An orthodontic dental film image processing method
Patent Information
- Application Number
- CN202410461149.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-17
- Publication Date
- 2026-10-09
AI Technical Summary
[0003]为了解决现有提升牙片影像对比度的方法对牙片影像的处理效果不理想的技术问题，本发明的目的在于提供一种口腔正畸用牙片影像处理方法，所采用的技术方案具体如下：
[0026]本发明首先获取牙片影像的灰度图像和灰度直方图，为后续分析牙片影像的图像特征，对牙片影像进行自适应处理做准备；进一步分析每个灰度级像素点的分布特征，初步获取每个灰度级的初始拉伸参数，为后续进行更准确的修正做准备；进一步分析灰度级与其相邻灰度级的差异特征，获取每个灰度级的修正参数，为修正初始拉伸参数提供依据；进一步根据修正参数对初始拉伸参数进行调整，然后利用调整后的修正拉伸参数调整直方图均衡化中的变换函数，获取修正变换函数，为实现图像自适应处理做好准备；进一步利用修正变换函数对图像进行自适应拉伸，获得自适应拉伸图像，提升改善图像对比度的效果，提升图像质量。本发明充分考虑了牙片影像不同灰度级的拉伸必要性，从每个灰度级的像素点的分布特征和相邻灰度级之间的差异特征两个角度衡量灰度级的拉伸必要性，实现对牙片影像的自适应拉伸，增强改善图像对比度的效果。
Smart Images
Figure CN122887743A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of dental radiograph image enhancement processing technology, and specifically to a method for processing dental radiograph images for orthodontic use. Background Technology
[0002] As people's happiness index improves, they are paying more and more attention to their oral health. During orthodontic treatment, dental X-rays contain information about the patient's teeth, alveolar bone, and adjacent structures. They are an important tool for dentists to understand the patient's dental condition and help them develop appropriate orthodontic treatment plans. High-contrast dental X-rays help highlight details and structures in the image, making it essential to improve the contrast of the taken images. However, when using histogram equalization to improve contrast, stretching the grayscale levels may not improve contrast and could even reduce it, resulting in unsatisfactory image processing results. Summary of the Invention
[0003] To address the technical problem that existing methods for improving the contrast of dental radiographs do not achieve ideal processing results, the present invention aims to provide a method for processing dental radiographs used in orthodontics. The specific technical solution adopted is as follows:
[0004] Acquire grayscale images and grayscale histograms of dental radiographs used in orthodontics;
[0005] Based on the distribution characteristics of pixels corresponding to each gray level in the grayscale histogram in the grayscale image, the initial stretching parameter corresponding to each gray level is obtained; the gray value difference characteristics and distribution characteristics of pixels between each gray level and its adjacent gray levels are analyzed, and combined with the initial stretching parameters of adjacent gray levels, the correction parameter of each gray level is obtained; the initial stretching parameter is adjusted according to the correction parameter to obtain the corrected stretching parameter; the transformation function in histogram equalization is adjusted according to the corrected stretching parameter to obtain the corrected transformation function;
[0006] The grayscale image is histogram equalized according to the modified transformation function to obtain an adaptive stretched image.
[0007] Furthermore, the method for obtaining the initial tensile parameters includes:
[0008] The ratio of the number of pixels corresponding to each gray level to the total number of pixels in the grayscale image is used as the density parameter for each gray level.
[0009] Based on the distribution position of the pixels corresponding to each gray level in the grayscale image, the sum of the single-source shortest path distances of the pixels is calculated and used as the discrete parameters corresponding to each gray level;
[0010] An initial stretching parameter calculation formula is constructed based on the density parameter and the discrete parameter of each gray level, and the initial stretching parameter of each gray level is obtained based on the initial stretching parameter calculation formula.
