model of the auxiliary component for each auxiliary component 3D model. For example, Figure 16A and 16B Multiple sampling points 1502 on the error surface 1501 are shown (only three are marked for clarity).

[0092] Method 1400 includes, at step 1406, identifying a plurality of training features for each of a plurality of sampling points. As described herein, the training features may include one or more measurements from the sampling points, which may include measurements relative to points on an initial 3D model. For example, the training features may include dimensions measured from each sampling point to other locations in one or more directions. Exemplary training features include measurements computed in the z-direction ( Figure 16C Shown and included Figure 18 (reference axis in) Figure 16A and Figure 16B The distance 1510 is represented as the dimension in the x-direction (in...). Figure 16A and Figure 16B (Entering and exiting pages), dimensions in the y-direction, such as in Figure 16A and Figure 16B The figure shows the surface normal measurement at a distance of 1514, and the distance to the tooth. Figure 16B The distance is shown as 1512. Other training features can also be used for training, and not all training features described in this paper must be used to train a specific model; this depends on the specific application of the method implemented. As used in this paper, the "z" direction refers to the direction along the longitudinal axis of the dental accessory (e.g., Figure 16A , Figure 16B and Figure 16C As shown), it corresponds to the longitudinal axis of the tooth to which the dental aid is configured to be bonded.

[0093] Method 1400 further includes, at step 1408, providing one or more target distances from the sampling point to the surface of the accessory well of the 3D model of the dental appliance for each sampling point, whereas in other methods, the target distances may be measured from the sampling point to a surface on the 3D model of an indirectly formed (e.g., thermoformed) accessory template (e.g., from a scan). The target distances may include some or all of the training feature dimensions. Figure 16B An exemplary target distance is shown, comprising a depth of 1512' in the z-direction (along the major axis of the auxiliary component in this example) measured from each sampling point to the surface of the auxiliary component well surface, and a surface normal measurement of 1514'. Figure 16B Only one sampling point is identified in the code, but training methods typically involve many points, such as hundreds of sampling points (e.g., between 200 and 500 sampling points).

[0094] Method 1400 creates a trained model with parameters that can predict the updated geometry of the initial 3D model of the dental aid upon receiving the initial 3D model of the dental aid to conform to the aid well of the dental appliance.

[0095] Any machine learning model in this paper can be a supervised model that is provided with one or more inputs and objectives, examples of which are provided in this paper.

[0096] Figure 17 An exemplary method 1600 executed by a trained model is shown (and can be implemented using one or more processors), such as according to Figure 15 Method 1400 trains the model. Method 1600 is a method for predicting the updated geometry of the initial 3D model of a dental accessory to conform to the attachment well of the dental appliance, and is... Figure 12Examples of specific implementations of the prediction method 1100 are provided. Method 1600 includes, at step 1602, receiving or generating an initial 3D model of a dental accessory, such as a CAD file including dental attachments. Method 1600 includes, at step 1604, identifying error surfaces on the initial 3D model 1503, such as… Figure 10 Error surface 904 in Figure 13A Error surface 1206 or Figure 16A Error surface 1501 in the middle. Method 1600 includes, at step 1606, determining a plurality of sampling points on the error surface, such as Figure 16A The sampling point 1502 shown is included. The prediction method 1600 includes, at step 1608, measuring one or more features of each of a plurality of sampling points on the error surface, such as any of the feature dimensions described herein (e.g., measurements in the z-direction, measurements in the x-direction, measurements in the y-direction, surface normal measurements, distance to the tooth).

[0097] The prediction method 1600 further includes, at step 1610, predicting the offset dimension for the sampling points based on the measurement characteristics of the sampling points on the error surface of the new 3D model of the dental aid, thereby creating an updated surface for the new 3D model. This updated surface can predict the configuration of indirectly formed template attachments and indirectly formed aid wells. The updated geometry of the 3D model of the dental aid (including the updated surface) facilitates a better force system for dental appliances and aids based on orthodontic treatment planning.

[0098] The predictive method presented in this paper provides an estimate or prediction of the geometry of actual appliance wells or other dental components. This can allow for greater flexibility in the fabrication of one or more dental components, while compensating for geometric differences and achieving better force systems based on orthodontic treatment.

[0099] The method for predicting the updated accessory geometry described herein may optionally further include predicting the variable geometry of the accessory, which may also be referred to herein as a glitter, glitter geometry, glitter layer, or composite layer, or similar derivatives thereof. During bonding, the dentist / technician follows standard orthodontic practice, which involves preparing the enamel surface (e.g., cleaning, polishing, and / or etching) and applying an adhesive (e.g., primer, resin, and / or binder) to bond the dental accessory to the tooth. This often results in material buildup between the tooth and the dental accessory (in the normal direction of the tooth surface). Figure 18 Both in the y-direction (as referred to in the text) and in the x-direction on the tooth surface, in Figure 18 (marked in the middle), rather than the original design scheme. Figure 18An accessory 1702 is shown, in this example a dental attachment, and a composite material 1705 between the tooth and the accessory, the composite material having a certain amount of material deposited on the tooth surface. Predicting the geometry of this glitter layer 1705 (including the height dimension y of the glitter layer in the direction perpendicular to the tooth surface 1705) allows the updated accessory geometry to take into account the composite material or glitter, and modifies the accessory geometry to compensate for the height of the composite material.

[0100] A method for predicting the updated geometry of an assistive device (which also predicts the flash geometry) can be a trained model trained with input features including flash features. For example, a scan can be generated from or received from a dental appliance that includes flash geometry. The input to the machine learning model can include multiple 3D models of the assistive device and multiple 3D models of the flash geometry. The objective can include the distance of the assistive device away from the teeth in the positive dimension, which can be considered as allowing the assistive device to compensate for the composite layer.

[0101] Additionally, indirect manufacturing processes (e.g., thermoforming) can result in indirectly formed dental appliances having geometries that do not precisely conform to the physical model of the dentition (e.g., SLA mold). For example, during thermoforming, polymer sheets may not completely wrap around or precisely conform to the physical model (e.g., SLA mold), which can lead to gaps near geometric intersections, observed as rounded corners. Methods for predicting updated geometries of 3D models of the dental aids described herein may include global rounding to simulate thermoforming errors in the appliance. Different materials have different thermoforming capabilities (such as EX15 and ST30), and the prediction methods described herein can modify one or more rounding radii to accommodate different materials.

[0102] The method described herein for predicting updated geometry may also include predicting rounding added to or attached to one or more surfaces of an initial 3D model due to manufacturing errors during the manufacturing process, where the dental appliance does not fully encompass or conform to a physical model of the dentition (e.g., a mold). Manufacturing errors may be based on material differences between the physical model of the dentition and the material on which the dental appliance is formed.

[0103] The method for predicting the updated geometry of the accessory also predicts the rounding added to the accessory. The method may be a trained model that is trained to predict the added rounding in response to an initial 3D model of the accessory.

