Jaw cyst medical image enhancement method and system based on image processing

Abstract

The invention relates to the field of jawbone CT image enhancement, in particular to a jawbone cyst medical image enhancement method and system based on image processing. The method comprises the following steps: obtaining a gray histogram of an image; on the basis, a gray class cluster is obtained through clustering; obtaining an organization class cluster gray scale and a non-organization class cluster gray scale according to the gray scale distribution in the class cluster and the number of pixel points; obtaining an edge coefficient according to the gray scale difference around the pixel point and the difference between the gray scale of other pixel points around and the gray scale of the non-tissue cluster; the pixel points are connected according to the edge coefficient difference between the pixel points and the surrounding pixel points, and a region segmentation line between the organization region and the non-organization region is obtained; and enhancing the jaw CT image according to the region separation line. According to the method, the clear edge in the jaw CT image can be obtained, so that related personnel can determine the specific position of the jaw cyst conveniently.

Description

Technical Field

[0001] The present invention relates to the field of jaw CT image enhancement, and in particular to a method and system for jaw cyst medical image enhancement based on image processing. Background Art

[0002] Medical imaging technology plays a vital role in the clinical diagnosis and treatment of jaw cysts. First, medical imaging, especially advanced imaging technologies such as cone beam CT, can provide accurate visual information of jaw cysts and help doctors evaluate the size, location and morphology of cysts, which is essential for formulating treatment plans and surgical strategies. Secondly, medical image enhancement processing can improve image quality, enhance the contrast between cysts and surrounding tissues, and make the boundaries of cysts clearer, thereby improving the accuracy of diagnosis, which is essential for early detection and precise treatment of cysts, especially when the boundaries of cysts are unclear or the contrast with surrounding tissues is low. Through deep learning and image processing technology, the segmentation and analysis process of jaw cysts can be automated and standardized, reducing the workload of doctors, improving diagnostic efficiency, and reducing diagnostic inconsistencies caused by differences in doctor experience. In summary, medical imaging technology not only provides a solid foundation for the clinical diagnosis and treatment of jaw cysts, but also further improves the accuracy of diagnosis and the effectiveness of treatment through the application of image enhancement processing and auxiliary diagnosis technology, which is of great significance to improving patient treatment effects and prognosis.

[0003] Since the density and structure of jaw cysts are similar to those of surrounding tissues, the boundaries are difficult to distinguish. The images are often not clear. When edge detection is used directly to detect the cyst boundary, it is necessary to continuously adjust the high and low threshold parameters in the detection algorithm to ensure that a clear edge can be obtained. Therefore, there is a lack of adaptive ability, resulting in unsatisfactory image enhancement effects. Summary of the invention

[0004] In order to solve the boundary of jaw cyst The image is often not clear. When edge detection is directly used to detect the cyst boundary, the parameters of the high and low thresholds in the detection algorithm need to be continuously adjusted to ensure that a clear edge can be obtained. Therefore, there is a lack of adaptive ability, which leads to an unsatisfactory effect of image enhancement. The purpose of the present invention is to provide a medical image enhancement method and system for jaw cysts based on image processing. The technical scheme adopted is as follows: a medical image enhancement method for jaw cysts based on image processing, the method comprising: obtaining a jaw CT image of a patient; obtaining a grayscale histogram of the grayscale values ​​of all pixels in the jaw CT image; and performing grayscale value analysis on the grayscale values ​​of all pixels according to the grayscale value distribution in the grayscale histogram. Perform row clustering to obtain all grayscale clusters; obtain the grayscale of tissue clusters and the grayscale of non-tissue clusters according to the grayscale distribution within all the grayscale clusters and the number of pixels corresponding to each grayscale value; obtain the edge coefficient of each pixel in the mandibular CT image according to the grayscale difference characteristics within the preset neighborhood of each pixel, and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; connect the pixels according to the difference in edge coefficients between each pixel and other pixels in the preset neighborhood to obtain the regional dividing line between the tissue area and the non-tissue area in the mandibular CT image; enhance the mandibular CT image according to the regional dividing line.

[0005] Furthermore, the method for obtaining all grayscale clusters includes: concentrating the grayscale values ​​of the grayscale histogram in three grayscale intervals; taking the area composed of pixels with grayscale values ​​closest to 0 in the grayscale histogram as the background area; screening out the pixels in the background area, clustering other pixels in the mandibular CT image, setting the number of clusters to 2, and obtaining 2 grayscale clusters.

