Impacted tooth auxiliary identification method based on oral cavity three-dimensional image

Abstract

The invention relates to the technical field of oral cavity image analysis, in particular to an impacted tooth auxiliary identification method based on an oral cavity three-dimensional image. The method comprises the following steps: filtering edge pixel points in an oral CT image to obtain an enhanced image according to the gray level change degree of the edge pixel points in the oral CT image and the shape, the edge clearness degree and the gray level distribution of an analysis area where the edge pixel points are located; according to the shape difference and inclination degree difference of the wisdom teeth in the three-dimensional model of the oral cavity in the enhanced image of the sagittal CT image of the oral cavity and other tooth areas, the area of the corresponding tooth area of the wisdom teeth in the enhanced image of the axial CT image of the oral cavity and the distance between the adjacent tooth areas in the enhanced image of the coronal CT image of the oral cavity, the tooth area of the wisdom teeth in the three-dimensional model of the oral cavity is obtained; and determining the impacted wisdom teeth in the oral cavity three-dimensional model. According to the invention, the recognition accuracy of the impacted wisdom teeth is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oral image analysis, and particularly relates to a method for assisting in the identification of impacted teeth based on three-dimensional oral images. Background Art

[0002] When a tooth is in an improper position in the jawbone and cannot erupt into the normal occlusal position, it is called an impacted tooth or impacted tooth. The most common impacted tooth is the third molar of the mandible, also called the impacted wisdom tooth. It is easy for dirt and bacteria to accumulate between the impacted tooth and the gum covering it, causing bad breath. When the body's resistance decreases, inflammation often occurs. Therefore, it is necessary to identify the impacted teeth in the oral cavity for timely treatment.

[0003] In the process of identifying impacted wisdom teeth, usually an X-ray image of a certain perspective of the oral cavity is obtained, and the impacted wisdom teeth are identified according to the position, angle, and eruption condition of the wisdom teeth in the image. However, in the image of a single perspective, situations such as teeth blocking the wisdom teeth may occur, resulting in errors in the relevant data of the teeth in the image and a low accuracy rate in the identification of impacted wisdom teeth. Summary of the Invention

[0004] In order to solve the technical problem that the data in the oral cavity image in a single perspective has errors, resulting in a low accuracy rate in the identification of impacted wisdom teeth, the purpose of the present invention is to provide a method for assisting in the identification of impacted teeth based on three-dimensional oral images, and the specific technical solution adopted is as follows:

[0005] The present invention proposes a method for assisting in the identification of impacted teeth based on three-dimensional oral images, and the method includes:

[0006] Obtain the oral CT images of the patient, and the oral CT images include: oral axial CT images, oral coronal CT images, and oral sagittal CT images;

[0007] Obtain the analysis area in each oral CT image; according to the degree of gray-scale change of each edge pixel point in each oral CT image, the shape, edge clarity, and gray-scale distribution of the analysis area where each edge pixel point is located, filter the edge pixel points in each oral CT image to obtain the enhanced image of each oral CT image;

[0008] Obtain the tooth area in the enhanced image of each oral CT image; perform three-dimensional reconstruction on the enhanced images of all oral CT images to obtain an oral three-dimensional model, and determine the wisdom teeth in the oral three-dimensional model; according to the shape difference and inclination degree difference between the tooth area corresponding to each wisdom tooth in the enhanced image of the oral sagittal CT image and the remaining tooth areas in the oral three-dimensional model, the area of the tooth area corresponding to each wisdom tooth in the enhanced image of the oral axial CT image, and the distance between adjacent tooth areas in the enhanced image of the oral coronal CT image, determine the impacted wisdom teeth in the oral three-dimensional model of the patient.

[0009] Further, the method for obtaining the enhanced image of each oral CT image includes:

[0010] According to the gray-scale change degree of each edge pixel point in each oral CT image, the shape, edge clarity, and gray-scale distribution of the analysis region where each edge pixel point is located, obtain the tooth probability value of each edge pixel point in each oral CT image;

[0011] For each oral CT image, randomly select an edge pixel point in the oral CT image as the point to be filtered. Use the tooth probability value as the weight of the gray-scale values of the remaining edge pixel points except the point to be filtered within the preset filtering window of the point to be filtered, and obtain the weighted average value as the filtered gray-scale value of the point to be filtered;

[0012] Use the filtered gray-scale value to update the gray-scale value of the edge pixel points in the oral CT image to obtain the enhanced image of the oral CT image.

[0013] Further, the obtaining of the tooth probability value of each edge pixel point in each oral CT image includes:

[0014] For each oral CT image, according to the shape and gray-scale distribution of each analysis region in the oral CT image, obtain the shape gray-scale index of each analysis region;

[0015] Calculate the average value of the absolute value of the difference between the gradient values of two adjacent edge pixel points on the edge of each analysis region in the oral CT image as the edge clarity index of each analysis region;

[0016] According to the gradient value of each edge pixel point in the oral CT image, and the shape gray-scale index and the edge clarity index of the analysis region where each edge pixel point is located, obtain the tooth probability value of each edge pixel point in the oral CT image.

[0017] Further, the obtaining of the shape gray-scale index of each analysis region includes:

[0018] For each analysis region in each oral CT image, obtain the discrete index of the gray-scale values of all pixel points in the analysis region; calculate the central value of the gray-scale values of all pixel points in the analysis region;

[0019] Obtain the geometric centroid and the gray-scale centroid of the analysis region, and use the distance between the geometric centroid and the gray-scale centroid as the shape regularity value;

[0020] Obtain the shape grayscale index of the analysis region according to the discrete index, the central value, and the shape rule value; both the discrete index and the shape rule value are negatively correlated with the shape grayscale index, and the central value is positively correlated with the shape grayscale index.

