Ansheng classification automatic identification method, electronic equipment and medium

Abstract

The embodiment of the invention relates to the technical field of digital design of medical instruments, and discloses an Angler classification automatic identification method, electronic equipment and a medium, the identification method comprises the following steps automatically executed by the electronic equipment: identifying characteristic parameters of characteristic teeth of upper and lower jaws of a patient from tooth data of the patient, the tooth data comprises at least part of rear teeth on the single side in an occlusion state, and the characteristic teeth belong to the part of rear teeth; according to the characteristic parameters, the relative position relation of the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal middle direction is determined; wherein the tooth data is a two-dimensional picture and / or a three-dimensional dental model; and according to the relative position relationship, determining Ansheng classification corresponding to the teeth of the patient, so that automatic identification of Ansheng classification is performed on the teeth of the patient, and doctors or professionals are helped to perform more accurate judgment.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of digital design of medical devices, and in particular to an automatic recognition method for Angle's classification, an electronic device, and a medium. Background Art

[0002] Malocclusion refers to the developmental deformities of the teeth, jaws, and face that may occur during a child's growth and development due to various factors, including genetics and the environment. (An ideal normal jaw refers to the presence of all upper and lower teeth, neatly arranged, with good cusp-to-fossa contact, normal jaw development, and good dental arch morphology), which can affect the beauty and health of the face. When orthodontists determine the corrective device for patients with malocclusion, they generally first determine the type of malocclusion and then use the corresponding corrective device. Therefore, the accuracy of the classification can significantly improve the accuracy of subsequent corrective device selection.

[0003] The Angle classification is a widely used malocclusion classification system, proposed by Dr. Angle in 1899. It primarily uses the maxillary first permanent molar as a reference point and is based on the anterior-posterior relationship between the upper and lower dental arches. Currently, this system relies primarily on the physician's judgment, which is limited by their experience and can lead to errors. These errors can lead to incorrect selection of orthodontic devices.

[0004] It can be seen that we need a more accurate and efficient method for identifying malocclusion, so as to more efficiently and accurately identify the type of malocclusion in patients and provide doctors with a more reliable reference basis. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide an automatic recognition method, electronic device and medium for Angle's classification, which can make Angle's classification more accurate and efficient, and further provide doctors or professionals with more accurate and reliable classification results.

[0006] In order to solve the above technical problems, an embodiment of the present application provides an automatic recognition method for Angle's classification, including an electronic device automatically performing the following steps: identifying characteristic parameters of the patient's upper and lower jaw characteristic teeth from the patient's dental data, the dental data including at least part of the posterior teeth on one side in the occlusal state, and the characteristic teeth belonging to the part of the posterior teeth; confirming the relative position relationship of the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal and upward directions based on the characteristic parameters; and determining the Angle's classification corresponding to the patient's teeth based on the relative position relationship.

[0007] An embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned Angle's classification automatic identification method.

[0008] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned Angle's classification automatic recognition method when executed by a processor.

[0009] The automatic Angle's classification recognition method in the embodiments of the present application uses an electronic device to automatically identify characteristic parameters of the characteristic teeth in the posterior region of the patient's upper and lower jaws from the patient's dental data. The electronic device then determines the relative positional relationship of the characteristic teeth in the mesiodistal direction of the upper and lower jaws based on the characteristic parameters. The Angle's classification corresponding to the patient's teeth is then determined based on the determined relative positional relationship. Through a series of automated steps, the electronic device can automatically identify the Angle's classification corresponding to the patient's teeth, and the classification results, which are based on the characteristic teeth in the posterior region, are accurate and highly reliable.

[0010] Additionally, the dental data is in the form of a two-dimensional photograph and / or a three-dimensional jaw model. Since tooth features can be visualized through these two-dimensional photographs and three-dimensional jaw models, limiting the dental data to these two types of photographs and / or three-dimensional jaw models allows for accurate identification of characteristic parameters, providing a highly reliable basis for subsequent determination of relative positional relationships.

[0011] In addition, the two-dimensional photograph is a side intraoral photograph. Since side intraoral photographs are routinely collected in the early stages of orthodontic treatment, limiting the use of side intraoral photographs for feature parameter identification is beneficial to reducing the amount of additional data collection, simplifying the operation on the doctor's side, and facilitating the promotion of the Angle's classification identification method in this application.

[0012] In addition, the maxillary and mandibular characteristic teeth are first molars respectively. Since the characteristic parameters corresponding to the first molars are more direct and reliable references for identifying Angle's classification, using the first molars as characteristic teeth is beneficial to the accuracy of Angle's classification identification in this application.

[0013] Furthermore, before identifying characteristic parameters of the patient's maxillary and mandibular characteristic teeth from the patient's dental data, the method includes classifying the teeth in the acquired dental data to determine the characteristic teeth. In this embodiment, the characteristic teeth are located by the tooth classification step, so that the characteristic parameters identified for the characteristic teeth are more accurate.

[0014] In addition, if the dental data is a two-dimensional photograph, classifying the teeth in the acquired dental data of the patient includes: using a pre-trained first dentition segmentation model to segment the dentition in the two-dimensional photograph to obtain individual teeth, and determining the characteristic teeth; if the dental data is a three-dimensional jaw model, classifying the teeth in the acquired dental data of the patient includes: extracting geometric features of the three-dimensional jaw model, segmenting the three-dimensional jaw model based on the geometric features, and determining the characteristic teeth. In this embodiment, corresponding tooth classification methods are defined when different types of dental data are obtained, so as to better process the dental data in the two-dimensional photograph and the three-dimensional jaw model, and to accurately locate the characteristic teeth.

