Cross-modal registration removable partial denture design method

Abstract

The invention provides a cross-modal registration removable partial denture design method. The cross-modal registration removable partial denture design method comprises the following steps: acquiring a two-dimensional oral panoramic film and three-dimensional intraoral scanning data of a patient; the radiology bone loss proportion of each tooth is calculated, and the image credibility component of each tooth position in the panoramic film is obtained based on the segmentation result; extracting a three-dimensional key point and a neck edge contour point set of each tooth; calculating a registration credibility component of each tooth position; fusing the image credibility component of each tooth position in the panorama and the registration credibility component to generate an image and registration credibility index; and taking the radiology bone loss proportion and the credibility index of each tooth position as design constraints, and performing automatic design of the removable partial denture. The aim of improving clinical scientificity, safety and interpretability of the design scheme is achieved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of digital technology for oral prosthetics, and relates to medical image processing and three-dimensional oral model calculation technology, in particular to a method for cross-modality registration based on panoramic radiographs and intraoral scanning data, quantitative evaluation of radiological bone loss information, and auxiliary design of removable partial dentures. BACKGROUND

[0002] The design of removable partial dentures needs to consider the following factors: missing tooth range (Kennedy classification), health status of remaining teeth (such as mobility, inclination angle, restoration, caries condition, etc.), periodontal support condition (degree of alveolar bone resorption), soft tissue morphology (mucosa active area), and denture seating path and undercut. Among them, the alveolar bone height and its loss degree are important basis for evaluating the stability of the remaining teeth.

[0003] Radiographic bone loss (RBL) is a commonly used imaging evaluation index, which is usually based on the ratio of alveolar bone height to root length in panoramic radiographs, and is used to evaluate the degree of periodontal disease and periodontal tissue support condition. In recent years, some studies have attempted to use deep learning methods to automatically evaluate RBL from panoramic radiographs to assist in the early identification of periodontal disease. However, the imaging process of panoramic radiographs has obvious technical sensitivity, which is easily affected by factors such as device parameters, patient position, and anatomical structure overlap, resulting in image distortion and unstable measurement.

[0004] The existing technology has the following shortcomings: (1) The existing RBL evaluation method based on panoramic radiographs mainly faces diagnostic or screening applications, and usually outputs in the form of overall or classified results of dentition, which cannot provide structured parameters that can be directly used for denture design at the level of each tooth; (2) In the process of digital denture design, intraoral scanning data can accurately reflect the three-dimensional morphology of the crown and soft tissue, but it cannot provide radiological information such as root and alveolar bone height. There is a lack of a reliable mechanism to map the RBL information obtained from panoramic radiographs to the three-dimensional tooth entity obtained from intraoral scanning; (3) Due to the differences in image quality and cross-modality registration errors, directly using panoramic radiograph evaluation results for denture design may lead to unreasonable selection of abutment teeth or setting of retention strength. The existing technology has not explicitly quantified the unreliability in the image and registration process and incorporated it into the denture design decision-making process.

[0005] Therefore, it is necessary to provide a technical scheme to evaluate the radiological bone loss in the panoramic film, quantify the image quality and cross-modality registration reliability, and use the related results to assist the automated design of the removable partial denture. SUMMARY

[0006] In view of the problems in the prior art, the present application provides a removable partial denture design method based on cross-modality registration. The method evaluates the radiological bone loss information of each tooth site in the panoramic film, and introduces image and registration reliability indicators to quantify the image quality and cross-modality mapping reliability, thereby converting the related image information into calculable design constraints for assisting the automated design of the removable partial denture.

[0007] The present application provides a removable partial denture design method based on cross-modality registration, comprising: acquiring two-dimensional oral panoramic film and three-dimensional intraoral scanning data of a patient; performing tooth-by-tooth detection and segmentation processing on the panoramic film, and extracting the enamel cementum junction reference point, apical point, and mesial and distal bone ridge top point of each tooth based on the segmentation result, calculating the radiological bone loss ratio of each tooth based on the reference point, apical point, and bone ridge top point, and obtaining the image reliability component of each tooth site in the panoramic film based on the segmentation result; performing tooth and gum segmentation processing on the intraoral scanning data, constructing a three-dimensional tooth site entity, and extracting the three-dimensional key point and neck margin contour point set of each tooth; establishing a parametric projection model of the dental arch based on the three-dimensional key point and neck margin contour point set of each tooth, performing cross-modality registration on the panoramic film and intraoral scanning data, solving the projection model parameters to obtain the registration residual through an optimization algorithm, and calculating the registration reliability component of each tooth site based on the registration residual; fusing the image reliability component of each tooth site in the panoramic film and the registration reliability component to generate an image and registration reliability indicator; using the radiological bone loss ratio and reliability indicator of each tooth site as a design constraint to perform automated design of the removable partial denture.