[0006] Furthermore, the method for obtaining the grayscale of the tissue cluster and the grayscale of the non-tissue cluster includes: taking one of the grayscale clusters as a reference cluster; taking the other grayscale cluster as a comparison cluster; obtaining the grayscale of the tissue cluster and the grayscale of the non-tissue cluster according to the calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster, and the calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster is as follows: ; In the formula, Represents the grayscale of tissue clusters; Represents the number of pixels of the reference cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the number of pixels in the comparison cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the grayscale of non-organized clusters; represents the minimum function; Represents the maximum value function.

[0007] Furthermore, the method for obtaining the edge coefficient includes: selecting any pixel point in the mandibular CT image as a reference pixel point; obtaining the number of tissue grayscale pixels and the number of non-tissue grayscale pixels in the preset neighborhood of the reference pixel point according to the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood of the reference pixel point and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; obtaining the edge coefficient according to the edge coefficient calculation formula, and the edge coefficient calculation formula is as follows: In the formula, Indicates the number of tissue grayscale pixels within the preset neighborhood of the reference pixel; Indicates the number of non-organized grayscale pixels within the preset neighborhood of the reference pixel; Indicates the number of other pixels in the preset neighborhood of the reference pixel; Represents the edge coefficient of the reference pixel; Indicates the maximum grayscale value of the pixel within the preset neighborhood of the reference pixel; Indicates the first pixel in the preset neighborhood of the reference pixel. Grayscale values ​​of other pixels; Represents an exponential function with a natural constant as base.

[0008] Furthermore, the method for obtaining the number of tissue grayscale pixels and the number of non-tissue grayscale pixels within a preset neighborhood of a reference pixel includes: calculating the grayscale value of each other pixel in the preset neighborhood of the reference pixel and the grayscale between the tissue cluster grayscale and the non-tissue cluster grayscale, and obtaining the tissue grayscale difference and the non-tissue grayscale difference respectively; comparing the tissue grayscale difference and the non-tissue grayscale difference of each other pixel, and taking other pixels whose tissue grayscale difference is greater than the non-tissue grayscale difference as tissue grayscale pixels, and taking other pixels whose tissue grayscale difference is less than the non-tissue grayscale difference as non-tissue grayscale pixels; and counting the number of tissue grayscale pixels and the number of non-tissue grayscale pixels in the preset neighborhood of the reference pixel.

[0009] Furthermore, the method for obtaining the region separation line includes: obtaining connectable pixel points of the reference pixel point in the preset neighborhood based on the edge similarity features between the reference pixel point and each other pixel point in the preset neighborhood; connecting the reference pixel point with each connectable pixel point to obtain the separation line of the reference pixel point in the preset neighborhood; traversing all pixel points to obtain the separation line of each pixel point in the preset neighborhood, splicing all separation lines to obtain the region separation line between the tissue area and the non-tissue area in the mandibular CT image.

[0010] Furthermore, based on the edge similarity features between the reference pixel and each other pixel in the preset neighborhood, the connectible pixel points of the reference pixel in the preset neighborhood are obtained, including: calculating the edge coefficient difference between the reference pixel and each other pixel in the preset neighborhood as a first difference; when the ratio of the first difference to the edge coefficient of the reference pixel is not greater than a preset first threshold, taking the corresponding other pixel points in the preset neighborhood as the connectible pixel points of the reference pixel in the preset neighborhood.

[0011] A medical image enhancement system for jaw cysts based on image processing, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned medical image enhancement method for jaw cysts based on image processing when executing the computer program.

[0012] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for medical image enhancement of jaw cysts based on image processing.

[0013] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the above-mentioned method for medical image enhancement of jaw cysts based on image processing are implemented.

