Oral inspection method, device, electronic device and medium based on artificial intelligence

Abstract

The disclosed embodiments relate to an artificial intelligence-based oral inspection method, device, electronic device, and medium, wherein the method comprises: obtaining a three-dimensional mesh of teeth to be inspected, inputting the three-dimensional mesh of teeth to be inspected into a pre-trained deep neural network for processing, obtaining three-dimensional feature points, and performing processing based on the three-dimensional feature points to obtain inspection results. By adopting the above technical solution, relevant calculations are performed on the three-dimensional feature points during the oral inspection process, and conditions such as missing teeth and crowding can be obtained, thereby avoiding the high cost and low efficiency of manual inspection. Furthermore, by identifying three-dimensional feature points based on a pre-trained deep neural network, the recognition accuracy of the three-dimensional feature points can be greatly improved, thereby improving the accuracy of the inspection results, and further improving the inspection efficiency and effectiveness in the oral inspection scenario.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent oral medicine technology, and in particular to an oral detection method, device, electronic equipment and medium based on artificial intelligence. Background Art

[0002] With the continuous development and progress of society and the continuous improvement of people's living standards, people are paying more and more attention to the condition of their oral teeth.

[0003] In the related art, dentists manually identify and measure oral conditions, such as missing teeth and crowding, which is time-consuming and inefficient. Summary of the Invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an oral cavity detection method, device, electronic device and medium based on artificial intelligence.

[0005] The present disclosure provides an artificial intelligence-based oral cavity detection method, the method comprising:

[0006] Obtain a three-dimensional mesh of the tooth to be detected;

[0007] Inputting the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points;

[0008] Processing is performed based on the three-dimensional feature points to obtain a detection result.

[0009] The present disclosure also provides an artificial intelligence-based oral cavity detection device, comprising:

[0010] An acquisition module, used for acquiring a three-dimensional mesh of the tooth to be detected;

[0011] A processing module, configured to input the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points;

[0012] The generating module is used to process the three-dimensional feature points to obtain a detection result.

[0013] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement the artificial intelligence-based oral detection method provided in the embodiment of the present disclosure.

[0014] An embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the artificial intelligence-based oral cavity detection method provided in the embodiment of the present disclosure.

[0015] The technical solution provided by the embodiments of the present disclosure has the following advantages over the existing technology: the artificial intelligence-based oral inspection solution provided by the embodiments of the present disclosure obtains a three-dimensional mesh of the teeth to be inspected, inputs the three-dimensional mesh of the teeth to be inspected into a pre-trained deep neural network for processing, obtains three-dimensional feature points, and processes based on the three-dimensional feature points to obtain the inspection results. Using the above technical solution, relevant calculations are performed on the three-dimensional feature points during the oral inspection process to obtain conditions such as missing teeth and crowding, thereby avoiding the high cost and low efficiency of manual inspection. In addition, the recognition of three-dimensional feature points based on the pre-trained deep neural network can greatly improve the recognition accuracy of the three-dimensional feature points, thereby improving the accuracy of the inspection results, further improving the inspection efficiency and effectiveness in the oral inspection scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0017] Figure 1 A schematic diagram of a flow chart of an oral cavity detection method based on artificial intelligence provided in an embodiment of the present disclosure;

[0018] Figure 2 A schematic diagram of a three-dimensional feature point provided in an embodiment of the present disclosure;

[0019] Figure 3 A schematic diagram of an archwire provided in an embodiment of the present disclosure;

[0020] Figure 4 A schematic diagram of an occlusal plane provided in an embodiment of the present disclosure;

[0021] Figure 5 A schematic diagram of a detection result provided in an embodiment of the present disclosure;

[0022] Figure 6 A schematic diagram of another detection result provided by an embodiment of the present disclosure;

[0023] Figure 7 A schematic diagram of another detection result provided in an embodiment of the present disclosure;

[0024] Figure 8 A schematic flow chart of another oral cavity detection method based on artificial intelligence provided by an embodiment of the present disclosure;

[0025] Figure 9 A schematic structural diagram of an artificial intelligence-based oral cavity detection device provided in an embodiment of the present disclosure;

[0026] Figure 10 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0030] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] In actual applications, the detection and identification process of common oral conditions such as missing teeth, crowding, and overbite requires dentists to manually identify and measure, which takes a long time and is inefficient.