[0008] Optionally, the calculation of the radiological bone loss ratio of each tooth comprises: based on the formula calculating the root length of the tooth site; based on the formula calculating the mesial height, based on the formula calculating the distal height; calculating the mesial bone loss ratio and distal bone loss ratio based on the root length, mesial height, and distal height of the tooth site; selecting the maximum of the mesial bone loss ratio and distal bone loss ratio as the radiological bone loss ratio of the tooth. in, For root length, For the root tip, As a reference point for the cementoenamel junction, Near to medium altitude, At a distance of medium altitude, To project onto the unit vector of the major axis, It is the proximal bony ridge. It is the distal ridge of the bone.

[0009] Optionally, the factor for calculating the image confidence component in the image confidence component of each tooth position in the panoramic film based on the segmentation results includes: Confidence of tooth segmentation, clarity of tooth margin gradient, and overlap score of adjacent tooth masking; The formula for calculating the image credibility component is as follows: ,in, For image credibility components, The confidence level for tooth position segmentation. For the clarity of the gradient at the tooth margin, The overlap score is given for masks of adjacent teeth.

[0010] Optionally, the step of establishing a parametric projection model of the dental arch based on the three-dimensional key points and cervical margin contour point set of each tooth includes: 3D points Using formula Perform a rigid body transformation, and then convert the transformation result... Mapped to panoramic pixel coordinates ; The mapping function is: , , in and For point The corresponding dental arch parameter coordinates, For arc length parameters, For height parameters, Let be a rotation matrix. It is a translation vector. This is the offset. The coefficient of the linear term, The coefficient of the quadratic term, As the vertical baseline, This is the vertical scaling factor. For coupling term coefficients, parameter set .

[0011] Optionally, the target function of the registration residual obtained by solving the projection model parameter through the optimization algorithm comprises: , wherein, , and are weight coefficients, is a key point error, is a contour error, is a constraint for maintaining the monotonicity of the tooth position; , , , wherein, is the total error of the key point matching item, is the total error of the contour matching item, is the total error of the constraint item for maintaining the monotonicity of the tooth position, is a Huber robust loss, is a collection point, is a minimum interval, is the two-dimensional key point coordinate corresponding to the dental arch parameterization projection function, is the three-dimensional key point coordinate corresponding to the dental arch parameterization projection function, is the signed distance field function of the dental arch parameterization projection function, is the three-dimensional key point coordinate corresponding to the is the horizontal coordinate of the two-dimensional point after projection.

[0012] Optionally, the calculation formula of the reliability index is: , wherein, is the reliability index, is the quantification result of the image layer unreliability, is the quantification result of the cross-modal registration layer unreliability, The larger the value is, the lower the reliability of the tooth position corresponding to the RBL result is.

[0013] Optionally, the role of the image and registration reliability index comprises: a risk penalty factor used in the abutment suitability score; a constraint factor used in the calculation of the upper limit of the undercut utilization depth; Criteria used for the selection and combination restrictions of fixation body types; Used as the basis for risk warnings and review markings in electronic design sheets.

[0014] Optionally, the formula for calculating the suitability score of the abutment teeth is as follows: , in, As a radiographic marker of bone loss, As a credibility indicator, The normalized result for looseness, This is the normalized result for the tilt angle. This serves as a risk marker for medical records.

[0015] Optionally, the constraint factor calculated using the upper limit of the indentation depth is: .

[0016] Optionally, after the step of automating the design of removable partial dentures using the radiographic bone loss ratio and reliability index of each tooth position as design constraints, the method further includes: The steps involve verifying and automatically repairing the automated design results based on manufacturing rules and clinical safety to obtain an electronic design sheet and manufacturable design data for removable partial dentures.

