Method and device for extracting a neck line of a dental preparation, equipment and medium

Abstract

Embodiments of the present disclosure relate to a tooth preparation body neck line extraction method, device, equipment and medium, wherein the method comprises: obtaining a three-dimensional digital model of a tooth preparation body, and obtaining a candidate two-dimensional digital image corresponding to the three-dimensional digital model; determining a candidate neck line according to the candidate two-dimensional digital image; and performing error correction processing on the candidate neck line in the three-dimensional digital model to obtain a target neck line. In the embodiments of the present disclosure, the extraction efficiency and accuracy of the tooth preparation body neck line are improved.

Description

Technical Field

[0001] This disclosure relates to the field of three-dimensional digital technology, and in particular to a method, apparatus, equipment and medium for extracting the cervical margin of a dental preparation. Background Technology

[0002] In the field of oral healthcare, the introduction of digital technology has brought about profound changes. Extracting the cervical margin of the tooth preparation is a crucial step in achieving marginal fit in dental restoration. The accuracy of this extraction directly determines the final shape of the restoration. The tooth preparation refers to the anatomical shape of the damaged tooth requiring reconstruction. The cervical margin of the preparation is the outer edge of the restoration model, extracted by the dentist during the initial tooth model preparation stage. It is a closed curve that includes cervical margin features. The fit between the cervical margin of the tooth preparation and the gingiva has a significant impact on patient comfort, oral health, and the success of the restoration.

[0003] In related technologies, key points on the cervical margin of the tooth preparation body are defined sequentially by relevant technicians, and each pair of feature points is connected by algorithms such as the shortest path. The cervical margin is obtained based on the connection results.

[0004] However, the above methods for obtaining the cervical margin not only require the algorithm to be robust, but also require certain skills from the operator, and consume a lot of manual interaction and operation time, which makes it impossible to guarantee the efficiency and accuracy of obtaining the cervical margin of the tooth preparation. Summary of the Invention

[0005] To solve or at least partially solve the above-mentioned technical problems, this disclosure provides a method, apparatus, device, and medium for extracting the cervical margin of a tooth preparation, thereby improving the efficiency and accuracy of extracting the cervical margin of a tooth preparation.

[0006] This disclosure provides a method for extracting the cervical margin line of a dental preparation. The method includes: acquiring a three-dimensional digital model of the dental preparation; acquiring candidate two-dimensional digital images corresponding to the three-dimensional digital model; determining candidate cervical margin lines based on the candidate two-dimensional digital images; and performing error correction processing on the candidate cervical margin lines in the three-dimensional digital model to obtain a target cervical margin line.

[0007] This disclosure also provides a device for extracting the cervical margin line of a dental preparation. The device includes: a first acquisition module for acquiring a three-dimensional digital model of the dental preparation; a second acquisition module for acquiring candidate two-dimensional digital images corresponding to the three-dimensional digital model; a determination module for determining candidate cervical margin lines based on the candidate two-dimensional digital images; and an error correction module for performing error correction processing on the candidate cervical margin lines in the three-dimensional digital model to obtain a target cervical margin line.

[0008] This disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method for extracting the cervical margin of a tooth preparation as provided in this disclosure.

[0009] This disclosure also provides a computer-readable storage medium storing a computer program for performing a method for extracting the cervical margin of a tooth preparation as provided in this disclosure.

[0010] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0011] The cervical margin extraction scheme for tooth preparations provided in this disclosure involves obtaining a three-dimensional digital model of the tooth preparation, acquiring candidate two-dimensional digital images corresponding to the three-dimensional digital model, determining candidate cervical margins based on the candidate two-dimensional digital images, and performing error correction processing on the candidate cervical margins in the three-dimensional digital model to obtain the target cervical margin. In this disclosure, the extraction efficiency and accuracy of cervical margins for tooth preparations are improved. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0013] Figure 1 A schematic flowchart illustrating a method for extracting the cervical margin of a tooth preparation body, provided in an embodiment of this disclosure;

[0014] Figure 2 A schematic diagram illustrating the unfolding of a three-dimensional digital model into a candidate two-dimensional digital image, as provided in an embodiment of this disclosure;

[0015] Figure 3 A schematic diagram of a candidate neckline provided in an embodiment of this disclosure;

[0016] Figure 4A schematic diagram of a three-dimensional digital model provided in an embodiment of this disclosure;

[0017] Figure 5 A schematic diagram of a candidate neckline and a target neckline provided in an embodiment of this disclosure;

[0018] Figure 6 This is a schematic diagram illustrating a scenario for extracting the cervical margin of a tooth preparation body, provided by an embodiment of this disclosure.

