Dental plaque quantitative analysis method and device and computer equipment

Abstract

The invention discloses a dental plaque quantitative analysis method, a dental plaque quantitative analysis device and computer equipment. The method comprises the following steps: acquiring an initial dental surface image of at least one specified orientation of a to-be-detected tooth; normalizing each initial dental surface image into the matched template image to obtain a normalized dental surface image; performing image segmentation on each regular tooth surface image to obtain a tooth image area and a dental plaque image area in the regular tooth surface image; and calculating the dental plaque proportion of the to-be-detected teeth according to the sizes of the tooth image region and the dental plaque image region of each regular tooth surface image. Accurate quantitative evaluation of the dental plaque on the to-be-detected teeth is achieved, the method has the advantages of being easy and convenient to operate, accurate in result and the like, and the quantitative evaluation result has comparability and can serve as a credible basis for dynamic monitoring of oral health.

Description

Technical Field

[0001] The present invention relates to the technical field of oral medicine, and in particular to a method, a device and a computer equipment for quantitative analysis of dental plaque. Background Art

[0002] For dental plaque testing, early methods mainly relied on the use of a display agent applied to the teeth to show dental plaque. This method is cumbersome to operate and the patient experience is poor.

[0003] With the advancement of technology, autofluorescence imaging technology has been gradually applied to the detection of dental plaque. This method obtains images with characteristic effects in optical imaging by designing a specific spectrum, so that teeth and plaque appear in different colors in the image, which can be distinguished by the human eye or identified by specific pixel RGB.

[0004] However, it is difficult for the human eye to perform quantitative analysis of dental plaque. Image analysis using pixel RGB has the following problems. Since dental plaque often appears in the hidden area between the teeth and gums, the color of the gums is close to the color of the dental plaque in the fluorescent image. Therefore, the accuracy of using RGB to judge the plaque area is low, and the quantitative calculation results are inaccurate. In addition, in some oral treatment scenarios, such as tracking the progress of dental treatment, the tooth surface of the same tooth needs to be photographed at regular intervals to detect the condition of dental plaque. However, since it is difficult to keep the distance and angle of each shot consistent, there are large differences in the recognition results of dental plaque in images obtained under different shooting conditions. Therefore, it is often difficult to give reliable quantitative characterization results of dental plaque. Summary of the invention

[0005] Based on this, it is necessary to address the problem of inaccurate identification of existing dental plaque, which leads to difficulty in quantitative analysis, and propose a method, device and computer equipment for quantitative analysis of dental plaque.

[0006] The first aspect of the present application provides a method for quantitative analysis of dental plaque, the method comprising:

[0007] Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0008] Regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image;

[0009] Performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0010] The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

[0011] Furthermore, the step of regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image comprises:

[0012] Classifying the initial tooth surface image by using a pre-trained image classification model to obtain a tooth surface image type;

[0013] Selecting a template image that matches the tooth surface image type from a template image library, and using the selected template image as a matching template image; wherein the template image library has a plurality of pre-designed template images pre-stored therein;

[0014] The initial tooth surface image is deformed, and the tooth image region in the initial tooth surface image is regularized to match the tooth image region of the template image, so as to obtain the regularized tooth surface image.

[0015] Furthermore, the step of deforming the initial tooth surface image, regularizing the tooth image region in the initial tooth surface image to a tooth image region that matches the template image, and obtaining the regular tooth surface image includes:

[0016] Inputting the initial tooth surface image and the tooth surface image type into a pre-trained key point detection model to obtain a first key point matrix on the initial tooth surface image; wherein the first key point matrix includes a plurality of first key points;

[0017] Obtaining a second key point matrix on the matching template image and a coordinate set of a second vertex array within the second key point matrix area, wherein the second key point matrix includes a plurality of second key points, and the first key point matrix and the second key point matrix have the same row dimension and column dimension;

[0018] In the first key point matrix area, a first vertex array is generated, the row dimension and column dimension of the first vertex array are the same as those of the second vertex array, and each vertex in the first vertex array is mapped to the coordinates of each vertex in the second vertex array to obtain the regular tooth surface image.

[0019] Furthermore, the step of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises:

[0020] Calculating the number of first pixels in the tooth image area and the number of second pixels in the dental plaque image area in each of the regular tooth surface images;

[0021] A first ratio of the second number of pixels to the first number of pixels is calculated, where the first ratio is the dental plaque ratio of the tooth to be detected.

[0022] Furthermore, after the step of calculating the ratio of the second number of pixels to the first number of pixels, wherein the ratio is the dental plaque ratio of the tooth to be detected, the step further includes:

[0023] Calculating the shape parameter value of the dental plaque image area in each of the regular tooth surface images, wherein the shape parameter includes at least one of the width of a single dental plaque and the area of ​​a single dental plaque;

[0024] The active plaque index of the tooth to be tested is determined according to the shape parameter value and the dental plaque ratio and in accordance with a predefined plaque classification standard, wherein the plaque classification standard stores different active plaque indices corresponding to different shape parameter values ​​and different dental plaque ratios.