[0015] In addition, the characteristic parameters are characteristic points on the occlusal surface of the characteristic teeth; and identifying the characteristic parameters of the patient's maxillary and mandibular characteristic teeth from the patient's dental data includes: determining the characteristic points on the occlusal surface of the characteristic teeth by establishing a bounding box around the characteristic teeth; or determining the characteristic points on the occlusal surface of the characteristic teeth using a trained feature point recognition model. The characteristic parameters are further limited to characteristic points on the occlusal surface, where points on the maxillary and mandibular occlusal surfaces are closer in vertical proximity, thereby enabling more accurate determination of the relative positional relationship of the maxillary and mandibular characteristic teeth in the mesiodistal direction.

[0016] In addition, the characteristic points on the occlusal surface include: buccal cusp points and / or buccal groove points. By limiting the characteristic points on the occlusal surface to buccal cusp points and / or buccal groove points, since the buccal cusp points are the most convex points of the occlusal surface and the buccal groove points are the lowest points of the buccal grooves on the buccal surface, the characteristics are more obvious, and it is easier to accurately identify during recognition, which is beneficial to the overall accuracy of the recognition method in this application.

[0017] In addition, the characteristic parameters include characteristic points on the occlusal surface of the characteristic teeth, and determining the relative positional relationship of the mandibular characteristic teeth and the mandibular characteristic teeth in the mesiodistal-upward direction based on the characteristic parameters includes: setting a reference vector based on the characteristic points of all the characteristic teeth in the upper and lower jaws, determining the relative positional relationship of each characteristic point on the reference vector; and determining the relative positional relationship of the characteristic teeth in the upper and lower jaws in the mesiodistal-upward direction based on the relative positional relationship of each characteristic point on the reference vector. Since the characteristic points on the occlusal surface of the teeth are distributed near the occlusal plane of the upper and lower jaws, the straight line fitted using these characteristic points can be approximately used as a reference line in the mesiodistal direction in the posterior tooth region.

[0018] In addition, the characteristic point is the buccal cusp. Since the buccal cusp is the most convex point of the occlusal surface, its characteristics are more obvious and it is easier to identify accurately during recognition, which is beneficial to the overall accuracy of the recognition method in this application.

[0019] Furthermore, determining the relative positional relationship of each feature point on the reference vector includes obtaining a projection point of each feature point on the reference vector, and using the relative positional relationship between the projection points as the relative positional relationship between the corresponding feature points. Since the relative positional relationship in the Angle classification is a relative positional relationship in the near, far, medial, and upward directions, determining the relative positional relationship using the projection points of the feature points on the reference vector avoids positional relationship judgment errors caused by distance differences in other directions, thereby improving the accuracy of the near, far, and medial positional relationship judgment.

[0020] Furthermore, setting a reference vector based on the characteristic points of all characteristic teeth in the upper and lower jaws includes: performing a straight line fit using each characteristic point and specifying any direction of the fitted line as the reference vector; or selecting two characteristic points that are farthest apart from each other from all characteristic points and using the direction of one of the two selected characteristic points pointing to the other as the reference vector. Furthermore, limiting the generation of the reference vector based on multiple characteristic points facilitates automatic and simple acquisition of the reference vector, improves feasibility, and increases accuracy.

[0021] In addition, the characteristic parameters include one or more of the long axis, center point, and jaw plane normal passing through the center point of the characteristic tooth. By limiting the characteristic parameters to include one or more of the long axis, center point, and jaw plane normal passing through the center point, different characteristic parameters can be flexibly combined to collaboratively determine the mesiodistal relative position relationship of the characteristic tooth, thereby improving accuracy and making the recognition method in this application more flexible and diverse, broadening its application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0023] Figure 1 This is a flow chart of an automatic identification method of Angle's classification provided according to one embodiment of the present application;

[0024] Figure 2a is a schematic diagram of a side intraoral photograph used in an automatic identification method for Angle's classification according to one embodiment of the present application;

[0025] Figure 2b is a schematic diagram showing the segmentation status of a side intraoral photograph after tooth segmentation, used in an automatic identification method for Angle's classification according to one embodiment of the present application;

[0026] Figure 31 is a schematic diagram of the relationship between the first molar and the corresponding bounding box in the automatic identification method of Angle's classification according to one embodiment of the present application;

[0027] Figure 4 is a schematic diagram of the buccal cusp positions of the upper and lower mandibular first molars in the automatic identification method of Angle's classification according to one embodiment of the present application;

[0028] Figure 5 Schematic diagram of the positional relationship between the buccal cusp positions and reference vectors of the upper and lower mandibular first molars in the automatic identification method of Angle's classification according to one embodiment of the present application;

[0029] Figure 6 Schematic diagram of the positional relationship between the buccal cusp positions and the corresponding bounding boxes of the upper and lower mandibular first molars in the automatic recognition method of Angle's classification according to one embodiment of the present application;

[0030] Figure 7a 、 Figure 7b and Figure 7c They are diagrams showing the relative positions of the buccal cusps of the upper and lower mandibular first molars in the automatic recognition method of Angle's classification according to one embodiment of the present application;

[0031] Figure 8 is a flow chart of an automatic identification method of Angle's classification according to another embodiment of the present application;

[0032] Figure 9a is a schematic diagram of the occlusal surface of the first molar in the automatic identification method of Angle's classification according to another embodiment of the present application;

[0033] Figure 9b is a schematic diagram of the buccal surface of the first molar in the automatic identification method of Angle's classification according to another embodiment of the present application;

[0034] Figure 10 is a schematic diagram of an automatic identification system for Angle's classification according to another embodiment of the present application;

[0035] Figure 11 is a schematic diagram of an electronic device according to another embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present application, many technical details are proposed to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0037] The "anterior region" and "posterior region" mentioned in various embodiments of this application are defined according to the classification of teeth in the second edition of "Introduction to Stomatology" published by Peking University Medical Press, pages 36-38. The posterior region includes premolars and molars, which are represented as teeth 4-8 using the FDI notation. The anterior region is represented as teeth 1-3 using the FDI notation. The teeth in the anterior region include central incisors, lateral incisors, and canines. The teeth in the anterior region are referred to as "anterior teeth" and the teeth in the posterior region are referred to as "posterior teeth."

