Oral cavity image segmentation method for oral cavity diagnosis and treatment

Abstract

The invention particularly relates to an oral cavity image segmentation method for oral cavity diagnosis and treatment, which relates to the technical field of oral cavity diagnosis and treatment, and comprises the following steps: acquiring evaluation indexes including axial surface polymerization deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation and occlusal surface minimum space deviation; according to the method, a full-process automatic scheme from image input to quality rating is constructed, and the diagnosis and treatment standardization level and efficiency are remarkably improved; on the basis of precise mask segmentation, through algorithms such as plane fitting and curvature calculation, multi-dimensional quantitative indexes such as axial plane polymerization deviation and shoulder curvature standard deviation are automatically extracted, and core diagnosis and treatment requirements such as dental crown retention force, sealing performance and repair space are comprehensively covered.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oral diagnosis and treatment, and in particular to an oral image segmentation method for oral diagnosis and treatment. BACKGROUND

[0002] In oral prosthetic diagnosis and treatment, tooth preparation is a key link, and its quality directly affects the retention, sealing and service life of the crown restoration.

[0003] Traditional tooth preparation quality evaluation mainly relies on the subjective experience of doctors, and is observed by the naked eye or measured by simple instruments, which has problems such as non-uniform evaluation standard, low precision and strong subjectivity, and can easily lead to unstable repair effect, and even cause complications such as micro-leakage, gingivitis and restoration rupture.

[0004] With the development of digital oral technology, 3D intraoral scanning, dental microscopes and other equipment have been widely used, which can obtain high-precision oral image data.

[0005] However, the existing oral image segmentation technology still has many shortcomings: The segmentation target is mainly large category structures such as teeth and gums, and it is difficult to accurately segment small size key structures such as preparation shoulder platform (width only 0.5-1mm); The segmentation network lacks targeted optimization and is easily disturbed by image noise, reflection and shadow, and the segmentation precision is insufficient; thirdly, there is a lack of integrated solution from image segmentation to quality evaluation, and the segmentation result cannot directly provide quantitative support for diagnosis and treatment evaluation, and additional manual intervention is required, which is low in efficiency.

[0006] Therefore, there is an urgent need for a method that can accurately segment key oral structures and quantitatively evaluate tooth preparation quality based on the segmentation results, in order to solve the defects of the prior art and improve the accuracy and standardization level of oral prosthetic diagnosis and treatment. SUMMARY

[0007] The purpose of the present application is to solve the above problems and provide an oral image segmentation method for oral diagnosis and treatment.

[0008] In order to achieve the above purpose, the present application adopts the following technical scheme: An oral image segmentation method for oral diagnosis and treatment, comprising: Obtaining 3D / 2D oral images, after integrity verification, through preprocessing, outputting standardized and high signal-to-noise ratio image data; Segmenting the prepared tooth, adjacent tooth, gingival edge and preparation shoulder platform, and generating a segmentation mask; Obtaining evaluation indexes including axial surface aggregation deviation, shoulder platform curvature standard deviation, shoulder platform width variation deviation coefficient, occlusal surface minimum space deviation and occlusal surface minimum space deviation. After comprehensive analysis and processing of each evaluation index, a comprehensive evaluation coefficient is obtained, and a corresponding tooth preparation quality grade is matched.

[0009] Preferably, after the 3D / 2D oral images are acquired and integrity verification is performed, the images are preprocessed to output standardized and high signal-to-noise ratio image data, specifically including: acquiring a three-dimensional digital model or a two-dimensional color image of the oral cavity; preprocessing the three-dimensional model: coordinate alignment: automatically aligning the STL model to the Frankfort plane as a standard jaw plane, and extracting the bilateral infraorbital points and external auditory canal points to construct a reference coordinate system; region of interest cropping: automatically identifying the crown-root boundary of the target prepared tooth based on dental anatomy features, and cropping the excess alveolar bone, other teeth and soft tissue model based on the boundary; smoothing the cropped model; two-dimensional image preprocessing: illumination normalization: decomposing the reflection component and the illumination component of the image, and adjusting the illumination component; color space conversion: converting the RGB image to the HSV color space, enhancing the color difference, and then converting back to the RGB space for output; image scaling and alignment: uniformly scaling the image to a preset pixel and automatically rotating the image based on the dental center axis.

[0010] Preferably, the specific steps include: segmenting the core target: the prepared tooth; reference target: adjacent teeth, gum edge, prepared shoulder, occlusal surface; the segmentation network uses an improved U-Net++ network as the basic architecture; a convolution block attention module is introduced, and channel attention and spatial attention mechanisms are added after each convolution block of the encoder; and an edge-aware loss function is designed; a 1x1 convolution is used instead of a 3x3 convolution in the last layer of the decoder, and a batch normalization layer is added.