[0034] To address these issues, this paper proposes an artificial intelligence-based oral inspection method. This method obtains a three-dimensional mesh of the teeth to be inspected and feeds it into a pre-trained deep neural network for processing, generating three-dimensional feature points. This feature points are then processed to produce inspection results. This method enables rapid and accurate identification of oral conditions and provides them to the user, improving the efficiency of oral inspections.

[0035] Specifically, Figure 1 This is a flow chart of an oral cavity detection method based on artificial intelligence provided by an embodiment of the present disclosure. This method can be performed by an oral cavity detection device based on artificial intelligence, wherein the device can be implemented using software and / or hardware and can generally be integrated into an electronic device. Figure 1 As shown, the method includes:

[0036] Step 101: Obtain a three-dimensional mesh of the tooth to be detected.

[0037] The 3D tooth mesh to be detected can be obtained by scanning the upper or lower teeth of a person's mouth in real time using a scanning device, or can be a 3D tooth mesh corresponding to the upper or lower teeth obtained from a download link or other device. The 3D tooth mesh refers to a set of 3D points and the connections within the 3D point set.

[0038] Step 102: Input the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points.

[0039] Among them, the three-dimensional feature points include but are not limited to the tooth identifier of each three-dimensional point (each tooth has a specific tooth identifier), the mesial and distal points of the incisor, the cusp of the canine, multiple cusps and pits of the molar and one or more of the local coordinate system of the tooth; among them, the mesial and distal points of the incisor refer to a three-dimensional point obtained from the three-dimensional point set corresponding to the incisor as the mesial point and the other three-dimensional point as the distal point.

[0040] In the embodiment of the present disclosure, a three-dimensional tooth mesh sample (i.e., a set formed by a three-dimensional point set and the connections within the point set) is obtained. There is one three-dimensional tooth mesh sample for each of the upper jaw and the lower jaw. Through deep neural network training and learning, the three-dimensional feature points of the teeth can be identified.

[0041] There are many ways to pre-train a deep neural network. In some embodiments, the required three-dimensional feature points are annotated in a training set (a plurality of three-dimensional tooth mesh samples), and the annotated training set is directly input into the deep neural network for learning to obtain a pre-trained deep neural network.

[0042] In other embodiments, the three-dimensional mesh samples of teeth are rendered into two-dimensional images at various sampling angles, including depth maps, curvature maps, texture maps, etc., and then feature two-dimensional points are marked on each image and input into a deep neural network for learning. The learned two-dimensional points are used to obtain three-dimensional feature points through a mapping relationship.

[0043] The above two methods are merely examples of pre-training a deep neural network, and the present disclosure does not impose any specific restrictions on the methods of pre-training a deep neural network.

[0044] Furthermore, the three-dimensional mesh of the teeth to be detected is input into a pre-trained deep neural network for processing to obtain the three-dimensional feature points of each tooth, such as tooth identification, cutting point and cusp point.

[0045] Step 103: Processing is performed based on the three-dimensional feature points to obtain a detection result.

[0046] In the disclosed embodiments, there are various ways to obtain detection results based on 3D feature point processing. In some implementations, a tooth identifier for each tooth is obtained based on the 3D feature points, and each tooth identifier is matched against a tooth identifier corresponding to a standard 3D tooth grid. If a target tooth identifier does not exist, the tooth corresponding to the target tooth identifier is determined to be non-existent. A standard 3D tooth grid, such as the 3D tooth grid corresponding to a normal upper and lower row of teeth, corresponds to 32 teeth and thus has 32 tooth identifiers.

[0047] In other embodiments, the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines, and multiple cusps of the molars) are obtained based on the three-dimensional feature points, fitting processing is performed based on the tangent points and cusps of the teeth to obtain the arch line, calculations are performed based on the arch line to obtain the dental arch length, and the degree of tooth crowding is determined based on the dental arch length and the sum of the widths of all teeth.

[0048] In some further embodiments, the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines and multiple cusps of the molars) are obtained based on the three-dimensional feature points, and fitting processing is performed based on the tangent points and cusps of the teeth to obtain the occlusal plane. The tangent points of the corresponding teeth of the upper and lower jaws are projected onto the occlusal plane to obtain the first projection points, and the vector distance between the first projection points is calculated to obtain the coverage value.

