METHOD FOR ANALYZING AN IMAGE OF A DENTAL ARCADE

专利摘要:
A method for modeling a dental arch of a patient, said method comprising the following steps: a) creating a historical library comprising more than 1,000 tooth models, called "historical tooth models", and assigning them to each model historic tooth, of value for at least one tooth attribute, or "tooth attribute value"; b) analyzing at least one "scan image" of the dental arch by means of a deep learning device, preferably a neural network, so as to determine at least one scan tooth area and at least one tooth attribute value associated with said scan tooth area; c) for each analysis tooth area determined in the previous step, searching, in the historical library, for a historical tooth model having a maximum proximity to the analysis image or to the tooth area of analyzing, or "optimal tooth model" and preferably having, for at least one tooth attribute, the same value as said analysis tooth area; d) arranging the set of optimal tooth patterns so as to create a pattern that has maximum proximity to the updated image, or "assembled model"; e) optionally, replacing at least one optimal tooth model with another tooth model and repeated in step d) so as to maximize the match between the assembled model and the analysis image; f) optionally, recovery of step b) with another analysis image and, in step d) and / or e), seeking maximum agreement with all the analysis images used.
公开号:FR3069359A1
申请号:FR1756944
申请日:2017-07-21
公开日:2019-01-25
发明作者:Philippe Salah；Thomas PELLISSARD；Guillaume GHYSELINCK；Laurent DEBRAUX
申请人:Dental Monitoring SAS；
IPC主号:

专利说明:

METHOD FOR ANALYZING AN IMAGE OF A DENTAL ARCH
Technical area
The present invention relates to the field of image analysis of dental arches.
State of the art
The most recent orthodontic treatments use images to assess therapeutic situations. This evaluation is conventionally carried out by an orthodontist, which requires that the patient transmits these images to the orthodontist, or even that he makes an appointment.
There is an ongoing need for a method to facilitate the analysis of dental arch images of patients.
An object of the invention is to meet this need.
Summary of the invention
The invention provides a method for analyzing an image, known as an “analysis image”, of a dental arch of a patient, method in which the analysis image is subjected to a deep learning device. , preferably a neural network, in order to determine at least one value of a tooth attribute relating to a tooth represented on the analysis image, and / or at least one value of an image attribute relating to the analysis image.
Analysis by tooth
The invention provides in particular a method for detailed analysis of a so-called "analysis image" image of a dental arch of a patient, said method comprising the following steps:
1) creation of a learning base comprising more than 1000 images of dental arches, or "historical images", each historical image comprising one or more zones each representing a tooth, or "historical tooth zones", each which, for at least one tooth attribute, a tooth attribute value is assigned;
2) training of at least one deep learning device, preferably a neural network, by means of the learning base;
3) subjecting the analysis image to at least one deep learning device so that it determines at least one probability relating to an attribute value of at least one tooth represented on a zone representing, at least partially said tooth in the analysis image, or "analysis tooth area";
4) determination, as a function of said probability, of the presence of a tooth of said arch at a position represented by said area of analysis tooth, and of the attribute value of said tooth.
A first deep learning device, preferably a neural network, can in particular be used to evaluate a probability relating to the presence, at a location of said analysis image, of an analysis tooth zone .
A second deep learning device, preferably a neural network, can in particular be used to evaluate a probability relating to the type of tooth represented in an analysis tooth area.
As will be seen in more detail in the following description, a detailed analysis method according to the invention advantageously makes it possible to immediately recognize the content of the analysis image.
The analysis image can advantageously be classified automatically. It is also immediately usable by a computer program.
The invention is based on the use of a deep learning device, preferably a neural network, the performance of which is directly linked to the richness of the learning base. There is therefore also a need for a method for rapidly enriching the learning base.
The invention therefore also relates to a method for enriching a learning base, in particular intended for the implementation of a detailed analysis method according to the invention, said enrichment method comprising the following steps:
A) at an “updated” instant, realization of a model of a dental arch of a patient, or “updated reference model”, and segmentation of the updated reference model so as to produce, for each tooth, a “ tooth model ”, and for at least one tooth attribute, assigning a tooth attribute value to each tooth model;
B) preferably less than 6 months, preferably less than 2 months, preferably less than 1 month, preferably less than 15 days, preferably less than 1 week, preferably less than 1 day before or after the updated instant , preferably substantially at the updated time, acquisition of at least one, preferably at least three, preferably at least ten, preferably at least one hundred images of said arch, or "updated images" , under respective actual acquisition conditions;
C) for each updated image, search for virtual acquisition conditions suitable for acquiring an image of the updated reference model, called "reference image", having maximum agreement with the image updated in said acquisition conditions virtual, and acquisition of said reference image;
D) identification, in the reference image, of at least one zone representing a tooth model, or “reference tooth zone” and, by comparison of the updated image and the reference image, determination, in the updated image, an area representing said tooth model, or "updated tooth area";
E) assignment, to said updated tooth area, of the tooth attribute value (s) of said tooth model;
F) addition of the updated image enriched with a description of said updated tooth area and of its tooth attribute value (s), or "historical image", in the learning base.
In particular, each execution of the method described in WO 2016/066651 preferably generates more than three, more than ten, preferably more than one hundred updated images which, by automated processing using the updated reference model, can produce as many historical images.
In a particular embodiment, the method for enriching a learning base comprises, in place of steps A) to C), the following steps:
A ') at an initial instant, realization of a model of a dental arch of a patient, or "initial reference model", and segmentation of the initial reference model so as to produce, for each tooth, a "model tooth ”, and for at least one tooth attribute, assigning a tooth attribute value to each tooth model;
B ') at an updated instant, for example spaced more than fifteen days, preferably more than a month, or even more than two months from the initial instant, acquisition of at least one, preferably at least at least three, preferably at least ten, preferably at least one hundred images of said arch, or "updated images", under respective actual acquisition conditions;
C ') for each updated image, search, by deformation of the initial reference model, for an updated reference model and virtual acquisition conditions suitable for acquiring an image of the updated reference model, known as the “image of reference ”, presenting maximum agreement with the updated image in said virtual acquisition conditions.
This process advantageously makes it possible, after generation of the initial reference model, preferably by means of a scanner, to enrich the learning base at different updated times, without the need to perform a new scan, and therefore without the patient having to go to the orthodontist. He can indeed acquire the updated images himself, as described in WO 2016/066651.
A single orthodontic treatment can thus lead to the production of hundreds of historical images.
The invention also relates to a method for training a deep learning device, preferably a neural network, comprising an enrichment of a learning base according to the invention, then the use of said base. learning to train the deep learning device.
Global analysis
The detailed analysis method described above advantageously allows a fine analysis of the analysis image, the situation of each being preferably evaluated.
Alternatively, the deep learning device can be used globally, the learning base containing historical images, the description of which provides a global attribute value for the image. The attribute is then not a "tooth" attribute, but is an "image" attribute. For example, this image attribute can define whether, with regard to the image as a whole or part of the image, the dental situation "is pathological" or "is not pathological", without an examination of each tooth is carried out. The image attribute also makes it possible to detect, for example, whether the mouth is open or closed, or, more generally, if the image is suitable for further processing, for example if it makes it possible to control the occlusion.
The image attribute can in particular relate to
- a position and / or an orientation and / or a calibration of an acquisition device used to acquire said analysis image, and / or
- a quality of the analysis image, and in particular relating to the brightness, to the contrast or to the sharpness of the analysis image, and / or
- the content of the analysis image, for example the representation of the arches, tongue, mouth, lips, jaws, gum, one or more teeth or an orthodontic appliance.
When the image attribute refers to the content of the image, the description of the historical images of the learning base specifies a characteristic of this content. For example, it can specify the position of the tongue (for example "recessed") or the opening of the patient's mouth (for example open or closed mouth) or the presence of a representation of an orthodontic appliance and / or its condition (e.g. intact, broken or damaged device).
A tooth attribute value can be used to define a value for an image attribute. For example, if a value of a tooth attribute is "decayed tooth", the value of an image attribute can be "unsatisfactory dental status".
The image attribute may in particular relate to a therapeutic situation.
The invention provides a method for the overall analysis of an image for analyzing a dental arch of a patient, said method comprising the following steps:
Γ) creation of a learning base comprising more than 1000 images of dental arches, or “historical images”, each historical image comprising an attribute value for at least one image attribute, or “value of image attribute ”;
2 ') training of at least one deep learning device, preferably a neural network, by means of the learning base;
3 ′) submission of the analysis image to the deep learning device so that it determines, for said analysis image, at least one probability relating to said image attribute value, and determination, in as a function of said probability, of a value for said image attribute for the analysis image.
The image attribute can in particular relate to the orientation of the acquisition device during the acquisition of the analysis image. For example, it can take the values "front photo", "left photo" and "right photo".
The image attribute can also relate to the quality of the image. It can for example take the values "insufficient contrast" and "acceptable contrast".
The image attribute can also relate to the patient's dental situation, for example relating to the presence of cavities or the state of an orthodontic appliance worn by the patient ("degraded" or "in good condition"). state ”for example) or the adequacy of the orthodontic appliance for the treatment of the patient (for example“ unsuitable ”or“ adapted ”).
The image attribute can also relate to the “presence” or “absence” of an orthodontic appliance, or to the state of opening of the mouth (“open mouth”, “closed mouth” for example ).
As will be seen in more detail in the following description, a method of global analysis of images according to the invention advantageously makes it possible to immediately and globally evaluate the content of the analysis image. In particular, it is possible to assess an overall dental situation and, for example, to deduce the need to consult an orthodontist.
Definitions
A "patient" is a person for whom a method according to the invention is implemented, regardless of whether this person is undergoing orthodontic treatment or not.
“Orthodontist” means any person qualified to provide dental care, which also includes a dentist.
"Orthodontic appliance" means all or part of an orthodontic appliance.
An orthodontic piece can in particular be an orthodontic splint. Such a gutter extends so as to follow the successive teeth of the arch on which it is fixed. It defines a generally "U" shaped trough, the shape of which is determined to ensure the fixing of the gutter to the teeth, but also according to a desired target positioning for the teeth. More specifically, the shape is determined so that, when the gutter is in its service position, it exerts stresses tending to move the treated teeth towards their target position, or to maintain the teeth in this target position.
The "service position" is the position in which the orthodontic piece is worn by the patient.
By "model" is meant a three-dimensional digital model. An arrangement of tooth models is therefore a model.
By image is meant a two-dimensional image, such as a photograph or an image from a film. An image is made up of pixels.
A "reference image" is a view of a "reference" model.
By "image of an arcade", or "model of an arcade", is meant a representation of all or part of said arcade.
The “acquisition conditions” of an image specify the position and the orientation in space of an image acquisition device relative to the patient's teeth (actual acquisition conditions) or to a model of teeth of the patient (virtual acquisition conditions), and preferably the calibration of this acquisition device. Acquisition conditions are said to be virtual when they correspond to a simulation in which the acquisition device would be in said acquisition conditions (positioning and preferably theoretical calibration of the acquisition device) relative to a model .
Under conditions of virtual acquisition of a reference image, the acquisition device can also be qualified as "virtual". The reference image is in fact acquired by a fictitious acquisition device, having the characteristics of the "real" acquisition device used for the acquisition of real images, and in particular updated images.
The "calibration" of an acquisition device consists of all the values of the calibration parameters. A calibration parameter is a parameter intrinsic to the acquisition device (unlike its position and orientation) whose value influences the acquired image. Preferably, the calibration parameters are chosen from the group formed by the aperture of the diaphragm, the exposure time, the focal distance and the sensitivity.
Discriminatory information is characteristic information which can be extracted from an image (image feature), conventionally by computer processing of this image.
Discriminatory information can have a variable number of values. For example, contour information can be equal to 1 or 0 depending on whether a pixel belongs to a contour or not. Brightness information can take a large number of values. Image processing makes it possible to extract and quantify discriminating information.
Discriminatory information can be represented in the form of a "card". A map is thus the result of an image processing in order to reveal the discriminating information, for example the contour of the teeth and gums.
We call “match” (“match” or “fit” in English) between two objects a measure of the difference between these two objects. A match is maximum ("best fit") when it results from an optimization allowing in order to minimize said difference.
An object modified to obtain maximum concordance can be called an "optimal" object.
Two images or "views" which have maximum agreement represent substantially at least the same tooth, in the same way. In other words, the representations of the tooth on these two images are substantially superimposable.
The search for a reference image having maximum agreement with an updated image is carried out by searching for the virtual acquisition conditions of the reference image having maximum agreement with the actual acquisition conditions of the updated image.
By extension, a model has a maximum agreement with an image when this model has been chosen from several models because it allows a view having a maximum agreement with said image and / or when this image has been chosen from several images because it presents a maximum agreement with a view of said model.
In particular, an updated image is in maximum agreement with a reference model when a view of this reference model provides a reference image in maximum agreement with the updated image.
The comparison between two images preferably results from the comparison of two corresponding cards. A measurement of the difference between two maps or between two images is conventionally called “distance”.
"Metaheuristic" methods are known optimization methods. They are preferably chosen from the group formed by
- evolutionary algorithms, preferably chosen from: evolutionary 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 research, and the GRASP method;
- the kangaroo algorithm,
- the method of Fletcher and Powell,
- the sound effects method,
- stochastic tunneling,
- climbing hills with random starts,
- the method of cross entropy, and
- the hybrid methods between the metaheuristic methods mentioned above.
An image, in particular relating to the definition of the tooth zones of this image and to the attribute attribute values associated therewith, and / or relating to an image attribute value, is called “description” of an image. of said image. There is no limit to the number of possible values for a tooth attribute or an image attribute.
A "historical" image is an image of a dental arch enriched with a description. The tooth areas of a historic image are referred to as "historic tooth areas".
Interpret including or including or presenting in a non-restrictive manner, unless otherwise indicated.
Brief description of the figures
Other characteristics and advantages of the invention will become apparent on reading the detailed description which follows and on examining the appended drawing in which:
- Figure 1 shows, schematically, the different steps of a detailed analysis process of an image, according to the invention;
- Figure 2 shows, schematically, the different stages of a method for enriching a learning base, according to the invention;
- Figure 3 shows, schematically, the different stages of a variant of a method for enriching a learning base according to the invention;
- Figure 4 shows, schematically, the different steps of a method of global analysis of an image, according to the invention;
- Figure 5 shows, schematically, the different steps of a step C) of a method for enriching a learning base, according to the invention;
- Figure 6 shows, schematically, the different steps of a method of modeling the dental arch of a patient, according to the invention;
- Figure 7 shows, schematically, the different steps of a method for evaluating a dental situation of a patient, according to the invention;
- Figure 8 shows, schematically, the different steps of a method of acquiring an image of a dental arch of a patient, according to the invention;
- Figure 9 shows, schematically, the different steps of a method for evaluating the shape of an orthodontic tray of a patient, according to the invention;
- Figure 10 shows an example of a reference image of an initial reference model;