[0104] Therefore, the method described herein for predicting the updated geometry of the initial 3D model of a dental aid can modify the error surface corresponding to the well surface that is predicted to deviate from the original design of the appliance, taking into account the increase in positive dimensions associated with the flash geometry, and / or the added rounding due to the manufacture of the dental appliance, thereby producing a better force system based on orthodontic treatment.

[0105] The methods described herein may include directly manufacturing dental aids in response to received instructions to directly manufacture dental aids based on updated geometry, which can be performed in... Figure 29 The manufacturing of auxiliary parts and / or appliances occurs in the dental auxiliary parts and / or appliance manufacturing system 2950. Manufacturing auxiliary parts may include removable templates that are directly manufactured integrally with dental auxiliary parts. Figure 19 An exemplary direct-manufacturing device 1900 is shown, which includes a plurality of attachments 1902 integrally formed with a template or locator 1904. The device 1900 also includes a removable component 1906 that facilitates easy removal from the attachments 1902, such that the template 1904 and the component 1906 can be removed once the attachments are secured to the teeth with the composite material.

[0106] Figure 19 Annex 1902 is generally shown as having a similar or identical geometry, but Annex 1902 may alternatively have a geometry based on other plans for orthodontic treatment. Figure 19 The device 1900 may include one or more attachments, optionally including attachments associated with each tooth.

[0107] Methods of manufacturing one or more dental aids may include directly manufacturing the dental aid without directly manufacturing the integral support structure coupled to the directly formed dental aid. For example... Figure 19 The accessory 1902 shown can be manufactured directly on its own without template 1904 or part 1906.

[0108] The direct manufacturing technologies described in this article may include layer-by-layer manufacturing technologies, and optionally 3D printing.

[0109] Figure 20Representative dental appliances that can be worn on teeth as part of any orthodontic treatment plan described herein are illustrated. In some examples, the dental appliance may include a housing (e.g., a continuous polymer housing or a segmented housing) having a tooth-receiving cavity that accommodates and optionally also resiliently repositions the tooth. The dental appliance or one or more parts thereof may be manufactured indirectly using a physical model of the tooth (such as a mold). For example, a dental appliance (e.g., a polymer appliance) may be formed using a physical model of the tooth and suitable sheets of polymer material. In some embodiments, the physical appliance may be manufactured directly from a digital model of the appliance, for example using additive manufacturing techniques (e.g., layer-by-layer). The dental appliance may fit on all or fewer teeth. The dental appliance may be specifically designed to accommodate a patient's teeth (e.g., the morphology of the tooth-receiving cavity matches the morphology of the patient's teeth) and may be manufactured based on a positive or negative mold of the patient's teeth generated by impressions, scanning, etc. Alternatively, the dental appliance may be a general-purpose appliance configured to accommodate teeth, but not necessarily shaped to match the morphology of a patient's teeth. In some cases, only some (or none) of the teeth housed by a dental appliance will be repositioned by the appliance, while other teeth can provide a base or anchoring area to hold the appliance in place when the appliance applies force to one or more of the repositioned teeth. In some cases, at some point during orthodontic treatment, the teeth will not be repositioned. The moved teeth can also serve as a base or anchor to hold the appliance in place while the patient wears it. Typically, no wires or other devices will be provided to hold the appliance in place on the teeth. However, in some cases, it may be desirable or necessary to provide separate attachments or other anchoring elements or aids 2004 on the teeth 2002, which have corresponding housings, wells, or orifices 2006 in the dental appliance, allowing the appliance to apply selected forces on the teeth. Exemplary appliances, including those used in the Invisalign® system, are described in numerous patents and patent applications of Alain Technologies, Inc. (including, for example, U.S. Patent Nos. 6,450,807 and 5,975,893) and on the company’s website accessible on the World Wide Web (e.g., see url “invisalign.com”). Examples of attachments suitable for use with orthodontic appliances that are mounted on the teeth are also described in the patents and patent applications of Alain Technologies, Inc., including, for example, U.S. Patent Nos. 6,309,215 and 6,830,450.

[0110] Auxiliary component 2004 is an example of an auxiliary component for which the method described herein can predict the updated geometry to conform to a dental appliance and can be directly manufactured according to the manufacturing method described herein.

[0111] Appliance 2000 may include auxiliary components (e.g., features, attachments, structures, devices, parts, etc.). Examples of such attachments include, but are not limited to, dental arch expanders, palatal expanders, double blocks, occlusal blocks, occlusal ramps, mandibular advancement splints, occlusal plates, bridges, hooks, brackets, headband tubes, springs, buffer tubes, palatal bars, frames, pin-tube devices, cheek shields, cheek arches, thread shields, lingual flanges and pads, lip pads or buffers, protrusions, depressions, etc.

[0112] While some methods described herein describe predicting updated geometry of a 3D model of a dental accessory to conform to the geometry of an accessory of a dental appliance (e.g., if the dental appliance is indirectly manufactured (or if the accessory and appliance are manufactured using any of the exemplary different manufacturing techniques described herein), this disclosure also relates to methods for predicting updated geometry of a 3D model of a dental appliance to conform to the geometry of a dental accessory. For example, the dental appliance may be directly manufactured, while one or more accessories may be indirectly manufactured, such as in conjunction with template attachments formed on a physical mold as described above, including references Figures 1 to 8 B. For example, template attachments can be indirectly formed on an SLA mold that has been 3D printed and includes one or more attachments with over-cured areas, as described above. Direct manufacturing techniques for manufacturing appliances can produce appliance auxiliary wells whose geometry does not match or is inconsistent with the corresponding dental auxiliary wells because the dental auxiliary wells are formed based on the mold shape of the auxiliary wells that include over-cured areas, such as... Figure 5C The example shown. Therefore, the predictive concepts in this paper are equally applicable to predicting the updated geometry of the initial 3D model of a dental appliance's accessory well to fit the dental accessory (or other surfaces of the appliance that the application may require).

[0113] Method 2100 is an exemplary method for forming a dental appliance, which can at least partially occur in Figure 29 In the treatment planning system 2930. Method 2100 includes, at step 2102, receiving or generating an initial 3D model of a dental appliance, wherein an example of a portion of the initial 3D model of the dental appliance is represented as Figure 25 Model 2304 in the text. The initial 3D model includes data configured to represent or render a 3D model, and can be... Figure 29 The treatment plan system 2930 is generated in part and is based on the use of Figure 29 Oral scan generated by the intraoral scanning system 2910.

[0114] Method 2100 includes, at step 2104, predicting an updated geometry of a 3D model of a dental appliance to conform to the dental aid. The updated geometry, as described herein, includes any type of adjustment to the initial 3D model, which is described in more detail herein as relating to the updated geometry of the initial 3D model of the predicted aid. Figure 27 An exemplary predicted updated geometry 2320 of an initial 3D model of a dental appliance is shown, wherein the updated geometry 2320 includes an updated surface 2310, which is predicted to conform to the geometry 2303 of the dental aid, which in this example includes an over-cured region 2305 (in... Figure 26 (marked in Chinese), as described in more detail in this article. Figure 27 An error surface 2309 of the initial 3D model of the appliance is shown, which in this example is updated to create the updated surface 2310. Figure 27 Several parallel arrows are also shown, indicating the general direction of the compression, where the error surface 2309 is adjusted to create an updated surface 2310 of the updated geometry 2320. The updated geometry more closely conforms to the accessory geometry because the accessory can be indirectly formed on a physical model of the dentition (e.g., thermoforming), thus creating a better force system between the appliance and the accessory as part of orthodontic treatment when the accessory is attached to the teeth and the directly manufactured appliance is worn on the patient's teeth.

