Method and apparatus for segmenting teeth in an image

Abstract

The application provides a tooth segmentation method and device in an image. The method comprises the following steps: acquiring a plurality of cross-sectional images of teeth, and determining a connected domain of each cross-sectional image; if a target connected domain of a current cross-sectional image comprises pixels of a plurality of connected domains of a previous cross-sectional image, it is determined that the target connected domain appears bifurcation intersection; performing corrosion processing on the target connected domain to obtain a final cross-sectional image; and performing tooth segmentation processing based on the final cross-sectional image. In this way, the problem of tooth data adhesion in single tooth positioning can be solved by judging whether the connected domain appears bifurcation intersection, and the accuracy of tooth segmentation and positioning is improved.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method and apparatus for segmenting teeth in an image. Background Technology

[0002] In existing technologies, after segmenting the tooth portion of oral CT (Computed Tomography) data, due to the accuracy of the segmentation algorithm, the loss of image conversion, and the actual distribution of teeth, there are often cases where multiple tooth images are in contact or even adhered together, which will seriously affect the localization of individual teeth.

[0003] Although clustering and other methods can roughly obtain the coordinates of each tooth, the error rate is very high, with serious cases of missed or false detections. Furthermore, relying on prior information such as the number of clusters makes it difficult to locate individual teeth in oral CT data. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method and apparatus for segmenting teeth in an image, so as to solve the problem of tooth data sticking together when locating a single tooth, and improve the accuracy of tooth segmentation and positioning.

[0005] In a first aspect, embodiments of the present invention provide a method for segmenting teeth in an image, the method comprising: acquiring multiple cross-sectional images of teeth, determining the connected components of each cross-sectional image; if the target connected component of the current cross-sectional image includes pixels of multiple connected components of the previous cross-sectional image, determining that the target connected component has bifurcated and intersecting; performing erosion processing on the target connected component to obtain a final cross-sectional image; and performing tooth segmentation processing based on the final cross-sectional image.

[0006] In a preferred embodiment of this application, after the step of acquiring cross-sectional images of multiple teeth described above, the method further includes: preprocessing the multiple cross-sectional images; wherein the preprocessing includes noise processing and hole processing.

[0007] In a preferred embodiment of this application, the above-described preprocessing steps for multiple cross-sectional images include: calculating the number of pixels and center position of each non-adjacent data block in the cross-sectional image; deleting data blocks with a number of pixels less than a threshold and data blocks with outlier center position coordinates.

[0008] In a preferred embodiment of this application, the above-described preprocessing step for multiple cross-sectional images includes: filling background image pixels in the multiple cross-sectional images.

[0009] In a preferred embodiment of this application, after the above-described step of determining the connected components of each cross-sectional image, the method further includes: calculating the superposition state matrix of each connected component; and determining, based on the superposition state matrix, whether the connected component includes pixels of multiple connected components of the previous cross-sectional image.

[0010] In a preferred embodiment of this application, the step of eroding the target connected region described above includes: replacing the pixel value of the target connected region with the pixel value of the corresponding region of the target connected region in the previous cross-sectional image.

[0011] In a preferred embodiment of this application, the step of eroding the target connected region includes: dilating the target connected region, deleting overlapping pixels and adjacent pixels of the dilated target connected region to obtain the final target connected region; and replacing the pixel values ​​of the final target connected region with the pixel values ​​of the corresponding region of the final target connected region of the previous cross-sectional image.

[0012] In a preferred embodiment of this application, the step of eroding the target connected region as described above includes: if the target connected region meets the preset erosion conditions, eroding the target connected region.

[0013] In a preferred embodiment of this application, the step of the target connected region satisfying the preset erosion conditions includes: if the area of ​​the target connected region is less than a preset area threshold and the erosion ratio is less than a preset ratio threshold, determining that the target connected region satisfies the preset erosion conditions; wherein, the erosion ratio is the ratio of the number of pixels eroded to the number of pixels retained.

