Method, device and computer equipment for generating dental arch line image

Abstract

The present application provides a method, device, and computer equipment for generating a dental arch line image. The method includes: converting a three-dimensional tooth model into a binary image, and obtaining a single-layer target image in DICOM format corresponding to the three-dimensional tooth model; determining the centroid coordinates corresponding to each tooth based on the binary image; converting each centroid coordinate into the corresponding target coordinates in the target image; fitting the coordinate points corresponding to each target coordinate into a target dental arch line through an interpolation spline curve algorithm; and fusing the target dental arch line with the target image into a dental arch line image. The present application determines the centroid coordinates corresponding to each tooth through a binary image, and converts each centroid coordinate into the corresponding target coordinates in a single-layer target image in DICOM format. This can accurately and quickly generate a target dental arch line to generate a dental arch line image.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, device and computer equipment for generating dental arch line images. Background Art

[0002] With the development of dental medical technology, the demand for dental care, such as dental implants, orthodontics, and oral disease diagnosis, is also expanding, and the requirements for dentists' experience and skills are also constantly increasing. In recent years, with the development of deep learning technology, the introduction of artificial intelligence in the medical field can greatly improve medical efficiency.

[0003] In dental treatment, Cone Beam Computed Tomography (CBCT) is often used to obtain oral information about the patient. To better observe the patient's oral condition, the CBCT images need to be expanded into panoramic films, which require precise dental arch lines.

[0004] The traditional method of obtaining the dental arch line requires the doctor to manually mark the dental arch line. This method is time-consuming and labor-intensive, difficult to ensure accuracy, and has low diagnostic efficiency. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a method, device and computer equipment for generating dental arch line images. The specific solutions are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for generating a dental arch line image, the method comprising:

[0007] Converting the three-dimensional tooth model into a binary image, and obtaining a single-layer target image in DICOM format corresponding to the three-dimensional tooth model;

[0008] Determining the centroid coordinates corresponding to each tooth based on the binary image;

[0009] Converting each of the centroid coordinates into corresponding target coordinates in the target image;

[0010] Fitting the coordinate points corresponding to the target coordinates into a target dental arch line by using an interpolation spline curve algorithm;

[0011] The target dental arch line and the target image are fused into a dental arch line image.

[0012] According to a specific embodiment disclosed in the present application, the step of generating the three-dimensional tooth model includes:

[0013] Acquire an original cone-beam CT image corresponding to the oral cavity, wherein the original cone-beam CT image includes multi-layer first sub-images;

[0014] Preprocessing the original cone-beam CT image through a two-dimensional convolutional network to obtain a basic oral image, wherein the number of filters in the two-dimensional convolutional network is the same as the number of layers of the first sub-image;

[0015] The basic oral cavity image is input into a pre-trained tooth extraction model to obtain the three-dimensional tooth model.

[0016] According to a specific embodiment disclosed in the present application, the step of obtaining a single-layer target image in DICOM format corresponding to the three-dimensional tooth model includes:

[0017] Selecting a basic cone-beam CT image corresponding to the three-dimensional tooth model in the original cone-beam CT image, wherein the basic cone-beam CT image includes multiple layers of second sub-images;

[0018] The second sub-images of each layer are fused into a target image in DICOM format by the maximum intensity projection method.

[0019] According to a specific embodiment disclosed in the present application, the step of determining the centroid coordinates corresponding to each tooth based on the binary image includes:

[0020] Determining a pixel point set corresponding to each tooth based on the binary image;

[0021] According to the formula as well as Calculate the coordinates of the center of mass of each tooth, where c x is the x-axis coordinate of the center of mass, c y is the y-axis coordinate of the center of mass, T 00 is the sum of the pixel values corresponding to all the pixels in the pixel set, T 01 is the product of the horizontal coordinate and the corresponding pixel value in the pixel point set, T 10 It is the product of the vertical coordinate and the corresponding pixel values in the pixel point set.

