How to obtain a model of the dental arch

Abstract

A method for obtaining a model of a dental arch of a user (U), comprising: a) obtaining a digital three-dimensional model (8) of the dental arch at an updated instant using a portable scanner (12) and extra-oral, and optionally dividing the obtained model so as to separate a part (30) of the model of the dental arch to obtain an "updated model", which may thus be the obtained model or the part of the obtained model separated by the division, wherein the object represented by the updated model is called the "updated object".

Description

[Technical field]

[0001] The present invention relates to a method for obtaining a model of a user's dental arch and to a computer program for implementing this method. [Background technology]

[0002] It is advisable for everyone to regularly check the alignment of their teeth, and in particular to check whether there is any deterioration in the position and / or shape, appearance (or texture) of the teeth.

[0003] During orthodontic treatment, such adverse changes may lead, among other things, to changes in treatment. After orthodontic treatment, such adverse changes are referred to as "relapse" and may lead to a repetition of the treatment. Finally, more generally, anyone may wish to observe possible movement and / or changes in shape and / or appearance of their teeth, regardless of any treatment.

[0004] Traditionally, monitoring is performed by orthodontists or dentists, who only have the appropriate equipment available to them. This monitoring is therefore expensive. Moreover, the visits are stressful. Finally, the professional scanners available are accurate but require a certain level of skill. The scanners are traditionally used either on the patient in the case of intraoral acquisitions, or by taking impressions of the patient's dental arch in the case of extraoral acquisitions.

[0005] Furthermore, US patent application US15 / 522,520 describes a method that allows to accurately evaluate the movement and / or deformation of teeth from an initial moment based on a simple photograph of the teeth taken by the user at an updated moment. For this purpose, at an initial moment, a digital three-dimensional model of the user's dental arch is created, preferably using a specialized scanner. This initial model is then segmented to define a tooth model for each tooth. Finally, the tooth model is moved so that the initial model of the dental arch is deformed to match the photograph as closely as possible. This method allows to obtain with great accuracy a model that represents the dental arch at an updated moment, without the user having to move to scan his teeth. This model is then compared with the initial model to monitor the position and / or shape of the user's teeth.

[0006] While this method is practical for the user, it requires at least one appointment to obtain an initial model of the dental arch, which then requires laborious data processing to segment and then deform the initial model.

[0007] Therefore, there is a need for a method of remotely monitoring a user's dental condition, such as that described in U.S. Patent Application No. US 15 / 522,520, but which is more practical for the user and can be implemented more quickly. Summary of the Invention [Problem to be solved by the invention]

[0008] One object of the present invention is to at least partially address this problem. [Means for solving the problem]

[0009] The present invention relates to a method for obtaining a model of at least one dental arch of a user (U), comprising the steps of: a) acquiring, at an updated moment, a digital three-dimensional model of the dental arch, i.e. the "acquired model", using a portable scanner (12) and at the user's side, preferably extra-oral, and optionally segmenting the acquired model so as to isolate a part of the model of the dental arch, preferably a tooth model, to obtain an "updated model", which may thus be the acquired model or the part of the acquired model separated by segmentation, where the object represented by the updated model is referred to as the "updated object", The above method further comprises the steps of:

[0010] As will be seen in more detail in the remainder of this specification, the inventors have discovered that it is possible to use a portable scanner, preferably extra-oral, to create models of the dental arch or teeth of sufficient quality to be used in orthodontics without taking special precautions, such methods seem incompatible with obtaining a sufficiently complete and accurate model.

[0011] Advantageously, the acquisition can be performed by the user himself, which opens up a wide range of applications. In particular, the acquisition no longer requires a trip to a dental professional. Moreover, the method according to the invention makes it possible to analyze the user's dental situation more quickly than according to the prior art methods. In particular, there is no need to build a dental arch model from a photograph.

[0012] Generally, 3D models of the dental arch are conventionally acquired intraoraly using a 3D optical scanner, where intraoral acquisition allows sensors to be brought very close to the dental arch and therefore provide highly accurate information.

[0013] Such extra-oral (or "extra-buccal") acquisition devices, i.e. acquisition sensors, in particular those of cameras or photographic image capture devices, are not introduced into the oral cavity of the user, and modernly use photographs to deform an initial model acquired using a conventional 3D optical scanner. The data processing required for this transformation is costly.

[0014] The inventors have successfully tested a portable scanner, preferably an extraoral portable scanner, in particular a LIDAR, and have found that such a scanner allows the patient himself to obtain a good model of the dental arch. Advantageously, it is not necessary for an initial model to be obtained, for example at the beginning of an orthodontic treatment, and then to be deformed on the basis of the images obtained by the scanner. Processing of the images obtained by the scanner makes it possible to obtain the model of the dental arch directly, according to techniques customarily used for 3D optical scanners.

[0015] In an advantageous embodiment, the portable scanner has low accuracy, because it is necessary to record the spatial positions of several interesting points on the dental arch to form an updated model. Advantageously, obtaining a low accuracy model is possible with limited and portable technical means. A low accuracy model also requires less memory to be stored therein. It can be easily and quickly transmitted remotely, for example by radio.

[0016] Preferably, the portable scanner comprises: integrated into a mobile phone for said extra-oral acquisition; or a mobile phone and an acquisition tool having an acquisition head capable of being introduced into the oral cavity of the user; The acquisition tool is Acquiring the acquired model, preferably by LIDAR, and transmitting it to the mobile phone, or A signal is acquired and transmitted to the mobile phone which generates the acquired model from the signal either autonomously or using a computer with which the mobile phone communicates.

[0017] Preferably, the mobile phone transmits the obtained model and / or the updated model to a dental professional, preferably wirelessly, preferably at a distance of more than 100 m, or more than 1 km, or more than 10 km, and / or less than 50,000 km from the user.