[0115] Method 2100 includes, at step 2106, generating a digital representation of the dental appliance based on the updated geometry, which can occur Figure 29 In the treatment planning system 2930. Method 2100 may also optionally include, at step 2108, receiving direct manufacturing instructions based on updated geometry by a direct manufacturing machine, and in response to the received instructions, directly manufacturing dental appliances using the manufacturing machine according to the direct manufacturing instructions, which can... Figure 29 This occurs in the auxiliary parts and / or appliance manufacturing system 2950.

[0116] Figure 22 from Figure 21 Step 2104 in the diagram illustrates an exemplary method 2200 for predicting updated geometry. Method 2200 includes, at step 2202, identifying error surfaces on the initial 3D model of the dental appliance, such as... Figures 25-27Error surface 2309 in the document refers to a surface of the dental aid that is predicted to deviate from the original design 2302 of the dental aid. The predicted deviation of the aid surface from the original design may be due to variations in manufacturing techniques, several examples of which are provided herein. For example, as described herein, the predicted deviation may occur due to a manufacturing process that includes 3D printing a physical model of the patient's dentition, such as any mold described herein. As mentioned above, the deviation may be a result of over-curing during 3D printing, examples of which are found in… Figures 5A-5C and Figure 26 As shown in the image.

[0117] Method 2200 further includes, at step 2204, modifying the error surface of the 3D model of the dental appliance to create an updated surface, an example of which is... Figure 27 The updated surface 2310 is shown in the diagram. As described herein, a modified error surface refers to any type of adjustment to the error surface, including one or more of its shape, profile, or geometry, which may or may not result in a change in volume. Similarly, an updated surface as described herein refers to a surface that has any type of adjustment, modification, or change compared to the error surface.

[0118] Adjusting the error surface as described herein includes modifying some aspects of the error surface in at least one dimension. Adjusting the geometry of the error surface refers to any adjustment to the geometry of the error surface. For example, adjusting the geometry of the error surface may include modifying the geometry of one or more portions of the error surface without modifying the geometry of one or more other portions of the error surface, or modifying the first portion to a greater extent than the second portion.

[0119] In some embodiments, adjusting the error surface includes optionally extruding at least a portion of the error surface outward in a direction perpendicular to at least a portion of the error surface. For example, Figure 27 The diagram illustrates modifying the error surface 2309 by extruding it outwards in direction E. Extruding at least a portion of the error surface in direction "E" does not require modifying all points on the surface or moving all points on the surface the same distance. Figure 27 As shown, for example, some portions of error surface 2309 are adjusted to a greater extent in direction E than other portions of error surface 2309. For example, a more centrally located region of error surface 2309 may be adjusted further than a more laterally positioned portion of error surface 2309.

[0120] In some implementations, adjusting the error surface may include squeezing at least a portion of the error surface inward in a direction perpendicular to at least a portion of the error surface, or the adjustment may include any necessary adjustments to produce optimal engagement between the mating surfaces of the dental device.

[0121] In some embodiments, the updated geometry of the auxiliary well of the instrument defines a volume larger than the volume defined by the initial 3D model of the auxiliary well, while in other embodiments, the volume may be smaller or the same. For example, as Figure 27 As shown, the updated geometry 2320 of the tool well defines a larger volume than the volume defined by the geometry of the 3D model of the tool well.

[0122] The method for forming a dental appliance described herein may include predicting an updated geometry of a 3D model of the dental appliance to conform to an accessory. An updated geometry conforming to an accessory is a geometry that more closely conforms to or matches the geometry of the corresponding accessory compared to the 3D model of the dental appliance. Conformation, as described in this context, includes the corresponding accessory and appliance well geometry, which are configured more similarly to each other compared to the initial 3D model of the dental appliance and the geometry of the accessory. In this context, conformation includes the corresponding accessory well and accessory geometry, which apply a more desired force system based on the orthodontic treatment plan than the geometry of the initial 3D model of the dental appliance and accessory.

[0123] The methods suitable for predicting the updated geometry of an initial 3D model of a dental appliance in this paper may include trained models (algorithms) trained with machine learning algorithms (learning algorithms). Trained models may generally be described in this paper as predictive models (PM) or over-fixed predictive models (OPM), particularly if the trained model is suitable for predicting the updated geometry of a dental appliance, compensating for over-fixation of the physical model of the accessory.

[0124] One aspect of this disclosure relates to a method for training a machine learning algorithm such that, once trained, the model is adapted to predict the updated geometry of an initial 3D model of a dental appliance to conform to the geometry of the accessory.

[0125] Figure 23 An exemplary method 2300 is shown for training a machine learning (“ML”) algorithm to create a trained model adapted to predict the updated geometry of a new initial 3D model of a dental appliance to conform to the aid. Method 2300 includes, at step 2302, training the ML algorithm with input features and a training objective. Once trained, at step 2304, the trained model is adapted to predict the updated geometry of the dental appliance based on the new initial 3D model of the dental appliance.

[0126] Methods for training the model may include providing input features, including a 3D model of a dental appliance and model data (e.g., scans) of an accessory that has been indirectly manufactured (e.g., thermoformed) on a physical model of the dentition (e.g., a mold), where the mold is 3D printed based on the 3D model of the accessory. A machine learning algorithm can be trained using the input of an initial 3D model of the appliance and the 3D model data (e.g., scans) of the indirectly manufactured accessory. The trained model is then adapted to receive a new initial 3D model of the dental appliance and predict the updated geometry of the appliance's 3D model to conform to the accessory.

[0127] Figure 24 An exemplary method 2400 for training an ML algorithm to create a trained model, which, once trained, is adapted to predict updated geometry of a new initial 3D model of a dental appliance (e.g., an accessory well) to conform to the accessory. Method 2400 includes, at step 2402, providing multiple 3D models of the dental appliance and multiple 3D models (e.g., scans) of the accessory, each dental appliance corresponding to one of the multiple 3D models of the accessory. For example, step 2402 may include providing... Figure 29 The treatment planning system 2930 generates 3D models of instruments, and can be used with Figure 29 The intraoral scanning system 2910 in the middle obtains a scan of the auxiliary parts for indirect manufacturing.

[0128] Method 2400 includes, at step 2404, identifying, for each of the 3D models of the appliance, multiple sampling points on the error surface of the 3D model of the appliance, an example of which is described herein for the error surface of an auxiliary component.

[0129] Method 2400 includes, in step 2406, identifying multiple training features for each of a plurality of sampling points. The training features, as described herein, may include one or more measurements from the sampling points, which may include measurements of points on an initial 3D model relative to the dental appliance well. Training features may include one or more of dimensions in the z-direction, dimensions in the y-direction (such as surface normal measurements), dimensions in the x-direction, or distances to teeth, and other training features may also be used. Depending on the desired application, not all training features must be used to train the model.