[0014] Secondly, embodiments of the present invention also provide a tooth segmentation device in an image, the device comprising: a connected component determination module, configured to acquire cross-sectional images of multiple teeth and determine the connected components of each cross-sectional image; a bifurcation and intersection judgment module, configured to determine that the target connected component has bifurcation and intersection if the target connected component of the current cross-sectional image includes pixels of multiple connected components of the previous cross-sectional image; an erosion processing module, configured to perform erosion processing on the target connected component to obtain a final cross-sectional image; and a tooth segmentation processing module, configured to perform tooth segmentation processing based on the final cross-sectional image.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] This invention provides a method and apparatus for segmenting teeth in an image. If the target connected region of the current cross-sectional image includes pixels from multiple connected regions of the previous cross-sectional image, it is determined that the target connected region exhibits bifurcation and intersection. The target connected region is then subjected to erosion processing, and tooth segmentation is performed based on the final cross-sectional image. This method addresses the problem of tooth data adhesion during single-tooth localization by determining whether the connected region exhibits bifurcation and intersection, thereby improving the accuracy of tooth segmentation and localization.

[0017] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0018] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 A schematic diagram of bifurcated intersecting teeth provided in an embodiment of the present invention;

[0021] Figure 2 A flowchart illustrating a method for segmenting teeth in an image, provided as an embodiment of the present invention;

[0022] Figure 3 A flowchart of another method for segmenting teeth in an image provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the program flow of a tooth segmentation algorithm provided in an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of the coordinate detection result of tooth segmentation provided in an embodiment of the present invention;

[0025] Figure 6 A schematic diagram of coordinate detection results for another tooth segmentation method provided in an embodiment of the present invention;

[0026] Figure 7 A schematic diagram of a tooth segmentation device in an image provided by an embodiment of the present invention;

[0027] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Currently, after segmenting the tooth portion of oral CT data, due to the accuracy of the segmentation algorithm, the loss of image conversion, and the actual distribution of teeth, there are often multiple tooth images that are in contact or even adhered together, which will seriously affect the localization of individual teeth.

[0030] While clustering and other methods can roughly obtain the coordinates of each tooth, the error rate is high, with severe cases of missed and false detections. Furthermore, the reliance on prior information such as the number of clusters makes locating individual teeth in oral CT data quite difficult. Therefore, this invention provides a method and apparatus for tooth segmentation in images, relating to medical digital image processing technology, specifically offering a three-dimensional single-tooth data segmentation method based on digital image processing technology.

[0031] To facilitate understanding of this embodiment, a method for segmenting teeth in an image disclosed in this embodiment of the invention will first be described in detail.

[0032] Example 1:

[0033] This invention provides a method for segmenting teeth in an image, which mainly involves the following concepts:

[0034] Forking and intersecting: See also Figure 1 The diagram shows a type of bifurcated intersecting tooth. If there is a shape at the point of contact between two teeth that is not present in a single tooth, this shape can be called a bifurcated intersecting tooth.

[0035] Erosion treatment: In this embodiment, the two teeth can be separated by repeatedly eroding the intersection of the two teeth.

[0036] Based on the above description, see Figure 2 The flowchart shown illustrates a method for segmenting teeth in an image, which includes the following steps:

[0037] Step S202: Obtain cross-sectional images of multiple teeth and determine the connected components of each cross-sectional image.

[0038] Multiple cross-sectional images of teeth can be determined based on CT data. Then, the cross-sectional images are traversed from top to bottom to detect connected components on the slices.

[0039] Step S204: If the target connected component of the current cross-sectional image includes pixels of multiple connected components of the previous cross-sectional image, determine that the target connected component has bifurcated and intersected.

[0040] If a connected component in a cross-sectional image contains pixels from two or more connected components in a previous slice, then that connected component in the current cross-section is said to have a bifurcation and intersection, and this connected component can be called the target connected component. The location of the bifurcation and intersection in the target connected component might be the contact area between two teeth or the concave / convex area on a tooth.

[0041] Step S206: Erosion processing is performed on the target connected region to obtain the final cross-sectional image.

[0042] Erosion is primarily used in morphology to remove certain parts of an image. Starting from the second cross-sectional image, if a bifurcation or intersection occurs, the corresponding connected components are eroded, thus separating the pixels of the two teeth in the current cross-section. The current cross-sectional image data is then updated, and the next cross-section is detected to obtain the final cross-sectional image.