[0011] Furthermore, the method for obtaining the correction parameter includes:
[0012] On the grayscale histogram, the grayscale level with the smaller grayscale level among two adjacent grayscale levels is designated as the first adjacent grayscale level, and the other is designated as the second adjacent grayscale level. A grayscale level is arbitrarily selected from the grayscale histogram as the target grayscale level. Correction parameters for each target grayscale level are obtained using a correction parameter calculation formula. The correction parameter calculation formula includes:
[0013] Where i is the index of the target gray level; W i jm represents the correction parameter for the i-th target gray level; (i,i-1) σ represents the first compact parameter between the i-th target gray level and its first adjacent gray level; (i,i-1) hl represents the first mean square error parameter between the i-th target gray level and its first neighboring gray level; i-1 This represents the initial stretching parameter for the first adjacent gray level; jm (i,i+1) σ represents the second compact parameter between the i-th target gray level and its second adjacent gray level; (i,i+1) hl represents the second mean square error parameter between the i-th target gray level and its second neighboring gray level; i+1 This represents the initial stretching parameter for the second adjacent gray level.
[0014] Furthermore, the method for obtaining the first compactness parameter and the second compactness parameter includes:
[0015] The frequency of pixels of the first adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the first closeness parameter between the target gray level and its first adjacent gray level is obtained; the frequency of pixels of the second adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the second closeness parameter between the target gray level and its second adjacent gray level is obtained.
[0016] Furthermore, the methods for obtaining the first mean squared error parameter and the second mean squared error parameter include:
[0017] Obtain the mean square error between the target gray level and its first adjacent gray level, and use it as the first mean square error parameter of the target gray level; obtain the mean square error between the target gray level and its second adjacent gray level, and use it as the second mean square error parameter of the target gray level.
[0018] Furthermore, the method for obtaining the corrected tensile parameters includes:
[0019] The product of the initial stretching parameter and the correction parameter for each gray level is used as the correction stretching parameter for the corresponding gray level.
[0020] Furthermore, the method for obtaining the modified transformation function includes:
[0021] The corrected stretching parameter for each gray level is multiplied by the corresponding gray level's transformation function value in the transformation function to form the corrected transformation function.
[0022] Furthermore, in the initial tensile parameter calculation formula: the density parameter is positively correlated with the initial tensile parameter; the discrete parameter is negatively correlated with the initial tensile parameter.
[0023] Furthermore, the algorithm for calculating the sum of the single-source shortest path distances is Dijkstra's algorithm.
[0024] Furthermore, the preset neighborhood is: an eight-neighborhood centered on the pixel.
[0025] The present invention has the following beneficial effects:
[0026] This invention first acquires the grayscale image and grayscale histogram of dental radiographs to prepare for subsequent analysis of image features and adaptive processing. It then analyzes the distribution characteristics of pixels at each grayscale level to obtain initial stretching parameters for each level, preparing for more accurate corrections. Next, it analyzes the differences between each grayscale level and its adjacent levels to obtain correction parameters for each level, providing a basis for correcting the initial stretching parameters. The initial stretching parameters are then adjusted based on these correction parameters, and the adjusted transformation function in histogram equalization is used to obtain a corrected transformation function, preparing for adaptive image processing. Finally, the corrected transformation function is used to adaptively stretch the image, resulting in an adaptively stretched image that improves image contrast and quality. This invention fully considers the necessity of stretching different grayscale levels in dental radiographs, measuring the stretching necessity from two perspectives: the distribution characteristics of pixels at each grayscale level and the differences between adjacent grayscale levels. This achieves adaptive stretching of dental radiographs, enhancing image contrast. Attached Figure Description
[0027] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 This is a flowchart of a dental radiograph image processing method for orthodontic purposes, provided as an embodiment of the present invention. Detailed Implementation
[0029] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a dental radiograph image processing method for orthodontics proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.
[0030] Unless otherwise defined, 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 pertains.
[0031] The following describes in detail, with reference to the accompanying drawings, a specific scheme for processing dental radiographs for orthodontic purposes provided by the present invention.
[0032] Please see Figure 1 The diagram illustrates a flowchart of a dental radiograph image processing method for orthodontic use according to an embodiment of the present invention, specifically including:
[0033] Step S1: Obtain the grayscale image and grayscale histogram of the dental radiographs used for orthodontic treatment.