[0038] The "jaw plane" mentioned in each embodiment of this application is obtained according to the definition and confirmation method on page 83 of the 6th edition of "Orthodontics". One method is to connect the occlusal midpoint of the first permanent molar and the midpoint between the upper and lower central incisors (1 / 2 of the overbite or open bite); the other method is obtained by evenly dividing the posterior jaw contact points, and the jaw contact points of the first permanent molar and the first deciduous molar or the first premolar are often used.

[0039] One embodiment of the present application relates to a method for automatic Angle's classification system recognition, wherein the recognition method is automatically performed by an electronic device, which may be implemented by hardware or a combination of computer software and hardware. For hardware implementation, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic devices for implementing the automatic Angle's classification system recognition function, or a combination of the aforementioned devices.

[0040] The specific process of the automatic identification method of Andersen classification performed by the electronic device in this embodiment can be as follows: Figure 1 As shown, the following steps are included:

[0041] Step 101: Identify characteristic parameters of the patient's upper and lower jaw teeth from the patient's dental data.

[0042] Specifically, the patient's dental data can be sent to an electronic device by a doctor, or uploaded to an electronic device by the patient himself, or directly collected by a dedicated camera when the patient is in a specific posture. The collection method can be determined by the selected collection device and will not be described in detail here. More specifically, the above-mentioned dental data includes at least part of the posterior teeth on one side in the occlusal state, and the above-mentioned characteristic teeth belong to the said part of the posterior teeth. This embodiment is described by taking the dental data as a two-dimensional photo as an example, combined with Figure 2a To further illustrate, the two-dimensional photograph in this embodiment can be a lateral intraoral photograph. Since lateral intraoral photographs are routinely collected in the early stages of orthodontic treatment, and primarily capture images of posterior molars, limiting the use of lateral intraoral photographs for feature parameter identification helps reduce the amount of additional data collected, simplifies operations on the physician side, and facilitates the promotion of the Angle's classification identification method in this application. In addition, lateral intraoral photographs are generally collected while the patient is biting, so their upper and lower teeth are already in occlusion, making Angle's classification identification more convenient.

[0043] It should be noted that in this embodiment, the maxillary and mandibular characteristic teeth are the maxillary first molars and mandibular first molars, respectively. Because the characteristic parameters corresponding to the first molars are more direct and reliable references for identifying the Angle's classification, using the first molars as the characteristic teeth facilitates the accuracy of Angle's classification identification in this application.

[0044] In some embodiments, before identifying the characteristic parameters of the patient's maxillary characteristic teeth and mandibular characteristic teeth from the patient's dental data, this step also includes: classifying the teeth in the acquired patient's dental data to determine the characteristic teeth. In this embodiment, the characteristic teeth are located by the tooth segmentation step so that the characteristic parameters identified for the characteristic teeth are more accurate. The specific method of tooth classification can be, for example, using a pre-trained first dentition segmentation model to segment the dentition in the two-dimensional photo to obtain each single tooth and determine the characteristic teeth. Specifically, the first dentition segmentation model in this embodiment can be trained based on a CNN structure network such as FCIS, MaskRCNN, UNet series or a transformer structure network such as ISTR, Mask2Former, etc. It can be understood that the specific first dentition segmentation model in actual applications can use an existing model or be trained separately, which will not be repeated here. Those skilled in the art will understand that in addition to using a trained dentition segmentation model for tooth segmentation, other methods can also be used for segmentation, which will not be listed here one by one. The segmentation results are as follows: Figure 2b As shown in the figure, different color blocks represent different teeth. The specific colors can be set as needed and are not limited here.

[0045] To continue, after the teeth in the dental data are classified, the first molar can be located, and then the characteristic parameters of the first molar can be identified. Specifically, the characteristic parameters in this embodiment can include characteristic points on the occlusal surface; correspondingly, the characteristic parameters of the patient's maxillary characteristic teeth and mandibular characteristic teeth identified from the patient's dental data include: determining the characteristic points on the occlusal surface of the characteristic teeth by establishing a bounding box for the characteristic teeth. Since it is necessary to confirm the relative position relationship of the upper and lower first molars in the mesiodistal direction, the selected reference features try to avoid differences in directions other than the mesiodistal direction, which may cause inaccurate confirmation. For the two teeth in the upper and lower jaws, respectively, the points on the occlusal surface are closer in the vertical direction. Therefore, in order to more easily and accurately confirm the relative position relationship of the two teeth in the mesiodistal direction, the points on the occlusal surface are selected to avoid position misjudgment, making the mesiodistal position judgment more accurate. Furthermore, the feature parameters were further limited to feature points on the occlusal surface. Points on the upper and lower occlusal surfaces are closer vertically, allowing for more accurate determination of the mesiodistal relative position of the upper and lower teeth. Furthermore, the bounding box method was used to completely enclose the target object within a relatively simple, enclosed space, making it easier to capture the surface features of the first molar.

