A dental caries visual identification method and system for oral implants

Abstract

The present invention relates to the field of image data processing technology, and specifically to a dental caries visual recognition method and system for oral implants, the method comprising: screening out a target tooth area from an acquired periapical film to be identified, and performing grayscale distribution analysis and brightness analysis on a preset neighborhood corresponding to each pixel point in each target tooth area; screening out suspected caries areas; drawing a target central axis of the target tooth area to which each suspected caries area belongs, determining a perpendicular line to the target central axis as a target perpendicular line, translating the target perpendicular line, and forming an intersection point group with the intersection point of each translated target perpendicular line and the edge of the suspected caries area; screening out a suspected pulp cavity point group from the set of intersection point groups corresponding to each suspected caries area; and screening out the target caries area based on all determined pulp cavity possibilities. The present invention improves the accuracy of identifying caries areas by performing image data processing on the periapical film to be identified.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method and system for visually identifying dental caries for oral implantation. Background Art

[0002] With the development of science and technology, the application of image processing is becoming more and more extensive. For example, it can be applied to dental caries identification. At present, the method commonly used to identify objects is to identify objects based on the grayscale values ​​of the collected object images.

[0003] However, when identifying caries based on grayscale values ​​from collected periapical films, the following technical problems often arise:

[0004] During the periapical radiograph acquisition process, the periapical radiograph may be blurred or have artifacts due to various factors such as improper film position fixation or improper X-ray vertical angle, resulting in the imaging grayscale of the tooth structure itself, such as the pulp cavity, being similar to the grayscale of the carious area. Therefore, when identifying caries containing carious areas, if only the difference in grayscale values ​​is considered, it may often cause misjudgment of carious pixels, resulting in poor accuracy in identifying carious areas, which in turn may lead to poor accuracy in identifying caries containing carious areas. Summary of the Invention

[0005] In order to solve the technical problem of poor accuracy in identifying carious areas, the present invention proposes a caries visual identification method and system for oral implants.

[0006] In a first aspect, the present invention provides a method for visually identifying dental caries for oral implants, the method comprising:

[0007] Filtering the target tooth area from the acquired periapical film to be identified, and performing grayscale distribution analysis and brightness analysis on the preset neighborhood corresponding to each pixel point in each target tooth area to obtain the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area;

[0008] Based on all grayscale distribution features and target brightness features, suspected caries areas are screened out from the target tooth area;

[0009] Draw a target central axis of the target tooth area to which each suspected caries area belongs, determine the perpendicular line of the target central axis as the target perpendicular line, translate the target perpendicular line, and form an intersection point group with the intersection point of each translated target perpendicular line and the edge of the suspected caries area to obtain a set of intersection point groups corresponding to each suspected caries area;

[0010] Screening out a suspected pulp cavity point group from the intersection point group set corresponding to each suspected caries lesion area, and obtaining a suspected pulp cavity point group set corresponding to each suspected caries lesion area;

[0011] Determine the pulp cavity possibility corresponding to each suspected caries area based on the contour chain code corresponding to each suspected caries area, the distance between each suspected caries area and the root endpoint within the target tooth area to which it belongs, and the set of suspected pulp cavity points corresponding to each suspected caries area;

[0012] According to all pulp cavity possibilities, the target caries lesion area is screened out from all suspected caries lesion areas.

[0013] In combination with the first aspect above, in a possible implementation, screening out the target tooth region from the acquired periapical radiograph to be identified includes:

[0014] Performing edge detection on the periapical slice to be identified and performing a morphological closing operation to obtain a target image;

[0015] determining the area enclosed by each closed contour in the target image as a suspected tooth area;

[0016] The maximum value of the consecutive repetition times corresponding to all chain code values ​​in the contour chain code of each suspected tooth area is determined as the target consecutive repetition time corresponding to each suspected tooth area;

[0017] The ratio of the area of ​​each suspected tooth region to the area of ​​its minimum circumscribed ellipse is determined as the target shape feature corresponding to each suspected tooth region;

[0018] Determine the aspect ratio of the minimum circumscribed rectangle corresponding to each suspected tooth region as a shape extension feature corresponding to each suspected tooth region;

[0019] Determining a tooth shape factor corresponding to each suspected tooth region according to the target continuous repetition number, target shape feature, and shape extension feature corresponding to each suspected tooth region, wherein the target continuous repetition number, target shape feature, and shape extension feature are all positively correlated with the tooth shape factor;

[0020] Normalizing the cumulative multiplication value of the target continuous repetition times, target shape features, and shape extension features corresponding to each suspected tooth region to obtain the tooth shape factor corresponding to each suspected tooth region;

[0021] If the tooth shape factor corresponding to the suspected tooth region is greater than a preset tooth shape threshold, the suspected tooth region is determined as the target tooth region.

[0022] In combination with the first aspect above, in one possible implementation, performing grayscale distribution analysis and brightness analysis on a preset neighborhood corresponding to each pixel point in each target tooth region to obtain grayscale distribution features and target brightness features corresponding to each pixel point in each target tooth region includes:

[0023] Determine any target tooth region as a marked tooth region, and determine any pixel point in the marked tooth region as a marked pixel point;

[0024] Determine the average of the grayscale values ​​corresponding to all pixels in a preset neighborhood corresponding to the marked pixel as a representative grayscale factor of the neighborhood corresponding to the marked pixel;

[0025] Determine the absolute value of the difference between the neighborhood representative grayscale factor corresponding to the marked pixel point and the grayscale value corresponding to each pixel point in the preset neighborhood corresponding to the marked pixel point as the target difference corresponding to each pixel point in the preset neighborhood corresponding to the marked pixel point;

[0026] Determine the cumulative value of the target differences corresponding to all pixels in a preset neighborhood corresponding to the marked pixel as the grayscale distribution feature corresponding to the marked pixel;

[0027] Determine the mean of the grayscale values ​​corresponding to all pixels in the marked tooth area as the tooth representative grayscale factor corresponding to the marked tooth area;

[0028] The ratio of the neighborhood representative grayscale factor to the tooth representative grayscale factor is determined as the target brightness feature corresponding to the marked pixel point.

[0029] In combination with the first aspect above, in one possible implementation, screening out suspected caries areas from the target tooth area based on all grayscale distribution features and target brightness features includes:

[0030] Determine the suspected caries factor corresponding to each pixel point in each target tooth area based on the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area, wherein the grayscale distribution characteristics are positively correlated with the suspected caries factor, and the target brightness characteristics are negatively correlated with the suspected caries factor;

[0031] If the suspected caries lesion factor corresponding to the pixel point is greater than the preset caries lesion threshold, the pixel point is determined as a suspected caries lesion pixel point;

[0032] Connected domains are extracted from the area formed by all suspected caries pixels, and the extracted connected domains are determined as suspected caries areas.

[0033] In combination with the first aspect above, in a possible implementation, screening out a suspected pulp cavity point group from the set of intersection point groups corresponding to each suspected caries area includes:

[0034] From the intersection point group set corresponding to each suspected caries area, an intersection point group with 2 intersection points and the intersection points located on both sides of the target central axis is selected as the suspected pulp cavity point group.