[0025] Furthermore, the designated position includes at least one of the lingual side, the buccal side and the occlusal side, and the step of acquiring the initial tooth surface image of at least one designated position of the tooth to be detected includes:

[0026] placing an imaging device on the lingual side of the tooth to be detected, and collecting an initial tooth surface image of the lingual side of the tooth to be detected; and / or,

[0027] Placing an imaging device on the buccal side of the tooth to be detected to collect an initial tooth surface image of the buccal side of the tooth to be detected; and / or,

[0028] An imaging device is placed on the occlusal surface side of the tooth to be detected, and an initial tooth surface image of the occlusal surface side of the tooth to be detected is collected.

[0029] Further, the initial tooth surface image of the tooth to be detected includes an initial tooth surface image of the lingual side, an initial tooth surface image of the buccal side and an initial tooth surface image of the occlusal side, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the lingual side of the tooth to be detected are used as the first tooth image area and the first dental plaque image area, respectively, the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the buccal side of the tooth to be detected are used as the second tooth image area and the second dental plaque image area, respectively, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the occlusal side of the tooth to be detected are used as the third tooth image area and the third dental plaque image area, respectively;

[0030] The step of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises:

[0031] Calculating the sum of the numbers of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area as the total number of dental plaque pixels;

[0032] Calculating the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area as the total number of tooth pixels;

[0033] A second ratio of the total number of dental plaque pixels to the total number of tooth pixels is calculated, where the second ratio is the dental plaque ratio of the tooth to be detected.

[0034] Furthermore, there are multiple teeth to be detected, and the step of calculating the dental plaque ratio of the teeth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises:

[0035] Calculate the sum of the number of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area of ​​all teeth to be detected as the second total number of dental plaque pixels;

[0036] Calculate the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area of ​​all teeth to be detected as a second total number of tooth pixels;

[0037] A third ratio of the second total number of dental plaque pixels to the second total number of tooth pixels is calculated, and the third ratio is the dental plaque ratio of all the teeth to be detected.

[0038] The second aspect of the present application provides a dental plaque quantitative analysis device, the device comprising:

[0039] An image acquisition module, used for acquiring an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0040] An image regularization module, used for regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image;

[0041] An image segmentation module, used for performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0042] The quantitative analysis module is used to calculate the dental plaque ratio of the tooth to be detected according to the area size of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

[0043] A third aspect of the present application provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor performs the following steps:

[0044] Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0045] Regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image;

[0046] Performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0047] The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

[0048] A fourth aspect of the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0049] Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0050] Regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image;

[0051] Performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0052] The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

[0053] The dental plaque quantitative analysis method, device and computer equipment of the present application achieve accurate quantitative evaluation of dental plaque on the teeth to be tested through the steps of collecting initial tooth surface images, regularizing images, image segmentation and calculating dental plaque ratio. The method has the advantages of simple operation and accurate results. The quantitative evaluation results are comparable and can be used as a reliable basis for dynamic monitoring of oral health, which helps to prevent and treat oral diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] in:

[0056] Figure 1 A diagram showing an application environment of a method for quantitative analysis of dental plaque in one embodiment;

[0057] Figure 2 A flowchart of a method for quantitative analysis of dental plaque in one embodiment;

[0058] Figure 3 is a structural block diagram of a dental plaque quantitative analysis device in one embodiment;

[0059] Figure 4 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Figure 1 This is a diagram of the application environment of quantitative analysis of dental plaque in one embodiment. Figure 1 , the dental plaque quantitative analysis method is applied to the dental plaque quantitative analysis system. The dental plaque quantitative analysis system includes a terminal 110 and a server 120. The terminal 110 and the server 120 are connected via a network. The terminal 110 can specifically be a desktop terminal or a mobile terminal connected to an oral plaque observer, an oral endoscope, etc. The mobile terminal can specifically be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented as an independent server or a server cluster composed of multiple servers. The terminal 110 is used to execute each step of the dental plaque quantitative analysis method; the server 120 is used to upload and store dental plaque detection results, such as the initial tooth surface image, the dental plaque ratio, etc.

[0062] like Figure 2 As shown, in one embodiment, a method for quantitative analysis of dental plaque is provided. The method can be applied to both a terminal and a server. This embodiment is illustrated by applying to a terminal. The method for quantitative analysis of dental plaque specifically comprises the following steps:

[0063] S1: Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0064] S2: regularize each initial tooth surface image into a matching template image to obtain a regularized tooth surface image;

[0065] S3: performing image segmentation on each regular tooth surface image to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0066] S4: Calculate the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image.

[0067] In this embodiment, in the above step S1, an imaging device is used to collect the initial tooth surface image. The imaging device can be a fluorescent imaging device, such as an existing oral dental plaque observation instrument, or a visible light imaging device. When a visible light imaging device is used, a dental plaque indicator needs to be used on the teeth. In the initial tooth surface image, the tooth image area and the dental plaque image area present different colors. For the fluorescent imaging device, an oral dental plaque observation instrument is used as an example for explanation. It is designed with a specific spectrum (light in a specific wavelength range for exciting autofluorescence), which can excite teeth and dental plaque to emit autofluorescence. By capturing autofluorescence, the observation instrument can form a clear tooth surface image. In the initial tooth surface image, the tooth image area is displayed as a light green with a fluorescent color, the dental plaque image area is a light pink with a fluorescent color, and the gum area is a darker light pink. For visible light imaging devices, after using a plaque indicator on the teeth, the plaque area will appear colored, which is different from the color of the tooth area (the area not covered with plaque), so that the tooth image area and the plaque image area can be clearly distinguished in the image taken by the visible light imaging device.

