Periodontal disease accurate quantitative evaluation method based on IOS image and CBCT image

Abstract

The invention relates to the technical field of tooth diagnosis, in particular to a periodontal disease accurate quantitative evaluation method based on an IOS image and a CBCT image, and the method comprises the following steps: carrying out the image segmentation of an intraoral scanning IOS image, so as to obtain an IOS segmentation result of each tooth; performing image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth; preprocessing and registering the IOS segmentation result and the CBCT segmentation result to obtain a data fusion model; obtaining a gingival contour and a tooth long axis according to the data fusion model, obtaining gingival contour points according to the gingival contour, obtaining an alveolar bone contour on the alveolar bone along the direction of the tooth long axis by the gingival contour points, and obtaining a GBD distance; and evaluating the periodontal disease according to the GBD distance. According to the method, the data fusion model is obtained according to the IOS segmentation result and the CBCT result, the gingival contour and the tooth long axis are obtained through the data fusion model, and the GBD distance between the gingival contour and the alveolar bone contour is measured in the direction of the tooth long axis so as to evaluate the health condition of the periodontal disease.

Description

Technical Field

[0001] The present invention relates to the technical field of dental diagnosis, and in particular to a method, system, device and storage medium for accurate quantitative evaluation of periodontal diseases based on IOS images and CBCT images. Background Art

[0002] Periodontal disease is a health problem of widespread concern worldwide, manifested as a progressive and mostly irreversible loss of gums and alveolar bone, ultimately leading to tooth loss. The Global Oral Health Status Report shows that nearly 19% of individuals over the age of 15 suffer from severe periodontal disease, totaling more than one billion cases worldwide, and the number is increasing year by year. Therefore, timely and accurate assessment is essential for effective treatment intervention. Clinically, measuring periodontal pocket depth with a periodontal probe is a standard practice for quantitatively assessing the severity of the disease. Shallow periodontal pocket depth usually implies healthier gums, while deeper periodontal pockets usually indicate inflammation and underlying periodontal disease. However, although this probing technique is standard, it is subjective, has the potential for human error, is invasive, and only measures the values ​​of six key points to measure the health of the teeth. Therefore, the development of an accurate, efficient, and non-invasive assessment system is essential for the effective management of periodontal disease.

[0003] Recently, with the development of medical imaging technology, some digital dental technologies (e.g., two-dimensional panoramic X-ray imaging, cone beam computed tomography (CBCT) imaging, and intraoral scanning (IOS) technology) have become important tools to assist periodontal assessment. Among the above technologies, X-ray imaging is designed based on the principle of tomography, and the obtained X-ray images can only provide two-dimensional projection information of teeth and bones; CBCT imaging scans the target area in all directions, and the obtained CBCT images can provide three-dimensional information of teeth and alveolar bones; IOS technology is to superimpose the data collected at different positions in the mouth, and finally form a complete three-dimensional IOS image, providing high-resolution crown (the part of the tooth exposed outside the gums) and gum information.

[0004] With the development of computer technology, many existing studies have used deep learning technology to evaluate periodontal health based on dental images (e.g., two-dimensional panoramic X-ray images and cone beam computed tomography (CBCT) images). Among them, some researchers detected the radiological bone level and cementum-enamel junction (CEJ) level from X-ray images, and then measured the distance between key points in the two levels along the long axis of the tooth to analyze the percentage of radiographic bone loss (RBL) and perform staging. In addition, some researchers discussed the role of three-dimensional CBCT images in the assessment of periodontal disease. They used commercial software to semi-automatically derive 3D models of teeth and bones, and used manual measurement methods to measure the distance of bone levels to determine the degree of periodontitis. Although these methods provide feasible strategies for the assessment of periodontal disease, they still have the following limitations. First, the information provided by the images used by these methods is insufficient, and the usefulness of gingival information for the assessment of early periodontal disease is not taken into account. X-ray images reflect overlapping information of structures such as teeth and bones, which are distorted and difficult to accurately determine the three-dimensional position and morphological information of the lesion; although CBCT images can provide complete three-dimensional bone information, they cannot reflect the health of the gums. Secondly, these methods evaluate the degree of alveolar bone loss, and only locate a single tooth and calculate the distance of a few points. This cannot fully display the extent of periodontal disease of each tooth, especially the extent of gum loss in the early stages. Finally, the measurement steps performed by these methods require additional image key point annotations, and quantitative measurements still rely heavily on the professional knowledge of dentists and cannot automatically provide quantitative results for periodontal evaluation. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and provide a method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images, comprising the following steps:

