Method for generating a model of a dental arch

Abstract

To provide a new method for providing an aligner.SOLUTION: A method generated to represent an intermediate model dental arch, comprising: 1) acquiring, at an update time ta in the course of a treatment, at least one updated image representing an active aligner attached to the dental arch in an operating position, i.e., an "image with aligner", or at least one updated image representing a dental arch without an aligner, i.e., an "image of exposed teeth".SELECTED DRAWING: Figure 8

Description

[Technical Field]

[0001] The present invention relates to a method for generating a three-dimensional digital model of a dental arch.

[0002] The invention also relates to a method for producing an orthodontic aligner by means of a production method according to the invention, in particular for the purpose of adapting an orthodontic treatment by means of such an aligner.

[0003] Finally, the invention relates to a computer system for implementing these methods. [Background technology]

[0004] 1 and 2, orthodontic aligner 10 is conventionally in the form of a one-piece removable device, conventionally made of a transparent polymeric material, and shaped to correspond to successive teeth in the dental arch to which orthodontic aligner 10 is attached. Orthodontic aligner 10 includes grooves 12 that are generally U-shaped and shaped so that multiple teeth in the dental arch, typically all of the teeth in the dental arch, can be accommodated in groove 12.

[0005] The shape of the grooves is determined to securely attach the aligner to the teeth, but also according to the desired target position of the teeth. More precisely, the shape is determined so that when the aligner is in its service position, it applies stresses that tend to move the treated teeth toward the target position.

[0006] Conventionally, at the beginning of orthodontic treatment, the shapes that the various aligners must have at various times during treatment are determined, and then all of the corresponding aligners are manufactured. For this purpose, the following steps are performed: - at an initial time t1, typically at the beginning of treatment, generating a three-dimensional digital model of the patient's dental arch in its initial configuration, referred to as an "initial model," and cutting the initial model to create tooth models; - Arches are separated at each intermediate time t nFrom the initial configuration through intermediate configurations at a final time t N+1 determining a dental arch treatment suitable for modification to a final configuration in - transforming the initial model to generate intermediate and final models representing the dental arch in the intermediate and final configurations, respectively; - determining a series of N aligners based on the initial, intermediate, and final models, where a first aligner is worn until time t2 and an nth aligner is worn until time t n From time t n+1 a step, the step being intended to be fitted to - manufacturing at least some of the aligners.

[0007] All of the manufactured aligners are then provided to the patient so that the patient can change aligners at predetermined intervals.

[0008] During treatment, the patient visits the orthodontist at regular intervals for visual examinations to verify, among other things, that the tooth movements are as expected and that the aligners the patient is wearing are still appropriate for treatment.

[0009] Specifically, the orthodontist may visually diagnose whether the aligner has become dislodged. Specifically, the groove bottom 20 has a shape that is substantially complementary to the shape of the free end 22 of the tooth (FIG. 5). Therefore, the contour of the groove bottom may be compared to the contour of the tooth D to evaluate the gap between the groove bottom and one or more free ends of the tooth.

[0010] If a misalignment is detected, the orthodontist takes new impressions of the teeth, or equivalently, takes new scans of the teeth, and then repeats the above process to design and manufacture a new set of aligners.

[0011] The patient will be forced to visit the orthodontist. This may reduce the patient's trust in the orthodontist. Finally, this involves additional costs. Therefore, the number of examinations by the orthodontist must be limited.

[0012] Additionally, improperly fitted aligners can be unsightly.

[0013] To solve these problems, the applicant proposed in EP3412245 a method for evaluating the shape of orthodontic aligners worn by a patient.

[0014] This method advantageously allows for remote detection of aligner dislocation, which significantly facilitates the assessment of the suitability of aligners for treatment. Specifically, this method may be performed, for example, based on simple images, especially photographs or videos, obtained by the patient without any special precautions. Thus, the number of appointments with the orthodontist may be limited.

[0015] However, when mismatched teeth are detected, especially if the aligners become dislodged from the teeth, an appointment must be made with the orthodontist to have a new set of aligners made. Aside from the inconvenience this poses to the patient, the appointment delays treatment; specifically, treatment must be interrupted from the time the dislodgment is detected until the new aligners are received.

[0016] Solutions are needed to address these problems. [Prior art documents] [Patent documents]

[0017] [Patent Document 1] EP3412245 [Patent Document 2] U.S. Patent No. 5,975,893A [Patent Document 3] PCT / EP2015 / 074896 [Patent Document 4] PCT / EP2015 / 074900 [Patent Document 5] EP3432218 [Patent Document 6] EP1835864 [Non-patent literature]

[0018] [Non-Patent Document 1] “Unpaired image-to-image translation using cycle-consistent adversarial networks” by Zhu, Jun-Yan et al. Summary of the Invention [Problem to be solved by the invention]

[0019] One object of the present invention is to at least partially meet this need. [Means for solving the problem]

[0020] The present invention provides a method for generating a three-dimensional digital model, called an "updated model," of a patient's dental arch during the course of treatment of said dental arch with orthodontic aligners, called "active aligners," particularly in the context of treatment with a series of orthodontic aligners intended to be successively attached to said dental arch, wherein said treatment is simulated by a treatment scenario generated at an initial time t1, e.g., the beginning of treatment, and wherein the treatment scenario includes a plurality of intermediate models, each intermediate model being a three-dimensional digital model of the dental arch, which are cut to create tooth models and determined to represent the dental arch at one respective intermediate time after the initial time.

[0021] The production method according to the invention comprises the following steps: 1) acquiring at least one update image at update times during treatment, each update image being either an aligner image representing an active aligner attached to the dental arch in a use position, or an exposed teeth image representing the dental arch without an aligner; 2) step 4), and preferably before step 3), determining said intermediate model or "active intermediate model" depending on the update time; 3) searching for one or more representations of teeth that do not fit the treatment scenario in the updated image, referred to as the "analysis updated image"; If one or more mismatched teeth are detected, 4) identifying one or more tooth models each representing one or more mismatched teeth in the active intermediate model; 5) Deforming the active intermediate model until an updated model is obtained that matches at least one of the update images, called a "deformed update image."

[0022] The present invention is based on the fact that, if mismatched teeth are ignored, the intermediate model of the treatment scenario designed before treatment begins correctly models the dental arch at the corresponding intermediate time. Specifically, if an aligner does not come off a tooth, this indicates that treatment is progressing as planned for that tooth. Therefore, at the intermediate time close to the update time, the corresponding intermediate model is actually matched for the "matched" teeth, which generally means nearly all teeth. Therefore, this active intermediate model, which is conventionally generated initially for aligner manufacturing, can be used as a starting point to create the updated model.

[0023] In particular, all of the parts of the active intermediate model that relate to the matching teeth are immediately available, and therefore an updated model may be constructed based on the active intermediate model, tracking only the actual positions of the tooth models of the non-matching teeth.

[0024] Advantageously, therefore, the patient no longer needs to perform new scans to adapt the aligner to the negative progression of the patient's treatment. The treatment scenario and one or preferably several updated images are sufficient. This significantly simplifies and accelerates treatment.

[0025] Furthermore, determining the updated model is simplified not only because the number of tooth models to be moved is very limited, typically 1-5 tooth models representing unmatched teeth, but also because such movements are constrained by the tooth models of the matching teeth.

[0026] The method may include, before step 1), a step of generating a treatment scenario including the plurality of intermediate models. The treatment scenario is generated after the treatment itself is determined. The treatment scenario may be generated simultaneously with the treatment itself being determined.