[0019] Figure 7 This is a schematic diagram of a device for extracting the cervical margin of a dental preparation, provided in an embodiment of the present disclosure.

[0020] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0021] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0022] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0023] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0024] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] To address the aforementioned issues, this disclosure provides a method for extracting the cervical margin line of a dental preparation. In this method, on one hand, the cervical margin line of the dental preparation is initially determined in a two-dimensional digital image. Since identifying the cervical margin line in a two-dimensional digital image is highly efficient and unaffected by variations in the preparation's diversity or the quality of the mesh surface, the accuracy and efficiency of the cervical margin line extraction are initially guaranteed. On the other hand, the initially determined cervical margin line of the dental preparation is mapped onto a digital three-dimensional model to ensure that the cervical margin line can be further refined within the digital three-dimensional model, thereby obtaining the final refined cervical margin line and ensuring the accuracy of the final extracted cervical margin line.

[0028] The method will be described below with reference to specific embodiments.

[0029] Figure 1 This is a flowchart illustrating a method for extracting the cervical margin of a dental preparation according to an embodiment of this disclosure. This method can be executed by a device for extracting the cervical margin of a dental preparation, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method includes:

[0030] Step 101: Obtain a three-dimensional digital model of the tooth preparation body and obtain the candidate two-dimensional digital image corresponding to the three-dimensional digital model.

[0031] In one embodiment of this disclosure, a three-dimensional digital model of the tooth preparation from which the cervical margin is to be extracted is obtained. In some possible implementations, the target oral cavity can be scanned using a pre-set three-dimensional data scanning device to obtain the three-dimensional digital model of the tooth preparation. This pre-set three-dimensional data scanning device can be a high-precision intraoral scanner, etc. The intraoral scanner uses an insertion optical scanning head to directly scan the patient's oral cavity. Using the principle of structured light triangulation imaging, a light pattern is projected onto the tooth preparation using a digital projection system. After the camera acquisition system acquires the pattern, it is processed by an algorithm to perform three-dimensional reconstruction and stitching to obtain the three-dimensional digital model. The three-dimensional digital model is composed of curved surface patches of multiple triangular meshes.

[0032] Considering that directly extracting the neckline from a 3D digital model may be affected by the geometric characteristics of the 3D digital model, resulting in low robustness of the extraction algorithm and affecting the extraction efficiency and accuracy of the neckline, while recognition algorithms in the 2D domain have relatively high accuracy and strong robustness, therefore, in the embodiments of this disclosure, candidate 2D digital images corresponding to the 3D digital model are obtained.

[0033] In different application scenarios, the methods for unfolding a 3D digital model to obtain candidate 2D digital images vary, as shown in the following examples:

[0034] In some possible examples, the corresponding triangular mesh vertices in the 3D digital model are determined, and candidate 2D digital images are obtained based on the mesh vertices.

[0035] For example, the first two-dimensional pixel point corresponding to each grid vertex in the three-dimensional digital model can be determined according to the first preset algorithm. The first preset algorithm includes, but is not limited to, Least Square Conformal Maps (LSCM). The LSCM algorithm can ensure that the local scale and feature information can be preserved as much as possible after the three-dimensional grid is transformed into a two-dimensional plane. Based on the LSCM algorithm, the first two-dimensional pixel point (u, v) of each grid vertex (x, y, z) on the two-dimensional plane can be obtained.

[0036] Since the three-dimensional digital model contains not only the vertices of the triangular mesh but also the three-dimensional points inside the triangles, in the embodiments of this disclosure, the first curvature value of each mesh vertex is also obtained. The second two-dimensional pixel point corresponding to the internal feature point of each triangular mesh in the three-dimensional digital model is determined according to the preset interpolation algorithm and the curvature value. That is, the curvature information on the vertices of the three-dimensional mesh is converted into the two-dimensional RGB space (0-255), and the pixel value of each second two-dimensional pixel point on the two-dimensional plane is assigned by the interpolation method corresponding to the preset interpolation algorithm, thus forming a candidate two-dimensional digital image.