[0034] In embodiments of the present invention, in order to adaptively stretch dental radiographs, it is necessary to analyze the specific features of different gray levels in the radiographs. Therefore, grayscale images and grayscale histograms of the radiographs are obtained to prepare for subsequent analysis and processing. It should be noted that the methods for obtaining grayscale images and grayscale histograms are well-known to those skilled in the art and will not be described in detail here. The processed dental radiographs are only auxiliary tools for doctors and professionals and cannot be directly used for medical diagnosis.
[0035] Step S2: Based on the distribution characteristics of pixels corresponding to each gray level in the grayscale image, obtain the initial stretching parameter for each gray level; analyze the gray value difference and distribution characteristics of pixels between each gray level and its adjacent gray levels, and obtain the correction parameter for each gray level by combining the initial stretching parameters of adjacent gray levels; adjust the initial stretching parameter according to the correction parameter to obtain the corrected stretching parameter; adjust the transformation function in histogram equalization according to the corrected stretching parameter to obtain the corrected transformation function.
[0036] When performing histogram equalization on dental radiographs, during gray-level stretching, some gray levels amplify the differences between themselves and adjacent gray levels, while others reduce the detail of the pixels corresponding to those gray levels before stretching, which is detrimental to the representation of those details. Therefore, in this embodiment of the invention, to improve the gray-level image processing effect of histogram equalization on dental radiographs, the distribution characteristics of pixels at each gray level and the difference characteristics between each gray level and its adjacent gray levels are analyzed. The transformation function in histogram equalization is then adjusted to achieve adaptive equalization, thereby enhancing the contrast of the dental radiographs.
[0037] Experience shows that the pixels of tooth components in dental radiographs are relatively concentrated and have a high distribution density. The more likely they are to be the same tissue, the better they can be stretched to grayscale, thus highlighting the image details. By utilizing the distribution characteristics of the pixels, the grayscale stretching parameters can be obtained in advance.
[0038] Preferably, in one embodiment of the present invention, considering that the larger the proportion of gray-level pixels in a gray-level image, the higher the density and the smaller the dispersion, the greater the importance of the pixel corresponding to the current gray-level in the image, and the stronger the necessity of gray-level stretching, the initial stretching parameters of the gray-level are obtained by analyzing the proportion and dispersion characteristics of pixels at each gray-level:
[0039] The ratio of the number of pixels corresponding to each gray level to the total number of pixels in the grayscale image is used as the density parameter of each gray level; based on the distribution position of the pixels corresponding to each gray level in the grayscale image, the sum of the single-source shortest path distances of the pixels is calculated and used as the discrete parameter corresponding to each gray level.
[0040] The initial stretching parameter calculation formula is constructed based on the density parameter and discrete parameter of each gray level, and the initial stretching parameter of each gray level is obtained based on the initial stretching parameter calculation formula.
[0041] The density parameter is positively correlated with the initial stretching parameter, while the discrete parameter is negatively correlated with the initial stretching parameter. In one embodiment of the present invention, the quotient of the density parameter and the discrete parameter for each gray level is used as the corresponding initial stretching parameter. In other embodiments of the present invention, other basic mathematical operations or function mappings can also be used to achieve the mapping that satisfies the correlation relationship. These are technical means well known to those skilled in the art and will not be elaborated here.
[0042] It should be noted that, in one embodiment of the present invention, each grayscale pixel is used to construct a weighted directed graph. Specifically, the weight is the distance between one pixel and another in the grayscale image, and the direction is the direction from one pixel to another. The pixel with the smallest weight is selected as the source point. Dijkstra's algorithm is applied to the weighted directed graph formed by these pixels. The weight of each edge in the resulting single-source shortest path graph is the distance, and the sum of the distances of all edges is the single-source shortest path distance sum. Constructing a weighted directed graph and using Dijkstra's algorithm to calculate the single-source shortest path distance sum are techniques well-known to those skilled in the art and will not be elaborated further.