[0027] The method according to the invention may include one or more of the following optional features. - at least some, and possibly all, of the intermediate models of the treatment scenario represent the dental arch in the expected configuration at an intermediate time representing an aligner change; - in step 1), a reminder is sent to the patient, preferably on the patient's mobile phone, whereby the patient takes at least one update image, preferably at least one aligner image and preferably at least one image of exposed teeth; - in step 1), more than two update images, preferably more than four update images, are acquired, - in step 1), at least two updated images are preferably acquired under different acquisition conditions, in particular with different orientations of the acquisition device, the angle of the optical axis of the acquisition device relative to the front of the patient differing between the acquisition of the at least two updated images by more than 20°, more than 30°, more than 45°, more than 60° or possibly more than 90°, - in step 1), at least one updated image, preferably each updated image, is an image extracted from a photograph or a video, - in step 1), at least one updated image, preferably each updated image, is an extraoral image, - in step 1), at least one updated image, preferably each updated image, is acquired preferably by the patient using a mobile phone, possibly after the dental retractor has been fitted, - in one embodiment, in step 1), at least one updated image, preferably each updated image, is acquired, preferably by the patient using a mobile phone, after the mobile phone and the dental retractor are attached to a holder and then the dental retractor is placed in the patient's mouth, - The holder takes the form of an exclusive casing opening onto the retractor and onto the mobile phone, - all update images are acquired at time intervals of duration less than 5 days, preferably less than 1 day, preferably less than 1 hour, preferably less than 10 minutes, - the patient sends one or more updated images to the computer, preferably by mobile phone, which acquired the aligner images; - the computer is configured to receive and process updated images of a plurality of patients, preferably more than 100, more than 1000, or more than 10000 patients; - before step 2), an intermediate model of the dental arch is generated from the intermediate model of the treatment scenario and then added to the treatment scenario via the intermediate model, - in step 2) the active intermediate model is determined manually by an operator, preferably a dental professional, more preferably an orthodontist, preferably using a computer that allows the operator to view the treatment scenario, or automatically by a computer, preferably said computer receiving updated images of a plurality of patients and processing them, preferably by comparing the update times with the intermediate times of the intermediate model of the treatment scenario, - in step 2), the active intermediate model is an intermediate model whose difference between the intermediate time and the update time is less than 4 weeks, less than 2 weeks, preferably less than 1 week, In step 2), the active intermediate model is the intermediate model whose intermediate time is closest to the update time; - in step 3), the search for mismatched tooth representations in the analyzed updated images is performed manually by an operator, preferably a dental professional, more preferably an orthodontist, preferably using a computer that allows the operator to view one or more updated images, or preferably automatically by a computer, preferably said computer having received and processed updated images of a plurality of patients, the computer preferably implementing a deep learning device, and preferably a neural network; - in step 3), the representation of the teeth in the analysis update image is considered to be incompatible with the treatment scenario if, when the analysis update image is matched and overlapped with a view of the active intermediate model that is matched to said analysis update image and that is at the same scale and life-size as the view of the active intermediate model (the actual dimensions of the teeth are the same as the dimensions of the tooth representation), at least one point of said representation is separated from a corresponding point in said view by a distance that is greater than 1 / 10 mm, 3 / 10 mm, 5 / 10 mm, or 1 mm, and preferably less than 7 mm or 5 mm; - in step 4), tooth models of non-matching teeth in the active intermediate model are identified manually by an operator, preferably a dental professional, more preferably an orthodontist, preferably using a computer that allows the operator to view the active intermediate model, or automatically by a computer, preferably said computer receiving and processing updated images of a plurality of patients, the computer preferably implementing a deep learning device, and preferably a neural network; - in step 3), the analysis update image is analyzed independently of the active intermediate model to detect non-matching teeth, in which case the active intermediate model may be determined after step 3); Alternatively, in step 3), the analysis update images are compared with views of an active intermediate model to detect non-matching teeth, in which case the active intermediate model must be determined before step 3), - In step 3), to detect mismatched teeth, A position, orientation, and calibration of the virtual acquisition device is sought that allows the virtual acquisition device to have a view on the active intermediate model that is as close as possible to the analysis update image, i.e., a view of the active intermediate model that has the greatest degree of fit (i.e., is the best fit) with said analysis update image, and then The view and the analysis-updated image are compared, or an updated map representing the distinguishing information of the analysis-updated image is compared with a reference map representing the distinguishing information in the view; - In step 3), to detect mismatched teeth, the analyzed and updated image is an aligner image, and the contour of at least one tooth and the contour of the aligner are determined in the analyzed and updated image, and then the contours are compared; - A tooth is considered mismatched if it deviates from the aligner by more than a threshold in the aligner image; - before step 5), the active intermediate model is processed to improve its accuracy, - in step 5), the deformation of the active intermediate model comprises, preferably consists of, a movement of the tooth models of said active intermediate model, - in step 5), the movement of the tooth models is continued until the positioning error for each tooth model with respect to the deformation update image is less than 1 mm, preferably less than 5 / 10 mm, preferably less than 3 / 10 mm, preferably less than 2 / 10 mm, preferably less than 1 / 10 mm, - in step 5), the tooth models of the non-matching teeth are moved manually by an operator, preferably a dental professional, more preferably an orthodontist, preferably using a computer that allows the operator to visualize the active intermediate model, or moved automatically by a computer, preferably said computer receiving and processing updated images of a plurality of patients, preferably the computer implementing a deep learning device, and preferably a neural network, or an optimization method, and preferably a metaheuristic optimization method, In step 5), the movement of the tooth model of the non-matching tooth is limited by the tooth model of the matching tooth, which remains stationary; In step 5), the movement of the tooth model of the non-matching tooth is an iterative process, in each iteration: one or more of said tooth models of non-matching teeth are moved to obtain a dental arch model to be tested, and then - the model to be tested is tested by evaluating the fit between said model and the modified updated images, in particular the images of exposed teeth, The updated model is the model with the best fit among all tested models, - before said iterative process, a position, orientation and calibration of the virtual acquisition device, or "constrained virtual acquisition conditions", is pursued that allows observing the active intermediate model to generate views in which the matching tooth representations can be coincident and superimposed with said matching tooth representations in the deformation updated image, and then During the iterative process, at each iteration, a fit between the model under test and the deformation updated image is evaluated by comparing the deformation updated image with a view of the model under test obtained under the constrained virtual acquisition conditions; The cycle of iterations is interrupted when the number of iterations exceeds a predetermined number or when the fitness value exceeds a predetermined threshold; - in step 5), during said deformation of the active intermediate model, only the tooth models of the non-matching teeth are moved, - at the end of step 3) or 4), preferably step 4), the degree of non-conformity of the non-conforming tooth or teeth and in particular the amount of movement of the dislocated tooth or teeth is determined based on at least one updated image, preferably by comparing said analyzed updated image with the active intermediate model, and then In step 5), the tooth model or models of the non-matching teeth are moved according to said measurements, preferably until the positioning error per tooth model relative to the deformed updated image is less than 1 mm, preferably less than 5 / 10 mm, preferably less than 3 / 10 mm, preferably less than 2 / 10 mm, preferably less than 1 / 10 mm; - in step 5), the deformation of the active intermediate model comprises a movement of one or more tooth models of the mismatched teeth, the amplitude and / or direction of said movement being determined depending on a measurement of the incompatibility of said one or more mismatched teeth, said measurement being performed based on at least one updated image, in particular an aligner image, preferably by comparing said updated image with the active intermediate model.

[0028] The present invention provides a method for manufacturing an orthodontic aligner, comprising steps 1) to 5), followed by the following steps: 6) designing, based on the updated model and the final model representing the dental arch in its theoretical final configuration, an "updated" aligner suitable for correcting the dental arch from its actual configuration at the time of the update towards said theoretical final configuration in its use position; 7) manufacturing the updated aligners and providing the updated aligners to the patient.

[0029] The theoretical final configuration planned for the dental arch at the final time after the last intermediate time is generally the theoretical final configuration of the dental arch that is targeted at the end of treatment.

[0030] The method according to the invention may be partly implemented by a computer, in particular with regard to the steps of modifying the model, calculating or examining the model to explore in particular constrained virtual acquisition conditions or analysing images or maps, for example to determine the contour.

[0031] The present invention provides - a computer program comprising program code instructions for carrying out one or more, preferably all, of steps 2), 3), 4), 5) and possibly step 6), when the computer program is executed by a computer; - a computer-readable storage medium on which such a program is stored, for example a memory or a CD-ROM, and - also relates to the computer on which such programs are loaded.

[0032] The present invention provides - a personal device, preferably a mobile phone, configured to acquire one or more update images in step 1), a computer loaded with a program comprising program code instructions for carrying out one or more, preferably all, of steps 2) to 5) and possibly step 6), when the program is executed by the computer, i.e. "configured" to carry out these steps; - optionally a computer loaded with a program configured to manufacture the aligner in step 7).

[0033] definition By "patient" or "user" is meant any person on whom the method according to the invention is carried out, whether or not that person is ill.

[0034] "Teeth" means a set of teeth in a dental arch.

[0035] "Dental practitioner" means any person qualified to provide dental care and specifically includes orthodontists and dentists.

[0036] The aligner used by the patient during treatment is called the “active aligner.” In multi-aligner treatment, each aligner is expected to be sequentially active.

[0037] A 3D scanner or "scanner" is a device that makes it possible to obtain a model of the dental arch.

[0038] The "use position" is the position of the aligner when it is attached to a dental arch to treat that arch. Traditionally, this attachment can be deactivated by the patient by simply pulling on the aligner.

[0039] Once the aligner is in its use position and attached to the dental arch, teeth that are not properly positioned within the aligner are called "out-of-place teeth" and "not-out-of-place teeth," respectively. An orthodontist can perfectly distinguish between out-of-place teeth and not-out-of-place teeth. This distinction may also be made by a computer by evaluating the distance between the tooth and the bottom of the groove in the aligner attached to the tooth.

[0040] More generally, teeth are said to be "fit" or "misfit" when, at update time, they are in or out of their planned positions with respect to the treatment scenario. A misfit tooth is an example of a misfit tooth.

[0041] The "update time" is the time over which an update image is acquired. This length of time is short enough that the tooth configuration changes very little during this time.

[0042] A dental arch configuration is said to be an "actual" configuration when it is the configuration that the patient's dental arch actually has. A dental arch configuration is said to be a "theoretical" configuration when it is a "simulated" or future "planned" configuration of the patient's dental arch.

[0043] "Model" means a three-dimensional digital model. A model consists of a set of voxels. A "model of a dental arch" is a model representing at least a portion of a dental arch, preferably at least two teeth, preferably at least three teeth, preferably at least four teeth. Figure 3 shows an example of a view of a dental arch model.

[0044] A "tooth model" is a three-dimensional digital model of the teeth of a patient's dental arch. The model of the dental arch may be cut to define at least some teeth, preferably all teeth represented in the dental arch model. Thus, the tooth model is a model within the model of the dental arch. FIG. 4 shows an example of a view of a cut dental arch model. Computational tools exist for manipulating the tooth models of the dental arch model. Such tools, among other things, allow for the setting of constraints to restrict movement of the tooth models to realistic movements, for example, to prevent adjacent tooth models from penetrating each other.

[0045] A "scenario" is a sequence of models of the dental arch representing successive dental arch configurations. Specifically, a "treatment scenario" or "treatment plan" includes models representing the configuration of the dental arch at various times during the treatment of the dental arch. These times are traditionally an initial time before treatment begins, an intermediate time during treatment, and a final time when treatment ends. Each model in the scenario representing a possible configuration of the dental arch at an intermediate time is called an "intermediate model." Figure 7 shows an example of a treatment scenario.

[0046] The intermediate and final arch configurations are theoretical configurations because they result from simulations into the future. These configurations are therefore expected or "planned" configurations and may therefore differ from reality at the intermediate time. By displaying a model of the scenario over time, it is possible to simulate the effects of treatment on the arch.

[0047] An example of a software package for manipulating tooth models and creating treatment scenarios is the Treat program, which is described at https: / / en.wikipedia.org / wiki / Clear_aligners#cite_note-invisalignsystem-10. U.S. Patent No. 5,975,893 A also describes creating treatment scenarios.

[0048] "Image" means a two-dimensional image, such as a photograph or an image extracted from a video. Images are made up of pixels.

