METHOD FOR EVALUATING AN ORTHODONTIC SOLDER

Abstract

The invention relates to a computer-based method for evaluating, at a current time, the conformity of an orthodontic aligner to a patient's dental arch, referred to as the "supporting arch." The method comprises the following successive steps: creation of a three-dimensional digital model of the supporting arch in its current configuration, or "updated reference model," and determination, within the updated reference model, of a support surface for the aligner; deformation of the support surface according to the geometry of the aligner to obtain a deformed support surface; comparison of an external surface of the aligner with the deformed support surface; and determination, based on this comparison, of at least one conformity score for the aligner to the supporting arch. No abstract figure is provided.

Description

Title of the invention: METHOD FOR EVALUATING AN ORTHODONTIC SOLDER technical field

[0001] The present invention relates to a method for evaluating the conformity of an orthodontic aligner worn by a patient, in particular for evaluating the conformity of the shape of the orthodontic aligner to the positioning of the patient's teeth. The invention also relates to a method for adapting a treatment using orthodontic aligners.

[0002] The invention also relates to a computer program for implementing these processes. State of the art

[0003] Typically, at the beginning of orthodontic treatment, the orthodontist determines the desired tooth positioning at a given point in the treatment, known as the "setup." The setup can be defined using an impression or a three-dimensional scan of the patient's teeth. The orthodontist then fabricates an orthodontic appliance adapted to this treatment accordingly.

[0004] The orthodontic appliance may be an orthodontic aligner. An aligner typically takes the form of a removable one-piece appliance, usually made of a transparent polymer material, which has a channel shaped so that several teeth of an arch, generally all the teeth of an arch, can be accommodated in it.

[0005] The shape of the channel is adapted to keep the gutter in position on the teeth, while exerting a corrective action on the positioning of certain teeth.

[0006] Typically, at the beginning of treatment, the shapes that the different aligners should take at different times during treatment are determined, and then all the corresponding aligners are manufactured. At predetermined times, the patient changes aligners.

[0007] Treatment using aligners is advantageously less burdensome for the patient. In particular, the number of appointments with the orthodontist is limited. Furthermore, the pain is less than with a metal orthodontic archwire attached to the teeth.

[0008] At regular intervals, the patient visits the orthodontist for a visual check, in particular to check if the movement of the teeth is in accordance with expectations and if the aligner he is wearing is still suitable for the treatment.

[0009] If the orthodontist diagnoses a maladaptation to the treatment, and in particular in detachment of the aligner, he takes a new impression of the teeth, or, equivalently, a new scan of the teeth, and then orders a new series of aligners configured accordingly.

[0010] The need to travel to the orthodontist is a burden for the patient. The patient's trust in their orthodontist may also be affected. Finally, it results in an additional cost. The number of check-up visits to the orthodontist should therefore be limited.

[0011] The unsuitability of a gutter can also be unsightly.

[0012] To solve these problems, the Applicant proposed, in EP3412245, a method for evaluating the shape of an orthodontic splint worn by a patient.

[0013] This method greatly facilitates the assessment of the suitability of the aligner for the treatment. In particular, it can be implemented using simple photographs or videos, taken without any special precautions, for example by the patient. The number of appointments with the orthodontist can therefore be limited.

[0014] The method described in EP3412245 is based on a comparison of the contours of the teeth and the splint in photographs. However, it can provide erroneous information when these contours are difficult to distinguish in the photographs.

[0015] There is a need for a solution to this problem.

[0016] One object of the invention is to meet, at least partially, this need. Summary of the invention

[0017] The invention provides a method for evaluating, by computer, at an "updated" time, the conformity of an orthodontic splint to a patient's dental arch, referred to as the "support arch", said method comprising the following successive steps:

[0018] A) creation of a three-dimensional digital model of the support arch, in its configuration at the updated time, or "updated reference model", and determination, in the updated reference model, of a support surface for the gutter; B) deformation, depending on the geometry of the gutter, of the support surface to obtain a deformed support surface; C) comparison of an external surface of the gutter with said deformed support surface, then determination, based on said comparison, of at least one gutter conformity score to the supporting arch.

[0019] As will be seen in more detail later in the description, the invention does not seek to compare the support surface with the inner surface of the tray on which the patient's teeth should rest in the service position. Remarkably, a deformed support surface is determined from the The support surface and the gutter geometry are then deformed, and this support surface is compared to the outer surface of the gutter. A method according to the invention thus uses the outer surface of the gutter to assess the potential separation of the inner surface of the gutter from the teeth. Advantageously, the outer surface of the gutter is easily identifiable in representations of the gutter.

[0020] The reliability of the comparison is improved. Step A)

[0021] The updated reference model can be produced with a scanner.

[0022] An "updated tooth model" is a tooth model in the model of updated reference.

[0023] In a particularly advantageous embodiment, at an initial time prior to step A), an initial reference model is created and the initial reference model is sliced ​​so as to define, for each tooth represented in the initial reference model, a digital three-dimensional reference model of said tooth, or "initial tooth model". Then, at the updated time, the initial tooth models are moved to create the updated reference model. The movement is preferably optimized to obtain an updated reference model compatible with at least one updated image of the supporting arch acquired less than one month, one week, one day, or one hour before the updated time.

[0024] The updated tooth models are then initial tooth models, possibly displaced.

[0025] The initial moment may be, in particular, at the beginning of orthodontic treatment, including the use of the orthodontic aligner. In one embodiment, the time interval between the initial moment and the start of the patient's orthodontic treatment is less than one month or one week.

[0026] The current time is during orthodontic treatment with aligners. The time interval between the current time and the initial time may therefore be greater than 1 week, 1 month or 3 months.

[0027] Preferably, the initial reference model is made with a scanner, with high precision.

[0028] The updated image, preferably a photograph, can be acquired with a mobile phone, for example by the patient themselves. Moving the initial tooth models advantageously allows for the creation of a very precise updated reference model, corresponding to the tooth configuration at the current moment, but based solely on the updated image(s), and therefore without having to perform a new scan. The procedure can thus be implemented without having to make an appointment with the orthodontist. Step B)

[0029] Preferably, said deformation is, at a point on the support surface, preferably at least at any point on the portion of the support surface that defines the free ends of the tooth patterns, preferably at any point on the support surface, determined as a function of the distance between the inner and outer surfaces of the groove at a point on the inner surface of the groove intended to be, in the service position, in contact with said point on the support surface. Preferably, said deformation is proportional, preferably of an amplitude substantially equal to said distance.

[0030] In one embodiment, the deformation is of constant amplitude, at every point of the support surface.

[0031] Preferably, in step B), the support surface is deformed so that the deformed support surface extends substantially along the outer surface of the representation of the gutter if this gutter were modeled in the updated reference model in its service position, in the absence of detachment of the gutter.