- Figure 11 (11 a-11 d) illustrates a processing for determining the tooth models in an initial reference model, as described in WO 2016 066651;
- Figure 12 (12a-12d) illustrates the acquisition of an image by means of a spacer, a cutting operation of this image, and the processing of an updated image to determine the contour of the teeth, as described in WO 2016 066651;
- Figure 13 schematically illustrates the relative position of registration marks 12 of a spacer 10 on updated images 14i and 142, according to the directions of observation shown in broken lines;
- Figures 14 and 15 show an orthodontic splint, in perspective and top view, respectively;
- Figure 16 illustrates step e) described in WO 2016 066651;
- Figure 17 illustrates a method of enrichment according to the invention.
detailed description
A detailed analysis method according to the invention requires the creation of a learning base. This creation preferably implements a process comprising steps A) to F), or, in one embodiment, in place of steps A) to C), preferably steps A ’) to C’).
First main embodiment of the enrichment process
Step A) is intended for the production of an updated reference model modeling an arch of the patient. It preferably comprises one or more of the characteristics of step a) of WO 2016 066651 to produce an initial reference model.
The updated reference model is preferably created with a 3D scanner. Such a model, called "3D", can be observed at any angle. An observation of the model, at a determined angle and distance, is called a "view" or "reference image". Figure 1a is an example of a reference image.
The updated reference model can be prepared from measurements made on the patient's teeth or on a molding of his teeth, for example a plaster molding.
For each tooth, a model of said tooth, or "tooth model" (FIG. 1d) is defined from the updated reference model. This operation, known in itself, is called “segmentation” of the updated reference model.
In the updated reference model, a tooth model is preferably delimited by a gingival edge which can be broken down into an inner gingival edge (on the side of the inside of the mouth relative to the tooth), an outer gingival edge ( oriented towards the outside of the mouth relative to the tooth) and two lateral gingival edges.
One or more tooth attributes are associated with tooth models depending on the teeth they model
The tooth attribute is preferably chosen from a tooth number, a type of tooth, a tooth shape parameter, for example a tooth width, in particular a mesio-palatal width, a thickness, a crown height, an index of deflection in mesial and distal of the incisal edge, or a level of abrasion, a parameter of appearance of the tooth, in particular a translucency index or a color parameter, a parameter relating to the state of the tooth , for example "abraded", "broken", "decayed" or "fitted" (ie in contact with an orthodontic appliance), an age for the patient, or a combination of these attributes.
A tooth attribute value can be assigned to each tooth attribute of a particular tooth model.
For example, the tooth attribute "tooth type" will have the value "incisor", "canine" or "molar" depending on whether the tooth model is that of an incisor, canine or molar, respectively.
The assignment of tooth attribute values to tooth models can be manual or, at least in part, automatic. For example, if the value of a tooth attribute is the same regardless of the tooth model, as for the tooth attribute "patient age", it may be enough to assign a value to a tooth model to determine the value of this attribute for other tooth models.
Likewise, tooth numbers are conventionally assigned according to a standard rule. So you just need to know this rule and the number of a tooth modeled by a tooth model to calculate the numbers of other tooth models.
In a preferred embodiment, the shape of a particular tooth model is analyzed so as to define its tooth attribute value, for example its number. This shape recognition is preferably carried out by means of a deep learning device, preferably a neural network. Preferably, we create a library of historical tooth models, each historical tooth model having a value for the tooth attribute, as described below (step a)), we train the deep learning device with views historical tooth models from this library, and then analyze one or more views of the particular tooth model with the deep learning device trained, so as to determine the tooth attribute value of said particular tooth model.
The assignment of tooth attribute values can then be fully performed without human intervention.
Step B) is intended for the acquisition of one or preferably several updated images.
Step B) preferably includes one or more of the characteristics of step b) of WO 2016 066651.
The acquisition of the updated images is carried out by means of an image acquisition device, preferably chosen from a mobile telephone, a so-called “connected” camera, a so-called “smart” watch, or “smartwatch”, a tablet or personal computer, desktop or portable, with an image acquisition system, such as a webcam or camera. Preferably the image acquisition device is a mobile phone.
Preferably, an updated image is a photograph or is an image extracted from a film. It is preferably in color, preferably in real color.
The time interval between steps A) and B) is as small as possible so that the teeth have not significantly moved between the realization of the updated model and the acquisition of the updated images. Reference images consistent with the updated images can then be acquired by observing the updated reference model.
Preferably, a dental retractor 10 is used during step B), as shown in FIG. 12a. The retractor conventionally comprises a support provided with a rim extending around an opening and arranged so that the patient's lips can rest there, letting the patient's teeth appear through said opening.
In step C), the updated reference model is explored to find, for each updated image, a reference image having maximum agreement with the updated image.
Step C) may include one or more of the characteristics of steps c), d) and e) of WO 2016 066651, insofar as they relate to such an exploration.
For each updated image, a set of virtual acquisition conditions is preferably roughly determined, approximating the actual acquisition conditions during the acquisition of said updated image. In other words, the position of the image acquisition device relative to the teeth is estimated at the time when it took the updated image (position of the acquisition device in space and orientation of this device) . This rough evaluation advantageously makes it possible to limit the number of tests on virtual acquisition conditions during the following operations, and therefore makes it possible to speed up these operations considerably.
To carry out this rough assessment, one or more heuristic rules are preferably used. For example, preferably, virtual acquisition conditions that can be tested during the following operations are excluded, conditions that correspond to a position of the image acquisition device behind the teeth or to a distance from the teeth greater than 1 m.
In a preferred embodiment, as illustrated in FIG. 13, reference marks represented on the updated image are used, and in particular reference marks 12 of the spacer, to determine a region of space that is substantially conical. delimiting virtual acquisition conditions that can be tested during the following operations, or test cone.
More specifically, there are preferably at least three reference marks 12 not aligned on the spacer 10, and their relative positions on the spacer are precisely measured.
The registration marks are then identified on the updated image, as described above. Simple trigonometric calculations are used to roughly determine the direction in which the updated image was taken.
Then, for each updated image, we look for a reference image with maximum agreement with the updated image. This research is preferably carried out by means of a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
Preferably, the updated image is processed to produce at least one updated map representing, at least partially, discriminating information, and said research includes the following steps:
Cl) determination of virtual acquisition conditions "to be tested";
C2) production of a reference image of the reference model updated in said virtual acquisition conditions to be tested;
C3) processing of the reference image to produce at least one reference card representing, at least partially, the discriminating information;
C4) comparison of the updated and reference cards so as to determine a value for an evaluation function, said value for the evaluation function depending on the differences between said updated and reference cards and corresponding to a decision to continue or to stop the search for virtual acquisition conditions approximating said real acquisition conditions with more accuracy than said virtual acquisition conditions to be tested determined at the last occurrence of step C1);
C5) if the said value for the evaluation function corresponds to a decision to continue the said search, modification of the virtual acquisition conditions to be tested, then resumed in step C2).
In step C1), one begins by determining virtual acquisition conditions to be tested, that is to say a virtual position and orientation capable of corresponding to the actual position and orientation of the apparatus of acquisition when capturing the updated image, but also, preferably, a virtual calibration capable of corresponding to the actual calibration of the acquisition device when capturing the updated image.
The first virtual acquisition conditions to be tested are preferably virtual acquisition conditions roughly evaluated, as described above.
In step C2), the image acquisition device is then virtually configured under the virtual acquisition conditions to be tested in order to acquire a reference image of the reference model updated in these virtual acquisition conditions at test. The reference image therefore corresponds to the image that the image acquisition device would have taken if it had been placed, relative to the updated reference model, and optionally calibrated, under the virtual acquisition conditions. to test.
If the updated image was taken at approximately the same time as the updated reference model was created by scanning the patient's teeth, the position of the teeth on the updated image is substantially identical to that in the updated reference model. If the virtual acquisition conditions to be tested are exactly the actual acquisition conditions, the reference image can therefore be exactly superimposed on the updated image. The differences between the updated image and the reference image result from errors in the evaluation of the virtual acquisition conditions to be tested, if they do not correspond exactly to the actual acquisition conditions.
In step C3), to compare the updated and reference images, the discriminating information of these two images is compared.
Preferably, at any time before step C4), the updated image is analyzed so as to produce an updated map relating to at least one discriminating item of information. The updated map therefore represents discriminating information in the repository of the updated image.
The discriminating information is preferably chosen from the group consisting of contour information, color information, density information, distance information, brightness information, saturation information, reflection information and combinations of this information.
Those skilled in the art know how to process an updated image to reveal discriminating information.
For example, FIG. 12d is an updated map relating to the contour of the teeth obtained from the updated image of FIG. 12b.
Similarly, a reference card representing the discriminating information is produced from the reference image (FIGS. 1 a and 1 lb).
In step C4), the updated and reference cards, both carrying the same discriminating information, are compared and the difference or "distance" between these two cards is evaluated by means of a score. For example, if the discriminating information is the contour of the teeth, we can compare the average distance between the points of the contour of the teeth which appears on the reference image and the points of the corresponding contour which appears on the updated image, the score being higher the shorter the distance.
The score can for example be a correlation coefficient.
Preferably, the virtual acquisition conditions include the calibration parameters of the acquisition device. The score is all the higher since the values of the calibration parameters tested are close to the values of the calibration parameters of the acquisition device used during the acquisition of the updated image. For example, if the diaphragm aperture tested is far from that of the acquisition device used during the acquisition of the updated image, the reference image has blurred regions and sharp regions which do not correspond blurred regions and sharp regions of the refreshed image. If the discriminating information is the contour of the teeth, the updated and reference maps will therefore not represent the same contours and the score will be low.
The score is then evaluated using an evaluation function. The evaluation function makes it possible to decide whether cycling on steps Cl) to C5) should be continued or stopped. The evaluation function can for example be equal to 0 if the cycling must be stopped or be equal to 1 if the cycling must continue.
The value of the evaluation function may depend on the score achieved. For example, it may be decided to continue cycling if the score does not exceed a threshold. For example, if an exact match between the updated and reference images leads to a score of 100%, the threshold can be, for example, 95%. Of course, the higher the threshold, the better the accuracy of the evaluation of the virtual acquisition conditions if the score manages to exceed this threshold.
The value of the evaluation function can also depend on scores obtained with previously acquired virtual acquisition conditions.
The value of the evaluation function can also depend on random parameters and / or the number of cycles already performed.
In particular, it is possible that, despite the repetition of the cycles, it is not possible to find virtual acquisition conditions which are sufficiently close to the actual acquisition conditions for the score to reach said threshold. The evaluation function can then lead to the decision to leave the cycle even though the best score obtained has not reached said threshold. This decision may result, for example, from a number of cycles greater than a predetermined maximum number.
A random parameter in the evaluation function can also allow the continuation of tests of new virtual acquisition conditions, although the score appears satisfactory.
The evaluation functions conventionally used in metaheuristic, preferably evolutionary, optimization methods, in particular in simulated annealing methods, can be used for the evaluation function.
In step C5), if the value of the evaluation function indicates that it is decided to continue cycling, the virtual acquisition conditions to be tested are modified and cycling is repeated in steps C1) to C5) consisting of producing a reference image and a reference card, comparing the reference card with the updated card to determine a score, then making a decision based on this score.
The modification of the virtual acquisition conditions to be tested corresponds to a virtual movement in space and / or to a modification of the orientation and / or, preferably, to a modification of the calibration of the acquisition device. This modification can be random, preferably so that the new virtual acquisition conditions to be tested always belong to the set determined during the rough evaluation. The modification is preferably guided by heuristic rules, for example by favoring the modifications which, according to an analysis of the previous scores obtained, appear to be the most favorable for increasing the score.
The cycling is continued until the value of the evaluation function indicates that it is decided to stop this cycling and to continue in step D), for example if the score reaches or exceeds said threshold.
Optimization of the virtual acquisition conditions is preferably carried out using a metaheuristic method, preferably evolutionary, preferably a simulated annealing algorithm. Such an algorithm is well known for nonlinear optimization.
If one has left the cycling, without a satisfactory score having been obtained, for example without the score having been able to reach said threshold, the process can be stopped (situation of failure) or a new step C) can be launched , with new discriminating information and / or with a new updated image. The process can also be continued with the virtual acquisition conditions corresponding to the best score achieved. A warning can be issued to inform the user of the error on the result.
If one has left the cycling cycle when a satisfactory score has been obtained, for example because the score has reached or even exceeded said threshold, the virtual acquisition conditions correspond substantially to the actual acquisition conditions of the updated image. .
Preferably, the virtual acquisition conditions include the calibration parameters of the acquisition device. The method thus makes it possible to evaluate the values of these parameters without it being necessary to know the nature of the acquisition device or its adjustment. The acquisition of the updated images can therefore be carried out without particular precautions, for example by the patient himself by means of his mobile telephone.
In addition, the search for the actual calibration is carried out by comparing an updated image with views of a reference model under virtual acquisition conditions to be tested. Advantageously, it does not require that the updated image show a calibration standard gauge, that is to say a gauge whose characteristics are precisely known enabling the calibration of the acquisition device to be determined.
Step C) therefore leads to the determination of virtual acquisition conditions having maximum agreement with the actual acquisition conditions. The reference image is therefore in maximum agreement with the updated image, that is to say that these two images are substantially superimposable.
In step D), the reference tooth areas are identified on the reference image and they are transferred to the updated image to define corresponding updated tooth areas.