[0006] Perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation result of each tooth;

[0007] Perform image segmentation on the CBCT image to obtain the CBCT segmentation result of each tooth;

[0008] Preprocessing and registering the IOS segmentation result and the CBCT segmentation result to obtain a data fusion model;

[0009] Acquire the gingival contour and the long axis of the tooth according to the data fusion model, acquire the gingival contour points according to the gingival contour, obtain the alveolar bone contour on the alveolar bone along the direction of the long axis of the tooth by using the gingival contour points and acquire the GBD distance;

[0010] Periodontal disease was assessed based on the GBD distance.

[0011] Preferably, performing image segmentation on the intraoral scanned IOS image to obtain an IOS segmentation result of each tooth includes:

[0012] Downsampling the intraoral scanned IOS images to obtain sampling points, and rotating the intraoral scanned IOS images in different directions to a unified position to obtain a unified IOS image;

[0013] Obtain tooth center data from the sampling point according to the unified IOS image, and generate a tooth image block of each tooth according to the tooth center data and the unified IOS image;

[0014] Obtaining gum label data according to the unified IOS image, and calculating average gum curvature information of the tooth image block according to the gum label data to obtain tooth gum boundary information;

[0015] The tooth image block and the tooth-gingival boundary information are segmented into IOS segmented teeth and gums according to the coronal segmentation network, and the IOS segmented teeth are corrected to obtain corrected tooth results.

[0016] Preferably, performing image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth further includes:

[0017] A second label classification network predicts a tooth label and a first predicted background label based on the CBCT image output;

[0018] A tooth region of interest ROI is obtained according to the CBCT image, and a third label classification network outputs a predicted tooth contour, predicted tooth contents and a second predicted background label from the tooth region of interest ROI;

[0019] classifying each classified tooth according to the tooth label, the first predicted background label, the predicted tooth contour, the predicted tooth content and the second predicted background label;

[0020] The tooth label classification network obtains the FDI label of each tooth from the tooth region of interest ROI;

[0021] Assign the correct tooth label to each classified tooth according to the FDI label.

[0022] Preferably, the IOS result and the CBCT result are preprocessed and registered to obtain a data fusion model, further comprising:

[0023] reconstructing teeth and alveolar bone meshes from the CBCT segmentation results according to a marching cube algorithm to obtain the reconstructed CBCT segmentation results;

[0024] The principal component directions of the reconstructed CBCT segmentation result and the IOS segmentation result are respectively extracted by principal component analysis, and the CBCT center point data are integrated, and the transformation parameters between the center point data of the reconstructed CBCT segmentation result and the IOS segmentation result are calculated by singular value decomposition, so as to complete the coarse registration by aligning the dental arch position and dental arch direction;

[0025] On the basis of the coarse registration, an iterative closest point matching registration algorithm is used for each tooth to perform point-to-plane registration on the reconstructed CBCT segmentation result and the IOS segmentation result, and a fine registration is completed to unify the IOS segmentation result and the reconstructed CBCT segmentation result to the same position to obtain a data fusion model.