[0043] Gray-level stretching cannot be based solely on pixel distribution characteristics. Since the purpose of gray-level stretching is to enhance image contrast and amplify differences, the necessity of stretching cannot be determined solely by the pixel distribution of each gray-level. It is also necessary to analyze the differences between the gray-level and its adjacent gray-levels to correct for the stretching necessity. The greater the difference, the less necessary the stretching is, as excessive amplification of the affected portion would be meaningless and would lead to amplification of other information. Therefore, analyzing the gray-level value differences and pixel distribution characteristics between each gray-level and its adjacent gray-levels, combined with the initial stretching parameters of adjacent gray-levels, yields the correction parameters for each gray-level.
[0044] Preferably, in one embodiment of the present invention, considering that the mean square error can reflect the spatial consistency between gray levels, the smaller the mean square error, the stronger the consistency, and the smaller the difference between gray levels; and considering that the density of the distribution of pixels of a gray level with pixels of adjacent gray levels can reflect the close relationship between gray levels, the correction parameters are obtained through the mean square error and the density.
[0045] In the grayscale histogram, the grayscale level with the smaller grayscale level among two adjacent grayscale levels is designated as the first adjacent grayscale level, and the other is designated as the second adjacent grayscale level. A grayscale level is arbitrarily selected from the grayscale histogram as the target grayscale level. Correction parameters for each target grayscale level are obtained using the correction parameter calculation formula. The correction parameter calculation formula includes:
[0046]
[0047] Where i is the index of the target gray level; W i jm represents the correction parameter for the i-th target gray level; (i,i-1) σ represents the first compact parameter between the i-th target gray level and its first adjacent gray level; (i,i-1) hl represents the first mean square error parameter between the i-th target gray level and its first neighboring gray level; i-1This represents the initial stretching parameter for the first adjacent gray level; jm (i,i+1) σ represents the second compact parameter between the i-th target gray level and its second adjacent gray level; (i,i+1) hl represents the second mean square error parameter between the i-th target gray level and its second neighboring gray level; i+1 This represents the initial stretching parameter for the second adjacent gray level.
[0048] In the formula for calculating the correction parameters, the larger the first mean square error parameter and the second mean square error parameter, the greater the difference between the target gray level and its adjacent gray levels, the less necessary the stretching, and the smaller the correction parameter. Conversely, the larger the first compactness parameter and the second compactness parameter, the more closely the target gray level and its adjacent gray level pixels are distributed, the greater the need for stretching, and the larger the correction parameter. It should be noted that in other embodiments of the present invention, other basic mathematical operations or function mappings can also be used to achieve mappings that satisfy the relevant relationships. These are all technical means well known to those skilled in the art and will not be elaborated upon here.
[0049] It should be noted that, considering that the two gray levels at the edge of the gray-level histogram only have a gray level on one side, the gray level with the smallest gray value is analyzed with its two adjacent larger gray levels, and the gray level with the largest gray value is analyzed with its two adjacent smaller gray levels.
[0050] Preferably, in one embodiment of the present invention, considering that the frequency of adjacent gray-level pixels appearing in the neighborhood of a pixel at a target gray level can reflect the density of pixels at different gray levels, the frequency of adjacent gray-level pixels appearing in the neighborhood of all pixels corresponding to the target gray level is statistically analyzed to obtain a density parameter:
[0051] The frequency of pixels of the first adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the first closeness parameter between the target gray level and its first adjacent gray level is obtained; the frequency of pixels of the second adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the second closeness parameter between the target gray level and its second adjacent gray level is obtained.
[0052] It should be noted that, in one embodiment of the present invention, when counting the frequency of adjacent gray-level pixels within a preset neighborhood of a pixel, the neighborhood range size is set to 3×3, and other pixels within the eight neighborhoods centered on the pixel are analyzed. In other embodiments of the present invention, the implementer may set neighborhood ranges of other sizes for analysis.
[0053] Preferably, in one embodiment of the present invention, considering that the mean square error can serve to measure the differences between gray levels, the mean square error is used as the corresponding calculation parameter:
[0054] Obtain the mean square error between the target gray level and its first adjacent gray level, as the first mean square error parameter of the target gray level; obtain the mean square error between the target gray level and its second adjacent gray level, as the second mean square error parameter of the target gray level.