[0068] The above-mentioned specified orientations include front, side, and occlusal surfaces. Initial tooth surface images can be collected in one or more orientations. As a preferred solution, initial tooth surface images in multiple orientations are collected, for example, three (front, side, and occlusal surfaces), so that the distribution of dental plaque can be evaluated more comprehensively.

[0069] The above-mentioned initial tooth surface image includes an image of a complete tooth surface of the tooth to be detected; for other adjacent teeth, if only a partial image is taken, it will not affect the subsequent steps; if the tooth surface image of the entire adjacent tooth is taken, it is necessary to adjust the shooting distance of the imaging device, or crop the initial image to retain only the complete tooth surface of the tooth to be detected, or mark the tooth surface of the tooth to be detected, so as to facilitate accurate identification of the tooth to be detected in the subsequent steps.

[0070] In the above step S2, the above template image is usually an image with a standard tooth morphology. For teeth in different tooth positions and tooth surfaces, corresponding template images are pre-designed, and the tooth morphology in the template image is set according to the tooth anatomical structure. For example, for teeth in a certain tooth position, template images corresponding to the three tooth surfaces (front, side and occlusal surfaces) of the tooth position are pre-designed; for teeth in different tooth positions, template images corresponding to different tooth positions are set respectively. It can be understood that for teeth with similar morphology, a template image can also be shared, so that the number of template images set can be appropriately reduced.

[0071] The above-mentioned matching means that the morphology of the teeth to be detected in the initial tooth surface image is close to the tooth morphology in the template image. The specific method of searching for the matching template image can be to search for the template image by inputting the tooth position and tooth surface of the teeth to be detected, or to automatically select the matching template image by analyzing the image. For quantitative analysis of dental plaque, an invariant (the tooth surface area of ​​the teeth to be detected is the best choice as an invariant) is required as a reference. However, when collecting the initial tooth surface image, it is difficult to keep the distance and angle of each shooting consistent, which leads to different sizes and angles of the teeth to be detected in the initial tooth surface images collected multiple times, and then the calculated tooth surface areas are different, making it difficult to compare the changes in dental plaque by quantitative comparison of multiple test results. In this embodiment, the initial tooth surface image is transformed into a matching template image through graphic transformation in step S2, so as to ensure that a consistent tooth surface area can be used each time, eliminating the influence of shooting distance, angle, etc.

[0072] In the above step S3, the regular tooth surface image is segmented into a tooth image area and a dental plaque image area using image processing techniques (such as threshold segmentation, edge detection, etc.), and the remaining parts (such as gums, tooth gaps, etc.) are removed as irrelevant background. Exemplarily, in the image after image segmentation processing, the irrelevant background is black, the tooth image area is green, and the dental plaque image area is red. Thus, the tooth image area and the dental plaque image area can be accurately distinguished, and the accuracy of the dental plaque ratio calculation in the subsequent steps is improved. The dental plaque image area refers to the part of the image that represents the dental plaque. The tooth image area refers to the part of the image that represents the teeth, in some embodiments, the entire tooth surface part (including the tooth surface part covered by dental plaque at the same time), and correspondingly, the size of the tooth image area is used as the invariant of dental plaque analysis; in other embodiments, the tooth surface part covered by dental plaque is not included, and correspondingly, the sum of the sizes of the tooth image area and the dental plaque image area is used as the invariant of dental plaque analysis.

[0073] In the above step S4, the above dental plaque ratio is used to reflect the severity of dental plaque on the teeth to be tested. The higher the ratio, the higher the severity of dental plaque; the lower the ratio, the lower the severity of dental plaque. By calculating the dental plaque ratio, the severity of dental plaque on the teeth to be tested can be quantitatively evaluated, providing doctors with an objective and accurate basis for diagnosis. At the same time, this ratio can also be used as a reliable basis for evaluating treatment effects and monitoring changes in dental health status.

[0074] This embodiment achieves an accurate quantitative evaluation of the dental plaque on the teeth to be tested through the steps of collecting initial tooth surface images, regularizing images, image segmentation and calculating the dental plaque ratio. It has the advantages of simple operation and accurate results. The quantitative evaluation results are comparable and can be used as a reliable basis for dynamic monitoring of oral health, which helps to prevent and treat oral diseases.

[0075] In one embodiment, the designated position includes at least one of the lingual side, the buccal side and the occlusal side, and the step S1 of acquiring the initial tooth surface image of at least one designated position of the tooth to be detected includes:

[0076] S101: placing an imaging device on the lingual side of the tooth to be detected, and collecting an initial tooth surface image of the lingual side of the tooth to be detected; and / or,

[0077] S102: placing an imaging device on the buccal side of the tooth to be detected, and collecting an initial tooth surface image of the buccal side of the tooth to be detected; and / or,

[0078] S103: placing an imaging device on the occlusal surface side of the tooth to be detected, and acquiring an initial tooth surface image of the occlusal surface side of the tooth to be detected.

[0079] In this embodiment, the execution order of the above steps S101-S103 can be in the above order or interchangeable, and this application does not limit this. In this embodiment, the imaging device can be a fluorescent imaging device, such as an existing oral dental plaque observation device, or a visible light imaging device. When a visible light imaging device is used, a dental plaque indicator needs to be used on the teeth.