[0043] It should also be noted that since the tooth surface is not completely smooth, some corrosion conditions can be set before corrosion treatment. Only target connected regions that meet the corrosion conditions can be corroded; otherwise, excessive segmentation will occur in some uneven areas of the tooth surface.

[0044] Step S208: Perform tooth segmentation processing based on the final cross-sectional image.

[0045] Finally, the final cross-sectional image can be processed for tooth segmentation, thereby segmenting the teeth with high accuracy in tooth segmentation and localization.

[0046] This invention provides a method for segmenting teeth in an image. If the target connected region of the current cross-sectional image includes pixels from multiple connected regions of the previous cross-sectional image, it is determined that the target connected region has bifurcated and intersecting. The target connected region is then subjected to erosion processing, and tooth segmentation is performed based on the final cross-sectional image. This method addresses the problem of tooth data adhesion during single-tooth localization by determining whether the connected regions have bifurcated and intersecting, thereby improving the accuracy of tooth segmentation and localization.

[0047] Example 2:

[0048] This embodiment provides another method for segmenting teeth in an image. This method is implemented based on the above embodiment and includes a data preprocessing process, a tooth segmentation process (obtaining the superimposed state matrix and calculating the erosion region), and a data postprocessing process. See also... Figure 3 The flowchart shows another method for segmenting teeth in an image, which includes the following steps:

[0049] Step S302: Obtain cross-sectional images of multiple teeth and preprocess the multiple cross-sectional images; wherein, the preprocessing includes noise reduction and hole removal.

[0050] The algorithm flow of this embodiment can be found in [reference]. Figure 4 The diagram shows a flowchart of a tooth segmentation algorithm. In this embodiment, the algorithm uses Python 3.9 as the programming language, and other components can be OpenCV 4.5 or VTK 9.1. The operating system can be Windows 10.

[0051] like Figure 4 As shown, starting from i=0, a connected component detection is performed on the i-th cross-sectional image to determine if any intersections or branches occur. If no intersections or branches occur, the traversal continues, and the value of i is incremented by 1 until the entire traversal is completed. If intersections or branches occur, the erosion region is calculated, and it is determined whether erosion processing is required. If so, erosion processing is performed; if not, the traversal continues, and the value of i is incremented by 1 until the entire traversal is completed.

[0052] For data preprocessing, the segmented tooth data contains noise and voids, which can interfere with the final result of the algorithm and need to be processed in advance. The preprocessing in this embodiment includes at least noise reduction and void reduction.

[0053] Specifically, noise can be processed as follows: calculate the number of pixels and center position of each non-adjacent data block in the cross-sectional image; delete data blocks with a pixel count less than a threshold and data blocks with outlier center position coordinates. Data noise refers to small-volume data blocks that do not belong to the teeth. The specific filtering scheme is to calculate the number of pixels and center position of each non-adjacent data block, and delete data blocks with a pixel count less than a threshold and data blocks with outlier center position z-coordinates.

[0054] Specifically, hole removal can be performed by filling background image pixels in multiple cross-sectional images. Holes refer to background image pixels surrounded by target object pixels. These holes may be caused by missing teeth or accuracy issues in the segmentation algorithm when obtaining tooth data. These holes may lead to additional bifurcation and intersection features, which can be removed by filling the background image pixels surrounded by target pixels in the original data.

[0055] Step S304: Determine the connected components of each cross-sectional image.

[0056] Step S306: If the target connected component of the current cross-sectional image includes pixels of multiple connected components of the previous cross-sectional image, determine that the target connected component has bifurcated and intersected.

[0057] Specifically, the superposition state matrix of each connected component can be calculated; based on the superposition state matrix, it can be determined whether the connected component includes pixels of multiple connected components of the previous cross-sectional image.