[0055] It should be noted that, given the pixel values and number of pixels at two gray levels, obtaining the mean square error between the two gray values is a well-known technique in the art, and will not be elaborated upon here.
[0056] After obtaining the initial stretching parameters and correction parameters for each gray level, the initial stretching parameters can be adjusted to make them more consistent with the actual characteristics of the image, thus obtaining more accurate correction stretching parameters.
[0057] Preferably, in one embodiment of the present invention, the product of the initial stretching parameter and the correction parameter of each gray level is used as the correction stretching parameter of the corresponding gray level.
[0058] The grayscale correction stretching parameter characterizes the necessity of grayscale stretching. The larger the correction stretching parameter, the greater the necessity for stretching the current grayscale level, thereby enhancing the contrast of the dental radiograph and facilitating observation and analysis. Therefore, after obtaining the correction stretching parameter, the transformation function used in histogram equalization can be adjusted to obtain a more accurate correction transformation function.
[0059] Preferably, in one embodiment of the present invention, considering that the correction stretching parameter corresponding to each gray level is different, the correction stretching parameter is constructed as a correction function to adjust the transformation function. Based on this, the correction stretching parameter of each gray level is multiplied by the transformation function value of the corresponding gray level in the transformation function to form the correction transformation function. The calculation formula of the correction transformation function is as follows:
[0060] T′ i =T i ×HL i
[0061] Where i is the gray level index; T' i T represents the value of the correction transformation function for the i-th gray level; i HL represents the transformation function value of the i-th gray level; i This represents the correction stretching parameter for the i-th gray level.
[0062] In the formula for calculating the transformation function, the larger the correction stretching parameter for a gray level, the greater the necessity for stretching the current gray level and the greater the degree of adjustment to the transformation function value.
[0063] It should be noted that the specific process of histogram equalization and the acquisition of the transformation function are well known to those skilled in the art. In other embodiments of the present invention, other basic mathematical operations or function mappings can also be used to achieve mappings that satisfy the relevant relationships. These are all well known to those skilled in the art and will not be elaborated here.
[0064] Step S3: Perform histogram equalization on the grayscale image according to the modified transformation function to obtain an adaptive stretched image.
[0065] After adaptively adjusting the transformation function used in histogram equalization through steps S1 to S2, the grayscale image of the dental radiograph can be adaptively stretched to obtain an adaptively stretched image. It should be noted that the stretching process of histogram equalization is a well-known technique in the art and will not be described in detail here.
[0066] In summary, this invention addresses the problem that existing methods for improving contrast in dental radiographs through histogram equalization do not produce ideal results. It proposes a new method for processing dental radiographs used in orthodontics. This method first analyzes the distribution characteristics of pixels at each gray level in the grayscale image to obtain initial stretching parameters for each gray level. It then analyzes the differences between adjacent gray levels and corrects the initial stretching parameters to obtain corrected stretching parameters. Next, it adjusts the transformation function used in histogram equalization based on the corrected stretching parameters. Finally, it performs adaptive histogram equalization using the corrected transformation function to obtain an adaptively stretched image. This invention fully considers the necessity of stretching different gray levels in dental radiographs, measuring the stretching necessity from two perspectives: the distribution characteristics of pixels at each gray level and the differences between adjacent gray levels. This achieves adaptive stretching of dental radiographs, enhancing and improving image contrast.
[0067] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0068] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
Claims
1. A method for processing dental radiographs used in orthodontics, characterized in that, The method includes: Acquire grayscale images and grayscale histograms of dental radiographs used in orthodontics; Based on the distribution characteristics of pixels corresponding to each gray level in the grayscale histogram in the grayscale image, the initial stretching parameter corresponding to each gray level is obtained; the gray value difference characteristics and distribution characteristics of pixels between each gray level and its adjacent gray levels are analyzed, and combined with the initial stretching parameters of adjacent gray levels, the correction parameter of each gray level is obtained; the initial stretching parameter is adjusted according to the correction parameter to obtain the corrected stretching parameter; the transformation function in histogram equalization is adjusted according to the corrected stretching parameter to obtain the corrected transformation function; The grayscale image is histogram equalized according to the modified transformation function to obtain an adaptive stretched image.