[0011] Preferably, the method further comprises: training the data, including dataset construction, data augmentation and determining training parameters; segmentation post-processing and precision verification: performing morphological optimization on the segmentation mask output by the network, including: connected region analysis: removing isolated noise regions with an area less than 50 pixels; Edge smoothing: Morphological closing operations are used to fill holes in the segmented area, and then median filtering is used to smooth the edges to ensure that the edge lines such as shoulders and ridges are continuous and without breaks; Regional consistency check: Check the positional relationship between the prepared tooth and the adjacent tooth. If there is a positional conflict, the dividing boundary is automatically adjusted to a preset reasonable range. Accuracy verification: For the segmentation results of each input image, the Dice coefficient, cross-union ratio and pixel accuracy of each target region are automatically calculated; Output: Generates a multi-channel segmentation mask, with each channel corresponding to a segmentation target. The mask corresponds one-to-one with the preprocessed original image.

[0012] Preferably, the process of obtaining the axial surface aggregation deviation includes: For 3D models: Point cloud data of the prepared tooth body is extracted from the segmentation mask, and the point cloud is divided into four axial regions: buccal, lingual, mesial, and distal, based on the tooth body's central axis. For each axial region, the point cloud is fitted to a plane using the least squares method; Calculate the angle between two planes based on their normal vectors. The axial convergence degree is obtained by adding the buccal-lingual tilt angle and the mesial-distal tilt angle. The normal range of the axial surface cohesion degree is preset. If the obtained axial surface cohesion degree is not within the normal range, the difference between the axial surface cohesion degree and the normal range is calculated and recorded as the axial surface cohesion deviation. For 2D images: If only a single 2D image is entered, two orthogonal images will be taken in the cheek-tongue direction and the near-to-mid direction; if multiple images have been entered, orthogonal view images will be automatically selected. For each image, extract the axial edge contour using the prepared tooth segmentation mask; Straight lines were fitted to the buccal, lingual, mesial, and distal margin contours to obtain the slope of each margin. The included angle is calculated based on the slope of the relative edges, the degree of aggregation is obtained by summing the angles, and the axial aggregation deviation is obtained.

[0013] Preferably, the process of obtaining the standard deviation of the shoulder curvature and the coefficient of variation of the shoulder width includes: Extract the edge contour of the pre-designed shoulder from the segmentation mask, and discretize the curve into a sequence of coordinate points: For a sequence of discrete coordinate points, the curvature of each point is calculated using the five-point numerical differentiation method; The standard deviation of the shoulder curvature was calculated. The maximum allowable threshold for the standard deviation of shoulder curvature is preset. If the standard deviation of shoulder curvature is greater than the maximum allowable threshold, the difference between the two is calculated and recorded as the standard deviation of shoulder curvature. extracting a gingival edge contour from the segmentation mask, and offsetting a preset distance in the direction of the tooth crown as a reference line based on the contour; uniformly selecting a preset number of measurement points on the prepared shoulder contour, and distributing the points equidistantly along the circumference of the shoulder, and measuring the vertical distance from the prepared surface to the reference line at each point; After obtaining each vertical distance, the mean and standard deviation are calculated, and the standard deviation is divided by the mean to obtain the shoulder width variation coefficient. A maximum allowable threshold of the preset shoulder width variation coefficient is set. If the shoulder width variation coefficient is greater than the maximum allowable threshold, the difference between the two is calculated and recorded as the shoulder width variation deviation coefficient.

[0014] Preferably, the process of obtaining the occlusal surface minimum space deviation includes: extracting the occlusal surface point cloud or contour of the adjacent tooth from the segmentation mask, and fitting a reference plane; uniformly selecting a preset number of measurement points in the prepared tooth occlusal surface segmentation area, covering the buccal side, lingual side, and central fossa; calculating the vertical distance from each measurement point to the reference plane; arranging the obtained vertical distances in ascending order according to their numerical values, and extracting the minimum vertical distance, which is recorded as the occlusal surface minimum space. A minimum occlusal surface space threshold is set. If the occlusal surface minimum space is less than the minimum space threshold, the difference between the two is calculated and recorded as the occlusal surface minimum space deviation.