[0046] In some embodiments, the characteristic point on the occlusal surface may be the buccal cusp point. Since the buccal cusp point is the most convex point of the occlusal surface, the characteristic is more obvious and is easier to identify accurately during recognition, which is beneficial to the overall accuracy of the recognition method in this application. Figure 3 As shown, the first molar is obtained by establishing a bounding box ( Figure 3 The buccal cusp of (16) Figure 3 161). Since teeth are nearly rectangular, a rectangular bounding box better fits the tooth shape. The method for establishing the bounding box will not be described in detail. To further explain, when establishing the bounding box, the minimum rectangular bounding box for each of the mandibular and maxillary molars is calculated. The two points where the occlusal surface of the tooth intersects one side of the bounding box are determined as the buccal cusps.

[0047] In some other embodiments, a trained feature point recognition model may be used to determine the feature points on the occlusal surface of the feature tooth. Specific training and model selection may adopt solutions in the prior art, which will not be described in detail here.

[0048] Step 102: confirm the relative positional relationship of the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal and upward directions based on the characteristic parameters.

[0049] Step 103: Determine the Angle's classification corresponding to the patient's teeth based on the relative position relationship.

[0050] Specifically, the above-mentioned relative position relationship can include the maxillary characteristic teeth in the distal direction of the mandibular characteristic teeth, the maxillary characteristic teeth in the mesial direction of the mandibular characteristic teeth, and can also specifically include the relative position relationship of the two buccal cusps of the maxillary characteristic teeth to the two buccal cusps of the mandibular, wherein the two buccal cusps of each molar specifically include the distal buccal cusp on the distal side and the mesial buccal cusp on the mesial side. The relative position relationship is specific such as the two buccal cusps of the maxillary first molar are respectively on the mesial and distal sides of the distal buccal cusp of the mandibular first molar, the mesial buccal cusp of the maxillary first molar is on the mesial side of the mesial buccal cusp of the mandibular first molar, the distal buccal cusp of the maxillary first molar is between the two buccal cusps of the mandibular first molar, and so on.

[0051] It should also be noted that when the characteristic parameters include characteristic points on the occlusal surface of the characteristic teeth, the above-mentioned determination of the mesiodistal positional relationship of each buccal cusp point may include: setting a reference vector based on the characteristic points of all characteristic teeth in the upper and lower jaws, determining the relative positional relationship of each characteristic point on the reference vector; and determining the relative positional relationship of the characteristic teeth in the upper and lower jaws in the mesiodistal direction based on the relative positional relationship of each characteristic point on the reference vector. Since the characteristic points on the occlusal surface of the teeth are distributed near the occlusal plane of the upper and lower jaws, the straight line fitted using these characteristic points can be approximately used as a reference line in the mesiodistal direction in the posterior tooth region.

[0052] To further illustrate, determining the relative position relationship of each feature point on the reference vector may include: obtaining the projection points of each feature point on the reference vector, and using the relative position relationship between the projection points as the relative position relationship between the corresponding feature points. Figure 4 and Figure 5 Specifically, mark the buccal cusp points u1 and u2 of the maxillary first molar and the buccal cusp points l1 and l2 of the mandibular first molar, and project the four points u1, u2, l1, and l2 onto the reference vector T0 to obtain the four projection points U1, U2, L1, and L2 on the reference vector T0, respectively. Then, the relative position relationship of the four projection points on the reference vector T0 can be determined. Since the relative position relationship in the Angle classification is a relative position relationship in the mesiodistal direction, using the projection points of the feature points on the reference vector to determine the relative position relationship can avoid position relationship judgment errors caused by distance differences in other directions, thereby improving the accuracy of the mesiodistal position relationship judgment.

[0053] More specifically, the reference vector can be obtained in a variety of ways in practical applications. In some embodiments, the above-mentioned setting of the reference vector based on the feature points of all the feature teeth of the upper and lower jaws may include: fitting a straight line with each feature point, and specifying any direction of the fitted straight line as the reference vector. Since each buccal cusp point is near the jaw plane, the relative position relationship in the two-dimensional photo can be roughly regarded as a mesiodistal relationship. Since each tooth has two buccal cusp points, the amount of data is relatively sufficient when fitting a straight line. The direction of the straight line fitted by the above-mentioned method on the side intraoral photo is roughly the same as the mesiodistal direction of the posterior tooth section in three-dimensional space. Therefore, the straight line fitted by the above-mentioned buccal cusp points is not only accurate in data judgment, but also has strong operability, which helps to reduce the amount of calculation. Furthermore, according to the above-mentioned steps, some embodiments use the bounding box method to confirm the buccal cusp point when identifying the buccal cusp point. Then the vertices ub1, ub2, lb1, and lb2 of the established bounding box on the occlusal side can also participate in the determination of the reference vector, from Figure 6 It can be seen that these bounding box vertices and the cheek cusp point are basically in the same plane. At this time, eight points u1, u2, l1, l2, ub1, ub2, lb1, and lb2 are used for straight line fitting to make the direction of the obtained reference vector more accurate.