[0021] Further, determining the impacted wisdom teeth in the patient's oral three-dimensional model according to the shape difference and inclination degree difference between the corresponding tooth regions and the remaining tooth regions of each wisdom tooth in the enhanced image of the oral sagittal CT image, the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image, and the spacing between adjacent tooth regions in the enhanced image of the oral coronal CT image includes:

[0022] Obtain the reference teeth of each wisdom tooth in the patient's oral three-dimensional model; according to the shape difference and inclination degree difference between the corresponding tooth regions of each wisdom tooth and its reference teeth in the enhanced image of the oral sagittal CT image, obtain the growth deviation value of each wisdom tooth;

[0023] Obtain the spacing between adjacent two tooth regions in the enhanced image of the oral coronal CT image; the spacing between the corresponding two tooth regions of adjacent two teeth among all the reference teeth of each wisdom tooth in the enhanced image of the oral coronal CT image in the oral three-dimensional model constitutes the tooth spacing set of each wisdom tooth; take the sum of the absolute values of the differences between the spacing between the corresponding two tooth regions of each wisdom tooth and its adjacent teeth in the enhanced image of the oral coronal CT image and each element in the tooth spacing set as the normal spacing difference value of each wisdom tooth;

[0024] Obtain the impacted tooth characteristic value of each wisdom tooth according to the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image, the growth deviation value, and the normal spacing difference value; the area is negatively correlated with the impacted tooth characteristic value, and both the growth deviation value and the normal spacing difference value are positively correlated with the impacted tooth characteristic value;

[0025] Use the impacted tooth characteristic value to determine the impacted wisdom teeth among all the wisdom teeth in the patient's oral three-dimensional model.

[0026] Further, the obtaining the growth deviation value of each wisdom tooth includes:

[0027] Obtain the minimum bounding rectangle of each tooth region in the enhanced image of the oral sagittal CT image;

[0028] Record the angle between the direction of the long side of the minimum bounding rectangle of each tooth region and the preset direction as the direction index of the corresponding tooth region; calculate the absolute value of the difference between the length and the width of the minimum bounding rectangle of each tooth region as the shape index of each tooth region;

[0029] According to the differences in the direction indexes and the shape indexes of each wisdom tooth and its corresponding control tooth in the corresponding tooth regions in the enhanced image of the oral sagittal CT image in the three-dimensional oral model of the patient, obtain the local normal deviation value of each wisdom tooth and its corresponding control tooth; take the sum of the local growth deviation values of each wisdom tooth and all its control teeth in the three-dimensional oral model as the growth deviation value of each wisdom tooth.

[0030] Further, the determining the impacted wisdom teeth among all the wisdom teeth in the three-dimensional oral model of the patient by using the impacted feature value includes:

[0031] For all the wisdom teeth in the three-dimensional oral model of the patient, regard the wisdom teeth corresponding to the impacted feature values greater than the preset judgment threshold as the impacted wisdom teeth in the three-dimensional oral model of the patient.

[0032] Further, the obtaining the analysis region in each oral CT image includes:

[0033] Perform edge detection on each oral CT image to obtain edge pixel points, perform curve fitting on the edge pixel points to obtain the edge lines in each oral CT image; regard the closed region formed by each edge line as the analysis region in each oral CT image.

[0034] Further, the obtaining the control teeth of each wisdom tooth in the three-dimensional oral model of the patient includes:

[0035] Use the FDI tooth position recording method to mark the teeth in the three-dimensional oral model of the patient, and regard the teeth in the same quadrant as each wisdom tooth as the control teeth of each wisdom tooth.

[0036] Further, the edge detection of each oral CT image is the Sobel operator.

[0037] The present invention has the following beneficial effects:

[0038] First aspect: The artifacts appearing in the CT images will interfere with the tooth tissue structure and increase the complexity of the enhanced images. In order to improve the accuracy of subsequent analysis, the oral CT images are filtered by combining the shape features, edge clarity features and gray scale distribution features of the tooth part and the artifact part to remove the artifact part in the images and obtain the enhanced images of the oral CT images; using the enhanced images for analysis can effectively reduce the interference of the artifacts on the process of identifying impacted wisdom teeth and improve the accuracy of identifying impacted wisdom teeth.

[0039] Second aspect: There are obvious differences in the shape regularity, size, and growth inclination direction between impacted wisdom teeth and normal wisdom teeth. By analyzing these characteristics in different-dimensional images such as the sagittal, axial, and coronal images of the oral cavity, the possibility that the wisdom teeth in the oral three-dimensional model are impacted wisdom teeth is determined, and then the impacted wisdom teeth of the patient are identified. By analyzing the characteristics of the impacted wisdom teeth in the enhanced images of the oral CT images from different perspectives, the problem that the accuracy rate of the possibility of identifying wisdom teeth as impacted wisdom teeth due to errors in the relevant data in the images from a single perspective is effectively solved, and the accuracy rate of identifying impacted wisdom teeth is further improved. Brief Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a flowchart of the steps of a method for assisting in the identification of impacted teeth based on oral three-dimensional imaging provided by an embodiment of the present invention;

[0042] Figure 2 It is a flowchart of the steps of a method for obtaining enhanced images of oral CT images provided by an embodiment of the present invention;

[0043] Figure 3 It is a flowchart of the steps of a method for determining impacted wisdom teeth provided by an embodiment of the present invention;

[0044] Figure 4 It is a system structure diagram of a system for assisting in the identification of impacted teeth based on oral three-dimensional imaging provided by an embodiment of the present invention;

[0045] Figure 5 It is a schematic diagram of a computer device of a device for assisting in the identification of impacted teeth based on oral three-dimensional imaging provided by an embodiment of the present invention. Detailed Embodiments

[0046] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific embodiments, structures, features, and effects of a method for assisting in the identification of impacted teeth based on oral three-dimensional imaging proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0048] The following specifically describes the specific solution of a method for assisting in the identification of impacted teeth based on three-dimensional oral images provided by the present invention with reference to the accompanying drawings.

[0049] Example 1:

[0050] The present invention proposes a method for assisting in the identification of impacted teeth based on three-dimensional oral images. Please refer to Figure 1 , which shows a flowchart of the steps of a method for assisting in the identification of impacted teeth based on three-dimensional oral images provided by an embodiment of the present invention. The method includes:

[0051] Step S1: Obtain the oral CT images of the patient. The oral CT images include: oral axial CT images, oral coronal CT images, and oral sagittal CT images.

