KR20230030109A - Automatic determination system for position abnormality of teeth through 3d scan data of teeth - Google Patents

Abstract

Provided is a technology which efficiently analyzes a patient's dental data to extract a result of automatically performing orthodontic diagnosis for each tooth, and trains a derivation algorithm through machine learning through sample data and the like to automatically perform diagnosis, the basis of treatment in orthodontic dentistry. According to one embodiment of the present invention, a system for automatically determining abnormal positions of teeth through a Three-dimensional (3D) scan image of teeth comprises: a tooth image processing unit applying a tooth image from a 3D tooth scan image generated by scanning an area including at least the teeth of a patient to a tooth image processing algorithm to generate tooth data for determining abnormal positions; an abnormal position classification unit applying the relative arrangement state of the tooth objects included in the dental data generated by the dental image processing unit to an automatic diagnosis algorithm to automatically classify a plurality of abnormal positions including at least a form of malocclusion; and a correction data generation unit combining each tooth image, each tooth data, identification information of each tooth, and classification result with respect to the abnormal position for each tooth according to a classification result of the abnormal position classification unit to generate oral condition information before treatment of the patient.

Description

Automatic determination system for position abnormalities of teeth through 3D dental scan images of teeth

The present invention relates to an automatic detection technology for an abnormal position of a tooth through a 3D tooth scan image of the tooth, and specifically, by processing an image of a tooth extracted from a secondary 3D tooth scan image, each tooth It relates to a technology for automatically determining the positional anomaly of each tooth necessary for establishing an orthodontic treatment plan and providing data for this by using the relationship of axes along with accurate relative coordinates and direction values for each.

Thanks to the development of artificial intelligence (AI), machine learning and deep learning technologies for image processing, various attempts are being made through the development of image processing technology. In particular, in the medical field, attempts have been made to utilize various image data that can be acquired from patients for diagnosis and treatment.

Among them, in the field of orthodontics, based on the acquisition result of the patient's three-dimensional tooth scan image, various orthodontic techniques are used according to the doctor's know-how, and a treatment that evens the patient's teeth is applied.

In the field of orthodontics, various attempts have been made to extract meaningful data for orthodontics and use them for orthodontic treatment using the above-described image processing technology. However, in the method of using image processing in the field of orthodontic dentistry, the field of application is limited to the extent to which dentists use 3D tooth scan images, and in the end, accurate orthodontic treatment is possible only when dentists acquire know-how through years of training. And, accordingly, there has been a problem that the orthodontic effect is derived very differently for each dentist.

In order to solve this problem, Korean Patent Publication No. 2016-0004862, etc., simulates orthodontic treatment by reflecting the results of a doctor's examination and diagnosis in real time after performing tooth modeling based on a 3D head image. We provide the technology that makes the operation possible.

However, in the orthodontic field technology using artificial intelligence technology for image processing in the prior art, it is nothing more than a technology that implements the degree of measurement points of a tooth by artificial intelligence or separates a tooth from a 3D tooth scan image, and eventually a doctor for diagnosis, etc. Since the opinion of is essential, as described above, in the case of a dentist without know-how, the diagnosis may not be performed properly, and there is a problem that can greatly affect the quality of treatment for the patient by the result.

Accordingly, the present invention efficiently analyzes patient's tooth data in the field of orthodontic dentistry using artificial intelligence image processing to derive the result of automatically performing diagnosis in the field of orthodontics for each tooth, thereby enabling such a model To provide a technology that can automatically perform a diagnosis, which is the basis of treatment in orthodontics, based on a 3-dimensional dental scan image through the construction and learning of a model by machine learning, specifically deep learning. There is a purpose.

In order to achieve the above object, a system for automatically determining a location abnormality of a tooth through a 3D tooth scan image of a tooth according to an embodiment of the present invention scans a region including at least the tooth of a person to be tested, and scans the 3D tooth. a tooth image processing unit generating tooth data for position abnormality determination by applying a tooth image from the scanned image to a tooth image processing algorithm; a positional anomaly classification unit that automatically classifies a plurality of positional anomalies including at least a form of malocclusion by applying the relative arrangement state of tooth objects included in the tooth data generated by the tooth image processing unit to an automatic diagnosis algorithm; And according to the classification result of the positional abnormality classification unit, each tooth image, each tooth data, identification information of each tooth, and the classification result of each tooth's positional abnormality are combined to create orthodontic data that is generated as oral condition information before treatment of the examinee. It is characterized in that it includes; part.