[0054] It should also be noted that in addition to the above method, other methods can also be used to set the reference vector, such as selecting the two feature points that are farthest apart from all the feature points, and using the direction in which one of the two selected feature points points to the other as the reference vector. Further limiting the generation of the reference vector to multiple feature points facilitates the automatic and simple acquisition of the reference vector, has good feasibility, and high accuracy. Specifically, Figure 4 For example, when the points involved in setting the reference vector include u1, u2, l1, and l2, and l1 and u2 are the two farthest points, the reference vector can be set using the line connecting l1 and u2 (not shown in the figure). Figure 6 For example, when the points involved in setting the reference vector include eight points: u1, u2, l1, l2, ub1, ub2, lb1, and lb2, the line connecting lb1 and ub2, which are the farthest apart, can be used to set the reference vector. This also yields a reference vector that roughly conforms to the mesiodistal direction. In addition to the two methods described above, other methods can also be used, such as using some buccal cusp points and some bounding box vertices to set the reference vector, or using two bounding box vertices close to the occlusal surface to set the reference vector. It can be seen that there are many different ways to select data when setting the reference vector to suit different needs, and we will not list them all here.

[0055] After confirming the relative position relationship of each buccal cusp in the mesiodistal direction, it is further explained that the relative position relationship of the buccal cusps of the maxillary and mandibular first molars can correspond to the Angle classification one by one. The specific correspondence can be determined according to the medical definition of the Angle classification, or specified by doctors / professionals based on the characteristics of the Angle classification, which is not limited here. In one embodiment, combined with Figure 7a 、 Figure 7b and Figure 7c To illustrate, when the mesiobuccal cusp of the maxillary first molar is located between the two buccal cusps of the mandibular first molar, and the distal buccal cusp of the mandibular first molar is located between the two buccal cusps of the maxillary first molar, it can be determined as Angle Class I, which can also be called neutral malocclusion or Class I malocclusion. When the mesiobuccal cusp of the maxillary first molar is located mesial to the mesiobuccal cusp of the mandibular first molar, and the distal buccal cusp of the maxillary first molar is located between the two buccal cusps of the mandibular first molar, it can be determined as Angle Class II, which can also be called distal malocclusion or Class II malocclusion. When both buccal cusps of the maxillary first molar are located distal to the distal buccal cusp of the mandibular first molar, it can be determined as Angle Class III, which can also be called mesial malocclusion or Class III malocclusion.

[0056] In some embodiments, after determining the above correspondence, the correspondence can be constructed into an implicit relationship function, and then the Angle's classification of the patient's teeth can be directly determined using conditional judgment. In other embodiments, the relationship between the above points can be constructed as features of the dental jaw, and the features can be combined to form a constructed feature. A machine learning algorithm is used to learn the mapping relationship between the constructed feature and the Angle's classification for each sample in the sample set, thereby obtaining a machine learning model that can be used for Angle's classification. In actual judgment, the Angle's classification of the patient's teeth can be automatically identified directly through the machine learning model.

[0057] Furthermore, the above-mentioned constructed features may include a combination of vectors between feature points, and the construction process is combined with Figure 6 Description, including:

[0058] (1) Calculate the minimum rectangular bounding boxes 601 and 602 of the upper and lower molars, respectively. For these two rectangular bounding boxes, select the vertices of the bounding boxes close to the two buccal cusps, which are ub1 and ub2 for the upper and lower molars and lb1 and lb2 for the lower and upper molars, respectively.

[0059] (2) A straight line is used to fit eight points, including the two buccal cusp points (u1, u2) of the maxillary jaw, the two bounding box points (ub1, ub2), and the corresponding buccal cusp points (l1, l2) and bounding box points (lb1, lb2) of the mandibular jaw.

[0060] (3) Calculate the projections of all eight buccal cusp points and bounding box points on the line. The names of the corresponding projection points are represented by capital letters: U1, U2, L1, L2, UB1, UB2, LB1, and LB2.

[0061] (4) Calculate the vectors UB1UB2 from the distal projection point (UB1) to the mesial projection point (UB2) of the maxillary bounding box, and calculate the vectors LB1LB2 from the distal projection point (LB1) to the mesial projection point (LB2) of the mandibular bounding box.

[0062] (4) Select the longest vector as the reference vector. In addition, the vertex of the bounding box of the upper and lower first molars that is offset the farthest can also be considered as the reference vector, such as LB1UB2. The specific selection can be made according to the actual situation and will not be listed here one by one.

[0063] (5) Calculate the vectors between each pair of points, such as calculating the vector U2L1 from the projection point of the mesiobuccal cusp of the maxillary first molar (U2) to the projection point of the distal buccal cusp of the mandibular first molar (L1); calculating the vector U2L2 from the projection point of the mesiobuccal cusp of the maxillary first molar (U2) to the projection point of the mesiobuccal cusp of the mandibular first molar (L2), etc. The calculation of vectors between other points is similar and will not be repeated here. The values ​​of these vectors are positive if they are in the same direction as the reference vector, and negative if they are in the opposite direction.

[0064] (6) Based on the previous calculation, a new feature is concatenated. For example, after concatenating five vectors,

[0065] X = [U2L1, U2L2, L2U1, L2U2, U1L1], and this new feature is used as the constructed feature. It can be understood that the number of vectors and the target in the above splicing vector can be adjusted as needed and are not limited here.

[0066] In summary, steps (1)-(6) are the specific process of constructing features. It should be noted that in the process of splicing vectors, considering the different resolutions of different images, a normalization operation can be performed. The normalization process includes: "Each quantity of the above features is divided by the length of the reference vector, and the result is the relative distance feature relative to the length of the reference vector". Then, a three-category classifier is trained on the training set using commonly used machine learning models, such as support vector machines, Boost class algorithms, etc., and the accuracy of the algorithm can be verified on the test set to obtain a classifier that can automatically identify the three classification results of the Angle classification.