2. The method for processing dental radiographs for orthodontic use according to claim 1, characterized in that, The method for obtaining the initial tensile parameters includes: The ratio of the number of pixels corresponding to each gray level to the total number of pixels in the grayscale image is used as the density parameter for each gray level. Based on the distribution position of the pixels corresponding to each gray level in the grayscale image, the sum of the single-source shortest path distances of the pixels is calculated and used as the discrete parameters corresponding to each gray level; An initial stretching parameter calculation formula is constructed based on the density parameter and the discrete parameter of each gray level, and the initial stretching parameter of each gray level is obtained based on the initial stretching parameter calculation formula.
3. The method for processing dental radiographs for orthodontic use according to claim 1, characterized in that, The method for obtaining the correction parameters includes: On the grayscale histogram, the grayscale level with the smaller grayscale level among two adjacent grayscale levels is designated as the first adjacent grayscale level, and the other is designated as the second adjacent grayscale level. A grayscale level is arbitrarily selected from the grayscale histogram as the target grayscale level. Correction parameters for each target grayscale level are obtained using a correction parameter calculation formula. The correction parameter calculation formula includes: Where i is the index of the target gray level; W i jm represents the correction parameter for the i-th target gray level; (i,i-1) σ represents the first compact parameter between the i-th target gray level and its first adjacent gray level; (i,i-1) hl represents the first mean square error parameter between the i-th target gray level and its first neighboring gray level; i-1 This represents the initial stretching parameter for the first adjacent gray level; jm (i,i+1) σ represents the second compact parameter between the i-th target gray level and its second adjacent gray level; (i,i+1) hl represents the second mean square error parameter between the i-th target gray level and its second neighboring gray level; i+1 This represents the initial stretching parameter for the second adjacent gray level.
4. The method for processing dental radiographs for orthodontic use according to claim 3, characterized in that, The methods for obtaining the first tightness parameter and the second tightness parameter include: The frequency of pixels of the first adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the first closeness parameter between the target gray level and its first adjacent gray level is obtained; the frequency of pixels of the second adjacent gray level appearing in the preset neighborhood of all pixels of the target gray level is counted, and the second closeness parameter between the target gray level and its second adjacent gray level is obtained.
5. The method for processing dental radiographs for orthodontic use according to claim 3, characterized in that, The methods for obtaining the first mean square error parameter and the second mean square error parameter include: Obtain the mean square error between the target gray level and its first adjacent gray level, and use it as the first mean square error parameter of the target gray level; obtain the mean square error between the target gray level and its second adjacent gray level, and use it as the second mean square error parameter of the target gray level.
6. The method for processing dental radiographs for orthodontic use according to claim 1, characterized in that, The method for obtaining the corrected tensile parameters includes: The product of the initial stretching parameter and the correction parameter for each gray level is used as the correction stretching parameter for the corresponding gray level.
7. The method for processing dental radiographs for orthodontic use according to claim 1, characterized in that, The method for obtaining the modified transformation function includes: The corrected stretching parameter for each gray level is multiplied by the corresponding gray level's transformation function value in the transformation function to form the corrected transformation function.
8. The method for processing dental radiographs for orthodontic use according to claim 2, characterized in that, In the initial tensile parameter calculation formula: the density parameter is positively correlated with the initial tensile parameter; the discrete parameter is negatively correlated with the initial tensile parameter.
9. The method for processing dental radiographs for orthodontic use according to claim 2, characterized in that, The algorithm for calculating the sum of shortest path distances from a single source is Dijkstra's algorithm.
10. A method for processing dental radiographs for orthodontic use according to claim 4, characterized in that, The preset neighborhood is: an eight-neighborhood centered on the pixel.