[0130] Method 2400 further includes, at step 2408, providing one or more target distances from the sampling point to the surface of the 3D model of the aid for each sampling point. The target distances can be measured in some or all training feature directions or even in alternative directions.

[0131] Method 2400 creates a trained model with parameters that can predict the updated geometry of the initial 3D model of a dental appliance to conform to the accessory when a new initial 3D model of the dental appliance is received.

[0132] Figure 28 An exemplary method 2800 that can be executed by a trained model is shown, such as according to Figure 24 Method 2400 trains the model. Method 2800 is a method for predicting the updated geometry of the initial 3D model of the dental appliance's accessory well to conform to the accessory, and is... Figure 22 An example of a specific implementation of the prediction method 2200. Method 2800 includes, at step 2802, receiving an initial 3D model of a dental appliance, which can be... Figure 29 The treatment plan is generated in the treatment planning system 2930. Method 2800 includes, at step 2804, identifying error surfaces on the initial 3D model, such as... Figures 25-27 Error surface 2309 in the error surface. Method 2800 includes, at step 2806, determining a plurality of sampling points on the error surface. Prediction method 2800 includes, at step 2808, measuring one or more features of each of the plurality of sampling points on the error surface, such as any feature size described herein (e.g., depth in the z-direction, a measurement in the x-direction, a measurement in the y-direction such as a surface normal measurement, or a distance to a tooth).

[0133] The prediction method 2800 further includes, at step 2810, predicting the offset dimensions of the sampling points based on the measurement characteristics of the sampling points on the error surface of the new 3D model of the dental appliance, thereby creating an updated surface of the new 3D model of the dental appliance that predicts the geometry of the accessory. Directly manufactured appliances, once their updated geometry is predicted, can better predict or estimate template attachments (e.g., thermoformed attachments) formed on a physical model of the dentition. The updated geometry of the 3D model of the dental appliance, including the updated surface, facilitates a better force system for orthodontic-based dental appliances and accessories.

[0134] The method described in this paper can predict the updated geometry of auxiliary wells in dental appliances, thereby providing an estimate or prediction of the auxiliary surface. This can allow for more manufacturing options to compensate for geometric differences and achieve better force systems, which are described in more detail in this paper.

[0135] Typically, these methods and apparatuses (systems, devices, etc., including software, hardware, and / or firmware) can be used in one or more parts of a dental computing environment, including as part of an intraoral scanning system, a physician system, a treatment planning (e.g., a technician) system, a patient system, and / or a manufacturing system. In particular, these methods and apparatuses can be used as part of a treatment planning system 2930 and an accessory and / or appliance manufacturing system 2950. For example, a method for predicting an updated geometry of one or more accessories or appliances can occur in the treatment planning system 2930, and a method for manufacturing accessories and / or appliances can occur in the accessory and / or appliance manufacturing system 2950.

[0136] Figure 29 The diagram illustrates a variant of a computing environment 2900 that can generate one or more orthodontic treatment plans specific to a patient and manufacture dental aids and appliances that, under the guidance of a dental professional, can complete the treatment plan to treat the patient. Figure 29 The example computing environment 2900 shown includes an intraoral scanning system 2910, a physician system 2920, a treatment planning system 2930 (e.g., a technician system), a patient system 2940, an assistive device and / or appliance manufacturing system 2950, ​​and a computer-readable medium 2960. Each of these systems can be equivalently referred to as a subsystem of the entire system (e.g., the computing environment). Although shown as discrete systems, some or all of these systems can be integrated and / or combined. In some variations, the computing environment (dental computing system) 2900 may include only one or a subset of these systems (which can also be referred to as a subsystem of the entire system 2900). As mentioned above, one or more of these systems can be combined or integrated with one or more other systems (subsystems), for example, the patient system and physician system may be part of a remote server accessible by a physician and / or patient interface. The computer-readable medium 2960 may be partitioned among all or some of the systems (subsystems); for example, the treatment planning system and the assistive device and / or appliance manufacturing system may be part of the same subsystem and may be on the computer-readable medium 2960. Furthermore, each of these systems can be further divided into subsystems or components that can be physically distributed (e.g., between local and remote processors) or integrated.

[0137] An intraoral scanning system may include an intraoral scanner and one or more processors for processing images. For example, an intraoral scanning system 2910 may include optics 2911 (e.g., one or more lenses, filters, mirrors, etc.), a processor 2912, a memory 2913, a scan capture module 2914, and a result simulation module 2915. Typically, the intraoral scanning system 2910 can capture one or more images of a patient's dentition. The use of the intraoral scanning system 2910 can be in a clinical setting (such as a doctor's office) or in an environment of the patient's choice (e.g., the patient's home). In some cases, the operation of the intraoral scanning system 2910 may be performed by an intraoral scanner, a dental camera, a mobile phone, or any other feasible device.

[0138] Optical components 2911 may include one or more lenses and optical sensors to capture reflected light, particularly reflected light from the patient's dentition. Scan capture module 2914 may include instructions (such as non-transitory computer-readable instructions) that may be stored in memory 2913 and executed by processor 2912 to control the capture of any number of images of the patient's dentition.

[0139] For example, the outcome simulation module 2915, which may be part of the intraoral scanning system 2910, may include instructions for simulating tooth positions based on the treatment plan. Alternatively or additionally, in some examples, the outcome simulation module 2915 may import tooth numbering information from a 3D model onto a 2D image to aid in determining the outcome simulation.

[0140] Any component system or subsystem of the dental computing environment 2900 can access or use a 3D model of the patient's dentition generated by the methods and apparatus described herein. For example, the physician system 2920 may include a treatment management module 2921 and an intraoral state capture module 2922 that can access or use the 3D model. The physician system 2920 may provide a "physician-oriented" interface to the computing environment 2900. The treatment management module 2921 can perform any operations that enable a physician or other clinician to manage the treatment of any patient. In some examples, the treatment management module 2921 may provide visualization and / or simulation of the patient's dentition relative to a treatment plan.

[0141] The intraoral state capture module 2922 can provide clinicians with images of the patient's dentition via the physician system 2920. These images can be captured by the intraoral scanning system 2910 and may also include simulated images of tooth movement based on the treatment plan.

[0142] In some examples, the treatment management module 2921 may enable the physician to modify or revise the treatment plan, particularly when images provided by the intraoral status capture module 2922 indicate that the movement of the patient's teeth may not conform to the treatment plan. The physician system 2920 may include one or more processors configured to execute any feasible non-transitory computer-readable instructions to perform any feasible operations described herein.