[0052] Specifically, use a cone beam X-ray computed tomography system to scan the patient's oral cavity to obtain the patient's oral computed tomography (CT) images. The oral CT images include: oral axial CT images, oral coronal CT images, and oral sagittal CT images. It should be noted that CT images are usually grayscale images.

[0053] Step S2: Obtain the analysis region in each oral CT image; perform filtering processing on the edge pixel points in each oral CT image according to the degree of gray-scale change of each edge pixel point, the shape, edge clarity, and gray-scale distribution of the analysis region where each edge pixel point is located, to obtain the enhanced image of each oral CT image.

[0054] In oral CT images, artifacts usually interfere with the real structure, and may even cover up real lesions or structures, affecting the doctor's judgment of CT images. Moreover, during feature extraction, artifacts increase the complexity of the images, affecting subsequent analysis and processing. Therefore, it is necessary to perform artifact removal processing on oral CT images.

[0055] First, obtain the analysis region in the oral CT image. The analysis region may be the tooth region and the artifact region. In this embodiment, the method for obtaining the analysis region is: perform edge detection on each oral CT image to obtain edge pixel points, perform curve fitting on the edge pixel points to obtain the edge lines in each oral CT image; use the closed region formed by each edge line as the analysis region in each oral CT image.

[0056] It should be noted that the Sobel operator is selected to perform edge detection on the oral CT image, and the least squares method is used to perform curve fitting on the edge pixel points in the oral CT image. Among them, both the Sobel operator and the least squares method are well-known techniques to those skilled in the art and will not be elaborated here.

[0057] The characteristics of the tooth part in the CT image are as follows: the tooth part shows obvious regular structural characteristics, the gray level distribution is relatively uniform and there is an obvious boundary with the surrounding tissues; the characteristics of the artifact part in the CT image are as follows: the artifact may appear as irregular shadows or stripes, the gray level distribution is uneven and the boundary with the surrounding tissues is relatively blurred. The clarity of the edge of the analysis area reflects the clarity of the boundary between the analysis area and the surrounding tissues, and the degree of gray level change of the edge pixel points presents the clarity of the local edge position of the analysis area. Therefore, the degree of gray level change of the edge pixel points, the shape of the analysis area where the edge pixel points are located, the edge clarity and the gray level distribution can clearly distinguish the characteristics of the tooth part and the artifact part, determine the possibility that the edge pixel points are in the tooth area, so as to perform filtering processing on the oral CT image, remove the artifact part in the image, and obtain the enhanced image of the oral CT image.

[0058] Please refer to Figure 2 , which shows the step flowchart of a method for obtaining an enhanced image of an oral CT image provided by an embodiment of the present invention. The method includes:

[0059] Step S210: Obtain the tooth possibility value of each edge pixel point in each oral CT image according to the degree of gray level change of each edge pixel point in each oral CT image, the shape, edge clarity and gray level distribution of the analysis area where each edge pixel point is located.

[0060] Preferably, in some possible implementation manners of the embodiment of the present invention, the method for obtaining the tooth possibility value includes: for each oral CT image, obtain the shape gray level index of each analysis area according to the shape and gray level distribution of each analysis area in the oral CT image; calculate the average value of the absolute value of the difference between the gradient values of two adjacent edge pixel points on the edge of each analysis area in the oral CT image as the edge clarity index of each analysis area; obtain the tooth possibility value of each edge pixel point in the oral CT image according to the gradient value of each edge pixel point in the oral CT image, and the shape gray level index and edge clarity index of the analysis area where each edge pixel point is located.

[0061] In this embodiment, the method for obtaining the shape gray-scale index includes: for each analysis region in each oral CT image, obtaining the discrete index of the gray-scale values of all pixel points in the analysis region; calculating the central value of the gray-scale values of all pixel points in the analysis region; obtaining the geometric centroid and the gray-scale centroid of the analysis region, and taking the distance between the geometric centroid and the gray-scale centroid as the shape regularity value; obtaining the shape gray-scale index of the analysis region according to the discrete index, the central value and the shape regularity value; both the discrete index and the shape regularity value are negatively correlated with the shape gray-scale index, and the central value is positively correlated with the shape gray-scale index.

[0062] The discrete index of the gray-scale values of all pixel points in the analysis region reflects the degree of gray-scale dispersion in the analysis region and is used to measure the uniformity of the gray-scale distribution in the analysis region. The variance, standard deviation, quartile deviation and range of a set of data can all reflect the degree of data dispersion. In this embodiment, the variance is selected as the discrete index, that is, the variance of the gray-scale values of the pixel points in the analysis region is used as the discrete index; if the discrete index is smaller, it indicates that the gray-scale distribution in the analysis region is more uniform, the shape gray-scale index is larger, and the possibility that the analysis region represents the tooth part is greater.

[0063] It is known that the tooth part is relatively clear and the artifact part is relatively blurred; the central value of the gray-scale values of the pixel points in the analysis region is used to measure the clarity of the analysis region, and the central value represents the overall gray-scale level of the pixel points in the analysis region. The mean, median and mode can all represent the overall level of a set of data. In this embodiment, the mean is selected as the central value, that is, the mean of the gray-scale values of the pixel points in the analysis region is used as the central value; if the central value is larger, it indicates that the analysis region is clearer, the shape gray-scale index is larger, and the possibility that the analysis region represents the tooth part is greater.

[0064] The gray-scale centroid of the analysis region represents the center of the gray-scale distribution in the analysis region; the distance between the geometric centroid and the gray-scale centroid of the analysis region, that is, the shape regularity value, is used to measure the degree of shape regularity of the analysis region. If the shape regularity value is smaller, it indicates that the gray-scale in the analysis region is relatively uniform, that is, the gray-scale distribution is more consistent with the geometric shape, and the possibility that the shape of the analysis region is symmetric is greater, that is, the shape of the analysis region is more regular, the shape gray-scale index is larger, and the possibility that the analysis region represents the tooth part is greater. If the shape regularity value is larger, it indicates that there are significant brightness differences inside the analysis region and the complexity of the region shape is greater, that is, the shape of the analysis region is more irregular, and the possibility that the analysis region represents the artifact part is greater. Among them, the method for obtaining the geometric centroid and the gray-scale centroid of the region is a well-known technology and will not be elaborated here.