[0026] Preferably, obtaining the alveolar bone contour on the alveolar bone and acquiring the GBD distance according to the gingival contour points on the data fusion model along the direction of the long axis of the tooth obtained by the data fusion model further comprises:

[0027] Obtaining a gingival contour according to vertices on the edge of the crown mesh of the data fusion model, specifying the number of gingival contour points according to the gingival contour, and obtaining gingival contour points by interpolation;

[0028] generating the tooth long axis from the tooth vertex data of the data fusion model by the principal component analysis;

[0029] The alveolar bone contour is obtained on the alveolar bone according to the gingival contour point along the direction of the long axis of the tooth to obtain the GBD distance.

[0030] Preferably, evaluating periodontal disease according to the GBD distance further comprises:

[0031] The dental health level is determined according to a set threshold and the GBD distance, wherein the dental health level is divided into levels including health, mild periodontal disease, moderate periodontal disease and severe periodontal disease.

[0032] Preferably, judging the tooth health degree according to the set threshold and the GBD distance further comprises:

[0033] If the GBD distance is within the first threshold, it is healthy;

[0034] If the GBD distance is between the first threshold and the second threshold, it is mild periodontal disease;

[0035] If the GBD distance is between the second threshold and the third threshold, it is moderate periodontal disease;

[0036] If the GBD distance is greater than the third threshold, it indicates severe periodontal disease.

[0037] Based on the same concept, the present invention also provides a periodontal disease precise quantitative assessment device based on IOS images and CBCT images, comprising:

[0038] An IOS image segmentation module is used to perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation result of each tooth;

[0039] A CBCT image segmentation module is used to perform image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth;

[0040] A multimodal data fusion module, used for format matching and registration of the IOS result and the CBCT result to obtain a data fusion model;

[0041] The GBD measurement and quantitative evaluation module is used to obtain the gingival contour and the long axis of the tooth according to the data fusion model, obtain the gingival contour points according to the gingival contour, obtain the alveolar bone contour on the alveolar bone along the direction of the long axis of the tooth and obtain the GBD distance, and evaluate periodontal disease according to the GBD distance.

[0042] Based on the same concept, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in the embodiment.

[0043] Based on the same concept, the present invention also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, enables one or more processors to perform the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in the embodiment.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1) The present invention obtains a data fusion model including aligned crowns, teeth and alveolar bones by combining three-dimensional IOS images and CBCT images, providing complete and high-precision crown, tooth and alveolar bone data;

[0046] 2) The present invention evaluates the health status of periodontal disease by measuring the GBD distance between the gingival contour and the alveolar bone contour along the long axis of the tooth in a three-dimensional digital space, and reduces the error of the evaluation method of measuring a small number of points in clinical and existing methods by customizing the number of measurement points. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the following detailed description of the preferred embodiment.The drawings are only for the purpose of illustrating the preferred embodiments and are not to be construed as limiting the invention.

[0048] Figure 1 It is a flow chart of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images of the present invention;

[0049] Figure 2 It is a flow chart of the method for accurate quantitative evaluation of periodontal disease based on IOS images and CBCT images of the present invention;

[0050] Figure 3 It is a structural schematic diagram of IOS image segmentation of the present invention;

[0051] Figure 4 It is a structural schematic diagram of CBCT image segmentation of the present invention;

[0052] Figure 5 It is a structural schematic diagram of GBD measurement and quantitative evaluation of the present invention;

[0053] Figure 6 This is a schematic diagram of the output results of some teeth of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0055] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0056] Example 1

[0057] See also Figure 1 and Figure 2 As shown, the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images provided in this embodiment includes the following steps:

[0058] The intraoral scanned IOS image is segmented to obtain the IOS segmentation result of each tooth. Specifically, in this embodiment, the points of the input IOS image containing the tooth image are downsampled and then processed to obtain the segmented crowns and gums.

[0059] See also Figure 3 As shown, the intraoral scanned IOS image is segmented to obtain the IOS segmentation results of each tooth, including:

[0060] Down-sampling the intraoral scanned IOS images to obtain sampling points, and rotating the intraoral scanned IOS images in different directions to a uniform position to obtain a uniform IOS image. Specifically, in this embodiment, the IOS images are rotated to a uniform position by a model rotation network in a Pointnet++ network. In other embodiments, other networks may be used to rotate the IOS images to a uniform position.