[0143] Alternatively or additionally, the treatment planning system 2930 may include any of the methods and devices described herein. The treatment planning system 2930 may include a scan processing / refinement module 2931, a segmentation module 2932, a phased module 2933, a treatment monitoring module 2934, and a treatment plan database 2935. Typically, the treatment planning system 2930 can determine a treatment plan for any feasible patient. The scan processing / refinement module 2931 may receive or acquire dental scans (such as scans from an intraoral scanning system 2910) and may process the scans to “clean them up” by removing scan errors and, in some cases, enhancing the detail of the scan images. The treatment planning system 2930 may perform segmentation. For example, the treatment planning system may include a segmentation module 2932, which may segment a dental model into individual parts including individual teeth, gingiva, jawbone, etc. In some cases, the dental model may be based on scan data from the scan processing / refinement module 2931.

[0144] The phased module 2933 can determine the different stages of the treatment plan. Each stage can correspond to a different dental appliance. The phased module 2933 can also determine the final position of the patient's teeth based on the treatment plan. Therefore, the phased module 2933 can determine some or all of the patient's orthodontic treatment plan. In some examples, the phased module 2933 can simulate the movement of the patient's teeth according to the different stages of the patient's treatment plan.

[0145] Treatment monitoring module 2934 can monitor the progress of orthodontic treatment planning. In some examples, treatment monitoring module 2934 can provide clinicians with an analysis of the progress of treatment planning. Orthodontic treatment plans can be stored in treatment plan database 2935. Although not shown here, treatment planning system 2930 may include one or more processors configured to execute any feasible non-transitory computer-readable instructions to perform any feasible operations described herein.

[0146] The patient system 2940 may include a treatment visualization module 2941 and an intraoral state capture module 2942. Typically, the patient system 2940 may provide a "patient-oriented" interface to the computing environment 2900. The treatment visualization module 2941 enables the patient to visualize how the orthodontic treatment plan is progressing and also visualizes predicted outcomes (e.g., the final position of the teeth).

[0147] In some examples, the patient system 2940 may capture a dentition scan for treatment visualization module 2941 via an intraoral state capture module 2942. The intraoral state capture module enables the patient to capture his or her own dentition via an intraoral scanning system 2910. Although not shown here, the patient system 2940 may include one or more processors configured to execute any feasible non-transitory computer-readable instructions to perform any feasible operations described herein.

[0148] The assistive device and / or appliance manufacturing system 2950 may include an assistive device and / or appliance manufacturing machine 2951, a processor 2952, a memory 2953, and an assistive device and / or appliance generation module 2954. Typically, the assistive device and / or appliance manufacturing system 2950 can directly or indirectly manufacture assistive devices and / or orthodontic appliances to realize orthodontic treatment plans. In some examples, orthodontic treatment plans may be stored in a treatment plan database 2935.

[0149] The assistive device and / or appliance manufacturing machine 2951 may include any feasible tools or equipment capable of manufacturing any suitable assistive device and / or dental appliance. The appliance generation module 2954 may include any non-transitory computer-readable instructions that, when executed by the processor 2952, instruct the assistive device and / or appliance manufacturing machine 2951 to produce one or more assistive devices and / or dental appliances. The memory 2953 may store data or instructions for use by the processor 2952. In some examples, the memory 2953 may temporarily store treatment plans, dental models, or intraoral scans.

[0150] Computer-readable medium 2960 may include some or all of the elements described herein with respect to computing environment 2900. Computer-readable medium 2960 may include non-transitory computer-readable instructions that, when executed by a processor, can provide the functionality of any apparatus, machine, or module described herein.

[0151] This disclosure contains the following terms.

[0152] Clause 1. A method of forming a dental aid, comprising: receiving or generating an initial three-dimensional (“3D”) model of the dental aid by a processor, the initial 3D model having an initial geometry; predicting an updated geometry of the initial 3D model of the dental aid by the processor to conform to an aid well of a dental appliance, wherein predicting the updated geometry includes: identifying error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to surfaces of the aid well that are predicted to deviate from an original design of the dental appliance; adjusting the error surfaces of the 3D model of the dental aid to create updated surfaces, wherein the updated geometry defines a modified geometry that differs from the initial geometry of the 3D model of the dental aid; and generating a digital representation of the dental aid based on the updated geometry.

[0153] Clause 2. The method according to Clause 1, wherein the initial 3D model is an initial 3D model of the dental attachment.

[0154] Clause 3. The method according to Clause 1 or Clause 2, wherein the error surface corresponds to the surface of the auxiliary well that is predicted to deviate based on manufacturing technology.

[0155] Clause 4. The method described in Clause 3, wherein the surface of the well of the dental aid is predicted to deviate based on a manufacturing technology different from that used in the manufacturing of the dental aid.

[0156] Clause 5. The method described in Clause 4, wherein the different manufacturing techniques include printing the orientation differences of the dental aids and the dental appliances.

[0157] Clause 6. The method according to Clause 5, wherein the difference in orientation includes opposite orientations, wherein the dental appliances are printed from bottom to top, and wherein the dental aids are printed from top to bottom.

[0158] Clause 7. The method described in Clause 5, wherein the difference in orientation includes a difference in printing angle, such as a 45-degree difference or a 90-degree difference.

[0159] Clause 8. The method described in Clause 4, wherein the different manufacturing techniques include the difference between indirect manufacturing and direct manufacturing.

[0160] Clause 9. The method according to Clause 3, wherein the manufacturing technology includes 3D printing of a physical model of the patient’s dentition, and the deviation is the result of different 3D printing technologies relative to the physical model.

[0161] Clause 10. The method according to Clause 9, including the dental appliance of the auxiliary well being indirectly formed on the physical model.

[0162] Clause 11. The method according to any one of Clauses 1-10, wherein adjusting the error surface includes changing the geometry of the error surface.

[0163] Clause 12. The method according to Clause 11, wherein adjusting the error surface includes extruding at least a portion of the error surface outward from a plane perpendicular to the error surface.

[0164] Clause 13. The method according to Clause 11 or Clause 12, wherein adjusting the error surface includes squeezing a portion of the error surface inward.

[0165] Clause 14. The method according to any one of Clauses 1-13, wherein adjusting the error surface includes changing one or more of the surface, shape, and profile of the error surface.

[0166] Clause 15. The method according to any one of Clauses 1-14, wherein the volume defined by the updated geometry is larger than the volume defined by the initial geometry.

[0167] Clause 16. The method according to any one of Clauses 1-14, wherein the volume defined by the updated geometry is the same as the volume defined by the initial geometry.

[0168] Clause 17. The method according to any one of Clauses 1-16, wherein predicting the updated geometry further comprises determining a plurality of sampling points on an error surface of an initial 3D model of the dental aid, and measuring one or more features of each of the sampling points.

[0169] Clause 18. The method according to Clause 17 further includes predicting, based on one or more measurement features, a sampling point offset distance of each of the plurality of sampling points from the error surface, and using the sampling point offset distance to modify the error surface to create the updated surface.

[0170] Clause 19. The method according to Clause 17 or Clause 18, wherein the one or more features of each of the sampling points include one or more of the following: depth along the major axis in the z direction, dimension in the x direction, dimension in the y direction such as a surface normal measurement, or distance to the tooth.