[0018] The analysis method according to the invention may also include one or more of the following optional features: In step a), the updated model is subjected to data processing in order to correct it, where the correction may comprise modifying the updated model or replacing the updated model with a corrected model; In step a), the updated model is compared to a correction model to obtain a measure of the difference in shape between the updated model and the correction model; and then the updated model is modified to reduce, preferably to minimize, said differences in shape, preferably by metaheuristic methods, in particular by metaheuristic methods selected from the methods listed below, preferably by simulated annealing, or Depending on the measure, the updated model is left unchanged or the updated model is replaced with the corrected model. In step a), the updated model is submitted to a neural network trained to make the digital three-dimensional model presented as input more realistic; the updated object is the dental arch or a tooth of the dental arch of the user; The correction model is a model obtained by scanning the updated object at a time instant different from the time instant of the update, or a model showing the updated object in a theoretical form, preferably resulting from a simulation, or a model of objects representing a set of individuals, where the objects are of the same type as the updated object, preferably a dental arch or teeth, e.g. a typodont or a tooth from a typodont; and; The correction model is a model of the updated object obtained by scanning, preferably by scanning using the portable scanner or using an industrial scanner, at a moment more than 2 weeks, more than 4 weeks, more than 6 weeks, more than 2 months, more than 3 months and / or less than 12 months or less than 6 months before the moment of the update, or a model of the updated object that simulates the shape of the updated object as expected at the updated moment, and that was preferably created at a moment that is more than 2 weeks, more than 4 weeks, more than 6 weeks, more than 2 months, more than 3 months, and / or less than 6 months prior to the updated moment; or a model of the updated object simulating the expected shape of the updated object at a "correction instant" that comes after or before the updated instant, where the time interval between the updated instant and the correction instant is preferably longer than 1 week, preferably longer than 2 weeks, preferably longer than 4 weeks, preferably longer than 6 weeks, preferably longer than 2 months, and / or shorter than 6 months; or a history model selected from a history library containing over 1000 history models representing objects of the same type as the updated object, where the selection is preferably guided such that the selected history model is the history model that best matches the updated model in terms of shape, or a model obtained by subjecting said historical model from said historical library to a statistical process, preferably such that said model obtained by the statistical process represents a population of individuals; and; the history library only includes history models that meet the same classification criteria as the updated model, e.g., history models related to individuals that share at least one characteristic with the user, e.g., history models of the same age and / or the same sex and / or the same pathological characteristics and / or that have undergone the same or similar orthodontic treatment; In step a), the updated model is corrected by inputting the updated model as an input to a neural network trained to correct models, preferably a model selected from the neural networks listed in the detailed description of step iv) below; and / or In step a), the updated model is subjected to the following steps i) to iv), namely: i) by creating a history library containing more than 1000, preferably more than 5000, preferably more than 10000, history models, where each history model models an object of the same type as the updated object, e.g., if the updated model models a dental arch or a tooth, then it models a dental arch or a tooth, respectively; and Assign values ​​for the classification criteria to each historical model; ii) by analyzing the updated model to determine values ​​of the classification criteria for the updated objects; iii) by searching a historical library for a historical model that has the same values ​​for the classification criteria and that best matches the updated model, i.e., the "best fit model"; iv) by modifying the updated model based on information related to an optimal model, where the modifying may include replacing the updated model with the optimal model; Corrected by; In step a), the acquired model is segmented so as to define a plurality of models of a plurality of teeth, and then, for each tooth model considered as an updated model, a cycle of steps i) to iv) is performed, where in step iv) the determined optimal model is arranged to replace said tooth model in the acquired model, which advantageously makes it possible to reconstruct a high accuracy dental arch model from a low accuracy acquired model; In step a), the updated model is subjected to the following steps i') to iii'), namely: i') a first certain zone formed by points on the updated model that represent a portion of the patient with greater than 90% accuracy, preferably greater than 95% accuracy, preferably greater than 99% accuracy, i.e. "first certain points"; and A first undetermined zone that constitutes the remainder of the updated model to 100%. By defining; ii') by defining a first reconstructed zone in the region of the first uncertain zone by extrapolating the first certain zone based on the unique first certain zone, and then a second certain zone formed by a point in the first undetermined zone that is away from the first reconstructed zone by less than a threshold distance, i.e., a "second certain point"; and A second undetermined zone that constitutes the remainder of the first undetermined zone. By defining; iii') extrapolating the constellation formed by the first certain zone and the second certain zone on the basis of a unique constellation to define a second reconstructed zone in the region of the second undetermined zone, and then By replacing the second undetermined zone with the second reconstructed zone to obtain a clean updated model. be corrected; In step a), by submitting the updated model to a trained neural network by supplying as input a rough model of an object of the same type as the updated object, where the rough model is made hyper-realistic as an output. The updated model is corrected; In step a), the updated model is subjected to data processing in order to simplify it; the portable scanner is integrated within a mobile phone or comprises a mobile phone and an acquisition tool including an acquisition head capable of being introduced into the oral cavity of the user, where the acquisition tool communicates with the mobile phone to transmit the acquired model or the updated model; The acquisition head is connected to the mobile phone, preferably via Bluetooth 登録商標 Connected or wired; said mobile phone being used for transmitting said obtained model or said updated model wirelessly, preferably to a dental professional, in particular to an orthodontist, and / or to a data processing centre, preferably used for the implementation of steps b) and / or c); The portable scanner is a LIDAR, or "light detection and ranging" scanner; In step a), the portable scanner shines structured light directly onto the patient's teeth and acquires an image other than a photograph; In step a), the user changes the angle of the portable scanner, preferably by moving the portable scanner relative to the patient's teeth, preferably horizontally and / or vertically, preferably in open and closed oral cavity conditions; In step a), the user moves the user's lips and / or the user's cheek to expose the user's teeth to the portable scanner, and then the acquired model is acquired extra-oral without the portable scanner being even partially inside the user's oral cavity; Preferably, the user utilizes a retractor and / or a support for the portable scanner to improve the quality of the acquired model; In step a), the portable scanner is fixed onto a support having a rim, where the rim is inserted between the lips and teeth of the user; the support includes a tubular retractor defining an oral opening, where the rim extends around a periphery of the oral opening; In step a), the user varies the angle of the portable scanner by moving the support, preferably horizontally and / or vertically, relative to the patient's teeth, preferably with the mouth open and with the mouth closed, while keeping the rim of the support between the user's teeth and the user's lips; In step a), the model acquired using the portable scanner is segmented to define a plurality of models of a plurality of teeth, and then each of the plurality of tooth models is successively corrected and / or simplified, preferably successively corrected and / or simplified as described above; The method further comprises, after step a), b) determining values ​​of at least one of the dimensional parameters of the updated model, i.e. "dimension values", and / or values ​​of the appearance parameters of the updated model, i.e. "appearance values"; wherein in step b) more than two dimensional values ​​are defined, preferably sufficient dimensional values ​​to define the spatial location of at least one point on the updated model, preferably more than 10 points, more than 10 points, more than 500 points on the updated model; The dimensional parameters are: The dimensions of the updated model; a distance from a point of interest on the updated model to a reference, preferably a distance to a reference that is fixed relative to the updated model, preferably a reference model arranged in a standard configuration like the updated model; and The appearance parameters may include color; reflectance; transparency; reflectance; tint; translucency; opalescence; an indication of the presence of tartar, plaque, or food deposits on the teeth. Selected from; To determine the dimension values, distances are measured between points on the updated model and a reference model similarly positioned in a standard configuration as the updated model; The reference model preferably comprises: an updated model of the object obtained by scanning, preferably using said portable scanner or using an industrial scanner, at a moment that is more than 2 weeks, more than 4 weeks, more than 6 weeks, more than 2 months, more than 3 months and / or less than 6 months before the updated moment, or a model of the updated object that simulates the expected shape of the object at the updated moment, preferably created at a moment that is more than 2 weeks, more than 4 weeks, more than 6 weeks, more than 2 months, more than 3 months, and / or less than 6 months before the updated moment; or an updated model of the object simulating an expected shape of the object at a reference instant following or preceding the updated instant, wherein the time interval between the updated instant and the reference instant is preferably longer than 1 week, preferably longer than 2 weeks, preferably longer than 4 weeks, preferably longer than 6 weeks, preferably longer than 2 months, and / or preferably shorter than 6 months; The model was preferably created more than 2 weeks, more than 4 weeks, more than 6 weeks, more than 2 months, or more than 3 months before the updated moment, or a history model selected from a history library comprising more than 1000, preferably more than 10000, more preferably more than 100000 history models representing objects of the same type as the updated object, wherein the selection is preferably guided such that the selected history model is the history model which best matches the updated model in terms of shape, or a model obtained by subjecting said historical model from said historical library to a statistical process, preferably such that said model obtained by the statistical process represents a population of individuals; is; The method further comprises, after step a), c) using said dimensional values ​​and / or said appearance values, Detecting or assessing tooth position or shape, and / or changes in tooth position or shape, and / or rates of change in tooth position or shape, and / or Detecting or assessing the position or shape of an orthodontic appliance, and / or changes in the position or shape of an orthodontic appliance, and / or the rate of change of the position or shape of an orthodontic appliance; and / or To measure the change in the shape of a patient's teeth between two dates The process includes the steps of; and / or In dentistry, In step c), the dimensional values ​​and / or the appearance values ​​are Detecting or assessing the location or shape of instances of staining or decay; Following tooth eruption; and / or Detecting recurrent or abnormal tooth positions; and / or Detecting tooth wear, and / or monitoring the opening and closing of at least one gap between two teeth; and / or Monitoring occlusal stability or correction; Monitoring the movement of the teeth towards a desired position; and / or Detecting or assessing dislodging of orthodontic appliances or orthodontic aligners; Optimizing appointment dates with dental professionals; and / or In particular, evaluating an orthodontic index selected from the orthodontic indexes listed in the definition of orthodontic index below, Preferably, the orthodontic indication comprises: If the user has reached the canine occlusion class n° I, and / or If the user has reached occlusion class n ° I, and / or The patient's anterior space is closed, and / or All spaces resulting from tooth extractions have been closed; and / or The user has a normal overjet, preferably an overjet of 1 to 3 mm; and / or The user has a normal overbite, preferably an overbite of 1 to 3 mm; and / or If the midline of the lower arch is offset from the midline of the upper arch, and / or If the user does not have a lateral offset of the upper dental arch relative to the lower dental arch, and / or In the latter two cases, if no tooth movement is detected during the monitoring period, and / or If all of your dentures fall out, or an orthodontic index that quantitatively evaluates and / or assesses the temporal changes in: Occlusion classes for canines, and / or Occlusion classes for molars, and / or the space in front of the patient, and / or Spaces resulting from tooth extractions, and / or Overjet and / or Overbite and / or an offset between the midline of the lower arch and the midline of the upper arch; and / or a lateral offset of the upper dental arch relative to the lower dental arch, and / or Tooth movement during the monitoring period in the latter two cases Showing, and / or To evaluate the effectiveness of active orthodontic treatment; and / or Measuring active orthodontic appliance activity; and / or Measuring the decline in effectiveness of passive orthodontic appliances; and / or comparing the updated instantaneous positions of the user's teeth with positions of the teeth represented by a target theoretical model, preferably an intermediate model representing the teeth in expected positions, for a final or intermediate step, i.e. an intermediate "setup", of an orthodontic treatment according to a treatment plan; and / or Evaluating the need to correct or adapt an orthodontic treatment, for example, within the scope of an orthodontic treatment using orthodontic aligners, by designing and manufacturing a new series of orthodontic aligners or by changing the type of orthodontic treatment, for example, from treatment using brackets to treatment using orthodontic aligners or vice versa; and / or To measure the change in the shape of a patient's dentures between two dates separated by the occurrence of a dental impact, by the use of a dental device intended to treat sleep apnea, or by the occurrence of an implant in the patient's oral cavity. Used for; In step a), the model acquired using the mobile phone is segmented to define a plurality of models of a plurality of teeth, and then step b) is performed to define at least one dimension value for each tooth model, which is defined as the updated model for step b); In step a), the user acquires, preferably using one and the same mobile phone, the acquired model and one or more updated images, preferably color photographs, preferably realistic color photographs, and In step b), dimensional and / or appearance information of one or more objects, preferably teeth, represented on one or more updated images is determined, and then said information is used to supplement and / or correct said dimensional values ​​and / or said appearance values ​​determined on the basis of the updated model; In step a), the model obtained comprises less than 500 points.

[0019] The present invention also provides A computer program, in particular a specialized application for mobile phones, comprising program code instructions for carrying out step a) and preferably step b), preferably step c), when said program is executed by a computer, A computer medium on which such a program is recorded, such as a memory or a CD-ROM, A portable scanner, in particular a portable scanner as described above, which is integrated into a mobile phone and into which such a program is loaded. Regarding.

[0020] The present invention therefore relates to a portable scanner, preferably integrated in a mobile phone, capable of performing the obtaining of step a), preferably one or more of the correction and / or simplification methods described herein, preferably step b), more preferably step c).

[0021] definition

[0022] "User" is understood to mean any person on whom the method according to the invention is carried out, whether this person is ill or not, whether this person is undergoing orthodontic treatment or not.

[0023] "Dental practitioner" is understood to mean any person qualified to provide dental care, including in particular orthodontists and dentists.

[0024] "Orthodontic treatment" is all or part of a treatment intended to correct the shape of the dental arch (active orthodontic treatment) or to maintain the shape of the dental arch (passive orthodontic treatment), especially after active orthodontic treatment has concluded.

[0025] Orthodontic landmarks are landmarks that allow a comprehensive assessment of the shape and / or changes in shape of the dental arches. These landmarks may be specific to one or two dental arches ("inter-arch" landmarks). The following may be mentioned as examples: overbite, overjet, size, especially Nance's index, deviations in the inter-incisor environment, occlusion class of the canines and / or molars, irregularity index, especially Little's index, anterior open bite, lateral open bite, lingual posterior crossbite, buccal posterior crossbite, ideal archwire length, presence or absence of interdental spacing, index of leveling of the curve of Spee, presence of significant rotations on certain teeth, e.g. more than 10°, and combinations of these indices and variations therein. An example of an orthodontic index is that used to define the ABO (American Board of Orthodontics) Discrepancy Index.

[0026] An "orthodontic appliance" is an appliance that is worn or intended to be worn by a user. Orthodontic appliances may be intended for curative or preventive treatment as well as aesthetic treatment. Orthodontic appliances are in particular archwire-and-bracket appliances, orthodontic aligners, or Carriere Motion type auxiliaries.

[0027] "Arch" or "dental arch" is understood to mean all or part of a dental arch.

[0028] "Image" is understood to mean a digital representation in two dimensions, for example an image extracted from a photograph or film. An image is made up of pixels.

[0029] "Model" is understood to mean a digital three-dimensional model. A model consists of a set of voxels, which conventionally include a grid of points connected by line segments, i.e., a collection of triangles.

[0030] A "tooth model" is a three-dimensional digital model of teeth. A model of a dental arch can be segmented to define tooth models for at least some of the teeth, preferably all of the teeth represented in the model of the dental arch. A tooth model is therefore a model within the model of the dental arch.

[0031] A "dental arch model" is a model representing at least a portion of a dental arch, preferably at least two teeth, more preferably at least three teeth, more preferably at least four teeth.