[0049] In some other embodiments, the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines and multiple cusps of the molars) are obtained based on the three-dimensional feature points, fitting processing is performed based on the tangent points and cusps of the teeth to obtain the occlusal plane, the plane normal of the occlusal plane is obtained, the tangent points of the corresponding teeth of the upper and lower jaws, the upper mandibular surface target points and the lower mandibular surface target points are projected onto the plane normal to obtain the second projection point, the first line segment and the second line segment are determined based on the second projection point, and the overbite value is determined based on the first line segment and the second line segment.

[0050] In some other embodiments, the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines and multiple cusps of the molars) are obtained based on the three-dimensional feature points, and fitting processing is performed based on the tangent points and cusps of the teeth to obtain the occlusal plane, and any occlusal target tooth pair of the upper and lower jaws corresponding to each other (referring to the upper and lower jaw teeth pair that occlude each other) is projected onto the occlusal plane to obtain the third projection point, and the correlation between the third projection points is obtained to obtain the occlusion type.

[0051] In some other embodiments, the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines and multiple cusps of the molars) are obtained based on the three-dimensional feature points, fitting processing is performed based on the tangent points and cusps of the teeth to obtain the occlusal plane, the cusps of the upper and lower teeth are projected onto the occlusal plane to obtain a fourth projection point, and a judgment is made based on the position information of the fourth projection point in the direction of the arch line normal to determine whether the tooth is an overbite or a lockbite.

[0052] The above methods are only examples. Different 3D feature points can be selected for processing according to the application scenario to obtain different detection results.

[0053] Based on the description of the above embodiment, a three-dimensional mesh of the teeth to be tested is obtained, and the three-dimensional mesh of the teeth to be tested is input into a pre-trained deep neural network for processing to obtain three-dimensional feature points. Processing is then performed based on the three-dimensional feature points to obtain a test result. Using the above technical solution, relevant calculations are performed on the three-dimensional feature points during the oral inspection process to determine conditions such as missing teeth and crowding, thereby avoiding the high cost and low efficiency of manual inspection. Furthermore, identifying three-dimensional feature points based on a pre-trained deep neural network can greatly improve the recognition accuracy of the three-dimensional feature points, thereby improving the accuracy of the test results, further improving the efficiency and effectiveness of inspections in oral inspection scenarios.

[0054] In some embodiments, the three-dimensional mesh of the teeth to be detected is input into a pre-trained deep neural network for processing to obtain three-dimensional feature points, including: inputting the three-dimensional mesh of the teeth to be detected into a pre-trained deep neural network for processing to obtain the tooth identifier of each three-dimensional point (each tooth has a specific tooth identifier), the mesial and distal points of the incisors, the cusps of the canines, multiple cusps and pits of the molars, and the local coordinate system of the teeth as three-dimensional feature points.

[0055] As an example, Figure 2 As shown, the three-dimensional mesh of the teeth to be detected corresponding to the maxillary and mandibular teeth is input into the pre-trained deep neural network for processing to obtain three-dimensional feature points, such as the tooth identifier of each tooth (1, 2 and 3, etc.). Each tooth identifier can identify a unique tooth. For example, the mesial and distal midpoints of the incisors, Figure 2 The mesial points (a1, a2, a3, a4) and distal points (b1, b2, b3, b4) on the four incisors shown; for example, the cusp of the canine, Figure 2 The cusps on the six canines shown are j1-j6, and the multiple cusps and pits of molars are also shown. Figure 2 The multiple cusps and pits of the six molars shown are shown. Taking one molar as an example, the multiple cusps are m1-m4, and the pits are w1 and w2, and the local coordinate system of the tooth is as follows: Figure 2 xy shown.

[0056] In some embodiments, processing is performed based on three-dimensional feature points to obtain detection results, including: obtaining a tooth identifier for each tooth based on the three-dimensional feature points, matching the tooth identifier for each tooth with the tooth identifier corresponding to the standard tooth three-dimensional grid, and in the case of matching a non-existent target tooth identifier, determining that a tooth corresponding to the non-existent target tooth identifier does not exist.

