Dental Monitoring

Guillaume Ghyselinck

Philippe Salah

Thomas Pellissard

Laurent Debraux

William Ayache

Louis Charles Roisin

Laura Misrachi

Thomas Pelissard

A method for analyzing an image, called 'analysis image', of a dental arch of a patient. The method in which the analysis image is submitted to a neural network, in order to determine at least one value of an image attribute relating to the analysis image. The analysis image is a photograph or an image taken from a film. The image attribute relates to a position or an orientation or a calibration of an acquisition apparatus used to acquire the analysis image or a combination thereof, 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, or a combination thereof.

Method for analyzing an image of a dental arch

Imaging device to acquire dental image having a support. The device includes a rigid portion on which an acquisition apparatus is to be fastened and a deformable portion defining a retractor opening. Associated method to manufacture a support of an imaging device to acquire dental image. The method includes manufacturing of a precursor of the support, in a first place, and providing the precursor to an operator, in a second place away from the first place. The distance between the first place and the second place is preferably greater than 1 km and/or less than 20 000 km. The method includes transformation of the precursor into the support.

Dental imaging device

A method for assessing the shape of an orthodontic aligner, said method comprising the following steps:

A simulating method. The method includes acquiring an image of a dental arch of a patient, called the 'original image.' The method includes subjecting the original image to a neural network, called the “modification neural network”, trained to locally modify the original image in order to obtain a “modified image.” The method includes presenting the modified image to the patient.

Method for simulating a dental situation

A system for manufacturing an orthodontic appliance. A scanner for creating a numerical three-dimensional initial reference model of at least a part of a patient's arch including one or more teeth. An image acquisition device for acquiring at least one two-dimensional updated image of the arch. The image acquisition device is positioned and oriented in space, relative to the teeth, under actual acquisition conditions. A computer for creating a numerical three-dimensional objective reference model, corresponding to a desired positioning, at a time point of a treatment, of the teeth, and deforming the initial reference model by moving one or more teeth of the initial reference model, to obtain an updated reference model corresponding to the positioning of the teeth on the two-dimensional updated image. A device for manufacturing an orthodontic appliance, based on a comparison, executed by the computer, between the updated reference model and the objective reference model.

Dentition control method

A method for modeling a dental arch of a patient. Creation of a historical library including more than 1000 historical tooth models, and assignment, to each historical tooth model, of a value for at least one tooth attribute value. Analysis of at least one analysis image of the dental arch by means of a deep learning device so as to determine at least one analysis tooth zone and at least one tooth attribute value. For each analysis tooth zone determined in the preceding step, search, in the historical library, for a historical tooth model exhibiting a maximal proximity with the analysis image. Arrangement of all of the optimal tooth models so as to create an assembled model which exhibits a maximal proximity Some optionally steps are possible.

A device including a camera, a processing unit and a screen. The camera configured to, at an updated instant, acquire, by a cellphone or a tablet, an updated image representing a real dental scene. The processing unit configured to determine a virtual dental scene as a representation of the real scene on the updated image and identify an element of the virtual scene which does not comply with an assessment criterion, and highlighting and/or adding a message regarding this element in the virtual scene. The screen configured to display the updated image and present the virtual scene overlaid with the representation of the real scene on the updated image displayed on the screen, in transparent mode or not on the representation. The processing unit, the camera and the screen are configured to communicate with one another. The patient acquires the updated image and observes the screen.

Method for analysing a dental situation

A method for monitoring the positioning of the teeth including production of a three-dimensional digital initial reference model of the arches of the patient and, for each tooth, definition, from the initial reference model, of a three-dimensional digital reference tooth model; acquisition of updated image of at least one two-dimensional image of the arches in actual acquisition conditions; analysis of each updated image and production, for each updated image, of an updated map; optionally, determination, for each updated image, of rough virtual acquisition conditions approximating the actual acquisition conditions; searching, for each updated image, for a final reference model corresponding to the positioning of the teeth during the acquisition of the updated image, for each tooth model, comparison of the positionings of the tooth model in the initial reference model and in the reference model obtained at the end of the preceding steps to determine the movement of the teeth.

Method for monitoring an orthodontic treatment

A method for evaluating, by computer, at an 'updated' time, the conformity of an orthodontic aligner with a dental arch of a patient, referred to as the “support arch.” The method includes the following successive steps: A) producing a digital three-dimensional model of the support arch in its configuration at the updated time, or an “updated reference model”, and determining from the updated reference model, a support surface for the aligner; B) deforming the support surface on the basis of the geometry of the aligner in order to obtain a deformed support surface; C) comparing an external surface of the aligner with the deformed support surface, then determining, on the basis of the comparison, at least one score for the conformity of the aligner with the support arch.

Method for evaluating an orthodontic aligner

A method for enriching a historical learning base. Training of a first neural network to transform first photos of first dental scenes into first hyper-realistic images to simulate the effect of a dental event on the first dental scenes. Submission, to the trained first neural network, of a source photo representing a source dental scene in a dental context, so as to obtain a final image representing, hyper-realistically, the source dental scene after simulation of the dental event. Creation of a descriptor of the final image, or 'final descriptor.' Creation of a historical record consisting of the final image and the final descriptor, and addition of the historical record in the historical learning base.

Method for enriching a learning base

A method for evaluating an orthodontic appliance. Acquisition of a two-dimensional 'appliance image' of teeth at least partially representing the orthodontic appliance in a service position. Acquisition of a two-dimensional “dentition image” of the teeth. If a determination of comparable dental and appliance attributes is not possible from the appliance image and from the dentition image, respectively, conversion of the appliance image and/or of the dentition image so that the appliance image be compatible with the dentition image. Determination of dental and appliance attributes relative to the shape of the tooth represented on the dentition image and relative to the shape of the orthodontic appliance on the appliance image. Comparison of the dental and appliance attributes, followed by determination of at least one score. At least one image is acquired with a mobile phone.

Method of evaluating an orthodontic appliance

A method and associated system. Such is for orthodontic treatment or for assessing shape of an aligner. Within an example, there is participation in communication of an assessment of the suitability of an aligner as a function of the value of: a tooth attribute of an analysis tooth zone of an analysis image, the tooth attribute relating to a separation between the tooth represented by the analysis tooth zone and the aligner represented on the analysis image, or an image attribute of an analysis image, the image attribute relating to a separation between at least one tooth represented on the analysis image and the aligner represented on the analysis image. The analysis image is an image of an aligner in a service position in which it is worn by the patient acquired by a cellphone more than 1 week, and is a photograph, or an image extracted from a film.

A method for transforming an 'original' view of an “original” digital three-dimensional model into a hyper-realistic view. The method includes creating a “transformation” learning base of more than 1000 “transformation” records. Each transformation record includes a “transformation” photo representing a scene, and a view of a “transformation” digital three-dimensional model modeling the scene, or “transformation view”, the transformation view representing the scene in the same way as the transformation photo. The method includes training at least one “transformation” neural network, by way of the transformation learning base. The method includes submitting the original view to the at least one transformation neural network, such that it transforms it into a hyper-realistic view.

Method for analyzing a photo of a dental arch

A method for generating a three-dimensional digital model of a dental arch of a patient. The method includes projection of at least one light beam onto the arch, so as to draw at least one light mark on the arch, and simultaneously, displacement of the arch across the beam and acquisition, during the displacement, of a series of updated images of the arch each showing an updated projection defined by the projected mark. The method includes identification of the updated projection on each updated image, then search for a three-dimensional digital model, called 'updated model', exhibiting a best fit with all the updated projections.

Growing community of inventors

Cantin, France

Guillaume Ghyselinck