In particular, the reference image is a view of the updated reference model segmented into tooth models. The limits of the representation of each tooth model on the reference image, or "reference tooth zone", can therefore be identified.
The superimposition of the updated and reference images then makes it possible to transfer the limits of the reference tooth areas to the updated image, and thus to define the updated tooth areas. The reference image being in maximum agreement with the updated image, the updated tooth zones therefore substantially define the limits of the tooth models represented on the reference image.
In step E), the tooth attribute value (s) of the corresponding tooth model are assigned to each updated tooth zone.
In particular, the reference image is a view of the updated reference model in which the tooth models have been assigned respective tooth attribute values for at least one tooth attribute, for example a tooth number. Each reference tooth area can therefore inherit the tooth attribute value from the tooth model it represents. Each updated tooth area can then inherit the tooth attribute value from the reference tooth area that was used to define it.
At the end of step E), an updated image and a description of the updated image are thus defined defining one or more updated tooth zones and, for each of these zones, a tooth attribute value for at minus a tooth attribute, for example a tooth number.
The updated image enriched with its description is called "historical image".
Figure 17a shows an example of an updated image (acquired in step B)) being analyzed to determine the contours of the teeth. Figure 17b shows the reference image showing maximum agreement with the updated image (resulting from step C)). The tooth numbers are displayed on the corresponding teeth. FIG. 17c illustrates the transfer of the tooth numbers to the updated tooth zones (steps D) and E))
In step F), the historical image is added to the learning base.
Steps A) to F) are preferably carried out for more than 1,000, more than 5,000, or more than 10,000 different patients, or "historical patients".
As is now apparent, the invention provides a particularly effective method for creating a learning base.
Second main embodiment of the enrichment process
The invention is however not limited to the embodiments described above.
In particular, the updated reference model is not necessarily the direct result of a scan of the patient's arch. The updated reference model can in particular be a model obtained by deformation of an initial reference model itself resulting directly from such a scan.
The process then preferably comprises, in place of steps A) to C), steps A ’) to C’) ·
Step A ’) is identical to step A). In step A ’), the generated reference model is however intended to be modified. It is therefore called an "initial reference model", not an "updated reference model", as in step A).
The initial reference model can in particular be generated at an initial instant preceding active orthodontic treatment, for example less than 6 months, less than 3 months, or less than 1 month before the start of treatment. Steps B ’) to C’) can then be implemented to monitor the progress of the processing between the initial instant and the updated instant of step B ’).
The initial instant may alternatively be an instant at the end of active orthodontic treatment, for example less than 6 months, less than 3 months, or less than 1 month after the end of treatment. Steps B ’) to C’) can then be implemented to monitor the occurrence of a possible recurrence.
Step B ') is identical to step B). In step B ’), the updated images are however also intended to guide the modification of the initial reference model to define the updated reference model, in step C’).
The time interval between steps A ’) and B’) is not limited, since, as explained below, the initial reference model will be deformed to obtain an updated reference model in maximum agreement with the updated images. The time interval between steps A ’) and B’) can be, for example, more than 1 week, 2 weeks, 1 month, 2 months or 6 months.
Step C ’) is more complex than step C) since the search for a reference image having a maximum agreement with an updated image is not limited to searching for the optimal virtual acquisition conditions. It also includes a search for an updated reference model, that is to say a reference model in which the teeth have substantially the same position as on the updated image.
Step C ’) preferably includes one or more of the characteristics of steps c), d) and e) of WO 2016 066651, and in particular of step e) illustrated in FIG. 16.
The objective is to modify the initial reference model until obtaining an updated reference model which has maximum agreement with the updated image. Ideally, the updated reference model is therefore an arcade model from which the updated image could have been taken if this model had been the arcade itself.
We therefore test a succession of reference models "to be tested", the choice of a reference model to be tested being preferably dependent on the level of correspondence of the reference models "to be tested" previously tested with the updated image.
Preferably, the search includes, for an updated image,
a first optimization operation making it possible to search, in a reference model to be tested determined from the initial reference model, virtual acquisition conditions which best correspond to the actual acquisition conditions of the updated image, and
- a second optimization operation making it possible to search, by testing a plurality of said reference models to be tested, the reference model best corresponding to the positioning of the patient's teeth during the acquisition of the updated image.
Preferably, a first optimization operation is performed for each test of a reference model to be tested during the second optimization operation.
Preferably, the first optimization operation and / or the second optimization operation, preferably the first optimization operation and the second optimization operation implement a metaheuristic method, preferably evolutionary, preferably a simulated annealing. .
Step C ’) therefore leads to the determination
- an updated reference model with maximum agreement with the updated image, and
- virtual acquisition conditions which are as close as possible to the actual acquisition conditions.
A process comprising steps A ’) to C’) can advantageously be implemented as part of active or passive orthodontic treatment, or, more generally, to monitor any development of the teeth.
In the various methods according to the invention, the enrichment of the learning base does not necessarily result from an enrichment method according to the invention.
In one embodiment, the learning base is created by an operator. The latter analyzes thousands of analysis images. So that the learning base can be used for the implementation of a detailed analysis process, it determines the tooth zones, then assigns them attribute values of tooth. So that the learning base can be used for the implementation of a global analysis process, it assigns image attribute values to each image. It can thus constitute historical images.
Method for detailed image analysis
The method for detailed analysis of an “analysis image” of a dental arch of a patient according to the invention comprises steps 1) to 4).
In step 1), a learning base is created comprising more than 1,000, preferably more than 5,000, preferably more than 10,000, preferably more than 30,000, preferably more than 50,000, preferably over 100,000 historical images. The higher the number of historical images, the better the analysis performed by the process.
Preferably, an enriched learning base is used according to an enrichment method according to the invention.
The learning base can however be made up by other methods, for example being created manually. To create a historical image of the learning base, an operator, preferably an orthodontist, identifies one or more “historic” tooth areas on a so-called image, then assigns, to each identified historic tooth area, a value for the minus a tooth attribute
In step 2), we train a deep learning device, preferably a neural network, with the learning base.
A "neural network" or "artificial neural network" is a set of algorithms well known to those skilled in the art.
The neural network can in particular be chosen from:
networks specialized in image classification, called "CNN" ("Convolutional neural network"), for example
- AlexNet (2012)
- ZF Net (2013)
- VGG Net (2014)
- GoogleNet (2015)
- Microsoft ResNet (2015)
- Caffe: BAIR Referenced CaffeNet, BAIR AlexNet
- Torch: VGG CNN S, VGG CNN M, VGG CNN M 2048, VGG CNN M l0 24, VGG_CNN_M_128, VGG_CNN_F, VGG ILSVRC-2014 16-layer, VGG ILSVRC-2014 19-layer, Network-in-Network (Imagenet & CIFAR -10)
- Google: Inception (V3, V4).
- Networks specializing in the localization and detection of objects in an image, the Object Detection Network, for example:
- R-CNN (2013)
- S SD (Single Shot MultiBox Detector: Object Detection network), Faster RCNN (Faster Region-based Convolutional Network method: Object Detection network)
- Faster R-CNN (2015)
- SSD (2015).
The above list is not exhaustive.
In step 2), the deep learning device is preferably driven by a learning process called "deep learning". By presenting, at the input of the deep learning device, historical images (images + descriptions), the deep learning device gradually learns to recognize patterns, in English "patterns", and to associate them with tooth fields and tooth attribute values, for example tooth numbers.
In step 3), we submit the image we want to analyze, or "analysis image", to the deep learning device.
Thanks to its training in step 2), the deep learning device is capable of analyzing the analysis image and of recognizing said patterns. In particular, it can determine a probability relating to:
- the presence, at a location in said analysis image, of an area representing, at least partially, a tooth, or "analysis tooth area",
- the attribute value of the tooth represented on said analysis tooth zone.
For example, he is able to determine that there is a 95% chance that some form of the scan image represents an incisor.
Preferably, the deep learning device analyzes the entire analysis image and determines probabilities for all of the analysis tooth zones that it has identified.
In step 4), the results of the previous step are analyzed to determine the teeth represented on the analysis image.
When the learning base contains more than 10,000 historical images, step 3) leads to particularly satisfactory results. In particular, such a learning base makes it possible to establish a probability threshold such that if a probability associated with an analysis tooth zone and with a tooth attribute value for this analysis tooth zone exceeds said threshold, the analysis tooth area effectively represents a tooth having said tooth attribute value.
Step 4) thus leads to the definition of an analysis image enriched with a description defining the analysis tooth zones and, for each analysis tooth zone, the values of the attributes of the tooth represented by the analysis tooth area.
Method for global image analysis
The method of global analysis of an updated image of a dental arch of a patient according to the invention comprises steps Γ) to 3 ’).
The method is similar to the detailed analysis method described above, with the difference that, according to the global analysis, it is not necessary to analyze the individual situation of each tooth. The analysis is global to the whole image. In other words, the deep learning device determines the value of an "image" attribute without having to determine tooth attribute values beforehand.
For example, the deep learning device can conclude that, "overall", the dental situation is "satisfactory" or "unsatisfactory", without determining the tooth possibly causing the dissatisfaction.
Step 1 ’) is similar to step 1). Historical images, however, include a description specifying an image attribute value for each image.
Step 2 ’) is similar to step 2).
In step 3 ’), the analysis image is submitted to the deep learning device.
Thanks to its training in step 2 ’), the deep learning device is able to analyze the analysis image and recognize said patterns. Based on these reasons, it can in particular determine a probability relating to the value of the image attribute considered.
Application to the modeling of a dental arch
A detailed analysis method according to the invention is in particular useful for modeling a dental arch, in particular for establishing a remote diagnosis.
It is desirable that everyone regularly have their teeth checked, in particular to check that the position of their teeth does not change unfavorably. During orthodontic treatment, this unfavorable development can in particular lead to modification of the treatment. After an orthodontic treatment, an unfavorable course, called "recurrence", can lead to a resumption of treatment. Finally, more generally and independently of any treatment, everyone may wish to follow the possible movements of their teeth.
Classically, the checks are carried out by an orthodontist who has suitable equipment. These controls are therefore expensive. In addition, visits are binding. Finally, some people are apprehensive about visiting an orthodontist and will give up making an appointment for a simple check-up or to assess the feasibility of orthodontic treatment.
US 2009/0291417 describes a method for creating and then modifying three-dimensional models, in particular for the manufacture of orthodontic appliances.
WO 2016 066651 describes a method for controlling the positioning and / or the shape and / or the appearance of teeth of a patient. This process includes a step of creating an initial reference model of the teeth, at an initial instant, preferably with a 3D scanner, then, at a later instant, or "updated instant", for example six months after the instant. initial, the creation of an updated reference model, by deformation of the initial reference model. This deformation is carried out in such a way that the updated reference model allows observations that are substantially identical to images of the teeth acquired at the updated instant, in particular photos or video images taken by the patient himself, without special precautions, say "updated images".
The updated images are therefore used to modify the very precise initial reference model. The updated reference model which results from the deformation of the initial reference model, guided by the analysis of the updated images, is therefore also very precise.
The method described in WO 2016/66651, however, requires an appointment with the orthodontist in order to create the initial reference model. This meeting is an obstacle to prevention. Indeed, a patient will not necessarily consult an orthodontist if he does not perceive the need for it. In other words, the process is often only implemented when a malocclusion is noted and it must be corrected.
There is therefore a need for a method responding to this problem, by facilitating prevention.
An object of the invention is to meet this need.
To this end, the invention provides a method of modeling a dental arch of a patient, said method comprising the following steps:
a) creation of a historical library comprising more than 1000 models of teeth, known as “models of historic teeth”, and attribution to each model of historic tooth, of a value for at least one attribute of tooth, or “value of 'tooth attribute';
b) analysis of at least one “image of analysis” of the dental arch according to a detailed analysis method according to the invention, so as to determine at least one zone of analysis tooth and at least one value d 'tooth attribute associated with said analysis tooth area;
c) for each analysis tooth zone determined in the previous step, search, in the historical library, for a historical tooth model having maximum proximity to the analysis image or to the analysis tooth zone analysis, or "optimal tooth model";
d) arrangement of the set of optimal tooth models so as to create a model which has maximum agreement with the updated image, or "assembled model";
e) optionally, replacement of at least one optimal tooth model by another historic tooth model and repeated in step d) so as to maximize the agreement between the assembled model and the analysis image;
f) optionally, repeat from step b) with another analysis image and in step d) and / or e), search for maximum agreement with all of the analysis images used.
The invention thus makes it possible, from a simple analysis image, for example from a photograph taken by means of a mobile telephone, to reconstruct, with good reliability, a dental arch. Of course, the analysis of a single analysis image is not enough to generate an assembled model that precisely matches the arrangement of the patient's teeth. Such precision is however generally not essential for carrying out an initial diagnosis of the patient's dental situation.
In addition, the precision of the assembled model can be increased if several analysis images are processed.
Steps b) to c) are preferably implemented for several analysis images and, in steps d) and e), optimal tooth models and an assembled model are sought in order to obtain maximum agreement with regard to all the analysis images (step f)).
The invention also relates to a method for evaluating a dental situation of a patient, comprising the following steps:
i) creation of an assembled model according to a modeling process according to the invention;
ii) transmission of the assembled model to a recipient, preferably an orthodontist and / or a computer;
iii) analysis of the patient's orthodontic situation, by the recipient, from the assembled model;
iv) preferably, informing the patient of the orthodontic situation, preferably via his mobile phone.
The patient can therefore very easily ask an orthodontist to check his dental situation, without even having to move, by simply transmitting one or preferably several photos of his teeth.
A modeling process is now described in detail.
In step a), a historical library is created comprising more than 1,000, preferably more than 5,000, preferably more than 10,000 models of historical teeth. The higher the number of historical tooth models, the more precise the assembled model.
Preferably, the library is enriched with the tooth models resulting from the implementation of the method described in WO 2016 066651 or from step A) or A ’) described above.