[0080] The lingual side (the side of the tooth close to the tongue), the buccal side (the side of the tooth close to the cheek), and the occlusal side (the side that contacts the upper and lower teeth when biting). Plaque detection in these three directions can provide the most comprehensive plaque information for a tooth. It is understandable that in some usage scenarios, it may not be necessary to detect all three directions, and only one or two directions may be detected.

[0081] In this embodiment, there is no special limitation on the distance and orientation between the imaging device and the tooth to be detected, as long as the entire tooth surface image of the tooth to be detected can be captured and the images of other teeth, gums, lips and tongue, etc. can be minimized.

[0082] In a specific embodiment, the step S2 of regularizing each initial tooth surface image into a matching template image to obtain a regularized tooth surface image includes:

[0083] S201: classifying the initial tooth surface image by using a pre-trained image classification model to obtain a tooth surface image type;

[0084] S202: Selecting a template image that matches the tooth surface image type from a template image library, and using the selected template image as a matching template image; wherein the template image library has a plurality of pre-designed template images pre-stored therein;

[0085] S203: deforming the initial tooth surface image, regularizing the tooth image region in the initial tooth surface image to match the tooth image region of the template image, and obtaining a regular tooth surface image.

[0086] In this embodiment, in the above step S201, the above tooth surface image types include lingual images, buccal images and occlusal images of different tooth positions. The above image classification model can be trained by conventional training methods to classify the input initial tooth surface image according to a pre-set category. Exemplarily, the image classification model can be trained in the following manner: obtain a training data set, the training data set contains a number of tooth surface images of different tooth positions and tooth surfaces, and manually mark the tooth positions and tooth surfaces of the images; divide the data in the training data set into a training set, a validation set and a test set in a ratio of 8:1:1; select a lightweight classification model (such as a Resnet18 model) as the initial classification model, input the data in the training set into the initial classification model, and perform model training; verify the model performance and optimize the model parameters through the data in the validation set; and then test the model through the data in the test set; and obtain the above image classification model.

[0087] In the above step S202, each template image in the template image library represents a specific tooth morphology, which is used to match the initial tooth surface image. According to the tooth surface image type obtained in step S201, a matching template image is searched and selected from the template image library. Specifically, a tooth position and tooth surface label can be set for each template image in the template image library, and the tooth position and tooth surface information in the tooth surface image type obtained in step S201 can be matched in the template image library to obtain a template image with information matching, thereby obtaining a matching template image; or corresponding image feature points can be generated according to the specific tooth surface image type, and the corresponding image feature points can be matched in the template image library to find the best matching template image, which is selected as the matching template image.

[0088] In the above step S203, the image is deformed to change the shape, size or direction of the image, so as to regularize the tooth image area in the initial tooth surface image to the tooth image area that matches the matching template image. This eliminates the inconsistency of the tooth surface area in each shot caused by the shooting angle and distance. Specifically, this can be achieved through an image deformation algorithm.

[0089] In a specific embodiment, the initial tooth surface image is deformed, and the tooth image region in the initial tooth surface image is regularized to match the tooth image region of the template image to obtain the regularized tooth surface image step S203, including:

[0090] S2031: inputting the initial tooth surface image and the tooth surface image type into a pre-trained key point detection model to obtain a first key point matrix on the initial tooth surface image; wherein the first key point matrix includes a plurality of first key points;

[0091] S2032: Obtain a second key point matrix on the matching template image and a coordinate set of a second vertex array within the second key point matrix area, wherein the second key point matrix includes a plurality of second key points, and the first key point matrix and the second key point matrix have the same row dimension and column dimension;

[0092] S2033: Generate a first vertex array in the first key point matrix area, wherein the first vertex array has the same row dimension and column dimension as the second vertex array, and map each vertex in the first vertex array to the coordinates of each vertex in the second vertex array to obtain the regular tooth surface image.

[0093] In this embodiment, in the above step S2031, the above key point detection model is used to generate a number of key points on the image. The specific positions of the above key points can be a series of points around the tooth area that are specifically defined according to the anatomical structure of the specific tooth surface of the tooth, such as positions with significant features, such as corner points, edge points, center points, tooth tips, tooth gaps, gum margins, etc.

[0094] The training of the key point detection model can adopt the existing training method. For example, the Yolov8 model is selected as the initial key point detection model; tooth surface images of different tooth surface image types are collected, covering different sides of different tooth surfaces such as the lingual side, buccal side and occlusal side, and a number of key points are annotated for each tooth surface image, and the tooth surface image type is annotated to obtain an image data set; the image data in the annotated image data set is divided into a training set, a validation set and a test set in a ratio of 8:1:1, the training set is used for model training, the validation set is used for model tuning, and the test set is used for model performance evaluation, and finally the key point detection model is obtained.

[0095] The initial tooth surface image and the corresponding tooth surface image types (lingual images, buccal images and occlusal images of different tooth positions) are used as input and sent to the pre-trained key point detection model. The model automatically generates several key points on the initial tooth surface image, namely the first key point matrix mentioned above. Each key point in the matrix has corresponding position information (such as x, y coordinates).