[0015] Preferably, the process of obtaining the minimum interproximal space includes: extracting the interproximal surface area of the prepared tooth and the adjacent tooth from the segmentation mask, respectively; using the KD tree algorithm to quickly calculate the minimum distance or minimum pixel distance between the two interproximal surfaces; uniformly selecting a preset number of cross sections along the vertical direction of the interproximal surface, calculating the interproximal space of each cross section, and arranging all the obtained interproximal spaces in ascending order according to their numerical values, and extracting the minimum interproximal space. A normal value range of the minimum interproximal space is set. If the minimum interproximal space is not within the normal value range of the minimum interproximal space, the difference between the minimum interproximal space and the normal value range is calculated and recorded as the minimum interproximal space deviation.

[0016] Preferably, the comprehensive evaluation coefficient is obtained after the comprehensive analysis and processing of each evaluation index, and the corresponding tooth preparation quality grade is matched. Specifically, it includes: The preset axial surface aggregation deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation, and weight factor of the occlusal surface minimum space deviation are multiplied and calculated, and a comprehensive evaluation coefficient is obtained after summation.

[0017] To sum up, due to the adoption of the technical scheme, the application has the following beneficial effects: 1. The application constructs a full-process automation scheme from image input to quality rating, significantly improving the standardization level and efficiency of diagnosis and treatment; based on accurate segmentation mask, through algorithms such as plane fitting and curvature calculation, multi-dimensional quantitative indicators such as axial surface aggregation deviation and shoulder curvature standard deviation are automatically extracted, fully covering core diagnosis and treatment requirements such as crown retention force, sealing, and repair space.

[0018] 2. The application realizes pixel-level accurate segmentation of key oral structures through targeted technical optimization, solving the pain points of insufficient segmentation of small targets and complex edges in the prior art; after segmentation, morphological optimization and precision verification are performed to ensure that the target of prepared teeth, adjacent teeth, and gum edges are not missed and have no edge breakpoints, providing reliable basic data support for subsequent diagnosis and treatment quality evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0019] In the following description of exemplary embodiments in conjunction with the accompanying drawings, more details, features and advantages of the application are disclosed, in which: Figure 1 The method flowchart of the application. DETAILED DESCRIPTION

[0020] Several embodiments of the application will be described in more detail below with reference to the accompanying drawings, so that those skilled in the art can implement the application. The application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the application comprehensive and complete, and to fully convey the scope of the application to those skilled in the art. The embodiments do not limit the application.

[0021] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and / or the present specification, and should not be interpreted in an idealized or overly formal sense, unless expressly so defined herein.

[0022] Example 1 The specific embodiments incorporate the accompanying drawings Figure 1 A detailed description will be given.

[0023] The accompanying drawings Figure 1 A flow chart of a dental image segmentation method for dental diagnosis and treatment is provided for the embodiments of the present application, which shows the complete steps from obtaining 3D / 2D dental images to obtaining comprehensive evaluation coefficients after comprehensive analysis and processing of each evaluation index.

[0024] In the present embodiment, it comprises: Compatible 3D / 2D dental images are obtained, and after integrity verification, standardized and high signal-to-noise ratio image data are output through targeted preprocessing such as coordinate alignment, cropping, denoising, and illumination normalization, providing reliable input for subsequent processes; Specifically, it comprises: Obtain a three-dimensional digital model or a two-dimensional color image inside the mouth; Three-dimensional digital model: receive the standard STL format file output by the intraoral scanner (such as 3Shape TRIOS, iTero Element), and the model resolution is required to be ≥0.05mm, and the point cloud density is required to be ≥1000 points / mm2 , to ensure that the details of the tooth surface (such as the shoulder edge) are completely retained; Two-dimensional color image: receive the JPG / PNG format image taken by a dental microscope (such as Carl Zeiss OP-MI100) or a high-definition oral camera, with a resolution of ≥2048x1536 pixels and a color mode of RGB, and the image should include the complete target prepared tooth, adjacent teeth and surrounding gum tissue, without obvious obstruction (such as instruments, saliva residue); The system automatically detects the integrity of the image. If the three-dimensional model has missing surfaces, the two-dimensional image has serious obstructions or the resolution does not meet the standard, an input data unqualified prompt will be generated, and the problem type (such as 3D model mesial surface missing, 2D image gum area severe reflection) will be clearly labeled to guide the user to re-collect; Pretreatment of three-dimensional model: Coordinate alignment: automatically align the STL model to the Frankfort plane (orbito-meatal plane) as the standard jaw plane, extract the bilateral infraorbital points and external auditory canal points in the model to construct a reference coordinate system, and eliminate the model tilt caused by different patient head postures; Region of interest cropping: based on dental anatomy features, automatically identify the crown-root boundary (enamel-cementum junction) of the target prepared tooth, take the boundary as the reference, extend upward to 2mm above the occlusal surface, extend to the adjacent tooth crown midline, and extend downward to the 1 / 3 of the tooth root, crop the remaining alveolar bone, other teeth and soft tissue model, and reduce the calculation amount; Denoising and smoothing: The moving least squares (MLS) method was used to smooth the cropped model, removing point cloud noise generated during the scanning process (such as isolated points and sharp protrusions). The smoothing coefficient was set to 0.03 to ensure that the surface morphology of the tooth is realistically restored, while retaining the edge information of key features such as the shoulder.