[0067] Generally speaking, the maxillary characteristic teeth and the mandibular characteristic teeth can be selected in the same tooth position or in different tooth positions. The relative position relationship between the teeth and the corresponding relationship of the Angle classification can be determined by the selected tooth position. In this embodiment, the corresponding relationship is confirmed by taking the first molar as the characteristic tooth as an example. However, those skilled in the art will understand that other tooth positions can also be selected, such as selecting the second molar adjacent to the first molar as an alternative. In particular, when the first molar is missing, it is also appropriate to select the second molar for judgment. The selection of specific characteristic teeth can be specified according to the needs of the doctor or determined by the choice of medical professionals, and will not be listed here one by one.

[0068] It is understood that although the buccal cusp point is used as an example of a characteristic point in this embodiment, the buccal groove point can also be used in actual applications. The buccal groove point is located between the two buccal cusp points, has obvious characteristics, and is easy and accurate to identify from the buccal side. The relative positional relationship of the buccal groove points of the upper and lower first molars in the mesiodistal direction can also represent the relative positional relationship of the upper and lower first molars in the mesiodistal direction. Since the buccal groove point is the lowest point of the buccal groove on the buccal surface of the tooth, it has obvious characteristics during identification and is relatively accurate. Therefore, the buccal groove point can also be used as a characteristic point in the actual application of this application, or a combination of the buccal cusp point and the buccal groove point can be used as a characteristic point. No further details will be given here.

[0069] As can be seen, the automatic Angle's classification recognition method in this embodiment uses an electronic device to automatically identify characteristic parameters of the characteristic teeth in the posterior region of the patient's upper and lower jaws from the patient's dental data. It then determines the relative positional relationship of the characteristic teeth in the upper and lower jaws in the mesiodistal direction based on the characteristic parameters. The corresponding Angle's classification of the patient's teeth is then determined based on this determined relative positional relationship. This combination of automated steps allows the electronic device to automatically identify the corresponding Angle's classification of the patient's teeth, and the classification results, which are based on the characteristic teeth in the posterior region, are accurate and highly reliable.

[0070] Another embodiment of the present application also relates to an automatic recognition method for Angle's classification. This embodiment is roughly the same as the above embodiment, with the main difference being that in the previous embodiment, the tooth data is a two-dimensional photo, while in this embodiment, the tooth data is a three-dimensional dental model. The three-dimensional dental model is also a common data that needs to be collected in the early stage of orthodontics, and the information carried in the three-dimensional dental model is richer than that of the two-dimensional photo. Therefore, in this embodiment, the use of a three-dimensional dental model as the tooth data can, on the one hand, make the result of the automatic recognition of Angle's classification more accurate, and on the other hand, it can also expand the application scenarios of this application and adapt to different needs.

[0071] The automatic identification method of Angle's classification in this embodiment is as follows Figure 8 As shown, the details are as follows:

[0072] Step 201 : identifying the buccal cusps and buccal grooves of the patient's upper and lower first molars from the patient's three-dimensional dental model.

[0073] Specifically, in this embodiment, the three-dimensional dental model can be obtained by oral scanning, specifically, the scanning equipment can be used to perform intraoral or extraoral scanning of the patient's upper and lower teeth, thereby obtaining a digital three-dimensional dental model, which can have high-precision crown information. It should also be noted that the dental model obtained by oral scanning in this embodiment has been occlusally matched, and is an upper and lower jaw model that maintains the patient's true occlusal relationship. In addition, in some embodiments, the three-dimensional dental model can be obtained by scanning a physical model, such as taking a mold of the patient's dentition in advance, making a plaster model, and then scanning the plaster model to obtain the above-mentioned three-dimensional dental model. It can be seen that there is more than one way to obtain a three-dimensional dental model, and it can be obtained according to actual needs, which is not limited here.

[0074] Regarding the identification of first molars from a 3D dental model, in some embodiments, tooth segmentation algorithms can be used for identification. For example, geometric features of the 3D dental model can be extracted, and then the 3D dental model is segmented based on the geometric features to identify specific characteristic teeth within the segmented teeth. In practical applications, tooth classification can also be performed by combining geometric features with color features. Specific algorithms can include machine learning methods, spectral clustering methods, etc., which are not listed here.

[0075] After identifying the first molar, the process of identifying the buccal cusp and buccal groove points of the first molar includes: taking iMeshSegNet as an example, using a neural network model to automatically predict the buccal cusp and buccal groove points on the buccal side of each tooth in the three-dimensional dental model. When training the model, the existing three-dimensional mesh data and landmark point labels can be used. The selected training model includes but is not limited to the neural network model of iMeshSegNet, and can also be used to predict the three landmark points of the two buccal cusps and one buccal groove point of the first molar, such as PointNet, PointNet++, etc. In actual applications, if the landmark points that need to be predicted are adjusted, the data set during training can be adjusted accordingly. It is widely used for tooth feature points, and the predicted buccal cusp points and buccal groove points are accurate.

[0076] In addition, in other embodiments, the geometric features of the cheek cusp point and cheek groove point can be used to identify the Figure 9aAs shown, the occlusal surface 26 of the tooth to be identified (e.g., the first molar) is divided into four regions along the mesiodistal (X-direction) and sagittal (Z-direction). For each region, a highest point along the Y-axis (vertical direction, or the long axis of the tooth, not shown in the figure) is determined as the buccal cusp point. Correspondingly, the lowest point of the buccal groove on the buccal surface of the tooth along the Y-axis is determined as the buccal groove point (as shown in FIG9 ). It can be seen that there are many different ways to determine the buccal cusp point and the buccal groove point, which can be selected according to actual needs and are not limited here.