[0032] The deformation of the support surface preferably reproduces the transformation that leads to the outer surface of the gutter from the inner surface of the gutter. In particular, the deformation preferably comprises a swelling of the support surface with an amplitude substantially equal to the distance between the inner and outer surfaces of the gutter, preferably substantially equal to this distance, at least in the portion of the inner surface that defines the free ends of the tooth models. For example, if the gutter has a constant thickness "e", the deformation is that which would be obtained by swelling the teeth to make them thicker by an additional thickness "e".

[0033] In a preferred embodiment, in step A), the updated reference model is cut so as to define, for each tooth represented in the updated reference model, an updated tooth model. The support surface is then defined by the surfaces of the updated tooth models. In step B), the surface of each updated tooth model is deformed to obtain a deformed tooth model, then the deformed tooth models are merged and the deformed support surface is defined as being at least a part, or even all, of the envelope of the assembly consisting of the merged deformed tooth models.The deformation of the surface of an updated tooth model is preferably a swelling of the updated tooth model, preferably of a constant amplitude, preferably greater than 0.5 mm and / or less than 5 mm, 4 mm or 2 mm, and / or is, at a point on the surface of an updated tooth model, determined as a function of the distance between the inner and outer surfaces of the tray at a point on the inner surface of the tray intended. to be, in the service position, in contact with said point on the surface of the updated tooth model. Preferably, the amplitude of said deformation at said point on the surface of an updated tooth model is proportional, preferably substantially equal to said distance.

[0034] In a preferred embodiment, - in step A), an image of the gutter is taken at the updated time, in a service position in which it is supported by said support arch, or "gutter image", - We determine the outline of the outer surface of the gutter, or "outer outline of the gutter", represented on the gutter image, - We look for "framed" observation conditions offering a view of the updated reference model compatible with the gutter image, that is to say, presenting a maximum concordance with the representations of the teeth on the gutter image, - in step B), the support surface is deformed, preferably the updated tooth models are inflated, preferably by a constant amplitude, and - in step C), the outer contour of the gutter is compared with a contour of the deformed support surface, or "deformed support contour", shown on a view of the deformed updated reference model observed under the framed observation conditions.

[0035] The outer contour of the gutter has the advantage of generally being clearly visible in the gutter image. The inventors discovered that this outer contour could be very significantly different from the contour of the free ends of the teeth covered by the gutter and along which it extends. However, after simulating tooth thickening on the updated reference model, the set of swollen tooth models defines a deformed support surface that is comparable to the outer surface of the gutter, at least in the vicinity of the free ends of the teeth.

[0036] In particular, the observation, under identical conditions, of the deformed support surface and the outer surface of the gutter makes it possible to define a deformed support contour and a gutter contour, respectively, the differences of which make it possible to evaluate the conformity, that is to say to detect a detachment (or "unseat") of the gutter.

[0037] For example, it can be deduced that if the deformed support contour is substantially identical to the outer contour of the splint, the splint rests on the teeth in the region of these contours. Conversely, the distance between these contours or the variation of this distance along these contours may indicate abnormal detachment of the splint.

[0038] Preferably, the image of the aligner, preferably a photograph, is acquired with a mobile phone. The evaluation is thus possible from a simple image of the aligner, for example, a photograph taken by the patient, for example, with their mobile phone. The procedure can therefore be reliably implemented using simple photographs or videos taken without any special precautions, for example, by the patient. The number of appointments with the orthodontist can therefore be limited.

[0039] The gutter image can serve as an updated image to move the tooth models from an initial reference model in order to create the updated reference model. Step C)

[0040] Step C) preferably comprises the following steps:

[0041] i) determination of a distance between the contour of the deformed support and the outer contour of the gutter; ii) determination of the conformity score based on the distance between said contours.

[0042] These distances can be measured in pixels.

[0043] Preferably, the method includes, in step C), an operation of comparing the conformity score to an acceptability threshold and, preferably, the emission of information based on the result of the comparison.

[0044] Preferably, before comparing the outer contour of the gutter and the contour of the deformed support, the representation of an element on the updated image and the representation of said element on the gutter image are superimposed in register, the element being an element not modified by wearing the gutter, preferably a gum contour.

[0045] The evaluation process is preferably implemented by computer, in particular for the steps of modifying a model, calculating or exploring a model, in particular to search for a framed view, or analyzing images or views to search for contours.

[0046] The evaluation process is implemented "by computer" because a computer is implemented to carry out, at least partially, some of its steps.

[0047] The invention also relates to: - a computer program, and in particular a specialized mobile phone application, comprising program code instructions for the execution of one or more, preferably all, steps B) to C), and preferably step A), when said program is executed by a computer, - a computer storage medium on which such a program is recorded, for example, a memory chip or a CD-ROM, and - a personal device, in particular a mobile phone or tablet, into which such a program is loaded.

[0048] The invention also relates to a system comprising: - a three-dimensional scanner capable of creating an initial reference model, or an updated reference model, and - a personal device, preferably a mobile phone, loaded with a program including program code instructions for the execution of one or more, preferably all, steps B) to C), and / or, in step A), for the generation of an updated reference model from an initial reference model, when said program is executed by a computer.

[0049] The invention also relates to a method for adapting orthodontic treatment, a method in which an evaluation method according to the invention is implemented, and then, depending on the result of said evaluation, a new splint is manufactured.

[0050] Orthodontic treatment can be therapeutic and / or aesthetic.

[0051] The invention finally relates to a method of manufacturing an orthodontic splint, a method in which a method of evaluating a first splint, according to the invention, is implemented, and then, depending on the result of said evaluation, a second splint is manufactured. Definitions

[0052] By "dentition" we mean a set of teeth.

[0053] By "patient" is meant any person for whom a procedure according to the invention is implemented, whether that person is ill or not.

[0054] The "acquisition conditions" specify the position and orientation in space of an image acquisition device relative to the patient's teeth (actual acquisition conditions) or to a three-dimensional model of the patient's teeth (virtual acquisition conditions), and preferably the calibration of this image acquisition device, and in particular the values ​​of the diaphragm aperture, exposure time, focal length, and sensitivity. Acquisition conditions are said to be "virtual" or "theoretical" when they correspond to a simulation in which the acquisition device would be in said acquisition conditions (theoretical positioning and, preferably, calibration of the acquisition device).

[0055] The "observation conditions" specify the conditions under which a model is observed. When the observation is carried out by an acquisition device to acquire an image, the observation conditions are the "acquisition conditions".

[0056] By "model" is meant a three-dimensional digital model. A model consists of a set of voxels. A "model of an arch" is a model representing at least part of a dental arch, preferably at least 2, preferably at least 3, preferably at least 4 teeth.