[0049] The acquisition conditions are: the spatial position, spatial orientation and calibration (e.g. iris aperture and / or exposure time and / or focal length and / or sensitivity values) of the actual device for acquiring images of the patient's dental arch (actual acquisition conditions), or - Specify the spatial position, spatial orientation and calibration (e.g. iris aperture and / or exposure time and / or focal length and / or sensitivity values) of the virtual device for acquiring images of the model of the patient's dental arch (virtual acquisition conditions).

[0050] The "calibration" of an acquisition device consists of all the values ​​of its calibration parameters. Calibration parameters are parameters that are specific to the acquisition device (as opposed to the position and orientation of the acquisition device) and whose values ​​affect the image that is acquired. For example, iris aperture is a calibration parameter that modifies the depth of field. Exposure time is a calibration parameter that modifies the brightness (or "exposure") of the image. Focal length is a calibration parameter that modifies the angle of view, i.e., the amount of "zoom." "Sensitivity" is a calibration parameter that modifies the response of the digital acquisition device's sensor to incident light.

[0051] The calibration parameters are preferably selected from the group formed by iris aperture, exposure time, focal length and sensitivity.

[0052] An observation of the model under determined conditions of virtual acquisition (especially by calibration of the virtual acquisition device), at a determined angle, and at a determined distance is called a "view."

[0053] "Dental arch image," "dental arch view," "dental arch representation," "dental arch scan," or "dental arch model" means an image, view, representation, scan, or model of all or part of said dental arch.

[0054] A model of a patient's dental arch "fits" an image when there is a view of this model that corresponds to the image, i.e., a view such that the tooth representations in the view are similarly positioned relative to each other as the tooth representations in the image, and thus the contours of the tooth model represented in the view can substantially match and overlap the contours of the tooth representations in the image.

[0055] This view of the model may be considered to "fit" or "congruently overlap" the image.

[0056] Deep learning algorithms are deep learning devices known to those skilled in the art, including "neural networks" or "artificial neural networks."

[0057] Those skilled in the art can choose a neural network depending on the task to be performed. In particular, the neural network can be chosen from, inter alia: - A network called a convolutional neural network (CNN) specialized for image classification, e.g., - AlexNet(2012) - ZF Net(2013) - VGG Net (2014) - GoogleNet (2015) - Microsoft ResNet(2015) - Caffe: BAIR Reference CaffeNet, BAIR AlexNet - Torch: VGG_CNN_S, VGG_CNN_M, VGG_CNN_M_2048, VGG_CNN_M_1024, VGG_CNN_M_128, VGG_CNN_F, VGG ILSVRC-2014 16-layer, VGG ILSVRC-2014 19-layer, Network-in-Network(Imagenet & CIFAR-10) - Google: Inception (V3, V4) - Networks specialized in identifying and detecting objects in images (object detection networks), e.g. - R-CNN (2013) - SSD (single shot multibox detector: object detection network), Faster R-CNN (faster region-based convolutional network method: object detection network) - Faster R-CNN (2015) - SSD (2015) - RCF(Richer Convolutional Features for Edge Detection)(2017) - Networks specialized in image generation, e.g. - Cycle-Consistent Adversarial Networks(2017) - Augmented CycleGAN (2018) - Deep Photo Style Transfer(2017) - FastPhotoStyle(2018) - pix2pix(2017) - Style-Based Generator Architecture for GANs(2018) - SRGAN(2018).

[0058] The above list is not exhaustive.

[0059] Training a neural network consists of exposing it to a training database containing information about two types of objects that the neural network must "match," i.e., learn to connect with each other.

[0060] The training may be based on a training database made up of records, each record comprising a first object of a first type and a corresponding second object of a second type.

[0061] Alternatively, training may be based on a training database consisting of records where each record contains either a first object of a first type or a second object of a second type, but where each record contains information about the type of object it contains. Such training techniques are described, for example, in the article "Unpaired image-to-image translation using cycle-consistent adversarial networks" by Zhu, Jun-Yan et al.

[0062] Training the neural network with these records teaches the neural network to take any object of the first kind and provide it with a corresponding object of the second kind.

[0063] The quality of the analysis performed by the neural network depends directly on the number of records in the training database, which preferably contains more than 10,000 records.

[0064] To assess the "placement error" of the tooth model, the distance between each point in the deformation updated image of the representation of the tooth modeled by the tooth model (when the deformation updated image at 1:1 scale is coincidentally overlapped with a view of the active intermediate model that fits the deformation updated image at 1:1 scale) and the corresponding point in said view is measured. The placement error is the longest of these distances when considering all points of the representation that have a corresponding point in said view. 1:1 scale means that the representation of the tooth is life-size, in which case the deformation updated image and the view of the active intermediate model represent the tooth with its actual dimensions.

[0065] The terms "comprise," "include," or "have" are to be interpreted broadly and without limitation, unless otherwise indicated.

[0066] Other features and advantages of the present invention will become more apparent upon reading the following detailed description and examining the accompanying drawings. [Brief explanation of the drawings]

[0067] [Figure 1] FIG. 1 is a perspective view of an orthodontic aligner. [Figure 2] FIG. 2 is a top view of the orthodontic aligner of FIG. 1. [Figure 3] FIG. 1 illustrates an example of an initial model (intermediate, final, and updated models may take similar forms). [Figure 4] FIG. 1 shows an example of a model in which a tooth model is cut (only the tooth model is shown). [Figure 5] FIG. 1 is a schematic diagram of a holding arch for holding orthodontic aligners. [Figure 6] 1 shows a system suitable for implementing the method according to the invention; [Figure 7] FIG. 1 illustrates a treatment scenario. [Figure 8] FIG. 1 shows a schematic diagram of a method according to the invention. [Figure 9] FIG. 10 is a diagram showing an example of an aligner image. [Figure 10] 1A-1C are diagrams illustrating the acquisition of aligner images and / or exposed tooth images. [Figure 11] 11A and 11B are schematic diagrams illustrating a retractor that may be used with the acquisition kit shown in FIG. 10. [Figure 12] FIG. 1 shows a schematic diagram of a first method for detecting outliers in an image. [Figure 13] FIG. 10 shows a schematic diagram of a second method for detecting outliers in an image. DETAILED DESCRIPTION OF THE INVENTION

[0068] In one embodiment, the method according to the present invention comprises, before carrying out steps 1) to 5), the following steps: At an initial time t1, typically at the beginning of treatment, a) generating a three-dimensional digital model, called an "initial model," of the patient's dental arch in its actual initial configuration and cutting the initial model to create tooth models; b) The dental arches are aligned at each intermediate time t n determining a dental arch treatment for modifying said initial configuration through theoretical intermediate configurations at n to a theoretical final configuration at a final time, generally at the end of treatment, where n is between 2 and N; c) transforming the initial model to generate a treatment scenario including a final model and an intermediate model representing the dental arch in a final configuration and an intermediate configuration, respectively; d) designing a series of aligners based on the initial, intermediate, and final models; e) manufacturing one or more of the aligners and providing these aligners to the patient (FIG. 8).

[0069] In one embodiment of the present invention, the method comprises steps 1) to 5) of the method for generating an updated model according to the present invention during treatment, followed preferably by the following steps: 6) designing an updated aligner based on the updated model and the final model, the updated aligner being configured to modify the dental arch from its actual configuration at the time of update towards said final configuration; 7) manufacturing updated aligners and providing the updated aligners to the patient.

[0070] In step a), an initial model is created at an initial time t1 which precedes the start of orthodontic treatment with orthodontic aligners, and is preferably less than 6 months before treatment begins, preferably less than 3 months or less than 1 month or less than 2 weeks before treatment begins.

[0071] The initial model may be created based on measurements taken on the patient's teeth or a physical model of the patient's teeth, for example a plaster model.

[0072] The initial model is preferably created by specialized equipment, such as a 3D scanner, which is preferably implemented by a dental professional, such as an orthodontist or an orthodontic laboratory. In the orthodontic clinic, a physical model of the patient or the patient's teeth can advantageously be placed in a precise position, and the specialized equipment can be state-of-the-art equipment. Thus, a highly accurate initial model can be obtained. The initial model preferably provides information about the tooth positions with an error of less than 5 / 10 mm, preferably less than 3 / 10 mm, and preferably less than 1 / 10 mm.

[0073] The initial model may for example be of point cloud type or one of the following types: STL, OBJ, 3D DXF, IGES, STEP, VDA. Advantageously, such a so-called "3D" model may be observed from any angle.

[0074] The initial model is conventionally viewable and manipulatable by computer. The initial model is then cut to define the tooth models.

[0075] Cutting a three-dimensional model to create a tooth model is a conventional operation in which the model is cut to define a representation of one or more of the teeth in the initial model. Other elements of the dental arch, such as the gums, may also be modeled.

[0076] The initial model may be cut manually by an operator using a computer, or automatically by a computer, which preferably implements a deep learning device, and preferably a neural network.

[0077] In particular, the tooth model may be defined, for example, as described in International Patent Application PCT / EP2015 / 074896.

[0078] FIG. 4 shows an example of an initial model from which tooth models 32 have been cut (only the tooth models are shown, and are shaded differently to make them more easily identifiable).

[0079] After cutting, the tooth model may be moved. The initial, post-cut model may be transformed by the computer in this manner, via movement of the tooth model, without modifying the tooth model, to simulate tooth movement from an initial time to a final time when the tooth is in its final configuration, which may indicate the end of treatment.

[0080] In step b), a treatment is determined to move one or more teeth from an initial configuration through an intermediate configuration to a final configuration.

[0081] A set of dental arch models that allow visualization of each stage of treatment forms a treatment scenario. A computer is used to display the treatment scenario and store initial models that are modified to simulate the configuration of the dental arch at various intermediate times.

[0082] Traditionally, there are multiple possible potential scenarios for a given treatment. In one embodiment, a computer determines the potential scenarios and selects a treatment scenario from those scenarios. In another embodiment, a computer determines the potential scenarios and presents them to a dental practitioner, who selects a treatment scenario from those scenarios. In another preferred embodiment, a dental practitioner, preferably an orthodontist, determines the potential scenarios and selects a treatment scenario from those scenarios. The computer advantageously allows the dental practitioner to visualize a simulation of the effect of the potential scenarios on the dental arch.