The tooth image processing unit gradually increases the size of a circle from the center of the simple coordinates of the 3D tooth scan image to search for the first point where the circle and the object included in the image touch, and puts a predetermined distance from the search point to a sphere. After scattering to be located in the tooth, invert the mesh direction expressed, and move at random speed in the circumferential direction based on a number of spheres in the reference coordinates, replicating the spheres at predetermined intervals, and placing the spheres evenly inside the tooth After setting the representative sphere of each tooth by growing the size of the replicated sphere to a predetermined size, extracting feature data for the coordinates and contact points of the teeth by setting the coordinates and contact point of the representative sphere to each representative sphere. And, based on the mesh information of the tooth image, it is preferable to generate tooth data of each tooth by deriving a tooth axis and processing the tooth image.

The tooth image processing unit may generate data capable of realizing an arrangement of the teeth of a person to be examined in a three-dimensional manner as the tooth data by applying coordinates and contact points of the teeth and axis data of the teeth to each tooth image.

The tooth image processing unit, using the center of volume and the center of width of the three-dimensional data for each tooth derived using the tooth data, a line passing through the center of volume and the center of width and a result of tooth image processing derived through statistical analysis It is possible to set a line obtained by correcting a penetrating line using a numerical correction value as an axis of the tooth.

Based on the position abnormality classification unit, based on the size and relative arrangement of the teeth, if the contact points between the teeth do not meet each other and intersect, it is a totality, if there is a space between the contact points between the teeth, it is a gap, and if the teeth are rotated with each other By rotation, if the vertical relationship of the tooth does not match the preset first value, in the vertical relationship, if the mesiodistal tooth axis inclination slope of the tooth does not match the preset second value, by the mesiodistal tooth axis inclination, the buccal-lingual tooth axis of the tooth It is possible to determine each malocclusion by the buccal-lingual tooth tilt when the inclination description does not match the preset third value, and by the fit if the cusp of the maxillary tooth is not located between two mandibular teeth.

The positional anomaly classification unit may determine the degree of detail based on the size of a numerical value that is a basis for determining each malocclusion, and may set the malocclusion classification information together.

Preferably, the correction data generation unit generates data obtained by converting mesh data of a tooth image derived from a 3D tooth scan image into an object format that can be simulated in a first program together with the oral condition information before treatment.

According to the present invention, information on the relative coordinates of each tooth, the contact point between teeth, and the axis of the teeth is obtained through modeling and analysis of the derived tooth image as well as derivation of the tooth image by processing the 3D tooth scan image. to extract tooth data. Through this, the tooth data of each tooth is compared and analyzed, various diagnosis results corresponding to malocclusion requiring orthodontic treatment are classified, and oral condition information before treatment, which is the patient's medical data, is automatically generated and provided to medical institutions. do.

Through this, compared to existing technologies, it not only extracts tooth data capable of treatment simulation based on the 3D dental scan image, but also automatically learns through the diagnosis result of a skilled doctor based on the extracted tooth data. By applying a classification algorithm for diagnosis results, there is an effect of generating oral condition information before treatment so that a specialized treatment plan can be established regardless of the dentist's skill level.

Through this, there is an effect that can induce an average increase in the quality of treatment in the field of orthodontics.

1 is a configuration block diagram of a system for automatically determining position abnormality of a tooth through a three-dimensional tooth portion scan image of a tooth according to an embodiment of the present invention.
Figure 2 is a view for explaining the flow of generating oral condition information before treatment according to an embodiment of the present invention.
3 is a view for explaining a flow in which representative coordinates and contact points of teeth for generating tooth data are extracted according to an embodiment of the present invention.
4 is a view for explaining a flow in which information about the axis of a tooth is extracted according to an embodiment of the present invention.
5 (a) to (g) are views for explaining an example in which a positional abnormality of a tooth is classified based on tooth data according to an embodiment of the present invention.
6 is an example of an internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are disclosed with reference now to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth in order to facilitate a general understanding of one or more aspects. However, it will also be appreciated by those skilled in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings describe in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in principle of the various aspects may be used, and the described descriptions are intended to include all such aspects and their equivalents.