[0035] In combination with the first aspect above, in a possible implementation, the formula corresponding to the pulp cavity probability corresponding to the suspected caries area is:

[0036] ;

[0037] ;

[0038] ;

[0039] ;

[0040] in, It is The probability of the pulp cavity corresponding to the suspected carious lesion area; is the serial number of the suspected caries lesion area; is the normalization function; It is The maximum value of the number of consecutive repetitions of all chain code values ​​within the contour chain code of the suspected caries area; The independent variable takes the value The function value when , and and There is a negative correlation; is a factor that is preset to be greater than 0; It is The mean value of the suspected caries factors corresponding to all pixels in the suspected caries area; It is The distance between a suspected carious area and a random root endpoint within the target tooth area to which it belongs; is the activation function, used for normalization; It is The number of suspected pulp cavity point groups in the set of suspected pulp cavity point groups corresponding to the suspected caries area; It is The number of pixels on the edge of the suspected caries area; The independent variable takes the value The function value when , and and There is a negative correlation; is a factor that is preset to be greater than 0; Characterization The average distance difference between the two intersection points and the target central axis in all suspected pulp cavity point groups corresponding to the suspected caries area; It is The sequence number of the suspected pulp cavity point group in the set of suspected pulp cavity point groups corresponding to the suspected caries area; It is the absolute value function; It is The first point in the set of suspected pulp cavity points corresponding to the suspected caries area In the group of suspected medullary cavity points, the first intersection point and the The distance between the target central axes of the target tooth areas to which the suspected caries areas belong; It is The first point in the set of suspected pulp cavity points corresponding to the suspected caries area In the group of suspected medullary cavity points, the second intersection point The distance between the target central axes of the target tooth areas to which the suspected caries areas belong.

[0041] In combination with the first aspect above, in a possible implementation, the method further includes:

[0042] Determining a caries severity index corresponding to each target caries lesion area according to the caries extension direction of each target caries lesion area and the tooth extension direction of the target tooth area to which it belongs, as well as the area of ​​each target caries lesion area;

[0043] The target tooth region to which the target caries region belongs is determined as a candidate tooth region, and pixel points adjacent to the target gingival region are screened from the contour of each candidate tooth region as target contour points, wherein the target gingival region is the gingival region in the periapical film to be identified;

[0044] Screening out gingival inflammation points from the target gingival region, and screening out inflamed contour points from all target contour points, screening out subgingival regions corresponding to each candidate tooth region from the target gingival region, and screening out effective caries regions from all target caries regions based on caries severity indicators corresponding to the target caries regions, wherein the effective caries regions represent target caries regions with a caries severity change trend;

[0045] The caries severity level corresponding to each candidate tooth area is determined based on the number of gingival inflammation points in the sub-gingival area corresponding to each candidate tooth area, as well as the number of inflammation contour points and the number of effective caries areas in each candidate tooth area. Among them, the number of gingival inflammation points, the number of inflammation contour points and the number of effective caries areas are all positively correlated with the caries severity level.

[0046] In conjunction with the first aspect above, in one possible implementation, determining the caries severity index corresponding to each target caries lesion area based on the caries lesion extension direction of each target caries lesion area and the tooth extension direction of the target tooth area to which it belongs, as well as the area of ​​each target caries lesion area, includes:

[0047] The angle between the caries extension direction of each target caries lesion area and the tooth extension direction of the target tooth area to which it belongs is determined as a caries extension feature corresponding to each target caries lesion area;

[0048] The caries severity index corresponding to each target caries lesion area was determined based on the pulp cavity possibility, caries extension characteristics, and area corresponding to each target caries lesion area. The pulp cavity possibility and caries extension characteristics were negatively correlated with the caries severity index, while the area of ​​the target caries lesion area was positively correlated with its caries extension characteristics.

[0049] In combination with the first aspect above, in a possible implementation, screening out effective caries lesion areas from all target caries lesion areas according to the caries lesion severity index corresponding to the target caries lesion area includes:

[0050] Along the tooth extension direction of the target tooth area, the target caries areas in the target tooth area are sorted in sequence, and any target caries area in the target tooth area is determined as a marked caries area. If the caries severity index corresponding to the marked caries area is less than the caries severity index corresponding to the next target caries area, the marked caries area is determined as a valid caries area.

[0051] In a second aspect, the present invention provides a dental caries visual recognition system for oral implants, comprising a processor and a memory, wherein the processor is configured to process instructions stored in the memory to implement the method of the first aspect or any possible implementation of the first aspect. The dental caries visual recognition system for oral implants may specifically include:

[0052] A screening and processing module is used to screen out target tooth areas from the acquired periapical films to be identified, and perform grayscale distribution analysis and brightness analysis on a preset neighborhood corresponding to each pixel point in each target tooth area to obtain grayscale distribution features and target brightness features corresponding to each pixel point in each target tooth area;

[0053] A suspected caries area screening module is used to screen out suspected caries areas from the target tooth area based on all grayscale distribution characteristics and target brightness characteristics;

[0054] A data line construction module is used to determine the target central axis of the target tooth area to which each suspected caries area belongs, determine the perpendicular line to the target central axis as the target perpendicular line, translate the target perpendicular line, and form an intersection point group with the intersection point of each translated target perpendicular line and the edge of the suspected caries area to obtain a set of intersection point groups corresponding to each suspected caries area;

[0055] A suspected pulp cavity point screening module is used to screen out a suspected pulp cavity point group from the intersection point group set corresponding to each suspected caries area, to obtain a suspected pulp cavity point group set corresponding to each suspected caries area;

[0056] A possibility determination module is used to determine the pulp cavity possibility corresponding to each suspected caries area based on the contour chain code corresponding to each suspected caries area, the distance between each suspected caries area and the root endpoint in the target tooth area to which it belongs, and the suspected pulp cavity point group set corresponding to each suspected caries area;

[0057] The target caries lesion area screening module is used to screen out the target caries lesion area from all suspected caries lesion areas based on all pulp cavity possibilities.

[0058] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and execute the executable program code from the memory, so that the device executes the method of the first aspect or any possible implementation of the first aspect.