[0058] To obtain the overlay state matrix, which is the result of overlaying the current slice and the previous slice along the z-axis, the overlay state matrix reflects the connectivity of target pixels between the upper and lower layers. First, the 3D tooth volume data is normalized. Then, the sum of the preceding and following cross-sectional images is calculated along the z-axis, yielding the overlay state matrix. In the matrix, a value of 2 indicates overlap between the preceding and following images in the current region; a value of 1 indicates the presence of pixel values ​​without overlap; and a value of 0 indicates the absence of pixel values.

[0059] Step S308: Erosion processing is performed on the target connected region to obtain the final cross-sectional image.

[0060] In this embodiment, erosion processing is performed on target connected regions with bifurcations and intersections, and there are at least two methods:

[0061] (1) Replace the pixel values ​​of the target connected region with the pixel values ​​of the corresponding region of the target connected region in the previous cross-sectional image.

[0062] Next, the pixel values ​​of the current target connected region are replaced with the pixel values ​​of the corresponding region of the previous slice. Since the connected regions of the corresponding regions in the previous slice are separated from each other, the region in the current slice will also be separated after the replacement. Moreover, each connected region after separation can maintain the connection between the upper and lower slices with only one connected region of the corresponding region in the previous slice, thus completing a segmentation in three dimensions.

[0063] (2) Dilate the target connected region, delete the overlapping and adjacent pixels of the dilated target connected region to obtain the final target connected region; replace the pixel values ​​of the final target connected region with the pixel values ​​of the corresponding region of the final target connected region of the previous cross-sectional image.

[0064] Before replacement, dilate the connected components in the previous slice that overlap with the current connected component. This will preserve the pixels on the periphery that should not be removed. Considering that the adjacency relationship of the connected components in the previous slice will change after dilation, resulting in incomplete segmentation, it is necessary to remove any overlapping and adjacent pixels that may appear after dilation before performing pixel replacement.

[0065] See Figure 4 The diagram shown illustrates the result of a corrosion treatment. Figure 4 The image on the left shows the corrosion treatment result after expansion and replacement (method 2). Figure 4 The right side of the image shows the result of direct replacement erosion (method 1). It can be seen that method 1 may cause pixels in the outer non-intersection area of ​​the two teeth to also be eroded, and the erosion effect will accumulate layer by layer, resulting in severe distortion of the final result.

[0066] To avoid the unevenness of the tooth surface and the segmentation of the root region, this embodiment can also set some corrosion conditions. If the target connected region meets the preset corrosion conditions, the target connected region is subjected to corrosion treatment.

[0067] Specifically, if the area of ​​the target connected region is less than a preset area threshold and the erosion ratio is less than a preset ratio threshold, the target connected region is determined to meet the preset erosion conditions; where the erosion ratio is the ratio of the number of pixels eroded to the number of pixels retained.

[0068] The cross-sectional area of ​​the protruding tooth region and the root is smaller than that of the main tooth body; therefore, the smaller connected regions in the previous layer can be considered noise and filtered out. The ratio of the number of pixels eroded to the number of pixels retained in each erosion operation is calculated. If the proportion of eroded pixels is large, the erosion operation is considered an error.

[0069] Step S310: Perform tooth segmentation processing based on the final cross-sectional image.

[0070] See Figure 5 A schematic diagram showing the coordinate detection results of tooth segmentation is shown. Figure 6 This is a schematic diagram showing another coordinate detection result for tooth segmentation. Wherein, Figure 5 Using the method provided in this embodiment, Figure 6 The method provided in this embodiment was not used.

[0071] To address the issue of tooth data adhesion during single-tooth localization, this invention proposes a three-dimensional volumetric data segmentation method based on morphological processing and recursive processing of preceding and following layers. The method involves preprocessing, layer-by-layer segmentation, and post-processing of the three-dimensional tooth data to achieve accurate tooth segmentation. Based on digital image processing technology, the method can accurately separate each tooth into strictly non-adjacent image data, while significantly improving the accuracy of tooth coordinate detection and arch curve generation.

[0072] Example 3:

[0073] Corresponding to the above method embodiments, this invention provides a device for segmenting teeth in an image, see [link to relevant documentation]. Figure 7 The diagram shows a structural schematic of a tooth segmentation device in an image. The tooth segmentation device includes:

[0074] The connected component determination module 71 is used to acquire cross-sectional images of multiple teeth and determine the connected components of each cross-sectional image.