One or more tooth attributes, particularly chosen from the list provided above, are associated with tooth models. A tooth attribute value is assigned to each tooth attribute of a particular tooth model, as described above (see the description in step A)). For example, a tooth model is that of an "incisor", "heavily worn" and whose color parameters are, in the L * a * b * color system according to standard NF ISO 7724, "a * = 2 "," b * = l "and" L * = 58 ".
In step b), the analysis image is analyzed according to a detailed analysis method according to the invention. The optional features of this process are also optional in step b).
According to one embodiment, in step b), the analysis image is acquired with a mobile phone before analyzing it.
According to one embodiment, at the beginning of step d), a first coarse arrangement is created by orienting the optimal tooth models so that their optimal viewing directions are all parallel, the optimal viewing direction of a tooth model being the direction in which said tooth model has maximum agreement with the analysis image.
According to one embodiment, in step d) and / or e) and / or f), a metaheuristic method is used, preferably evolutionary, preferably by simulated annealing.
At the end of step b), an analysis image is obtained enriched with a description providing, for each analysis tooth zone, a tooth attribute value for at least one tooth attribute, by example a tooth number.
In step c), a search is made in the historical library, for each analysis tooth zone determined in the previous step, of a historical tooth model having maximum proximity to the analysis tooth zone. This tooth model is called the "optimal tooth model".
"Proximity" is a measure of one or more differences between the historic tooth model and the analysis tooth area. These differences may include a difference in shape, but also other differences such as a difference in translucency or color. Maximum proximity can be sought by successively minimizing several differences, or by minimizing a combination of these differences, for example a weighted sum of these differences.
"Proximity" is therefore a broader concept than "concordance", the concordance measuring only a proximity relative to the shape.
The evaluation of the proximity of a historic tooth model to an analysis tooth zone preferably comprises a comparison of at least one value of a tooth attribute of the analysis tooth zone with the value of this attribute for the historic tooth model. Advantageously, such an evaluation is very rapid.
For example, if the description of the analysis tooth zone provides a value for the type or number of the tooth, the thickness of the tooth represented and / or the height of its crown and / or its mesio- palatine and / or the deflection index in mesial and distal of its incisal edge, this value can be compared with the value of the corresponding attribute of each of the historical tooth models.
Preferably, we are looking for a historic tooth model having, for at least one tooth attribute, the same value as said analysis tooth zone. The tooth attribute can in particular relate to the type of tooth or the tooth number. In other words, the historical tooth models are filtered to examine in more detail than those relating to the same type of tooth as the tooth represented on the analysis tooth area.
Alternatively or, preferably, in addition to this comparison of attribute values, the shape of the tooth represented on the analysis tooth area can be compared with the shape of a historic tooth model to be evaluated, preferably at by means of a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
To this end, we observe from different angles the historical tooth model to be evaluated. Each view thus obtained is compared with the analysis image, preferably with the analysis tooth area so as to establish a "distance" between this view and said analysis image or, preferably, said tooth area analysis. The distance thus measures the difference between the view and the analysis tooth area.
The distance can be determined after processing the analysis view and image or, preferably, the analysis tooth area, so as to show, on corresponding maps, the same discriminating information, by example contour information, as described above in step C3) or in WO 2016 066651.
For each historic tooth model tested, a view is thus determined that provides a minimum distance from the analysis image or from the analysis tooth area. Each historical tooth model examined is thus associated with a particular minimum distance, which measures its shape proximity to the analysis tooth area.
The optimal historical tooth model is the one that, based on the comparison (s) made, is considered to be the closest to the analysis tooth area.
The minimum distances obtained for the different tooth models tested are then compared and, to define the optimal tooth model, the one with the smallest minimum distance is used. The optimal tooth model therefore has maximum agreement with the analysis image.
The search for maximum concordance is preferably carried out by means of a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
In a preferred embodiment, a first evaluation of the historical tooth models is carried out successively by comparing the values of at least one tooth attribute, for example of the tooth number, with the corresponding values of the analysis tooth zone. , then a second evaluation by shape comparison. The first, rapid evaluation advantageously makes it possible to filter the historical tooth models in order to submit to the second, slower evaluation, only the historical tooth models retained by the first evaluation.
For example, if an analysis tooth zone represents a # 15 tooth, the first evaluation allows only the tooth models modeling # 15 teeth to be retained. During the second evaluation, one searches among the set of historic tooth models modeling teeth # 15, the historic tooth model whose shape most closely resembles that of the tooth shown.
More preferably, several first evaluations are carried out before carrying out the second evaluation. For example, the first evaluations make it possible to filter the historic tooth models so as to retain only the tooth models modeling teeth # 15 and which have a crown height of between 8 and 8.5 mm.
At the end of step c), an optimal tooth model was thus associated with each of the analysis tooth zones.
In step d), we create an assembled model by arranging the optimal tooth models.
A first coarse arrangement can be established by considering the tooth attribute values of the optimal tooth models. For example, if the tooth numbers of optimal tooth models are those of canines and incisors, these tooth models can be arranged in an arc conventionally corresponding to the region of the arch that carries these types of teeth.
The shape of this arc can be refined based on other tooth attribute values.
The order of the optimal tooth models is that of the corresponding analysis tooth areas.
Furthermore, the minimum distance associated with an optimal tooth model results from an observation of the tooth model in an "optimal" direction of observation. In other words, it is probably in this direction that the tooth that this model models is also observed in the analysis image. All the optimal tooth models are thus preferably oriented so that their respective optimal observation directions are all parallel.
It is thus possible to define a first arrangement of the optimal tooth models.
Preferably, the first arrangement of the optimal tooth models is then modified iteratively, so as to have maximum agreement with the analysis image.
To assess an arrangement, we observe it from different angles. Each view thus obtained is compared with the analysis image so as to establish a "distance" between this view and said analysis image. Distance thus measures the difference between the view and the analysis image.
The distance can be determined after processing the view and the analysis image so as to reveal, on one of the corresponding maps, discriminating information, for example contour information, as described above in step C3) or in WO 2016 066651.
For each arrangement examined, a view is thus determined which provides a minimum distance from the analysis image. Each arrangement examined is thus associated with a minimum distance.
We then compare the minimum distances obtained for the different arrangements tested and we choose, to define the optimal arrangement, the one with the smallest minimum distance. The optimal arrangement therefore has maximum agreement with the analysis image.
The search for maximum concordance is preferably carried out by means of a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
At the end of step d), an optimal arrangement of the optimal tooth models, that is to say the assembled model, is obtained.
In optional step e), one or more optimal tooth models are replaced by other tooth models, then resumed in step d) so as to maximize the agreement between the assembled model and the image of analysis.
It is indeed possible that an optimal tooth model, in the "optimal" arrangement, no longer has a maximum agreement with the analysis image. In particular, the tooth model could be observed in an "optimal" direction which provided a view with a minimum distance from the analysis image (reason why it was considered optimal). But, in the optimal arrangement, it is no longer oriented in the optimal direction.
A new search for an assembled model can therefore be carried out by modifying the models of teeth, for example by replacing the models of optimal teeth by models of close teeth.
The search for tooth models to be tested is preferably carried out using a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
In the preferred embodiment, the method therefore implements a double optimization, on the tooth models and on the arrangement of the tooth models, the assembled model being the arrangement of a set of tooth models which provides the minimum distance from the analysis image, considering all possible tooth models and all possible layouts.
In step f), optional and preferred, the method implements several images of analysis of the patient's arch, preferably more than 3, more than 5, more than 10, more than 50, preferably more than 100 analysis images. The assembled model is thus more complete. More preferably, the method implements an optimization so that the assembled model obtained is optimal with regard to all of the analysis images. In other words, the assembled model is preferably the one that maximizes the agreement with the set of analysis images.
In the preferred embodiment, the method therefore implements a double or, preferably a triple optimization, on the tooth models on the one hand, on the arrangement of the tooth models and / or on a plurality of images. on the other hand, the assembled model being the arrangement of a set of tooth models which provides the minimum average distance, over all of the analysis images, by considering all the possible tooth models and, preferably all possible arrangements.
As is now clearly apparent, the invention thus makes it possible to construct an assembled dental arch model from simple analytical images, for example from photographs taken using a mobile telephone. Of course, the precision of the assembled model does not reach that of a scan. In certain applications, for example for carrying out an initial diagnosis of the patient's dental situation, such precision is however not essential.
The assembled model can therefore be used to analyze the patient's orthodontic situation, following steps ii) to iv).
In step ii), the assembled model is sent to an orthodontist and / or to a computer with diagnostic software.
In one embodiment, the assembled model is sent accompanied by a questionnaire completed by the patient in order to improve the quality of the analysis in step iv).
In step iii), the orthodontist and / or the computer examines the assembled model. Unlike an updated image, the assembled model allows observation from any angle. The analysis is advantageously more precise.
In step iv), the orthodontist and / or the computer informs the patient, for example by sending him a message on his phone. This message can in particular inform the patient of an unfavorable situation and invite him to make an appointment with the orthodontist.
The orthodontist can also compare the assembled model with assembled models received previously for the same patient. Its analysis advantageously makes it possible to assess the evolution of the situation. The message can thus inform the patient of an unfavorable development of his situation, which improves prevention.
The assembled model can also be compared with one or more models obtained by scanning the teeth or by molding the patient's teeth, or with an updated reference model resulting from the implementation of a method described in WO 2016 066651.
Application to on-board control
An image analysis according to the invention is also useful for guiding the acquisition of an image of a dental arch, in particular for establishing a remote diagnosis.
In particular, WO2016 / 066651 describes a method in which an initial reference model is deformed so as to obtain an updated reference model allowing the acquisition of reference images having maximum agreement with the "updated" images of the arch. acquired at the present time.
The reference images are therefore views of the updated reference model, observed under virtual acquisition conditions which are as consistent as possible with the actual acquisition conditions implemented to acquire the updated images of the patient's arch.
The search for these virtual acquisition conditions is preferably carried out using metaheuristic methods.
To speed up this research, WO2016 / 066651 recommends carrying out a first rough evaluation of the actual acquisition conditions. For example, we exclude from the search conditions that would correspond to a position of the acquisition device at a distance from the teeth greater than 1 meter.
There is however a permanent need to accelerate the execution of the method described in WO2016 / 066651, and in particular, to search, more quickly, for virtual acquisition conditions having maximum agreement with the actual acquisition conditions implemented. works to acquire an updated image of the patient's arch.
An object of the invention is to respond, at least partially, to this problem.
The invention provides a method of acquiring an image of a dental arch of a patient, said method comprising the following steps:
a ') activation of an image acquisition device so as to acquire an image, called "analysis image", of said arch;
b ') analysis of the analysis image by means of a deep learning device, preferably a neural network, trained by means of a learning base, preferably according to a detailed analysis method according to the invention, so as to identify at least one analysis tooth area representing a tooth on said analysis image, and to determine at least one tooth attribute value for said analysis tooth area, or according to a global analysis method according to the invention;
c ′) determination, for the analysis image, of a value for an image attribute, said value being a function of said tooth attribute value if a detailed analysis method according to the invention has been implemented in the previous step;
d ') optionally, comparing said image attribute value with a setpoint;
e ') transmission of an information message as a function of said comparison.
As will be seen in more detail in the following description, an acquisition method according to the invention therefore makes it possible to verify whether an analysis image complies with a set point and, if it does not comply with the set point, to guide the operator to acquire a new analysis image. The method therefore allows "on-board control", preferably in the image acquisition device.
In particular, to implement the method of WO2016 / 066651, it may be desired to acquire updated images according to different acquisition directions, for example a front image, a right image and a left image. These updated images, acquired successively, can be classified accordingly. The search for virtual acquisition conditions with maximum agreement with the actual acquisition conditions is accelerated.
Indeed, the search can start from virtual acquisition conditions in which the acquisition device, virtual, is opposite, to the left or to the right of the updated reference model, depending on whether the updated image considered is classified. as a front, left, or right image, respectively.
The operator, usually the patient, may however be mistaken when acquiring the updated images. In particular, he may forget to take an updated image, for example the front view, or reverse two updated images. Typically, the operator can take a picture on the right while expecting a picture on the left.
This inversion of the updated images can considerably slow down their processing. For example, if the updated image is supposed to be an image taken on the left but that it was mistakenly taken on the right, said search for optimal virtual acquisition conditions, that is to say having maximum agreement with the actual acquisition conditions will start from a starting point offering a left view of the reference model, while the optimal virtual acquisition conditions correspond to a right view. Research will therefore be considerably slowed down.
Thanks to the invention, each updated image is an analysis image which can be analyzed and controlled, preferably in real time.
For example, the acquisition method makes it possible to determine that the updated image has been “taken on the right” and to compare this image attribute value with the instruction which had been given to the operator to take the image. updated on the left. The attribute value of the updated image (image taken on the right) does not correspond to the setpoint (acquire an updated image on the left), the acquisition device can immediately notify the operator so that he changes the direction acquisition.
An acquisition process is now described in detail.
In step a ’), the operator activates the image acquisition device so as to acquire an analysis image.
In one embodiment, the operator triggers the acquisition device so as to store the analysis image, preferably takes a photo or video of his teeth, preferably by means of a mobile telephone equipped with 'a camera.
Step a ’) can be performed as the acquisition of the images updated in step B) described above.
In another embodiment, the analysis image is not stored. In particular, the analysis image may be the image which, in real time, appears on the screen of the operator's mobile phone, generally the patient.