[0171] Clause 20. The method according to any one of Clauses 1-19, wherein an updated geometry of the 3D model of the dental aid creates a better force system between the dental aid and the dental appliance for orthodontic treatment, compared to an initial geometry of the 3D model of the dental aid and the force system between the dental appliance and the dental appliance.

[0172] Clause 21. The method according to any one of Clauses 1-20, wherein the dental appliance is an orthodontic appliance, a palatal expander, or a retainer.

[0173] Clause 22. The method according to any one of Clauses 1-21 further includes sending the digital representation to a client device.

[0174] Clause 23. The method according to any one of Clauses 1-22 further includes displaying a visual representation of the digital representation on a user interface.

[0175] Clause 24. The method according to any one of Clauses 1-22 further includes manufacturing the dental aid based on the updated geometry.

[0176] Clause 25. The method according to any one of Clauses 1-24 further comprises: outputting direct manufacturing instructions to manufacture a dental accessory based on the updated geometry; and receiving the direct manufacturing instructions via a direct manufacturing machine, and directly manufacturing the dental accessory using the manufacturing machine according to the received instructions.

[0177] Clause 26. The method according to Clause 25, wherein directly manufacturing the dental aid includes directly manufacturing a removable locator integrally formed with the dental aid.

[0178] Clause 27. The method according to Clause 26, wherein directly manufacturing the dental aid further comprises directly manufacturing a plurality of dental aids, each dental aid integrally formed with the removable locator, each of the plurality of dental aids including an updated geometry different from the corresponding initial 3D model data of the dental aid.

[0179] Clause 28. The method according to Clause 27, wherein directly manufacturing the dental aid includes directly manufacturing the dental aid without directly manufacturing an integral support structure coupled to the directly formed dental aid.

[0180] Clause 29. The method described in Clause 25, wherein direct manufacturing of the dental aid may optionally include additive or subtractive processes.

[0181] Clause 30. The method according to any one of Clauses 1-29, wherein predicting the updated geometry of the 3D model of the dental aid comprises predicting the updated geometry using a trained machine learning algorithm, the trained machine learning algorithm having been trained to identify error surfaces on an initial 3D model of the dental aid and modify the error surfaces to create the updated surfaces.

[0182] Clause 31. The method according to Clause 30, wherein the machine learning algorithm has been further trained to identify multiple sampling points on the error surface and predict the offset distance of the sampling points to modify the error surface of the 3D model of the dental aid, thereby creating an updated surface.

[0183] Clause 32. The method according to any one of Clauses 1-31, wherein predicting the updated geometry of the 3D model of the dental aid further includes predicting a flash geometry between the tooth and the aid, wherein the flash geometry includes a height y dimension perpendicular to the tooth surface and optionally includes an x ​​dimension in a direction parallel to the tooth surface.

[0184] Clause 33. The method according to any one of Clauses 1-32, wherein predicting the updated geometry of the 3D model of the dental aid further includes predicting rounding or smoothing added to one or more surfaces of the initial 3D model due to manufacturing errors.

[0185] Clause 34. The method according to Clause 33, wherein the predicted addition of rounding is based on the predicted addition of rounding caused by the manufacturing process of dental appliances not being fully encased in the physical model of the dentition.

[0186] Clause 35. The method according to Clause 33, wherein the manufacturing error is based on the material difference between the physical model of the dentition and the material of the dental appliance.

[0187] Clause 36. A method of forming a dental aid, comprising: manufacturing a dental aid using a direct manufacturing machine, wherein the direct manufacturing machine receives a digital representation of the dental aid generated by the following steps: receiving or generating an initial three-dimensional (“3D”) model of the dental aid by a processor, the initial 3D model having an initial geometry; predicting an updated geometry of the initial 3D model of the dental aid by the processor to conform to an aid well of a dental appliance, wherein predicting the updated geometry includes: identifying error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to surfaces of the aid well predicted to deviate from the original design of the dental appliance; adjusting the error surfaces of the 3D model of the dental aid to create an updated surface, wherein the updated geometry defines a modified geometry different from the initial geometry of the 3D model of the dental aid; and generating a digital representation of the dental aid based on the updated geometry.

[0188] Clause 37. A method of forming a dental appliance, comprising: receiving or generating an initial three-dimensional (“3D”) model of the dental appliance by a processor, the initial 3D model having an initial geometry; predicting an updated geometry of the initial 3D model of the dental appliance by the processor to conform to a dental aid; wherein predicting the updated geometry includes: identifying error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental aid predicted to deviate from an original design of the dental aid; adjusting the error surfaces of the 3D model of the dental appliance to create updated surfaces, wherein the updated geometry defines a modified geometry different from the initial 3D model of the dental appliance; and generating a digital representation of the dental appliance based on the updated geometry.

[0189] Clause 38. The method according to Clause 37, wherein the initial 3D model is an initial 3D model of an orthodontic appliance, palatal expander, or retainer.

[0190] Clause 39. The method according to Clause 36 or Clause 37, wherein the error surface corresponds to a surface of the dental aid that is predicted to deviate based on manufacturing techniques.

[0191] Clause 40. The method according to Clause 39, wherein the surface of the dental aid is predicted to deviate based on a manufacturing technology different from that used to manufacture the dental appliance.

[0192] Clause 41. The method according to Clause 40, wherein the different manufacturing techniques include printing the orientation differences of the dental aids and the dental appliances.

[0193] Clause 42. The method according to Clause 41, wherein the difference in direction is opposite, and optionally wherein the dental aids are printed from bottom to top, and wherein the dental appliances are printed from top to bottom.

[0194] Clause 43. The method described in Clause 41, wherein the difference in direction includes a difference in the relative angle of the print, optionally a 180-degree difference, optionally a 45-degree difference, or optionally a 90-degree difference.

[0195] Clause 44. The method described in Clause 40, wherein the different manufacturing techniques include the difference between indirect manufacturing and direct manufacturing.

[0196] Clause 45. The method according to Clause 39, wherein the manufacturing technology includes 3D printing the dental appliance, and the predicted deviation is the result of different 3D printing technologies occurring during the 3D printing of a physical model including the dental appliance.

[0197] Clause 46. The method according to any one of Clauses 37-45, wherein the auxiliary component is indirectly formed on a physical model of the dental arch.

[0198] Clause 47. The method according to Clause 46, wherein adjusting the error surface includes changing the geometry of the error surface.

[0199] Clause 48. The method according to Clause 46, wherein adjusting the error surface includes extruding at least a portion of the error surface outward.

[0200] Clause 49. The method according to Clause 47 or Clause 48, wherein adjusting the error surface includes squeezing a portion of the error surface inward.

[0201] Clause 50. The method according to any one of Clauses 37-49, wherein adjusting the error surface includes changing one or more of the surface, shape, and profile of the error surface.

[0202] Clause 51. The method according to any one of Clauses 37-50, wherein the volume defined by the updated geometry is larger than the volume defined by the initial geometry.

[0203] Clause 52. The method according to any one of Clauses 36-49, wherein the volume defined by the updated geometry is the same as the volume defined by the initial geometry.