[0032] A model, in particular a model of a dental arch or a model of teeth, is "hyper-realistic" when a person observing it has the impression that he or she is observing the modeled object itself, in particular, the colours of the model are the colours of the modeled object.

[0033] A "rough" model is understood to mean a model resulting from a scan, possibly modified according to the present invention, but whose colors have not been modified to hyper-realistic colors.

[0034] The "type" of a modeled object, and in particular the "type" of the updated object, defines the nature of this object. The object may in particular be of type "tooth" or "dental arch" or "gingiva". The object may also be a subgroup of teeth, for example a group of incisors, or a group of teeth with one or more tooth numbers, or a subgroup of a dental arch, for example the upper dental arch.

[0035] A "classification criterion" is an attribute of a modeled object, in particular a dental arch or teeth, that allows it to be classified. For example, the classification criterion can be an occlusion class, a range for the dimensions of the modeled object (e.g. height, width, concavity, intercanine distance, intermolar width, intermolar width, arch length, arch circumference), the age, sex, pathology or orthodontic treatment of the person who owns the modeled object, an orthodontic index, in particular an orthodontic index selected from the orthodontic indexes listed above, or a combination thereof.

[0036] The use of classification criteria makes it possible in particular to select modeled objects that have similar or identical characteristics. Advantageously, it makes it possible to form a learning base that is adapted to the objects that the neural network is intended to process. For example, if the neural network is intended to correct a tooth model representing tooth number 14, it is preferable to train the neural network on a learning base that contains only records relating to tooth number 14. The tooth number is therefore the classification criterion.

[0037] A "standard configuration" is a positioning of a model in space, at a predefined orientation and at a predefined scale. To compare the shapes of two models representing an object, e.g. a dental arch or teeth, the two models can be placed in a standard configuration. Standardization methods for placing and sizing models in a standard configuration are well known. To compare the shapes of two models, it is possible to use, among others, the iterative closest point algorithm (described in https: / / en.wikipedia.org / wiki / Iterative_Closest_Point).

[0038] "Segmenting" a dental arch model into "tooth models" is an operation for segmenting and autonomously rendering the representations of teeth (tooth models) in the dental arch model. There are computational tools for manipulating tooth models or dental arch models. An example of software for manipulating tooth models and creating treatment scenarios is the Treat program, which is described in the following webpage: https: / / en.wikipedia.org / wiki / Clear_aligners#cite_note-invisalignsystem-10.

[0039] A "statistical procedure" is a procedure that, when applied to a data set, makes it possible to determine characteristics specific to that data set, such as the mean, standard deviation, or median. Statistical procedure tools are well known to those skilled in the art.

[0040] A "metaheuristic" method is a known optimization method. Within the scope of the present invention, a metaheuristic method is preferably: An evolutionary algorithm, preferably Evolution strategies, genetic algorithms, differential evolution algorithms, distribution estimation algorithms, artificial immune systems, shuffled complex evolution path reconstruction, simulated annealing, ant colony algorithms, particle swarm optimization algorithms, taboo searching, and GRASP methods an evolutionary algorithm selected from the above; Kangaroo algorithm, Fletcher-Powell method, Noise method, stochastic tunneling, Random restart hill-climbing, Cross entropy method, and A method that is a hybrid between the metaheuristic methods cited above, The compound is selected from the group formed by:

[0041] A "match" or "fit" between two objects refers to a measure of the difference, or "distance," between those two objects. When this difference is minimal, the match is greatest (the "best fit").

[0042] A "neural network" or "artificial neural network" is a set of algorithms known to those skilled in the art. To operate a neural network, it must be trained from a learning base by a learning process called "deep learning".

[0043] A "learning base" is a base of computer records suitable for training a neural network. The quality of the analysis performed by a neural network depends directly on the number of records in the learning base. Conventionally, the learning base contains more than 1000 records, preferably more than 10,000 records.

[0044] Training a neural network is suitable for the desired purpose and does not pose any particular difficulties to the person skilled in the art. Training a neural network consists in confronting it with a learning base that contains information about first and second objects that it must learn to "match", i.e. connect with each other.

[0045] Training may be performed from a "paired" learning base or learning base "with pairs" that consists of "pair" records, i.e., each pair record includes a first object for the input of the neural network and a second corresponding object for the output of the neural network. It is also said that the input and output of the neural network are "paired." By training the neural network with all of these pairs, the neural network learns to provide, from any object similar to the first object, a corresponding object similar to the second object.

[0046] The paper "Image-to-Image Translation with Conditional Adversarial Networks" by Phillip Isola Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros of the Berkeley AI Research (BAIR) at the University of California, Berkeley, demonstrates the use of a paired learning base.

[0047] The function of a "reference" is to serve as a reference for measuring one or more distances. A reference is, for example, a three-dimensional reference system, for example an orthonormal reference system. The three-dimensional reference system is preferably fixed relative to the model in question. If the model represents a dental arch, the model may have its origin, for example, in the center of the user's buccal cavity. In particular, the three-dimensional reference system is preferably independent of the position and orientation of the portable scanner.

[0048] The dimensions of a dental arch (length, width, height) are conventionally measured considering the dental arch to be in a horizontal plane. The height direction Y is therefore the vertical direction. The width direction X is the lateral direction to the user, which extends from the right to the left of the user. The length direction Z is the depth direction of the user, which extends from the front to the back of the user.

[0049] Tooth dimensions (length, width, height) are conventionally measured considering the dental arch to be in a horizontal plane. The height direction Y' is therefore a vertical direction. The width direction X' is perpendicular to the height direction and is the direction of the maximum dimension of the tooth when viewed from the front. The length direction Z' is perpendicular to the directions Y' and X'.

[0050] According to the international convention of the World Dental Federation, each tooth in the dental arch has a predefined number. The tooth numbers defined by this convention are shown in FIG.

[0051] A "point of interest" is a point that can be identified on a dental arch model or tooth model, such as a tooth cusp or a canine cusp, an interproximal contact point, i.e., a contact point between one tooth and an adjacent tooth, such as a mesial or distal point on the incisal edge of a tooth, or a point in the center of the crown, i.e., the "barycenter."

[0052] "Angle" is the orientation of the optical axis of the portable scanner relative to the user while acquiring the model in step a).

[0053] A 3D scanner, i.e. scanner, is a device for obtaining a model of teeth or a model of a dental arch. It conventionally uses structured light and forms the 3D model based on various images, preferably by matching specific points on these images.

[0054] More specifically, the portable scanner projects structured light onto the patient's teeth while acquiring the images. The scanner may project a light emitting pattern onto the teeth. The deformation of this pattern allows the scene to be interpreted spatially.

[0055] Commonly used techniques include projection of one or two dimensional patterns, multistripe laser triangulation (MLT) and digital fringes, as well as modulated phase techniques.

[0056] As an alternative or in addition to structured light projection, the portable scanner projects modulated light onto the patient's teeth while acquiring the images. The projected light is therefore dynamic, and the scanner's camera measures the changes in the reflected light over time and infers therefrom the distance traveled by the light. Commonly used techniques include, inter alia, modulated phase techniques.

[0057] By analysing the images it is possible to build the model.

[0058] The images may be of the same type as images acquired by a conventional intraoral 3D optical scanner.

[0059] The images are representations of the observed scene (in this example the patient's teeth) whose properties are specific to the properties of the light source illuminating the scene, and are preferably not realistic photographs of the scene as one would observe the scene directly.

[0060] The maximum difference in true-to-scale shape between a model acquired using a scanner and the scanned object is inversely proportional to the performance of the scanner. It is referred to as the "acquisition resolution" or "precision" of the scanner. The smaller the resolution, the more realistic the model is.

[0061] LIDAR is particularly well suited for the present invention because it allows an accurate model of the dental arch to be obtained outside the oral cavity at the patient's own location, with the laser light projected directly onto the patient's teeth.

[0062] Commercial scanners preferably have an accuracy of less than 5 / 10 mm (i.e. the maximum difference in shape between a model acquired using the scanner and the actual scanned object true to scale is less than 5 / 10 mm), preferably less than 3 / 10 mm, preferably less than 1 / 10 mm, preferably less than 1 / 50 mm, preferably less than 1 / 100 mm, and / or greater than 1 / 500 mm.

[0063] "Cellphone" or "Mobile phone" refers to the iPhone 登録商標This type of device is referred to as a mobile phone. Such devices are usually less than 500g, or less than 200g, and are equipped with a photographic image capture device with a lens that can take films or photographs, or a scanner that can capture 3D digital models. Mobile phones can also exchange data with other devices more than 500km away from the mobile phone, and can display captured films, photographs or models on a screen.

[0064] A "retractor" or "dental retractor" is a device intended to retract the lips. The retractor has upper and lower rims and / or right and left rims that extend around the retractor opening and are intended to be introduced between the teeth and the lips. In the use position, the user's lips are pressed against these rims so that the teeth are visible through the retractor opening. The retractor thus allows the teeth to be viewed without being obstructed by the lips.

[0065] However, because the teeth are not fixed to the retractor, the user can modify the teeth visible through the retractor opening by rotating the user's head relative to the retractor. They can also modify the spacing between the dental arches. In particular, the retractor presses against the lips rather than against the teeth to move the two jaws away from each other.

[0066] In one embodiment, the retractor is configured to resiliently space the upper and lower lips apart so that the teeth are visible through an opening in the retractor.

[0067] In one embodiment, the retractor is configured so that the distance between the upper and lower rims and / or the distance between the right and left rims is constant.

[0068] Retractors are described, for example, in International Patent Application No. PCT / EP2015 / 074896, U.S. Pat. No. US 6,923,761, or U.S. Patent Application Publication No. US 2004 / 0209225.

[0069] The "position of use" is the position where the user acquires the model acquired in step a). When a support is used to securely fasten the portable scanner, the support is partially introduced into the user's oral cavity, as shown in Figures 2 and 3.

[0070] A "closed mouth" is a bite position in which the patient's upper and lower dental arches are in contact. An "open mouth" is an open mouth position in which the patient's upper and lower dental arches are not in contact.

[0071] The method according to the invention (apart from the acquisition operation using the portable scanner) is implemented by a computer, preferably exclusively by a computer.

[0072] "Computer" denotes a data processing unit comprising a collection of machines with data processing capabilities. This unit may in particular be integrated in a portable scanner or in a mobile phone with which a portable scanner is integrated, or it may be a PC type computer, or a server, for example a server remote from the user, for example in the "cloud", or a computer located at the dental practitioner's premises. The mobile phone and the computer are then equipped with communication means for exchanging with each other, in particular for transmitting the updated model, optionally corrected and / or simplified, and / or one or more dimensional values ​​determined according to the invention.