[0057] A "support surface" of a splint is a surface that partially or completely models the surface of a dental arch against which the splint rests in the service position. It may be, but is not necessarily limited to, the surface against which the splint rests in the service position. In particular, it may be the surface that models the teeth.

[0058] A 3D scanner is a device that allows a model of an object to be obtained.

[0059] An observation of a model, under determined observation conditions, in particular at a determined angle and distance, is called a "view".

[0060] By "image" we mean a two-dimensional image, such as a photograph. An image is made up of pixels.

[0061] By "view of an arch", "representation of an arch", "scan of an arch", or "model of an arch", one means a view, a representation, a scan or a model of all or part of said dental arch.

[0062] A three-dimensional digital model of a patient's set of teeth is "compatible" (or "exhibits maximum concordance") with an image when there exists a view of that model that corresponds to said image, that is, such that the teeth of said model are positioned, relative to each other, like the real teeth they model. Thus, an updated reference model is compatible with an updated image if a view of the updated reference model allows the contours of the tooth models to be observed in such a way that they are superimposable in register with the contours of said teeth on said updated image.

[0063] Similarly, a view of a model can be considered "compatible," or "register-matchable," with an image when it exhibits maximum concordance with the image. Achieving maximum concordance can, in particular, result from an optimization operation or the implementation of a neural network.

[0064] Simulating tooth thickening is an operation by which a layer of material, or "thickness," is simulated on the outer surface of the tooth. The "outer surface" of the tooth is the surface of the tooth exposed to the oral environment, excluding the tooth roots. Therefore, thickening a tooth does not result in the boundary between the gum and the tooth being moved towards the free edge of the tooth.

[0065] The simulation of a thickening of a tooth carried out on a model of that tooth produces a "swelling" of that tooth model.

[0066] The simulation of a thickening of a plurality of teeth is an operation by which the addition of an extra thickness to the outer surface of each of the teeth is simulated. teeth, ignoring physical interactions between adjacent teeth. The simulation of thickening of a plurality of teeth is performed using an arch model, with each tooth model in the arch model being inflated to represent the thickening of the modeled tooth. When two tooth models are side-by-side, their inflation can lead to interpenetration of these tooth models.

[0067] The “service position” is the position in which the gutter is worn by the patient.

[0068] “Understand”, “include” or “present” must be interpreted in such a way broad, non-limiting, unless otherwise indicated. Brief description of the figures

[0069] Other features and advantages of the invention will become apparent upon reading the detailed description that follows and upon examination of the accompanying drawing in which: - [Fig.l] represents a perspective view of an orthodontic splint; - [Fig.2] represents a top view of the orthodontic splint of the [Fig.l] ; - [Fig.3] represents an example of a reference model; - [Fig.4] represents an example of an initial reference model of which the tooth models have been cut out (only the tooth models are shown); - [Fig. 5] schematically represents a support arch carrying a orthodontic splint; - [Fig.6] represents a register superimposition of a gutter image, in the form of a photo, and a framed view of an updated reference model, the representations of the teeth on the gutter image showing maximum concordance with the representations of the teeth on this view; - [Fig.7] represents the superposition of [Fig.6] after deformation of the models of teeth by swelling; - [Fig. 8] schematically illustrates a method according to the invention in a mode favorite achievement; - [Fig.9] schematically illustrates a process according to the invention; - [Fig. 10] schematically illustrates the acquisition of a gutter image; - [Fig. 11] schematically illustrates a spreader that can be used with the kit acquisition represented on the [Fig. 10]; - [Fig. 12] illustrates an example of the implementation of steps i) to iii) for a step C); - [Fig. 13] illustrates an example of the implementation of steps i' ) to iü') for a step C). Detailed description

[0070] As shown in [Fig. 1], a gutter 10 extends so as to follow the successive teeth of the supporting arch on which it is fixed. It defines a generally U-shaped groove.

[0071] The inner surface 12 of the tray, oriented towards the teeth in the service position, is called the "channel." The shape of the channel is determined to ensure the attachment of the tray to the teeth, but also according to a desired target positioning of the teeth. More precisely, the shape is determined so that, when the tray is in its service position, it exerts forces tending to move the treated teeth towards their target positioning.

[0072] The teeth which support the gutter in the service position belong to the support arch 13 of the gutter.

[0073] The outer surface 14 is the surface opposite the inner surface 12. It is oriented towards the cheeks and lips in the service position.

[0074] The material of the splint separating the outer surface 14 and inner surface 12 of the splint at a point M on the inner surface defines the thickness "e" of the orthodontic splint. This thickness is visible in [Fig. 3]. The splint may have a variable or substantially constant thickness.

[0075] In the region of the free ends of the teeth, the thickness is conventionally substantially constant. The outer surface 14 of the groove, which extends parallel to the bottom 20 of the channel, therefore generally appears to be substantially the same shape as the bottom of the channel.

[0076] According to the invention, the shape of the gutter is evaluated by comparing the outer surface of this gutter, in its service position, with a surface of a model of the dental arch, or "support surface" 33, which has been deformed according to the geometry of the gutter, or "deformed support surface" 33.

[0077] In a preferred embodiment, this evaluation is carried out by comparing representations of these surfaces on images. In particular, an outer contour of the gutter represented on a gutter image, preferably a photograph, is compared with a "deformed support contour" defined by observation of the deformed reference model.

[0078] The bottom 20 of the groove has a shape substantially complementary to that of the free ends 22 of the teeth. Consequently, in an image representing the bottom of the groove, the contour of the bottom of the groove can be compared to a contour of the teeth to evaluate a gap between the bottom of the groove and one or more free ends of teeth. In an image, especially in a photo, the outline of the bottom of the groove is often difficult to distinguish, particularly because the gutter is not perfectly transparent and can distort the path of light.

[0079] Unlike the channel, the outer surface 14 of the channel has the advantage of being clearly visible in images, and particularly in photographs. However, as illustrated in [Fig. 5], the outer surface 14 is not simply a homothety of the channel bottom. The shape of the outer surface 14 can therefore deviate significantly from that of a surface identical to that of the channel, particularly in the regions between the teeth.

[0080] In an image, the contour of the outer surface 14 of the gutter, or “outer contour of the gutter” 24, does not therefore precisely define the contour of the bottom of the groove. A comparison between the outer contour of the gutter 24 and the contour of the free ends of the teeth that support the gutter, or “support contour” 30 ([Fig. 5]), therefore does not allow for a completely reliable conclusion regarding the possible detachment of the teeth from the bottom of the groove.

[0081] The method of the invention aims to detect, from the outer contour of the gutter, which is generally clearly visible, situations in which the free end 22 of a tooth is no longer in contact with the bottom of the gutter, and preferably to measure the extent of this detachment.