[0204] Clause 53. The method according to any one of Clauses 37-52, wherein predicting the updated geometry further comprises determining a plurality of sampling points on an error surface of an initial 3D model of the dental appliance, and measuring one or more features of each of the sampling points.

[0205] Clause 54. The method according to Clause 53 further includes predicting, based on one or more measurement features, a sampling point offset distance of each of the plurality of sampling points from the error surface, and using the sampling point offset distance to modify the error surface to create an updated surface.

[0206] Clause 55. The method according to Clause 53 or Clause 54, wherein the one or more features of each of the sampling points include one or more of the following: depth along the longitudinal axis of the dental aid, dimension in the x-direction, dimension in the y-direction, surface normal measurement, or distance to the tooth.

[0207] Clause 56. The method according to any one of Clauses 37-55, wherein an updated geometry of the 3D model of the dental appliance facilitates a better force system between the dental appliance and the accessory based on orthodontic treatment, compared to an initial geometry of the 3D model of the dental accessory and the force system between the accessory and the accessory.

[0208] Clause 57. The method according to any one of Clauses 47-56, wherein the dental aid is a dental attachment or other engagement feature.

[0209] Clause 58. The method according to any one of Clauses 37-57 further includes sending the digital representation to a client device.

[0210] Clause 59. The method according to any one of Clauses 37-58 further includes displaying a visual representation of the digital representation on a user interface.

[0211] Clause 60. The method according to any one of Clauses 37-58 further includes manufacturing the dental appliance based on the updated geometry.

[0212] Clause 61. The method according to any one of Clauses 37-60 further includes receiving a direct manufacturing instruction from a direct manufacturing machine, and directly manufacturing the dental appliance using the manufacturing machine based on the received instruction.

[0213] Clause 62. The method according to Clause 61, wherein directly manufacturing the dental appliance includes additive or subtractive manufacturing processes.

[0214] Clause 63. The method according to Clause 62, wherein predicting the updated geometry of the 3D model of the dental appliance comprises predicting the updated geometry using a trained machine learning algorithm, the trained machine learning algorithm having been trained to identify error surfaces on an initial 3D model of the dental appliance and modify the error surfaces of the 3D model of the dental appliance to create the updated surface of the dental appliance.

[0215] Clause 64. The method according to Clause 63, wherein the machine learning algorithm has been further trained to identify multiple sampling points on the error surface and predict the offset distance of the sampling points to modify the error surface of the 3D model of the dental appliance, thereby creating the updated surface.

[0216] Clause 65. A method for training a machine learning prediction model to predict an updated geometry of a three-dimensional (“3D”) model of a dental aid to conform to an aid well of a dental appliance, comprising: providing a plurality of 3D models of dental aids, each of the plurality of 3D models of dental aids including an error surface; providing a plurality of 3D models of dental appliances, each of the plurality of 3D models of dental appliances including an aid receiving well, wherein each of the plurality of 3D models of dental aids is associated with a corresponding aid receiving well of one of the plurality of 3D models of dental appliances; identifying a plurality of sampling points on each error surface; identifying a plurality of training features associated with each of the plurality of sampling points; and providing one or more target distances from each of the plurality of sampling points to a surface of the aid receiving well to train the prediction model using the plurality of features associated with each of the plurality of sampling points and the target distances, wherein the trained prediction model is adapted to receive an initial 3D model of the dental aid as input and, based on the initial 3D model of the dental aid, predict an updated geometry of the 3D model of the dental aid to conform to an aid well of the dental appliance.

[0217] Clause 66. A method for training a machine learning prediction model to predict an updated geometry of a three-dimensional (“3D”) model of a dental appliance to conform to an accessory, comprising: providing 3D models of a plurality of dental appliances, each of the plurality of 3D models of dental appliances including an error surface in an accessory well; providing 3D models of a plurality of dental accessories, wherein each of the plurality of 3D models of dental accessories is associated with a corresponding accessory receiving well of one of the plurality of 3D models of dental appliances; identifying a plurality of sampling points on each error surface; identifying a plurality of features associated with each of the plurality of sampling points; and providing one or more target distances from each of the plurality of sampling points to a surface of the accessory to train the prediction model using the plurality of features associated with each of the plurality of sampling points and the target distances, wherein the trained prediction model is adapted to receive an initial 3D model of the dental appliance as input and, based on the initial 3D model of the dental appliance, predict an updated geometry of the 3D model of the dental appliance to conform to an accessory.

[0218] Clause 67. A system comprising: one or more processors; and a memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: receiving or generating an initial three-dimensional (“3D”) model of a dental aid having an initial geometry by the processors; predicting an updated geometry of the 3D model of the dental aid to conform to an aid well of a dental appliance by the processors, wherein predicting the updated geometry comprises: identifying error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to surfaces of the aid well predicted to deviate from the original design of the dental appliance; modifying the error surfaces of the 3D model of the dental aid to create updated surfaces, wherein the updated geometry defines a modified geometry different from the initial geometry of the 3D model of the dental aid; and generating a digital representation of the dental aid based on the updated geometry.

[0219] Clause 68. A system comprising: one or more processors; a memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: receiving or generating an initial three-dimensional (“3D”) model of a dental appliance, the initial 3D model having an initial geometry; predicting an updated geometry of the initial 3D model of the dental appliance by the processor to conform to a dental accessory; wherein predicting the updated geometry comprises: identifying error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental accessory predicted to deviate from an original design of the dental accessory; modifying the error surfaces of the 3D model of the dental appliance to create updated surfaces, wherein the updated geometry defines a modified geometry of the dental accessory and the dental appliance that differs from the initial 3D model of the dental appliance; and generating a digital representation of the dental appliance based on the updated geometry.

[0220] Clause 69. A method of forming a dental aid, comprising: receiving or generating an initial three-dimensional (“3D”) model of the dental aid by a processor, the initial 3D model having an initial geometry; predicting an updated geometry of the initial 3D model of the dental aid by the processor, wherein predicting the updated geometry includes: identifying error surfaces on the initial 3D model of the dental aid; adjusting the error surfaces of the 3D model of the dental aid to create an updated surface different from the error surfaces, such that the updated geometry differs from the initial geometry; and generating a digital representation of the dental aid based on the updated geometry.

[0221] Clause 70. The method according to Clause 69, wherein the error surface corresponds to the surface of the auxiliary well that is predicted to deviate from the original design of the dental appliance.

[0222] Clause 71. The method according to Clause 69, wherein adjusting the error surface of the initial 3D model includes predicting over-cured geometry associated with the initial 3D model and adjusting the error surface of the 3D model to create the updated geometry, thereby compensating for the predicted over-cured geometry.

[0223] Clause 72. The method according to Clause 71, wherein manufacturing a dental aid based on the updated geometry includes manufacturing a dental aid having a geometry that conforms to or is similar to the initial 3D model.

Claims

1. A method of forming a dental accessory, comprising: The processor receives or generates an initial 3D model of a dental aid, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the initial 3D model of the dental aid to conform to the aid's well in the dental appliance. The predicted updated geometry includes: Identify error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to the surfaces of the aid wells that are predicted to deviate from the original design of the dental appliance; Adjust the error surfaces of the 3D model of the dental aid to create an updated surface. The updated geometry is defined as a modified geometry that differs from the initial geometry of the 3D model of the dental aid; and A digital representation of the dental aid is generated based on the updated geometry.