[0057] In the embodiment of the present disclosure, the tooth identifier can uniquely represent a tooth. Therefore, the three-dimensional grid of the teeth to be detected is input into the pre-trained deep neural network for processing to obtain the tooth identifier of each tooth corresponding to the three-dimensional grid of the teeth to be detected, and the tooth identifier of each tooth is further matched with the tooth identifier corresponding to the standard three-dimensional grid of teeth. For example, if the tooth identifier of each tooth is 1-16, and all the tooth identifiers corresponding to the standard three-dimensional grid of teeth are also 1-16, then it is determined that there is no missing tooth. For example, if the tooth identifier of each tooth is 1-7, 9-16, and all the tooth identifiers corresponding to the three-dimensional grid of teeth to be detected are 1-16, and it is determined that the target tooth identifier 8 does not exist, then it is determined that the tooth corresponding to the target tooth identifier 8 does not exist, and there is a missing tooth. That is, the pre-trained deep neural network can determine all existing tooth identifiers, and the non-existent tooth identifiers are missing teeth.

[0058] In some embodiments, processing is performed based on three-dimensional feature points to obtain detection results, including: obtaining the tangent points and cusps of the teeth (including the tangent points of the incisors, the cusps of the canines and multiple cusps of the molars) based on the three-dimensional feature points, performing fitting processing based on the tangent points and cusps of the teeth to obtain the arch line, performing calculations based on the arch line to obtain the dental arch length, and determining the degree of tooth crowding based on the dental arch length and the sum of the widths of all teeth.

[0059] Specifically, the least squares method is used to fit each tangent point and the cusp point to obtain the arch line, such as using a biquadratic equation (the fitting goal is to minimize the sum of the squares of the distances from all tangent points and cusps to the arch line), as shown in Figure 3 Archwire shown (partially shown).

[0060] Furthermore, after obtaining the arch line, the arch length is calculated based on the arch line to obtain the dental arch length, and the dental crowding degree value is determined based on the dental arch length and the sum of the widths of all teeth. For example, the dental arch length from the tooth marked as left sixth to right sixth is calculated (that is, the length of the dental arch curve from the left sixth tooth to the right sixth tooth), and the sum of the widths of all teeth is subtracted to obtain the dental crowding degree value of the single jaw. Among them, the calculation method of each tooth width is: in the following way Figure 3 On the mesial and distal coordinate axes shown, the maximum and minimum coordinate values ​​of all tooth points are calculated to be the tooth width.

[0061] In some embodiments, processing is performed based on three-dimensional feature points to obtain detection results, including: obtaining the tangent points and cusps of the teeth based on the three-dimensional feature points, performing fitting processing based on the tangent points and cusps of the teeth to obtain the occlusal plane, projecting the tangent points of the corresponding teeth of the upper and lower jaws onto the occlusal plane to obtain the first projection point, calculating the vector distance between the first projection points, and obtaining the coverage value.

[0062] Specifically, the tangent points and cusps are fitted to the occlusal plane using the least square method (so that the sum of the squares of the distances from all tangent points and cusps to the occlusal plane is minimized), as shown in Figure 4 Occlusal plane shown.

[0063] Furthermore, the tangent points of the corresponding teeth of the upper and lower jaws are projected onto the occlusal plane to obtain the first projection points, and the vector distance between the first projection points is calculated to obtain the coverage value. Figure 5 As shown, the incisor points of the upper and lower jaws ( Figure 5 Project A1 and A2 in the figure onto the occlusal plane and calculate the vector distance between the first projection points (B1 and B2) (e.g. Figure 5 In the figure, B2 is positive if it is to the right of B1, and negative if it is to the right of B1) which is the coverage value, so that the test results such as underbite, 1, 2, 3 degrees of coverage and normal can be obtained (refers to the vector distance between maxillary B1 and mandibular B2. The larger the vector distance, the higher the coverage (1, 2, 3 degrees). A smaller and positive vector distance indicates normal coverage, and a negative vector distance indicates underbite).

[0064] In some embodiments, it also includes: obtaining the plane normal of the occlusal plane, projecting the tangent points of the corresponding teeth of the upper and lower jaws, the upper mandibular surface target point and the lower mandibular surface target point onto the plane normal respectively to obtain a second projection point, determining the first line segment and the second line segment based on the second projection point, and determining the overbite value based on the first line segment and the second line segment.