[0077] Step 202: confirm the relative positional relationship of the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal direction based on the positions of the buccal cusp points and buccal groove points of the maxillary and mandibular first molars.

[0078] Step 203: Determine the Angle's classification corresponding to the patient's teeth based on the relative position relationship.

[0079] Specifically, the above steps 202 and 203 are similar to steps 102 and 103 in the first embodiment. After the cheek groove point is added to participate in the judgment, the amount of information is more sufficient.

[0080] Specifically, the mesiodistal axis is obtained based on the maxillary first molar or the mandibular first molar, and the mesiodistal axis is used as a reference vector for subsequent confirmation of the relative position relationship.

[0081] It can be understood that in addition to the above-mentioned method of directly obtaining the mesiodistal axis and using the mesiodistal axis as the reference vector, a feature point fitting method can also be used, such as determining the mesiodistal relative position relationship based on six points, namely, two buccal cusps and one buccal groove point of the maxillary first molar, and two buccal cusps and one buccal groove point of the mandibular first molar. Among them, the reference vector can be determined by the above-mentioned six points, and the reference vector can be fitted with a straight line using the above-mentioned six points, or the two points with the farthest distance from each other are selected from the above-mentioned six points for connection. Based on the obtained straight line, any extension direction of the straight line is selected as the above-mentioned reference vector, and the relative position relationship of the above-mentioned six points is confirmed using the reference vector as a reference.

[0082] Furthermore, when determining the relative positional relationship of each feature point in the near, far, medial, and upward directions, the projection points of each feature point on the reference vector can be obtained, and the relative positional relationship between the projection points can be used as the relative positional relationship between the corresponding feature points. Since the relative positional relationship in the Angle classification is a relative positional relationship in the near, far, medial, and upward directions, using the projection points of the feature points on the reference vector to determine the relative positional relationship avoids positional relationship judgment errors caused by distance differences in other directions, thereby improving the accuracy of the near, far, and medial positional relationship judgment.

[0083] It can be seen that the Angle classification automatic recognition method in this embodiment automatically identifies the buccal cusp and buccal groove points of the first molars in the posterior tooth area of ​​the patient's upper and lower jaws from the patient's three-dimensional dental model through an electronic device, and then confirms the relative position relationship of the upper and lower jaw characteristic teeth in the mesiodistal direction based on the buccal cusp and buccal groove points, and then determines the Angle classification corresponding to the patient's teeth based on the confirmed relative position relationship. Through the combination of a series of automatic steps, the electronic device can automatically identify the Angle classification corresponding to the patient's teeth, and the classification result is accurately identified and highly reliable by judging the characteristic teeth in the posterior tooth area. It is further limited that a variety of methods can be used to identify the first molar, and a variety of methods can be used to identify the buccal cusp and buccal groove points on the first molar, so that the Angle classification automatic recognition method of this application is more flexible and changeable, and different implementation methods can be selected according to different needs and different application scenarios, which is convenient for the promotion of this application.

[0084] It is worth mentioning that the above-mentioned embodiment uses the buccal cusp of the characteristic tooth or the combination of the buccal cusp and buccal groove point of the characteristic tooth as data to automatically determine the Angle's classification of the patient's teeth. In actual applications, one or more characteristic parameters of the long axis, center point, and jaw plane normal of the characteristic tooth through the center point can also be used. By limiting the characteristic parameters to include one or more of the long axis, center point, and jaw plane normal of the characteristic tooth through the center point, different characteristic parameters can be flexibly combined to collaboratively determine the mesiodistal relative position relationship of the characteristic tooth, thereby improving accuracy and making the recognition method in this application more flexible and diverse, broadening its application scenarios. Specifically, when more characteristic parameters are collected, the relative position relationship of the teeth can be determined more accurately, thereby making the recognition of Angle's classification more accurate. At the same time, more characteristic parameters are available, making the implementation of this application more flexible and diverse. Specifically, since the actual tooth data obtained may have problems such as incomplete tooth information, the selected characteristic parameters can be determined based on the information covered in the obtained tooth data.

[0085] It should also be noted that the relative positional relationship between different characteristic parameters and teeth can be set based on physiological characteristics. For example, if the long axis of the tooth is selected, since the long axis of the tooth is approximately close to the vertical direction, the relative positional relationship of the long axis of the tooth in the mesiodistal direction can roughly correspond to the relative positional relationship of the teeth in the mesiodistal direction. For another example, if the center point is selected, which can be the geometric center point or center of gravity of the crown, then the relative positional relationship of the center points of the upper and lower characteristic teeth in the mesiodistal direction can also roughly correspond to the relative positional relationship of the characteristic teeth themselves in the mesiodistal direction. The judgment of the relative positional relationship between other characteristic parameters can also be set based on physiological characteristics, and will not be listed here one by one.

[0086] It is worth mentioning that the above examples in this embodiment are all illustrative for ease of understanding and do not constitute a limitation on the technical solutions of the present invention.

[0087] The steps of the various methods above are divided only for the purpose of clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0088] One embodiment of the present application relates to an automatic identification system for Angle's classification, such as Figure 10 As shown, including:

[0089] The receiving module is used to receive the patient's dental data.

[0090] The recognition module is used to identify characteristic parameters of the patient's upper and lower jaw characteristic teeth from the patient's dental data. Specifically, the dental data includes at least a portion of the posterior teeth on one side in the occlusal state, and the characteristic teeth belong to the portion of the posterior teeth.

[0091] The position confirmation module is used to confirm the relative position relationship of the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal and upward directions based on the above characteristic parameters.