[0096] In the above step S2032, the second key point matrix on the matching template image and the second vertex array in the second key point matrix area are pre-calibrated and associated and stored in the template image. The row dimension of the first key point matrix is ​​the same as the row dimension of the second key point matrix, and the column dimension of the first key point matrix is ​​the same as the column dimension of the second key point matrix. The vertices of the grid obtained by dividing the grid in the second key point matrix area are the above-mentioned second vertices. The density of the divided grid can be determined according to the specific image and deformation accuracy requirements, and the embodiment of the present invention does not make special restrictions on this. By matching the first key point matrix and the second key point matrix, the deformation area, graphic angle, etc. are determined, which helps to establish the correct mapping relationship between each first vertex and each second vertex when the image is deformed in the subsequent steps.

[0097] In the above step S2033, the above deformation method can be based on the FFD (Free-Form Deformation) deformation method, according to the first key point matrix and the second key point matrix, and optionally also includes the vertices automatically generated by the tooth surface image, to deform the tooth surface image into the image coordinate axis of the matching template image. The core formula of FFD is the Bernstein polynomial:

[0098]

[0099] Where l, m, and n are the number of grids divided in the directions of the s, t, and u coordinate axes respectively; P i,j,k is the key point coordinate value; B i,l (s) is the Bernstein polynomial;

[0100]

[0101] According to the vertex row and column dimensions of the second vertex array, a grid with the same row and column dimensions is generated in the first key point matrix area in the initial tooth surface image to obtain the first vertex array. During the deformation process, each vertex in the first vertex array is made to correspond one-to-one with each vertex in the second vertex array, and finally the final rendering deformation of the regular tooth surface image is achieved through triangular mapping.

[0102] By image deformation, the tooth image area in the initial tooth surface image is regularized to be consistent with the template image, thereby eliminating the inconsistency of the tooth surface image caused by differences in shooting conditions. The regularized tooth surface image has higher comparability.

[0103] In a specific embodiment, the step S4 of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image includes:

[0104] S401: Calculating the number of first pixels in the tooth image area and the number of second pixels in the dental plaque image area in each regular tooth surface image;

[0105] S402: Calculate a first ratio of the second pixel number to the first pixel number, where the first ratio is the dental plaque ratio of the tooth to be detected.

[0106] In this embodiment, the first pixel number represents the total number of pixels in the tooth image area, and the second pixel number represents the number of pixels in the dental plaque image area. The counting can be performed by traversing the pixels in the image. Through the above steps, a quantitative dental plaque ratio can be obtained, providing an intuitive and reliable dental plaque analysis result for oral health assessment and treatment.

[0107] In a specific embodiment, after the step S402 of calculating the ratio of the second number of pixels to the first number of pixels, where the ratio is the dental plaque ratio of the tooth to be detected, the method further includes:

[0108] S403: Calculating shape parameter values ​​of the dental plaque image area in each regular tooth surface image, where the shape parameter includes at least one of the width of a single dental plaque and the area of ​​a single dental plaque;

[0109] S404: Determine the active plaque index of the tooth to be tested according to the shape parameter value and the dental plaque ratio and a predefined plaque classification standard, wherein the plaque classification standard stores different active plaque indices corresponding to different shape parameter values ​​and different dental plaque ratios.

[0110] In this embodiment, during the process of dental plaque detection and evaluation, in addition to calculating the dental plaque ratio, the shape and size of the dental plaque can also be combined to further refine the evaluation index to obtain an active plaque index.

[0111] In the above step S403, the shape of a single dental plaque in the regular tooth surface image is identified, which further helps to understand the extent of the dental plaque expansion. Specifically, the dental plaque image area can be further processed to identify the boundary of each dental plaque, and then calculate its width and area.

[0112] In the above step S404, the above plaque classification standard is set based on clinical data and doctor experience, which stores the correspondence between different shape parameter values, different plaque ratios and active plaque index. The active plaque index is a comprehensive evaluation index that more intuitively and accurately reflects the activity, distribution and potential harm of dental plaque based on the numerical value of the accurate plaque ratio obtained in this application. Exemplarily, the plaque classification standard is set according to the following rules, for example:

[0113] Active plaque index = 0: no plaque on the tooth surface, plaque ratio = 0;

[0114] Active plaque index = 1: There are scattered dot-like plaques at the gingival margin of the tooth neck, and the plaque ratio of 1 / 5>>0;

[0115] Active plaque index = 2: the width of the plaque at the cervical region does not exceed 1 mm, 1 / 4> plaque ratio>=1 / 5;

[0116] Active plaque index = 3: The plaque coverage area of ​​the tooth neck exceeds 1mm, occupies less than 1 / 3 of the tooth surface, 1 / 3> plaque ratio>=1 / 4;

[0117] Active plaque index = 4: plaque coverage area is between 1 / 3 and 2 / 3 of the tooth surface, 2 / 3> plaque ratio>=1 / 3;

[0118] Active plaque index = 5: The plaque coverage area accounts for more than 2 / 3 of the tooth surface, and the plaque ratio is >= 2 / 3.