[0059] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0060] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0061] The present invention has the following beneficial effects:

[0062] The present invention discloses a method for visually identifying dental caries for oral implants. The method processes image data of a periapical film to be identified to identify a carious area, thereby achieving caries identification. This method solves the technical problem of poor accuracy in identifying carious areas and improves the accuracy of identifying carious areas. Compared with caries identification methods that only consider grayscale differences, the present invention comprehensively considers multiple indicators related to tooth caries conditions, such as grayscale distribution characteristics and target brightness characteristics, so that suspected carious areas can be preliminarily screened out. However, in actual situations, due to the influence of various factors, the tooth pulp cavity and the tooth carious lesion grayscale may have a certain similarity. Therefore, all the screened suspected carious areas may contain a tooth pulp cavity area. Therefore, a pulp cavity feature analysis is performed on the suspected carious areas, and multiple indicators related to pulp cavity features, such as suspected pulp cavity point group, contour chain code, and pulp cavity possibility, are quantified. This allows the target carious area representing the actual carious area to be distinguished from the suspected carious area, thereby improving the accuracy of identifying the carious area and thus improving the accuracy of caries identification. Secondly, compared with caries identification that relies on subjective observation by dentists, the present invention quantifies multiple indicators related to tooth caries conditions when performing caries identification, which can more objectively identify caries areas to a certain extent, thereby improving the accuracy of caries identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0064] Figure 1 This is a flow chart of a method for visually identifying dental caries for oral implants according to the present invention;

[0065] Figure 2 This is a schematic diagram of the screening process for suspected caries lesion areas according to the present invention;

[0066] Figure 3 Schematic diagram of the process for determining the severity level of caries lesions according to the present invention;

[0067] Figure 4 A schematic diagram of the structure of a dental caries visual recognition system for oral implants according to the present invention;

[0068] Figure 5 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0069] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0070] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0071] refer to Figure 1 , showing the process of some embodiments of a dental caries visual identification method for oral implantation of the present invention. The dental caries visual identification method for oral implantation comprises the following steps:

[0072] Step S1, screen out the target tooth area from the acquired periapical film to be identified, and perform grayscale distribution analysis and brightness analysis on the preset neighborhood corresponding to each pixel point in each target tooth area to obtain the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area.

[0073] Among them, the periapical film to be identified can be the periapical film to be used for caries identification. The periapical film, also known as the X-ray film, is the most common dental film. A periapical film can often only show 2-3 teeth. The periapical film can often be used to observe whether there are lesions at the root of the tooth, whether the tooth is loose, etc. Therefore, the periapical film can be used to identify the caries of the tooth, thereby realizing caries identification. Among them, the tooth with caries is caries. The target tooth area can be the tooth area in the periapical film to be identified. The preset neighborhood can be a pre-set neighborhood. For example, the preset neighborhood can be an eight-neighborhood.

[0074] It should be noted that dental caries is a common bacterial disease in the oral cavity. As the disease progresses, the teeth change color and form substantial lesions. If not treated in time, as inorganic matter demineralizes and organic matter decomposes, cavities will form in the affected area, destroying the tooth crown and eventually leading to tooth loss.

[0075] As an example, this step may include the following steps:

[0076] The first step is to obtain the periapical film to be identified.

[0077] For example, a periapical film of the patient can be collected by angled projection, and the collected periapical film can be preprocessed to serve as the periapical film to be identified. The preprocessing can include but is not limited to filtering, denoising, and image enhancement.

[0078] It should be noted that in the process of collecting the patient's periapical film through the method of angle line projection, a film can be placed on the lingual side of the teeth in the patient's mouth, and the X-ray tube can be placed perpendicular to the film and exposed. The X-ray image obtained is the periapical film.

[0079] In the second step, edge detection is performed on the above-mentioned periapical slice to be identified, and a morphological closing operation is performed to obtain the target image.

[0080] For example, the Canny operator can be used to perform edge detection on the above-mentioned apical slice to be identified, and a morphological closing operation can be performed on the obtained edge detection image to bridge the narrow discontinuities in the image and fill the breaks in the contour line. The image after the morphological closing operation is recorded as the target image.

[0081] In the third step, the area enclosed by each closed contour in the target image is determined as the suspected tooth area.

[0082] Among them, the contour is also called the edge.

[0083] It should be noted that, in actual situations, tooth contours often present closed contours, and therefore, the closed contours in the target image may be tooth contours.

[0084] In the fourth step, the maximum value of the continuous repetition times corresponding to all chain code values ​​in the contour chain code of each suspected tooth area is determined as the target continuous repetition time corresponding to each suspected tooth area.

[0085] Among them, the contour chain code in the embodiment of the present invention can be an 8-neighborhood chain code.

[0086] For example, any suspected tooth area can be determined as a reference tooth area, and the chain code value corresponding to each pixel point on the reference tooth area contour is obtained according to the contour chain code of the reference tooth area, and regional growth is performed on all pixel points on the reference tooth area contour according to the chain code values ​​corresponding to all pixel points on the reference tooth area contour. The number of pixel points in the area obtained by regional growth can represent the number of consecutive repetitions of the corresponding chain code value, and the number of pixel points in the maximum area obtained by regional growth at this time can be recorded as the target number of consecutive repetitions corresponding to the reference tooth area, wherein the rule of regional growth in the embodiment of the present invention can be that the chain code value is the same.

[0087] It should be noted that, in general, the more times the same chain code value is repeated in a region's contour, the smoother the region's edge is. Therefore, the greater the number of consecutive repetitions of the target corresponding to a suspected tooth region, the smoother the edge of the suspected tooth region is.

[0088] In the fifth step, the ratio of the area of ​​each suspected tooth region to the area of ​​its minimum circumscribed ellipse is determined as the target shape feature corresponding to each suspected tooth region.

[0089] It should be noted that, in reality, the shape of a tooth is often similar to an ellipse. Therefore, a larger ratio of the area of ​​a suspected tooth region to the area of ​​its minimum circumscribed ellipse indicates that the suspected tooth region is closer to an ellipse, and more likely to represent a tooth.

[0090] In the sixth step, the aspect ratio of the minimum circumscribed rectangle corresponding to each suspected tooth region is determined as the shape extension feature corresponding to each suspected tooth region.

[0091] It should be noted that, in actual situations, the aspect ratio of the tooth region is often relatively large. Therefore, when the aspect ratio of the minimum circumscribed rectangle corresponding to the suspected tooth region is relatively large, it often indicates that the suspected tooth region is more likely to represent a tooth.

[0092] In the seventh step, a tooth shape factor corresponding to each suspected tooth region is determined based on the target continuous repetition times, target shape characteristics, and shape extension characteristics corresponding to each suspected tooth region.

[0093] Among them, the target continuous repetition times, target shape characteristics and shape extension characteristics can all be positively correlated with the tooth shape factor.

[0094] For example, the cumulative multiplication value of the target continuous repetition number, the target shape feature, and the shape extension feature corresponding to each suspected tooth region may be normalized to obtain the tooth shape factor corresponding to each suspected tooth region.

[0095] It should be noted that, when the tooth shape factor corresponding to the suspected tooth region is larger, it often indicates that the edge of the suspected tooth region is smoother, and often indicates that the suspected tooth region is more likely to represent a tooth.

[0096] In the eighth step, if the tooth shape factor corresponding to the suspected tooth region is greater than a preset tooth shape threshold, the suspected tooth region is determined as the target tooth region.

[0097] The preset tooth shape threshold may be a pre-set threshold, for example, 0.5.

[0098] It should be noted that the target tooth region can represent a real tooth.

[0099] In the ninth step, any target tooth region is determined as a marked tooth region, and any pixel point in the marked tooth region is determined as a marked pixel point.

[0100] In the tenth step, the average of the grayscale values ​​corresponding to all pixels in the preset neighborhood corresponding to the marked pixel point is determined as the representative grayscale factor of the neighborhood corresponding to the marked pixel point.