[0065] Specifically, continue with Figure 5 For example, the incisor points of the upper and lower jaws ( Figure 5 A1 and A2) and the point farthest from the maxillary face ( Figure 5 C1 and C2 in the figure are projected onto the plane normal Y of the occlusal plane (the second projection points are D1, D2, D3 and D4). In this way, the upper and lower teeth are each a line segment above the plane normal, and the incisal end point of the maxillary tooth is calculated ( Figure 5 The position of D1 and D2 in the mandibular line segment (longer arrow) (i.e. the ratio of the first line segment between D1 and D2 (shorter arrow) to the second line segment between D1 and D4 (longer arrow)) can be used to obtain five results: open bite, 1, 2, 3 degrees and normal (the larger the ratio, the larger the overbite 1, 2, 3 degrees, the smaller the ratio, the normal, and a negative ratio means open bite). Among them, Figure 5 The directions of the arrows are only examples, and the ratio is positive when the arrow directions of the first line segment of D1 and D2 and the arrow directions of the second line segment of D1 and D4 are the same, or the ratio is negative when the arrow directions of the first line segment of D1 and D2 and the arrow directions of the second line segment of D1 and D4 are opposite.

[0066] In some embodiments, the method further includes: projecting any mutually occluding target tooth pair corresponding to the upper and lower jaws onto the occlusal plane to obtain a third projection point, acquiring a correlation between the third projection points, and obtaining an occlusal type.

[0067] Specifically, the cusp (such as tooth No. 6 or other teeth can also be used in a similar way) of any tooth in the upper and lower jaws that occludes the target tooth mark is moved to the right. Figure 6 E, F1 and F2 as shown are projected onto the occlusal plane to obtain the third projection points. Based on the relationship between these third projection points, the occlusal classes 1, 2 and 3 of the Angle classification are obtained (e.g. Figure 6 As shown, when the third projection point corresponding to E is in the middle of the third projection points corresponding to F1 and F2, it is a Class 1 occlusion (neutral occlusion). When the third projection point corresponding to E appears on both sides of the third projection points corresponding to F1 and F2, it corresponds to Class 2 (mesial direction) and Class 3 (distal direction), respectively.

[0068] In some embodiments, the cusps of the upper and lower teeth are projected onto the occlusal plane to obtain a fourth projection point, and a judgment is made based on the position information of the fourth projection point in the normal direction of the arch line to determine whether the tooth is an underbite or a lockbite.

[0069] Specifically, the tooth points of the upper and lower jaws (cusps on the buccal and lingual sides) are projected onto the occlusal plane to obtain the fourth projection point, such as Figure 7As shown, project G1-G4 onto the occlusal plane. Based on the position of the fourth projection point in the normal direction of the arch line, we can determine whether these teeth are crossbite (when the buccal cusp of the maxillary teeth is inside the buccal cusp of the mandibular teeth) or lockbite (when the lingual cusp of the maxillary teeth is outside the buccal cusp of the mandibular teeth). In other words, if the lingual cusp of the maxillary teeth is closer to the buccal side than the buccal cusp of the mandibular teeth, it is lockbite. Figure 7 The figure will change to G3 on the left of G2. If the maxillary buccal cusp is closer to the lingual side than the mandibular buccal cusp, it is an underbite. Figure 7 The display will change to show G1 to the right of G2.

[0070] Specifically, Figure 8 This is a flow chart of another oral cavity detection method based on artificial intelligence provided by the embodiment of the present disclosure. This embodiment further optimizes the oral cavity detection method based on artificial intelligence on the basis of the above embodiment. Figure 8 As shown, the method includes:

[0071] Step 201: Obtain a three-dimensional mesh of the tooth to be detected.

[0072] In step 202, the three-dimensional mesh of the tooth to be detected is input into a pre-trained deep neural network for processing to obtain three-dimensional feature points.

[0073] Step 203: Obtain a tooth identifier for each tooth based on the three-dimensional feature points, and match the tooth identifier for each tooth with the tooth identifier corresponding to the standard three-dimensional tooth grid. If a target tooth identifier does not exist, determine that the tooth corresponding to the target tooth identifier does not exist.

[0074] Step 204: Acquire the tangent points and cusps of the teeth based on the three-dimensional feature points, perform fitting processing based on the tangent points and cusps of the teeth, and obtain the arch line and occlusal plane.

[0075] After step 204 , steps 205 and / or 206 and / or 207 and / or 208 and / or 209 may be performed.

[0076] Step 205: Calculate based on the arch line to obtain the dental arch length, and determine the degree of dental crowding based on the dental arch length and the sum of the widths of all teeth.