[0083] In step c), the initial model is transformed to generate a final model representing the dental arch in its theoretical final configuration and intermediate models representing stages between the initial and final models.

[0084] The deformations may be determined in response to the orthodontic treatment by a dental professional, preferably an orthodontist, using a computer that enables the dental professional to visualize the effect of the envisaged treatment on the dental arch, or may be determined automatically by a computer, which preferably implements a deep learning device, and preferably a neural network.

[0085] Preferably, steps b) and c) are simultaneous. In particular, the treatment scenario is determined as a result of one or more simulations performed by moving the tooth models and thereby transforming the initial model into the configuration of the final model. Once a treatment has been selected, it is sufficient to simulate this treatment and save the transformed initial model at intermediate times to generate an intermediate model.

[0086] FIG. 9 shows an example of a treatment scenario that includes an initial model, two intermediate models, and a final model.

[0087] In step d), a series of aligners are designed to modify the dental arch through tooth movement according to the treatment scenario.

[0088] In step e), one or more of the first aligners in the series are manufactured. Conventionally, all aligners in the series are manufactured. These aligners are provided to the patient so that the patient may begin treatment.

[0089] The method comprising steps a) through e) is known and widely used for designing and manufacturing a series of orthodontic aligners.

[0090] Traditionally, patients are monitored by their orthodontist. As explained in the introduction, the orthodontist periodically checks the fit of the aligners and, if they are not fitting well with the treatment, especially if the aligners are dislodged, generates a new dental arch model via a scanner and then repeats steps b) through e) with the initial model replaced by this new model, thereby creating a new set of aligners to cover the remainder of the treatment.

[0091] According to the present invention, the method includes steps 1) to 5) and preferably steps 1) to 7) during treatment.

[0092] In step 1), at the update time, an update image is obtained, called the "analysis" update image, which makes it possible to detect incompatibilities, in particular deviations of the teeth relative to the aligners worn at the update time.

[0093] The update time may be, for example, more than two weeks, more than four weeks, more than eight weeks, or more than twelve weeks after the initial time.

[0094] Preferably, at least one reminder is sent to the patient prior to the update time, for example, less than two weeks prior to the update time, informing the patient that an analysis update image needs to be taken. This reminder may take paper form, or preferably electronic form, for example, email, an automatic alert from a dedicated mobile application, or SMS. Such a reminder may be sent by the orthodontic office or orthodontic laboratory, by the dentist, or by a dedicated application on the patient's mobile phone.

[0095] The analysis update image is taken by an image capture device, preferably a personal capture device, preferably equipped with an image capture system such as a webcam or camera, such as a mobile phone, a so-called "connected" camera, a so-called "smart" watch, a tablet, or a (desktop or laptop) personal computer.

[0096] The analysis update image is preferably an extraoral image.

[0097] In one embodiment, a photography kit 15 is used, as shown in Figures 10 and 11. Such a kit preferably comprises a holder 17, a dental retractor 19, and an image capture device, preferably a mobile phone 21. The dental retractor 19 and the capture device, preferably a mobile phone, are preferably removably attached to the holder 17.

[0098] The retractor 19 may have the characteristics of a conventional retractor.

[0099] As shown in FIG. 11 (with the retractor 19 separated from the holder), the retractor 19 preferably comprises a groove 23 extending around the retractor opening of axis X and positioned so that the patient's lips are positioned therein while the patient's teeth are visible through said retractor opening.

[0100] The retractor 19 may be attached to the holder by one or more clips 27a and 27b, for example magnetic clips.

[0101] The retractor preferably includes lugs 26a and 26b for moving the cheek out of the way so that an acquisition device attached to the holder can obtain photographs of the vestibular surfaces of teeth located at the back of the mouth, such as molars, through the retractor opening.

[0102] The holder preferably takes the form of a casing opening exclusively over the retractor opening and over the mobile phone, so that the mobile phone views the patient's dental arch through the casing. Advantageously, the holder allows presetting the position of the mobile phone relative to the dental arch.

[0103] The acquisition is preferably performed by the patient or a friend or relative of the patient, but may also be performed by another person, in particular a dentist or orthodontist, preferably without the need to precisely position the image acquisition device relative to the teeth.

[0104] The analysis-updated image is preferably a photograph or an image extracted from a video. The analysis-updated image is preferably a color image, preferably a true color image. More preferably, the analysis-updated image is a photograph showing the actual dental arch as perceived by the human eye (as opposed to a tomographic or panoramic image obtained by X-ray).

[0105] The analysis update image is then preferably sent to a centralized computer, preferably by the mobile phone that captured the analysis update image.

[0106] A dedicated application is loaded onto the mobile phone and preferably guides the patient audibly and / or visually through the various actions to be performed and sends analytical update images.

[0107] In one embodiment, the analysis update image is an aligner image, which advantageously makes it possible to detect incompatibilities, in particular deviations, by analyzing only this image, which may be done by comparing this image with the active intermediate model.

[0108] In one embodiment, the analysis update image is an image of the exposed teeth, which advantageously allows for detection of incompatibilities with high accuracy, particularly without being hindered by the aligner display, but in which case it is necessary to compare this image with the active intermediate model.

[0109] In step 1), an aligner image and an image of the exposed teeth are preferably acquired to take advantage of the two complementary analyses.

[0110] In step 1), at least one image of the exposed teeth is preferably acquired which is used as a deformation update image in step 5).

[0111] In step 2), the intermediate model or "active intermediate model" is determined, preferably by a computer, depending on the update time. Step 2) may be performed subsequent to step 3), if in step 3) the analysis update image is analyzed independently of the active intermediate model to detect non-matching teeth.

[0112] From the treatment scenario, preferably by computer, an intermediate model is selected that should best represent the dental arch at the update time according to this scenario. Assuming treatment is progressing according to the treatment scenario, the intermediate model whose intermediate time is closest to the update time may be selected. This intermediate model is said to be "active."

[0113] An active intermediate model is an intermediate model whose intermediate time is close to the update time, preferably less than 4 weeks, less than 2 weeks, preferably less than 1 week from the update time. Preferably, the intermediate time of an active intermediate model precedes the update time.

[0114] In a preferred embodiment, the active intermediate model is not modified prior to step 5), so tooth movement is assessed by comparing the analysis update images with the intermediate model designed at the initial time.

[0115] In a preferred embodiment, the active intermediate model may be coarsely corrected, for example manually, to take into account modifications of the patient's dental arch between the initial time and the update time that are not due to drift during the course of treatment, for example to remove tooth models of missing or extracted teeth.

[0116] In step 3), the display in the analysis update image of teeth that do not fit the treatment scenario, especially teeth that are out of aligner, is pursued.

[0117] The centralized computer is preferably programmed to automatically detect and identify mismatched teeth.

[0118] Detecting incompatibilities with the active intermediate model The computer may use the analysis update images, particularly in the form of images of exposed teeth, to compare with the active intermediate model.

[0119] It is preferable to seek a position, orientation, and calibration of the virtual acquisition device (this position, orientation, and configuration are collectively referred to as the "virtual acquisition condition") that best corresponds ("best fit") to the actual acquisition conditions of the analysis-updated image.

[0120] The view under the virtual acquisition conditions is then compared with the analysis update image.

[0121] Comparison of said views with the analyzed and updated images allows not only to detect non-matching teeth, i.e., dislocated teeth, but also non-dislocated teeth whose positions do not correspond to the treatment scenario.

[0122] The comparison of the view and the analyzed updated image may be performed, for example, by comparing corresponding maps of the differentiation information representing the tooth contours. The comparison procedure described below for comparing the test map and the updated map may be used.

[0123] The search for virtual acquisition conditions and the comparison may in particular be carried out according to the teachings of PCT / EP2015 / 074896.

[0124] In a preferred embodiment, a representation of a tooth in the analysis-updated image is considered not compatible with the treatment scenario if at least one point of this representation in a scale of 1:1 is more than 1 / 10 mm, more than 3 / 10 mm, or more than 5 / 10 mm away from a corresponding point in said view in a scale of 1:1 (i.e. a point representing the same point on the tooth) and is preferably less than 7 mm or 5 mm.

[0125] This distance may also be measured in pixels, which advantageously eliminates the need to establish a scale.

[0126] The incompatibility is therefore advantageously an incompatibility that allows to detect drifts in the performance of the treatment: in particular, too long a distance is not considered to be related to a drift in the treatment, but rather to an anomaly due to, for example, a bad tooth identification due to the tooth being masked in the analysis update image.

[0127] Detection of outliers in aligner images without relying on active intermediate models To detect misalignment by computer, the analysis update image, which may take the form of an aligner image, may be analyzed to determine, among other things, the contours of the bottoms of the aligner grooves and the contours of the free ends of the teeth.

[0128] Those skilled in the art will know how to process the images or views to isolate features, including, for example, applying known masks or filters supplied with image processing software. Such processing operations allow, for example, to detect areas of high contrast.

[0129] These processing operations are specifically carried out in the following known and preferred manner: - Applying a Canny filter, in particular searching for edges using the Canny algorithm, - applying a Sobel filter and in particular calculating derivatives by the extended Sobel operator; - Applying a Laplace filter to calculate the Laplacian of the image; - Detecting blobs in images ("Blobdetector"); - Applying a threshold: applying a set threshold to each element of a vector; - resizing using the relationship between areas of pixels ("Resize(Area)") or performing bicubic interpolation in a pixel's neighborhood; - Shrinking an image by a specific structuring element; - Dilating an image by a specific structuring element; - Performing retouching using areas especially close to the restored area; - applying a bilateral filter; - Applying Gaussian Blur, - Applying Otsu's method to find the threshold that minimizes the intraclass variance, - Applying A* filter to find paths between points, - applying an adaptive threshold to the vector; - applying an equalization filter to the histogram of a particular grayscale image; - Detecting blur ("BlurDetection") and using its Laplacian to calculate the entropy of the image; - Detecting contours in binary images ("FindContour"); - Performing a color fill ("FloodFill"), in particular filling connected elements with a determined color.