[0082] The method is implemented when the patient needs to check the conformity of the splint he is wearing with the planned treatment, for example more than 2 weeks or more than 4 weeks after the start of treatment with the splint.

[0083] Preferably, at least one reminder informing the patient of the need to implement the procedure is sent to the patient. This reminder may be in paper form or, preferably, in electronic form, for example, as an email, an automatic alert from a specialized mobile application, or an SMS. Such a reminder may be sent by the orthodontic practice or laboratory, by the dentist, or via a specialized application on the patient's mobile phone, for example.

[0084] According to one embodiment of the invention, the outer contour of the gutter 24 is not compared to the support contour or the contour of the bottom of the gutter, but to a deformed support contour 30' ([Fig.5]) determined from the support contour 30, as described in detail below.

[0085] In step A), an updated reference model 31 ([Fig.3]) is first created to model the arch which carries or is intended to carry the gutter, at the time of the evaluation, called the "updated time". Implementation of the updated reference model

[0086] The updated reference model can be produced by any means. The updated reference model is then sliced ​​to define "updated" tooth models, as described below for the initial reference model.

[0087] To limit the number of appointments with the orthodontist, the updated reference model is indeed preferably created from an initial reference model.

[0088] The initial reference model is made at an initial time, preferably less than 6 months, preferably less than 3 months or less than 1 month or less than 2 weeks after or before the start of orthodontic treatment applied to the patient.

[0089] The initial reference model is, for example, of the type .stl or .Obj, .DXF 3D, IGES, STEP, VDA, or Point Cloud. Advantageously, such a model, called "3D", can be observed from any angle.

[0090] The initial reference model can be prepared from measurements taken on the patient's teeth or on a physical model of his teeth, for example a plaster model.

[0091] The initial reference model is preferably created using professional equipment, for example, a 3D scanner, preferably operated by a healthcare professional, for example, an orthodontist or an orthodontic laboratory. In an orthodontic practice, the patient or a physical model of their teeth can advantageously be positioned precisely, and the professional equipment can be refined. This results in a highly accurate initial reference model. The initial reference model preferably provides information on tooth positioning with an error of less than 0.5 mm, preferably less than 0.3 mm, and preferably less than 0.1 mm.

[0092] The initial reference model is then cut to define "initial" tooth models.

[0093] The segmentation of a three-dimensional model into tooth models is a classic operation by which the model is segmented in order to delimit the representation of one or more teeth. Tooth models can, for example, be defined as described, for example, in international application PCT / EP2015 / 074896.

[0094] The cutting can be partially automated.

[0095] Fig. 4 represents an example of a reference model in which the tooth models 32 have been cut out (only the tooth models are shown; they have different appearances in order to be more easily identifiable).

[0096] The initial reference model thus cut can then be deformed, by displacement of the initial tooth models, preferably without modification of the initial tooth models, to simulate the effect of time between the initial instant and the updated instant, in particular to simulate orthodontic treatment up to the updated instant.

[0097] The time interval between the initial and updated times may be less than 4 weeks, less than 2 weeks, or less than 1 week. This time interval may also be greater than 4 weeks or greater than 1 month, for example, if the aligner is not the first aligner used for orthodontic treatment and the initial reference model was made at the beginning of treatment.

[0098] To perform this update of the initial reference model, preferably an updated image is used, taken at the updated time, with an image acquisition device, preferably a mobile phone, a so-called "connected" camera, a so-called "smart" watch, or "smartwatch", a tablet or a personal computer, fixed or portable, comprising an image acquisition system, such as a webcam or a camera.

[0099] The updated image is extra-oral.

[0100] Preferably, a photo-taking kit 15 is used, as illustrated in Figures 10 and 11. Preferably, such a kit comprises a support 17, a dental retractor 19, and an acquisition device, preferably a mobile phone 21. The dental retractor 19 and the acquisition device are preferably removably attached to the support 17.

[0101] The spacer 19 may have the characteristics of conventional spacers.

[0102] As shown in [Fig. 11] (where it has been separated from the support), it preferably comprises a rim 23 extending around a retractor opening of axis X and arranged so that the patient's lips can rest on it, leaving the patient's teeth visible through said retractor opening.

[0103] The spacer 14 can be fixed to the support by one or more fasteners 27a and 27b, for example magnetic fasteners.

[0104] Preferably, the retractor has cheek retraction tabs 26a and 26b so that the acquisition device, fixed to the support, can acquire, through the retractor opening, images of the buccal surfaces of teeth located at the back of the mouth, such as molars. This feature is particularly advantageous for implementing the methods described in PCT / EP2015 / 074897.

[0105] The acquisition is preferably carried out by the patient or a relative of the patient, but may be carried out by any other person, in particular a dentist or an orthodontist, preferably without imposing a precise positioning of the image acquisition device in relation to the teeth.

[0106] Preferably, the updated image is a photograph or an image extracted from a film. It is preferably in color, preferably in true color.

[0107] In one embodiment, the updated image is an image of the teeth in the absence of the orthodontic aligner, referred to as the "naked updated image". The model update The initial reference is facilitated, as the teeth are clearly visible on an updated nude image.

[0108] In another embodiment, the patient wears the splint during the acquisition of the updated image. In other words, the same image not only allows the outer contour of the splint to be seen, and thus subsequently serves as an image of the splint, but also determines the position of the teeth at the updated time, in order to update the initial reference model.

[0109] The update of the initial reference model from the updated image is preferably carried out using an optimization algorithm.

[0110] Preferably, an iterative process is implemented whereby, at each iteration, one or more tooth models are moved, and then optimal observation conditions of the initial model thus modified (called "reference model to be tested") are determined, the optimal observation conditions being defined as the conditions allowing observation of the reference model to be tested in such a way that the view of said model is as close as possible to the updated image.

[0111] Steps c) to e) described in PCT / EP2015 / 074896 are preferably implemented:

[0112] c) analysis of the updated image (also referred to as "updated image" in PCT / EP2015 / 074896) and production of an updated map relating to discriminating information; d) optionally, determination, for the updated image, of coarse virtual acquisition conditions approximating the actual acquisition conditions of said updated image; e) search, from the updated map, for an updated reference model corresponding to the positioning of the teeth during the acquisition of the updated image, the search being preferably carried out using a metaheuristic method, preferably evolutionary, preferably by simulated annealing.

[0113] All features of steps c) to e) described in PCT / EP2015 / 074896 are applicable.

[0114] Following step c), the updated image is analyzed so as to produce an updated map relating to at least one discriminating piece of information.

[0115] A "discriminating information" is a characteristic information that can be extracted from an image ("image feature"), classically by computer processing of that image.

[0116] Discriminatory information can have a variable number of values. For example, edge information can be equal to 1 or 0 depending on whether a pixel belongs to an edge or not. Brightness information can take a large number of values. Image processing allows the extraction and quantification of discriminating information.