References to “embodiment,” “example,” “aspect,” “example,” etc., used in this specification should not be construed as indicating that any aspect or design described is preferable to or advantageous over other aspects or designs. .

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. It should be understood that it does not.

In addition, terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are those commonly understood by those of ordinary skill in the art to which the present invention belongs. have the same meaning. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the embodiments of the present invention, an ideal or excessively formal meaning not be interpreted as

1 is a configuration block diagram of a system for automatically determining an abnormal position of a tooth through a three-dimensional dental scan image of a tooth according to an embodiment of the present invention, and FIG. 2 is oral condition information before treatment according to an embodiment of the present invention. Figure 3 is a view for explaining the flow of generating, Figure 3 is a view for explaining the flow of extracting representative coordinates and contacts of teeth for tooth data generation according to an embodiment of the present invention, Figure 4 is one of the present invention Figures 5 (a) to (g) are diagrams for explaining the flow of extracting information about the axis of a tooth according to the implementation of the embodiment, and FIGS. It is a drawing for explaining an example of being classified. In the following description, one or more drawings will be simultaneously referred to and described for a detailed description of each embodiment and detailed components of the present invention.

First, referring to FIG. 1 , a system for automatically determining position abnormality of a tooth through a three-dimensional tooth scan image of a tooth according to an embodiment of the present invention (10, hereinafter referred to as 'the system of the present invention') includes a tooth image processing unit. (!1), characterized in that it includes a position anomaly classifying unit 12 and a calibration data generating unit 13. Meanwhile, the input data of the system 10 of the present invention is input from the database 20, and the output data is also shown as being stored in the database 20.

In the present invention, the database 20 manages both the three-dimensional dental scan image described later and oral condition information before treatment, and accordingly, through machine learning such as deep learning using the data stored in the database 20, Automatic generation of treatment plans using oral condition information, generation of oral condition information before treatment through tooth images, and generation and learning of various artificial intelligence algorithms for generating tooth images from 3D dental scan images are performed. Through this, the functions of each component of the present invention can be performed.

On the other hand, the system 10 of the present invention can be understood as the same device as the computing device of FIG. 6 to be described later. In this case, the system 10 is configured to be included in one computing device, or the system 10 of the present invention Each configuration may be configured to include one or more computing devices.

The tooth image processing unit 11 performs a function of generating tooth data for determining a positional abnormality by applying a tooth image to a tooth image processing algorithm from a three-dimensional tooth portion scan image obtained by scanning at least an area including the teeth of a subject to be examined. am.

In the present invention, the 3D tooth scan image is data configured in the form of a 3D tooth scan image obtained from a head scan device of a subject in the field of dentistry, such as an stl object. The Stl file format is the de facto standard data transfer format in the high-speed prototyping industry. In the present invention, in addition to the stl file format described above, a format of a 3D tooth scan image that can be obtained through a 3D scanner in various types of dentistry may be used.

The tooth image processing algorithm obtains a tooth image from a 3D tooth scan image obtained by scanning the head of a subject, and determines the location abnormality of the tooth, such as coordinates of the tooth, contact point between the teeth, and axis data of the tooth. It means an algorithm having the above-described three-dimensional tooth portion scan image or separated tooth image as an input value and tooth data as an output value in order to generate tooth data for the purpose of generating tooth data.

The tooth image processing algorithm may be learned using a 3D tooth scan image or separated tooth image as a plurality of sample data and tooth data extracted by an expert's judgment or diagnosis of the corresponding image.

In the present invention, the tooth image processing algorithm can be learned, for example, by various learning techniques included in machine learning, and is included in deep learning neural networks (Deep Learning NN) or machine learning techniques for learning various known artificial intelligence algorithms can be learned by

Specifically, an embodiment of extracting data for determining an abnormal position of a tooth may be applied in a method as shown in FIGS. 3 and 4 .

For example, as shown in FIG. 3, the tooth image processing unit 11 places a circle at the center of the simple coordinates 201 of the three-dimensional tooth scan image (S1) and then gradually increases the size of the circle so that the circle and the image The first point 211 reached by the object included in is searched for (S2).

In other words, it is a process of deriving a central circle. The point in the first circle 211 where the circle and the object meet while gradually increasing the size of the circle in the simple coordinate center 201 of the 3D tooth scan image such as the input stl object. It is searched, it is determined that the object is located at the corresponding point, and the microspheres 221 are scattered at regular intervals at the corresponding point, so that they are located inside each tooth.