[0037] In one embodiment of this disclosure, a corresponding candidate two-dimensional digital image is generated based on a three-dimensional digital model through mesh parameterization. Specifically, the first preset algorithm is mesh parameterization, and preferably, least-squares conformal parameterization is used.

[0038] For example, such as Figure 2 As shown, through the aforementioned mesh parameterization and other first preset algorithms, the 3D digital model can be unfolded to obtain the corresponding candidate 2D digital image. The 2D pixels in the candidate 2D digital image correspond to the corresponding 3D model points in the 3D digital model. That is, while generating the corresponding candidate 2D digital image through mesh parameterization of the 3D digital model, a mapping relationship is formed between the 2D pixels in the candidate 2D digital image and the 3D model points in the 3D digital model. A 2D pixel in the candidate 2D digital image can be used to determine a corresponding 3D model point in the 3D digital model, and vice versa.

[0039] In some possible examples, the coordinate transformation relationship between the three-dimensional model points in the three-dimensional digital model and the two-dimensional pixel points in the candidate two-dimensional digital image can be predetermined. For example, multiple sets of sample data can be pre-constructed, each set of sample data containing a sample three-dimensional digital model and a sample two-dimensional digital image corresponding to the sample three-dimensional digital model. Multiple reference pixels in each sample two-dimensional digital image can be obtained, and multiple reference three-dimensional points matching the multiple reference pixels can be determined in the corresponding sample three-dimensional digital model. The reference pixels and the corresponding reference three-dimensional points belong to the same point on the tooth. The matching method of multiple reference pixels and reference three-dimensional points can be implemented according to feature matching algorithms, etc.

[0040] Then, the two-dimensional coordinates of each reference pixel and the three-dimensional coordinates of the corresponding reference three-dimensional point are obtained, and the coordinate transformation relationship is determined based on the two-dimensional coordinates and the three-dimensional coordinates.

[0041] In this example, based on this coordinate transformation relationship, the two-dimensional pixels corresponding to the three-dimensional coordinates of the three-dimensional digital model can be determined, thereby obtaining a candidate two-dimensional digital image composed of two-dimensional pixels.

[0042] Step 102: Determine the candidate neckline based on the candidate two-dimensional digital image.

[0043] In one embodiment of this disclosure, candidate neckline is determined based on candidate two-dimensional digital images. As such, since the relevant algorithm for determining candidate neckline from candidate two-dimensional digital images is robust, the extracted candidate neckline has high efficiency and accuracy.

[0044] In some alternative implementations, a deep learning model can be trained based on a large amount of sample data, including two-dimensional digital images and manually labeled neckline regions. The specific training process involves inputting an unlabeled two-dimensional digital image of the neckline region into the deep learning model, outputting a neckline region mask. This mask is then compared with manually labeled neckline regions to calculate a loss function. The deep learning model is then optimized using backpropagation. This process is iterated until the loss function no longer decreases, indicating model convergence. The trained deep learning model is then obtained. Inputting candidate two-dimensional digital images into the pre-trained deep learning model outputs the "predicted" neckline region, thus determining the candidate neckline. Figure 3 Taking the scenario shown as an example, we can... Figure 2 After the obtained candidate two-dimensional digital images are input into a pre-trained deep learning model, the candidate neckline output by the model is quickly obtained.

[0045] Furthermore, considering that the candidate two-dimensional digital image may not completely correspond to the three-dimensional digital model, for example, if the second two-dimensional pixel in the three-dimensional digital model is calculated by interpolating the first curvature value of each grid vertex according to the preset interpolation algorithm, the second two-dimensional pixel may have a certain error, and the obtained candidate neckline may have an error. Therefore, in order to further refine the candidate neckline, the candidate neckline can also be determined in the three-dimensional digital model, so as to further refine the candidate neckline in the three-dimensional digital model.