[0119] In a specific embodiment, the initial tooth surface image of the tooth to be detected includes an initial tooth surface image of the lingual side, an initial tooth surface image of the buccal side, and an initial tooth surface image of the occlusal side, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the lingual side of the tooth to be detected are used as the first tooth image area and the first dental plaque image area, respectively, the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the buccal side of the tooth to be detected are used as the second tooth image area and the second dental plaque image area, respectively, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the occlusal side of the tooth to be detected are used as the third tooth image area and the third dental plaque image area, respectively;

[0120] Step S4 of calculating the dental plaque ratio of the teeth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image includes:

[0121] S411: Calculate the sum of the number of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area as a first total number of dental plaque pixels;

[0122] S412: Calculate the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area as a first total number of tooth pixels;

[0123] S413: Calculate a second ratio of the first total number of dental plaque pixels to the first total number of tooth pixels, where the second ratio is the dental plaque ratio of the tooth to be detected.

[0124] In the present embodiment, the three template images of the lingual side, buccal side and occlusal side are regularized using the same scaling ratio based on a standard tooth. In addition to calculating the plaque ratio of each tooth surface, the accurate plaque analysis results of the entire tooth can be further obtained, which is convenient for doctors and patients to understand the severity of the plaque more intuitively.

[0125] Since the lingual, buccal and occlusal surfaces are based on the same anatomical structure of a standard tooth, the pixels of the tooth image area of ​​each tooth surface in the regular tooth surface image can be added together, and the pixels of the dental plaque image area of ​​each tooth surface can be added together to calculate the dental plaque ratio of the entire tooth. However, in the prior art, for images of different tooth surfaces, since the shooting distance and angle cannot be guaranteed to be consistent, it is impossible to ensure that the acquisition results of different tooth surfaces maintain the same scaling ratio as the teeth, so the data of three different tooth surfaces cannot be compared horizontally, and cannot be directly integrated into the quantitative evaluation results of the entire tooth.

[0126] In another specific embodiment, there are multiple teeth to be detected, and the step of calculating the dental plaque ratio of the teeth to be detected according to the size of the tooth image area and the dental plaque image area of ​​each regular tooth surface image includes:

[0127] Calculate the sum of the number of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area of ​​all teeth to be detected as the second total number of dental plaque pixels;

[0128] Calculate the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area of ​​all teeth to be detected as a second total number of tooth pixels;

[0129] A third ratio of the second total number of dental plaque pixels to the second total number of tooth pixels is calculated, and the third ratio is the dental plaque ratio of all teeth to be detected.

[0130] In this embodiment, the number of teeth to be tested can be a specific number of teeth or the number of teeth in the entire oral cavity (e.g., 28 teeth, 32 teeth, etc.). The template images of the lingual side, buccal side, and occlusal side of each tooth in the entire oral cavity are respectively scaled at the same scale as the anatomical structure of the corresponding standard tooth. After the initial tooth surface images of the lingual side, buccal side, and occlusal side of each tooth to be tested are regularized, in addition to calculating the dental plaque ratio of each tooth surface and the dental plaque analysis result of a tooth, the dental plaque analysis results of several specific teeth and the entire oral cavity can be further obtained, so that doctors and patients can pay more targeted attention to specific teeth and more intuitively understand the dental health status of the entire oral cavity.

[0131] like Figure 3 As shown, in one embodiment, a dental plaque quantitative analysis device is provided, the device comprising:

[0132] An image acquisition module 10 is used to acquire an initial tooth surface image of at least one designated position of the tooth to be detected;

[0133] An image regularization module 20 is used to regularize each initial tooth surface image into a matching template image to obtain a regularized tooth surface image;

[0134] An image segmentation module 30 is used to perform image segmentation on each regular tooth surface image to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0135] The quantitative analysis module 40 is used to calculate the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image.

[0136] Furthermore, the image regularization module 20 includes:

[0137] An image classification unit, used for classifying the initial tooth surface image by using a pre-trained image classification model to obtain a tooth surface image type;

[0138] The template selection unit is used to select a template image that matches the tooth surface image type from the template image library, and use the selected template image as a matching template image; wherein the template image library has a plurality of pre-designed template images pre-stored therein;

[0139] The image deformation unit is used to deform the initial tooth surface image, regularize the tooth image area in the initial tooth surface image to the tooth image area that matches the template image, and obtain a regular tooth surface image.

[0140] Furthermore, the image deformation unit includes:

[0141] The first key point generation subunit is used to input the initial tooth surface image and the tooth surface image type into a pre-trained key point detection model to obtain a first key point matrix on the initial tooth surface image; wherein the first key point matrix includes a plurality of first key points;

[0142] A second key point acquisition subunit is used to acquire a second key point matrix on the matching template image and a coordinate set of a second vertex array within the second key point matrix area, wherein the second key point matrix includes a plurality of second key points, and the first key point matrix and the second key point matrix have the same row dimension and column dimension;

[0143] The deformation subunit generates a first vertex array in the first key point matrix area, wherein the first vertex array has the same row dimension and column dimension as the second vertex array, and maps each vertex in the first vertex array to the coordinates of each vertex in the second vertex array to obtain the regular tooth surface image.

[0144] Furthermore, the quantitative analysis module 40 includes:

[0145] A first calculation unit is used to calculate the number of first pixels in the tooth image area and the number of second pixels in the dental plaque image area in each regular tooth surface image;

[0146] The second calculation unit is used to calculate a first ratio of the second pixel quantity to the first pixel quantity, where the first ratio is the dental plaque ratio of the tooth to be detected.