[0092] The classification determination module is used to determine the Angle classification corresponding to the patient's teeth based on the above relative position relationship.

[0093] Specifically, the receiving module, identification module, location confirmation module, and classification determination module can be implemented using one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic devices for implementing the automatic Angle's classification recognition function, or a combination of these devices. Furthermore, the receiving module, identification module, location confirmation module, and classification determination module can be implemented using a single device or a combination of multiple devices, without limitation herein.

[0094] It is worth mentioning that the Angle classification automatic identification system also includes a peripheral device interface for connecting the above-mentioned devices, as well as a processor and memory connected to the interface through a bus. As the basic components in the device, it provides the system with timing, peripheral interface management, voltage regulation, power management and other control functions.

[0095] Another embodiment of the present application relates to an electronic device, such as Figure 11As shown, it includes: at least one processor 1101; and a memory 1102 communicatively connected to the at least one processor 1101; wherein the memory 1102 stores instructions that can be executed by the at least one processor 1101, and the instructions are executed by the at least one processor 1101 to enable the at least one processor 1101 to execute the automatic recognition method of Angle's classification in the above-mentioned embodiments.

[0096] The memory and processor are connected using a bus, which can include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are therefore not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor.

[0097] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0098] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0099] That is, those skilled in the art will understand that all or part of the steps in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a program, which is stored in a storage medium and includes a number of instructions for causing a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program code.

[0100] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and that in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. An automatic recognition method for Angle's classification, characterized by: The identification method includes automatically performing the following steps by an electronic device: Identifying characteristic parameters of characteristic teeth of the patient's upper and lower jaws from the patient's dental data, wherein the dental data includes at least a portion of posterior teeth on one side in an occlusal state, and the characteristic teeth belong to the portion of posterior teeth; According to the characteristic parameters, determining the relative positional relationship between the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal and upward directions; According to the relative positional relationship, the Angle classification corresponding to the patient's teeth is determined; wherein the tooth data is a two-dimensional photo and / or a three-dimensional dental model.

2. The automatic identification method of Angle's classification according to claim 1, characterized in that: The maxillary characteristic teeth and the mandibular characteristic teeth are first molars respectively.

3. The automatic identification method of Angle's classification according to claim 1 or 2, characterized in that: Before identifying the characteristic parameters of the patient's maxillary characteristic teeth and mandibular characteristic teeth from the patient's dental data, the method includes: The teeth in the acquired patient's dental data are classified to determine the characteristic teeth.

4. The automatic identification method of Angle's classification according to claim 3, characterized in that: If the dental data is a two-dimensional photo, classifying the teeth in the acquired dental data of the patient includes: using a pre-trained first dentition segmentation model to segment the dentition in the two-dimensional photo to obtain individual teeth, and determining the characteristic teeth; If the tooth data is a three-dimensional jaw model, classifying the teeth in the acquired patient's tooth data includes: extracting geometric features of the three-dimensional jaw model, segmenting the three-dimensional jaw model according to the geometric features, and determining the characteristic teeth.

5. The automatic identification method of Angle's classification according to claim 1, characterized in that: The characteristic parameters are characteristic points on the occlusal surface of the characteristic teeth; the characteristic parameters for identifying the patient's maxillary characteristic teeth and mandibular characteristic teeth from the patient's tooth data include: Determine the characteristic points on the occlusal surface of the characteristic tooth by establishing a bounding box for the characteristic tooth; or The trained feature point recognition model is used to determine the feature points on the occlusal surface of the feature tooth.

6. The automatic identification method of Angle's classification according to claim 5, characterized in that: The characteristic points on the occlusal surface include: buccal cusp points and / or buccal groove points.

7. The automatic identification method of Angle's classification according to claim 1 or 5, characterized in that: The characteristic parameters include characteristic points on the occlusal surface of the characteristic teeth, and determining the relative positional relationship between the maxillary characteristic teeth and the mandibular characteristic teeth in the mesiodistal-upward direction based on the characteristic parameters includes: Setting a reference vector based on the characteristic points of all characteristic teeth in the upper and lower jaws, and determining the relative position relationship of each characteristic point on the reference vector; According to the relative positional relationship of each characteristic point on the reference vector, the relative positional relationship of the characteristic teeth of the upper and lower jaws in the mesiodistal direction is determined.

8. The automatic identification method of Angle's classification according to claim 7, characterized in that: The characteristic point is the cheek cusp point.

9. The automatic identification method of Angle's classification according to claim 7, characterized in that: Determining the relative position relationship of each feature point on the reference vector includes: The projection points of each feature point on the reference vector are obtained, and the relative positional relationship between the projection points is used as the relative positional relationship between the corresponding feature points.

10. The automatic identification method of Angle's classification according to claim 7, characterized in that: The step of setting the reference vector according to the characteristic points of all characteristic teeth in the upper and lower jaws includes: Perform straight line fitting with each feature point, and designate any direction of the fitted straight line as the reference vector; or, Two feature points that are farthest apart from each other among all feature points are selected, and the direction in which one of the two selected feature points points to the other is used as the reference vector.

11. The automatic identification method of Angle's classification according to claim 1, characterized in that: The characteristic parameters include one or more of the long axis, the center point, and the normal line of the jaw plane passing through the center point of the characteristic tooth.

12. The automatic identification method of Angle's classification according to claim 1, characterized in that: The two-dimensional photograph is a side intraoral photograph.

13. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the automatic identification method of Angle's classification according to any one of claims 1 to 12.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for automatic identification of the Angle's classification system according to any one of claims 1 to 12 is implemented.

Images