[0101] In the eleventh step, the absolute value of the difference between the neighborhood representative grayscale factor corresponding to the marked pixel point and the grayscale value corresponding to each pixel point in its corresponding preset neighborhood is determined as the target difference corresponding to each pixel point in the preset neighborhood corresponding to the marked pixel point.

[0102] In the twelfth step, the accumulated value of the target differences corresponding to all pixels in the preset neighborhood corresponding to the marked pixel is determined as the grayscale distribution feature corresponding to the marked pixel.

[0103] For example, the formula for determining the grayscale distribution characteristics corresponding to the pixel points in the target tooth area can be:

[0104] ;in, It is within the target tooth area The grayscale distribution characteristics corresponding to each pixel. is the serial number of the target tooth area. It is The sequence number of the pixel points in the target tooth area. is the number of pixels in the preset neighborhood. It is the serial number of the pixel in the preset neighborhood. It is the absolute value function. It is within the target tooth area The first pixel in the preset neighborhood corresponding to the pixel point The grayscale value corresponding to each pixel. It is within the target tooth area The neighborhood corresponding to each pixel represents the grayscale factor. Characterize target differences.

[0105] It should be noted that, because teeth block X-rays, different areas inside teeth have different X-ray blocking abilities. Therefore, X-ray imaging results in different areas are different. For example, high-density tooth structures such as enamel, cementum, and dentin appear as brighter and more evenly distributed white images under X-rays, while caries areas often damage tooth structures, causing changes in the density of normal tooth structures. For example, demineralization in caries areas shows shadows with increased transmittance in the hard tissues of the teeth. Therefore, caries areas often appear as darker areas with uneven grayscale distribution in X-rays. When The larger the The more uneven the grayscale distribution in the preset neighborhood corresponding to the pixel point is, the more uneven the grayscale distribution in the preset neighborhood corresponding to the pixel point is. The more uneven the grayscale distribution around a pixel is, the more likely it is that the The more pixels there are, the more likely they are caries pixels.

[0106] In the thirteenth step, the mean of the grayscale values ​​corresponding to all the pixels in the marked tooth area is determined as the tooth representative grayscale factor corresponding to the marked tooth area.

[0107] In the fourteenth step, the ratio of the neighborhood representative grayscale factor to the tooth representative grayscale factor is determined as the target brightness feature corresponding to the marked pixel point.

[0108] For example, the formula for determining the target brightness feature corresponding to the pixel points in the target tooth area can be:

[0109] ;in, It is within the target tooth area The target brightness feature corresponding to each pixel. is the serial number of the target tooth area. It is The sequence number of the pixel points in the target tooth area. It is within the target tooth area The neighborhood corresponding to each pixel represents the grayscale factor. It is The tooth corresponding to the target tooth area represents the grayscale factor, that is, The mean of the grayscale values ​​corresponding to all pixels in the target tooth area.

[0110] It should be noted that the carious area often appears as a darker area with uneven grayscale distribution in X-rays. The larger the The higher the grayscale of the preset neighborhood corresponding to the pixel point, the brighter it is. The brighter the grayscale around the pixel, the brighter it is. The more pixels there are, the more likely they are not caries pixels.

[0111] Step S2: Screening out suspected caries areas from the target tooth area based on all grayscale distribution features and target brightness features.

[0112] As an example, the process of screening suspected caries lesions could be as follows Figure 2 As shown, the following steps may be specifically included:

[0113] Step 201 : determining a suspected caries factor corresponding to each pixel point in each target tooth region based on a grayscale distribution feature and a target brightness feature corresponding to each pixel point in each target tooth region.

[0114] The grayscale distribution feature may be positively correlated with the suspected caries lesion factor, and the target brightness feature may be negatively correlated with the suspected caries lesion factor.

[0115] For example, the formula for determining the suspected caries factor corresponding to the pixel point in the target tooth area can be:

[0116] ;in, It is within the target tooth area The suspected caries factor corresponding to each pixel point. is the serial number of the target tooth area. It is The sequence number of the pixel points in the target tooth area. is the normalization function. It is within the target tooth area The grayscale distribution characteristics corresponding to each pixel. It is within the target tooth area The target brightness feature corresponding to each pixel.

[0117] It should be noted that when The larger the The grayscale distribution in the preset neighborhood corresponding to the pixel point is more uneven. The smaller the time, the more likely it is that The grayscale of the preset neighborhood corresponding to the pixel point is relatively dark. The larger the The more pixels there are, the more likely they are caries pixels.

[0118] Step 202: If the suspected caries lesion factor corresponding to the pixel point is greater than a preset caries lesion threshold, the pixel point is determined as a suspected caries lesion pixel point.

[0119] The preset caries threshold may be a pre-set threshold, for example, 0.5.

[0120] Step 203: extracting connected domains from the area formed by all suspected caries pixels, and determining the extracted connected domains as suspected caries areas.

[0121] It should be noted that the target tooth region without suspected caries area can often represent a tooth without caries, that is, the tooth represented by the target tooth region without suspected caries area is often not a carious tooth.

[0122] Step S3: draw the target central axis of the target tooth area to which each suspected caries area belongs, determine the perpendicular line of the target central axis as the target perpendicular line, translate the target perpendicular line, and form an intersection group with the intersection point of the target perpendicular line after each translation and the edge of the suspected caries area to obtain a set of intersection groups corresponding to each suspected caries area.

[0123] The target central axis of the target tooth region may be a straight line that roughly divides the target tooth region into two equal parts, the left and the right.

[0124] It should be noted that due to factors such as improper shooting angles or exposure conditions, X-ray imaging results may contain artifacts and blurring, which may lead to uneven grayscale distribution in the X-ray imaging results of the pulp cavity area, and thus misidentify the pulp cavity area as a caries area. Therefore, the suspected caries area may represent a real caries area or the pulp cavity area. Secondly, because the pulp cavity area is usually symmetrical about the central axis of the tooth, the target central axis and the intersection group set can facilitate the subsequent distinction between the real caries area and the pulp cavity area.

[0125] As an example, this step may include the following steps:

[0126] In the first step, the center point of the upper edge of the tooth crown of the target tooth region is connected with the center of gravity of the target tooth region, and the resulting connecting line is used as the target central axis of the target tooth region.

[0127] The upper edge of the tooth crown may be the edge of the tooth surface used for chewing food. For example, the upper edge of the tooth crown of the target tooth region may be obtained by using a neural network or threshold segmentation technique.

[0128] In the second step, any suspected caries area is determined as a reference caries area, and the perpendicular line of the target central axis of the target tooth area to which the reference caries area belongs is determined as the reference perpendicular line. The reference perpendicular line is translated within the target tooth area to which the reference caries area belongs, and the intersection points of the reference perpendicular line with the edge of the reference caries area each time during the translation process constitute an intersection point group of the reference caries area, and all the intersection point groups of the reference caries area constitute an intersection point group set corresponding to the reference caries area.

[0129] Step S4: screening out suspected pulp cavity point groups from the intersection point group sets corresponding to each suspected caries area, to obtain suspected pulp cavity point group sets corresponding to each suspected caries area.