[0061] According to the unified IOS image, tooth center data is obtained from the sampling point, and a tooth image block of each tooth is generated according to the tooth center data and the unified IOS image. Specifically, in this embodiment, the tooth center point data of the IOS image after rotating to a unified position is obtained by a centroid prediction network in the Poi ntnet++ network. In other embodiments, other networks may be used to obtain the tooth center point data of the IOS image after rotating to a unified position.

[0062] Obtaining gum label data according to the unified IOS image, calculating the average curvature information of the gums of the tooth image block according to the gum label data to obtain the gum boundary information of the tooth. Specifically, in this embodiment, the gum label data of the IOS image after rotating to a unified position is obtained by a gum separation network in a Poinnet++ network. In other embodiments, the gum label data of the IOS image after being rotated to a unified position by other networks may be used.

[0063] The tooth image blocks and the tooth-gingival boundary information are segmented into IOS segmented teeth and gums according to the crown segmentation network, and the IOS segmented teeth are corrected to obtain the corrected tooth results. Specifically, in this embodiment, 32 types of teeth and 1 type of gums are segmented through the crown segmentation network in the Poi ntnet++ network. In other embodiments, other networks can be used to segment 32 types of teeth and 1 type of gums, and output IOS segmented tooth labels.

[0064] More preferably, correcting the IOS segmented teeth to obtain a corrected teeth result further includes:

[0065] To handle the situation where there may be FDI label errors in the correction results, the label correction submodule aggregates the segmentation results of each crown according to the cost ranking algorithm and the dental arch curve to minimize the problems of label reversal and identical labels.

[0066] This embodiment can accurately segment all the patient's crowns by segmenting the IOS image, and classify them according to the FDI system proposed by the International Dental Federation, so as to obtain a unique identification of each crown.

[0067] See also Figure 4 As shown, image segmentation is performed on the cone beam computed tomography (CBCT) image to obtain a CBCT segmentation result for each tooth.

[0068] Preferably, performing image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth further includes:

[0069] The second label classification network (Tooth Regi on Segmentation Network) predicts the tooth label and the first predicted background label according to the CBCT image output. Specifically, in this embodiment, the second label classification network uses the encoder and decoder in the nnUNet network;

[0070] According to the CBCT image, the tooth region of interest ROI is obtained, and the third label classification network (Tooth Boundary and Inter ior Segmentation Network) outputs the predicted tooth contour, predicted tooth contents and the second predicted background label from the tooth region of interest ROI. Specifically, in this embodiment, the third label classification network uses the encoder and decoder in the nnUNet network to locate the tooth region of interest ROI, and segment the predicted tooth contour, predicted tooth contents and the second predicted background label based on the tooth region of interest ROI, because the amount of calculation for tooth segmentation directly on the CBCT three-dimensional image will be very large. Therefore, by first determining the tooth region of interest ROI, irrelevant areas can be excluded, and only the tooth region of interest can be retained to reduce the amount of calculation for subsequent segmentation;

[0071] Each classified tooth is classified according to the tooth label, the first predicted background label, the predicted tooth contour, the predicted tooth content and the second predicted background label. Specifically, in this embodiment, the decoder in the nnUNet network is used to decode the tooth label, the first predicted background label, the predicted tooth contour, the predicted tooth content and the second predicted background label. The results of the two-label classification and the three-label classification of the tooth are first integrated through the watershed algorithm to obtain the complete shape of each tooth, and the alveolar bone is segmented at the same time.

[0072] The tooth label classification network obtains the FDI label of each tooth from the tooth region of interest ROI;

[0073] The correct tooth label is assigned to each classified tooth according to the FDI label. Specifically, in this embodiment, a voting strategy is used to calculate the probability of the label of each tooth in the watershed algorithm result and the overlapping part in the tooth label classification network result, and the final tooth label is obtained based on probability voting, but the implementation method is not limited to this voting mechanism.