In a first embodiment, in step b ’), the analysis image is analyzed according to a detailed analysis method according to the invention. This analysis preferably results in the assignment of a tooth attribute value to each identified analysis tooth zone, for example in assigning a tooth number to each of the analysis tooth zones.
In step c '), an attribute value of the analysis image is determined based on the tooth attribute values. The attribute value of the analysis image can be relative to its general orientation and can for example take one of the following three values: "photo on the right", "photo on the left" and "photo on the front". The attribute value of the analysis image can also be the list of the numbers of the teeth represented, for example, "16, 17 and 18". The attribute value of the analysis image can also be, for example, the "presence" or "absence" of an orthodontic appliance, or the state of opening of the mouth ("open mouth"). , " closed mouth ").
In another embodiment, a global analysis method according to the invention is implemented in step b ’). Advantageously, such a method makes it possible to directly obtain a value for an image attribute, without having to determine values for a tooth attribute. It is therefore advantageously faster. The information resulting from a global analysis may, however, be less precise than that resulting from a detailed analysis.
Steps a ’) to c’) thus make it possible to characterize the analysis image.
The characterization of the analysis image makes it possible to guide the operator if the analysis image does not correspond to the expected image, for example because its quality is insufficient or because it does not represent the desired teeth. .
In step d), the image attribute value of the analysis image is compared with a setpoint.
For example, if the instruction was to acquire an image on the right and the image attribute value is "taken on the left", the comparison leads to the conclusion that the acquired image is "unsatisfactory".
In step e ’), a message is sent to the operator, preferably by the acquisition device.
Preferably, the information message relates to the quality of the acquired image and / or to the position of the acquisition device with respect to said arch and / or to the setting of the acquisition device and / or when you open your mouth and / or wear an orthodontic appliance.
For example, if the acquired image is "unsatisfactory", the acquisition device can emit a light, for example red, and / or ring, and / or generate a voice message, and / or vibrate, and / or display a message on his screen.
For example, if the image is to be acquired while the patient is wearing their orthodontic appliance and this is not the case, the acquisition appliance may issue the message "wear your appliance for this image".
For example, if the image was acquired when the patient does not open his mouth enough or his mouth is closed, the acquisition device may issue the message "open your mouth more for this image".
In one embodiment, steps b ’) to c’) are implemented only if the operator saves the analysis image, that is to say that he presses the trigger. The message then invites the operator to acquire a new analysis image. Optionally, the acquisition device erases the unsatisfactory analysis image.
In one embodiment, steps b ') to c') are implemented permanently when the acquisition device is running and the analysis image is an image which appears on a screen of the device acquisition. The acquisition device can thus, for example, emit red light as long as the analysis image is unsatisfactory, and emit green light when the analysis image is satisfactory. Advantageously, the acquisition device then stores only analysis images which are satisfactory.
As is now clearly apparent, the invention therefore provides on-board control during the acquisition of analysis images. Applied to updated images of the process of WO2016 / 066651, steps a ’) to e’) make it possible to ensure that these images are indeed in conformity with the need, and therefore to considerably speed up the execution of this process.
Steps d) and e are optional. In one embodiment, the analysis image is only associated with its description, which specifies its image attribute value. This description also makes it possible to considerably speed up the execution of the method of WO2016 / 066651 since, when the analysis image is used as an updated image of this method, it makes it possible to approximately determine the conditions of actual acquisition of this image, by eliminating the risk of a gross error, for example due to an inversion between two images.
Steps d) and e are preferred, however. They allow, for example, to prevent the operator from forgetting a left image, or taking two redundant right images.
Application to the control of an orthodontic splint
Conventionally, at the start of an orthodontic treatment, the orthodontist determines the positioning of the teeth that he wishes to obtain at a time during the treatment, known as a set-up. The set-up can be defined by means of an impression or from a three-dimensional scan of the patient's teeth. The orthodontist then has or manufactures, therefore, an orthodontic appliance suitable for this treatment.
The orthodontic appliance can be an orthodontic tray (“align” in English). A gutter is conventionally in the form of a removable monobloc device, conventionally made of a transparent polymer material, which has a chute shaped so that several teeth of an arch, generally all the teeth of an arch, can be accommodated there.
The shape of the chute is adapted to hold the gutter in position on the teeth, while exerting an action to correct the positioning of certain teeth (Figures 14 and 15).
Classically, at the start of the treatment, the shapes which the different gutters must take at different times of the treatment are determined, then all the corresponding gutters are made. At predetermined times, the patient changes gutters.
The treatment using gutters is advantageously not very restrictive for the patient. In particular, the number of orthodontist appointments is limited. In addition, the pain is less than with a metal orthodontic archwire attached to the teeth.
The market for orthodontic aligners is therefore growing.
At regular intervals, the patient goes to the orthodontist for a visual check, in particular to check if the movement of the teeth is in accordance with expectations and if the splint worn by the patient is still suitable for the treatment.
If the orthodontist diagnoses an inadequacy to the treatment, he performs a new impression of the teeth, or, equivalently, a new three-dimensional scan of the teeth, then orders a new series of aligners configured accordingly. It is considered that on average, the number of gutters finally produced is around 45, instead of the 20 gutters conventionally provided at the start of treatment.
The need to travel to the orthodontist is a constraint for the patient. The patient's confidence in his orthodontist can also be damaged. Unsuitability can be unsightly. Finally, this results in an additional cost.
The number of follow-up visits to the orthodontist must therefore be limited.
There is a need for solutions to these problems.
An object of the invention is to respond, at least partially, to this need.
The invention provides a method for evaluating the shape of an orthodontic splint, said method comprising the following steps:
a) acquisition of at least one image representing at least partially the gutter in a service position in which it is carried by a patient, called "analysis image";
b) analysis of the analysis image by means of a deep learning device, preferably a neural network, trained by means of a learning base, so as to determine a value for at least one attribute of an "analysis tooth area" of the analysis image, the tooth attribute relating to a spacing between the tooth represented by the analysis tooth area, and the groove represented on the analysis image, and / or for an image attribute of the analysis image, the image attribute relating to a spacing between at least one tooth represented on the analysis image, and the gutter represented on said analysis image;
c) preferably, evaluation of the suitability of the gutter as a function of the value of said attribute of tooth or image;
d) preferably, sending an information message based on said assessment.
As will be seen in more detail in the following description, an evaluation method according to the invention considerably facilitates the evaluation of the good suitability of the gutter for treatment, while making this evaluation particularly reliable. In particular, the method can be implemented from simple photographs or films, taken without particular precautions, for example by the patient. The number of orthodontist appointments may therefore be limited.
Preferably, in step b ”), all of said analysis tooth zones are identified, and the value of said tooth attribute is determined for each analysis tooth zone, and, in step c”), the adequacy of the gutter is determined as a function of said tooth attribute values.
Preferably, said tooth attribute is chosen from the group formed by a maximum spacing along the free edge of the tooth, an average spacing along the free edge of the tooth, and said image attribute is chosen from the formed group by a maximum spacing along the set of teeth shown, an average spacing along the free edges of the set of teeth shown, overall acceptability of the spacing of the teeth shown.
The tooth attribute relating to a spacing can in particular be the existence of a spacing, this attribute being able to take the attribute values of tooth "yes" or "no"; or a value measuring the extent of the gap, such as a maximum gap seen or an assessment of a scale.
In step b ”), a detailed analysis method according to the invention is preferably implemented, a tooth attribute of each historical tooth zone of each historical image of the learning base being relative to a spacing between the tooth represented by the historic tooth area, and a gutter carried by said tooth and represented on said historic image.
Preferably, step b ”) comprises the following steps:
bl) preferably before step a ”), creation of a learning base comprising more than 1,000, preferably more than 5,000, preferably more than 10,000 images of dental arches, or“ historical images ” , each historic image representing a gutter worn by a "historic" patient and comprising one or more zones each representing a tooth, or "historic tooth zones", each of which, for at least one attribute of tooth relating to a spacing between the tooth represented by the historic tooth zone considered, and the gutter represented, a tooth attribute value is assigned;
b2) learning a deep learning device, preferably a neural network, by means of the learning base;
b3) submitting the analysis image to the deep learning device so that the deep learning device determines at least one probability relating to
- the presence, at a location of said analysis image, of an analysis tooth zone, and
- the tooth attribute value of the tooth represented on said analysis tooth zone;
b4) determination, as a function of said probability, of the presence of a spacing between the gutter and the tooth represented by said area of analysis tooth, and / or of an amplitude of said spacing.
Steps b ”l) to b” 4) may include one or more of the characteristics, possibly optional, of steps 1) to 4) described above, respectively.
In one embodiment, in step b ”), a global analysis method according to the invention is implemented, an image attribute of each historical image of the learning base being relative to a spacing between at least one tooth shown on the historical image, and a gutter carried by said tooth and represented on said historical image.
Preferably, step b ”) comprises the following steps:
b'T) creation of a learning base comprising more than 1,000 images of dental arches, or “historical images”, each historical image comprising an attribute value for at least one image attribute, or “value image attribute ”, relating to a spacing between at least one tooth shown on the analysis image, and the gutter represented on said analysis image;
b2 ') training of at least one deep learning device, preferably a neural network, by means of the learning base;
b3 ′) submission of the analysis image to the deep learning device so that it determines, for said analysis image, at least one probability relating to said image attribute value, and determination, in as a function of said probability, of the presence of a spacing between the gutter and the tooth or teeth shown on the analysis image, and / or of an amplitude of said spacing.
Steps b ”l’) to b ”3’) may include one or more of the optional features of steps Γ) to 3 ’) described above, respectively.
The process is now described when a detailed analysis is carried out in step b ”) ·
Prior to step a ”), the learning base must be enriched, preferably according to an enrichment method according to the invention, in order to contain historical images whose description specifies, for each of the historical tooth zones, a value for the tooth attribute relative to the spacing.
This information can be entered manually. For example, we can present to an operator, preferably to an orthodontist, an image representing one or more so-called “historic” tooth areas, and ask him to identify these historic tooth areas and to indicate, for each area of historical tooth, whether there is a gap or not and / or to assess the amplitude of this gap.
A historic image can be a photo representing a gutter worn by a historic patient. Alternatively, a historical image can be the result of a processing of an image representing a bare dental arch (that is to say without a gutter) and an image representing the same arch bearing the gutter. The image representing the naked arch can in particular be a view of a model of the arch deformed to obtain maximum agreement with the image representing the arch bearing the gutter. Such treatment can be particularly useful for making the contours of the teeth and gutter appear better when the teeth are barely visible through the gutter.
In step a ”), the acquisition of the analysis image can be carried out like the acquisition of the images updated in step B) described above.
Preferably, at least one reminder informing the patient of the need to create an analysis image is sent to the patient. This reminder can be in paper form or, preferably, in electronic form, for example in the form of an email, an automatic alert of a specialized mobile application or an SMS. Such a reminder can be sent by the orthodontic office or laboratory or by the dentist or by the patient's specialized mobile application, for example.
Step a ”) is carried out when the evaluation of the shape of a gutter is desired, for example more than 1 week after the start of treatment with the gutter.
The analysis image is an image representing the gutter carried by the patient's teeth.
In step b ”), the analysis image is analyzed according to a detailed analysis method according to the invention.
The deep learning device was trained by means of a learning base containing historical images whose description specifies, for at least one, preferably each historic tooth zone, a value for a tooth attribute relating to a spacing between the tooth represented by the historic tooth area and the gutter carried by said tooth and represented on said historical image.
The deep learning device is therefore capable of analyzing the analysis image to determine, preferably for each of the “analysis tooth zones”, the existence, or even the importance, of a separation of the gutter. of the tooth shown in the analysis tooth area.
In step c ”), we assess, based on the results of the previous step, if the tray is not too loose from the teeth. For example, we find out if the spacing of the gutter with at least one tooth exceeds an acceptability threshold and, in this case, we decide to replace the gutter with a better adapted gutter.
In step d), information relating to the evaluation in the previous step is sent, in particular to the patient and / or the orthodontist.
In one embodiment, the method comprises, in step b ”), a global analysis according to the invention. The other steps are not changed.
The analysis of the analysis image and of the historical images is then carried out globally, without identifying the individual situation of each of the teeth represented and the image attribute relates to the image as a whole.
For example, the image attribute relating to the spacing may be relative to the acceptability of a dental situation, due to one or more spacings, or relating to the overall magnitude of the spacing (s) of the teeth. For example, the value of the image attribute can be "globally acceptable" or "globally unacceptable".
As is now clearly apparent, a method according to the invention makes it possible, from simple photos or a simple film, to determine whether the gutter is abnormally detached, or even, if a detailed analysis has been carried out in step b ”), To determine the regions in which the gutter has moved away from the teeth and to assess the extent of this separation.
The invention also relates to a method for adapting an orthodontic treatment, method in which a method of evaluating the shape of an orthodontic splint according to the invention is implemented, then, depending on the result of said evaluation. , a new splint is made and / or the patient is advised, for example so that he improves the conditions of use of his orthodontic splint, in particular the positioning and / or the time slots for wearing and / or the maintenance of his orthodontic splint, to optimize the treatment.
The use of aligners is not limited to therapeutic treatments. In particular, an evaluation process can be implemented to evaluate a gutter exclusively used for aesthetic purposes.
The method can also be used to assess other orthodontic parts or appliances.
Computer program
The invention also relates to:
a computer program, and in particular a specialized application for a mobile telephone, comprising program code instructions for the execution of one or more steps of any method according to the invention, when said program is executed by a computer,
- a computer medium on which such a program is recorded, for example a memory or a CD-ROM.
Of course, the invention is not limited to the embodiments described above and shown.
In particular, the patient is not limited to a human being. A method according to the invention can be used for another animal.