[0022] According to a specific embodiment disclosed in the present application, the step of determining a set of pixel points corresponding to each tooth based on the binary image includes:

[0023] Determining closed pixel contour lines based on the grayscale value of each pixel in the binary image;

[0024] Determine whether the area of the first closed region corresponding to each closed pixel contour line is greater than a threshold;

[0025] If the area of any of the first closed regions is greater than a threshold, corroding the closed region to obtain at least two second closed regions with areas smaller than the threshold, and determining the number of the first closed regions and the second closed regions with areas smaller than the threshold as the number of teeth;

[0026] If the area of each of the first closed regions is less than or equal to the threshold, determining the number of the first closed regions as the number of teeth;

[0027] All pixel points in the first closed region and the second closed region whose areas are smaller than the threshold are determined as pixel point sets corresponding to the teeth.

[0028] According to a specific embodiment disclosed in the present application, the step of converting each of the centroid coordinates into corresponding target coordinates in the target image includes:

[0029] Obtaining a pixel interval value corresponding to the target image;

[0030] The target coordinates corresponding to each center of mass coordinate in the target image are obtained by summing the pixel interval value, the center of mass coordinate corresponding to each tooth, and the preset origin coordinates of the target image.

[0031] In a second aspect, an embodiment of the present application provides a device for generating a dental arch line image, the device comprising:

[0032] An image acquisition module, configured to convert a three-dimensional tooth model into a binary image and acquire a single-layer target image in DICOM format corresponding to the three-dimensional tooth model;

[0033] A coordinate calculation module, configured to determine the centroid coordinates corresponding to each tooth based on the binary image;

[0034] A coordinate conversion module, used for converting each of the centroid coordinates into corresponding target coordinates in the target image;

[0035] A curve fitting module, used for fitting the coordinate points corresponding to the target coordinates into a target dental arch line through an interpolation spline curve algorithm;

[0036] An image fusion module is used to fuse the target dental arch line and the target image into a dental arch line image.

[0037] According to a specific embodiment disclosed in this application, the coordinate conversion module is specifically applied to:

[0038] Obtaining a pixel interval value corresponding to the target image;

[0039] The target coordinates corresponding to each center of mass coordinate in the target image are obtained by summing the pixel interval value, the center of mass coordinate corresponding to each tooth, and the preset origin coordinates of the target image.

[0040] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed on the processor, the method for generating a dental arch line image as described in any embodiment of the first aspect is implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed on a processor, the method for generating a dental arch line image as described in any embodiment of the first aspect is implemented.

[0042] Compared with the prior art, this application has the following beneficial effects:

[0043] This application converts a three-dimensional dental model into a binary image and obtains a single-layer target image in DICOM format corresponding to the three-dimensional dental model; determines the centroid coordinates corresponding to each tooth based on the binary image; converts each centroid coordinate into the corresponding target coordinates in the target image; fits the coordinate points corresponding to each target coordinate into a target dental arch line through an interpolation spline curve algorithm; and fuses the target dental arch line with the target image into a dental arch line image. By determining the centroid coordinates corresponding to each tooth through a binary image and converting each centroid coordinate into the corresponding target coordinates in a single-layer target image in DICOM format, a target dental arch line can be accurately and quickly generated to generate a dental arch line image. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope of protection of the present invention. In each of the drawings, similar components are numbered similarly.

[0045] Figure 1 A schematic diagram of a process for generating a dental arch line image provided in an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a three-dimensional tooth model involved in a method for generating a dental arch line image provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of a binary image involved in a method for generating a dental arch line image provided in an embodiment of the present application;

[0048] Figure 4A schematic diagram of the composition of a CBCT image involved in a method for generating a dental arch line image provided in an embodiment of the present application;

[0049] Figure 5 A schematic diagram of an etching process involved in a method for generating a dental arch line image provided in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of a dental arch line image involved in a method for generating a dental arch line image provided in an embodiment of the present application;

[0051] Figure 7 This is a module block diagram of a dental arch line image generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0053] The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the figures is not intended to limit the scope of the claimed invention, but rather merely represents selected embodiments of the present invention. All other embodiments derived by those skilled in the art based on the embodiments of the present invention without inventive effort are intended to be within the scope of protection of the present invention.