[0046] It should be noted that the methods for determining the two-dimensional candidate neckline in the three-dimensional digital model differ in different application scenarios, as shown in the following examples:

[0047] In some possible embodiments, candidate neckline lines are marked in a candidate 2D digital image to obtain a marked target 2D digital image. The candidate neckline lines in the target 2D digital image are 2D candidate neckline lines. The target 2D digital image is then reprojected onto a 3D digital model to determine the candidate neckline line corresponding to the aforementioned 2D candidate neckline line in the 3D digital model. The candidate neckline line in the 3D digital model is a 3D candidate neckline line. Reprojection involves determining the corresponding 3D candidate neckline line in the 3D digital model based on the 2D candidate neckline line in the target 2D digital image. It should be noted that the target 2D digital image is a candidate 2D digital image with determined 2D candidate neckline lines. The mapping relationship between the 2D pixels in the candidate 2D digital image and the 3D model points in the 3D digital model is also the mapping relationship between the 2D pixels in the target 2D digital image and the 3D model points in the 3D digital model. Based on this mapping relationship, the 3D candidate neckline line corresponding to the 2D candidate neckline line in the target 2D digital image can naturally be determined in the 3D digital model. In this embodiment, the two-dimensional candidate neckline is composed of multiple two-dimensional pixels corresponding to the candidate neckline in the two-dimensional digital image, and the three-dimensional candidate neckline is composed of multiple three-dimensional model points corresponding to the three-dimensional candidate neckline in the three-dimensional digital model. The reprojection in this embodiment can also be implemented using any existing reprojection algorithm, including but not limited to raster reprojection algorithms.

[0048] When reprojecting a target two-dimensional digital image onto a three-dimensional digital model, the mapping relationship between two-dimensional pixels in the target two-dimensional digital image and corresponding three-dimensional model points in the three-dimensional digital model is determined. This mapping relationship describes the correspondence between two-dimensional pixels of the same point on the tooth preparation body and three-dimensional model points. For example, this mapping relationship can describe the coordinate transformation relationship between two-dimensional pixels of the same point on the tooth preparation body and three-dimensional model points.

[0049] Furthermore, based on the mapping relationship, the first three-dimensional point corresponding to each two-dimensional point in the two-dimensional candidate neckline is determined in the three-dimensional digital model. For example, a sampling two-dimensional point can be determined in the two-dimensional candidate neckline using a random sampling algorithm, and the first three-dimensional point corresponding to the sampling two-dimensional point can be determined according to the mapping relationship. Alternatively, the first three-dimensional point corresponding to each two-dimensional point in the two-dimensional candidate neckline can be determined in the three-dimensional digital model according to the mapping relationship. Then, the candidate neckline in the three-dimensional digital model is obtained based on the first three-dimensional point.

[0050] It is important to emphasize that the purpose of determining the 3D candidate cervical margin line corresponding to the 2D candidate cervical margin line in the 3D digital model is to determine the position of the candidate cervical margin line in the 3D digital model, facilitating further refinement of the candidate cervical margin line within the 3D digital model. The determination of the 3D candidate cervical margin line corresponding to the 2D candidate cervical margin line in the 3D digital model can be non-visual or visual. In some possible implementations, to improve the intuitiveness of obtaining the cervical margin line of the tooth preparation, the 3D candidate cervical margin line corresponding to the 2D candidate cervical margin line will be displayed visually, for example, as shown below. Figure 4 As shown, a three-dimensional digital model is displayed, and the corresponding candidate neckline is displayed in the three-dimensional digital model.

[0051] Step 103: Perform error correction processing on the candidate neckline in the three-dimensional digital model to obtain the target neckline.

[0052] In one embodiment of this disclosure, after obtaining a three-dimensional digital model, error correction processing is performed on candidate neckline lines within the three-dimensional digital model to obtain the target neckline line, wherein, as... Figure 5 As shown, the target neckline corrects the error of the candidate neckline, ensuring the accuracy of the obtained target neckline.