[0117] The updated map represents discriminating information in the reference frame of the updated image. The discriminating information is preferably chosen from the group consisting of contour information, color information, density information, distance information, brightness information, saturation information, reflection information, and combinations of these.

[0118] In the optional step d), the actual acquisition conditions of the updated image are roughly evaluated, i.e., the position and orientation in space of the acquisition device relative to the teeth and its calibration. Step d) advantageously limits the number of tests on virtual acquisition conditions in step e), and therefore considerably speeds up step e).

[0119] Preferably, one or more heuristic rules are used. For example, preferably, conditions corresponding to a position of the image acquisition device behind the teeth or a distance from the teeth greater than 1 m are excluded from the virtual acquisition conditions that can be tested in step e). In a preferred embodiment, registration marks represented on the updated image are used to determine a substantially conical region of space delimiting virtual acquisition conditions that can be tested in step e), or "test cone".

[0120] The objective of step e) is to modify the initial reference model until an updated reference model is obtained that corresponds to the updated image. Ideally, the updated reference model is therefore a three-dimensional digital reference model from which the updated image could have been taken if this model had been real.

[0121] A succession of reference models "to be tested" is therefore tested, the choice of a reference model to be tested preferably depending on the level of correspondence of the previously tested reference models "to be tested" with the updated image. This choice is preferably made by following a known optimization process, in particular chosen from among metaheuristic optimization processes, preferably evolutionary, in particular from simulated annealing processes.

[0122] The optimization methods described in PCT / EP2015 / 074896 are in particular applicable.

[0123] Preferably, step e) comprises the following steps:

[0124] el) definition of a reference model to be tested as the initial reference model and then,

[0125] e2) following the following steps, testing virtual acquisition conditions with the reference model to be tested in order to closely approximate the said actual acquisition conditions;

[0126] e21) determination of virtual acquisition conditions to be tested; e22) creation of a two-dimensional reference image of the reference model to be tested under the said virtual acquisition conditions to be tested; e23) processing of the reference image to produce at least one reference map representing, at least partially, said discriminating information; e24) comparison of the updated and reference maps so as to determine a value for a first evaluation function, said value for the first evaluation function depending on the differences between said updated and reference maps and corresponding to a decision to continue or stop the search for virtual acquisition conditions approximating said real acquisition conditions of the updated image more accurately than said virtual acquisition conditions to be tested determined at the last occurrence of step e21); e25) if said value for the first evaluation function corresponds to a decision to continue said search, modification of the virtual acquisition conditions to be tested, then resumed at step e22);

[0127] e3) determination of a value for a second evaluation function, said value for the second evaluation function depending on the differences between the updated and reference maps in the virtual acquisition conditions best approximating said real acquisition conditions and resulting from the last occurrence of step e2), said value for the second evaluation function corresponding to a decision to continue or stop the search for a reference model approximating the positioning of the teeth during the acquisition of the updated image with more accuracy than said reference model to be tested used in the last occurrence of step e2), and if said value for the second evaluation function corresponds to a decision to continue said search, modification of the reference model to be tested by moving one or more tooth models, then resumed at step e2).

[0128] Steps e1) to e3) are described in detail in PCT / EP2015 / 074896, or WO2016066651.

[0129] The updated reference model obtained at the end of step e) is a three-dimensional model resulting from successive modifications of the initial reference model, and is very accurate. Advantageously, it is thus itself very accurate, even though it was obtained from simple photographs taken without any particular precautions.

[0130] Insofar as the teeth are substantially undeformable, the displacement of the tooth models from the initial reference model makes it possible to obtain a model an updated reference image that can be observed under viewing conditions in which the view of the updated reference model is compatible with the updated image. In other words, this view can be superimposed "in register" on the updated image so that the teeth represented in the view and in the updated image overlap almost exactly.

[0131] The update of the initial reference model can be refined by repeating the preceding operations with several updated images. This leads to an updated reference model that represents the teeth substantially in their configuration at the updated time. Gutter image acquisition

[0132] Regardless of the realization of the updated reference model, at the updated instant, an image of gutter 36 is acquired, that is to say, an image of the patient's arch wearing the gutter.

[0133] The gutter image is preferably acquired as the updated image described below, preferably with a mobile phone, preferably with an acquisition kit comprising a support on which the mobile phone and a dental retractor are fixed, such as that described above.

[0134] The gutter image is extra-oral. Framing

[0135] Conditions are then sought that allow observation of the updated reference model and that correspond to the observation conditions of the patient's teeth under which the tray image was acquired. These conditions, referred to as "framed observation conditions," allow observation of the updated reference model in such a way that the view of said model is as close as possible to the tray image.

[0136] The search for framed observation conditions leads to virtually moving around the updated reference model until a "framed" position is found that is compatible with the gutter image, i.e. in which teeth or parts of teeth can be observed as they would have been represented on the gutter image if the gutter had been transparent.

[0137] For this purpose, it is generally possible to identify on the gutter image reference points whose position in the updated reference model is known.

[0138] Alternatively, it is possible to acquire a new gutter image and resume the search for such landmarks.

[0139] The markers preferably belong to teeth known to be immobile, for example because they are untreated (if such teeth are visible in the image of the tray) or to parts of the tray in contact with such teeth, and therefore also immobile. Immobile teeth can be easily identified, since these are teeth whose tooth model was not moved during the previous step. In one embodiment, the reference points are gum contours.

[0140] Preferably, at least three non-collinear points are used as reference points. Analyzing the distances between the representations of these reference points on the gutter image then allows, by simple calculation, for the evaluation of the framed observation conditions.

[0141] On the view of the updated reference model in the framed observation conditions, the markers have relative positions identical to those they have in the gutter image.

[0142] As an alternative to the use of reference frames, the search for framed observation conditions can be carried out by following a known optimization process, in particular chosen from among metaheuristic optimization processes, preferably evolutionary, in particular from among simulated annealing processes.

[0143] The optimization methods described in PCT / EP2015 / 074896 are in particular applicable.

[0144] These methods advantageously allow the virtual movement around the updated reference model to be guided until maximum concordance is obtained between the view observed by the virtual image acquisition device and the gutter image.

[0145] In one embodiment, the following steps are taken: i. analysis of the gutter image and creation of a "gutter" map relating to discriminating information; ii. determination of virtual acquisition conditions to be tested; iii. acquisition of a view of the updated reference model under the said virtual acquisition conditions to be tested; iv. vision processing to produce at least one reference map representing, at least partially, said discriminating information; v. comparison of the gutter and reference maps so as to determine a value for an evaluation function, said value depending on the differences between said gutter and reference maps and corresponding to a decision to continue or stop the search for virtual acquisition conditions approximating said real acquisition conditions of the gutter image with more accuracy than said virtual acquisition conditions to be tested determined at the last occurrence of step ü; vi. if said value for the evaluation function corresponds to a decision to continue said research, modification of the virtual acquisition conditions to be tested, then resumption at step iii,

[0146] otherwise, determination of the framed observation conditions as being the last virtual acquisition conditions tested.