On the other hand, in a 3D tooth scan image such as an stl file format, the surface of a three-dimensional object is represented by many triangular faces in 3D, as described above. Therefore, when using the input 3D tooth scan image, the surface and A collision event can be easily detected, but an event escaping from the inside of the tooth to the outside cannot be detected. Since the circle must be located in the tooth and prevented from escaping in the process described later, according to the present invention, the tooth image processing unit 11 regenerates the triangle data of the model in the reverse direction to prevent the phenomenon, that is, the 3D tooth scan. Data UT obtained by inverting the mesh of the image T is generated (S3, S4).

Thereafter, in order to evenly fill the teeth with spheres, the spheres are evenly formed inside the teeth by repeating the process of duplicating the spheres 221 (S5) while moving at a random speed in the peripheral direction based on the plurality of spheres generated at the reference coordinates. allow it to be placed.

Thereafter, in step S6, the size of the replicated spheres is gradually increased in the process of creating a plurality of sphere dispersion (S5). In this process, space is insufficient and most of the spheres come out of the tooth, and after increasing the spheres to a sufficient size (1 unit to 5 units), the size of the spheres is reduced to below a certain level, that is, below the above-mentioned size. Then, representative spheres are evenly distributed on each tooth.

In this way, for example, spheres 231 corresponding to each of the 14 lower and upper teeth are generated. Then, when the coordinates represented by the spheres 231 are derived, the representative coordinates of each tooth are derived, and the spheres 231 The contact point between the teeth is derived through the contact point of . In this way, the above-described coordinates of the tooth and feature data of the contact point are extracted.

In the above-described embodiment, the tooth image is obtained by separating the image of the object corresponding to the tooth from the 3D tooth scan image as described above. In the preprocessing process, the mesh of each tooth must be separated through a tooth-specific separation operation in order to simulate a known tooth separation operation and movement of each tooth and obtain information on each tooth.

To this end, images of each individual tooth are derived through a mesh separation program based on the SplitDisjointMesh function in programs such as the Rhino 3D work tool.

Based on the mesh information for each tooth of the tooth image, the tooth image is processed by deriving the axis of the tooth to generate tooth data of each tooth, that is, data including the above-described feature data and the derived axis of the tooth.

Meanwhile, for the axis of the tooth, a process of deriving the axis is performed as in the example of FIG. 4 .

For example, the tooth image processing unit 11 processes the mesh information (T) for all teeth as described above to learn about individual teeth, and from the three-dimensional data for each tooth, that is, the mesh information (ET), the volume center point (VC) ) and the area center point (AC) are automatically derived. The volume center point (VC) is the center point of the volume of each tooth data, and the width center point (AC) means, for example, the area center point of the part having the largest area of the tooth or the center point of the surface corresponding to the uppermost surface.

At this time, a line passing through the central point of volume (VC) and the central point of area (AC) is primarily selected as the axis of the corresponding tooth. On the other hand, according to the above-described tooth image processing algorithm, the above-described tooth data, for example, an error correction function for the above-described tooth axis is derived through statistical analysis of the tooth image processing result. Using the numerical correction value derived accordingly, when the penetrating line is corrected, the corrected line is set as the axis A of the tooth.

Through this, through machine learning for the three-dimensional data of the tooth, that is, the shape/movie characteristics of the model and statistical analysis, an axis parallel to the root of the tooth is automatically derived and used as tooth data, while treatment using this It can be used for simulation for planning.

Meanwhile, as described above, the mesh data of individual teeth may be converted into an obj format that can be used in simulation such as Unity. The tooth data described above may be combined with this obj format. In this case, when implementing the rhino 3D modeling tool automation program using a program such as Python, it is possible to respond to the automation service by automating all processes using the tool as a script.

That is, through this format conversion, by applying tooth coordinates, contact points, and axis data of teeth to each tooth image, data that can implement a three-dimensional arrangement of the teeth of a subject to be examined is generated as the above-described tooth data so that it can be used for subsequent processing. is to do Such image format conversion may be performed by a correction data generating unit 13 to be described later.