[0073] Conventionally, a computer comprises, among other things, a processor, memory, a human-machine interface (conventionally comprising a screen), and a communication system (such as a personal computer) that can communicate with the internet, via Wi-Fi, or via Bluetooth. 登録商標The computer may also include a module for communication over the Internet or over a telephone network. Software configured to implement the method of the invention is loaded into the memory of the computer. The computer may also be connected to a printer.

[0074] "First" and "second" are used for purposes of clarity.

[0075] Similarly, for purposes of clarity "Base" refers to the model used in the preferred simplification method; "reference" means the model used in step b) to assess dimensional or appearance values, or the model at the moment when an object modelled by said reference model is predicted to have the shape or appearance of this model; "Correction" refers to the model or moment used in the preferred correction method; "Updated" refers to step a), and in particular to the model resulting from step a); "Historical" refers to one or more models obtained prior to an updated moment, in particular modeling the dental arch or teeth of a "historical" individual different from the user; "Best fit" refers to the model from the collection of models that has the closest shape to the updated model.

[0076] "Vertical", "Horizontal", "Right (side)", "Left (side)", "Front" or "From the front", "Back" "Top" and "bottom" refer to a user standing vertically.

[0077] The terms "including," "having," and "indicating" are to be construed in an open-ended manner, unless otherwise indicated.

[0078] Further features and advantages of the present invention will become more apparent upon reading the following detailed description and examining the accompanying drawings. [Brief description of the drawings]

[0079] [Figure 1]FIG. 1 illustrates a schematic diagram of an exemplary kit according to the present invention. [Diagram 2] FIG. 2 shows diagrammatically a kit according to the invention in the position of use, with the user looking from the front. [Diagram 3] FIG. 3 shows diagrammatically a kit according to the invention in the position of use, with the user looking from the side. [Figure 4] FIG. 4 shows the acquired models with three different acquisition resolutions. [Diagram 5] FIG. 5 is an example of an obtained model after processing the tooth model with segmentation, where the tooth model is colored in dark gray. [Figure 6] FIG. 6 illustrates the tooth numbering used in the dental department. [Figure 7] FIG. 7 illustrates an acquisition method according to the present invention. [Figure 8] FIG. 8 illustrates a first correction method according to the present invention. [Figure 9] FIG. 9 illustrates a second correction method according to the present invention. [Figure 10] FIG. 10 is a schematic diagram showing an example of a portable scanner according to an embodiment of the present invention. [Figure 11] FIG. 11 shows various shots providing complementary data. [Figure 12] FIG. 12 shows a device 6' for implementing the image acquisition method. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0080] In the various figures, the same references are used to denote similar or identical objects.

[0081] The aim of the method according to the invention shown in FIG. 7 is to quickly provide a digital three-dimensional model, ie an "updated model", of a user's dental arch, or a part of this arch.

[0082] In step a), at the updated moment, the user uses the portable scanner 6 to generate an "acquired model".

[0083] Preferably, the obtained model represents at least two, preferably at least three, preferably at least four, preferably all, teeth of a dental arch.

[0084] A portable scanner is an autonomous scanner, particularly in that it has its own built-in energy source, typically a battery, and its weight allows it to be operated by hand.

[0085] Preferably, the portable scanner weighs less than 1 kg, preferably less than 500 g, preferably less than 200 g and / or more than 50 g.

[0086] Preferably, the maximum dimension of the portable scanner is less than 30cm, less than 20cm, less than 15cm, and / or more than 5cm.

[0087] The portable scanner preferably has an acquisition resolution of less than 10 mm, preferably less than 5 mm, preferably less than 3 mm, preferably less than 2 mm, preferably less than 1 mm, preferably less than 1 / 2 mm, preferably less than 1 / 5 mm, preferably less than 1 / 10 mm.

[0088] The portable scanner is preferably configured such that the acquired model comprises more than 5000 points and / or less than 200000 points or less than 150000 points.

[0089] FIG. 4 shows examples of dental arch models 8 acquired with a portable scanner containing 5000 points, 11500 points and 154000 points, respectively.

[0090] The portable scanner 6 may be integrated in or communicate with a mobile phone 12 as in Fig. 1. Thus, step a) can be easily performed by the user. By means of the mobile phone, it is also possible to transfer the updated model to a remote computer.

[0091] The updated moment may be during an orthodontic treatment undergone by the user, or may be outside of any orthodontic treatment.

[0092] In step a), the user preferably holds a portable scanner in his / her hand. Preferably, the portable scanner is not fixed, e.g., not fixed by a structure that is stationary on the ground, e.g., a tripod. Preferably, the user's head is not fixed.

[0093] In one embodiment, the user scans the dental arcade without using any device other than the portable scanner.

[0094] In a preferred embodiment, the user separates the user's lips and uses a tool to better expose the dental arch to the portable scanner, which can be, for example, a spoon that is placed in the user's mouth.

[0095] In one embodiment, the user employs a retractor and / or buccal support that is placed partially within the user's mouth.

[0096] Support for the portable scanner

[0097] In a particularly advantageous embodiment, in step a), the user uses a kit 10 (FIG. 1) comprising a portable scanner 6 and a support 14, and at the same time: Parting the user's lips to free their teeth; and To facilitate positioning and orientation of the portable scanner 6 relative to the teeth This makes it possible.

[0098] The support 14 preferably takes the overall shape of a tubular body with an opening referred to as the "oral opening" Oo intended to be introduced into the patient's oral cavity, and an opposing opening referred to as the "acquisition opening" facing the lens of the portable scanner, and is rigidly, preferably removably, fixed to the support 14.

[0099] Preferably, the acquisition opening also faces the flash of the portable scanner, which allows the flash to be used to illuminate the user's teeth during the acquisition.

[0100] The support 14 makes it possible to define the distance between the portable scanner and the oral cavity opening Oo and to orient the portable scanner relative to the oral cavity opening. Advantageously, therefore, in the position of use, the data acquired by the portable scanner 6 through its lens, the acquisition opening and the oral cavity opening are acquired at a predefined distance from the user's teeth and in a predefined orientation. Preferably, the support is configured so that this distance and this orientation are constant.

[0101] Preferably, the support 14 is a tubular retractor 16 defining an oral opening Oo, where the tubular retractor 16 preferably comprises a rim 22 intended to extend radially outwardly around the periphery of the oral opening Oo and to be introduced between the lips and teeth of a user; and an adapter 18 to which the portable scanner 6 is fixed, for example clamped between two jaws 241 and 242 as shown in FIG. 1, said adapter 18 being fixed, for example, firmly to the retractor 16, preferably removably, for example by means of a clip 20, or made integral with the retractor, so that the lens of the portable scanner can "see" the oral opening, has.

[0102] Maximum height of rim 22 h22 is preferably greater than 3 mm and less than 10 mm.

[0103] To obtain the acquired model, the user assembles the tubular retractor 16 to the adapter 18 by means of the clip 20, and then the portable scanner is assembled onto the adapter 18 so that the portable scanner can perform a scan through the tubular retractor 16 and the adapter 18. The user then places the end of the tubular retractor opposite the portable scanner into the user's oral cavity by inserting the rim 22 between the lips and teeth. Thus, the lips are placed outside the tubular retractor 16, which allows a clear view of the teeth through the oral cavity opening Oo.

[0104] As illustrated in Figures 2 and 3, in the obtained use position, the teeth do not rest on the support, so that the user U can modify the teeth that are seen by the portable scanner through the oral opening by turning his head relative to the support. They can also modify the spacing of the user's dental arches. In particular, the support supports the lips but does not push the teeth so as to move the two jaws apart from each other.

[0105] The obtained model may represent all or part of a dental arch, or two dental arches.

[0106] Segmenting the obtained model

[0107] In one embodiment, the dental arch model acquired with the portable scanner is segmented, preferably to define at least one tooth model 30. Thus, in one embodiment, the updated model is reduced to a portion of the acquired model, preferably to a tooth model.

[0108] Preferably, steps b) and c) are performed sequentially for each tooth model.

[0109] Segmenting the model may implement any known segmentation method.

[0110] The corrections of the updated model may result from a segmentation of the acquired model and consist of modifying it so that it matches the object it models better. For this purpose, it is possible, inter alia, to improve the resolution of the model and / or to supplement it and / or to give it more realistic colors, for example to make it hyperrealistic, and / or to clean up the model. Cleaning up the model consists of removing parts of the model that do not model the target object, for example by removing the representation of an orthodontic bracket when the target object is a tooth, or of removing imperfections resulting from the acquisition operation, in particular to clean up saliva artifacts during the acquisition.

[0111] correction

[0112] The updated model is subjected to data processing for correction, which may be performed before or after simplification.

[0113] In a preferred embodiment shown in FIG. 8, the updated model is compared to a "corrected model" and then corrected as a function of the results of this comparison.

[0114] Preferably, when the model to be corrected is a tooth model, the following steps are followed: i) creating a "historical library" containing over 1000 tooth models (called "historical tooth models") and attributing a tooth number to each historical tooth model; ii) analyzing the tooth model to be corrected to determine the number of teeth modeled by the tooth model to be corrected; iii) searching the historical tooth model from the historical library that has the same number and that best matches the tooth model to be corrected, i.e. the "best fit tooth model"; iv) modifying the tooth model to be corrected based on information about the optimal tooth model, where the modification may include replacing the tooth model to be corrected with the optimal tooth model.

[0115] In step i) a history library is created, preferably comprising more than 2000, preferably more than 5000, preferably more than 10000 and / or less than 10 million tooth models.

[0116] In particular, the historical tooth model can be derived from a model of the dental arch of a "historical" patient, acquired with a scanner. This dental arch model can be segmented to isolate the tooth representation, i.e. the tooth model, as in FIG. 5.

[0117] Therefore, the historical library includes historical tooth models and the number of teeth modeled by these historical tooth models.

[0118] In step ii), the tooth model to be corrected is analyzed to determine the number.

[0119] Tooth numbers are conventionally assigned according to a standard convention, so to determine the number of another tooth model, all that is needed is to know this convention and the tooth number of the model.

[0120] In a preferred embodiment, the shape of the tooth model to be corrected is analyzed to define its number. This shape recognition is preferably performed by a neural network.