[0025] 2D image preprocessing: Illumination normalization: The Retinex algorithm is used to decompose the reflection component and illumination component of the image. By adjusting the illumination component, reflections (such as strong light reflection on the enamel surface) and shadows (such as shadows at the junction of the gum and tooth) caused by differences in shooting angle and light source intensity are eliminated, so that the image brightness is uniform and the contrast is consistent. Color space conversion: Convert the RGB image to the HSV color space, enhance the color difference between the tooth (whiter) and the gum (redder) by adjusting the saturation channel, and then convert it back to the RGB space for output, providing clearer feature differentiation for subsequent segmentation; Image scaling and alignment: The image is uniformly scaled to a preset pixel size (2048×2048 pixels) (keeping the aspect ratio unchanged and filling the edges with black), and the image is automatically rotated based on the tooth's central axis to make the buccal and lingual surfaces of the target prepared tooth parallel to the horizontal direction of the image, ensuring the consistency of the direction of subsequent feature calculations; The preprocessed 3D model and 2D image are grayscale normalized (pixel values ​​are mapped to the [0,255] range), and the image comparison files before and after preprocessing are saved for subsequent result tracing.

[0026] An improved U-Net++ network (including CBAM attention mechanism and edge-aware loss function) was used to segment key targets such as prepared teeth, adjacent teeth, gingival margins, and prepared shoulders, and pixel-level segmentation masks were generated and verified for accuracy. Specifically, it includes: Core segmentation objective: tooth preparation (only including the exposed tooth structure after preparation, excluding the original crown portion that has not been removed); Reference target: Adjacent teeth (teeth on the left / right side that are in direct contact with the target prepared tooth, including the entire crown portion); Gingival margin (the junction between the gingiva and the tooth structure, distinguishing between free gingiva and attached gingiva); Prepare the shoulder (the edge line of the neck of the tooth body is a key fitting area for crown restoration and needs to be accurate to the pixel level). Occlusal surface (the occlusal contact surface of the prepared tooth and adjacent teeth, used for spatial distance measurement); The segmentation network uses an improved U-Net++ network as its basic architecture. Compared with the traditional U-Net, it adds a multi-scale feature fusion path, which improves the segmentation ability of small targets (such as pre-existing shoulder platforms with a width of only 0.5-1mm) and complex edges. A convolutional block attention module (CBAM) is introduced, adding channel attention and spatial attention mechanisms after each convolutional block of the encoder. By learning weight allocation, the network automatically focuses on key areas such as the crown and shoulder, suppressing interference from irrelevant information such as gingival background and image noise. And design an edge-aware loss function: ,in , , These are the preset weighting factors; For Dice's loss; For edge loss; Cross-entropy loss; Decoder optimization: Replace 3×3 convolutions with 1×1 convolutions in the last layer of the decoder to reduce parameter redundancy, and add batch normalization (BN) layers to accelerate network convergence and avoid overfitting.

[0027] Training the data includes dataset construction, data augmentation, and determining training parameters; Dataset construction: Collect a predetermined number (1000 cases) of clinical dental preparation images (including 500 3D models and 500 2D images), covering different tooth positions such as anterior teeth, premolars, and molars, as well as different preparation quality samples such as excellent, qualified, and unqualified. The images were manually annotated by three chief physicians with more than 10 years of experience in dental restoration. The annotation results were used as true labels after passing the consistency test (Kappa coefficient ≥ 0.85). Data augmentation: Perform augmentation operations on the training set, such as random flipping (horizontal / vertical), rotation (±15°), scaling (0.8-1.2 times), and adding Gaussian noise (variance ≤0.01), to expand the dataset size and improve the network's generalization ability; Training parameters: The Adam optimizer is used, with an initial learning rate of [value missing]. The learning rate decays with the number of iterations (decaying to 0.9 of the original value every 10 epochs), the number of training epochs is 50, the batch size is 8, and an early stopping strategy is adopted (training stops if the validation set loss does not decrease for 5 consecutive epochs).