权利要求:
Claims (15)
[1" id="c-fr-0001]
1. A method of modeling a dental arch of a patient, said method comprising the following steps:
a) creation of a historical library comprising more than 1000 models of teeth, known as “models of historic teeth”, and attribution to each model of historic tooth, of a value for at least one attribute of tooth, or “value of 'tooth attribute';
b) analysis of at least one “analysis image” of the dental arch using a deep learning device, preferably a neural network, so as to determine at least one analysis tooth area and at least one tooth attribute value associated with said analysis tooth area;
c) for each analysis tooth zone determined in the previous step, search, in the historical library, for a historical tooth model having maximum proximity to the analysis image or to the analysis tooth zone analysis, or "optimal tooth model" and preferably having, for at least one attribute of a tooth, the same value as said zone of analysis tooth;
d) arrangement of the set of optimal tooth models so as to create a model which has maximum proximity to the updated image, or "assembled model";
e) optionally, replacement of at least one optimal tooth model by another tooth model and repeated in step d) so as to maximize the agreement between the assembled model and the analysis image;
f) optionally, repeat from step b) with another analysis image and, in step d) and / or e), search for maximum agreement with all of the analysis images used.
[2" id="c-fr-0002]
2. Method according to the immediately preceding claim, in which said tooth attribute is chosen from a tooth number, a type of tooth, a parameter of shape of the tooth, a parameter of appearance of the tooth, a parameter relating to the state of the tooth, age for the patient, or a combination of these attributes.
[3" id="c-fr-0003]
3. Method according to any one of the preceding claims, in which step c) comprises, to evaluate the proximity of a historic tooth model with the analysis tooth area, a comparison of at least one value d 'a tooth attribute of the analysis tooth area with the value of this attribute for the historic tooth model.
[4" id="c-fr-0004]
4. Method according to any one of the preceding claims, in which step c) comprises, to evaluate the proximity of a historic tooth model with the analysis tooth area, a comparison of the shape of the tooth shown on the analysis tooth area with that of the historic tooth model.
[5" id="c-fr-0005]
5. Method according to any one of the preceding claims, in which in step c), a first evaluation of the historical tooth models is carried out successively by comparison of the values of at least one tooth attribute, preferably of the type of tooth or tooth number, with the corresponding values of the analysis tooth area, then a second evaluation by shape comparison.
[6" id="c-fr-0006]
6. Method according to any one of the preceding claims, in which in step c), the research includes, in particular for carrying out a shape comparison, the implementation of a metaheuristic method, preferably evolutionary, preferably by simulated annealing.
[7" id="c-fr-0007]
7. Method according to any one of the preceding claims, in which the optimal tooth model is sought with regard to a plurality of analysis images.
[8" id="c-fr-0008]
8. Method according to any one of the preceding claims, in which, in step
a), we create a historical library with more than 10,000 historical tooth models.
[9" id="c-fr-0009]
9. Method according to any one of the preceding claims, in which, in step
b), we acquire the analysis image with a mobile phone before analyzing it.
[10" id="c-fr-0010]
10. Method according to any one of the preceding claims, in which, at the beginning of step d), a first coarse arrangement is created by orienting the optimal tooth models so that their optimal directions of observation are all parallel, the optimal observation direction of a tooth model being the direction in which said tooth model has maximum agreement with the analysis image.
[11" id="c-fr-0011]
11. Method according to the immediately preceding claim, wherein said first arrangement of the optimal tooth models is modified iteratively, so as to have maximum agreement with the analysis image.
[12" id="c-fr-0012]
12. Method according to any one of the preceding claims, in which in step d) and / or e) and / or f), a metaheuristic method, preferably evolutionary, preferably by simulated annealing, is used.
[13" id="c-fr-0013]
13. Method according to any one of the preceding claims, in which steps b) to c) are implemented for several analysis images and, in steps d) and e), optimal tooth models and a model assembled so as to obtain maximum agreement with regard to all of the analysis images.
[14" id="c-fr-0014]
14. Method for evaluating a dental situation of a patient, said method comprising the following steps:
i) creation of an assembled model according to a modeling process according to any one of the preceding claims;
ii) transmission of the assembled model to a recipient;
iii) analysis of the patient's orthodontic situation, by the recipient, from the assembled model;
iv) preferably, informing the patient of the orthodontic situation, preferably via his mobile phone.
[15" id="c-fr-0015]
15. Method according to the immediately preceding claim, in which, in step ii), the assembled model is sent accompanied by a questionnaire completed by the patient in order to improve the quality of the analysis in step iv).