[0130] The following non-limiting methods: - Applying the "MeanShift" filter, thereby finding objects in the image projection; - Applying "CLAHE", where CLAHE stands for "Contrast Limited Adaptive Histogram Equalization"; - Applying a "Kmeans" filter to determine the cluster centers and groups of samples around the clusters; - applying a DFT filter, thereby performing a discrete, forward, or inverse Fourier transform of a vector; - calculating moments; - Applying the "HuMoments" filter to calculate the Hu moment invariants; - calculating the integral of the image; - applying a Scharr filter and making it possible to calculate the derivatives of the image by implementing the Scharr operator; - Finding the convex hull of points ("ConvexHull"), - Searching for points of convexity of contours ("ConvexityDefects"), - comparing shapes to each other ("MatchShapes"); - Checking whether there is a point on the contour ("PointPolygonText"), - applying Harris corner detection ("CornerHarris"), - Detecting corners by searching for the minimum eigenvalue of the gradient matrix ("CornerMinEigenVal"); - Applying the Hough transform to find circles in a grayscale image ("HoughCircles"), - "Active contour modeling" (tracing the contours of objects based on potentially "noisy" 2D images), - Computing a force field ("gradient vector flow" or GVF) in a portion of the image; Applying a cascade classifier ("CascadeClassification") may be implemented, although this is not preferred.

[0131] The determination of the tooth geometry may be optimized according to the teachings of PCT / EP2015 / 074900.

[0132] In one embodiment, the groove bottom profile and the tooth free end profile are divided to define segments of these profiles for each tooth. The groove bottom profile segments and tooth free end profile segments are each referred to as an "outer tooth profile" 24. i and "internal tooth profile" 30 i(Figures 12 and 14). The adjectives "inner" and "outer" are used here only for clarity of description. In Figure 12, dotted lines indicate the boundaries of successive segments.

[0133] The comparison may then be carried out by any means, in particular using the techniques for comparing inner and outer tooth profiles described in EP 3412245.

[0134] Specifically, for each of a plurality of teeth for which the inner and outer tooth profiles have been determined, the following steps are performed: i) determining the distance between an inner tooth profile and an outer tooth profile; ii) determining a distance threshold, preferably based on the distance determined in step i); iii) for each of said teeth: - the distance between the inner and outer tooth profiles and - determining a distance score depending on a distance threshold.

[0135] In step i), the distance d between the inner and outer tooth contours is determined for each of said teeth (FIG. 13).

[0136] The distance between the inner and outer tooth contours of a tooth may for example be the average or longest distance between pixels of said contours that correspond to the same point on the tooth.

[0137] This distance is preferably measured in pixels, which advantageously makes it unnecessary to establish a scale.

[0138] In step ii), a distance threshold Sd is determined, preferably based on the distance determined in step i).

[0139] In step ii), the distance threshold Sd is preferably substantially equal to the shortest distance determined in step i) (d min). Conventionally, at least one of the teeth to be treated is in contact with the bottom of the groove into which it is inserted. In that case, the distance between the inner and outer tooth contours of this tooth is the minimum distance d corresponding to the normal situation. min This distance may therefore be used as a standard for evaluating the distance between the inner and outer tooth profiles of the outer teeth in step iii).

[0140] In step iii), a score called the "distance score" S(d,Sd) is calculated for each tooth: - the distance d between the inner and outer tooth profiles and - The determination is made according to a distance threshold Sd.

[0141] The distance score for a tooth is preferably equal to (d-Sd), i.e., the difference between the distance between the inner and outer tooth contours of this tooth and the distance threshold. The higher the distance score, the further the affected tooth is out of the groove.

[0142] FIG. 12 shows an example of the implementation of steps i) to iii), where tooth D1 is positioned dd from the bottom of the aligner. min >It misses the point Sd.

[0143] For each of the plurality of teeth for which the inner and outer tooth profiles have been determined, the following steps are performed: i') for each pair consisting of a left tooth adjacent to a right tooth of a triplet of at least first, second, and third adjacent teeth, for which an inner tooth contour and an outer tooth contour have been determined, the first and third teeth are adjacent to the second tooth; determining an offset between the inner tooth profile of the left tooth and the inner tooth profile of the right tooth, referred to as the "inner offset"; and determining an offset between the outer tooth profile of the left tooth and the outer tooth profile of the right tooth, referred to as the "outer offset"; Next, determining the difference between the medial and lateral offsets, referred to as the "offset difference"; ii') determining an offset difference threshold, preferably based on the offset difference determined in step i'); iii') It is also possible to carry out a step of determining for at least one tooth, preferably for each tooth of said triplet, at least one offset score as a function of the offset difference with respect to the adjacent tooth and an offset difference threshold.

[0144] In step i'), at least one triplet consisting of first, second and third teeth D1, D2 and D3, respectively, is considered to have the first and third teeth adjacent to the second tooth, i.e. the first, second and third teeth are considered to be consecutive along the dental arch.

[0145] The inner tooth profiles 301, 302, and 303 and the outer tooth profiles 241, 242, and 243 of teeth D1, D2, and D3, respectively, are determined.

[0146] The inner "offset" or outer "offset" respectively refers to the distance between the inner or outer tooth contours, respectively, of two adjacent teeth.

[0147] The following: - "First inner offset" Δ 1-2 the offset between the inner tooth profile of the first tooth 301 and the inner tooth profile of the second tooth 302, referred to as i; - "Second inner offset" Δ 2-3 the offset between the inner tooth profile of the second tooth 302 and the inner tooth profile of the third tooth 303, referred to as i; - "First outer offset" Δ 1-2 the offset between the outer tooth profile of the first tooth 241 and the outer tooth profile of the second tooth 242, referred to as e; - "Second outer offset" Δ 2-3 The offset between the outer tooth profile of the second tooth 242 and the outer tooth profile of the third tooth 243, referred to as e, is determined.

[0148] The inner offset between the inner tooth profiles of two adjacent teeth is preferably equal to the longest distance between the inner tooth profiles of the two teeth.

[0149] The lateral offset between the lateral tooth profiles of two adjacent teeth is preferably equal to the longest distance between the lateral tooth profiles of the two teeth.

[0150] The inner and outer offsets are preferably measured in pixels, which advantageously eliminates the need to establish a scale.

[0151] Then, the following: - "First offset difference" Δ 1-2 (=Δ 1-2 i-Δ 1-2 e), the first medial offset Δ 1-2 i and the first outer offset Δ 1-2 The difference between e and - "Second offset difference" Δ 2-3 (=Δ 2-3 i-Δ 2-3 e), a second medial offset Δ 2-3 i and the second outer offset Δ 2-3 The difference between e is determined.

[0152] In the example of Figure 12, Δ 1-2 is Δ 2-3 Much smaller than.

[0153] In step ii'), an offset threshold SΔ is preferably determined by multiplying the first and second offset differences Δ 1-2 and Δ 2-3 The judgment is based on the following.

[0154] In step ii'), the offset threshold is preferably substantially equal to the smallest difference between the offsets determined in step i').

[0155] Conventionally, at least two adjacent teeth under treatment are in contact with the bottom of the groove into which they are inserted. In this case, the offset difference between the two teeth under treatment is substantially zero. Therefore, this zero offset difference corresponds to the normal situation, and the offset difference between adjacent teeth under treatment may be evaluated using this zero offset difference as a standard.

[0156] In FIG. 13, the offset difference between the two teeth D1 and D2 is substantially zero.

[0157] In step iii'), for each pair of teeth in the triplet, at least one score, called an "offset score", is determined depending on the offset difference between said tooth and its adjacent teeth and an offset difference threshold.

[0158] Specifically, the offset difference of the first tooth with respect to the second tooth may be compared to an offset difference threshold SΔ, where the offset difference threshold SΔ is, for example, zero, and the offset difference threshold may be subtracted from the offset difference of the first tooth with respect to the second tooth to determine an offset score for the first tooth and the second tooth.

[0159] This offset score, for example, if positive, indicates that one or each of the first and second teeth is likely off the bottom of the groove.

[0160] In FIG. 13, the offset difference between tooth D2 and tooth D3 is positive, indicating that either the second or third tooth is off.

[0161] In FIG. 13, the offset difference between the two teeth D1 and D2 is substantially zero, and therefore a positive offset difference between the two teeth D2 and D3 indicates that the third tooth is disengaged.

[0162] Generally, when the first offset score for a first and second tooth indicates that one of the two teeth is out of alignment, a second offset score is determined for the second tooth and a third tooth adjacent to the second tooth. If the second offset score is lower than the first offset score, it is likely that the first tooth is out of alignment from the bottom of the groove. If not, it is likely that the second tooth is out of alignment.

[0163] Alternatively, identification of mismatched teeth, particularly dislocated teeth, may be performed by an operator, preferably a dental professional, more preferably an orthodontist, simply by observing the aligner image displayed on a computer screen.

[0164] Analysis using deep learning devices A deep learning device, preferably a neural network, may be used to identify mismatched teeth in the analyzed updated images.

[0165] Specifically, it can be carried out as described in EP3432218.

[0166] The following steps: I. creating a training database containing more than 1000, preferably more than 5000, preferably more than 10000, preferably more than 30000, preferably more than 50000, preferably more than 100000 history records, each record including a history image and a history description, each history image including one or more zones representing a tooth, i.e., "history tooth zones," and an associated history description specifying, for each history tooth zone, a tooth attribute value for at least one tooth attribute; II. Training at least one deep learning device, preferably a neural network, with a training database; III. Sending an analysis update image, preferably an aligner image, to the at least one deep learning device, whereby the deep learning device determines at least one probability for attribute values ​​of at least one tooth represented in a zone at least partially representing said tooth in the analysis update image, i.e., a "tooth analysis zone," and attribute values ​​related to the fit of said represented tooth; IV. Determining whether a tooth of said dental arch is present in a position represented by said tooth analysis zone and an attribute value of said tooth depending on said probability.