[0065] In summary, both the discrete index and the shape regularity value are negatively correlated with the shape grayness index, and the concentration value is positively correlated with the shape grayness index. In the embodiments of the present invention, the product of the discrete index and the shape regularity value of the analysis region is used as the numerator, and the ratio obtained by using the concentration value as the denominator is subjected to negative correlation mapping to obtain the shape regularity value of the analysis region; if the shape regularity value is larger, the greater the possibility that the analysis region represents the tooth region, and the greater the tooth possibility value.

[0066] In the embodiments of the present invention, the correlation relationship between the discrete index, the shape regularity value, the concentration value and the shape grayness index can also be constructed through other basic mathematical operations, which will not be limited and elaborated herein.

[0067] Since there is an obvious boundary between the tooth tissue and the surrounding tissue, but the boundary between the artifact part and the surrounding tissue is relatively blurred, the gradient values of the edge pixel points of the tooth part are generally larger, the gradient values of the edge pixel points of the artifact part are smaller and the gradient values are relatively random, so the difference in the gradient values of adjacent edge pixel points on the edge of the tooth part is smaller, and the difference in the gradient values of adjacent edge pixel points on the edge of the artifact part is larger. Therefore, the average value of the absolute value of the difference in the gradient values of two adjacent edge pixel points on the edge of the analysis region can measure the edge clarity of the analysis region to obtain the edge clarity index. If the edge clarity index is smaller, the boundary between the analysis region and the surrounding tissue is clearer, the greater the possibility that the analysis region represents the tooth region, and the greater the tooth possibility value.

[0068] The gradient value of the edge pixel point represents the local edge clarity. When the gradient value of the edge pixel point is larger, the local edge clarity is greater, and the greater the possibility that the edge pixel point is on the edge of the tooth region, and the greater the tooth possibility value.

[0069] Therefore, both the gradient value of the edge pixel point and the shape grayness index are positively correlated with the tooth possibility value, and the edge clarity index is negatively correlated with the tooth possibility value.

[0070] In a specific implementation manner of the embodiments of the present invention, the tooth possibility value is expressed by the formula:

[0071] p a =Norm(G a ×exp(-BQ a )×XH a )

[0072]

[0073] In the formula, p a is the tooth possibility value of the ath edge pixel point in each oral CT image; G a is the gradient value of the ath edge pixel point in each oral CT image; BQ ais the edge clarity index of the analysis area where the a-th edge pixel point is located in each oral CT image; XH a is the shape gray level index of the analysis area where the a-th edge pixel point is located in each oral CT image; σ a is the discrete index of the gray level values of the pixel points within the analysis area where the a-th edge pixel point is located in each oral CT image; is the central value of the gray level values of the pixel points within the analysis area where the a-th edge pixel point is located in each oral CT image; D a is the shape regularity value of the analysis area where the a-th edge pixel point is located in each oral CT image; Norm is the normalization function; exp is the exponential function with the natural constant as the base. It should be noted that if the tooth possibility value p a is larger, the possibility that the a-th edge pixel point is at the edge of the tooth tissue is greater.

[0074] Step S220: For each oral CT image, randomly select an edge pixel point in the oral CT image as the point to be filtered, use the tooth possibility value as the weight of the gray level values of the remaining edge pixel points except the point to be filtered within the preset filtering window of the point to be filtered, obtain the weighted average value as the filtered gray level value of the point to be filtered.

[0075] Filter each edge pixel point by using other edge pixel points within the local area of each edge pixel point; the tooth possibility values of the edge pixel points within the local area of the edge pixel points of the tooth part are larger, so that the gray level value after filtering of the edge pixel points of the tooth part is still larger; however, the tooth possibility values of the edge pixel points within the local area of the edge pixel points of the artifact part are smaller, so that the gray level value after filtering of the edge pixel points of the artifact part is smaller, thereby achieving the purpose of removing the artifact part in the oral CT image.

[0076] Taking any edge pixel point in the oral CT image, i.e., the point to be filtered, as an example, the filtered gray level value of the point to be filtered is expressed by the formula:

[0077]

[0078] In the formula, I g is the filtered gray level value of the point to be filtered; g is the point to be filtered; W is the total number of the remaining edge pixel points except the point to be filtered within the preset filtering window of the point to be filtered; ρ g,w is the tooth possibility value of the w-th edge pixel point except the point to be filtered within the preset filtering window of the point to be filtered; I w is the gray level value of the w-th edge pixel point except the point to be filtered within the preset filtering window of the point to be filtered.

[0079] It should be noted that in this embodiment, the edge pixel points are located at the center position of their preset filtering window, and the size of the preset filtering window takes an empirical value of 9×9. The implementer can set it according to specific circumstances. The method for obtaining the filtering gray values of all edge pixel points in each oral CT image is the same as that for obtaining the filtering gray value of the point to be filtered.

[0080] Step S230: Update the gray values of the edge pixel points in the oral CT image by using the filtering gray values to obtain the enhanced image of the oral CT image.

[0081] The gray values of the non-edge pixel points in each oral CT image remain unchanged, and the gray values of the edge pixel points are replaced with the filtering gray values to obtain the enhanced image of the oral CT image; the enhanced image effectively removes the influence of artifacts and retains the features of the tooth part.

[0082] Step S3: Obtain the tooth regions in the enhanced image of each oral CT image; perform three-dimensional reconstruction on the enhanced images of all oral CT images to obtain an oral three-dimensional model, and determine the wisdom teeth in the oral three-dimensional model; according to the shape difference and inclination difference between the tooth regions corresponding to each wisdom tooth in the enhanced image of the oral sagittal CT image and the remaining tooth regions, the area of the tooth region corresponding to each wisdom tooth in the enhanced image of the oral axial CT image, and the spacing between adjacent tooth regions in the enhanced image of the oral coronal CT image, determine the impacted wisdom teeth in the patient's oral three-dimensional model.