[0014] The present invention has the following beneficial effects: the present invention collects the patient's jaw CT image and enhances the jaw CT image, so that relevant personnel can accurately identify the cyst area of ​​the patient's jaw; since the grayscale histogram can reflect the grayscale value concentration of the jaw CT image, the jaw CT image can be divided into a background area, a non-tissue area and a tissue area according to the grayscale value concentration, so firstly a grayscale histogram of the grayscale values ​​of all pixels in the jaw CT image is obtained, and the pixels are divided into two grayscale clusters according to the grayscale distribution of the grayscale histogram; the overall grayscale values ​​of the two grayscale clusters are quantified to reflect the approximate grayscale in the tissue area and the non-tissue area, so as to facilitate the subsequent determination of the jaw CT image. Whether the pixel points of the T image tend to be edge pixels; so analyze the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; compared with the pixels inside different regions, the grayscale distribution of the pixels on the edge of the region has a higher grayscale contrast, and the more obvious the grayscale contrast is, the more likely it is that the pixel points are located on the edge of the region, so according to the grayscale difference characteristics within the preset neighborhood of each pixel point in the mandibular CT image, and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster, obtain the edge coefficient of each pixel point; connect the pixels through the edge coefficient to obtain the regional segmentation line; enhance the mandibular CT image according to the regional segmentation line. The present invention can obtain clear edges in the mandibular CT image so that relevant personnel can determine the specific location of the jaw cyst. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for medical image enhancement of jaw cysts based on image processing provided by one embodiment of the present invention; Figure 2 A conventional edge detection image of a jaw CT image provided by an embodiment of the present invention; Figure 3 This is a region segmentation line effect diagram of a jaw CT image provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a medical image enhancement method and system for jaw cysts based on image processing proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the medical image enhancement method and system for jaw cyst based on image processing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a method for medical image enhancement of jaw cysts based on image processing provided by an embodiment of the present invention. The method comprises: Step S1: acquiring a jaw CT image of a patient.

[0021] The embodiment of the present invention is mainly used in the scenario of cyst identification in jaw CT images. Therefore, in the embodiment of the present invention, the patient's jaw CT image is collected and the jaw CT image is enhanced so that relevant personnel can accurately identify the cyst area in the patient's jaw.

[0022] In the embodiment of the present invention, the patient needs to sit on a chair in front of the CBCT scanner, keep the head in the middle and try not to move. Usually, the patient is required to tilt the head slightly upward or forward to ensure that the jaw area can be clearly displayed. The scanning range and parameters, such as resolution and scanning time, are selected. When the scanning starts, the patient remains still, and the CBCT device starts to rotate and simultaneously takes a series of The radiographic image is stored to obtain the initial jaw CT image of the patient.

[0023] The jaw CT image is grayed and denoised to obtain the jaw CT image of the patient. It should be noted that the graying and denoising methods are both well-known technical means to those skilled in the art, and are not limited or elaborated herein.

[0024] Step S2: Obtain a grayscale histogram of the grayscale values ​​of all pixels in the mandibular CT image; cluster the grayscale values ​​of all pixels according to the grayscale value distribution in the grayscale histogram to obtain all grayscale clusters; obtain the grayscale of the tissue cluster and the grayscale of the non-tissue cluster according to the grayscale distribution in all grayscale clusters and the number of pixels corresponding to each grayscale value; obtain the edge coefficient of each pixel according to the grayscale difference characteristics within a preset neighborhood of each pixel in the mandibular CT image, and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; connect the pixels according to the difference in edge coefficients between each pixel and other pixels in the preset neighborhood to obtain a region dividing line between the tissue region and the non-tissue region in the mandibular CT image.

[0025] By observing the mandibular CT image, it can be known that the area with the lowest grayscale value is the background area, the area with the highest grayscale value is the non-tissue area, and the area with grayscale values ​​between the two is the tissue area. The grayscale histogram can reflect the grayscale value concentration of the mandibular CT image. According to the concentration of grayscale values, the mandibular CT image can be divided into background area, non-tissue area and tissue area. Therefore, in an embodiment of the present invention, the grayscale histogram of the grayscale values ​​of all pixels in the mandibular CT image is first obtained, and the pixels are divided into three grayscale clusters according to the grayscale distribution of the grayscale histogram.

[0026] Preferably, in one embodiment of the present invention, the method for obtaining grayscale clusters includes: since the overall grayscale values ​​of the background area, tissue area and non-tissue area in the mandibular CT image are respectively in a smaller grayscale interval, the grayscale values ​​of the grayscale histogram are concentrated in three grayscale intervals, and the three grayscale intervals correspond to the grayscale values ​​of the pixels in the background area, the grayscale values ​​of the pixels in the tissue area and the grayscale values ​​of the pixels in the non-tissue area, respectively.

[0027] The area composed of pixels whose grayscale values ​​are closest to 0 in the grayscale histogram is taken as the background area. Since the background area is an interference factor in the embodiment of the present invention, the pixels in the background area are screened out, and other pixels in the mandibular CT image are clustered. The number of clusters is set to 2, and two grayscale clusters are obtained. The cluster with a smaller overall grayscale value in the two grayscale clusters corresponds to the grayscale value of the pixels in the tissue area, and the cluster with a larger overall grayscale value corresponds to the grayscale value of the pixels in the non-tissue area. It should be noted that the embodiment of the present invention uses the K-means clustering algorithm to cluster the grayscale value types other than the grayscale value of the background area. The algorithm is a technical means well known to those skilled in the art and is not limited or elaborated here.