[0147] In step i., the representation of the gutter on the gutter image is preferably disregarded. Preferably, only the contours of the teeth visible on the gutter image are considered.

[0148] The research leads to framed observation conditions of the updated reference model which provide a framed view in which the representations of the teeth are superimposable in register with the representations of the teeth on the gutter image, i.e. in such a way that the teeth represented on the framed view and on the gutter image overlap substantially exactly.

[0149] As an alternative to the use of markers, the search for framed observation conditions can also be carried out using a neural network.

[0150] A "neural network" or "artificial neural network" is a set of algorithms well known to those skilled in the art. The neural network may in particular be chosen from: - networks specialized in image classification, called "CNNs" ("Convolutional neural networks"), for example 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_( ILSVRC-2014 16-layer,VGG ILSVRC-2014 19-layer,Network-in-Network (Imagenet & CIFAR-10) - Google: Inception (V3, V4) - networks specializing in the localization and detection of objects in an image, Object Detection Networks, for example: 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).

[0151] The framed observation conditions are substantially identical to the actual acquisition conditions at the time the gutter image was acquired. By observing the updated reference model under the framed observation conditions, one observes Therefore, the teeth at the time the gutter image was acquired. The view of the updated reference model under these framed acquisition conditions, or "framed view," is thus comparable to the gutter image, but without the gutter. In particular, the shapes and dimensions of the contours in the framed view are comparable to those of the tooth contours visible in the gutter image.

[0152] The outer contour of the splint 24 in the splint image is not, however, perfectly comparable to the contours of the free ends of the teeth shown in the framed view. Indeed, the outer contour of the splint is not a simple translation of its inner contour. Step B) aims to modify the updated reference model to obtain a contour better suited for comparison with the outer contour of the splint.

[0153] In step B), the tooth models 32 of the updated reference model ([Fig.6]) are deformed according to the geometry of the gutter.

[0154] Preferably, the deformation is determined as a function of the thickness of material between the inner surface of the gutter and the outer surface of the gutter.

[0155] Preferably, the tooth models are deformed so that the surfaces of these models which define the free ends of said models extend substantially along the outer surface of the representation of the gutter if this gutter were modeled in the updated reference model in its service position, in the absence of detachment.

[0156] Preferably, the deformation simulates a thickening, preferably constant, of the modeled teeth. The deformed tooth models 32' ([Fig. 7]) thus represent the teeth initially modeled on the surface of which an additional layer of material has been deposited. This deformation is similar to a swelling of the tooth models.

[0157] The thickening can be constant, for example equal to the average thickness of the gutter. Preferably, the thickening is greater than 0.5 mm, preferably greater than 1 mm and / or less than 3 mm, preferably less than 2 mm.

[0158] In one embodiment, the local deformation of a tooth model is determined as a function of the local thickness of the gutter.

[0159] “Depending on the geometry of the gutter” does not mean that the deformation The applied deformation must be specific to each splint. It can, in particular, be determined for a set of splints with common characteristics, for example, for all splints produced by a manufacturer. In one embodiment, the deformation is constant regardless of the location on the surface of the tooth model considered.

[0160] Each tooth model is preferably deformed individually, independently of the presence of other tooth models. The deformations of the Tooth models can thus lead to the penetration of one tooth model into another adjacent tooth model. The resulting deformed updated reference model then no longer corresponds to any possible reality.

[0161] The union, or "fusion", of the deformed tooth patterns is delimited externally by a deformed support surface.

[0162] Preferably, the deformation is determined so that this deformed support surface has substantially the same shape as the outer surface of the splint when the splint is in a treatment-appropriate shape in its service position. If the deformed support surface does not have the same shape as the outer surface of the splint, the dental situation is not perfectly adapted and the orthodontist may consider it abnormal and requiring correction.

[0163] The representation of the outer surface of the gutter on the gutter image is called the "outer contour of the gutter" 24. The representation of the deformed support surface on the deformed updated reference model view, under framed observation conditions, is called the "deformed support contour" 30'. An unsuitable dental situation can therefore be detected by comparing these contours.

[0164] In step C), such a comparison is carried out.

[0165] The updated deformed reference model is observed under the framed viewing conditions, and the deformed support contour is determined on the resulting framed view 38. Similarly, the gutter image is analyzed to determine the outer gutter contour.

[0166] A person skilled in the art knows how to process an image or view to isolate a contour. This processing includes, for example, the application of well-known masks or filters provided with image processing software. Such processing makes it possible, for example, to detect regions of high contrast.

[0167] These treatments include, in particular, one or more of the following known and preferred methods, namely: - by applying a Canny filter, in particular to search for contours using the Canny algorithm; - by applying a Sobel filter, in particular to calculate derivatives using the extended Sobel operator; - by applying a Laplace filter, to calculate the Laplacian of an image; - by detecting spots on an image (“Blobdetecor”); - by applying a threshold ("Threshold") to apply a fixed threshold to each element of a vector; - by resizing, using relationships between pixel areas ("Resize(Area)") or bi-cubic interpolations on the pixel environment; - by erosion of the image by means of a specific structuring element; - by dilating the image using a specific structuring element; - by retouching, in particular by using regions in the vicinity of the restored area; - by applying a bilateral filter; - by applying a Gaussian blur; - by applying an Otsu filter, to find the threshold that minimizes the intra-class variance; - by applying a filter A*, to search for a path between points; - by applying an adaptive threshold to apply an adaptive threshold for a vector; - by applying an equalization filter to a histogram of a particular greyscale image; - by blur detection (“BlurDetection”), to calculate the entropy of an image using its Laplacian; - by edge detection ("FindContour") of a binary image; - by color filling (“FloodFill”), in particular to fill a connected element with a specific color.

[0168] The following non-limiting methods, although not preferred, may also be implemented: - by applying a “MeanShift” filter, so as to find an object on a projection of the image; - by applying a "CLAHE" filter, for "Contrast Limited Adaptive Histogram Equalization"; - by applying a "Kmeans" filter, to determine the center of clusters and groups of samples around clusters; - by applying a DFT filter, so as to perform a discrete, direct or inverse Fourier transform of a vector; - by calculating moments; - by applying a "HuMoments" filter to calculate invariants of Hu invariants; - by calculating the integral of an image; - by applying a Scharr filter, allowing the calculation of a derivative of the image by implementing a Scharr operator; - by searching for the convex hull of points (“ConvexHull”); - by searching for convexity points of a contour (“ConvexityDefects”); - by comparing shapes ("MatchShapes"); - by checking if points are in a contour ("PointPolygonTest"); - by Harris contour detection (“ComerHarris”); - by searching for the minimum eigenvalues ​​of gradient matrices, to detect corners (“CornerMinEigenVal”); - by applying a Hough transform to find circles in a greyscale image ("HoughCircles"); - by “Active contour modeling” (tracing the contour of an object from a potentially “noisy” 2D image); - by calculating a force field, called GVF (“gradient vector flow”), in a part of the image; - by cascade classification (“CascadeClassification”).