The positional anomaly classification unit 12 automatically detects a plurality of positional anomalies, including at least the form of malocclusion, by applying the relative arrangement state of tooth objects included in the tooth data generated by the tooth image processing unit 11 to an automatic diagnosis algorithm. performs the classification function.

The relative arrangement state of the tooth object means a relative state with respect to the arrangement of the upper, lower, left, and right teeth. This can be derived by comparing tooth data for teeth adjacent to each other based on the above-described tooth data, that is, information on coordinates, contact points, and axes of each tooth.

The automatic diagnosis algorithm can be learned by the above-described machine learning, and the specific comparison process is as described later, that is, the automatic diagnosis algorithm is learned in automatically discriminating abnormalities in the position of teeth according to the specific comparison process described later. It can be understood as meaning that a comparison reference value used in the corresponding comparison process is learned, or that a specific comparison process itself is learned.

An example of this is described in detail in FIG. 5 . First, (a) of FIG. 5 means an abnormality classification (A) corresponding to crowding. Total growth means a case where the mesial-distal contact points of adjacent teeth overlap each other, and first, it is determined based on whether the teeth are arranged overlapping each other, that is, whether the contact points between teeth do not meet each other and intersect.

If the corresponding judgment result is No, if the contact points meet each other and the arrangement is normal, it is judged as a normal arrangement. The result of the special judgment instruction can be used for learning the automatic diagnosis algorithm described above. On the other hand, if there is a space without overlapping, it proceeds to the void evaluation described later, and if not, it is also classified as a special situation.

On the other hand, if the result of the determination is Yes, the relative degree of total growth is determined based on the overlapping degree. That is, if the degree of overlapping each other is, for example, -2 mm or less, it is judged as degree 1, -2 to -4 mm, degree 2, and -4 mm or more, it is judged as degree 3.

On the other hand, (b) of FIG. 5 means an abnormality classification (B) corresponding to the above-described void (Spacing). The gap means a case where the mesial-distal contact points of adjacent teeth are separated from each other and there is a space between the teeth. First, it is determined whether the teeth are arranged apart from each other, that is, whether there is a space between the contact points between the teeth without overlapping each other.

If the corresponding determination result is No, if the contact points meet each other and the arrangement is normal, the normal arrangement is performed, and if there is no space and overlapping, the above-mentioned totality evaluation is performed. On the other hand, if the contact points meet each other but the arrangement is not normal, or if there is no space and does not overlap, it is also classified as a special situation as described above.

On the other hand, if the result of the determination is Yes, the relative air gap is also determined based on the width of the spaces apart from each other. When the degree of width of the space is, for example, 2 mm or less, it is judged as degree 1, degree 2 when it is 2 to 4 mm, and grade 3 when it is 4 mm or more.

(c) of FIG. 5 means an abnormality classification (C) corresponding to rotation. Rotation refers to a case in which the tooth is determined to be rotated when the mesiodistal contact points of the tooth deviate from the normal arrangement line. In this case, it is determined based on the corresponding array line to determine whether the teeth are rotated.

If the result of the judgment is No, if the contact contacts meet each other and the arrangement is normal, it is judged as normal arrangement. complex classification. If the judgment result is No, but the arrangement is not normal or does not show a complex aspect, it is also classified as a special situation and a special judgment instruction is requested.

When the corresponding determination result is Yes, the degree of rotation is determined according to the relative degree of rotation of the teeth. For example, if it is 4 degrees or less, it is judged as precision 1 degree, if it is 4 to 8 degrees, it is judged as precision 2 degrees, and if it is more than 8 degrees, it is judged as precision 3 degrees.

(d) of FIG. 5 means an anomaly classification (D) corresponding to a vertical relationship (openbite & deepbite). The vertical relationship is an evaluation of the degree of overbite of the upper and lower teeth, and all upper teeth must cover the lower teeth. If this relationship is out of alignment, it is classified as an abnormal classification (D) corresponding to the vertical relationship, and a predetermined first value is set as a normal value to match the characteristics of each tooth. The corresponding first value may also be set by learning through the above-described sample data.

In the classification process, it is determined whether the teeth correspond to normal values or fall within the range of normal values to match the characteristics of each tooth described above. If the determination result is Yes, if the vertical cover is normal compared to the reference value, it is determined as a normal state, but if not, it is classified as a special situation as described above and a special judgment instruction is requested.