[0130] As an example, an intersection point group having two intersection points and having intersection points located on both sides of the target central axis can be screened out from the intersection point group set corresponding to each suspected caries area as the suspected medullary cavity point group.

[0131] For example, any suspected caries area is determined as a reference caries area, the target central axis of the target tooth area to which the reference caries area belongs is determined as the reference central axis, and any suspected pulp cavity point group in the set of suspected pulp cavity point groups corresponding to the reference caries area is determined as the reference suspected pulp cavity point group. The number of intersections in the reference suspected pulp cavity point group can be 2, and the two intersections in the reference suspected pulp cavity point group are respectively located on both sides of the reference central axis.

[0132] It should be noted that, since the pulp cavity area is usually symmetrical about the central axis of the tooth, the intersection point in the suspected pulp cavity point group may be a pulp cavity edge pixel point.

[0133] Step S5, determining the possibility of the pulp cavity corresponding to each suspected caries area based on the contour chain code corresponding to each suspected caries area, the distance between each suspected caries area and the root endpoint in the target tooth area to which it belongs, and the set of suspected pulp cavity point groups corresponding to each suspected caries area.

[0134] The root endpoint, also known as the root cusp, can be obtained, for example, through techniques such as neural networks or threshold segmentation.

[0135] As an example, the formula for determining the likelihood of a pulp cavity corresponding to a suspected caries area may be:

[0136] ;

[0137] ;in, It is The probability of the pulp cavity corresponding to the suspected carious lesion area. is the serial number of the suspected caries area. is the normalization function. It is The maximum value of the number of consecutive repetitions of all chain code values ​​within the contour chain code of a suspected caries area. The independent variable takes the value The function value when , and and There is a negative correlation. For example, ; It is a factor that is pre-set to be greater than 0, mainly used to prevent the denominator from being 0, for example, It can be 0.001. It is The mean value of the suspected caries factors corresponding to all pixels in the suspected caries area. It is The distance between a suspected carious area and a random root endpoint in the target tooth area. In practice, there are often teeth with one or two roots. is the activation function used for normalization. It is The number of suspected pulp cavity point groups in the set of suspected pulp cavity point groups corresponding to the suspected caries area. It is The number of pixels on the edge of the suspected caries area. The independent variable takes the value The function value when , and and There is a negative correlation. For example, ; It is a factor that is pre-set to be greater than 0, mainly used to prevent the denominator from being 0, for example, It can be 0.001. Characterization The average distance difference between the two intersection points and the target central axis in all suspected pulp cavity point groups corresponding to the suspected caries area. It is The sequence number of the suspected pulp cavity point group in the set of suspected pulp cavity point groups corresponding to the suspected caries area. It is the absolute value function. It is The first point in the set of suspected pulp cavity points corresponding to the suspected caries area In the group of suspected medullary cavity points, the first intersection point and the The distance between the target central axes of the target tooth areas to which the suspected caries areas belong. It is The first point in the set of suspected pulp cavity points corresponding to the suspected caries area In the group of suspected medullary cavity points, the second intersection point The distance between the target central axes of the target tooth areas to which the suspected caries areas belong.

[0138] It should be noted that, in actual situations, caries areas are usually formed in the crown of the tooth, causing damage to the tooth structure, such as demineralization of the tooth hard tissue, decomposition of organic matter and dissolution of inorganic matter, etc., which makes the shape of the caries area irregular and the edges not smooth. The caries area is mostly located on the tooth surface, such as the occlusal surface and the adjacent surface, which are far away from the root apex of the tooth. The pulp cavity area is often located in the center of the tooth and extends toward the root. It is usually symmetrical about the central axis of the tooth and has smooth edges. The larger the The smoother the edge of the suspected caries area, the The more suspected caries area is, the more likely it is to be the pulp cavity area. The larger the The more suspected caries area is, the more likely it is to be a real caries area. The larger the The farther the suspected caries area is from the root apex of the tooth, the more likely it is that the The more suspected caries area is, the more likely it is to be a real caries area. The larger the The more intersection points there are in the suspected pulp cavity point group corresponding to the suspected caries area, the more likely it is that the The more pixels in the suspected caries area that may be the pulp cavity, the more likely it is that the The more suspected caries area is, the more likely it is to be the pulp cavity area. The smaller the time, the more likely it is that The more likely the intersection points in the suspected pulp cavity point group corresponding to the suspected caries area are to be symmetrical about the target central axis, the more likely the intersection points are to be symmetrical about the target central axis. The more suspected caries area is, the more likely it is to be the pulp cavity area. The larger the The more likely the suspected caries area is, the more likely it is that it is the pulp cavity area rather than the real caries area.

[0139] Step S6: based on all pulp cavity possibilities, select a target caries lesion area from all suspected caries lesion areas.

[0140] The target tooth region to which the target caries region belongs can represent dental caries.

[0141] As an example, if the pulp cavity probability corresponding to the suspected caries region is less than a preset caries distinction threshold, the suspected caries region is determined as the target caries region. The preset caries distinction threshold may be a pre-set threshold, for example, 0.5.

[0142] Alternatively, as Figure 3 As shown, the present invention may further include the following steps:

[0143] Step 301 : determining a caries severity index corresponding to each target caries area according to the caries extension direction of each target caries area and the tooth extension direction of the target tooth area to which it belongs, as well as the area of ​​each target caries area.

[0144] The caries extension direction can represent the caries spread direction. For example, the caries extension direction of the target caries lesion area can be obtained by: determining any pixel point on the target caries lesion area contour as a marked caries lesion pixel point, and determining two pixel points on the target caries lesion area contour adjacent to the marked caries lesion pixel point as a first pixel point and a second pixel point respectively; determining the absolute value of the slope of the line connecting the first pixel point and the marked caries lesion pixel point as a first change representative factor; determining the absolute value of the slope of the line connecting the second pixel point and the marked caries lesion pixel point as a second change representative factor; determining the sum of the first change representative factor and the second change representative factor as a target change index corresponding to the marked caries lesion pixel point; selecting a pixel point with the largest target change index from the target caries lesion area contour as a target extension endpoint; and determining the direction in which the center of gravity of the target caries lesion area points to the target extension endpoint as the caries lesion extension direction of the target caries lesion area.

[0145] The tooth extension direction can represent the direction from the tooth's center of gravity to the root. For example, if the tooth represented by the target tooth region has one root, the tooth extension direction of the target tooth region can be the direction from the target tooth region's center of gravity to the root endpoint. If the tooth represented by the target tooth region has two roots, the tooth extension direction of the target tooth region can be the direction from the target tooth region's center of gravity to the two root endpoints. The direction of the target direction vector from the target tooth region's center of gravity to the root endpoint can be the direction from the target tooth region's center of gravity to the root endpoint. The modulus of the target direction vector from the target tooth region's center of gravity to the root endpoint can be equal to the distance between the target tooth region's center of gravity and the root endpoint.