[0167] The deep learning device may be a neural network specifically specialized for identifying and detecting objects in images (i.e., an object detection network), and may specifically be selected from the above-mentioned examples of such networks.

[0168] The deep learning device not only allows for identifying tooth representations in the analyzed updated image, but also allows for determining whether the teeth are compatible or not.

[0169] In step I, tooth attributes are attributes whose values ​​are unique to each tooth.

[0170] For example, a tooth attribute "out of place" may have a value of "fit" or "misfit," depending on whether the tooth is properly or improperly positioned relative to the aligner.

[0171] In step II, historical records can be input into a deep learning device, where each record includes a historical image and, for each tooth represented in the historical image, a description describing the tooth's contours and any incompatibilities. Thus, the deep learning device gradually learns to recognize patterns in the images and associates the patterns with tooth zones and tooth attribute values ​​for incompatibilities, particularly for tooth misalignments.

[0172] In step III, the deep learning device recognizes the pattern in the analysis-updated image. Specifically, the deep learning device: - the presence, at a location in said analysis image, of a zone that at least partially represents a tooth ("tooth analysis zone"); - determining probabilities for attribute values ​​of teeth represented within said tooth analysis zones;

[0173] For example, in an aligner image, the deep learning device may determine that there is a 99.5% probability that the shape in the analyzed image represents a tooth, and a 99% probability that this tooth is out of alignment with the aligner.

[0174] Preferably, the deep learning device analyzes the entire analysis update image and determines the probability for all of the identified tooth analysis zones.

[0175] In step IV, a determination is preferably made, preferably by a computer, for each tooth represented in the analyzed and updated image, whether the represented tooth should be considered a matching tooth or a non-matching tooth depending on the probability determined in step III. For example, if the probability that a tooth is non-matching is higher than a threshold, e.g., 98%, the tooth may be considered out of alignment with the aligner.

[0176] Analysis and combination of aligner and exposed tooth images Mismatched teeth are preferably detected through comparison of exposed tooth images with the active intermediate model and detection by analyzing only the aligner images, thereby improving the final result.

[0177] Specifically, if the analysis update image is an aligner image, some outliers may be difficult to detect by analyzing only this image. Thus, if only the analysis of the aligner image is considered, teeth that do not fit may be deemed to fit. Using the exposed tooth image and the active intermediate model, it may be possible to detect incompatibilities that cannot be detected in the aligner image.

[0178] If no mismatched teeth are detected, treatment may continue without modifying the treatment scenario. Thus, the aligner designed in step d) is always suitable for treatment. An information message is preferably sent to the patient indicating that treatment is progressing correctly. An information message is also preferably sent to the patient's orthodontist.

[0179] If one or more mismatched teeth are detected, the process proceeds to step 4).

[0180] In step 4), tooth models of the active intermediate model are identified that represent the teeth identified in step 3) as mismatched teeth, in particular as out-of-place teeth.

[0181] This identification may be performed by any computer that has access to the active intermediate model and the identifiers of the mismatched teeth, particularly the outlying teeth, determined in step 3. Such identifiers may be transmitted to a computer that has access to the active intermediate model, or vice versa, i.e., the active intermediate model may be transmitted to a computer that has access to the identifiers.

[0182] The active intermediate model is preferably sent in step 3) to a centralized computer which analyzes the analysis update image and detects non-matching teeth, particularly missing teeth, and this centralized computer then performs step 4).

[0183] Alternatively, step 4) may be performed by an operator who has access to the active intermediate model.

[0184] In step 5), the active intermediate model is deformed until a configuration is found that matches the update image taken at update time. This update image, called the "deformed update image," is preferably an image of the exposed teeth without aligners, i.e., an image of the exposed dental arch, which facilitates deformation of the active intermediate model.

[0185] The deformation update image may be the same as or different from the analysis update image. The deformation update image is preferably acquired and transmitted as described above for the analysis update image, preferably by a mobile phone, preferably by an acquisition kit comprising a mobile phone and a holder to which a dental retractor is attached. The deformation update image is preferably an extraoral image.

[0186] Deformations achieved by operating on all tooth models of the active intermediate model are very time-consuming to implement. In particular, the inventors have observed that such deformations do not result in a model that accurately represents the actual configuration of the dental arch at the time of update. Specifically, the inventors have observed that extraoral update images do not always allow for the accurate determination of the teeth's (especially molars') positions in the posterior part of the mouth when all tooth models are movable during deformation. Thus, such deformations may result in substantial deviations from the active intermediate model in areas where the active intermediate model accurately represents the actual positions of the teeth. Therefore, aligners manufactured based on such deformations may be unusable.

[0187] In one embodiment of the present invention, the active intermediate model is not deformed except in the areas of the tooth models of non-matching teeth, especially missing teeth, thus the general shape of the active intermediate model is preserved and only these tooth models are moved.

[0188] Therefore, the deformation of the active intermediary model is limited to the movement of the tooth models of the active intermediary model that represent the non-matching teeth.

[0189] Specifically, deforming the intermediate model by moving only the tooth models of the mismatched teeth allows for a very accurate assessment of the relative deviation of the mismatched teeth at update time relative to the active intermediate model before deformation.

[0190] In a preferred embodiment, the movement of the tooth models continues until the placement error for each tooth model relative to the deformed updated image is less than 1 mm, preferably less than 5 / 10 mm, preferably less than 3 / 10 mm, preferably less than 2 / 10 mm, preferably less than 1 / 10 mm.

[0191] constraints Preferably, virtual acquisition conditions are sought that correspond to the actual acquisition conditions of the deformation update image and allow observing the active intermediate model so that the view of the active intermediate model is as close as possible to the deformation update image. This search may have been performed in step 3) if the deformation update image is the analysis update image.

[0192] In one embodiment, such virtual acquisition conditions are determined by taking into account all tooth models. Therefore, non-matching teeth will have a negative impact on the accuracy of the virtual acquisition conditions. However, such teeth are few in number and their impact is generally low.

[0193] The virtual acquisition conditions are preferably determined without taking into account the tooth models of non-matching teeth, especially teeth that are out of alignment. It is therefore possible to determine "constrained" virtual acquisition conditions that correspond exactly to the real acquisition conditions of the deformation updated images and allow observing the active intermediate model so that the views of the active intermediate model, called "constrained views", are very close to the deformation updated images. The resulting constrained views are very accurate, especially for matching teeth, since they are not corrupted by the effects of non-matching teeth.

[0194] In particular, in the latter embodiment, the representation of the matching tooth in the deformation-updated image may advantageously be used as a fiducial whose position in the active intermediate model is known, in particular in the view obtained under said virtual acquisition conditions, such fiducial has the same relative position as it has in the deformation-updated image.

[0195] Preferably, at least three non-aligned points, e.g., cusps of the matching teeth, especially the non-misaligned teeth, are used as references, in which case analysis of the distances between these references in the deformation update image makes it possible to evaluate said virtual acquisition conditions via simple calculations.

[0196] Advantageously, said virtual acquisition conditions may then be used to test all of the positions of the tooth models of non-matching teeth, in particular of the missing teeth.

[0197] Moving mismatched tooth models via optimization The active intermediate model is preferably transformed by an optimization algorithm.

[0198] Preferably, an iterative process is performed in which, in each iteration, one or more tooth models of non-matching teeth, particularly out-of-place teeth, are moved, and then the fit between the active intermediate model thus modified and the deformed updated image is evaluated, and the iteration continues until the modified model and the deformed updated image are found to be compatible.

[0199] The number of iterations may be, for example, more than 10, more than 100, more than 1000, more than 10,000, and / or less than 1,000,000.

[0200] The following steps: A) analyzing the modified updated image and generating an updated image with respect to the distinguishing information; B) based on the updated map and via movement of tooth models of non-matching teeth, in particular outlying teeth, searching for an updated model that corresponds to the tooth position when the deformed updated image was acquired, wherein the search is preferably performed by an evolutionary metaheuristic method, preferably simulated annealing.

[0201] After step A), the modified updated image is analyzed to generate an updated map of at least one form of discrimination information.

[0202] "Distinguishing information" is characteristic information (ie, image features) that may be extracted from an image, conventionally by computer processing of that image.

[0203] The differentiation information may have a variable number of values. For example, the shape information may be equal to 1 or 0 depending on whether the pixel belongs to a certain shape or not. The gloss information may take on multiple values. Image processing makes it possible to extract and quantify the differentiation information.

[0204] The updated map represents distinguishing information in the reference frame of the transformed updated image. The distinguishing information is preferably selected from the group consisting of contour information, color information, density information, distance information, gloss information, saturation information, and information relating to the reflection and combination of these forms of information. The distinguishing information is preferably contour information.

[0205] The purpose of step B) is to modify the active intermediate model until an updated model corresponding to the deformation is obtained. Ideally, the updated model is therefore a 3D digital dental arch model, and if this 3D dental arch model is real, the deformed updated image can be obtained based on this model, ignoring the aligner if it is represented in the deformed updated image.

[0206] Thus, different models are successively tested, and the selection of the model to be tested preferably depends on the level of correspondence between the already tested models and the modified updated image, this selection preferably being performed using an optimization method selected from known optimization methods, in particular preferably from evolutionary metaheuristic optimization methods, in particular from simulated annealing methods.

[0207] Preferably, the metaheuristic optimization method comprises: - preferably, Evolutionary algorithms selected from evolutionary strategies, genetic algorithms, differential evolution algorithms, distribution estimation algorithms, artificial immune systems, path relinking, shuffled complex evolution, simulated annealing, ant colony optimization algorithms, particle swarm optimization algorithms, tabu search, and GRASP methods; - Kangaroo algorithm, - Fletcher-Powell method, - noise method, - Probabilistic tunneling, - random-restart hill climbing, - Cross-entropy method, and It is selected from the group formed by hybrid methods that combine the above-mentioned metaheuristic methods.