[0147] Furthermore, the quantitative analysis module 40 also includes:

[0148] A third calculation unit is used to calculate the shape parameter value of the dental plaque image area in each regular tooth surface image, where the shape parameter includes at least one of the width of a single dental plaque and the area of ​​a single dental plaque;

[0149] The classification unit is used to determine the active plaque index of the tooth to be tested according to the shape parameter value and the dental plaque ratio and a predefined plaque classification standard, wherein the plaque classification standard stores different active plaque indices corresponding to different shape parameter values ​​and different dental plaque ratios.

[0150] Further, the specified orientation includes at least one of the lingual side, the buccal side and the occlusal side, and the image acquisition module 10 includes:

[0151] A first acquisition unit is used to place an imaging device on the lingual side of the tooth to be detected, and acquire an initial tooth surface image of the lingual side of the tooth to be detected;

[0152] A second acquisition unit is used to place the imaging device on the buccal side of the tooth to be detected, and acquire an initial tooth surface image of the buccal side of the tooth to be detected;

[0153] The third acquisition unit is used to place the imaging device on the occlusal surface side of the tooth to be detected, and acquire an initial tooth surface image of the occlusal surface side of the tooth to be detected.

[0154] Further, the initial tooth surface image of the tooth to be detected includes an initial tooth surface image of the lingual side, an initial tooth surface image of the buccal side and an initial tooth surface image of the occlusal side, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the lingual side of the tooth to be detected are used as the first tooth image area and the first dental plaque image area, respectively, the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the buccal side of the tooth to be detected are used as the second tooth image area and the second dental plaque image area, respectively, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the occlusal side of the tooth to be detected are used as the third tooth image area and the third dental plaque image area, respectively;

[0155] The quantitative analysis module 40 includes:

[0156] A fourth calculation unit, configured to calculate the sum of the numbers of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area as a first total number of dental plaque pixels;

[0157] A fifth calculation unit, configured to calculate the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area as a first total number of tooth pixels;

[0158] The sixth calculation unit is used to calculate a second ratio of the first total number of dental plaque pixels to the first total number of tooth pixels, where the second ratio is the dental plaque ratio of the tooth to be detected.

[0159] Furthermore, there are multiple teeth to be detected, and the quantitative analysis module 40 includes:

[0160] A seventh calculation unit, used for calculating the sum of the number of pixels in the first dental plaque image area, the second dental plaque image area and the third dental plaque image area of ​​all teeth to be detected as a second total dental plaque pixel number;

[0161] An eighth calculation unit, used for calculating the sum of the number of pixels of the first tooth image area, the second tooth image area and the third tooth image area of ​​all teeth to be detected as a second total number of tooth pixels;

[0162] The ninth calculation unit is used to calculate a third ratio of the second total number of dental plaque pixels to the second total number of tooth pixels, where the third ratio is the dental plaque ratio of all the teeth to be detected.

[0163] The dental plaque quantitative analysis device of this embodiment achieves an accurate quantitative evaluation of the dental plaque on the teeth to be tested through the steps of collecting initial tooth surface images, regularizing images, image segmentation and calculating dental plaque ratio. It has the advantages of simple operation and accurate results. The quantitative evaluation results are comparable and can be used as a reliable basis for dynamic monitoring of oral health, which helps to prevent and treat oral diseases.

[0164] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement a method for quantitative analysis of dental plaque. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement a method for quantitative analysis of dental plaque. Those skilled in the art will appreciate that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0165] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0166] Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0167] Regularizing each initial tooth surface image into a matching template image to obtain a regularized tooth surface image;

[0168] Performing image segmentation on each regular tooth surface image to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0169] The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image.

[0170] The dental plaque quantitative analysis device of this embodiment achieves an accurate quantitative evaluation of the dental plaque on the teeth to be tested through the steps of collecting initial tooth surface images, regularizing images, image segmentation and calculating dental plaque ratio. It has the advantages of simple operation and accurate results. The quantitative evaluation results are comparable and can be used as a reliable basis for dynamic monitoring of oral health, which helps to prevent and treat oral diseases.

[0171] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps:

[0172] Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected;

[0173] Regularizing each initial tooth surface image into a matching template image to obtain a regularized tooth surface image;

[0174] Performing image segmentation on each regular tooth surface image to obtain a tooth image region and a dental plaque image region in the regular tooth surface image;

[0175] The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each regular tooth surface image.

[0176] The dental plaque quantitative analysis device of this embodiment achieves an accurate quantitative evaluation of the dental plaque on the teeth to be tested through the steps of collecting initial tooth surface images, regularizing images, image segmentation and calculating dental plaque ratio. It has the advantages of simple operation and accurate results. The quantitative evaluation results are comparable and can be used as a reliable basis for dynamic monitoring of oral health, which helps to prevent and treat oral diseases.

[0177] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0178] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0179] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for quantitative analysis of dental plaque, characterized in that: The method comprises: Acquire an initial tooth surface image of at least one designated position of the tooth to be inspected; Regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image; Performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image; The dental plaque ratio of the tooth to be detected is calculated according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

2. The method for quantitative analysis of dental plaque according to claim 1, characterized in that: The step of regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image comprises: Classifying the initial tooth surface image by using a pre-trained image classification model to obtain a tooth surface image type; Selecting a template image that matches the tooth surface image type from a template image library, and using the selected template image as a matching template image; wherein the template image library has a plurality of pre-designed template images pre-stored therein; The initial tooth surface image is deformed, and the tooth image region in the initial tooth surface image is regularized to match the tooth image region of the template image, so as to obtain the regularized tooth surface image.