If the determination result is No, it is determined whether the standard value evacuation vertical cover is insufficient, and if insufficient, depending on the degree of deficiency, for example, in the case of 0 mm or less, the degree of deficiency is 1, in the case of 0 to -3 mm, the degree of deficiency is 2, -3 mm or more In this case, the degree of deficiency is judged as 3. If the vertical cover is not insufficient and excessive, it is judged as excessive degree 1 if it is 2 mm or less than the standard value, excessive degree 2 if it is 2 mm to 4 mm, and excessive degree 3 if it is more than 4 mm.

(e) of FIG. 5 means an abnormality classification (E) corresponding to mesiodistal tooth tipping. The mesiodistal alveolar inclination refers to a classification of a state in which the inclination of each tooth in the mesiodistal plane is excessively inclined mesial or excessively inclined distal.

In this process, first, it is determined whether the inclination of the mesial-distal tooth axis of each tooth coincides with a given second predetermined value. This second value may also be set for each tooth by algorithm learning through the above-described sample data.

If the corresponding judgment result is Yes and the axis inclination is within 2 degrees or normal, it is judged to be normal. Otherwise, it is classified as a special situation and special judgment instructions are requested.

On the other hand, if the corresponding determination result is No, it is determined whether the excessive inclination direction is mesial, and if it is not mesial and the direction is not centrifugal, it is classified as a special situation and a special judgment instruction is requested. On the other hand, if the slope is 4 degrees or less, it is determined as 1 degree of angst, 4 to 8 degrees, 2 degrees of angst, and 8 degrees or more, 3 degrees of angst.

In the case of centrifugal, depending on the degree of inclination, it is determined that the centrifugal degree is 1 degree when the inclination is less than -4 degrees, the centrifugal degree is 2 degrees when the inclination is between -4 and -8 degrees, and the centrifugal degree is 3 degrees when it is more than -8 degrees.

(f) of FIG. 5 means an abnormality classification (F) corresponding to the torque of the buccal-lingual axis. The bucco-lingual tooth inclination refers to a classification for determining whether the degree of inclination of a tooth on the bucco-lingual side of each tooth is a buccal excessive tilt or a lingual excessive tilt. First, in the corresponding process, it is determined whether the inclination of the inclination of the buccal-lingual tooth axis of each tooth coincides with a given third value. This third value may be set to a value different from the above-described mesial-distal tooth axis inclination, set for each tooth, or set by algorithm learning through sample data.

If the corresponding judgment result is Yes, if the axis inclination is within 2 degrees or normal, it is judged as a normal state, and if not, it is classified as a special situation and a special judgment instruction is requested.

On the other hand, if the corresponding determination result is No, it is determined whether the excessive inclination direction is buccal, and if it is not buccal and the direction is not lingual, it is classified as a special situation and a special determination instruction is requested. On the other hand, if it is buccal, if the degree of inclination is 4 degrees or less, the buccal degree is 1 degree, if it is 4 to 8 degrees, it is judged as 2 degrees, and if it is more than 8 degrees, it is judged as 3 degrees.

In the case of lingual, depending on the degree of inclination, it is determined that the lingual degree is 1 degree if the slope is less than -4 degrees, the lingual degree is 2 degrees if it is -4 degrees to -8 degrees, and the lingual degree is 3 degrees if it is more than -8 degrees.

(g) of FIG. 5 means an abnormality classification (G) corresponding to fitting. Mating means a classification determined by evaluating the occlusion state between the upper and lower teeth. As a 1:2 relationship between teeth, it is judged based on whether or not the state of meshing with each other like teeth is normal, and it is evaluated based on whether the cusps of the upper teeth are located in the cusps of the lower teeth.

In the case of the anterior (proximal) position, - is marked, and in the case of the posterior (distal) position, + is marked to perform the classification. First, in the process, it is determined whether the cusps of the upper teeth are located between two lower teeth when the upper and lower teeth of the posterior teeth should be arranged like sawtooth in the anterior-posterior (proximal-distal) plane.

If the result of the judgment is Yes, and if the fit of the upper and lower posterior teeth is normal, it is determined as a normal state, and if not, it is classified as a special situation and a special judgment instruction is requested.