[0074] This embodiment can accurately segment all the patient's teeth by segmenting the CBCT image, obtain standard FDI numbers, and segment the alveolar bone at the same time.

[0075] The IOS segmentation results and the CBCT segmentation results are preprocessed and registered to obtain a data fusion model. Specifically, in this embodiment, aligned crowns, teeth, and alveolar bones are obtained according to the IOS segmentation results and the CBCT segmentation results.

[0076] Preferably, the IOS results and the CBCT results are preprocessed and registered to obtain a data fusion model, further comprising:

[0077] Reconstructing the teeth and alveolar bone meshes from the CBCT segmentation results according to the marching cubes algorithm to obtain the reconstructed CBCT segmentation results;

[0078] The principal component directions of the reconstructed CBCT segmentation results and the IOS segmentation results are respectively extracted by principal component analysis, and the CBCT center point data are integrated. The transformation parameters between the center point data of the reconstructed CBCT segmentation results and the IOS segmentation results are calculated by singular value decomposition (SVD), so as to complete the rough registration by aligning the dental arch position and dental arch direction. Specifically, in this embodiment, principal component analysis (PCA) is used to extract multiple principal component directions of the reconstructed CBCT segmentation results and the IOS segmentation results. In this embodiment, three principal component directions are extracted;

[0079] On the basis of coarse registration, the iterative closest point (ICP) matching registration algorithm is used for each tooth to perform point-to-plane registration on the reconstructed CBCT segmentation results and the IOS segmentation results, and fine registration is completed to unify the IOS segmentation results and the reconstructed CBCT segmentation results to the same position, obtain the data fusion model, and further obtain the dental arch curve based on the data fusion model.

[0080] See also Figure 5 As shown, the gingival contour (Gingival Contour) and the tooth long axis (Tooth's Longtud inal Ax is) are obtained according to the data fusion model, the gingival contour points are obtained according to the gingival contour, the alveolar bone contour (Alveotar Bone Contour) is obtained on the alveolar bone along the direction of the tooth long axis of the gingival contour points and the GBD (gum-bone) distance is obtained. Specifically, in this embodiment, the gingival contour is obtained according to the crown of the data fusion model, and the tooth long axis and the alveolar bone contour are obtained according to the tooth mesh data and the alveolar bone mesh data of the data fusion model.

[0081] Preferably, obtaining the alveolar bone contour on the alveolar bone and acquiring the GBD distance according to the gingival contour points on the data fusion model along the direction of the long axis of the tooth obtained by the data fusion model further comprises:

[0082] The gingival contour is obtained according to the vertices on the edge of the crown mesh of the data fusion model, and the number of gingival contour points is specified according to the gingival contour, and the gingival contour points are obtained by interpolation method;

[0083] The tooth long axis is generated from the tooth vertex data of the data fusion model by principal component analysis. Specifically, in this embodiment, principal component analysis (PCA) is used to identify the main features with the largest amount of information from the high-dimensional tooth vertex data to generate the tooth long axis for describing its geometric shape. In other embodiments, other methods may be used to obtain the tooth long axis;

[0084] The alveolar bone contour is obtained on the alveolar bone according to the gingival contour point along the direction of the long axis of the tooth to obtain the GBD distance. Specifically, in this embodiment, the alveolar bone contour point is obtained by measuring the gingival contour point along the direction of the long axis of the tooth to obtain the GBD distance between the corresponding points of the gingival contour point and the alveolar bone contour point.

[0085] Based on the obtained gingival contour and alveolar bone contour, the gingival contour point measured the gingival-bone GBD distance along the long axis of the tooth representing the tooth direction information, and the accurate quantitative assessment results of periodontal disease were obtained based on the GBD value and the set threshold.

[0086] The periodontal disease is evaluated according to the GBD distance. Specifically, in this embodiment, the average GBD distance of all points of the gum contour points and the alveolar bone contour points is compared with a set threshold.