[0083] To analyze the tooth features, obtain the tooth regions in the enhanced image of the oral CT image. It should be noted that in this embodiment, the method for obtaining the tooth regions is the same as that for obtaining the analysis regions. However, since the enhanced image of the oral CT image has effectively removed the influence of artifacts, the region obtained by edge detection of the enhanced image is only the tooth region. Other embodiments can also choose methods such as contour extraction and region growing to obtain the tooth regions.

[0084] By using the CT reconstruction method for the enhanced image of the patient's oral axial CT image, the enhanced image of the oral coronal CT image, and the enhanced image of the oral sagittal CT image, obtain the patient's oral three-dimensional model. Use the Fédération Dentaire Internationale (FDI) tooth position recording method to label the teeth in the patient's oral three-dimensional model. In this embodiment, the teeth numbered 18, 28, 38, and 48 are used as wisdom teeth; this solution only identifies impacted wisdom teeth from the wisdom teeth. Among them, the FDI tooth position recording method is well-known content and will not be elaborated here.

[0085] Impacted wisdom teeth may exhibit irregular shapes, be smaller in size and grow obliquely. However, the shapes of normal wisdom teeth are more regular, their sizes are larger, and their growth directions are perpendicular. Additionally, due to the compression of impacted wisdom teeth by surrounding teeth or bones, the spacing between an impacted wisdom tooth and its adjacent teeth is smaller than that between normal adjacent teeth. Therefore, by analyzing the shape differences and inclination degree differences between the corresponding tooth regions and the remaining tooth regions of each wisdom tooth in the enhanced image of the oral sagittal CT image, and combining the area of the corresponding tooth region of the wisdom tooth in the enhanced image of the oral axial CT image with the spacing of the adjacent tooth regions in the enhanced image of the oral coronal CT image for analysis, impacted wisdom teeth can be determined.

[0086] Please refer to Figure 3 , which shows a flowchart of the steps of a method for determining impacted wisdom teeth provided by an embodiment of the present invention. The method includes:

[0087] Step S310: Obtain the reference teeth of each wisdom tooth in the oral three-dimensional model of the patient; according to the shape differences and inclination degree differences between the corresponding tooth regions of each wisdom tooth and its reference teeth in the enhanced image of the oral sagittal CT image, obtain the growth deviation value of each wisdom tooth.

[0088] The FDI tooth position recording method divides the teeth in the oral cavity into four quadrants, and the teeth in the same quadrant as each wisdom tooth are recorded as the reference teeth of each wisdom tooth. As an example, in the upper right quadrant, the teeth numbered 11, 12, 13, 14, 15, 16, and 17 are the reference teeth of the tooth numbered 18, and each wisdom tooth has 7 reference teeth.

[0089] Due to the growth restriction of impacted wisdom teeth caused by the compression of surrounding teeth or bones, impacted wisdom teeth may exhibit irregular shapes and be smaller in size, and may even grow obliquely. However, because normal wisdom teeth have sufficient growth space, the shapes of normal wisdom teeth are more regular, their sizes are larger, and their growth directions are perpendicular. This solution assumes that the growth conditions of the reference teeth of each wisdom tooth are good, that is, the sizes of the reference teeth are relatively regular and they grow perpendicular to the horizontal plane; the sagittal view provides a perspective for observing the oral structure from the side and can clearly show the vertical growth of the teeth.

[0090] The shape and inclination degree of the corresponding tooth regions of the reference teeth of the wisdom teeth in the enhanced image of the oral sagittal CT image both represent the normal tooth growth conditions. The shape differences and inclination degree differences between the corresponding tooth regions of each wisdom tooth and its reference teeth in the enhanced image of the oral sagittal CT image in the oral three-dimensional model represent the degree of deviation of the growth conditions of the wisdom teeth compared to normal teeth, and the growth deviation value of the wisdom teeth is obtained.

[0091] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the growth deviation value of each wisdom tooth includes: obtaining the minimum circumscribed rectangle of each tooth region in the enhanced image of the oral sagittal CT image; recording the included angle between the direction of the long side of the minimum circumscribed rectangle of each tooth region and the preset direction as the direction index of the corresponding tooth region; calculating the absolute value of the difference between the length and width of the minimum circumscribed rectangle of each tooth region as the shape index of each tooth region; obtaining the local normal deviation value of each wisdom tooth and each of its corresponding control teeth according to the differences in the direction index and the shape index of the corresponding tooth regions in the enhanced image of the oral sagittal CT image of each wisdom tooth and each of its corresponding control teeth in the patient's oral three-dimensional model; and taking the sum of the local growth deviation values of each wisdom tooth and all of its corresponding control teeth in the oral three-dimensional model as the growth deviation value of each wisdom tooth.

[0092] In the sagittal view of the oral cavity, the direction of the long side of the minimum circumscribed rectangle of each tooth region is usually close to the vertical direction. The direction index of the tooth region is used to measure the growth direction of the tooth, that is, the degree of inclination. Since the shape of a normal wisdom tooth is relatively regular, the length and width of the minimum circumscribed rectangle of the tooth region are relatively close. An impacted wisdom tooth may have an irregular shape, so the difference between the length and width of the minimum circumscribed rectangle of the impacted wisdom tooth is relatively large. Therefore, in this embodiment, the absolute value of the difference between the length and width of the minimum circumscribed rectangle of each tooth region in the enhanced image of the oral sagittal CT image is used as the shape index to measure the shape regularity feature of the tooth region.

[0093] If the differences in the direction index and the shape index of the corresponding tooth regions of each wisdom tooth and its corresponding control teeth in the enhanced image of the oral sagittal CT image are both larger, then the difference in the shape and growth direction of the wisdom tooth compared to the normal tooth is larger, the local normal deviation value is larger, and the possibility that the wisdom tooth is an impacted wisdom tooth is greater. Therefore, in the embodiments of the present invention, the product of the differences in the direction index and the shape index of the corresponding tooth regions of each wisdom tooth and each of its corresponding control teeth in the enhanced image of the oral sagittal CT image is used as the local normal deviation value. By analyzing the deviation situation of the wisdom tooth and all of its corresponding control teeth, the growth deviation value is obtained.