[0028] The overall grayscale values ​​of the two grayscale clusters are quantified to reflect the approximate grayscale in the tissue area and the non-tissue area, so as to facilitate the subsequent determination of whether the pixel points of the mandibular CT image tend to be edge pixels.

[0029] Preferably, in an embodiment of the present invention, the method for acquiring the grayscale of the tissue cluster and the grayscale of the non-tissue cluster includes: taking one of the grayscale clusters as a reference cluster; and taking the other grayscale cluster as a comparison cluster.

[0030] The grayscale of the tissue cluster and the grayscale of the non-tissue cluster are obtained according to the calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster. The calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster is as follows: ; In the formula, Represents the grayscale of tissue clusters; Represents the number of pixels of the reference cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the number of pixels in the comparison cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the grayscale of non-organized clusters; represents the minimum function; Represents the maximum value function.

[0031] In the calculation formula of the grayscale of tissue cluster and non-tissue cluster, the more pixels corresponding to each grayscale value in the grayscale cluster, the more important the grayscale value is. and As the weight, the larger it is, the weighted average of the pixels corresponding to each gray value in the grayscale cluster is obtained. as well as , is used to represent the overall grayscale value of the grayscale cluster, where the smaller one is the grayscale of the tissue cluster and the larger one is the grayscale of the non-tissue cluster.

[0032] Compared with the pixels inside different regions, the grayscale distribution of the pixels on the edge of the region has a higher grayscale contrast. The embodiment of the present invention quantifies this contrast relationship. The pixels with more obvious grayscale contrast tend to be located on the edge of the region. Therefore, in the embodiment of the present invention, the edge coefficient of each pixel is obtained according to the grayscale difference characteristics within the preset neighborhood of each pixel in the mandibular CT image, and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster.

[0033] Preferably, in an embodiment of the present invention, the method for obtaining the edge coefficient includes: selecting any pixel point in the mandibular CT image as a reference pixel point; since the embodiment of the present invention only studies the pixel points in the tissue area and the non-tissue area, the grayscale value of each other pixel point in the preset neighborhood of the reference pixel point is calculated, and the grayscale between the grayscale of the tissue cluster and the grayscale of the non-tissue cluster is calculated to obtain the tissue grayscale difference and the non-tissue grayscale difference respectively; in the embodiment of the present invention, the preset neighborhood is set to be centered on the reference pixel point, It should be noted that the preset neighborhood can be set by yourself and is not limited here.

[0034] Compare the tissue grayscale difference and non-tissue grayscale difference of each other pixel point, and take other pixels whose tissue grayscale difference is greater than that of non-tissue grayscale difference as tissue grayscale pixels, and take other pixels whose tissue grayscale difference is less than that of non-tissue grayscale difference as non-tissue grayscale pixels; count the number of tissue grayscale pixels and non-tissue grayscale pixels within the preset neighborhood of the reference pixel point.

[0035] The edge coefficient is obtained according to the edge coefficient calculation formula. The edge coefficient calculation formula is as follows: In the formula, Indicates the number of tissue grayscale pixels within the preset neighborhood of the reference pixel; Indicates the number of non-organized grayscale pixels within the preset neighborhood of the reference pixel; represents the number of other pixels in the preset neighborhood of the reference pixel. In the embodiment of the present invention, is 8; Represents the edge coefficient of the reference pixel; Indicates the maximum grayscale value of the pixel within the preset neighborhood of the reference pixel; Indicates the first pixel in the preset neighborhood of the reference pixel. Grayscale values ​​of other pixels; Represents an exponential function with a natural constant as base.

[0036] In the edge coefficient calculation formula, the sum of the number of tissue grayscale pixels and the number of non-organization grayscale pixels is the number of other pixels in the preset neighborhood; the greater the difference between the maximum grayscale value and the grayscale mean of the pixels in the preset neighborhood, the more likely the grayscale value of the pixels in the preset neighborhood of the reference pixel is to have an obvious grayscale contrast, and the stronger the edge coefficient of the reference pixel is at this time; the larger the value of any one of the number of tissue grayscale pixels and the number of non-organization grayscale pixels is, the more pixels with a single grayscale value tendency there are, that is, the reference pixel is more likely to belong to a pixel inside a certain area, that is, The larger it is, the smaller the value range of the function in [1,7] becomes, and the smaller the edge coefficient of the reference pixel becomes.