2. The method according to claim 1, wherein, The generation process includes: receiving a digital representation of the dental aid based on the updated geometry via a direct manufacturing machine, and manufacturing the dental aid using the manufacturing machine according to the digital representation.

3. The method according to claim 1, wherein, The initial 3D model is the initial 3D model of the dental attachments.

4. The method according to claim 2 or claim 3, wherein, The error surface corresponds to the surface of the auxiliary well that is predicted to deviate based on the manufacturing technology specific to the direct manufacturing machine.

5. The method according to claim 2, wherein, Based on a manufacturing technology different from that used for the dental aid, it is predicted that the surface of the well in the aid will deviate.

6. The method according to claim 3, wherein, The different manufacturing techniques include differences in the orientation of the printed dental aids and dental appliances.

7. The method according to claim 4, wherein, The differences in orientation include opposite orientations, optionally wherein the dental appliances are printed from bottom to top, and wherein the dental aids are printed from top to bottom.

8. The method according to claim 4, wherein, The differences in orientation include differences in printing angle, such as a 45-degree difference or a 90-degree difference.

9. The method according to claim 3, wherein, The different manufacturing technologies include the differences between indirect and direct manufacturing.

10. The method according to claim 4, wherein, The manufacturing technology includes 3D printing of a physical model of the patient's dentition, and the deviation is the result of different 3D printing technologies relative to the physical model.

11. The method according to claim 9, wherein, The dental appliance, including the auxiliary well, is indirectly formed on the physical model.

12. The method according to any one of claims 1-11, wherein, Adjusting the error surface includes changing the geometry of the error surface.

13. The method according to claim 12, wherein, Adjusting the error surface includes extruding at least a portion of the error surface outward from a plane perpendicular to the error surface.

14. The method according to claim 11 or claim 13, wherein, Adjusting the error surface includes squeezing a portion of the error surface inward.

15. The method according to any one of claims 1-14, wherein, Predicting the updated geometry also includes: determining multiple sampling points on the error surface of the initial 3D model of the dental aid, and measuring one or more features of each of the sampling points.

16. The method according to any one of claims 1-15, wherein, The dental appliances are orthodontic appliances, palatal expanders, or retainers.

17. A method of forming a dental accessory, comprising: Dental aids are manufactured using a direct manufacturing machine, wherein the direct manufacturing machine receives a digital representation of the dental aid generated in the following manner: The processor receives or generates an initial 3D model of a dental aid, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the initial 3D model of the dental aid to conform to the aid's well in the dental appliance. The predicted updated geometry includes: Identify error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to the surfaces of the aid wells that are predicted to deviate from the original design of the dental appliance; Adjust the error surfaces of the 3D model of the dental aid to create an updated surface. The updated geometry is defined as a modified geometry that differs from the initial geometry of the 3D model of the dental aid; and A digital representation of the dental aid is generated based on the updated geometry.

18. A method of forming a dental appliance, comprising: The processor receives or generates an initial 3D model of a dental appliance, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the initial 3D model of the dental appliance to conform to the dental aid. The predicted updated geometry includes: Identify error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental appliance that are predicted to deviate from the original design of the dental appliance; Adjust the error surfaces of the 3D model of the dental instrument to create an updated surface. The updated geometry is defined as a modified geometry that differs from the initial 3D model of the dental instrument; and A digital representation of the dental appliance is generated based on the updated geometry.

19. A method for training a machine learning prediction model to predict the updated geometry of a 3D model of a dental accessory to conform to the accessory well of a dental appliance, comprising: Provide 3D models of multiple dental aids, each of the multiple dental aids 3D models including an error surface; Provided are 3D models of a plurality of dental appliances, each of the 3D models of the plurality of dental appliances including an accessory receiving well, wherein each of the 3D models of the plurality of dental accessories is associated with a corresponding accessory receiving well of one of the 3D models of the plurality of dental appliances; Identify multiple sampling points on each error surface; Identify multiple training features associated with each of the plurality of sampling points; and One or more target distances are provided from each of the plurality of sampling points to the surface of the auxiliary component receiving well, in order to train a prediction model using multiple features associated with each of the plurality of sampling points and the target distances. The trained prediction model is adapted to receive an initial 3D model of a dental aid as input, and based on the initial 3D model of the dental aid, predict an updated geometry of the 3D model of the dental aid to conform to the aid well of the dental appliance.

20. A method for training a machine learning prediction model to predict the updated geometry of a 3D model of a dental appliance to conform to the accessory, comprising: Provide 3D models of multiple dental appliances, each of the multiple dental appliances including an error surface in an auxiliary well; Provide 3D models of multiple dental aids, wherein each of the multiple 3D models of dental aids is associated with a corresponding aid receiving well of one of the multiple 3D models of dental appliances; Identify multiple sampling points on each error surface; Identify multiple features associated with each of the plurality of sampling points; and One or more target distances from each of the plurality of sampling points to the surface of the auxiliary component are provided to train a prediction model using multiple features associated with each of the plurality of sampling points and the target distances. The trained prediction model is adapted to receive an initial 3D model of a dental appliance as input, and based on the initial 3D model of the dental appliance, predict the updated geometry of the 3D model of the dental appliance to conform to the accessory.

21. A system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: The processor receives or generates an initial 3D model of a dental aid, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the 3D model of the dental aid to conform to the aid's shape in the dental appliance. The predicted updated geometry includes: Identify error surfaces on the initial 3D model of the dental aid, wherein the error surfaces correspond to the surfaces of the aid wells that are predicted to deviate from the original design of the dental appliance; The error surfaces of the 3D model of the dental aid were modified to create an updated surface. The updated geometry is defined as a modified geometry that differs from the initial geometry of the 3D model of the dental aid; and A digital representation of the dental aid is generated based on the updated geometry.

22. A system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: The processor receives or generates an initial 3D model of a dental appliance, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the initial 3D model of the dental appliance to conform to the dental aid. The predicted updated geometry includes: Identify error surfaces on the initial 3D model of the dental appliance, wherein the error surfaces correspond to surfaces of the dental appliance that are predicted to deviate from the original design of the dental appliance; The error surfaces of the 3D model of the dental instrument are modified to create an updated surface. The updated geometry defines a modified geometry for the auxiliary components of the dental appliance that differs from the initial 3D model of the dental appliance; and A digital representation of the dental appliance is generated based on the updated geometry.

23. A method of forming a dental accessory, comprising: The processor receives or generates an initial 3D model of a dental aid, the initial 3D model having an initial geometry; The processor predicts the updated geometry of the initial 3D model of the dental aid, wherein predicting the updated geometry includes: Identify error surfaces on the initial 3D model of the dental aid; Adjust the error surface of the 3D model of the dental aid to create an updated surface different from the error surface, such that the updated geometry differs from the initial geometry; and A digital representation of the dental aid is generated based on the updated geometry.

Images