[0075] The bifurcation and intersection judgment module 72 is used to determine that the target connected region has bifurcation and intersection if the target connected region of the current cross-section image includes pixels of multiple connected regions of the previous cross-section image.

[0076] The corrosion processing module 73 is used to perform corrosion processing on the target connected region to obtain the final cross-sectional image.

[0077] Tooth segmentation processing module 74 is used to perform tooth segmentation processing based on the final cross-sectional image.

[0078] This invention provides a tooth segmentation device for images. If the target connected region of the current cross-sectional image includes pixels from multiple connected regions of the previous cross-sectional image, it is determined that the target connected region has bifurcated and intersecting. The target connected region is then subjected to erosion processing, and tooth segmentation is performed based on the final cross-sectional image. This method solves the problem of tooth data adhesion during single-tooth localization by determining whether the connected region has bifurcated and intersecting, thus improving the accuracy of tooth segmentation and localization.

[0079] The aforementioned device includes: a preprocessing module for preprocessing multiple cross-sectional images; wherein the preprocessing includes noise reduction and hole removal.

[0080] The aforementioned preprocessing module is used to calculate the number of pixels and center position of each non-adjacent data block in the cross-sectional image; and to delete data blocks with a number of pixels less than the number threshold and data blocks with outlier center position coordinates.

[0081] The aforementioned preprocessing module is used to fill background image pixels in multiple cross-sectional images.

[0082] The aforementioned bifurcation and intersection judgment module is used to calculate the superposition state matrix of each connected component; based on the superposition state matrix, it determines whether the connected component includes pixels of multiple connected components of the previous cross-sectional image.

[0083] The aforementioned erosion processing module is used to replace the pixel values ​​of the target connected region with the pixel values ​​of the corresponding region of the target connected region in the previous cross-sectional image.

[0084] The aforementioned erosion processing module is used to dilate the target connected region, delete overlapping and adjacent pixels of the dilated target connected region, and obtain the final target connected region; the pixel values ​​of the final target connected region are replaced with the pixel values ​​of the corresponding region of the final target connected region of the previous cross-sectional image.

[0085] The aforementioned corrosion processing module is used to perform corrosion processing on the target connected region if the target connected region meets the preset corrosion conditions.

[0086] The aforementioned erosion processing module is used to determine that the target connected region meets the preset erosion conditions if the area of ​​the target connected region is less than a preset area threshold and the erosion ratio is less than a preset ratio threshold; wherein, the erosion ratio is the ratio of the number of pixels eroded to the number of pixels retained.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the tooth segmentation device in the image described above can be referred to the corresponding process in the embodiments of the tooth segmentation method in the aforementioned image, and will not be repeated here.

[0088] Example 4:

[0089] This invention also provides an electronic device for running the tooth segmentation method in the above-described image; see also Figure 8 The diagram shows the structure of an electronic device, which includes a memory 100 and a processor 101. The memory 100 stores one or more computer instructions, which are executed by the processor 101 to implement the tooth segmentation method in the image above.

[0090] Furthermore, Figure 8 The electronic device shown also includes a bus 102 and a communication interface 103, with the processor 101, the communication interface 103 and the memory 100 connected via the bus 102.