[0169] The determination of tooth contours can be optimized by following the teachings of PCT / EP2015 / 074900.

[0170] The framed view after deformation is preferably superimposed in register on the gutter image, so as to superimpose the elements common to the framed view after deformation and the gutter image, for example, gum contours or tooth contours visible in both the framed view after deformation and the gutter image. The outer contour of the gutter and the deformed support contour are thus positioned relative to each other.

[0171] In one embodiment, the outer contour of the gutter and the deformed support contour are divided so as to define portions of these contours for each tooth. The portions of the outer contour of the gutter and the deformed support contour are called "outer tooth contours" 24 and "inner tooth contours" 301, respectively. The adjectives "inner" and "outer" are used here only for the sake of clarity. In [Fig. 12], the dashed segments separate the successive portions.

[0172] The comparison can then be carried out by any means, and in particular as the comparison of the contours of the inner and outer tooth described in EP3412245.

[0173] In particular, for each of a plurality of teeth for which internal and external tooth contours have been determined, the following steps can be taken:

[0174] i) determination of a distance between the contours of the inner and outer teeth;

[0175] ii) determination of a distance threshold, preferably from the distances determined in step i);

[0176] iii) for each of said teeth, determination of a distance score, as a function of - the distance between the inner and outer tooth contours and - of the distance threshold.

[0177] In step i), a distance d is determined between the inner and outer tooth contours of each of said teeth ([Fig. 12]).

[0178] The distance between the inner and outer contours of a tooth can be, for example, the average distance or the maximum distance between the pixels of said contours corresponding to the same point of the tooth.

[0179] The distance is preferably measured in pixels, which advantageously avoids having to establish a scale.

[0180] In step ii), a distance threshold Sd is determined, preferably from the distances determined in step i).

[0181] Preferably, in step ii), the distance threshold Sd is substantially equal to the smallest of the distances determined in step i) (d min). Conventionally, at least one of the treated teeth is in contact with the bottom of the groove in which it is inserted. The distance between the inner and outer tooth contours of this tooth is then equal to a minimum distance d min corresponding to a normal situation. It can therefore serve as a standard for evaluating, in step iii), the distances between the inner and outer tooth contours of the other teeth.

[0182] In step iii), a score called the "distance score" S(d,Sd) is determined for each tooth, as a function of - the distance d between the inner and outer tooth contours and - of the distance threshold Sd.

[0183] Preferably, the distance score for a tooth is equal to (d - Sd), that is, the difference between the distance between the inner and outer contours of that tooth and the distance threshold. The higher the distance score, the more the tooth in question is detached from the groove.

[0184] Fig. 12 illustrates an example of implementation of steps i) to iii), in which a DI tooth is detached from the bottom of the gutter and such that d - d min > Sd.

[0185] For each of a plurality of teeth for which internal and external tooth contours have been determined, the following steps can also be taken:

[0186] i') for each pair of a left tooth and a right tooth adjacent by at least a triplet of first, second and third adjacent teeth for each of which inner and outer tooth contours have been determined, the first and third teeth being adjacent to the second tooth,

[0187] determination of a shift between the inner tooth contour of said left tooth and the inner tooth contour of said right tooth, referred to as "inner shift", and determination of a shift between the outer tooth contour of said left tooth and the outer tooth contour of said right tooth, referred to as "outer shift",

[0188] then

[0189] determination of the difference between the internal offset and the external offset, known as the "offset difference";

[0190] ii') determination of a difference threshold for offsets, preferably from the differences in offsets determined in step i');

[0191] iii' ) determination, for at least one, preferably for each tooth of said triplet, of at least one offset score, as a function of the difference in offsets with an adjacent tooth and the threshold for difference in offsets.

[0192] At step i'), we consider at least triplet consisting of first, second and third teeth, D1, D2 and D3, respectively, the first and third teeth being adjacent to the second tooth, that is to say the first, second and third teeth succeeding each other along an arch.

[0193] The internal tooth contours 30'b 30'2 and 30'3, and external 24b 242 and 243, respectively, of teeth D1, D2 and D3, respectively, are determined.

[0194] An internal or external "offset", respectively, represents a distance between the internal or external tooth contours, respectively, of two adjacent teeth.

[0195] We determine - a shift between the inner tooth contour of said first tooth 30' i and the inner tooth contour of said second tooth 30'2, called "first inner shift", Ai _ 2i; - a shift between the inner tooth contour of said second tooth 30'2 and the inner tooth contour of said third tooth 30'3, called "second inner shift", A2 3i; - a shift between the outer tooth contour of said first tooth 24i and the outer tooth contour of said second tooth 242, called "first outer shift", Ai _ 2e; - offset between the outer tooth contour of said second tooth 242 and the outer tooth contour of said third tooth 243, called "second outer offset", A2 3e.

[0196] The internal offset between the internal tooth contours of two adjacent teeth is preferably equal to the greatest distance between the internal tooth contours of these two teeth.

[0197] The external offset between the external tooth contours of two adjacent teeth is preferably equal to the greatest distance between the external tooth contours of these two teeth.

[0198] Internal and external offsets are preferably measured in pixels, which advantageously avoids having to establish a scale.

[0199] Next, we determine: - the difference between the first internal shift Ai _ 2i and the first external shift Ai _ 2e, called "first difference of shifts" Ai 2 (= A, 2i - A, 2e); - the difference between the second internal offset A23i and the second external offset A2 3e, called "second difference of offsets" A2.3 (= A2 3i ■ A23c).

[0200] In the example of [Fig. 12], Ai 2 is much weaker than A2 3.

[0201] In step ii'), a threshold for the difference in SA shifts is determined, preferably from the first and second differences in shifts Ab2 and A2 3 determined in step i').

[0202] Preferably, in step ii'), the shift threshold is substantially equal to the smallest of the shift differences determined in step i').

[0203] Typically, at least two adjacent treated teeth are in contact with the bottom of the groove in which they are inserted. The difference in offset between these two treated teeth is then essentially zero. This zero difference in offset corresponds to a normal situation and can therefore serve as a standard for evaluating the differences in offset between adjacent treated teeth.

[0204] On [Fig. 13], the difference in offsets between the two teeth Di and D2 is substantially zero.