[0037] The pixel points are connected by edge coefficients to obtain the region segmentation line.

[0038] Preferably, in an embodiment of the present invention, a method for obtaining a region separation line includes: calculating the difference in edge coefficients between a reference pixel and each other pixel in a preset neighborhood as a first difference; when the ratio between the first difference and the edge coefficient of the reference pixel is not greater than a preset first threshold, using other pixel points in the corresponding preset neighborhood as connectable pixel points of the reference pixel in the preset neighborhood. In an embodiment of the present invention, the preset first threshold is set to 0.9. It should be noted that the preset first threshold can be set voluntarily and is not limited here.

[0039] The reference pixel point is connected to each connectable pixel point to obtain the separation line of the reference pixel point in the preset neighborhood; all pixel points are traversed to obtain the separation line of each pixel point in the preset neighborhood, and all separation lines are spliced ​​to obtain the regional separation line between the tissue area and the non-tissue area in the mandibular CT image.

[0040] The region segmentation line replaces the edge boundary line obtained by conventional edge detection.

[0041] Step S3: enhancing the jaw CT image according to the region separation line.

[0042] The results obtained by directly using the traditional edge detection algorithm are as follows Figure 2 In the conventional edge detection image of a jaw CT image shown in FIG. 1 , it can be observed that the edges of some tissues or non-tissues are not well marked, especially the edges of the cyst part, which are not detected. Through the processing of the embodiment of the present invention, it is possible to obtain Figure 3 As shown in the regional segmentation line effect diagram of the mandibular CT image, it can be observed that the identification of the tissue and non-tissue edges is significantly clearer than that of the traditional edge detection algorithm, and the edges of the key positions where the cysts are located are also detected.

[0043] At this point, the enhancement of the jaw CT image is completed.

[0044] In summary, the patient's mandibular CT image is obtained; the grayscale histogram of the grayscale values ​​of all pixels in the mandibular CT image is obtained; according to the grayscale value distribution in the grayscale histogram, the grayscale values ​​of all pixels are clustered to obtain all grayscale clusters; according to the grayscale distribution in all grayscale clusters and the number of pixels corresponding to each grayscale value, the grayscale of the tissue cluster and the grayscale of the non-tissue cluster are obtained; according to the grayscale difference characteristics within the preset neighborhood of each pixel in the mandibular CT image, and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster, the edge coefficient of each pixel is obtained; according to the difference in edge coefficients between each pixel and other pixels in the preset neighborhood, the pixels are connected to obtain the regional dividing line between the tissue area and the non-tissue area in the mandibular CT image; the mandibular CT image is enhanced according to the regional dividing line.

[0045] An embodiment of the present invention provides a medical image enhancement system for jaw cysts based on image processing, the system comprising a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, the method described in steps S1-S3 can be implemented.

[0046] The third objective of an embodiment of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method described in steps S1-S3 is implemented when the processor executes the computer program.

[0047] A fourth objective of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in steps S1-S3 is implemented.

[0048] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0049] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A medical image enhancement method for jaw cyst based on image processing, characterized in that: The method comprises: obtaining a patient's jaw CT image; obtaining a grayscale histogram of the grayscale values ​​of all pixels in the jaw CT image; clustering the grayscale values ​​of all pixels according to the grayscale value distribution in the grayscale histogram to obtain all grayscale clusters; obtaining the grayscale of tissue clusters and the grayscale of non-tissue clusters according to the grayscale distribution in all the grayscale clusters and the number of pixels corresponding to each grayscale value; obtaining the edge coefficient of each pixel according to the grayscale difference characteristics in a preset neighborhood of each pixel in the jaw CT image and the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; connecting the pixels according to the difference in edge coefficients between each pixel and other pixels in the preset neighborhood to obtain a region dividing line between a tissue region and a non-tissue region in the jaw CT image; and enhancing the jaw CT image according to the region dividing line.

2. The method for medical image enhancement of jaw cyst based on image processing according to claim 1, characterized in that: The method for obtaining all grayscale clusters includes: concentrating the grayscale values ​​of the grayscale histogram in three grayscale intervals; taking the area composed of pixels whose grayscale values ​​are closest to 0 in the grayscale histogram as the background area; filtering out the pixels in the background area, clustering other pixels in the mandibular CT image, setting the number of clusters to 2, and obtaining 2 grayscale clusters.