[0053] It should be noted that the methods for error correction processing of candidate necklines in 3D digital models to obtain the target neckline differ in different application scenarios, as shown in the following examples:

[0054] In some possible embodiments, the logic of algorithms such as random walk algorithms can be used for error correction. In this embodiment, the known and unknown regions in the three-dimensional digital model are determined based on the candidate neckline. The known region in this embodiment can be understood as the region composed of three-dimensional points that do not belong to the neckline, typically located in the cusp region (e.g., Figure 6 The upper half of the tooth preparation body shown), the unknown region is understood as the region consisting of three-dimensional points that may belong to the candidate cervical margin and their nearby three-dimensional points (e.g. Figure 6 (The candidate neckline and its surrounding area are shown).

[0055] In some possible embodiments, in the three-dimensional digital model, associated three-dimensional points of the second three-dimensional point in the candidate cervical margin are determined. For example, associated three-dimensional points of the sampled second three-dimensional point in the candidate cervical margin are determined, or associated three-dimensional points of each second three-dimensional point in the candidate cervical margin are determined. The associated three-dimensional point can be understood as a three-dimensional point in the three-dimensional digital model whose distance from the corresponding second three-dimensional point in the candidate cervical margin is less than a preset distance threshold. The preset distance threshold can be calibrated based on experimental data. In this embodiment, the region corresponding to the second two-dimensional point and the associated three-dimensional point is determined as an unknown region. That is, in this embodiment, the candidate cervical margin and its surrounding area can be considered as an unknown region by using a preset distance. In this embodiment, to ensure the accuracy of the unknown region determination, the major axis of the tooth in the three-dimensional digital model of the tooth preparation is parallel to the Z-axis of the coordinate system (it should be emphasized that parallelism here can be understood as the direction of the central axis of the major axis of the tooth being parallel to the Z-axis; visually, the major axis of the tooth can be approximately parallel to the Z-axis). The direction from the root to the crown in the three-dimensional digital model of the tooth preparation is the positive direction of the Z-axis. It should be noted that in this disclosure, the first three-dimensional point, the second three-dimensional point, and the three-dimensional model point are all three-dimensional points in the three-dimensional digital model that contain three-dimensional coordinate information.

[0056] Furthermore, in this embodiment, according to the second preset algorithm, the second curvature value of the sampled grid points in the three-dimensional digital model is traversed in the direction from the determined area to the unknown area. The sampled grid point can be understood as any three-dimensional point on the target tooth model. The second preset algorithm can be the random walk algorithm mentioned above, etc.

[0057] The target sampling grid points that satisfy the preset convergence conditions corresponding to the preset second preset algorithm are determined based on the second curvature value. When the second preset algorithm is a random walk algorithm, the walking logic of the random walk algorithm is as follows: start from one or a series of vertices and traverse a graph. At any vertex, the traverser will walk to the neighboring vertex of this vertex with probability 1-a, and randomly jump to any vertex in the graph with probability a (the vertices to which they jump can be understood as the sampling grid points mentioned above). a is called the jump probability. After each walk, a probability distribution is obtained. This probability distribution describes the probability of each vertex in the graph being visited. This probability distribution is used as the input for the next walk and this process is iterated repeatedly. When the preset convergence conditions are met, this probability distribution will tend to converge.

[0058] In this embodiment, considering that the second curvature value of the sampling grid point on the neckline is greater than the curvature value of the sampling grid point on the non-neckline, the convergence condition in this embodiment corresponds to the inability to walk near the neckline to accurately determine the target sampling grid point on the corresponding target neckline. In this embodiment, the preset convergence condition can be that the second curvature value of the current sampling grid point is greater than the curvature value of the previous adjacent sampling grid point, and the second curvature value of the current sampling grid point is greater than the curvature value of the next adjacent sampling grid point, etc. That is, if the second curvature value of the current sampling grid point is greater than that of the adjacent sampling grid points, then the preset convergence condition is considered to be met, and the random walk is stopped to determine the corresponding current sampling grid point as the target sampling grid point.