[0208] Preferably, step B) comprises the following steps: B1) defining the model to be tested by moving in the active intermediate model of the tooth model of a non-matching tooth, in particular a tooth that is out of alignment; B3) generating a view of the model to be tested under said constrained virtual acquisition conditions; B4) processing the views to generate at least one test map that at least partially represents said differentiation information; B5) testing the model to be tested by comparing the updated map with the test map, thereby measuring the difference between the updated map and the test map, this difference being called "goodness of fit" or "match"; B6) depending on said difference, for example if the difference is less than a threshold value, - modify the model to be tested by moving one or more tooth models of non-matching teeth, especially of the missing teeth, and then return to step B3), or - defining the updated map as the tested model that has the smallest difference from the updated map of the test map.

[0209] The measurement of the difference depends on the discrimination information used, and may be measured, for example, via the ratio of the number of points belonging to both the contour of the test map and the contour of the updated map to the total number of points of the contour of the updated map, or via the product of the inverse of the average distance between the contours represented in the updated map and the test map and the length of the contour represented in the updated map.

[0210] The updated model obtained at the end of step B) is therefore highly accurate, since it is a model resulting from successive modifications of the active intermediate model and is obtained by deformation of the initial model. Advantageously, the updated model is therefore highly accurate, despite being obtained based on simple photographic or video images taken without any particular precautions.

[0211] Tooth models cannot interpenetrate each other. Therefore, the movement of the tooth model of the dislodged tooth, especially in step 5), is restricted by the tooth model of the non-dislodged tooth that remains stationary, which further accelerates the search for the updated model.

[0212] Moving the teeth model of the active intermediate model results in an updated model that may be observed under the condition that the view of the updated model matches the deformed updated image, in other words, this view may coincidentally overlap with the deformed updated image, such that the teeth represented in the view and the teeth represented in the deformed updated image overlap substantially exactly.

[0213] The update of the active intermediate model may be refined by repeating the previous operation using multiple update images as analysis and / or deformation update images, resulting in an updated model that represents the teeth substantially in their actual configuration at the time of the update. As an alternative or in addition to using optimization methods, the search for the updated model is performed using a deep learning device, and preferably a neural network.

[0214] Movement of the tooth model of the mismatched tooth in response to the assessment of the mismatch In one embodiment, analysis of the analysis update image allows the non-conformance to be quantified by a "degree of non-conformance."

[0215] Specifically, in one embodiment, analysis of the analysis update image allows for measurement of the deviation, preferably the variation of deviation along the edge of the deviation tooth.

[0216] This information about the incompatibility is preferably used in step 5) to move the tooth models of the mismatched teeth, especially the missing teeth. For example, in FIG. 12, the measurement of d can be used to move, for example, the translation dd min tooth D1 may be moved downward via

[0217] It is particularly useful to have as an initial action in step 5) a movement of the tooth model according to the nature and amplitude of the incompatibility assessed based on the analyzed updated image, which is preferably followed by a fine movement, preferably via optimization or using a deep learning device, preferably a neural network.

[0218] In step 6), at least one updated aligner is designed that is suitable for modifying the dental arch from its actual configuration at the time of the update toward its final configuration. "Toward said final configuration" means that the updated aligner is shaped to modify the configuration of the dental arch closer to the final configuration. However, multiple new aligners may be required to reach the final configuration.

[0219] Preferably, a new set of aligners is designed taking into account the updated model rather than the initial model. Steps a) to d) above are used to do this, preferably exchanging the initial time and initial model for the updated time and updated model, respectively.

[0220] In step 7), at least one or more aligners of the new series of aligners are manufactured, preferably similar to step e).

[0221] The aligner may be manufactured, for example, according to the teachings of EP1835864.

[0222] These new aligners are given to the patient, for example, by mail.

[0223] The patient then continues treatment with these new aligners.

[0224] system The method according to the invention is at least partly, preferably entirely, implemented by a computer. Any computer may be envisaged, in particular a PC, a server or a tablet.

[0225] A computer conventionally comprises, inter alia, a processor, a memory, a human-machine interface conventionally comprising a keyboard, a screen and a mouse, a module for communication via the Internet, via WiFi, via Bluetooth or via a telephone network, and a communication bus. The memory conventionally comprises a ROM memory and a RAM memory. A software package configured to carry out part of the method of the invention is loaded into the memory of the computer.

[0226] The computer may be connected to a printer, scanner, CD-ROM drive, DVD drive, hard disk drive, disc burner, or loudspeaker.

[0227] A communication bus is a device that ensures wired or remote communication between other elements of a computer.

[0228] The computer, automatically or with the assistance of an operator, - in step a), displaying and manipulating the initial model, in particular modifying the observation points of the initial model; - in step a), cutting the initial model, - Decide on the final model, - determining and / or displaying potential scenarios for a given treatment; - displaying and / or determining treatment scenarios and thus determining and storing intermediate models; - in step 2) determining the active intermediate model, - in step 3), analyzing the updated image to detect non-matching teeth, especially missing teeth, - in step 4), identifying tooth models of non-matching teeth, in particular of out-of-place teeth, within the active intermediate model; - In step 5), the teeth model of the active intermediate model is moved; In optional step 6) and step d), it may be used to design an aligner.

[0229] The operator may in particular be a dental professional, preferably an orthodontist. The computer may implement one or more deep learning devices, preferably neural networks.

[0230] FIG. 6 shows a system in a preferred embodiment of the present invention.

[0231] The system comprises a plurality of mobile phones 21, for example more than 1000, preferably more than 10,000, belonging to a patient P and each communicating with a centralized computer 50.

[0232] The centralized computer 50 is preferably configured to receive and process updated images, particularly aligner images Ig and exposed teeth images Id, for a plurality of patients, preferably more than 100, more than 1000, or more than 10,000 patients. The centralized computer 50 may be configured to receive and process updated images for patients who are all being treated by the same orthodontist. The centralized computer 50 is preferably configured to receive and process updated images for patients who are being treated by a plurality of different orthodontists, for example, more than 10, more than 100, or more than 1000 orthodontists.

[0233] The centralized computer 50 comprises a communications module for communicating with a plurality of local computers 52, e.g., more than 10 or more than 100 local computers, preferably located within the orthodontic clinic, e.g., via WiFi, via Bluetooth, via optical fiber, or via the telephone network.

[0234] The system also includes multiple scanners 54 that communicate with one or more local computers, preferably each scanner communicating with a single local computer, for example, via a wired link, WiFi, Bluetooth, fiber optics, or telephone network. Each scanner 54 is preferably located in the same location as its respective local computer, preferably within the same orthodontic office.

[0235] The system also comprises a manufacturing unit provided with a manufacturing computer 56 which communicates with the centralized computer and / or local computers, for example via a wired link, via WiFi, via Bluetooth, via optical fiber or via a telephone network.

[0236] Example In step a), at an initial time, an initial model M0 is generated using a scanner 54. The initial model M0 is then sent to a local computer 52. A software package loaded on the local computer preferably enables the initial model to be automatically cut to create tooth models.

[0237] After examining the patient, the orthodontist creates the final model M by moving the tooth model using a local computer. f Define the following.

[0238] The local computer 52 is preferably programmed to determine one or more scenarios of dental arch modification in steps b) and c) so that the dental arch reaches a final configuration corresponding to the final model. The local computer also preferably allows the orthodontist to view potential scenarios and select a treatment scenario. The orthodontist can also preferably create or modify scenarios suggested by the local computer 52.

[0239] The intermediate times and corresponding intermediate models may be defined by the local computer or may be suggested to the orthodontist by the local computer 52 so that the orthodontist may verify and / or modify the intermediate times and intermediate models.

[0240] The local computer 52 stores the treatment scenario, in particular the at least intermediate model M i and the initial and final models M0, M f to the centralized computer 50.

[0241] In step d), a software package loaded on the centralized computer 50 determines the shape of the aligner to be manufactured based on these models and then sends this information I0 to the manufacturing unit in step e) for the purpose of manufacturing the aligner G0.

[0242] Alternatively, the initial, intermediate and final models may be sent by the centralized computer 50 to a manufacturing computer 56, which determines the shape and controls the manufacturing of the N aligners in step d).

[0243] Again alternatively, step d) may be performed by the local computer 52. The local computer then transmits the information necessary to manufacture the aligner to the manufacturing unit.

[0244] Aligner G0 is sent to the patient, and the patient begins treatment.

[0245] The patient preferably receives a reminder requesting the patient to take one or more update images, preferably at least one aligner image and preferably one or more images of the exposed teeth.

[0246] In step 1), the patient takes photos at the time of the update, both with and without the active aligner that should be worn at that time. The patient uses their mobile phone 21 for this purpose and transfers these photos to the centralized computer 50.

[0247] In step 2), the centralized computer identifies the active intermediate model according to the update time of the photograph acquisition. Preferably, the centralized computer identifies as the active intermediate model the intermediate model whose intermediate time is closest to the update time. More preferably, the centralized computer identifies as the active intermediate model the intermediate model used to design the active aligner worn by the patient at the update time.

[0248] In step 3), the centralized computer 50 analyzes the photographs, particularly photographs depicting the aligners in their positions, with the goal of automatically detecting misfits, particularly misaligned teeth, and identifying any misfitting, particularly misaligned teeth. If no misfitting, particularly misaligned teeth, are detected, the centralized computer 50 sends a message to the patient and / or orthodontist informing them that treatment is progressing normally.

[0249] Preferably, the centralized computer 50 is programmed to identify such teeth.

[0250] If not so programmed, the centralized computer 50, in step 4), optionally with the assistance of an operator, identifies tooth models of non-matching teeth, particularly teeth that are out of place.

[0251] In step 5), the centralized computer generates an updated model M that matches the photo taken at the update time. a The active intermediate model is modified by moving the tooth models of the mismatched teeth, especially the outlying teeth, until

[0252] In step 6), the centralized computer designs one or more new aligners G1 taking into account the updated model, and then sends the information necessary to manufacture the aligners G1 to the manufacturing computer 56 of the manufacturing unit.