[0054] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present invention, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0055] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0056] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present invention pertain. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present invention.

[0057] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0058] The method for generating a dental arch line image provided in this application can be divided into the following steps:

[0059] 1. Use a segmentation network to segment the lower teeth data and / or upper teeth data in the oral image;

[0060] 2. Perform edge detection on the segmented lower tooth data and / or upper tooth data and find the centroid coordinates of each tooth;

[0061] 3. Input the coordinate points corresponding to all the centroid coordinates into the target image in DICOM format, and fit the coordinate points on the target image into a spline curve to obtain the target dental arch line to generate a dental arch line image.

[0062] See also Figure 1 , Figure 1 This is a flow chart of a method for generating a dental arch line image provided in an embodiment of the present application. Figure 1 As shown, the method for generating the dental arch line image mainly includes:

[0063] Step S101 : converting a three-dimensional tooth model into a binary image, and acquiring a single-layer target image in DICOM format corresponding to the three-dimensional tooth model.

[0064] Usually, when performing oral medical diagnosis, a CBCT image corresponding to the patient's oral cavity is obtained. Such a CBCT image not only contains the upper teeth image or lower teeth image required for generating the dental arch line, but also includes other non-tooth images that are not needed. Therefore, a segmentation network can be used to segment the lower teeth data in the oral image. Among them, the lower teeth data and / or upper teeth data can be displayed through different types of images or models, including but not limited to three-dimensional tooth models. In specific implementation, the three-dimensional tooth model can be rotated at different angles to obtain different views suitable for subsequent analysis.

[0065] See also Figure 2 , Figure 2A schematic diagram of a three-dimensional tooth model involved in a method for generating a dental arch line image provided in an embodiment of the present application. Stereo lithography (STL) is a three-dimensional graphic file format. An STL file consists of the definition of multiple triangular facets, and the definition of each triangular facet includes the three-dimensional coordinates of each fixed point of the triangle and the normal vector of the triangular facet. During specific implementation, other three-dimensional graphic file formats can be used to display the three-dimensional tooth model according to the user's actual usage needs and specific application scenarios, which are not specifically limited here.

[0066] Since it is necessary to find the centroid coordinates of each tooth, searching directly on the 3D image corresponding to the 3D tooth model will greatly increase the amount of calculation, and the resulting dental arch lines are often on the same plane. Therefore, the 3D tooth model can be converted into a binary image and then the centroid is found. Figure 3 , Figure 3 A schematic diagram of a binary image involved in a method for generating a dental arch line image provided in an embodiment of the present application.

[0067] The Digital Imaging and Communications in Medicine (DICOM) format is an international standard (ISO 12052) for medical images and related information. DICOM is widely used in radiology, cardiovascular imaging, and radiological diagnostic equipment, including but not limited to X-rays, CT, MRI, and ultrasound, and is increasingly being used in other medical fields such as ophthalmology and dentistry. In the field of oral medicine, medical images of patients are usually stored in the DICOM file format. This format contains relevant information about the patient, such as name, gender, age, and other image-related information, such as information about the equipment that captured and generated the image. Doctors can use a DICOM reader to easily read medical images and diagnose problems found in medical images.

[0068] See also Figure 4 , Figure 4 A schematic diagram of the composition of a CBCT image used in a method for generating a dental arch line image according to an embodiment of the present application. During CBCT image acquisition, a highly sensitive detector performs continuous cross-sectional scans around a specific part of the human body. The resulting CBCT image is a multi-layer image. Stacking these multi-layer CBCT images along the Z axis creates a three-dimensional image. Each layer of the CBCT image can be saved in DICOM format.