If the judgment result is No, it is determined whether the maxillary teeth are positioned forward, and if the maxillary teeth are positioned forward, if the degree of deviation is 2 mm or less, the degree of backward position of the mandible is 1 degree, 2 mm to 4 mm , it is judged as 2 degrees of mandibular posterior position, and 3 degrees of mandibular posterior position if it is 4 mm or more. On the other hand, when the maxillary teeth are tilted backward, based on the degree of tilt, -2mm or less, the mandibular anterior position is 1 degree, -2mm to -4mm, the mandibular anterior position is 2 degrees, and -4mm or more, the mandibular anterior position judged on a scale of 3.

In this way, the grounds for judgment of malocclusion are classified into 7 categories, and each standard value described above is learned through sample data learning and actual case learning, or an algorithm through special judgment instructions by medical staff in special situations. When learning, it is possible to make a very accurate judgment according to the basis of judgment of malocclusion, and there is an effect of enabling an efficient and clear treatment solution to be established in the subsequent diagnosis.

In addition, as described above, the location anomaly classifying unit 12 may determine the degree of detail based on the size of a numerical value that is the basis for determining each malocclusion and set it together in the malocclusion classification information as described above.

The correction data generation unit 13 uses the classification result of the position abnormality classification unit 12 and the tooth data generated by the tooth image processing unit 11 for each tooth image, each tooth data, each tooth identification information and It performs a function of combining classification results for position abnormalities for each tooth, generating oral condition information of the subject before treatment, and storing it in the database 20 .

According to the above-described function execution, the oral condition information of the subject before treatment is, for example, a tooth image as independent mesh information of each tooth, tooth data including feature data and axes, identification information for each tooth, and positions classified for each tooth. Includes classification results for Corresponding data will be stored, for example, in the database 20, and through this, it can be used for automatic treatment simulation using AI or establishment of a treatment plan.

On the other hand, as described above, in order to be able to use the oral condition information before the treatment in automatic treatment simulation or treatment plan establishment, it is necessary to be able to move by orthodontics for each tooth, so as described above, for example, Unity It can be converted to obj format that can be used in simulation. The tooth data described above may be combined with this obj format.

That is, when the data is converted into the above-described format by the calibration data generation unit 13, when implementing the rhino 3D modeling tool automation program using a program such as Python, all processes using the tool are automated with scripts. to respond to automated services.

Through this format conversion, by applying the coordinates and contact points of the teeth and the axis data of the teeth to each tooth image, data that can implement the test subject's tooth arrangement in 3D is generated as the above-described tooth data and used for subsequent processing will be.

6 illustrates an example of an internal configuration of a computing device according to an embodiment of the present invention, and in the following description, descriptions of unnecessary embodiments overlapping with those of FIGS. 1 to 5 will be omitted. do it with

As shown in FIG. 6, a computing device 10000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( It may include at least an I/O subsystem (11400), a power circuit (11500), and a communication circuit (11600). In this case, the computing device 10000 may correspond to a user terminal connected to the tactile interface device (A) or the aforementioned computing device (B).

The memory 11200 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. there is. The memory 11200 may include a software module, a command set, or other various data necessary for the operation of the computing device 10000.

In this case, access to the memory 11200 from other components, such as the processor 11100 or the peripheral device interface 11300, may be controlled by the processor 11100.

Peripheral interface 11300 may couple input and/or output peripherals of computing device 10000 to processor 11100 and memory 11200 . The processor 11100 may execute various functions for the computing device 10000 and process data by executing software modules or command sets stored in the memory 11200 .

Input/output subsystem 11400 can couple various input/output peripherals to peripheral interface 11300. For example, the input/output subsystem 11400 may include a controller for coupling a peripheral device such as a monitor, keyboard, mouse, printer, or touch screen or sensor to the peripheral interface 11300 as needed. According to another aspect, input/output peripherals may be coupled to the peripheral interface 11300 without going through the input/output subsystem 11400.

The power circuit 11500 may supply power to all or some of the terminal's components. For example, power circuit 11500 may include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator or power It may contain any other components for creation, management and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, the communication circuit 11600 may include an RF circuit and transmit/receive an RF signal, also known as an electromagnetic signal, to enable communication with another computing device.

The embodiment of FIG. 6 is only an example of the computing device 10000, and the computing device 11000 may omit some components shown in FIG. 6, further include additional components not shown in FIG. 6, or 2 It may have a configuration or arrangement combining two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 10000 may be implemented as hardware including one or more signal processing or application-specific integrated circuits, software, or a combination of both hardware and software.

Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in computer readable media. In particular, the program according to the present embodiment may be configured as a PC-based program or a mobile terminal-only application. An application to which the present invention is applied may be installed in a user terminal through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of a user terminal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or to provide instructions or data to a processing device. may be permanently or temporarily embodied in Software may be distributed on networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved. Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (7)

It relates to a system for automatically determining position abnormality of a tooth through a three-dimensional tooth scan image of a tooth implemented by a computing device including one or more processors and one or more memories for storing commands executable by the processor,
a tooth image processing unit for generating tooth data for determining a position abnormality by applying a tooth image to a tooth image processing algorithm from a three-dimensional tooth portion scan image obtained by scanning an area including at least the teeth of a subject to be examined;
a positional abnormality classification unit that automatically classifies a plurality of positional abnormalities including at least a form of malocclusion by applying the relative arrangement state of tooth objects included in the tooth data generated by the tooth image processing unit to an automatic diagnosis algorithm; and
Orthodontic data generation unit for combining each tooth image, each tooth data, each tooth identification information, and the classification result for each tooth positional abnormality according to the classification result of the positional anomaly classification unit and generating oral condition information before treatment of the subject A system for automatically determining position abnormality of a tooth through a three-dimensional tooth portion scan image of a tooth, characterized in that it comprises:
According to claim 1,
The tooth image processing unit,
Search for the first point where the circle and the object included in the image touch by gradually increasing the size of the circle at the center of the simple coordinates of the 3D tooth scan image, and scatter spheres at predetermined intervals from the search point to locate them in the tooth After doing so, the expressed mesh direction is reversed, and the spheres are copied at predetermined intervals while moving at a random speed in the peripheral direction based on a plurality of spheres at the reference coordinates so that the spheres are evenly placed inside the tooth, and then the replicated spheres are After setting the representative sphere of each tooth by growing the size of the sphere to a predetermined size, extracting feature data for the coordinates and contact points of the teeth by setting the coordinates and contact points of the representative sphere to each representative sphere, and Based on the mesh information for the tooth, the axis of the tooth is derived and the tooth image is processed to generate tooth data of each tooth.
According to claim 2,
The tooth image processing unit,
A tooth through a three-dimensional tooth scan image of a tooth, characterized in that by applying the coordinates and contact points of the tooth and the axis data of the tooth to each tooth image, data capable of realizing the arrangement of the teeth of the examinee in three dimensions is generated as the tooth data. position abnormality automatic determination system.
According to claim 2,
The tooth image processing unit,
Using the center of volume and center of width of the three-dimensional data for each tooth derived using the tooth data, a line passing through the center of volume and the center of width and a numerical correction value derived through statistical analysis of the tooth image processing result An automatic tooth position abnormality detection system through a three-dimensional tooth scan image of the tooth, characterized in that the line corrected by the penetrating line is set as the axis of the tooth.
According to claim 4,
The location abnormality classification unit,
Based on the size and relative arrangement of the teeth, if the contact points between the teeth do not meet each other and intersect, it is a cyst, if there is a space between the contact points between the teeth, it is a gap, if the teeth are rotated with each other, it is a rotation, and the vertical direction of the teeth Vertical relationship if the relationship does not match the preset first value, mesial distal tooth axis slope if the mesiodistal tooth slope slope of the tooth does not match the preset second value, and buccal-lingual tooth axis slope descriptor of the tooth equals the preset value 3 If the numerical value does not match, each malocclusion is determined by the buccal lingual axial tilt, and if the cusp of the upper jaw is not located between the two lower teeth, by mating. position abnormality automatic determination system.
According to claim 5,
The location abnormality classification unit,
An automatic tooth position abnormality detection system through a three-dimensional dental scan image of the teeth, characterized in that the degree of detail is determined based on the size of the numerical value that is the basis for the judgment of each malocclusion and set together in the malocclusion classification information.
According to claim 1,
The calibration data generating unit,
The three-dimensional tooth scan image of the tooth, characterized in that the data obtained by converting the mesh data of the tooth image derived from the three-dimensional tooth scan image into an object format that can be simulated in a first program is generated together with the oral condition information before the treatment. An automatic tooth position abnormality detection system through

Images