[0253] In step 7), the manufacturing unit manufactures new aligners G1, which are then sent to the patient, who may continue their treatment with these new aligners.

[0254] Variations In one embodiment, the method according to the present invention uses the aligner images to update the determined active intermediate model at an initial time and at an intermediate time t indicating an aligner change. i Therefore, the intermediate model of the treatment scenario represents the dental arch in the expected configuration at each intermediate time t when the patient is required to change aligners. n Thus, the patient begins wearing the first aligner in the series at the beginning of treatment, i.e., essentially at the initial time t1 when the initial model is generated, and then changes aligners at intermediate times t2, t3, etc. Thus, the patient begins wearing the first aligner in the series at the beginning of treatment, i.e., essentially at the initial time t1 when the initial model is generated, and then changes aligners at intermediate times t2, t3, etc. i is the expected time to replace the (i-1)th orthodontic aligner in the series with the i-th orthodontic aligner in the series, where i is greater than or equal to 2. If treatment is planned to use, for example, 30 aligners (N=30), the patient will be expected to receive treatment at time t 30 The 30th aligner was started at t and this aligner was placed at the final time t 31 Wear it until

[0255] The number N of aligners may be more than 5, more than 10, more than 20, or more than 30 and / or less than 60, preferably less than 50.

[0256] The time interval between two successive changes of the aligners, i.e., between two successive intermediate times, may be more than 7 days, or more than 15 days, and / or less than 60 days, preferably less than 30 days.

[0257] In one embodiment, the treatment scenario is not limited to a series of intermediate models for aligner changes, but includes other intermediate models where the intermediate time does not indicate an aligner change. Preferably, the treatment scenario is a substantially continuous series of intermediate models. Thus, the treatment scenario is similar to a movie that allows visualization of the progression from the initial model to the final model.

[0258] Therefore, the suitability of the active aligner may advantageously be checked at any time. Update images may be acquired at any update time during treatment. Then, depending on the treatment scenario, an active intermediate model is selected that corresponds to the update time, i.e., represents the dental arch in the configuration expected according to the treatment scenario with respect to the update time.

[0259] In one embodiment, additional intermediate models may be generated from the intermediate models of the treatment scenario and added to the treatment scenario. Specifically, if the update time is between two intermediate times t i and t i+1 and the intermediate time t i and t i+1 From the intermediate model, additional intermediate models may be created that serve as active intermediate models. Additional intermediate models may be generated, particularly during treatment.

[0260] As is now clear, the method according to the invention makes it possible to obtain, based on a simple photograph or a simple video, a highly accurate updated model that corresponds to the actual configuration of the dental arch at the time of the update, without the need to perform a new scan. Thus, the method may be performed without the need to make an appointment with an orthodontist.

[0261] Of course, the invention is not limited to the embodiments described and illustrated above.

[0262] Orthodontic treatment may be for therapeutic and / or cosmetic purposes.

[0263] Multiple update images may be used in step 3) and / or step 5).

[0264] Tooth model placement errors may be used to detect drift in orthodontic treatment, i.e., to detect situations where the progression of tooth positions does not follow the treatment scenario.

[0265] Finally, the patient need not necessarily be a human being: in particular, the method according to the invention may be used with other animals. [Explanation of symbols]

[0266] 10 Orthodontic Aligners 12 grooves 15 Photography Kit 17 Holder 19 Dental retractors, retractors 20 bottom 21 Mobile Phone 22 Free end 23 Groove 241 outer tooth profile, first tooth 242 outer tooth profile, second tooth 243 Outer tooth profile, third tooth twenty four i Outer tooth outline 26a, 26b lugs 27a, 27b clip 301 Inner tooth profile, first tooth 302 inner tooth profile, second tooth 303 Inner tooth profile, third tooth 30 i Inner tooth outline 32 tooth model 50 Centralized Computer 52 Local Computer 54 Scanner 56 Manufacturing Computer D1, D2, D3 teeth d distance d min Shortest distance G0, G1 aligner I0 Information Image of exposed teeth Ig Aligner Image M0 early model M i Intermediate model M f Final model M a Updated model P patient Sd distance threshold S(d,Sd) distance score t1 initial time t n Intermediate Time t N+1 Final Time X-axis

Claims

1. A computer-readable storage medium for storing computer programs, The computer program includes program code instructions for executing a method of generating a three-dimensional digital model of the patient's dental arch, called the "updated model," during the treatment of the dental arch by an orthodontic aligner called the "active aligner." The aforementioned treatment, initial time (t １ ) generates multiple intermediate models (M ｉ The treatment scenario is simulated by including the following: each intermediate model is a three-dimensional digital model of the dental arch, the intermediate model is cut to create a tooth model, and each intermediate time (t) after the initial time ｉ Determined to represent the dental arch in ) The method for generating the above is: 2) A step of determining the intermediate model or "active intermediate model" according to the update time in the process of the treatment, 3) A step of searching for the representation of one or more teeth that do not conform to the treatment scenario in an updated image called an "analysis update image," wherein the updated image represents the active aligner attached to the dental arch at the usage position, or the image of an exposed tooth (Id) represents the dental arch without an aligner, and is acquired by an image acquisition device at the update time. If one or more mismatched teeth are detected, 4) The steps of identifying one or more tooth models that represent one or more mismatched teeth in the active intermediate model, 5) A step in which the active intermediate model is automatically deformed by a computer until an updated model that conforms to at least one of the updated images called a "deformed updated image" is obtained, wherein during the deformation of the active intermediate model, the tooth models that are moved are only tooth models of teeth that do not conform. Includes, In the method described above, the non-conformity of at least one of the misfit teeth is measured by comparing the updated image with the active intermediate model, and then, in step 5), the tooth model of the at least one misfit tooth is moved in a computer-readable storage medium in accordance with the measurement.

2. In step 3), in order to detect mismatched teeth, the position, localization, and calibration of the virtual acquisition device are pursued so that the virtual acquisition device has a view on the active intermediate model that is as close as possible to the analysis update image, and then, The view and the analysis update image are compared, or the updated map representing the distinction information of the analysis update image is compared with the reference map representing the distinction information in the view, and / or The computer-readable storage medium according to claim 1, wherein the analysis update image is an aligner image, and the external shape of at least one tooth and the external shape of the active aligner are determined in the analysis update image, and then the external shapes are compared with each other.

3. In step 5), the movement of the tooth model of the misfitted tooth is an iterative process, and in each iteration, One or more of the tooth models of the mismatched teeth are moved to obtain the dental arch model to be tested, and then, The dental arch model to be tested is tested by evaluating the degree of fit between the dental arch model and the deformed updated image. The computer-readable storage medium according to claim 1, wherein the updated model is the model having the best fit among all the tested models.

4. Prior to the iterative process, the position, localization, and calibration of the virtual acquisition device, or "constrained virtual acquisition conditions," are pursued to enable observation of the active intermediate model to generate a view in which the representation of the fitted teeth in the deformed updated image can coincide with and overlap the representation of the fitted teeth, and then, The computer-readable storage medium according to claim 3, wherein during the iterative process, in each iteration, the degree of fit between the dental arch model under test and the deformed updated image is evaluated by comparing the deformed updated image with a view of the dental arch model under test under the constrained virtual acquisition conditions.

5. The updated image is an image extracted from a photograph or video, and is acquired using a mobile phone, as described in any one of claims 1 to 4, on a computer-readable storage medium.

6. The computer-readable storage medium according to any one of claims 1 to 5, wherein in step 5), the deformation of the active intermediate model includes movement of the tooth model of the active intermediate model, the movement is continued until the positional error for each tooth model, taking into account the deformation update image, is less than 1 mm, preferably less than 5 / 10 mm, preferably less than 3 / 10 mm, preferably less than 2 / 10 mm, preferably less than 1 / 10 mm.

7. In step 5), the deformed updated image is an image of an exposed tooth, according to any one of claims 1 to 6, on the computer-readable storage medium.

8. The computer-readable storage medium according to any one of claims 1 to 7, wherein the active intermediate model is selected such that the difference between the intermediate time and the update time of the active intermediate model is less than two weeks.

9. The computer-readable storage medium according to any one of claims 1 to 8, wherein the intermediate model of the treatment scenario represents the dental arch in the configuration expected at an intermediate time indicating aligner replacement.

10. The computer-readable storage medium according to any one of claims 1 to 9, wherein the treatment scenario is a substantially continuous series of intermediate models.

11. The computer-readable storage medium according to any one of claims 1 to 10, wherein, prior to step 2), an intermediate model of the dental arch is generated from an intermediate model of the treatment scenario and then added to the treatment scenario via the intermediate model.

12. In step 3), the representation of a tooth in the analysis update image is not suitable for the treatment scenario if, when the analysis update image coincides with and overlaps with the view of the active intermediate model that is adapted to the analysis update image which is at the same scale and actual size as the view of the active intermediate model, at least one point of the representation is located at a distance of more than 1 / 10 mm and less than 7 mm from a corresponding point in the view, according to any one of claims 1 to 11.

13. A system for manufacturing orthodontic aligners, A computer-readable storage medium for storing a computer program including program code instructions for performing a method for generating an updated model according to any one of claims 1 to 12, the medium then stores a computer program including program code instructions for performing a method for generating an updated model according to any one of claims 1 to 12, 6) A step of designing an “updated” aligner suitable for modifying the dental arch from the actual configuration at the update time to the theoretical final configuration, based on the updated model and the final model representing the dental arch in the theoretical final configuration, and transmitting the information necessary to manufacture the updated aligner to a manufacturing unit. Computer-readable storage media, A manufacturing unit, 7) A manufacturing unit that carries out the step of manufacturing the updated aligner, Equipped with, Step 6) above is performed by a computer, in a system.

14. The computer-readable storage medium according to claim 1, wherein step 2) is performed following step 3).

Images