[0059] In actual execution, to further ensure that the acquired target sampling grid points belong to the neckline, when traversing the second curvature values ​​of the sampling grid points in the 3D digital model according to the second preset algorithm, the second curvature values ​​of the sampling grid points with larger second curvature values ​​can be further increased. For example, the initial curvature values ​​of grid points in unknown regions can be identified, and it can be determined whether the initial curvature values ​​are greater than or equal to a preset curvature threshold (where the preset curvature threshold can be set according to the needs of the scenario). If it is greater than the preset curvature threshold, the weight of the initial curvature value is increased. For example, the initial curvature values ​​greater than the preset curvature threshold are multiplied by a preset weight value greater than 1 to obtain the increased curvature value. Thus, it can be further ensured that when the random walk algorithm reaches the target sampling grid point, it can stop walking, thus ensuring the accuracy of the target sampling grid point.

[0060] Furthermore, after determining the target sampling grid points, the target sampling grid points are fitted to obtain the target neckline. The fitting algorithm for fitting the target sampling grid points includes, but is not limited to, Bézier curve fitting and 3D B-spline fitting. In some possible embodiments, to avoid the obtained target neckline being insufficiently smooth, a smoothing method can be used to process the target sampling grid points to obtain the target neckline. That is, after fitting the target sampling grid points to obtain a fitting curve according to a preset fitting algorithm, the fitting curve is sampled to obtain multiple sampling 3D points. These sampling 3D points can be obtained using any random sampling algorithm. Then, the corresponding target neckline is obtained based on these multiple sampling 3D points. In this embodiment, a smoother target neckline is obtained by resampling and fitting the fitting curve.

[0061] In some possible embodiments, since the curvature values ​​near the neckline are significantly larger, after determining the candidate neckline, the third curvature value of the candidate neckline 3D point belonging to the triangle mesh vertex in each candidate neckline is also determined, and the fourth curvature value of the other adjacent 3D mesh vertices on the triangle mesh where each candidate neckline 3D point is located is determined. If the third curvature value is greater than the fourth curvature value of all its adjacent 3D mesh points, then the corresponding candidate neckline 3D point is determined as the target neckline 3D point on the target neckline. If the third curvature value is not greater than the fourth curvature value of the other adjacent 3D mesh vertices, then the largest fourth curvature value among the fourth curvature values ​​of the other adjacent 3D mesh vertices is determined, and the comparison continues. The fourth curvature value is compared with the fifth curvature values ​​of other adjacent 3D mesh vertices on the triangular mesh containing it. If the fourth curvature value is greater than the fifth curvature values ​​of all the other adjacent 3D mesh vertices, then the 3D mesh vertex corresponding to the fourth curvature value is determined as a target neckline 3D point on the target neckline. If the fourth curvature value is not greater than the fifth curvature values ​​of the other adjacent 3D mesh vertices, then the largest fifth curvature value among the fifth curvature values ​​of the other adjacent 3D mesh vertices is determined. The sixth curvature value of the other adjacent 3D mesh vertices on the triangular mesh containing the largest fifth curvature value is then compared, and so on, to determine multiple target neckline 3D points on the target neckline. The target neckline is then determined based on the target neckline 3D points.

[0062] In summary, the method for extracting the cervical margin of a tooth preparation according to the embodiments of this disclosure obtains a three-dimensional digital model of the tooth preparation, acquires candidate two-dimensional digital images corresponding to the three-dimensional digital model, then determines candidate cervical margins based on the candidate two-dimensional digital images, and performs error correction processing on the candidate cervical margins in the three-dimensional digital model to obtain the target cervical margin. In the embodiments of this disclosure, the extraction efficiency and accuracy of the cervical margin of the tooth preparation are improved.

[0063] To achieve the above embodiments, this disclosure also proposes a device for extracting the cervical margin of a dental preparation.

[0064] Figure 7 This is a schematic diagram of a device for extracting the cervical margin of a dental preparation according to an embodiment of this disclosure. This device can be implemented by software and / or hardware, and is generally integrated into an electronic device for extracting the cervical margin of a dental preparation. Figure 7 As shown, the device includes: a first acquisition module 710, a second acquisition module 720, a determination module 730, and an error correction module 740, wherein,

[0065] The first acquisition module 710 is used to acquire a three-dimensional digital model of the tooth preparation body;

[0066] The second acquisition module 720 is used to acquire candidate two-dimensional digital images corresponding to the three-dimensional digital model;

[0067] Determining module 730 is used to determine candidate neckline based on candidate two-dimensional digital images.