[0069] The step of generating the three-dimensional tooth model comprises:

[0070] Acquire an original cone-beam CT image corresponding to the oral cavity, wherein the original cone-beam CT image includes multi-layer first sub-images;

[0071] Preprocessing the original cone-beam CT image through a two-dimensional convolutional network to obtain a basic oral image, wherein the number of filters in the two-dimensional convolutional network is the same as the number of layers of the first sub-image;

[0072] The basic oral cavity image is input into a pre-trained tooth extraction model to obtain the three-dimensional tooth model.

[0073] In practice, a segmentation network can be used to segment the lower or upper teeth to create a 3D tooth model. Since CBCT image data is a 3D slice sequence, typically sized at 640 x 640 x 400, the data volume is too large. Directly using a 3D convolutional network can cause GPU memory overflow. Directly converting CBCT images to JPGs lacks spatial information, resulting in inaccurate tooth segmentation data.

[0074] Therefore, to ensure that spatial information is not lost and that video memory overflows due to excessive data volume are avoided, a two-dimensional convolutional network can be used to preprocess the raw cone-beam CT images to obtain basic oral images. Specifically, when using a two-dimensional convolutional network, the filters in the network are treated as the number of layers in the CBCT image. For example, the input is fixed to Conv2D(640,640,400). Here, 640 is the tensor, which matches the size of a single CBCT image; 400 is the filter, which matches the number of CBCT layers. This preprocessing effectively processes the three-dimensional data as two-dimensional data while simultaneously achieving the technical effect of preserving significant spatial information. The deconvolution output also outputs the filters as the number of layers in the two-dimensional matrix. The remaining structure is essentially the same as the Unet network and will not be elaborated on here.

[0075] The training process of the tooth extraction model is illustrated using an example of mandibular teeth. For any amount of CBCT data, Minics software can be used to manually segment the mandibular teeth as label data. A data generator can be used to address the technical issue of large data volumes. Specifically, the data generator's batch size can be set to 4, meaning that the next batch of data is generated only after every four batches of data are fed into training. This eliminates the problem of storing all training data in memory and causing memory overflow. Compared to directly using a 3D convolutional network, this approach can reduce the time required for a single inference by half.

[0076] Step S102: determining the centroid coordinates corresponding to each tooth based on the binary image.

[0077] See also Figure 3 Each tooth in a binary image is discrete and, in image processing, multiple targets. Therefore, it is necessary to locate all teeth in the binary image. Each tooth is represented by a collection of pixels, and the number of targets can be determined by finding pixel contours vertically. A pixel value is a value assigned by the computer when the image is digitized. It represents the average brightness or average reflectance density of a small square or pixel. Although conventional edge detection algorithms such as Sobel and Canny can detect edge pixels based on differences in image grayscale values to determine boundaries, these methods do not consider the contour as a whole, resulting in inaccurate edge detection. In a binary image, the contour of each tooth corresponds to a series of pixels. Pixel contours describe a continuous sequence of points with the same pixel value. Edge pixels can be combined into pixel contour curves to describe the edge information of the image. Therefore, closed pixel contours can be determined based on the grayscale values of each pixel in the binary image. Generally, the number of closed pixel contours corresponds to the number of teeth.

[0078] In special cases where teeth are misaligned, two or more teeth may be closely spaced or spatially overlapped, resulting in the recognition of closed pixel contours corresponding to two or more teeth as one. To reduce recognition errors in these situations, the following steps can be used to improve the accuracy of subsequent dental arch line generation:

[0079] Determine whether the area of the first closed region corresponding to each closed pixel contour line is greater than a threshold;

[0080] If the area of any of the first closed regions is greater than a threshold, corroding the closed region to obtain at least two second closed regions with areas smaller than the threshold, and determining the number of the first closed regions and the second closed regions with areas smaller than the threshold as the number of teeth;

[0081] If the area of each of the first closed regions is less than or equal to the threshold, determining the number of the first closed regions as the number of teeth;

[0082] All pixel points in the first closed region and the second closed region whose areas are smaller than the threshold are determined as pixel point sets corresponding to the teeth.