[0028] Post-segmentation processing and accuracy verification: Post-processing steps: Morphological optimization of the segmentation mask output by the network, including: Connected component analysis: Remove isolated noise regions with an area less than 50 pixels (such as mis-segmented gingival dots); Edge smoothing: Morphological closing operation (3×3 kernel size) is used to fill the small holes in the segmentation area, and then median filtering (3×3 window size) is used to smooth the edges to ensure that the edge lines such as shoulders and ridges are continuous and without breaks; Regional consistency check: Check the positional relationship between the prepared tooth and the adjacent tooth (must meet the clinical anatomical distance, such as interproximal space ≥0.1mm). If there is a positional conflict (such as overlapping segmented areas), the segmentation boundary is automatically adjusted to a preset reasonable range. Accuracy verification: For each input image segmentation result, the Dice coefficient, intersection-over-union (IoU) ratio, and pixel accuracy (PA) of each target region are automatically calculated, and an accuracy report is generated. If the Dice coefficient of a target region is less than a preset threshold (e.g., <0.92), it will be marked as insufficient segmentation accuracy, and the network will be triggered to re-segment (adjust attention weights) or prompt the user to check the quality of the input image. Output: Generates a multi-channel segmentation mask (3D model as point cloud label, 2D image as pixel label), each channel corresponds to a segmentation target (e.g., channel 1 = prepared tooth, channel 2 = adjacent tooth, channel 3 = gingival margin, channel 4 = prepared shoulder, channel 5 = occlusal surface). The mask corresponds one-to-one with the preprocessed original image, which facilitates region localization during subsequent feature calculation.

[0029] Based on the segmentation mask, evaluation indicators including axial plane aggregation deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation, and occlusal surface minimum space deviation are obtained through algorithms such as plane fitting, curvature calculation, and distance measurement. The process of obtaining the axial plane convergence deviation includes: The sum of the inclination angles of the prepared body relative to the two side walls (buccal-lingual, mesial-distal) reflects the taper characteristics of the prepared body, which directly affects the retention and stability of the crown. Too little convergence (<4°) will make it difficult for the crown to be placed, while too much convergence (>14°) will reduce retention. The ideal range is 6-10°.

[0030] For 3D models: Point cloud data of the prepared tooth was extracted from the segmentation mask. Based on the tooth's central axis (extracted by principal component analysis PCA), the point cloud was divided into four axial regions: buccal, lingual, mesial, and distal (each region occupies 90° of the circumference of the prepared tooth). For each axial region, the point cloud is fitted to a plane using the least squares method to obtain the plane equations for each axial plane (e.g., the cheek plane equation). Equation of the lateral plane: , , , To prepare the three-dimensional coordinates of each point in the point cloud of the axial plane region of the tooth; , , It is the normal vector component of the cheek-side axial plane fitting plane; It is a constant term of the cheek-side axial plane fitting plane; , , These are the normal vector components of the plane fitted to the tongue-side axial surface; It is a constant term for the plane fitting the axial surface of the tongue; The angle (i.e., tilt angle) between two opposing planes (buccal-lingual, mesial-distal) is calculated using the normal vectors of the two opposing planes, as shown in the following formula: , , , where are the normal vectors relative to the plane. The angle between the two planes is expressed in degrees. buccal-lingual tilt angle ( ) and near-to-far tilt angle ( The axial convergence is obtained by adding the values ​​of the two sides; if the prepared tooth is an anterior tooth, only the mesiodistal inclination angle is calculated as the axial convergence. The normal range of the axial surface cohesion degree is preset. If the obtained axial surface cohesion degree is not within the normal range, the difference between the axial surface cohesion degree and the normal range is calculated, and the absolute value is recorded as the axial surface cohesion deviation. For 2D images: If only a single 2D image is entered, the system prompts the user to take two orthogonal images in the cheek-tongue direction and the near-to-mid direction; if multiple images have been entered, the system automatically filters out orthogonal view images. For each image, the prepared tooth segmentation mask is used to extract the axial edge contour using the Canny edge detection algorithm; Straight lines were fitted to the buccal, lingual, mesial, and distal margin contours to obtain the slope of each margin. Calculate the included angle based on the slope of the relative edges, sum them to obtain the degree of convergence (the calculation logic is the same as that of the 3D model, and it needs to be multiplied by the perspective correction coefficient, such as 1.05, to compensate for the perspective error of the 2D image), and obtain the axial plane convergence deviation.