3. The method for quantitative analysis of dental plaque according to claim 2, characterized in that: The step of deforming the initial tooth surface image, regularizing the tooth image region in the initial tooth surface image to a tooth image region that matches the template image, and obtaining the regular tooth surface image comprises: Inputting the initial tooth surface image and the tooth surface image type into a pre-trained key point detection model to obtain a first key point matrix on the initial tooth surface image; wherein the first key point matrix includes a plurality of first key points; Obtaining a second key point matrix on the matching template image and a coordinate set of a second vertex array within the second key point matrix area, wherein the second key point matrix includes a plurality of second key points, and the first key point matrix and the second key point matrix have the same row dimension and column dimension; In the first key point matrix area, a first vertex array is generated, the row dimension and column dimension of the first vertex array are the same as those of the second vertex array, and each vertex in the first vertex array is mapped to the coordinates of each vertex in the second vertex array to obtain the regular tooth surface image.

4. The method for quantitative analysis of dental plaque according to claim 1, characterized in that: The step of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises: Calculating the number of first pixels in the tooth image area and the number of second pixels in the dental plaque image area in each of the regular tooth surface images; A first ratio of the second number of pixels to the first number of pixels is calculated, where the first ratio is the dental plaque ratio of the tooth to be detected.

5. The method for quantitative analysis of dental plaque according to claim 4, characterized in that: After the step of calculating the ratio of the second number of pixels to the first number of pixels, wherein the ratio is the dental plaque ratio of the tooth to be detected, the method further includes: Calculating the shape parameter value of the dental plaque image area in each of the regular tooth surface images, the shape parameter including at least one of the width of a single dental plaque and the area of ​​a single dental plaque; The active plaque index of the tooth to be tested is determined according to the shape parameter value and the dental plaque ratio and in accordance with a predefined plaque classification standard, wherein the plaque classification standard stores different active plaque indices corresponding to different shape parameter values ​​and different dental plaque ratios.

6. The method for quantitative analysis of dental plaque according to claim 1, characterized in that: The designated position includes at least one of the lingual side, the buccal side and the occlusal side, and the step of acquiring the initial tooth surface image of at least one designated position of the tooth to be detected includes: placing an imaging device on the lingual side of the tooth to be detected, and collecting an initial tooth surface image of the lingual side of the tooth to be detected; and / or, Placing an imaging device on the buccal side of the tooth to be detected to collect an initial tooth surface image of the buccal side of the tooth to be detected; and / or, An imaging device is placed on the occlusal surface side of the tooth to be detected, and an initial tooth surface image of the occlusal surface side of the tooth to be detected is collected.

7. The method for quantitative analysis of dental plaque according to claim 6, characterized in that: The initial tooth surface image of the tooth to be detected includes an initial tooth surface image of the lingual side, an initial tooth surface image of the buccal side and an initial tooth surface image of the occlusal side, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the lingual side of the tooth to be detected are used as the first tooth image area and the first dental plaque image area, respectively, the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the buccal side of the tooth to be detected are used as the second tooth image area and the second dental plaque image area, respectively, and the tooth image area and the dental plaque image area in the regular tooth surface image corresponding to the initial tooth surface image of the occlusal side of the tooth to be detected are used as the third tooth image area and the third dental plaque image area, respectively; The step of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises: Calculating the sum of the numbers of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area as a first total number of dental plaque pixels; Calculating the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area as a first total number of tooth pixels; A second ratio of the first total number of dental plaque pixels to the first total number of tooth pixels is calculated, and the second ratio is the dental plaque ratio of the tooth to be detected.

8. The method for quantitative analysis of dental plaque according to claim 7, characterized in that: The number of teeth to be detected is multiple, The step of calculating the dental plaque ratio of the tooth to be detected according to the area sizes of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images comprises: Calculate the sum of the number of pixels in the first dental plaque image area, the second dental plaque image area, and the third dental plaque image area of ​​all teeth to be detected as the second total number of dental plaque pixels; Calculate the sum of the numbers of pixels in the first tooth image area, the second tooth image area, and the third tooth image area of ​​all teeth to be detected as a second total number of tooth pixels; A third ratio of the second total number of dental plaque pixels to the second total number of tooth pixels is calculated, and the third ratio is the dental plaque ratio of all the teeth to be detected.

9. A dental plaque quantitative analysis device, characterized in that: The device comprises: An image acquisition module, used for acquiring an initial tooth surface image of at least one designated position of the tooth to be inspected; An image regularization module, used for regularizing each of the initial tooth surface images into a matching template image to obtain a regularized tooth surface image; An image segmentation module, used for performing image segmentation on each of the regular tooth surface images to obtain a tooth image region and a dental plaque image region in the regular tooth surface image; The quantitative analysis module is used to calculate the dental plaque ratio of the tooth to be detected according to the area size of the tooth image area and the dental plaque image area of ​​each of the regular tooth surface images.

10. A computer device, characterized in that: The device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for quantitative analysis of dental plaque according to any one of claims 1 to 8.

Images