[0121] Preferably, a neural network is used, preferably a neural network selected from "object detection networks", for example a neural network selected from the following neural networks: Faster 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), SPP-Net, 2014, OverFeat (Sermanet et al.), 2013, GoogleNet (Szegedy et al.), 2015, VGGNet (Simonyan and Zisserman), 2014, Fast R-CNN (Girshick et al.), 2014, Fast R-CNN (Girshick et al.), 2015, ResNet (He et al.), 2016, Faster R-CNN (Ren et al.), 2016, FPN (Lin et al.), 2016, YOLO (Redmon et al.), 2016, SSD (Liu et al.), 2016, ResNet v2 (He et al.), 2016, R-FCN (Dai et al.), 2016, ResNeXt (Lin et al.), 2017, DenseNet (Huang et al.), 2017, DPN (Chen et al.), 2017, YOLO9000 (Redmon and Farhadi), 2017, Hourglass (Newell et al.), 2016, MobileNet (Howard et al.), 2017, DCN (Dai et al.), 2017, RetinaNet (Lin et al.), 2017, Mask R-CNN (He et al. al.), 2017, RefineDet (Zhang et al.), 2018, Cascade RCNN (Cai et al.), 2018, NASNet (Zoph et al.), 2019, CornerNet (Law and Deng), 2018, FSAF (Zhu et al.), 2019, SENet (Hu et al.), 2018, ExtremeNet (Zhou et al.), 2019, NAS-FPN (Ghiasi et al. al.), 2019, Detnas (Chen et al.), 2019, FCOS (Tian et al.), 2019, CenterNet (Duan et al.), 2019, EfficientNet (Tan and Le), 2019, AlexNet (Krizhevsky et al.), 2012, Cbnet (2020), Point-gnn (2020), MDFN (2020), CADN (2021).

[0122] Preferably, the neural network is trained by supplying the tooth models as inputs and the associated tooth numbers as outputs, so that the neural network learns to supply tooth numbers for the tooth models that it is presented with as inputs.

[0123] It is then possible to modify the tooth model to be corrected based on the historical tooth model having the same number.

[0124] In step iii), a historical tooth model that best matches the tooth model to be corrected is searched from the historical library among the historical tooth models having the same number as the tooth model to be corrected, this historical tooth model is described as the "best fit tooth model".

[0125] "Fit" is a measure of the difference in shape between a historical tooth model and the tooth model to be corrected. The difference in shape may be, for example, the average distance between the historical tooth model and the tooth model to be corrected after the historical tooth model and the tooth model to be corrected are placed in a standard configuration.

[0126] Preferably, the best fit, or "best match," is considered to be achieved when the cumulative Euclidean distance between a point on the historical tooth model and a point on the tooth model to be corrected is smallest.

[0127] In step iv), based on the information about the optimal tooth model used as the correction model, the tooth model to be corrected is modified.

[0128] For example, in the standard configuration, zones of the tooth model to be corrected that are separated from the optimal tooth model by a distance greater than a first distance threshold, e.g. more than 1 mm, can be replaced with zones of the optimal tooth model facing them, and / or The "white" zones of the tooth model to be corrected, i.e. the undefined zones facing the zones of the optimal tooth model which are not white, can be replaced with these zones of the optimal tooth model.

[0129] Modification of the tooth model to be corrected may also consist of replacing the tooth model to be corrected with an optimal tooth model.

[0130] Preferably, steps i) to iv) are performed for each segmented tooth model in the acquired model.

[0131] The above method can be applied to an updated model representing the dental arch. In steps ii) and iii) a classification criterion for the updated model is consequently adapted. The classification criterion may for example be one or more attributes related to the dental arch, for example the width of the dental arch, or one or more attributes related to the two dental arches, instead of the tooth number. The classification criterion may in particular be selected from those listed above in the definition of the classification criterion.

[0132] The updated model may be subjected to a neural network trained for this purpose by a learning base. The neural network may in particular be chosen among the following networks: Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks (2017), Deformable Shape Completion with Graph Convolutional Autoencoders (2018), Learning 3D Shape Completion Under Weak Supervision (2018), PCN: Point Completion Network (2019), TopNet: Structural Point Cloud Decoder (2019), RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion (2019), Cascaded Refinement Network for Point Cloud Completion (2020), PF-Net: Point Fractal Network for 3D Point Cloud Completion (2020), Point Cloud Completion by Skip-attention Network with Hierarchical Folding (2020), GRNet: Gridding Residual Network for Dense Point Cloud Completion (2020), and Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (2021).

[0133] For example, each record in the training base is Incomplete models of objects, e.g. Incomplete model of the dental arch, or An incomplete model of the tooth model, and It's the same model, but it's a highly refined model. may include.

[0134] Preferably, the objects modeled in the records belong to one and the same class defined by a classification criterion, for example, if these objects are teeth, the tooth number of the tooth model is preferably the same for all records in the learning base.

[0135] Preferably, we use neural networks specialized for 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), WaveGAN 2020, GAN-LSTM 2019, CSGAN 2021, DivCo 2021.

[0136] After being trained using this learning base by sequentially feeding the imperfect model and the corresponding perfect model as output for each record, the neural network can convert the imperfect model into the perfect model.

[0137] The complete model is used as the "correction model".

[0138] The correction model can be used to perform quality control during the acquisition of the acquired model, i.e. to check that the acquisition does not produce defects. Defects are parts of the acquired model that do not correctly represent the dental arch or arch. For example, the model may have roughness or indentations that do not exist in reality, i.e. do not exist in the dental arch or on the dental arch.

[0139] By correcting the acquired model it is also possible to remove imperfections resulting from such acquisition operations.

[0140] Cleaning up

[0141] Cleaning up the updated model is preferably performed independently of the correction method described above (steps i) to iv)), the aim being to process the updated model so that it not only loses the representation of the external object, but also replaces it with a surface that represents as faithfully as possible the surface of the dental arch covered by the object.

[0142] In a preferred embodiment shown in FIG. 9, the updated model is cleaned up to eliminate representations of objects external to the user, e.g., orthodontic brackets, and at least partially mask the objects to be modeled, e.g., teeth, according to the following steps: i') a first certain zone formed by points on the updated model, i.e. "first certain points", which represent the object to be modeled, e.g. a tooth, with an accuracy of more than 90%; and A first undetermined zone that constitutes the remainder of the updated model to 100%. To define; ii') by defining a first reconstructed zone in the region of the first uncertain zone by extrapolating the first certain zone based on the unique first certain zone, and then a second certain zone formed by a point in the first undetermined zone that is a distance away from the first reconstructed zone that is less than a threshold distance, i.e., a "second certain point"; and A second undetermined zone that constitutes the remainder of the first undetermined zone. To define; iii') extrapolating the constellation formed by the first certain zone and the second certain zone on the basis of a unique constellation to define a second reconstructed zone in the region of the second undetermined zone, and then Replace the second undetermined zone with the second reconstructed zone to obtain a clean updated model. The substrate is partially masked according to the process of (a).

[0143] These operations advantageously eliminate representations of external objects from the updated model and obtain a clean updated model that accurately represents the object to be modeled.

[0144] The external object may be all or part of an orthodontic appliance, a crown, an implant, a bridge, an elastic band, a veneer, among others. It may also be all or part of a foodstuff, a drop of saliva, a tool.

[0145] In step i'), the representation of the external object is isolated. More specifically, points of the updated model that are virtually certain to be representations of points on the dental arch are identified.

[0146] Algorithms for detecting objects in an image are well known to those skilled in the art. Preferably, neural networks are used, preferably "Object Detection Networks", such as those selected from those listed above.

[0147] After training, these neural networks are able to detect points on the updated model that represent points on the dental arch, i.e., "first certain points", with an accuracy above a 90% or higher accuracy threshold. A set of these points is referred to as a "first certain zone" and constitutes part of the updated model. Points on the updated model that are not included in the first certain zone collectively form a "first undetermined zone".

[0148] Preferably, the accuracy threshold is greater than 95%, preferably greater than 98%, preferably greater than 99% and / or less than 99.99%.

[0149] Training a neural network to detect objects in an image is not difficult for those skilled in the art. For example, it is possible to provide the neural network with a dental arch model as input and the same dental arch model as output, in which zones representing the dental arch and zones representing external objects have been specially identified. In this way, the neural network learns to define these zones on the dental arch model.

[0150] The objective of the steps below is to fill in the "first white zone" of the updated model that would appear if the first undetermined zone was removed.

[0151] In step ii'), the first certain zone is used to define a surface that fills the first white zone, this surface being referred to as the "first reconstructed zone".

[0152] Techniques for performing this extrapolation are well known. An example that can be cited is WENDLAND, Holger. Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree. Advances in computational Mathematics, 1995, vol. 4, no 1, p. 389-396.

[0153] To refine the reconstruction of the dental arch surface masked by the external object, points of the first undetermined zone that are close to the first reconstructed zone are then identified, these points being therefore points on the updated model that are close to a surface extrapolated from points that represent virtually certain points on the dental arch.

[0154] These points on the updated model, i.e. "second certain points", are also considered to be points that represent points on the dental arch with high accuracy. A set of these points is referred to as a "second certain zone". These points are therefore the updated model points that were discarded by the analysis of step i') and that were retained because they are close to a surface extrapolated from the points retained by the analysis of step i').

[0155] On the updated model, points that do not belong to either the first certain zone or the second certain zone together form a "second undetermined zone."

[0156] The suitability of a point in the first uncertainty zone with the first reconstructed zone can be evaluated by a measure of the Euclidean distance between the point and the first reconstructed zone, and if this distance is smaller than a distance threshold, the point in the first uncertainty zone is considered to be part of the second certain zone.

[0157] If the model is to scale, ie represents the modelled object in its actual dimensions, then the threshold distance is preferably greater than 0.1 mm and / or less than 1 mm.

[0158] The threshold distance can also be determined by analysis of the distribution of the Euclidean distances between points in the first undetermined zone and points in the first reconstructed zone, for example as a function of the mean and standard deviation of these distances. For example, a dynamic calculation can be performed using a method of the "3-sigma rule" type.

[0159] In step iii'), the objective is to replace the second undetermined zone with a second reconstructed zone which best corresponds to the surface of the dental arch, for which purpose a first certain zone and a second certain zone are extrapolated in the area of ​​the second undetermined zone.

[0160] It is particularly noted that the extrapolation is not based on only the first certain zone, but on the union of the first certain zone and the second certain zone. Tests have shown that this extrapolation method makes it possible to reliably obtain a second reconstructed zone that represents the surface of the dental arch.

[0161] The extrapolation in step iii') can use the same method as the extrapolation carried out in step ii'). The extrapolation in step iii') can also use a different method.

[0162] The first certain zone and the second certain zone and the second reconstructed zone constitute a clean updated model from which representations of foreign objects have been removed.