类似技术:

---

公开号 | 公开日 | 专利标题

---

EP3432217A1|2019-01-23|Method for analysing an image of a dental arch

---

EP3213293B1|2021-09-29|Control of dentition

---

EP3893156A1|2021-10-13|Method of analyzing an image of a dental arch

---

FR3069361B1|2019-08-23|METHOD FOR ANALYZING AN IMAGE OF A DENTAL ARCADE

---

EP3445270A1|2019-02-27|Dentition control method

---

EP3212113B1|2019-12-11|Method for monitoring an orthodontic treatment

---

EP3212115B1|2019-09-11|Method for monitoring an orthodontic treatment

---

EP3432267B1|2021-02-24|Method for analyzing an image of a dental arch

---

EP3432312A1|2019-01-23|Method for analysing an image of a dental arch

---

EP3517071A1|2019-07-31|Method for enriching a digital dental model

---

WO2020234411A1|2020-11-26|Method for generating a model of a dental arch

---

FR3095334A1|2020-10-30|METHOD OF EVALUATION OF AN ORTHODONTIC GUTTER

同族专利:

---

公开号 | 公开日

---

US20190026894A1|2019-01-24|

---

US20210358124A1|2021-11-18|

---

EP3432312A1|2019-01-23|

---

FR3069359B1|2019-08-23|

---

US11107218B2|2021-08-31|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

US20080172386A1|2007-01-17|2008-07-17|Ammar Hany H|Automated dental identification system|

---

FR3027505A1|2014-10-27|2016-04-29|H 43|METHOD FOR CONTROLLING THE POSITIONING OF TEETH|

---

US6648640B2|1999-11-30|2003-11-18|Ora Metrix, Inc.|Interactive orthodontic care system based on intra-oral scanning of teeth|

---

US8874452B2|2004-02-27|2014-10-28|Align Technology, Inc.|Method and system for providing dynamic orthodontic assessment and treatment profiles|

---

US8439672B2|2008-01-29|2013-05-14|Align Technology, Inc.|Method and system for optimizing dental aligner geometry|

---

US9788917B2|2010-03-17|2017-10-17|ClearCorrect Holdings, Inc.|Methods and systems for employing artificial intelligence in automated orthodontic diagnosis and treatment planning|

---

FR3010629B1|2013-09-19|2018-02-16|Dental Monitoring|METHOD FOR CONTROLLING THE POSITIONING OF TEETH|

---

US8885901B1|2013-10-22|2014-11-11|Eyenuk, Inc.|Systems and methods for automated enhancement of retinal images|

---

FR3027507B1|2014-10-27|2016-12-23|H 42|METHOD FOR CONTROLLING THE DENTITION|

---

US9993217B2|2014-11-17|2018-06-12|Vatech Co., Ltd.|Producing panoramic radiograph|

---

US10248883B2|2015-08-20|2019-04-02|Align Technology, Inc.|Photograph-based assessment of dental treatments and procedures|

---

FR3050375A1|2016-04-22|2017-10-27|H43 Dev|METHOD FOR CONTROLLING THE DENTITION|

---

US10888399B2|2016-12-16|2021-01-12|Align Technology, Inc.|Augmented reality enhancements for dental practitioners|CN112105315A|2018-05-08|2020-12-18|阿莱恩技术有限公司|Automatic ectopic tooth detection based on scanning|

---

DE102018210258A1|2018-06-22|2019-12-24|Sirona Dental Systems Gmbh|Process for the construction of a dental component|

---

FR3096255A1|2019-05-22|2020-11-27|Dental Monitoring|PROCESS FOR GENERATING A MODEL OF A DENTAL ARCH|

法律状态:
2019-01-25| PLSC| Publication of the preliminary search report|Effective date: 20190125 |

---

2019-07-30| PLFP| Fee payment|Year of fee payment: 3 |

---

2020-07-21| PLFP| Fee payment|Year of fee payment: 4 |

---

2021-05-26| PLFP| Fee payment|Year of fee payment: 5 |

优先权:

---

申请号 | 申请日 | 专利标题

---

FR1756944A|FR3069359B1|2017-07-21|2017-07-21|METHOD FOR ANALYZING AN IMAGE OF A DENTAL ARCADE|

---

FR1756944|2017-07-21|FR1756944A| FR3069359B1|2017-07-21|2017-07-21|METHOD FOR ANALYZING AN IMAGE OF A DENTAL ARCADE|

---

US16/031,172| US11107218B2|2017-07-21|2018-07-10|Method for analyzing an image of a dental arch|

---

EP18184486.1A| EP3432312A1|2017-07-21|2018-07-19|Method for analysing an image of a dental arch|

---

US17/391,198| US20210358124A1|2017-07-21|2021-08-02|Method for analyzing an image of a dental arch|