[0094] It should be noted that in the embodiments of the present invention, the preset direction is the horizontal direction, and the value range of the direction index of the tooth region is [0°, 90°].

[0095] In a specific implementation manner of the embodiments of the present invention, the growth deviation value of each wisdom tooth is expressed by the formula:

[0096]

[0097] In the formula, SP is the growth deviation value of each wisdom tooth in the patient's oral three-dimensional model; θ 0It is the direction index of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral sagittal CT image in the three-dimensional oral model of the patient; θ m It is the direction index of the m-th control tooth of each wisdom tooth in the three-dimensional oral model of the patient in the corresponding tooth region in the enhanced image of the oral sagittal CT image; X 0 It is the shape index of the corresponding tooth region of each wisdom tooth in the three-dimensional oral model of the patient in the enhanced image of the oral sagittal CT image; X m It is the shape index of the m-th control tooth of each wisdom tooth in the three-dimensional oral model of the patient in the corresponding tooth region in the enhanced image of the oral sagittal CT image; |θ 0 -θ m |×|X 0 -X m | is the local normal deviation value of each wisdom tooth in the three-dimensional oral model of the patient from its m-th control tooth; M is the total number of control teeth of each wisdom tooth in the three-dimensional oral model of the patient; || is the absolute value function; Norm is the normalization function.

[0098] Step S320: Obtain the spacing between two adjacent tooth regions in the enhanced image of the oral coronal CT image; the spacings between two adjacent teeth among all the control teeth of each wisdom tooth in the three-dimensional oral model in the corresponding two tooth regions in the enhanced image of the oral coronal CT image form the tooth spacing set of each wisdom tooth; the sum of the absolute values of the differences between the spacing between each wisdom tooth and its adjacent tooth in the corresponding two tooth regions in the enhanced image of the oral coronal CT image and each element in the tooth spacing set is used as the normal spacing difference value of each wisdom tooth.

[0099] Use MydentalX software to measure the spacing between two adjacent tooth regions in the enhanced image of the oral coronal CT image.

[0100] Taking the upper right quadrant of the oral cavity as an example for analysis, the teeth numbered 11, 12, 13, 14, 15, 16, and 17 are the control teeth of the tooth numbered 18. The numbers of two adjacent teeth among all the control teeth of the wisdom tooth numbered 18 include: (11, 12), (12, 13), (13, 14), (14, 15), (15, 16), (16, 17); the spacings between the above two adjacent teeth form the tooth spacing set of the wisdom tooth numbered 18.

[0101] The coronal view provides a front-to-back sectional view of the oral cavity; due to the impacted wisdom tooth being compressed by the surrounding teeth or bones, resulting in the spacing between the impacted wisdom tooth and its adjacent tooth being less than the spacing between normal adjacent teeth, the normal spacing difference value is determined based on the differences in these two types of spacings, and the possibility of the wisdom tooth being impacted is measured by the spacing between the teeth.

[0102] The distance between two adjacent teeth among all the reference teeth of each wisdom tooth is the normal tooth distance. The greater the difference between the distance between each wisdom tooth and its adjacent tooth and the elements in the tooth distance set, the greater the likelihood that each wisdom tooth is an impacted wisdom tooth. Therefore, the sum of the absolute values of the differences between the distance between each wisdom tooth and its adjacent tooth in the enhanced image of the oral coronal CT image of the oral three-dimensional model and each element in the tooth distance set is used as the normal distance difference value of each wisdom tooth. If the normal distance difference value is greater, it indicates that the difference between the distance between each wisdom tooth and its adjacent tooth and the normal tooth distance is greater, and thus the likelihood that each wisdom tooth is an impacted wisdom tooth is greater.

[0103] It should be noted that each wisdom tooth in the oral three-dimensional model has only one adjacent tooth. The adjacent tooth of the wisdom tooth numbered 18 is numbered 17, the adjacent tooth of the wisdom tooth numbered 28 is numbered 27, the adjacent tooth of the wisdom tooth numbered 38 is numbered 37, and the adjacent tooth of the wisdom tooth numbered 48 is numbered 47.

[0104] Step S330: Obtain the impacted feature value of each wisdom tooth according to the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image of the oral three-dimensional model, the growth deviation value, and the normal interval difference value; the area and the impacted feature value are negatively correlated, and both the growth deviation value and the normal interval difference value are positively correlated with the impacted feature value; use the impacted feature value to determine the impacted wisdom teeth among all the wisdom teeth in the patient's oral three-dimensional model.

[0105] Impacted wisdom teeth are partially or completely buried under the gum due to insufficient space, incorrect angle, or interference from other teeth, so the occlusal surface of impacted wisdom teeth is usually smaller; normal wisdom teeth can usually erupt completely, so the occlusal surface of impacted wisdom teeth is usually smaller than that of normal wisdom teeth. The axial view provides a view of the teeth on the horizontal plane and can clearly show the occlusal surface of the teeth, that is, the corresponding tooth region of the wisdom tooth in the enhanced image of the oral axial CT image represents the occlusal surface of the wisdom tooth. The smaller the area of this occlusal surface, the less the wisdom tooth has erupted completely, and the greater the likelihood that the wisdom tooth is an impacted wisdom tooth.

[0106] Therefore, the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image and the impacted feature value are negatively correlated, and both the growth deviation value and the normal interval difference value are positively correlated with the impacted feature value. If the impacted feature value of the wisdom tooth is greater, the likelihood that the wisdom tooth is an impacted wisdom tooth is greater.

[0107] In the embodiment of the present invention, a negative correlation mapping is performed on the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image of the patient's oral three-dimensional model, and the product of the growth deviation value, the normal interval difference value, and the negative correlation mapping result is normalized to obtain the impacted feature value of each wisdom tooth.