[0163] Visual corrections

[0164] Preferably, the updated model is made hyper-realistic by means of a neural network.

[0165] The updated model can be submitted to a neural network trained for this purpose by a learning base, for example, as described in http: / / cs230.stanford.edu / projects_winter_2020 / reports / 32639841.pdf.

[0166] For example, each record in the learning base is A rough model of the object, e.g. A rough model of the dental arch, or A rough model of the tooth model, and Same model, but surreal may include.

[0167] The rough model preferably has a similar appearance to the updated model.The rough model may be a scan, preferably performed using the same or similar portable scanner as used in step a).

[0168] The rough model can be made hyper-realistic, for example, by projecting a photograph.

[0169] Preferably, the objects modeled in the records belong to one and the same class defined by a classification criterion, for example, if these objects are teeth, the tooth number of the tooth model is preferably the same for all records in the learning base.

[0170] Preferably, the following neural networks are used, e.g. specialized for generating images: 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).

[0171] After being trained on a learning basis by being fed, for each record, a rough model as input and a hyper-realistic model as output, the neural network can convert the rough model into a hyper-realistic model.

[0172] By means of the correction methods described above, the updated model can advantageously be transformed into an updated model that represents the modeled object, e.g. a real dental arch, with high realism.

[0173] Simplify

[0174] Before use, for example during step b), the updated model (which may be modified) can be simplified, in particular to facilitate processing in step b), which can also be performed before or after a possible correction, or between two instances of the correction process.

[0175] The updated model, preferably the corrected updated model, is preferably displayed on a screen, preferably on the screen of a mobile phone if the mobile phone has an integrated portable scanner and / or on a screen in the dental professional's office.

[0176] in a portable scanner, preferably in a mobile phone incorporating said portable scanner, or in a mobile phone communicating with the acquisition tool, or a data processing center in communication with the mobile phone, the mobile phone transmitting the acquired model or the updated model to the data processing center; One or more of the segmentation and / or correction and / or cleanup and / or appearance correction and / or simplification operations described above may be performed.

[0177] In step b) at least one value of a dimensional parameter of the updated model, i.e. a "dimension value", and / or at least one value of an appearance parameter of the updated model, i.e. an "appearance value", is determined.

[0178] Step b) can be performed in the mobile phone or in a processing center, where the processing center is remote from the mobile phone, and where the mobile phone transmits the updated model to the processing center.

[0179] The updated model used in step b) is the acquired model, i.e. a rough model generated by the portable scanner, or a part of the obtained model, for example a part of the obtained model resulting from a computerized segmentation of the obtained model, or the obtained model after correction and / or simplification, or A portion of the obtained model after correction and / or simplification It can be.

[0180] A "dimension value" is a value that depends on the shape of the updated model. This value is the value of a "dimension parameter", which can be, among other things, the dimensions of the updated model, e.g., width, length or height of the dental arch or teeth; the distance from the point on the updated model to the reference, or Parameters derived from these dimensions and distances, such as orthodontic indexes, canine / molar occlusion classes, overbite or overjet measures, number of teeth, or indication of the presence or absence of teeth. may be selected from among:

[0181] The dimensional values ​​may be measured on the updated model or may be derived from one or more measurements made on the updated model.

[0182] For example, it is possible to measure the spacing between two teeth, the position of a point of interest to a reference, e.g. to an orthonormal frame of reference (which is fixed in relation to the updated object (particularly a dental arch or tooth) or in relation to another tooth, e.g. to evaluate the position of a tooth compared to other teeth), the offset of a tooth with respect to other teeth or to a predefined position in the frame of reference, the position of one or more teeth with respect to fixed or removable orthodontic appliances placed on the teeth or soft tissue, a size index or irregularity index of a dental arch, misalignment of a tooth with respect to other teeth or with respect to the gums of a tooth, a tooth deformation (e.g. caries depth), a gum deformation, the width of a dental arch, or the relative position of one dental arch with respect to another dental arch.

[0183] The dimension value may also be a measure of the difference in shape between the updated model and a reference model. In particular, it is possible to compare the shapes and / or positions of the teeth in the updated model and the teeth in the reference model.

[0184] An "appearance value" is a value that depends on the appearance of the surface of the updated model. This value is a value of an "appearance parameter", which may be selected from, among others, color; reflectance; transparency; reflectivity; shade; translucence; opalescence; an indication of the presence of tartar, plaque or food deposited on the tooth.

[0185] The appearance value may also be a measure of the difference in appearance between the updated model and a reference model. In particular, it is possible to compare the appearance of teeth in the updated model with the appearance of teeth in a reference model.

[0186] The reference model is selected as a function of the target application.

[0187] For example, if the aim is to verify that a dental situation is normal at the moment of the update, i.e. to verify that the dental situation does not require intervention by a dental professional, in particular for therapeutic or aesthetic reasons, the reference model may be a model representing an object of the same type as the updated object, or a model representing the updated object, in a dental situation considered to be normal at the moment of the update.

[0188] The reference model may represent a set of individuals, preferably comprising more than 100 individuals, more preferably more than 1000 individuals and / or less than 1 million individuals, e.g. If the updated object is a tooth, then a typodont tooth, or If the updated object is a dental arch, then the dental arch corresponds to the average dental arch shape of a set of individuals. It is.

[0189] The reference model may be a model representing an object of the same type as the updated object, and preferably represents the updated object, but with the position and / or shape and / or appearance of the updated object expected at a reference instant coming before or after the updated instant, or at a reference instant coming simultaneously with the updated instant.

[0190] The reference moment is in particular a stage of an orthodontic treatment undergone by the user (e.g., the start or end of an orthodontic treatment, or an intermediate stage or intermediate "set-up" or "staging" of an orthodontic treatment).

[0191] The time interval between the updated instant and the reference instant may be longer than one week, preferably longer than two weeks, longer than four weeks, longer than six weeks, longer than two months, and / or less than six months.

[0192] The reference model may be obtained by a scanner, for example by the user using a portable scanner, preferably a commercial scanner, or may be constructed based on photographs of the dental arch and a library of historical teeth, as described in European Patent Publication No. EP 18184486, which corresponds to U.S. Patent Application No. US 16 / 031,172.

[0193] The reference model is preferably obtained by computer simulation, so that it represents the dental arch in its intended configuration at a reference moment, in particular at the end of an orthodontic treatment or at an updated moment.

[0194] For example, the result may be a modification of an initial model, e.g., an initial model generated by scanning the user's dental arch, preferably generated more than one week before the updated moment, e.g., an initial model generated at the beginning of an orthodontic treatment. The initial model is conventionally segmented to define a tooth model. By moving the tooth model, it is possible to simulate the progress of an orthodontic treatment.

[0195] An example of software for manipulating tooth models and creating treatment scenarios is the Treat program, which is described on the following webpage: https: / / en.wikipedia.org / wiki / Clear_aligners#cite_note-invisalignsystem-10. US Pat. No. 5,975,893 A also describes the creation of treatment scenarios.

[0196] In one embodiment, the following is performed: - generating a tooth model by segmenting a reference model generated before said updated instant or by segmenting said updated model; moving one or more of the tooth models without deforming the tooth models until a modified model is obtained that best matches the shape of the updated model or the reference model, respectively; Evaluation of a difference in the position of at least one tooth model between the position of the tooth model in the reference model or the updated model, respectively, and the position of the model in the modified model (determination of at least one dimension value).

[0197] In step c), the dimensional and / or appearance values ​​determined in step b) are used to decide whether a treatment is necessary and / or to contribute to the decision of this treatment, in particular for therapeutic or aesthetic purposes.

[0198] The dimensional values ​​and / or the appearance values, and preferably the updated model, may be presented to the user, for example by being displayed on the screen of the user's mobile phone.

[0199] Additionally or alternatively, they can also be transmitted, preferably wirelessly, by a mobile phone, preferably with an integrated portable scanner or a mobile phone in communication with the acquisition tool, to a dental professional, in particular an orthodontist, or to a remote computer in communication with said mobile phone.

[0200] Preferably, the dimensional values ​​and / or the appearance values ​​are interpreted, preferably by a computer, preferably by a mobile phone with an integrated portable scanner, and recommendations are presented to the user, preferably on the screen of the user's mobile phone.

[0201] Use updated images

[0202] In one particularly advantageous embodiment, in step a), the user acquires one or more "updated" images, preferably extraoral images, in addition to the updated model, preferably using a mobile phone equipped to acquire the acquired model.

[0203] Preferably, the updated images are photographs or images extracted from film, they are preferably in color, preferably in true color, and preferably they substantially represent the dental arch as seen by an operator of the device for obtaining these images.

[0204] The information provided by the updated images makes it possible to supplement the information provided by the acquired model, which may in particular relate to the dimensions and / or appearance of one or more objects, preferably teeth, represented on one or more updated images. In particular, the analysis of the updated images, preferably computer-updated images, makes it possible to verify and / or correct dimensional and / or appearance values ​​determined from the updated model and / or to supplement the teachings derived from the updated model.

[0205] For example, the updated model may make it possible to detect caries on the surface of the tooth, and the updated image may reveal a dark zone at the location of this caries. In this way, the updated image confirms the presence of caries. It also makes it possible to confirm the location of the caries. In this way, by analyzing the model and the updated image, it is possible to detect caries and to monitor changes in the caries.

[0206] The updated image can also provide information about the appearance of the teeth, e.g. tooth color, very reliably, so that by projecting onto the updated model it is possible to color the surfaces of the updated model very realistically.

[0207] Furthermore, preferably, multiple updated images are acquired taken from different angles, i.e., different orientations of the capture device relative to the user's buccal cavity. For example, one set of updated images may include six images representing the dental arch "front view", the dental arch "front right view", the dental arch "right view", the dental arch "front left view", the dental arch "left view" and the dental arch "below view".

[0208] Preferably, at least one updated image is acquired from a front view of the user, preferably at least one updated image is acquired from the right of the user, and at least one updated image is acquired from the left of the user.

[0209] A set of updated images preferably comprises more than 2, preferably more than 3, preferably more than 5, preferably more than 6, and / or less than 30, preferably less than 20, preferably less than 15, preferably less than 10 updated images.

[0210] In one embodiment, the updated images are processed to generate the correction model and / or the reference model. For this purpose, any conventional technique can be implemented.

[0211] By obtaining two models at the updated instant, specifically the updated model and a model obtained from the updated image, and then comparing these models, it is possible to make the most of the 3D and 2D representations provided by the portable scanner and the image acquisition device, respectively.