[0083] Erosion is an image processing method in morphology, which uses structural elements of a certain shape to measure and extract the corresponding shape in the image to achieve the purpose of analysis and recognition. Figure 5 , Figure 5A schematic diagram of the etching process involved in a method for generating a dental arch line image provided in an embodiment of the present application. Corrosion is performed on overlapping portions of a binary image, reducing and refining the highlighted or white areas within the image to produce a set of non-overlapping pixels, enabling tooth recognition. In specific implementations, the threshold and the area of the second closed region can be customized based on historical experience, actual user needs, or specific application scenarios, and are not further defined here.

[0084] After determining the pixel point set corresponding to each tooth based on the binary image, according to the formula as well as Calculate the coordinates of the center of mass of each tooth. x is the x-axis coordinate of the center of mass, c y is the y-axis coordinate of the center of mass, T 00 is the sum of the pixel values corresponding to all the pixels in the pixel set, T 01 is the product of the horizontal coordinate and the corresponding pixel value in the pixel point set, T 10 It is the product of the vertical coordinate and the corresponding pixel values in the pixel point set.

[0085] In practice, the center of mass is found for the pixel set corresponding to each tooth. Because a tooth's cross-section is irregular, its center of mass and centroid are not necessarily equal. In an image, since each shape is composed of pixels, the center of mass is the weighted average of the pixel values corresponding to all the pixels that make up the shape.

[0086] Step S103: converting each of the centroid coordinates into corresponding target coordinates in the target image.

[0087] According to step S101, the dental arch line usually needs to be displayed on a DICOM reader. Therefore, the centroid coordinates of each tooth detected in the binary image in JPG format need to be converted into the corresponding target coordinates in the target image, that is, DICOM coordinates.

[0088] Specifically, the step of obtaining a single-layer target image in DICOM format corresponding to the three-dimensional tooth model includes:

[0089] Selecting a basic cone-beam CT image corresponding to the three-dimensional tooth model in the original cone-beam CT image, wherein the basic cone-beam CT image includes multiple layers of second sub-images;

[0090] The second sub-images of each layer are fused into a target image in DICOM format by the maximum intensity projection method.

[0091] See also Figure 4Because CBCT images are multi-layered, to facilitate direct viewing and diagnosis, CBCT images encompassing the lower dental arch or specialized upper dental arch can be fused into a single CBCT image using maximum intensity projection. The centroid coordinates from the binary JPG image are then converted to the single CBCT image. This eliminates the influence of the DICOM data's Z axis on the coordinate conversion process, reduces the computational effort involved, and speeds up arch line generation.

[0092] The step of converting each of the centroid coordinates into corresponding target coordinates in the target image comprises:

[0093] Obtaining a pixel interval value corresponding to the target image;

[0094] The target coordinates corresponding to each center of mass coordinate in the target image are obtained by summing the pixel interval value, the center of mass coordinate corresponding to each tooth, and the preset origin coordinates of the target image.

[0095] The primary component of a DICOM file is the dataset, which consists of DICOM data elements arranged in a specified order. DICOM files are generally transmitted explicitly, with data elements arranged in ascending order according to their tags. DICOM tags can be categorized into four main categories: Patient, Study, Series, and Image, representing image information or related parameter information. Each DICOM tag is typically identified by a combination of two hexadecimal numbers. Therefore, in practice, the corresponding pixel interval value can be obtained from the tag information in the DICOM file.

[0096] Step S104: fitting the coordinate points corresponding to the target coordinates into a target dental arch line by using an interpolation spline curve algorithm.

[0097] After converting the coordinates of each centroid into the corresponding target coordinates in the target image in DICOM format, the coordinate points corresponding to each target coordinate can be fitted using the interpolation spline curve algorithm to obtain an accurately predicted target dental arch line.

[0098] During specific implementation, other fitting algorithms besides the interpolation spline algorithm may be selected for fitting according to the actual use requirements of the user and specific application scenarios, which is not further limited here.

[0099] Step S105 : fusing the target dental arch line and the target image into a dental arch line image.