[0205] At step iü'), for each pair of teeth of said triplet, at least one score, called "offset score", is determined as a function of the difference in offsets with a tooth adjacent to said tooth and the threshold of difference in offsets.

[0206] In particular, the difference in offsets between the first and second teeth can be compared to the SA offset difference threshold, for example, zero. The offset difference threshold can, in particular, be subtracted from the difference in offsets between the first and second teeth to determine a first and second tooth offset score.

[0207] This offset score indicates, for example if it is positive, that one or both of the first and second teeth are likely to be detached from the bottom of the groove.

[0208] On [Fig. 13], the difference in offsets between the two teeth D2 and D3 is positive, which constitutes an indication of detachment of the second or third tooth.

[0209] On [Fig. 13], the difference in offsets between the two teeth Di and D2 being substantially zero, the positive difference in offsets between the two teeth D2 and D3 therefore indicates a detachment of the third tooth.

[0210] Generally, when a first score that is out of sync for the first and second teeth indicates a detachment of one of these two teeth, a The second score is offset 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 has detached from the bottom of the groove. Otherwise, it is probably the second tooth that has detached.

[0211] Preferably, information, for example a warning, is sent to an operator to inform them, where applicable, that the situation is abnormal. The information relating to a tooth depends on the compliance score. Preferably, the information includes a value that quantifies, for at least one tooth, the level of detachment of the splint above that tooth, this value preferably being established from the compliance score calculated for that tooth.

[0212] In one embodiment, this information is used to establish a diagnosis and / or to modify the treatment, in particular to recommend a change of splint and / or to determine characteristics of a future splint for the patient.

[0213] As is now clear, a method according to the invention makes it possible, from simple photographs or a simple film, to determine the areas in which the splint has moved away from the teeth and to assess the extent of this separation. This assessment is advantageously reliable, even when the splint does not allow the teeth housed within it to be distinguished.

[0214] Of course, the invention is not limited to the embodiments described and represented above.

[0215] Generally, according to the invention, a comparison of the outer surface of the gutter with the deformed support surface can be made by any means.

[0216] The comparison of these surfaces is preferably carried out by comparing representations of these surfaces on the gutter image and on the view of the deformed updated reference model obtained under the framed viewing conditions, which is superimposable in register with the gutter image. However, in one embodiment, a three-dimensional digital model of at least the outer surface of the gutter, or "gutter model," is created before step C), for example with a scanner, preferably while the gutter is in the service position, and, in step C), the gutter model is directly compared with said deformed support surface.

[0217] Finally, the patient is not limited to a human being. In particular, a method according to the invention can be used for another animal.

Claims

Demands

1. A computer program comprising program code instructions for the implementation, when said program is executed on a computer, of a method for evaluating, at an "updated" time, the conformity of an orthodontic splint (10) to a patient's dental arch, referred to as the "support arch" (13), said method comprising the following successive steps: A) creation of a digital three-dimensional model of the support arch, in its configuration at the updated time, or "updated reference model" (31), and determination, in the updated reference model, of a support surface (33) of the splint; B) deformation, according to the geometry of the splint, of the support surface to obtain a deformed support surface (33');C) comparison of an outer surface of the gutter (14) with said deformed support surface, then determination, based on said comparison, of at least one conformity score of the gutter to the support arch, the gutter having an inner surface (12) opposite the outer surface (14).;

2. Computer program according to the preceding claim, wherein said deformation is of constant amplitude at every point of the support surface (33) and / or is, at a point of the support surface (33), determined as a function of the distance between the inner (12) and outer (14) surfaces of the gutter at a point (M) of the inner surface of the gutter intended to be, in a service position, in contact with said point of the support surface.

3. A computer program according to any one of the preceding claims, wherein, in step B), the support surface (33) is deformed, preferably at least the part of the support surface which defines the free ends (22) of the teeth of said arch, so that the deformed support surface (33') extends substantially along the outer surface of the representation of the splint if this splint were modeled in the updated reference model (31) in the service position, in the absence of splint detachment.

4. Computer program according to any one of the preceding claims, wherein said deformation is a swelling of the support surface of an amplitude substantially equal to said distance between the inner (12) and outer (14) surfaces of the gutter.

5. A computer program according to any one of the preceding claims, wherein, in step A), the updated reference model is cut so as to define, for each tooth represented in the updated reference model, a digital three-dimensional reference model of said tooth, or "updated tooth model" (32), and wherein, in step B), the surface of each updated tooth model is deformed to obtain a deformed tooth model (32'), then the deformed tooth models are merged and the deformed support surface is defined as being at least a part of the envelope of the set of merged deformed tooth models.

6. Computer program according to the preceding claim, wherein the deformation of the surface of an updated tooth model (32) is a swelling of the updated tooth model, preferably of constant amplitude, and / or is, at a point on the surface of an updated tooth model, determined as a function of the distance between the inner and outer surfaces of the gutter at a point (M) on the inner surface (12) of the gutter intended to be, in a service position, in contact with said point on the surface of the updated tooth model.

7. A computer program according to any one of the preceding claims, wherein, in step A), an image of the splint at the current instant is taken, in a service position in which it is supported by said support arch, or "splint image" (36), a contour of the outer surface of the splint, or "outer contour of the splint" (24), represented on the splint image, is determined, and "framed" viewing conditions are sought that provide a "framed" view of the current reference model exhibiting maximum concordance with the representations of the teeth on the splint image (36), and wherein, in step C), the outer contour of the splint is compared with a contour of the deformed support surface, or "deformed support contour." » (30'), represented on a view of the deformed updated reference model observed under the framed observation conditions.

8. A computer program according to any one of the preceding claims, wherein an initial reference model is created at an initial time prior to the updated time, and then the initial reference model is cut so as to define, for each tooth represented in the initial reference model, a digital three-dimensional reference model of said tooth, or "initial tooth model", and then the initial tooth models (32) are moved to realize the updated reference model at step A).

9. A computer program according to the preceding claim, wherein the initial tooth models are moved until an updated reference model is obtained that is compatible with at least one updated image of the supporting arch, the updated image being acquired less than one month before the updated time, the updated image being able to represent the splint or not.

10. Computer program according to any one of claims 8 and 9, and according to claim 7, wherein the time interval between the updated time and the initial time is greater than 1 week, and / or the time interval between the initial time and the start of orthodontic treatment of the patient with aligners is less than 1 month or 1 week, the updated time being during said orthodontic treatment.

11. A computer program according to any one of claims 9 and 10, wherein in step C), before comparing the outer contour of the splint and the deformed support contour (30'), the representation of an element on the updated image and the representation of said element on the splint image are superimposed in register, the element being an element not modified by wearing the splint, preferably a gum contour.

Images