[0212] The method may be performed independently of any orthodontic treatment, and may be performed, inter alia, to ensure that the tooth position and / or shape are not "abnormal", i.e., do not meet therapeutic or aesthetic criteria. An appointment should then preferably be made with a dental professional. The method may be performed prior to orthodontic treatment.

[0213] Upstream of an orthodontic treatment, the method can be implemented, inter alia, to obtain future tooth positions and anatomical structures and initiate the manufacture of interceptive orthodontic appliances or customized orthodontic appliances, such as clear orthodontic aligners, or to design a customized treatment using arch wires and brackets.

[0214] The method can be carried out during orthodontic treatment, in particular for controlling its progress, wherein step a) is carried out less than 3 months, less than 2 months, less than 1 month, less than 1 week, less than 2 days before the start of the treatment, i.e. after the fitting of an appliance intended to correct the position of the user's teeth (referred to as an "active retainer appliance").

[0215] During orthodontic treatment, the method can be implemented to obtain updated models of the teeth and enable the manufacture of new orthodontic appliances, such as implants, orthodontic aligners, or vestibular orthodontic appliances.

[0216] Preferably, the updated model generated in step a) and / or one or more values ​​determined in step b) are transmitted to dental practitioners to assist in establishing a diagnosis.

[0217] The method may also be performed after orthodontic treatment to verify that the positions of the teeth have not changed adversely ("relapse"). Step a) is then preferably performed less than 3 months, less than 2 months, less than 1 month, less than 1 week, less than 2 days after the end of treatment, i.e., after fitting of appliances intended to keep the teeth in place (referred to as "passive retainer appliances").

[0218] The dimensions are preferably: To detect recurrence, and / or To determine the rate of change in tooth position; and / or To optimize appointment dates with dental professionals; and / or To assess the effectiveness of orthodontic treatment; and / or and / or to evaluate the change in the tooth position towards a reference model corresponding to the determined tooth position, in particular the improved tooth position. to modify an ongoing orthodontic treatment, for example by manufacturing a new series of orthodontic aligners; and / or In dentistry, and / or visualising and / or measuring and / or detecting plaque and / or caries and / or microcracks and / or wear, e.g. wear resulting from bruxism or from the wearing of active or passive orthodontic appliances, in particular in the event of breakage or dislodgement of orthodontic archwires; Visualizing and / or measuring and / or detecting changes in volume, in particular during tooth growth or after treatment by a dental professional, e.g. after deposition of an adhesive on the tooth surface; Prior to any orthodontic treatment, especially to evaluate the benefits of orthodontic treatment, and to evaluate the chances of interceptive treatment, Used.

[0219] The appearance values ​​are preferably used to detect or assess the location or shape of instances of staining or caries.

[0220] In a particularly advantageous embodiment, both the dimensional value and the appearance value are used. Advantageously, therefore, the method can be used to precisely monitor, in a localized manner, changes in certain pathologies, in particular staining, demineralization, or caries.

[0221] As is now apparent, the present invention provides a method that allows a particular user, e.g. a patient, to generate a model of one or more of his / her dental arches or one or more of his / her teeth, without the need for any particular device, except for a portable scanner, preferably built into the user's mobile phone.

[0222] The acquired model may be acquired without introducing the portable scanner into the oral cavity of the user, i.e. extra-oral, by processing the updated model to correct it, in particular to model areas of the oral cavity not accessed by the portable scanner, e.g. in the interproximal space.

[0223] In one embodiment, in step a), the model obtained is rough, in particular representing a "3D skeleton" of one or more dental arches of the user and including less than 500 points, less than 200 points, less than 100 points, or less than 50 points, and / or more than 10 points. Processing the updated model to modify it, in particular using a neural network or based on a history library, advantageously makes it possible to reconstruct a much more accurate model of one or more dental arches of the user.

[0224] In one embodiment, the portable scanner is introduced partially into the user's oral cavity. Advantageously, the rear surfaces of the teeth can be scanned.

[0225] As shown in FIG. 10, the portable scanner 6 preferably communicates with a mobile phone 12, preferably wirelessly, preferably via Bluetooth. 登録商標 and an acquisition tool 31 for communicating with the mobile phone via a wireless LAN. Wired communication is also possible.

[0226] The acquisition tool comprises an acquisition head 32 that can be introduced into the oral cavity of the user, which either acquires an acquired model and transmits it to the mobile phone 12, or acquires a signal, e.g. a set of images, and transmits it to the mobile phone 12, so that the latter generates the acquired model from the signal.

[0227] Preferably, the acquisition tool has no physical link to the mobile phone or is connected to the mobile phone by a flexible link, eg wireless.

[0228] Preferably, the acquisition tool is provided with a handle 34 to facilitate manipulation by the user or the associated object, for example in the manner of a toothbrush.

[0229] In one embodiment, the acquisition tool is fixed to the mobile phone, for example, by clips, self-adhesive tape, clamping jaws, screws, magnets, covers or flexible bands, preferably elastic bands. The fixing can be due to shape complementarity with the mobile phone. For example, the acquisition tool can be fixed to the housing of the mobile phone.

[0230] In one embodiment, the method also implements a measurement head that communicates with the mobile phone and is introduced into the user's oral cavity to obtain supplemental data, such as the data described below. Spaces between teeth, Lingual surface of teeth Palate, e.g., the palate including the median palatine suture Soft tissues (sores, benign or malignant lesions, depressions), Tooth Shade the presence of dental caries or stains, the condition and / or shape of the implants, crowns and / or bridges; the condition of any vestibular or lingual appliances (e.g., lingual or vestibular brackets, palatal expanders, or other treatment aids) or retainer appliances (palatal arch wires); The distance between various parts of one and the same vestibular or lingual appliance side or other auxiliary appliance, The condition of anchoring devices (mini-screw type), soft tissue suture points, soft tissue healing after surgery, Curve of Spee Wilson's Curve, Distance between canines, The distance between the molars.

[0231] FIG. 11 shows supplementary data, in particular the mid-palatal suture (Image 1), the soft tissue suture points (Image 2), the distance between the various parts of one and the same vestibular or lingual appliance or other auxiliary appliance (Images 3 and 4), the condition and / or shape of the implants, crowns and / or bridges (Images 5 and 8), the condition of the anchoring device (mini-screw type) and the distance between the anchoring device and the appliance present in the oral cavity (Image 6), the vestibular or lingual treatment appliance (e.g. 10 shows various shots that provide supplemental data regarding the palate, including the condition of any missing or lingual or vestibular brackets, palatal expanders, or other treatment aids) or retainer treatment appliances (palatal arch wires) (Figure 7), the spaces between the teeth, the state of soft tissue healing after surgery (Figure 9), the lingual surfaces of the teeth (Figure 10), the inter-canine distance and the inter-molar distance (Figure 10), the shade of the teeth (Figure 11), the curvature of Spee (Figure 12), the curvature of Wilson (Figure 13), and the presence of cavities or stains (Figure 14).

[0232] The measuring head may be integrated with a measurement tool that exhibits one or more of the characteristics of the acquisition tool, but in contrast to the latter, the measurement tool does not serve to acquire the acquired model.

[0233] The obtained model can then be corrected, in particular to be supplemented and / or cleaned up and / or made hyper-realistic, and the user can send the model to a dental professional, possibly one the user has never met, which the dental professional can analyze, in particular to establish a diagnosis and / or to give advice to the user and / or to schedule an appointment.

[0234] Of course, the invention is not limited to the described and illustrated embodiments.

[0235] The methods for correcting and simplifying the update model described above are an invention independent of the described methods.

[0236] Improvement points

[0237] Beyond the above-mentioned method, more generally, the invention also relates to a method for acquiring at least one image of at least one dental arch of a user by means of a mobile phone and an acquisition tool comprising an acquisition head equipped with a camera, preferably a camera that can be introduced into the oral cavity of the user, during which the acquisition head: capturing the captured image and transmitting it to the mobile phone; or A signal is acquired and transmitted to the cell phone which generates an image from the signal, either autonomously or using a computer with which the cell phone communicates.

[0238] The at least one image is preferably a photograph, preferably a photograph that realistically represents the dental arch as one would observe it directly.

[0239] Although the images can be used to generate a model according to step a), the image acquisition method according to the invention is no longer limited to this particular embodiment, since the images can be used for other purposes, and therefore this method is described below as a "general method".

[0240] However, insofar as the features described above for step a) are technically compatible with the general method, they may be applied to this method.

[0241] The mobile phone and the acquisition tool are preferably operated exclusively by a user.

[0242] The acquisition can be performed extra-oral, with the camera of the acquisition tool not entering the user's oral cavity. The acquisition can be performed intra-oral, with the camera of the acquisition tool entering the user's oral cavity.

[0243] In one embodiment, the acquisition tool is fixed to the mobile phone, for example, by clips, self-adhesive tape, clamping jaws, screws, magnets, covers or flexible bands, preferably elastic bands. The fixing can be due to shape complementarity with the mobile phone. For example, the acquisition tool can be fixed to the housing of the mobile phone.

[0244] Preferably, however, the mobile phone and the acquisition tool communicate with each other but can be moved independently of each other. Preferably, the mobile phone and the acquisition tool are not connected to each other by any rigid device, preferably any mechanism, and the mobile phone can be moved in space, preferably in all spatial dimensions, without necessarily carrying the acquisition tool along with the mobile phone.

[0245] Preferably, the screen displays the scene observed by a camera of the acquisition head.

[0246] Independence of movement between the mobile phone and the acquisition tool makes it possible, in particular, to use the mobile phone screen to visualize the scene observed by the acquisition head's camera without visualization being hindered by handling of the acquisition head.

[0247] In one embodiment, during the acquisition, the user observes the screen of the mobile phone, where the mobile phone is preferably stationary relative to the ground, for example placed on a table, and operates the acquisition tool.Therefore, the user can easily position the acquisition tool at a desired position, preferably for extraoral acquisition.Moreover, this embodiment advantageously allows the use of the mobile phone camera located on the opposite side to the screen, without requiring the user to use a mirror.

[0248] Preferably, the user has at least one image taken from the front, preferably at least one image taken from the right of the user, and also preferably at least one image taken from the left of the user.

[0249] Preferably, the user captures at least one image with the oral cavity open and at least one image with the oral cavity closed.

[0250] The set of captured images preferably comprises more than 2, preferably more than 3, preferably more than 5, preferably more than 6, and / or less than 30, preferably less than 20, preferably less than 15, preferably less than 10 images.

[0251] Preferably, the user parts their lips and uses a tool to better expose the dental arch to the camera of the acquisition tool, which can be, for example, a spoon that is placed in the user's mouth.