3. The method for medical image enhancement of jaw cyst based on image processing according to claim 1, characterized in that: The method for obtaining the grayscale of the tissue cluster and the grayscale of the non-tissue cluster includes: taking one of the grayscale clusters as a reference cluster; taking the other grayscale cluster as a comparison cluster; and obtaining the grayscale of the tissue cluster and the grayscale of the non-tissue cluster according to the calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster. The calculation formula of the grayscale of the tissue cluster and the grayscale of the non-tissue cluster is as follows: ; In the formula, Represents the grayscale of tissue clusters; Represents the number of pixels of the reference cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the number of pixels in the comparison cluster; Indicates the first The number of pixels corresponding to the gray value; Indicates the first Gray value; Represents the grayscale of non-organized clusters; represents the minimum function; Represents the maximum value function.

4. The method for medical image enhancement of jaw cyst based on image processing according to claim 1, characterized in that: The method for obtaining the edge coefficient includes: selecting any pixel point in the mandibular CT image as a reference pixel point; obtaining the number of tissue grayscale pixels and the number of non-tissue grayscale pixels in the preset neighborhood of the reference pixel point according to the grayscale difference between the grayscale values ​​of other pixels in the preset neighborhood of the reference pixel point and the grayscale of the tissue cluster and the grayscale of the non-tissue cluster; obtaining the edge coefficient according to the edge coefficient calculation formula, and the edge coefficient calculation formula is as follows: In the formula, Indicates the number of tissue grayscale pixels within the preset neighborhood of the reference pixel; Indicates the number of non-organized grayscale pixels within the preset neighborhood of the reference pixel; Indicates the number of other pixels in the preset neighborhood of the reference pixel; Represents the edge coefficient of the reference pixel; Indicates the maximum grayscale value of the pixel within the preset neighborhood of the reference pixel; Indicates the first pixel in the preset neighborhood of the reference pixel. Grayscale values ​​of other pixels; Represents an exponential function with a natural constant as base.

5. The method for medical image enhancement of jaw cyst based on image processing according to claim 4, characterized in that: The method for obtaining the number of tissue grayscale pixels and the number of non-tissue grayscale pixels within a preset neighborhood of a reference pixel includes: calculating the grayscale value of each other pixel in the preset neighborhood of the reference pixel and the grayscale between the tissue cluster grayscale and the non-tissue cluster grayscale, and obtaining the tissue grayscale difference and the non-tissue grayscale difference respectively; comparing the tissue grayscale difference and the non-tissue grayscale difference of each other pixel, and taking other pixels whose tissue grayscale difference is greater than the non-tissue grayscale difference as tissue grayscale pixels, and taking other pixels whose tissue grayscale difference is less than the non-tissue grayscale difference as non-tissue grayscale pixels; and counting the number of tissue grayscale pixels and the number of non-tissue grayscale pixels in the preset neighborhood of the reference pixel.

6. The method for medical image enhancement of jaw cyst based on image processing according to claim 1, characterized in that: The method for obtaining the regional separation line includes: obtaining connectable pixel points of the reference pixel point in the preset neighborhood based on the edge similarity characteristics between the reference pixel point and each other pixel point in the preset neighborhood; connecting the reference pixel point with each connectable pixel point to obtain the separation line of the reference pixel point in the preset neighborhood; traversing all pixel points to obtain the separation line of each pixel point in the preset neighborhood, splicing all separation lines to obtain the regional separation line between the tissue area and the non-tissue area in the mandibular CT image.

7. The method for medical image enhancement of jaw cyst based on image processing according to claim 6, characterized in that: Based on the edge similarity features between the reference pixel and each other pixel in the preset neighborhood, Obtaining connectable pixel points of a reference pixel point within a preset neighborhood includes: calculating the difference in edge coefficients between the reference pixel point and each other pixel point in the preset neighborhood as a first difference; when the ratio between the first difference and the edge coefficient of the reference pixel point is not greater than a preset first threshold, using the corresponding other pixel points in the preset neighborhood as connectable pixel points of the reference pixel point in the preset neighborhood.

8. A medical image enhancement system for jaw cysts based on image processing, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the medical image enhancement method for jaw cyst based on image processing as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a medical image enhancement method for jaw cysts based on image processing as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the medical image enhancement method for jaw cyst based on image processing as described in any one of claims 1 to 7 are implemented.

Images