[0068] Error correction module 740 is used to perform error correction processing on candidate necklines in a three-dimensional digital model to obtain the target neckline.

[0069] The device for extracting the cervical margin of a dental preparation provided in this embodiment can perform the method for extracting the cervical margin of a dental preparation provided in any embodiment of this disclosure. It has the corresponding functional modules and beneficial effects for performing the method. The implementation principle is similar and will not be described again here.

[0070] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instructions, which, when executed by a processor, implements the method for extracting the cervical margin of the tooth preparation body in the above embodiments.

[0071] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0072] The following is a detailed reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing the electronic device 800 in the embodiments of this disclosure. The electronic device 800 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, 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 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0073] like Figure 8 As shown, the electronic device 800 may include a processor (e.g., a central processing unit, a graphics processor, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a memory 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device 800. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0074] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 800 with various devices is shown; however, 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 alternatively.

[0075] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a memory 808, or installed from a ROM 802. When the computer program is executed by the processor 801, it performs the functions defined in the method for extracting the cervical margin of a tooth preparation according to embodiments of this disclosure.

[0076] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0077] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0078] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0079] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0080] A three-dimensional digital model of the prepared tooth is obtained, and candidate two-dimensional digital images corresponding to the three-dimensional digital model are acquired. Then, candidate cervical margin lines are determined based on the candidate two-dimensional digital images. Error correction processing is performed on the candidate cervical margin lines in the three-dimensional digital model to obtain the target cervical margin line. In the embodiments of this disclosure, the extraction efficiency and accuracy of the cervical margin line of the prepared tooth are improved.

[0081] Electronic devices can be programmed with computer program code in one or more programming languages ​​or combinations thereof to perform the operations of this disclosure. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0083] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0084] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0085] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0086] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0087] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0088] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for extracting the cervical margin of a prepared tooth, characterized in that, Includes the following steps: A three-dimensional digital model of the tooth preparation body is obtained, and a candidate two-dimensional digital image corresponding to the three-dimensional digital model is obtained, wherein the three-dimensional digital model of the tooth preparation body is obtained by scanning the target oral cavity using a preset three-dimensional data scanning device; Candidate neckline lines are determined based on the candidate two-dimensional digital images; In the three-dimensional digital model, the candidate neckline is subjected to error correction processing to obtain the target neckline; The step of performing error correction processing on the candidate neckline in the three-dimensional digital model to obtain the target neckline includes: The defined and unknown regions in the three-dimensional digital model are determined based on the candidate neckline; According to the second preset algorithm, the second curvature value of the sampling grid points in the unknown region is traversed in the direction from the determined region to the unknown region; Based on the second curvature value, determine the target sampling grid points that satisfy the preset convergence conditions corresponding to the second preset algorithm; The target sampling grid points are fitted to obtain the target neckline.

2. The method as described in claim 1, characterized in that, The step of obtaining the candidate two-dimensional digital image corresponding to the three-dimensional digital model includes: Determine the vertices of the triangular mesh in the three-dimensional digital model; The candidate two-dimensional digital image is obtained based on the grid vertices.

3. The method as described in claim 2, characterized in that, The step of obtaining the candidate two-dimensional digital image based on the grid vertices includes: The first two-dimensional pixel point corresponding to the grid vertex is determined according to the first preset algorithm; Obtain the first curvature value of the mesh vertex, and determine the second two-dimensional pixel point corresponding to the internal feature point of the triangular mesh in the three-dimensional digital model according to the preset interpolation algorithm and the curvature value; The candidate two-dimensional digital image is obtained based on the first two-dimensional pixel and the second two-dimensional pixel.

4. The method as described in claim 1, characterized in that, The step of obtaining the candidate two-dimensional digital image corresponding to the three-dimensional digital model includes: Based on the three-dimensional digital model, mesh parameterization is performed to generate corresponding candidate two-dimensional digital images.

5. The method as described in claim 1, characterized in that, The step of determining the candidate neckline based on the candidate two-dimensional digital image includes: The candidate two-dimensional digital image is input into a pre-trained deep learning model, and the candidate neckline is determined based on the output of the deep learning model.