[0252] In one embodiment, the user employs a retractor that is placed partially within the user's mouth.

[0253] Preferably, the general method includes analysing the images after said acquisition to define the user's dental condition, preferably to design an active or passive orthodontic treatment plan and / or to confirm proper progress of ongoing active or passive orthodontic treatment.

[0254] Preferably, the obtaining method includes, after the analysis of the image, manufacturing an orthodontic appliance, such as an orthodontic aligner, and preferably shipping the orthodontic appliance to a user.

[0255] The above described use of the updated image can also be applied to an image or images acquired according to conventional methods.

[0256] The at least one image preferably comprises: To detect recurrence, and / or To determine the rate of change in tooth position; and / or To optimize appointment dates with dental professionals; and / or To assess the effectiveness of orthodontic treatment; and / or and / or to evaluate the change in the tooth position towards a reference model corresponding to the determined tooth position, in particular the improved tooth position. to modify an ongoing orthodontic treatment, for example by manufacturing a new series of orthodontic aligners; and / or In dentistry, and / or visualising and / or measuring and / or detecting plaque and / or caries and / or microcracks and / or wear, e.g. wear resulting from bruxism or from the wearing of active or passive orthodontic appliances, in particular in the event of breakage or dislodgement of orthodontic archwires; Visualizing and / or measuring and / or detecting changes in volume, in particular during tooth growth or after treatment by a dental professional, e.g. after deposition of an adhesive on the tooth surface; Prior to any orthodontic treatment, especially to evaluate the benefits of orthodontic treatment, and to evaluate the chances of interceptive treatment, It is used for.

[0257] Figure 12 shows a device 6' for implementing such an image acquisition method. The kit is connected to a mobile phone 12', preferably wirelessly, preferably via Bluetooth. 登録商標 and an acquisition tool 31' for communicating with the mobile phone via Bluetooth or via WiFi. Wired communication is also possible.

[0258] The acquisition tool 31' comprises an acquisition head 32 that can be introduced into the oral cavity of the user, which acquires the image and transmits it to the mobile phone 12', or acquires a signal and forwards it to the mobile phone 12', so that the latter generates the image from the signal.

[0259] Preferably, the acquisition tool has no physical link to the mobile phone or is connected to the mobile phone by a flexible link, eg wireless.

[0260] Preferably, the acquisition tool is provided with a handle 34' to facilitate manipulation by the user or an associate thereof, for example in the manner of a toothbrush.

[0261] The mobile phone 12' may include one or more of the features of the mobile phone 12. Preferably, it is not fixed to any support, in particular the support 10 described above, to the user, who can freely manipulate it.

Claims

1. A method for obtaining a model of at least one dental arch of a user (U), comprising the steps of: a) acquiring, at an updated moment, a digital three-dimensional model (8) of said at least one dental arch, i.e. an "acquired model", using a portable scanner (12) and at the user's side, and optionally segmenting said acquired model so as to isolate a part (30) of said model of said dental arch, to obtain an "updated model", which may thus be said acquired model or said part of said acquired model separated by segmentation, wherein said object represented by said updated model is referred to as an "updated object", The process includes the steps of: wherein the portable scanner is integrated into a mobile phone (12) for said extraoral acquisition, or a mobile phone (12) and an acquisition tool comprising an acquisition head (32) capable of being introduced into the oral cavity of the user; The acquisition tool includes: obtaining the obtained model and transmitting it to the mobile phone (12); or acquiring a signal and transmitting it to said mobile phone (12), which generates said acquired model from said signal either autonomously or using a computer with which said mobile phone communicates; The method.

2. The method of claim 1 , wherein the mobile phone transmits the acquired model and / or the updated model to a dental practitioner.

3. 2. The method of claim 1, wherein in step a) the updated model is subjected to data processing in order to correct it, where the correction may comprise modifying the updated model or replacing the updated model with a corrected model.

4. In step a), the updated model is compared to a correction model to obtain a measure of the difference in shape between the updated model and the correction model; and then the updated model is modified to reduce the difference in shape, or Depending on the measure, the updated model remains unchanged or is replaced by the corrected model; and / or The updated model is submitted to a neural network that is trained to make the digital three-dimensional model presented as input more realistic. The method of claim 1.

5. The correction model: a model obtained by scanning the updated object at a time instant different from the time instant of the update, or a model showing the updated object, respectively, in the resulting shape from the simulation; or a model of objects representing a set of individuals, said objects being of the same type as the updated object; The method according to claim 3 or 4, wherein

6. The correction model: a model of the updated object obtained by scanning using the portable scanner; or a model of the updated object simulating the expected shape of the updated object at the time of the update; or a model of the updated object simulating the expected shape of the updated object at a time instant, referred to as a "correction instant", which comes after or before the updated instant, where the time interval between the updated instant and the correction instant is greater than one week; or a history model selected from a history library containing over 1000 history models representing objects of the same type as the updated object; or A model obtained by subjecting the historical model from the historical library to statistical processing. The method according to claim 5, wherein

7. In step a), the updated model is by inputting the updated model as an input to a neural network trained to correct the model; and / or By the following steps i) to iv), namely: i) creating a history library containing over 1000 history models, where each history model models an object of the same type as the updated object, and attributing to each history model a value for a classification criterion; ii) by analysing the updated model to determine values ​​of the classification criteria for the updated objects; iii) by searching a historical library for a historical model that has the same values ​​for the classification criteria and that best matches the updated model, i.e., the "best fit model"; iv) by modifying the updated model based on information related to an optimal model, where the modifying may include replacing the updated model with the optimal model; and / or By the following steps i') to iii'), namely: i') a first certain zone formed by a point on the updated model that represents a portion of the patient with greater than 90% accuracy, i.e., a "first certain point"; and A first undetermined zone that constitutes the remainder of the updated model to 100%. By defining ii') by defining a first reconstructed zone in the region of the first uncertain zone by extrapolating said first certain zone based on only said first certain zone, and then a second certain zone formed by a point in the first undetermined zone that is less than a threshold distance away from the first reconstructed zone, i.e., a "second certain point"; and A second undetermined zone that constitutes the remainder of the first undetermined zone. By defining iii') extrapolating the constellation formed by said first certain zone and said second certain zone on the basis of a unique constellation to define a second reconstructed zone in the region of said second undetermined zone, and then by replacing the second undetermined zone with the second reconstructed zone to obtain a clean updated model; and / or by submitting the updated model to a neural network that has been trained by providing as input a rough model of an object of the same type as the updated object, where the rough model is made hyper-realistic as an output. The method according to claim 3 or 4, wherein the method is corrected.

8. 8. The method of claim 7, comprising segmenting the acquired model to define a plurality of models of a plurality of teeth, and then performing a cycle of steps i) to iv) for each tooth model considered to be an updated model, where in step iv) the best fit model replaces the tooth model in the acquired model.

9. The method according to any one of claims 1 to 4, wherein in step a) the updated model is subjected to data processing in order to simplify it.

10. The method according to any one of claims 1 to 4, wherein the portable scanner is a LIDAR.

11. 5. The method according to claim 1, wherein in step a) the user moves his / her lips and / or his / her cheek to make his / her teeth visible to the portable scanner, and then the acquired model is acquired extra-oral without placing the portable scanner even partially inside the user's oral cavity.

12. 12. The method of claim 11, wherein in step a) the portable scanner is fixed on a support provided with a rim (22), wherein the rim is inserted between the lips and teeth of the user.

13. 13. The method of claim 12, wherein the support (14) comprises a tubular retractor (16) defining an oral opening (Oo), and wherein the rim extends around a periphery of the oral opening (Oo).

14. The method according to any one of claims 1 to 4, wherein in step a) the user changes the angle of the portable scanner (12) to horizontal.

15. After step a), The method according to any one of claims 1 to 4, further comprising the step of b) determining values ​​of at least one of the following: dimensional parameters of the updated model, i.e. "dimension values", and / or appearance parameters of the updated model, i.e. "appearance values".

16. The dimensional parameters are the dimensions of said updated model; the distance from a point of interest on the updated model to a reference; and parameters derived from one or more dimensions of the updated model and / or one or more distances from one or more points of interest on the updated model to the reference; Or, The appearance parameters may be: color; reflectance; transparency; reflectance; tint; translucency; opalescence; an indication of the presence of tartar, plaque or food deposits on the teeth. The method of claim 15, wherein the compound is selected from the group consisting of

17. 16. The method of claim 15, wherein to determine dimensional values, distances are measured between points on the updated model and a reference model similarly positioned in a standard configuration as the updated model.

18. The reference model is an updated model of the object obtained by scanning with said portable scanner at a time instant not less than two weeks prior to said updated time instant; or A model of the updated object that simulates the expected shape of the updated object at the updated moment and that was created at a moment that is more than two weeks prior to the updated moment; or a model of the updated object, i.e. a "reference model", simulating the expected shape of the updated object at a reference instant following or preceding the updated instant, where the time interval between the updated instant and the reference instant is greater than one week; and The reference model was created more than two weeks prior to the update moment; or a history model selected from a history library containing over 1000 history models representing objects of the same type as the updated object; or a model obtained by subjecting a historical model from a historical library containing over 1000 historical models representing objects of the same type as the updated object to the statistical process such that the model obtained by the statistical process represents a population of individuals; 18. The method of claim 17, wherein:

19. 16. The method of claim 15, wherein in step a), the model acquired using the mobile phone is segmented to define a plurality of models of a plurality of teeth, and then step b) is performed to define at least one dimension value for each tooth model, which is defined as the updated model for step b).

20. In step a), the user acquires the acquired model and one or more updated images using one and the same mobile phone; and In step b), information relating to the dimensions and / or appearance of the teeth represented on the one or more updated images is determined, and then said information is used to supplement and / or correct said dimension values ​​and / or said appearance values. The method of claim 15.

21. The method according to any one of claims 1 to 4, wherein in step a) the obtained model comprises less than 500 points.

22. 5. The method according to claim 1, wherein in step a) supplementary data that is not essential for the generation of the acquired model is acquired by a measuring head in communication with the mobile phone and introduced into the oral cavity of the user.

23. The method according to any one of claims 1 to 4, wherein the portable scanner uses structured light and forms the acquired model based on various images by matching specific points on the images.

24. 1. A kit comprising a portable scanner (12) and a support (14) removably fixed in a position enabling the portable scanner (12) to observe an oral cavity opening (Oo) defined by the support, the support comprising a rim (22) that can be inserted between the lips and teeth of a user for the acquisition of step a) of the method according to any one of claims 1 to 4 in a use position in which the portable scanner observes the teeth of the user through the oral cavity opening.

Images