[0031] The process of obtaining the standard deviation of shoulder curvature and the coefficient of variation of shoulder width includes: The prepared shoulder is the connection point between the crown and the tooth body. Its continuity (no interruption, no sharp edges) and width uniformity directly affect the seal and fit of the crown, avoiding complications such as microleakage and gingivitis after restoration.

[0032] Extract the edge contour of the pre-designed shoulder from the segmentation mask (3D model is a spatial curve, 2D image is a planar curve), and discretize the curve into a sequence of coordinate points: 3D: ; 2D: ; For a sequence of discrete coordinate points, the curvature of each point is calculated using the five-point numerical differentiation method. The formula is as follows (taking a 2D curve as an example): ,in , The first derivative, , It is the second derivative; The standard deviation of shoulder curvature is calculated; the smaller the standard deviation of shoulder curvature, the smoother the shoulder. The maximum allowable threshold of the standard deviation of shoulder curvature is preset. If the standard deviation of shoulder curvature is greater than the maximum allowable threshold, the difference between the two is calculated, and the absolute value is recorded as the standard deviation of shoulder curvature. Extract the gingival margin contour from the segmentation mask, and use this contour as a reference to offset it towards the crown by a preset distance (0.5 mm, the lower limit of the clinically standard shoulder width) as a reference line; A predetermined number (50) of measurement points are evenly selected on the prepared shoulder profile and distributed equidistantly along the circumference of the shoulder. The vertical distance from the surface of the prepared body to the reference line (i.e., the width of the shoulder) is measured at each point. After obtaining each vertical distance, calculate the mean and standard deviation, and divide the standard deviation by the mean to obtain the shoulder width variation coefficient. The maximum allowable threshold for the shoulder width variation coefficient is preset. If the shoulder width variation coefficient is greater than the maximum allowable threshold, calculate the difference between the two, and record the absolute value as the shoulder width variation deviation coefficient.

[0033] The process of obtaining the minimum spatial deviation of the occlusal surface includes: The occlusal surface of the prepared dental prosthesis must provide sufficient vertical space for the crown restoration (such as porcelain crown or all-ceramic crown) to ensure the thickness (usually ≥1.5mm) and strength of the restoration and to prevent the restoration from breaking during occlusion.

[0034] Extract the occlusal surface point cloud (3D) or contour (2D) of adjacent teeth from the segmentation mask, and use the RANSAC algorithm to fit the reference plane (excluding abnormal points such as occlusal surface wear and defects). A predetermined number (30) of measurement points are evenly selected within the preparatory body occlusal surface segmentation area, covering key locations such as the buccal side, lingual side, and central fossa; Calculate the vertical distance from each measurement point to the reference plane (the direction of the distance is the direction of tooth eruption, i.e., perpendicular to the occlusal plane and upwards). The obtained vertical distances are sorted in ascending order of numerical value, and the minimum vertical distance is extracted and recorded as the minimum space of the occlusal surface. A minimum space threshold of the occlusal surface is preset. If the minimum space of the occlusal surface is less than the minimum space threshold, the difference between the two is calculated, and the absolute value is recorded as the minimum space deviation of the occlusal surface.

[0035] If the target tooth to be prepared is an anterior tooth (without a clear occlusal surface), then the measurement will be changed to the distance from the incisal edge to the reference plane (≥1.0mm); if the adjacent tooth is missing, the system will prompt the user to enter the occlusal surface data of the opposing tooth or use the standard occlusal plane as a reference.

[0036] The process of obtaining the minimum adjacent face gap includes: A clear and continuous interproximal space must be maintained between the prepared tooth and the adjacent tooth to facilitate the placement and cleaning of the crown during restoration, and to avoid the interproximal contact being too tight (causing the crown to fail to be placed) or too loose (causing food impaction).

[0037] Extract the adjacent surface regions of the preparatory body and adjacent teeth from the segmentation mask (3D is point cloud, 2D is contour). The KD tree algorithm is used to quickly calculate the minimum distance (3D model) or minimum pixel distance (2D image, which needs to be multiplied by the image scaling factor when converted to actual distance). The ideal clinical range is 0.1-0.3 mm. A predetermined number (20) of cross sections are uniformly selected along the vertical direction of the proximal surface (the direction of crown height). The interproximal gap of each cross section is calculated, and all the obtained interproximal gaps are arranged in ascending order according to their numerical values. The minimum interproximal gap is extracted. The normal range of the minimum interproximal gap is preset. If the minimum interproximal gap is not within the normal range, the difference between the minimum interproximal gap and the normal range is calculated, and the absolute value is recorded as the minimum interproximal gap deviation.