[0146] For example, determining the caries severity index corresponding to each target caries area may include the following steps:

[0147] In the first step, the angle between the caries extension direction of each target caries lesion area and the tooth extension direction of the target tooth area to which it belongs is determined as the caries extension feature corresponding to each target caries lesion area.

[0148] It should be noted that the smaller the caries extension feature corresponding to the target caries area, the more similar the caries extension direction of the target caries area is to the tooth extension direction of the target tooth area to which it belongs, which often means that the target caries area is more likely to extend deeper into the tooth, which may affect the pulp cavity or even the root apex, and the degree of caries may be more severe.

[0149] In the second step, the caries severity index corresponding to each target caries area is determined based on the pulp cavity possibility, caries extension characteristics and area corresponding to each target caries area.

[0150] Among them, pulp cavity possibility and caries extension characteristics can be negatively correlated with caries severity indicators, while the area of ​​the target caries lesion area can be positively correlated with its caries extension characteristics.

[0151] For example, the formula for determining the caries severity index corresponding to the target caries area can be:

[0152] ;

[0153] in, It is The caries severity index corresponding to the target caries area. is the serial number of the target caries area. It is The probability of the pulp cavity corresponding to the target carious lesion area. It is The caries extension characteristics corresponding to the target caries area. It is a factor that is pre-set to be greater than 0, mainly used to prevent the denominator from being 0, for example, It can be 0.001. It is The area of ​​the target caries lesion. It is The area of ​​the target tooth area to which the target caries area belongs.

[0154] It should be noted that when The larger the The more likely a suspected caries area is to be a pulp cavity area rather than a real caries area, the less likely it is that there is no severe caries. The smaller the time, the more likely it is that The more similar the caries extension direction of the target caries area is to the tooth extension direction of the target tooth area to which it belongs, the more likely it is that the The more likely a target caries area is to extend deeper into the tooth, the more severe the caries is likely to be. The larger the The larger the area of ​​the target caries area is, the larger the proportion of the target caries area is. The larger the The more likely the target caries area is to extend deeper into the tooth and the more severe the caries is, the more likely it is that the first The more severe the caries condition in the target caries area.

[0155] In step 302, the target tooth region to which the target caries region belongs is determined as a candidate tooth region, and pixel points adjacent to the target gum region are screened from the contour of each candidate tooth region as target contour points.

[0156] The target gingival area may be the gingival area in the periapical film to be identified.

[0157] It should be noted that, in actual situations, teeth and gums are often connected together, so the pixels adjacent to the gums on the tooth contour are often the pixels at the junction of the teeth and gums. Therefore, the target contour point can represent the position point on the junction line between the teeth and gums.

[0158] Step 303: Filter out gingival inflammation points from the target gingival area, filter out inflamed contour points from all target contour points, filter out sub-gingival areas corresponding to each candidate tooth area from the target gingival area, and filter out effective caries areas from all target caries areas based on the caries severity index corresponding to the target caries area.

[0159] Among them, the effective caries lesion area can represent the target caries lesion area with a trend of severe caries lesion change.

[0160] It should be noted that areas with more severe caries often affect the root apex of the teeth, leading to the occurrence of apical periodontitis. Therefore, screening out the gingival inflammation points can facilitate the subsequent analysis of the caries situation in the target caries area.

[0161] For example, screening out gingival inflammation points from a target gingival area may include the following steps:

[0162] In the first step, based on the grayscale values ​​of the pixels in the preset neighborhood corresponding to each pixel in the target gum area, the formula for determining the probability of gum inflammation corresponding to each pixel in the target gum area can be:

[0163] ;

[0164] in, The first The probability of gingival inflammation corresponding to each pixel. is the serial number of the pixel in the target gingival area. is the normalization function. The first The maximum value of the grayscale values ​​corresponding to all pixels in the preset neighborhood corresponding to the pixel point. The first The minimum value among the grayscale values ​​corresponding to all pixels in the preset neighborhood corresponding to the pixel point. is a natural exponential function. The first The mean of the grayscale values ​​corresponding to all pixels in the preset neighborhood corresponding to the pixel. It is the mean of the grayscale values ​​corresponding to all pixels in the periapical film to be identified.

[0165] It should be noted that the degree of inflammation in different parts of the gums is often different, and the corresponding grayscale is often different. Therefore, the grayscale changes around the inflamed pixels are often more unstable, and the pixels in the inflamed area outside the root apex are often darker overall. The larger the The greater the grayscale change in the preset neighborhood corresponding to the pixel point, the greater the grayscale change in the preset neighborhood. The more pixels there are, the more likely they are inflammation pixels. The smaller the time, the more likely it is that The grayscale of the preset neighborhood corresponding to the pixel point is more likely to be darker overall, which often indicates that the The more pixels there are, the more likely they are inflammation pixels. The larger the The more pixels there are, the more likely they are to be gingivitis pixels.

[0166] In the second step, any pixel point in the target gingival area is determined as a reference gingival point. If the possibility of gingival inflammation corresponding to the reference gingival point is greater than a preset gingival inflammation threshold, the reference gingival point is determined as a gingival inflammation point.

[0167] The preset gingival inflammation threshold may be a pre-set threshold, for example, the preset gingival inflammation threshold may be 0.5.

[0168] For another example, screening out inflammation contour points from all target contour points may include the following steps:

[0169] In the first step, the inflammation possibility of the contour corresponding to each target contour point is determined according to the gradient amplitude corresponding to each target contour point.

[0170] Among them, the gradient amplitude is also called the gradient size.

[0171] For example, the mean of the gradient amplitudes corresponding to all target contour points can be determined as the gradient representative value, and the ratio of the gradient amplitude corresponding to each target contour point to the gradient representative value can be normalized to obtain the contour inflammation possibility corresponding to each target contour point.

[0172] It should be noted that apical periodontitis creates a distinct light-dark boundary between the root apex and the gingival region in X-ray imaging. Therefore, the gradient amplitude corresponding to the pixel points on the inflamed root contour is often larger. Therefore, the greater the likelihood that the target contour point is inflamed, the more likely it is to be an inflamed root contour point.

[0173] In the second step, if the contour inflammation possibility corresponding to the target contour point is greater than a preset contour inflammation threshold, the target contour point is determined as an inflammation contour point.

[0174] The preset contour inflammation threshold may be a preset threshold, for example, the preset contour inflammation threshold may be 0.5.

[0175] It should be noted that the inflamed contour point may be an inflamed tooth root contour point.

[0176] For another example, a method for selecting a sub-gingival region corresponding to each candidate tooth region from within the target gingival region may include segmenting the target gingival region to obtain a sub-gingival region corresponding to each candidate tooth region using the intersection curve segment of each candidate tooth region and the target gingival region as a segmentation step. The sub-gingival region corresponding to a candidate tooth region may represent a portion of the gingival region connected to the candidate tooth region.

[0177] For example, the method for screening effective caries areas can be: along the tooth extension direction of the target tooth area, the target caries areas in the target tooth area are sorted in sequence, that is, the closer the target caries area is to the tooth root, the larger its serial number is, and any target caries area in the target tooth area is determined as a marked caries area. If the caries severity index corresponding to the above-mentioned marked caries area is less than the caries severity index corresponding to the next target caries area, then the above-mentioned marked caries area is determined as an effective caries area.