[0091] The memory 100 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 103 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network. The bus 102 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0092] Processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 101 or by instructions in software form. Processor 101 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 100, and processor 101 reads information from memory 100 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0093] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the tooth segmentation method in the above-described image. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0094] The computer program product of the tooth segmentation method and apparatus in the image provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0095] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and / or device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0096] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0097] If the aforementioned functions are implemented as software functional units 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 this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0099] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for segmenting teeth in an image, characterized in that, The method includes: Acquire multiple cross-sectional images and determine the connected components of each cross-sectional image; wherein, the cross-sectional images include teeth; If the target connected component of the current cross-sectional image includes pixels of multiple connected components of the previous cross-sectional image, it is determined that the target connected component has a bifurcation and intersection. The target connected component is eroded to obtain the final cross-sectional image; Tooth segmentation is performed based on the final cross-sectional image; After determining the connected components of each of the cross-sectional images, the method further includes: calculating the superposition state matrix of each of the connected components; and determining, based on the superposition state matrix, whether the connected component includes pixels of multiple connected components of the previous cross-sectional image. The superposition state matrix is ​​the result of superimposing the current slice and the previous slice of the image along the z-axis. The superposition state matrix reflects the connectivity of the target pixel between the upper and lower layers. The step of calculating the superposition state matrix of each connected component includes: normalizing the three-dimensional tooth volume data, and calculating the sum of the front and rear cross-sectional images according to the z-axis size to obtain the superposition state matrix. In the superposition state matrix, the region with a value of 2 indicates that the front and rear images overlap in the current region, the region with a value of 1 indicates that the front and rear images have pixel values ​​in the current region but do not overlap, and the region with a value of 0 indicates that the front and rear images do not have pixel values ​​in the current region.

2. The method according to claim 1, characterized in that, After acquiring multiple cross-sectional images, the method further includes: The multiple cross-sectional images are preprocessed; wherein the preprocessing includes noise reduction and hole removal.

3. The method according to claim 2, characterized in that, The steps for preprocessing the multiple cross-sectional images include: Calculate the number of pixels and center position of each non-adjacent data block in the cross-sectional image; Delete data blocks whose number of pixels is less than the number threshold and data blocks whose center position coordinates are outliers.

4. The method according to claim 2, characterized in that, The steps for preprocessing the multiple cross-sectional images include: Background image pixels in the multiple cross-sectional images are filled.

5. The method according to claim 1, characterized in that, The steps of eroding the target connected component include: The pixel values ​​of the target connected component are replaced with the pixel values ​​of the corresponding region of the target connected component in the previous cross-sectional image.

6. The method according to claim 1, characterized in that, The steps of eroding the target connected component include: The target connected component is dilated, and overlapping and adjacent pixels of the dilated target connected component are deleted to obtain the final target connected component. The pixel values ​​of the final target connected region are replaced with the pixel values ​​of the corresponding region of the final target connected region in the previous cross-sectional image.

7. The method according to claim 1, characterized in that, The steps of eroding the target connected component include: If the target connected component meets the preset erosion conditions, the target connected component is subjected to erosion treatment.

8. The method according to claim 7, characterized in that, The steps for satisfying the pre-set erosion conditions for the target connected component include: If the area of ​​the target connected region is less than a preset area threshold and the erosion ratio is less than a preset ratio threshold, the target connected region is determined to meet the preset erosion conditions; wherein, the erosion ratio is the ratio of the number of pixels eroded to the number of pixels retained.

9. A device for segmenting teeth in an image, characterized in that, The device includes: A connected component determination module is used to acquire multiple cross-sectional images and determine the connected components of each cross-sectional image; wherein, the cross-sectional images include teeth; The bifurcation and intersection determination module is used to determine that the target connected region has bifurcation and intersection if the target connected region of the current cross-sectional image includes pixels of multiple connected regions of the previous cross-sectional image. The corrosion processing module is used to perform corrosion processing on the target connected region to obtain the final cross-sectional image; A tooth segmentation processing module is used to perform tooth segmentation processing based on the final cross-sectional image; The bifurcation and intersection judgment module is used to calculate the superposition state matrix of each connected component; and determine whether the connected component includes pixels of multiple connected components of the previous cross-sectional image based on the superposition state matrix. The superposition state matrix is ​​the result of superimposing the current slice and the previous slice of the image along the z-axis. The superposition state matrix reflects the connection between the target pixels in the upper and lower layers. The bifurcation and intersection judgment module is used to normalize the three-dimensional tooth data and calculate the sum of the front and rear cross-sectional images according to the z-axis size to obtain the superposition state matrix. In the superposition state matrix, the region with a value of 2 indicates that the front and rear images overlap in the current region, the region with a value of 1 indicates that the front and rear images have pixel values ​​in the current region but do not overlap, and the region with a value of 0 indicates that the front and rear images have no pixel values ​​in the current region.

Images