[0038] After comprehensive analysis and processing of various evaluation indicators, a comprehensive evaluation coefficient is obtained, and the corresponding tooth preparation quality grade is matched. Specifically, it includes: The weighting factors for the pre-defined axial surface convergence deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation, and occlusal surface minimum space deviation are calculated by multiplying the axial surface convergence deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation, and occlusal surface minimum space deviation with their corresponding weighting factors, and then summing them to obtain the comprehensive evaluation coefficient.

[0039] By pre-setting weighting factors for core evaluation indicators such as axial plane aggregation deviation and shoulder curvature standard deviation, a comprehensive evaluation coefficient is generated through weighted summation, successfully solving the problem of the one-sidedness of evaluating the quality of tooth preparation with a single indicator.

[0040] Its weighting settings can accurately match clinical treatment needs, highlighting the key impacts of axial convergence and shoulder precision on crown retention and sealing, while also taking into account auxiliary dimensions such as occlusal space and interproximal space. This achieves systematic integration of multi-dimensional quality information, allowing the assessment results to comprehensively reflect the overall level of tooth preparation and avoiding the neglect of other potential treatment risks due to the achievement of a single indicator.

[0041] Transforming scattered quantitative indicators into intuitive comprehensive evaluation coefficients and corresponding quality levels significantly improves the practicality and standardization of clinical applications.

[0042] Traditional assessments rely on doctors' subjective experience and judgment, which are easily affected by individual differences. This method, however, establishes a standardized quality assessment system through a unified weighted calculation logic, reducing human error and making the assessment results more objective and comparable.

[0043] Meanwhile, a clear quality grading system can provide doctors with clear diagnostic and treatment references, help quickly locate deficiencies in the preparation process, adjust and optimize the plan in a timely manner, thereby improving the success rate of crown restoration, reducing the risk of postoperative complications, and forming a complete closed loop from image segmentation and index calculation to quality assessment, providing efficient and reliable decision support for oral diagnosis and treatment.

[0044] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0045] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0046] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0047] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0048] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0049] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0050] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0051] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0052] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0053] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An oral image segmentation method for oral diagnosis, characterized by, The method comprises the following steps: Obtain 3D / 2D oral images, and after integrity verification, output standardized and high signal-to-noise ratio image data through preprocessing; Segment the prepared tooth, adjacent tooth, gum edge and prepared shoulder, and generate a segmentation mask; Obtain evaluation indexes including axial surface aggregation deviation, shoulder curvature standard deviation, shoulder width variation deviation coefficient, occlusal surface minimum space deviation and occlusal surface minimum space deviation; After comprehensive analysis and processing of each evaluation index, a comprehensive evaluation coefficient is obtained, and a corresponding tooth preparation quality grade is matched.

2. The oral image segmentation method for oral diagnosis according to claim 1, wherein, Obtain 3D / 2D oral images, and after integrity verification, output standardized and high signal-to-noise ratio image data through preprocessing, specifically comprising: Obtain a three-dimensional digital model or a two-dimensional color image inside the oral cavity; Preprocess the three-dimensional model, including coordinate alignment and region of interest cropping; And smooth the cropped model; Two-dimensional image preprocessing, including illumination normalization, color space conversion, image scaling and alignment.

3. The dental image segmentation method for dental diagnosis according to claim 1, wherein, Segment the prepared tooth, adjacent tooth, gum edge and prepared shoulder, and generate a segmentation mask, specifically comprising: Segmentation core target: prepared tooth; reference target: adjacent tooth, gum edge, prepared shoulder and occlusal surface; the segmentation network uses an improved U-Net++ network as the basic architecture; Add channel attention and spatial attention mechanisms after each convolution block of the encoder, and design an edge perception loss function; In the last layer of the decoder, a 1×1 convolution is used, and a batch normalization layer is added.

4. The dental image segmentation method for dental diagnosis according to claim 3, wherein, Further comprising: Train the data, including data set construction, data enhancement and determination of training parameters; Morphological optimization of the segmentation mask output by the network, including: Connected region analysis: remove isolated noise regions with an area less than 50 pixels; Edge smoothing: fill the holes in the segmentation area by morphological closing operation, and then smooth the edges by median filtering to ensure that the shoulder edge line is continuous and has no breakpoints; Region consistency check: check the positional relationship between the prepared tooth and the adjacent tooth; Accuracy verification: automatically calculate the Dice coefficient, intersection-over-union ratio and pixel accuracy of each target region for the segmentation result of each input image; Output result: generate a multi-channel segmentation mask image, each channel corresponds to a segmentation target, and the mask image corresponds to the preprocessed original image one by one.