[0108] In the embodiments of the present invention, the correlation relationship between the area of the corresponding tooth region of each wisdom tooth in the enhanced image of the oral axial CT image, the growth deviation value, and the normal interval difference value can also be constructed through other basic mathematical operations, which will not be limited and elaborated here.

[0109] It should be noted that in the embodiments of the present invention, the Norm function is used for normalization processing, and the reciprocal of the area of the tooth region is taken to achieve negative correlation mapping; other normalization methods such as function transformation and maximum-minimum normalization can also be selected, and negative numbers are taken and negative correlation mapping is performed through function conversion, which will not be limited here. In this embodiment, the total number of pixel points in the tooth region is used as the area of the tooth region.

[0110] For all wisdom teeth in the patient's oral three-dimensional model, the wisdom teeth corresponding to the impaction characteristic values greater than the preset judgment threshold are used as the impacted wisdom teeth in the patient's oral three-dimensional model. It should be noted that in this embodiment, the preset judgment threshold takes an empirical value of 0.7, and the implementer can set it according to specific circumstances.

[0111] In order to facilitate the identification of the impacted wisdom teeth of other patients, the patient's oral three-dimensional model is input into a pre-trained neural network, and the numbers of the impacted wisdom teeth in the oral three-dimensional model are output.

[0112] The present invention identifies the impacted wisdom teeth in the oral three-dimensional model through a convolutional neural network. The input of the neural network is the patient's oral three-dimensional model, and the output is the numbers of the impacted wisdom teeth in the oral three-dimensional model.

[0113] Among them, the relevant content of the convolutional neural network includes: the data set of the neural network is divided into a training set and a validation set; the training process of the neural network is the recognition process of the impacted wisdom teeth in the oral three-dimensional model, and the specific recognition process is: in the oral three-dimensional model, the numbers of the impacted wisdom teeth are obtained; the loss function of the neural network is the cross-entropy function. Among them, the convolutional neural network is a well-known technology to those skilled in the art and will not be elaborated here. It should be noted that the numbers of the impacted wisdom teeth refer to the numbers of teeth in the FDI tooth position recording method.

[0114] So far, the present invention is completed.

[0115] Embodiment 2:

[0116] The present invention provides an impacted tooth assisted recognition system based on oral three-dimensional imaging. Please refer to Figure 4 , which shows the system structure diagram of an impacted tooth assisted recognition system based on oral three-dimensional imaging provided by an embodiment of the present invention. The system includes:

[0117] A data acquisition module 410 is configured to obtain oral CT images of a patient. The oral CT images include: axial oral CT images, coronal oral CT images, and sagittal oral CT images.

[0118] An image enhancement module 420 is configured to obtain an analysis region in each oral CT image; filter edge pixels in each oral CT image according to the degree of gray-scale change of each edge pixel, the shape, edge sharpness, and gray-scale distribution of the analysis region where each edge pixel is located in each oral CT image, so as to obtain an enhanced image of each oral CT image.

[0119] An impacted wisdom tooth recognition module 430 is configured to obtain a tooth region in the enhanced image of each oral CT image; perform three-dimensional reconstruction on the enhanced images of all oral CT images to obtain an oral three-dimensional model, and determine wisdom teeth in the oral three-dimensional model; determine impacted wisdom teeth in the oral three-dimensional model of the patient according to the shape difference and inclination degree difference between the tooth region corresponding to each wisdom tooth and the remaining tooth regions in the enhanced image of the oral sagittal CT image, the area of the tooth region corresponding to each wisdom tooth in the enhanced image of the oral axial CT image, and the spacing between adjacent tooth regions in the enhanced image of the oral coronal CT image.

[0120] It should be noted that: for the device provided in the above embodiment, only the division of the above functional modules is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, an impacted tooth assisted recognition system based on oral three-dimensional images and an embodiment of an impacted tooth assisted recognition method provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be elaborated here.

[0121] Embodiment 3:

[0122] Figure 5 The figure is a schematic diagram of a computer device of an impacted tooth assisted recognition device based on oral three-dimensional images provided by an embodiment of the present invention. Exemplarily, as Figure 5 shown, the computer device includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502. When the processor 502 executes the computer program 503, the computer device can execute any one of the impacted tooth assisted recognition methods based on oral three-dimensional images introduced above.

[0123] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor. Among them, executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute an impacted tooth assisted recognition method based on three-dimensional oral images provided by an embodiment of the present application.

[0124] This embodiment can divide the functions of the device according to the above method example. For example, it can correspond to each functional module, or integrate two or more functions into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0125] It should be understood that the device provided in this embodiment is used to execute the above-mentioned impacted tooth assisted recognition method based on three-dimensional oral images, so the same effect as the above implementation method can be achieved.

[0126] In the case of adopting an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc.

[0127] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits included in the disclosure of the present application. The processor can also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0128] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0130] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for assisting the identification of impacted teeth based on three-dimensional oral images, characterized in that: The method includes: Acquire an oral CT image of the patient, wherein the oral CT image includes: an oral axial CT image, an oral coronal CT image, and an oral sagittal CT image; Acquire the analysis area in each oral CT image; perform filtering processing on the edge pixels in each oral CT image according to the grayscale change degree of each edge pixel in each oral CT image, the shape, edge clarity and grayscale distribution of the analysis area where each edge pixel is located, and obtain an enhanced image of each oral CT image; The tooth region in the enhanced image of each oral CT image is obtained; the enhanced images of all oral CT images are three-dimensionally reconstructed to obtain an oral three-dimensional model, and the wisdom teeth in the oral three-dimensional model are determined; the impacted wisdom teeth in the patient's oral three-dimensional model are determined based on the shape difference and inclination difference between the tooth region corresponding to each wisdom tooth in the enhanced image of the oral sagittal CT image and the remaining tooth regions in the oral three-dimensional model, the area of ​​the tooth region corresponding to each wisdom tooth in the enhanced image of the oral axial CT image, and the distance between adjacent tooth regions in the enhanced image of the oral coronal CT image.

2. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 1, characterized in that: The method for acquiring the enhanced image of each oral CT image comprises: According to the grayscale change degree of each edge pixel point in each oral CT image, the shape, edge clarity and grayscale distribution of the analysis area where each edge pixel point is located, the possible tooth value of each edge pixel point in each oral CT image is obtained; For each oral CT image, an edge pixel point in the oral CT image is randomly selected and recorded as the point to be filtered, and the tooth possible value is used as the weight of the grayscale values ​​of the remaining edge pixels except the point to be filtered in the preset filtering window of the point to be filtered, and the weighted average value is obtained as the filtered grayscale value of the point to be filtered; The grayscale values ​​of edge pixels in the oral CT image are updated using the filtered grayscale values ​​to obtain an enhanced image of the oral CT image.

3. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 2, characterized in that: The step of obtaining the possible tooth value of each edge pixel point in each oral CT image includes: For each oral CT image, a shape grayscale index of each analysis area is obtained according to the shape and grayscale distribution of each analysis area in the oral CT image; The average of the absolute values ​​of the gradient differences between two adjacent edge pixels on the edge of each analysis area in the oral CT image is calculated as the edge clarity index of each analysis area; According to the gradient value of each edge pixel point in the oral CT image, and the shape gray index and the edge clarity index of the analysis area where each edge pixel point is located, the tooth possible value of each edge pixel point in the oral CT image is obtained.

4. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 3, characterized in that: The step of obtaining the shape grayscale index of each analysis area includes: For each analysis area in each oral CT image, a discrete index of the grayscale values ​​of all pixels in the analysis area is obtained; and a centralized value of the grayscale values ​​of all pixels in the analysis area is calculated; Obtaining the geometric centroid and the grayscale centroid of the analysis area, and taking the distance between the geometric centroid and the grayscale centroid as the shape rule value; The shape grayscale index of the analysis area is obtained according to the discrete index, the concentrated value and the shape regularity value; the discrete index and the shape regularity value are both negatively correlated with the shape grayscale index, and the concentrated value is positively correlated with the shape grayscale index.

5. The method for auxiliary identification of impacted teeth based on oral three-dimensional images according to claim 1, characterized in that: The method determines the impacted wisdom tooth in the patient's oral three-dimensional model according to the shape difference and inclination difference between the tooth region corresponding to each wisdom tooth in the enhanced image of the oral sagittal CT image and the remaining tooth regions in the oral three-dimensional model, the area of ​​the tooth region corresponding to each wisdom tooth in the enhanced image of the oral axial CT image, and the spacing between adjacent tooth regions in the enhanced image of the oral coronal CT image, including: Obtain a reference tooth for each wisdom tooth in the patient's three-dimensional oral model; obtain a growth deviation value for each wisdom tooth based on a shape difference and a tilt difference between each wisdom tooth in the three-dimensional oral model and its reference tooth in a corresponding tooth region in an enhanced image of an oral sagittal CT image; Obtaining the distance between two adjacent tooth areas in the enhanced image of the oral coronal CT image; forming a tooth distance set for each wisdom tooth by the distance between two adjacent teeth in all control teeth of each wisdom tooth in the oral three-dimensional model and the corresponding two tooth areas in the enhanced image of the oral coronal CT image; taking the sum of the distance between each wisdom tooth in the oral three-dimensional model and its adjacent teeth and the absolute value of the difference between the distance between two corresponding tooth areas in the enhanced image of the oral coronal CT image and each element in the tooth distance set as the normal distance difference value of each wisdom tooth; Obtain the impacted characteristic value of each wisdom tooth according to the area of ​​the tooth region corresponding to each wisdom tooth in the enhanced image of the oral axial CT image in the oral three-dimensional model, the growth deviation value and the normal interval difference value; the area is negatively correlated with the impacted characteristic value, and the growth deviation value and the normal interval difference value are both positively correlated with the impacted characteristic value; The impacted wisdom teeth among all the wisdom teeth in the patient's oral three-dimensional model are determined using the impacted characteristic value.

6. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 5, characterized in that: The step of obtaining the growth deviation value of each wisdom tooth includes: Obtaining the minimum circumscribed rectangle of each tooth region in the enhanced image of the oral sagittal CT image; The angle between the direction of the long side of the minimum circumscribed rectangle of each tooth area and the preset direction is recorded as the direction index of the corresponding tooth area; the absolute value of the difference between the length and the width of the minimum circumscribed rectangle of each tooth area is calculated as the shape index of each tooth area; According to the differences in the direction indicators and the shape indicators of the corresponding tooth areas between each wisdom tooth and each of its control teeth in the enhanced image of the oral sagittal CT image in the patient's oral three-dimensional model, the local normal deviation value of each wisdom tooth and each of its control teeth is obtained; the cumulative sum of the local growth deviation values ​​of each wisdom tooth and all of its control teeth in the oral three-dimensional model is used as the growth deviation value of each wisdom tooth.

7. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 5, characterized in that: The method of determining the impacted wisdom tooth among all wisdom teeth in the patient's oral three-dimensional model by using the impacted characteristic value includes: For all wisdom teeth in the patient's oral three-dimensional model, the wisdom teeth corresponding to the impaction characteristic values ​​greater than the preset judgment threshold are regarded as the impacted wisdom teeth in the patient's oral three-dimensional model.

8. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 1, characterized in that: The step of obtaining the analysis area in each oral CT image includes: Edge detection is performed on each oral CT image to obtain edge pixel points, and curve fitting is performed on the edge pixel points to obtain edge lines in each oral CT image; and the closed area formed by each edge line is used as the analysis area in each oral CT image.

9. The method for assisting in identifying impacted teeth based on oral three-dimensional images according to claim 5, characterized in that: The step of obtaining a reference tooth of each wisdom tooth in the patient's oral three-dimensional model comprises: The teeth in the patient's three-dimensional oral model were marked using the FDI tooth position recording method, and the teeth in the same quadrant as each wisdom tooth were recorded as the control teeth for each wisdom tooth.

10. The method for auxiliary identification of impacted teeth based on oral three-dimensional images according to claim 8, characterized in that: The edge detection for each oral CT image is performed using a Sobel operator.

Images