[0077] Step 206: Project the tangent points of the corresponding teeth of the upper and lower jaws onto the occlusal plane to obtain first projection points, calculate the vector distance between the first projection points, and obtain the coverage value.

[0078] Step 207: Obtain the plane normal of the occlusal plane, project the tangent points of the corresponding teeth of the upper and lower jaws, the upper mandibular surface target point, and the lower mandibular surface target point onto the plane normal to obtain a second projection point, determine the first line segment and the second line segment based on the second projection point, and determine the overbite value based on the first line segment and the second line segment.

[0079] Step 208 : Project any occlusal target tooth pair of the upper and lower jaws onto the occlusal plane to obtain third projection points, obtain the correlation between the third projection points, and obtain the occlusion type.

[0080] Step 209 , projecting the cusps of the upper and lower teeth onto the occlusal plane to obtain a fourth projection point, and determining whether the tooth is an underbite or a lockbite based on the position information of the fourth projection point in the normal direction of the archline.

[0081] It should be noted that this disclosure Figure 8 For specific real-time methods, please refer to the above embodiments Figure 1-Figure 7 The description is not detailed here.

[0082] In this way, all oral conditions can be provided to users quickly and accurately, further improving the efficiency of oral testing and meeting user needs and experience.

[0083] Figure 9 This is a schematic diagram of the structure of an oral cavity detection device based on artificial intelligence provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Figure 9 As shown, the device includes:

[0084] An acquisition module 301 is used to acquire a three-dimensional mesh of a tooth to be detected;

[0085] A processing module 302 is configured to input the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points;

[0086] The generating module 303 is configured to perform processing based on the three-dimensional feature points to obtain a detection result.

[0087] Optionally, the generating module 303 is specifically configured to:

[0088] Acquiring a tooth identifier of each tooth based on the three-dimensional feature points;

[0089] Matching based on the tooth identifier of each tooth and the tooth identifier corresponding to the standard tooth three-dimensional grid;

[0090] In the case of matching a non-existent target tooth identifier, it is determined that the tooth corresponding to the target tooth identifier does not exist.

[0091] Optionally, the generating module 303 is further configured to:

[0092] Acquire the tangent point and the cusp point of the tooth based on the three-dimensional feature points;

[0093] Performing fitting processing based on the tangent points and cusps of the teeth to obtain an archline;

[0094] Calculating based on the arch line to obtain the dental arch length;

[0095] A dental crowding value is determined based on the dental arch length and the sum of the widths of all teeth.

[0096] Optionally, the generating module 303 is further configured to:

[0097] Acquire the tangent point and the cusp point of the tooth based on the three-dimensional feature points;

[0098] Perform fitting processing based on the tangent points and cusps of the teeth to obtain an occlusal plane;

[0099] Projecting the tangent points of the corresponding teeth of the upper and lower jaws onto the occlusal plane respectively to obtain a first projection point;

[0100] Calculate the vector distance between the first projection points to obtain a coverage value.

[0101] Optionally, the generating module 303 is further configured to:

[0102] obtaining a plane normal of the occlusal plane;

[0103] Projecting the tangent points of the corresponding teeth of the upper and lower jaws, the upper mandibular surface target point, and the lower mandibular surface target point onto the plane normal respectively to obtain a second projection point;

[0104] determining a first line segment and a second line segment based on the second projection point;

[0105] An overbite amount value is determined based on the first line segment and the second line segment.

[0106] Optionally, the generating module 303 is further configured to:

[0107] Projecting any mutually occluding target tooth pair of the upper and lower jaws onto the occlusal plane to obtain a third projection point;

[0108] The correlation between the third projection points is obtained to obtain the occlusion type.

[0109] Optionally, the generating module 303 is further configured to:

[0110] Projecting the cusps of the upper and lower teeth onto the occlusal plane to obtain a fourth projection point;

[0111] A judgment is made based on the position information of the fourth projection point in the normal direction of the arch line to determine whether the tooth is an underbite or a lockbite.

[0112] The artificial intelligence-based oral detection device provided in the embodiments of the present disclosure can execute the artificial intelligence-based oral detection method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the artificial intelligence-based oral cavity detection method provided by any embodiment of the present disclosure.

[0114] Figure 10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 10 , which shows a schematic structural diagram of an electronic device 400 suitable for implementing the embodiments of the present disclosure. The electronic device 400 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0115] like Figure 10 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the electronic device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0116] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 10 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0117] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the artificial intelligence-based oral detection method of the embodiment of the present disclosure are performed.