[0178] Step 304 : Determine the caries severity level corresponding to each candidate tooth region based on the number of gingival inflammation points in the sub-gingival region corresponding to each candidate tooth region, the number of inflammation contour points in each candidate tooth region, and the number of effective caries regions.

[0179] Among them, the number of gingival inflammation points, the number of inflammation contour points and the number of effective caries areas can all be positively correlated with the severity of caries lesions.

[0180] For example, the formula for determining the caries severity level corresponding to the candidate tooth region may be:

[0181] ;in, It is The caries severity level corresponding to each candidate tooth area. is the sequence number of the candidate tooth region. is the normalization function. It is The number of inflamed contour points in the candidate tooth area. It is The number of target contour points in the candidate tooth area. It is The number of gingival inflammation points in the sub-gingival area corresponding to the candidate tooth area. It is The number of effective caries areas within the candidate tooth area. It is The number of target caries lesions within the candidate tooth area.

[0182] It should be noted that the inflamed contour point can represent the inflamed tooth root contour point. The larger the The more inflammation contour points there are in the candidate tooth area, the more likely it is that the first The more inflamed root contour points on the teeth represented by the candidate tooth area, the more likely the candidate tooth area is to be caries-inflamed. The more serious the caries situation of the tooth represented by the candidate tooth area, the more serious the caries situation of the tooth represented by the candidate tooth area. The larger the The more gingival inflammation points there are in the sub-gingival area corresponding to the candidate tooth area, the more likely it is that the first The more severe the inflammation of the tooth represented by the candidate tooth area is. The larger the The more caries lesions there are in the candidate tooth area, the more serious the caries lesions are. The more severe the dental caries of the tooth represented by the candidate tooth region, the more severe the dental caries may be. The larger the The more severe the caries condition of the tooth represented by the candidate tooth region is.

[0183] Secondly, doctors can use the caries severity levels corresponding to the candidate tooth regions to determine the caries status of the teeth represented by the reference candidate tooth regions. Therefore, quantifying the caries severity levels corresponding to the reference candidate tooth regions can assist doctors in determining the caries status of teeth, thereby facilitating the design of treatment plans for caries represented by the reference candidate tooth regions. Reference candidate tooth regions can also be marked with different colors based on the different caries severity levels corresponding to different reference candidate tooth regions, for easier observation by doctors.

[0184] refer to Figure 4 Based on the same inventive concept as the above method embodiment, the present invention provides a dental caries visual recognition system for oral implants. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a dental caries visual recognition method for oral implants may specifically include:

[0185] The screening and processing module 401 is used to screen out the target tooth area from the acquired periapical film to be identified, and perform grayscale distribution analysis and brightness analysis on the preset neighborhood corresponding to each pixel point in each target tooth area to obtain the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area.

[0186] The suspected caries area screening module 402 is used to screen out suspected caries areas from the target tooth area based on all grayscale distribution features and target brightness features.

[0187] The data line construction module 403 is used to make the target central axis of the target tooth area to which each suspected caries area belongs, determine the perpendicular line of the target central axis as the target perpendicular line, translate the target perpendicular line, and form an intersection group with the intersection point of the target perpendicular line after each translation and the edge of the suspected caries area to obtain a set of intersection groups corresponding to each suspected caries area.

[0188] The suspected pulp cavity point screening module 404 is configured to screen out suspected pulp cavity point groups from the intersection point group set corresponding to each suspected caries lesion area, thereby obtaining a suspected pulp cavity point group set corresponding to each suspected caries lesion area.

[0189] The possibility determination module 405 is used to determine the pulp cavity possibility corresponding to each suspected caries area based on the contour chain code corresponding to each suspected caries area, the distance between each suspected caries area and the root endpoint in the target tooth area to which it belongs, and the set of suspected pulp cavity point groups corresponding to each suspected caries area.

[0190] The target caries lesion area screening module 406 is configured to screen out a target caries lesion area from all suspected caries lesion areas based on all pulp cavity possibilities.

[0191] Figure 5 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 5 As shown, the computer device 500 includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any one of the caries visual identification methods for oral implants introduced above.

[0192] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to perform any of the above-described methods for visually identifying dental caries for oral implants.

[0193] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the above-mentioned caries visual identification methods for oral implants.

[0194] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned caries visual identification methods for oral implants.

[0195] In summary, compared to caries identification that only considers the difference in grayscale values, the present invention comprehensively considers multiple indicators related to the tooth caries situation, such as grayscale distribution characteristics and target brightness characteristics, so that suspected caries areas can be preliminarily screened out. However, in actual situations, due to the influence of various factors, the tooth pulp cavity and the tooth caries grayscale may have a certain similarity. Therefore, all the suspected caries areas screened out may contain tooth pulp areas. Therefore, pulp cavity feature analysis is performed on the suspected caries areas, and multiple indicators related to pulp cavity features are quantified, such as suspected pulp cavity point groups, contour chain codes, and pulp cavity possibilities. This allows the target caries area representing the real caries area to be distinguished from the suspected caries area, thereby improving the accuracy of identifying the caries area and thus improving the accuracy of caries identification. Secondly, compared to caries identification that relies on subjective observation by dentists, the present invention quantifies multiple indicators related to the tooth caries situation when performing caries identification, which can more objectively identify the caries area to a certain extent, thereby improving the accuracy of caries identification.

[0196] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A dental caries visual identification method for oral implants, characterized in that: The following steps are involved: Filtering the target tooth area from the acquired periapical film to be identified, and performing grayscale distribution analysis and brightness analysis on the preset neighborhood corresponding to each pixel point in each target tooth area to obtain the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area; Based on all grayscale distribution features and target brightness features, suspected caries areas are screened out from the target tooth area; Draw a target central axis of the target tooth area to which each suspected caries area belongs, determine the perpendicular line of the target central axis as the target perpendicular line, translate the target perpendicular line, and form an intersection point group with the intersection point of each translated target perpendicular line and the edge of the suspected caries area to obtain a set of intersection point groups corresponding to each suspected caries area; From the intersection point group set corresponding to each suspected caries area, a group of intersection points with two intersection points and intersection points located on both sides of the target central axis is selected as the suspected pulp cavity point group, thereby obtaining a suspected pulp cavity point group set corresponding to each suspected caries area; Determine the pulp cavity possibility corresponding to each suspected caries area based on the contour chain code corresponding to each suspected caries area, the distance between each suspected caries area and the root endpoint within the target tooth area to which it belongs, and the set of suspected pulp cavity points corresponding to each suspected caries area; According to all pulp cavity possibilities, the target caries lesion area is selected from all suspected caries lesion areas; The formula corresponding to the pulp cavity probability of the suspected caries area is: ； ； ； ； in, It is The probability of the pulp cavity corresponding to the suspected carious lesion area; is the serial number of the suspected caries lesion area; is the normalization function; It is The maximum value of the number of consecutive repetitions of all chain code values ​​within the contour chain code of the suspected caries area; 、 is a factor that is preset to be greater than 0; It is The mean value of the suspected caries factors corresponding to all pixels in the suspected caries area; It is The distance between a suspected carious area and a random root endpoint within the target tooth area to which it belongs; is the activation function, used for normalization; It is The number of suspected pulp cavity point groups in the set of suspected pulp cavity point groups corresponding to the suspected caries area; It is The number of pixels on the edge of the suspected caries area; Characterization The average distance difference between the two intersection points and the target central axis in all suspected pulp cavity point groups corresponding to the suspected caries area; It is The sequence number of the suspected pulp cavity point group in the set of suspected pulp cavity point groups corresponding to the suspected caries area; It is the absolute value function; 、 It is The first point in the set of suspected pulp cavity points corresponding to the suspected caries area In the suspected medullary cavity point group, the first intersection point and the second intersection point are respectively The distance between the target central axes of the target tooth areas to which the suspected caries areas belong; The formula for determining the suspected caries factor corresponding to the pixel point in the target tooth area is: ;in, It is within the target tooth area The suspected caries factor corresponding to each pixel; is the serial number of the target tooth area; It is The sequence number of the pixel points in the target tooth area; It is within the target tooth area Grayscale distribution characteristics corresponding to each pixel; It is within the target tooth area The target brightness feature corresponding to each pixel.