5. The dental image segmentation method for dental diagnosis according to claim 1, wherein, The acquisition process of the axial surface aggregation deviation comprises: For 3D model: Extract the point cloud data of the prepared tooth from the segmentation mask, and divide the point cloud into buccal, lingual, mesial and distal axial surface regions based on the tooth axis; Fit a plane to the point cloud in each axial surface region using the least squares method; According to the normal vectors of the two relative planes, calculate the included angle between the two planes; Add the buccal-lingual inclination angle and the mesial-distal inclination angle to obtain the axial surface aggregation degree; Pre-set the normal value range of the axial surface aggregation degree, calculate the difference between the axial surface aggregation degree and the normal value range, and record it as the axial surface aggregation deviation; For 2D image: If only a single 2D image is input, supplement two orthogonal images in the buccal-lingual and mesial-distal directions; if multiple images have been input, automatically select the orthogonal view images; Extract the axial surface edge contour from the prepared tooth segmentation mask of each image; Fitting straight lines to the buccal, lingual, mesial and distal edge contours respectively to obtain the slope of each edge; According to the slope of the relative edge, the included angle is calculated, the aggregation degree is summed up, and the axial surface aggregation deviation is obtained.

6. The dental image segmentation method for dental diagnosis according to claim 5, wherein, The process of obtaining the shoulder curvature standard deviation and the shoulder width variation deviation coefficient includes: Extract the edge contour of the prepared shoulder from the segmentation mask, and discretize the curve into a coordinate point sequence: For the discrete coordinate point sequence, the curvature of each point is calculated using the five-point numerical differentiation method; Calculate the shoulder curvature standard deviation; And preset the maximum allowable threshold of the shoulder curvature standard deviation, if the shoulder curvature standard deviation is greater than the maximum allowable threshold, the difference between the two is calculated, which is recorded as the shoulder curvature standard deviation.

7. The dental image segmentation method for dental diagnosis according to claim 6, wherein, Also includes: Extract the gum edge contour from the segmentation mask, and offset the contour by a preset distance in the direction of the crown as a reference line; Uniformly select a preset number of measurement points on the prepared shoulder contour, which are distributed equidistantly along the shoulder circumference. Measure the vertical distance from the prepared body surface to the reference line at each point. Calculate the mean and standard deviation of each vertical distance, and divide the standard deviation by the mean to obtain the shoulder width variation coefficient. Pre-set the maximum allowable threshold of the shoulder width variation coefficient. If the shoulder width variation coefficient is greater than the maximum allowable threshold, the difference between the two is calculated, which is recorded as the shoulder width variation deviation coefficient.

8. The dental image segmentation method for dental diagnosis according to claim 1, wherein, The process of obtaining the minimum occlusal space deviation includes: Extract the occlusal surface point cloud or contour of the adjacent tooth from the segmentation mask, and fit the reference plane; Uniformly select a preset number of measurement points within the segmentation area of the prepared body occlusal surface; Calculate the vertical distance from each measurement point to the reference plane; Extract the minimum vertical distance, which is recorded as the minimum occlusal space. Pre-set the minimum occlusal space threshold. If the minimum occlusal space is less than the minimum space threshold, the difference between the two is calculated, which is recorded as the minimum occlusal space deviation.

9. The dental image segmentation method for dental diagnosis according to claim 1, wherein, The process of obtaining the minimum interproximal space includes: Extract the adjacent surface area of the prepared body and the adjacent tooth from the segmentation mask respectively; Use the KD tree algorithm to quickly calculate the minimum distance or minimum pixel distance between the two adjacent surfaces; Uniformly select a preset number of cross sections along the vertical direction of the adjacent surface, calculate the interproximal space of each cross section, and extract the minimum interproximal space; Pre-set the normal value range of the minimum interproximal space, calculate the difference between the minimum interproximal space and the normal value range, and record it as the minimum interproximal space deviation.

10. The dental image segmentation method for dental diagnosis according to claim 9, wherein, After comprehensive analysis and processing of each evaluation index, the comprehensive evaluation coefficient is obtained, and the corresponding tooth preparation quality grade is matched, which specifically includes: After presetting the weight factors of the axial surface aggregation deviation, the shoulder curvature standard deviation, the shoulder width variation deviation coefficient, the minimum occlusal space deviation and the minimum occlusal space deviation, the comprehensive evaluation coefficient is calculated by weighted summation.

Images