[0118] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0119] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0120] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0121] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: receives the user's information display trigger operation during the playback of the video; obtains at least two target information associated with the video; displays the first target information among the at least two target information in the information display area of ​​the playback page of the video, wherein the size of the information display area is smaller than the size of the playback page; receives the user's first switching trigger operation, and switches the first target information displayed in the information display area to the second target information among the at least two target information.

[0122] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0125] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0126] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

[0128] processor;

[0129] a memory for storing instructions executable by the processor;

[0130] The processor is used to read the executable instructions from the memory and execute the instructions to implement any artificial intelligence-based oral detection method provided in the present disclosure.

[0131] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute any artificial intelligence-based oral detection method provided by the present disclosure.

[0132] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0133] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0134] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. An oral cavity detection method based on artificial intelligence, characterized in that: include: Obtaining a three-dimensional mesh of the tooth to be inspected; Inputting the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points; Acquiring the tangent points and cusps of the teeth based on the three-dimensional feature points, performing fitting processing based on the tangent points and cusps of the teeth to obtain an arch line and an occlusal plane, and performing processing based on the arch line and / or the occlusal plane to obtain a detection result; The processing based on the occlusal plane to obtain the detection result includes: projecting any mutually occluding target tooth pair of the upper and lower jaws onto the occlusal plane to obtain a third projection point, obtaining a correlation between the third projection points, and obtaining an occlusal type; The cusps of the upper and lower teeth are projected onto the occlusal plane to obtain a fourth projection point, and a judgment is made based on the position information of the fourth projection point in the normal direction of the arch line to determine whether the tooth is an underbite or a lockbite.

2. The oral cavity detection method based on artificial intelligence according to claim 1, further comprising: Acquiring a tooth identifier of each tooth based on the three-dimensional feature points; Matching based on the tooth identifier of each tooth and the tooth identifier corresponding to the standard tooth three-dimensional grid; In the case of matching a non-existent target tooth identifier, it is determined that the tooth corresponding to the target tooth identifier does not exist.

3. The oral cavity detection method based on artificial intelligence according to claim 1, characterized in that: The processing based on the archwire to obtain a detection result includes: Calculating based on the arch line to obtain the dental arch length; A dental crowding value is determined based on the dental arch length and the sum of the widths of all teeth.

4. The oral cavity detection method based on artificial intelligence according to claim 1, characterized in that: The processing based on the occlusal plane to obtain a detection result includes: Projecting the tangent points of the corresponding teeth of the upper and lower jaws onto the occlusal plane respectively to obtain a first projection point; Calculate the vector distance between the first projection points to obtain a coverage value.

5. The oral cavity detection method based on artificial intelligence according to claim 1, characterized in that: Also includes: obtaining a plane normal of the occlusal plane; Projecting the tangent points of the corresponding teeth of the upper and lower jaws, the upper mandibular surface target point, and the lower mandibular surface target point onto the plane normal respectively to obtain a second projection point; determining a first line segment and a second line segment based on the second projection point; An overbite amount value is determined based on the first line segment and the second line segment.

6. An oral cavity detection device based on artificial intelligence, characterized in that: include: An acquisition module, used for acquiring a three-dimensional mesh of the tooth to be detected; A processing module, configured to input the three-dimensional mesh of the tooth to be detected into a pre-trained deep neural network for processing to obtain three-dimensional feature points; a generation module, configured to obtain the tangent points and cusps of the teeth based on the three-dimensional feature points, perform fitting processing based on the tangent points and cusps of the teeth to obtain an arch line and an occlusal plane, and perform processing based on the arch line and / or the occlusal plane to obtain a detection result; The detection result is obtained by processing based on the occlusal plane, including: Projecting any mutually occluding target tooth pair of the upper and lower jaws onto the occlusal plane to obtain a third projection point, obtaining a correlation between the third projection points, and obtaining an occlusal type; The cusps of the upper and lower teeth are projected onto the occlusal plane to obtain a fourth projection point, and a judgment is made based on the position information of the fourth projection point in the normal direction of the arch line to determine whether the tooth is an underbite or a lockbite.

7. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the artificial intelligence-based oral detection method described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and the computer program is used to execute the artificial intelligence-based oral detection method described in any one of claims 1 to 5.

Images