[0100] See also Figure 6 , Figure 6A schematic diagram of a dental arch line image used in a method for generating a dental arch line image provided in an embodiment of the present application. After fitting a target dental arch line, the target dental arch line can be fused with the target image to generate an dental arch line image that includes the target dental arch line. This allows the doctor to more conveniently observe the patient's oral condition based on the dental arch line image, thereby improving diagnostic efficiency.

[0101] The method for generating a dental arch line image provided in this application determines closed pixel contour lines based on the grayscale value of each pixel in a binary image. If the area of the first closed region corresponding to any closed pixel contour line is greater than a threshold, the closed region is eroded to accurately determine the number of teeth and further determine the centroid coordinates of each tooth. By converting each centroid coordinate into the corresponding target coordinates in a single-layer target image in DICOM format, a target dental arch line can be accurately and quickly generated to produce a dental arch line image.

[0102] Corresponding to the above method embodiment, see Figure 7 The present invention further provides a dental arch line image generation device 700, the dental arch line image generation device 700 comprising:

[0103] An image acquisition module 701 is configured to convert a three-dimensional tooth model into a binary image and acquire a single-layer target image in DICOM format corresponding to the three-dimensional tooth model;

[0104] A coordinate calculation module 702 is used to determine the centroid coordinates corresponding to each tooth based on the binary image;

[0105] A coordinate conversion module 703 is used to convert each of the centroid coordinates into corresponding target coordinates in the target image;

[0106] The curve fitting module 704 is used to fit the coordinate points corresponding to the target coordinates into a target dental arch line by using an interpolation spline curve algorithm;

[0107] An image fusion module 705 is configured to fuse the target dental arch line with the target image into a dental arch line image;

[0108] In specific implementation, the coordinate conversion module 703 is specifically used for:

[0109] Obtaining a pixel interval value corresponding to the target image;

[0110] The target coordinates corresponding to each center of mass coordinate in the target image are obtained by summing the pixel interval value, the center of mass coordinate corresponding to each tooth, and the preset origin coordinates of the target image.

[0111] In addition, a computer device is also provided, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed on the processor, the method for generating the dental arch line image is implemented.

[0112] In addition, a computer-readable storage medium is also provided, which stores a computer program. When the computer program is executed on a processor, it implements the above-mentioned method for generating a dental arch line image.

[0113] The specific implementation process of the dental arch line image generation device, computer equipment and computer-readable storage medium provided in this application for the accessory requirements can be referred to the specific implementation process of the dental arch line image generation method provided in the above embodiment, and will not be repeated here.

[0114] This application provides a device, computer device, and computer-readable storage medium for generating dental arch line images for accessory requirements. Closed pixel contour lines are determined based on the grayscale value of each pixel in a binary image. If the area of the first closed region corresponding to any closed pixel contour line is greater than a threshold, the closed region is eroded to obtain an accurate number of teeth and further obtain the centroid coordinates of each tooth. By converting each centroid coordinate into the corresponding target coordinates in a single-layer target image in DICOM format, a target dental arch line can be accurately and quickly generated to generate a dental arch line image.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes 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 structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0116] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0117] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0118] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for generating a dental arch line image, characterized in that: The method for generating the dental arch line image includes: Acquire an original cone-beam CT image corresponding to the oral cavity, wherein the original cone-beam CT image includes multi-layer first sub-images; Preprocessing the original cone-beam CT image through a two-dimensional convolutional network to obtain a basic oral image, wherein the number of filters in the two-dimensional convolutional network is the same as the number of layers of the first sub-image; Inputting the basic oral cavity image into a pre-trained tooth extraction model to obtain a three-dimensional tooth model, converting the three-dimensional tooth model into a binary image, and selecting a basic cone-beam CT image corresponding to the three-dimensional tooth model in the original cone-beam CT image, wherein the basic cone-beam CT image includes multiple layers of second sub-images; The second sub-images of each layer are fused into a target image in DICOM format by using the maximum intensity projection method; Determining closed pixel contour lines based on the grayscale value of each pixel in the binary image; Determine whether the area of the first closed region corresponding to each closed pixel contour line is greater than a threshold; If the area of any of the first closed regions is greater than a threshold, corroding the closed region to obtain at least two second closed regions with areas smaller than the threshold, and determining the number of the first closed regions and the second closed regions with areas smaller than the threshold as the number of teeth; If the area of each of the first closed regions is less than or equal to the threshold, determining the number of the first closed regions as the number of teeth; Determine all pixel points within the first closed region and the second closed region whose areas are smaller than the threshold as a pixel point set corresponding to the tooth; According to the formula as well as Calculate the coordinates of the center of mass of each tooth, where c x is the x-axis coordinate of the center of mass, c y is the y-axis coordinate of the center of mass, T 00 is the sum of the pixel values corresponding to all the pixels in the pixel set, T 01 is the product of the horizontal coordinate and the corresponding pixel value in the pixel point set, T 10 is the product of the vertical coordinate and the corresponding pixel value in the pixel point set; Obtaining a pixel interval value corresponding to the target image; Based on the pixel interval value, the centroid coordinates corresponding to each tooth and the preset origin coordinates of the target image, a sum is performed to obtain the target coordinates corresponding to each centroid coordinate in the target image; Fitting the coordinate points corresponding to the target coordinates into a target dental arch line by using an interpolation spline curve algorithm; The target dental arch line and the target image are fused into a dental arch line image.