2. A dental caries visual identification method for oral implantation according to claim 1, characterized in that: The step of screening out the target tooth area from the acquired periapical radiograph to be identified comprises: Performing edge detection on the periapical slice to be identified and performing a morphological closing operation to obtain a target image; determining the area enclosed by each closed contour in the target image as a suspected tooth area; The maximum value of the consecutive repetition times corresponding to all chain code values ​​in the contour chain code of each suspected tooth area is determined as the target consecutive repetition time corresponding to each suspected tooth area; The ratio of the area of ​​each suspected tooth region to the area of ​​its minimum circumscribed ellipse is determined as the target shape feature corresponding to each suspected tooth region; Determine the aspect ratio of the minimum circumscribed rectangle corresponding to each suspected tooth region as a shape extension feature corresponding to each suspected tooth region; Normalizing the cumulative multiplication value of the target continuous repetition times, target shape features, and shape extension features corresponding to each suspected tooth region to obtain the tooth shape factor corresponding to each suspected tooth region; If the tooth shape factor corresponding to the suspected tooth region is greater than a preset tooth shape threshold, the suspected tooth region is determined as the target tooth region.

3. The method for visually identifying dental caries for oral implantation according to claim 1, characterized in that: The grayscale distribution analysis and brightness analysis are performed on the preset neighborhood corresponding to each pixel point in each target tooth area to obtain the grayscale distribution characteristics and target brightness characteristics corresponding to each pixel point in each target tooth area, including: Determine any target tooth region as a marked tooth region, and determine any pixel point in the marked tooth region as a marked pixel point; Determine the average of the grayscale values ​​corresponding to all pixels in a preset neighborhood corresponding to the marked pixel as a representative grayscale factor of the neighborhood corresponding to the marked pixel; Determine the absolute value of the difference between the neighborhood representative grayscale factor corresponding to the marked pixel point and the grayscale value corresponding to each pixel point in the preset neighborhood corresponding to the marked pixel point as the target difference corresponding to each pixel point in the preset neighborhood corresponding to the marked pixel point; Determine the cumulative value of the target differences corresponding to all pixels in a preset neighborhood corresponding to the marked pixel as the grayscale distribution feature corresponding to the marked pixel; Determine the mean of the grayscale values ​​corresponding to all pixels in the marked tooth area as the tooth representative grayscale factor corresponding to the marked tooth area; The ratio of the neighborhood representative grayscale factor to the tooth representative grayscale factor is determined as the target brightness feature corresponding to the marked pixel point.

4. The method for visually identifying dental caries for oral implantation according to claim 1, characterized in that: The method of screening out suspected caries areas from the target tooth area based on all grayscale distribution characteristics and target brightness characteristics includes: If the suspected caries lesion factor corresponding to the pixel point is greater than the preset caries lesion threshold, the pixel point is determined as a suspected caries lesion pixel point; Connected domains are extracted from the area formed by all suspected caries pixels, and the extracted connected domains are determined as suspected caries areas.

5. The method for visually identifying dental caries for oral implantation according to claim 1, characterized in that: The method further comprises: Determine the caries severity index corresponding to each target caries lesion area based on the caries extension direction of each target caries lesion area, the tooth extension direction of the target tooth area to which it belongs, and the area of ​​each target caries lesion area, wherein the caries extension direction represents the caries spread direction, and the tooth extension direction represents the direction from the center of gravity of the tooth to the tooth root; The target tooth region to which the target caries region belongs is determined as a candidate tooth region, and pixel points adjacent to the target gingival region are screened from the contour of each candidate tooth region as target contour points, wherein the target gingival region is the gingival region in the periapical film to be identified; Screening out gingival inflammation points from the target gingival region, and screening out inflamed contour points from all target contour points, screening out subgingival regions corresponding to each candidate tooth region from the target gingival region, and screening out effective caries regions from all target caries regions based on caries severity indicators corresponding to the target caries regions, wherein the effective caries regions represent target caries regions with a caries severity change trend; The caries severity level corresponding to each candidate tooth area is determined based on the number of gingival inflammation points in the sub-gingival area corresponding to each candidate tooth area, as well as the number of inflammation contour points and the number of effective caries areas in each candidate tooth area. Among them, the number of gingival inflammation points, the number of inflammation contour points and the number of effective caries areas are all positively correlated with the caries severity level.

6. The method for visually identifying dental caries for oral implantation according to claim 5, characterized in that: Determining the caries severity index corresponding to each target caries area according to the caries extension direction of each target caries area and the tooth extension direction of the target tooth area to which it belongs, as well as the area of ​​each target caries area, includes: The angle between the caries extension direction of each target caries lesion area and the tooth extension direction of the target tooth area to which it belongs is determined as a caries extension feature corresponding to each target caries lesion area; The caries severity index corresponding to each target caries lesion area was determined based on the pulp cavity possibility, caries extension characteristics, and area corresponding to each target caries lesion area. The pulp cavity possibility and caries extension characteristics were negatively correlated with the caries severity index, while the area of ​​the target caries lesion area was positively correlated with its caries severity index.

7. The method for visually identifying dental caries for oral implantation according to claim 5, characterized in that: The method of screening out effective caries lesion areas from all target caries lesion areas according to the caries lesion severity index corresponding to the target caries lesion area includes: Along the tooth extension direction of the target tooth area, the target caries areas in the target tooth area are sorted in sequence, and any target caries area in the target tooth area is determined as a marked caries area. If the caries severity index corresponding to the marked caries area is less than the caries severity index corresponding to the next target caries area, the marked caries area is determined as a valid caries area.

8. A dental caries visual recognition system for oral implants, characterized in that: The method comprises a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement a dental caries visual identification method for oral implantation according to any one of claims 1 to 7.

Images