6. The method as described in claim 1, characterized in that, Before performing error correction processing on the candidate neckline in the three-dimensional digital model to obtain the target neckline, the method further includes: Two-dimensional candidate neckline lines are determined in the candidate two-dimensional digital images to obtain the target two-dimensional digital image; The target two-dimensional digital image is reprojected into the three-dimensional digital model, and the candidate neckline corresponding to the two-dimensional candidate neckline is determined in the three-dimensional digital model. The candidate neckline is a three-dimensional candidate neckline.

7. The method as described in claim 6, characterized in that, The step of reprojecting the target two-dimensional digital image onto the three-dimensional digital model, and determining the candidate neckline corresponding to the two-dimensional candidate neckline in the three-dimensional digital model, includes: Determine the mapping relationship between two-dimensional pixels in the target two-dimensional digital image and corresponding three-dimensional model points in the three-dimensional digital model; Based on the mapping relationship, determine the first three-dimensional point corresponding to the two-dimensional point in the three-dimensional candidate neckline in the three-dimensional digital model, and obtain the candidate neckline based on the first three-dimensional point.

8. The method as described in claim 1, characterized in that, The step of determining the known and unknown regions in the three-dimensional digital model based on the candidate neckline includes: In the three-dimensional digital model, an associated three-dimensional point of the second three-dimensional point in the candidate neckline is determined, wherein the distance between the associated three-dimensional point and the corresponding second three-dimensional point in the candidate neckline is less than a preset distance threshold; The region corresponding to the second 3D point and the associated 3D point is determined as the unknown region; The region located above the unknown region in the three-dimensional digital model is defined as the defined region, wherein the Z-axis of the coordinate system of the three-dimensional digital model of the tooth preparation is parallel to the long axis of the tooth in the three-dimensional digital model of the tooth preparation, and the direction from the root to the crown in the three-dimensional digital model of the tooth preparation is the positive direction of the Z-axis.

9. The method as described in claim 1, characterized in that, The preset convergence conditions include: The second curvature value of the current sampling grid point is greater than the curvature value of the previous adjacent sampling grid point, and the second curvature value of the current sampling grid point is greater than the curvature value of the next adjacent sampling grid point.

10. The method as described in claim 1, characterized in that, The process of fitting the target sampling grid points to obtain the target neckline includes: A fitting curve is obtained by fitting the target sampling grid points according to a preset fitting algorithm; The fitted curve is sampled to obtain multiple sampled three-dimensional points, and the target neckline is obtained based on the multiple sampled three-dimensional points.

11. The method as described in claim 1, characterized in that, Before sampling the second curvature value of the grid points in the unknown region of the three-dimensional digital model, the method further includes: Identify the initial curvature values ​​of grid points in the unknown region, and determine candidate grid points whose initial curvature values ​​are greater than a preset curvature threshold; Calculate the product of the preset weight and the initial curvature value of the candidate grid point, and update the curvature value of the candidate grid point according to the product value, wherein the preset weight is greater than 1.

12. A device for extracting the cervical margin of a tooth preparation body, characterized in that, include: The first acquisition module is used to acquire a three-dimensional digital model of the tooth preparation body, wherein the three-dimensional digital model of the tooth preparation body is acquired by scanning the target oral cavity using a preset three-dimensional data scanning device; The second acquisition module is used to acquire candidate two-dimensional digital images corresponding to the three-dimensional digital model; The determination module is used to determine candidate neckline lines based on the candidate two-dimensional digital images. An error correction module is used to perform error correction processing on the candidate neckline in the three-dimensional digital model to obtain the target neckline. The step of performing error correction processing on the candidate neckline in the three-dimensional digital model to obtain the target neckline includes: The defined and unknown regions in the three-dimensional digital model are determined based on the candidate neckline; According to the second preset algorithm, the second curvature value of the sampling grid points in the unknown region is traversed in the direction from the determined region to the unknown region; Based on the second curvature value, determine the target sampling grid points that satisfy the preset convergence conditions corresponding to the second preset algorithm; The target sampling grid points are fitted to obtain the target neckline.

13. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for extracting the cervical margin of the tooth preparation body as described in any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for performing the method for extracting the cervical margin of a tooth preparation as described in any one of claims 1-11.

Images