[0087] The assessment of periodontal disease based on GBD distance further includes:

[0088] The dental health level is judged according to the set threshold and GBD distance, where the dental health level is divided into levels including healthy, mild periodontal disease, moderate periodontal disease and severe periodontal disease.

[0089] See also Figure 6 As shown in FIG. 1 , judging the tooth health degree according to the set threshold and GBD distance further includes:

[0090] If the GBD distance is within the first threshold, the tooth is healthy. Specifically, in this embodiment, the first threshold is 2 mm. When the GBD distance is less than 2 mm, the tooth is healthy.

[0091] If the GBD distance is between the first threshold and the second threshold, it is mild periodontal disease. Specifically, in this embodiment, the second threshold is 4 mm. When the GBD distance is between 2 mm and 4 mm, the tooth has mild periodontal disease. That is, when the tooth label is 47 and the GBD distance is 3.14 mm, the tooth health level is mild periodontal disease.

[0092] If the GBD distance is between the second threshold and the third threshold, it is moderate periodontal disease. Specifically, in this embodiment, the third threshold is 6 mm. When the GBD distance is between 4 mm and 6 mm, the tooth has moderate periodontal disease, that is, when the tooth label is 11 and the GBD distance is 5.14 mm, the tooth health level is moderate periodontal disease. When the tooth label is 12 and the GBD distance is 5.40 mm, the tooth health level is moderate periodontal disease.

[0093] If the GBD distance is greater than the third threshold, it is severe periodontal disease (Server Periodontal Disease). Specifically, in this embodiment, when the GBD distance is greater than 6 mm, the tooth has severe periodontal disease, that is, when the tooth label is 13 and the GBD distance is 6.40 mm, the tooth health level is severe periodontal disease.

[0094] Example 2

[0095] This embodiment provides a periodontal disease precise quantitative assessment system based on IOS images and CBCT images, which is used to execute the method in the above embodiment 1, including:

[0096] An IOS image segmentation module is used to perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation result of each tooth;

[0097] A CBCT image segmentation module is used to perform image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth;

[0098] A multimodal data fusion module, used for format matching and registration of the IOS result and the CBCT result to obtain a data fusion model;

[0099] The GBD measurement and quantitative evaluation module is used to obtain the gingival contour and the long axis of the tooth according to the data fusion model, obtain the gingival contour points according to the gingival contour, obtain the alveolar bone contour on the alveolar bone along the direction of the long axis of the tooth and obtain the GBD distance, and evaluate periodontal disease according to the GBD distance.

[0100] Example 3

[0101] In some embodiments of the present application, a computer device is also provided, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in any one of Example 1.

[0102] The present invention also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in any one of Example 1.

[0103] It is understandable that, for the aforementioned precise quantitative assessment method of periodontal disease based on IOS images and CBCT images, if they are all implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0104] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0105] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A precise quantitative assessment method for periodontal disease based on IOS images and CBCT images, characterized in that: The following steps are involved: Perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation result of each tooth; Perform image segmentation on the CBCT image to obtain the CBCT segmentation result of each tooth; Preprocessing and registering the IOS segmentation result and the CBCT segmentation result to obtain a data fusion model; Acquire the gingival contour and the long axis of the tooth according to the data fusion model, acquire the gingival contour points according to the gingival contour, obtain the alveolar bone contour on the alveolar bone along the direction of the long axis of the tooth by using the gingival contour points and acquire the GBD distance; Periodontal disease was assessed based on the GBD distance.

2. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 1, characterized in that: Perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation results of each tooth, including: Downsampling the intraoral scanned IOS images to obtain sampling points, and rotating the intraoral scanned IOS images in different directions to a unified position to obtain a unified IOS image; Obtain tooth center data from the sampling point according to the unified IOS image, and generate a tooth image block of each tooth according to the tooth center data and the unified IOS image; Obtaining gum label data according to the unified IOS image, and calculating average gum curvature information of the tooth image block according to the gum label data to obtain tooth gum boundary information; The tooth image block and the tooth-gingival boundary information are segmented into IOS segmented teeth and gums according to the coronal segmentation network, and the IOS segmented teeth are corrected to obtain corrected tooth results.

3. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 1, characterized in that: Performing image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth further includes: A second label classification network predicts a tooth label and a first predicted background label based on the CBCT image output; A tooth region of interest ROI is obtained according to the CBCT image, and a third label classification network outputs a predicted tooth contour, predicted tooth contents and a second predicted background label from the tooth region of interest ROI; classifying each classified tooth according to the tooth label, the first predicted background label, the predicted tooth contour, the predicted tooth content and the second predicted background label; The tooth label classification network obtains the FDI label of each tooth from the tooth region of interest ROI; Each classified tooth is assigned a correct tooth label according to the FDI label.

4. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 1, characterized in that: Preprocessing and registering the IOS result and the CBCT result to obtain a data fusion model further includes: reconstructing teeth and alveolar bone meshes from the CBCT segmentation results according to a marching cube algorithm to obtain a reconstructed CBCT segmentation result; The principal component directions of the reconstructed CBCT segmentation result and the IOS segmentation result are respectively determined by principal component analysis, and the CBCT center point data are integrated, and the transformation parameters between the center point data of the reconstructed CBCT segmentation result and the IOS segmentation result are calculated by singular value decomposition, so as to complete the coarse registration by aligning the dental arch position and dental arch direction; On the basis of the coarse registration, an iterative closest point matching registration algorithm is used for each tooth to perform point-to-plane registration on the reconstructed CBCT segmentation result and the IOS segmentation result, and a fine registration is completed to unify the IOS segmentation result and the reconstructed CBCT segmentation result to the same position to obtain a data fusion model.

5. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 4, characterized in that: According to the gum contour points on the data fusion model, the alveolar bone contour is obtained on the alveolar bone along the direction of the long axis of the tooth obtained by the data fusion model and the GBD distance is obtained, further comprising: Obtaining a gingival contour according to vertices on the edge of the crown mesh of the data fusion model, specifying the number of gingival contour points according to the gingival contour, and obtaining gingival contour points by interpolation; generating the tooth long axis from the tooth vertex data of the data fusion model by the principal component analysis; The alveolar bone contour is obtained on the alveolar bone according to the gingival contour point along the direction of the long axis of the tooth to obtain the GBD distance.

6. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 5, characterized in that: Assessing periodontal disease according to the GBD distance further comprises: The dental health level is determined according to a set threshold and the GBD distance, wherein the dental health level is divided into levels including health, mild periodontal disease, moderate periodontal disease and severe periodontal disease.

7. The method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images according to claim 6, characterized in that: Judging the degree of tooth health according to the set threshold and the GBD distance further includes: If the GBD distance is within the first threshold, it is healthy; If the GBD distance is between the first threshold and the second threshold, it is mild periodontal disease; If the GBD distance is between the second threshold and the third threshold, it is moderate periodontal disease; If the GBD distance is greater than the third threshold, it indicates severe periodontal disease.

8. The precise quantitative assessment system for periodontal disease based on IOS images and CBCT images is characterized by: include: An IOS image segmentation module is used to perform image segmentation on the intraoral scanned IOS image to obtain the IOS segmentation result of each tooth; A CBCT image segmentation module is used to perform image segmentation on the CBCT image to obtain a CBCT segmentation result of each tooth; A multimodal data fusion module, used for format matching and registration of the IOS result and the CBCT result to obtain a data fusion model; The GBD measurement and quantitative evaluation module is used to obtain the gingival contour and the long axis of the tooth according to the data fusion model, obtain the gingival contour points according to the gingival contour, obtain the alveolar bone contour on the alveolar bone along the direction of the long axis of the tooth and obtain the GBD distance, and evaluate periodontal disease according to the GBD distance.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for accurate quantitative assessment of periodontal disease based on IOS images and CBCT images as described in any one of claims 1 to 7.

Images