2. A device for generating a dental arch line image, characterized in that: The dental arch line image generating device includes: An image acquisition module, configured to acquire an original cone-beam CT image corresponding to the oral cavity, wherein the original cone-beam CT image includes a multi-layer first sub-image; Preprocessing the original cone-beam CT image through a two-dimensional convolutional network to obtain a basic oral image, wherein the number of filters in the two-dimensional convolutional network is the same as the number of layers of the first sub-image; Inputting the basic oral cavity image into a pre-trained tooth extraction model to obtain a three-dimensional tooth model, converting the three-dimensional tooth model into a binary image, and selecting a basic cone-beam CT image corresponding to the three-dimensional tooth model in the original cone-beam CT image, wherein the basic cone-beam CT image includes multiple layers of second sub-images; The second sub-images of each layer are fused into a target image in DICOM format by using the maximum intensity projection method; A coordinate calculation module, configured to determine closed pixel contour lines based on the grayscale value of each pixel in the binary image; Determine whether the area of the first closed region corresponding to each closed pixel contour line is greater than a threshold; If the area of any of the first closed regions is greater than a threshold, corroding the closed region to obtain at least two second closed regions with areas smaller than the threshold, and determining the number of the first closed regions and the second closed regions with areas smaller than the threshold as the number of teeth; If the area of each of the first closed regions is less than or equal to the threshold, determining the number of the first closed regions as the number of teeth; Determine all pixel points within the first closed region and the second closed region whose areas are smaller than the threshold as a pixel point set corresponding to the tooth; According to the formula as well as Calculate the coordinates of the center of mass of each tooth, where c x is the x-axis coordinate of the center of mass, c y is the y-axis coordinate of the center of mass, T 00 is the sum of the pixel values corresponding to all the pixels in the pixel set, T 01 is the product of the horizontal coordinate and the corresponding pixel value in the pixel point set, T 10 is the product of the vertical coordinate and the corresponding pixel value in the pixel point set; A coordinate conversion module, used for obtaining the pixel interval value corresponding to the target image; Based on the pixel interval value, the centroid coordinates corresponding to each tooth and the preset origin coordinates of the target image, a sum is performed to obtain the target coordinates corresponding to each centroid coordinate in the target image; A curve fitting module, used for fitting the coordinate points corresponding to the target coordinates into a target dental arch line through an interpolation spline curve algorithm; An image fusion module is used to fuse the target dental arch line and the target image into a dental arch line image.

3. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed on the processor, the method for generating a dental arch line image according to claim 1 is implemented.

4. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed on a processor, the method for generating a dental arch line image according to claim 1 is implemented.

Images