[0017] The present invention provides a cross-modal registration method for designing removable partial dentures. This method automatically assesses radiographic bone loss (RBL) at each tooth position in panoramic radiographs and maps it to a 3D dental arch scan through cross-modal registration. Simultaneously, it introduces the Image and Registration Reliability Index (CRI) to quantify the reliability of the RBL results. Using RBL and CRI as constraints, it automatically generates safe and interpretable removable partial denture design schemes and electronic design sheets. This accurately and reliably integrates key information from two-dimensional images into the three-dimensional digital design process. Under the premise of quantitatively assessing data reliability, it achieves personalized intelligent design of removable partial dentures driven by objective image data, with known and controllable risks, thereby improving the clinical scientificity, safety, and interpretability of the design scheme. Attached Figure Description

[0018] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0019] Figure 1 A flowchart illustrating the cross-modal registration removable partial denture design method provided in this disclosure. Detailed Implementation

[0020] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0021] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0022] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0023] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The illustrations only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0024] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0025] RBL (Radiographic Bone Loss) refers to radiographic bone loss. CEJ (Cemento-Enamel Junction) refers to the cementoenamel junction; CRI (Confidence / Reliability Index) refers to the confidence index of image and registration. Tooth position: FDI coding is adopted. Orientation: including mesial / distal / buccal / lingual.

[0026] Radiological bone loss, including tooth position , definition: Root length : the distance from the CEJ reference point to the apical point along the tooth long axis.

[0027] In order to characterize the reliability of tooth-by-tooth RBL results in engineering and clinical applications, image and registration reliability indicators are introduced ∈[0, 1], the larger the value, the lower the reliability.

[0028] CRI consists of the following two parts: Image reliability component : reflects the image quality and measurement stability in the panoramic film; Registration reliability component : reflects the local reliability of 2D-3D cross-modal mapping.

[0029] The comprehensive reliability is defined as: This definition is used for risk union modeling to ensure that the overall design strategy automatically tends to be conservative when any source is unreliable.

[0030] The technical purposes to be achieved by the embodiment include: 1. How to automatically obtain a calculable RBL indicator for each tooth in the panoramic film; 2. How to establish a cross-modal registration mapping between 2D panoramic film and 3D oral scan, and quantify the registration quality; 3. How to uniformly represent image measurement error and registration error as tooth-by-tooth reliability indicators; 4. How to convert RBL and its reliability into calculable constraints in the design of removable partial dentures (abutment selection, upper limit of undercut utilization depth, limit of clasp type, etc.).

[0031] The embodiment can automatically evaluate RBL in the panoramic film, and reliably map the results to 3D tooth position entities on the premise of clearly defining the reliability, for driving the design of removable partial dentures.

[0032] As Figure 1 shown, the embodiment discloses a cross-modal registration design method for removable partial dentures, characterized in that it comprises: Step S101: acquiring two-dimensional oral panoramic film and three-dimensional intraoral scanning data of a patient; Step S102: Perform tooth-by-tooth detection and segmentation processing on the panoramic film, and extract the enamel-cementum junction reference point, apical point, and mesial-distal bone ridge top point of each tooth based on the segmentation results. Calculate the radiological bone loss ratio of each tooth based on the reference points, apical points, and bone ridge top points, and obtain the image reliability component of each tooth site in the panoramic film based on the segmentation results. Step S103: Perform tooth and gum segmentation processing on the intraoral scan data, construct a three-dimensional tooth site entity, and extract three-dimensional key points and neck margin contour points of each tooth. Step S104: Establish a parametric projection model of the dental arch based on the three-dimensional key points and neck margin contour points of each tooth, perform cross-modality registration on the panoramic film and intraoral scan data, solve the projection model parameters to obtain the registration residual error, and calculate the registration reliability component of each tooth site based on the registration residual error. Step S105: Fuse the image reliability component of each tooth site in the panoramic film and the registration reliability component to generate an image and registration reliability index. Step S106: Use the radiological bone loss ratio and reliability index of each tooth site as design constraints to perform automatic design of the removable partial denture.

[0033] In step S101, the panoramic film P is read, and grayscale normalization and distortion / noise preprocessing (such as median filtering, CLAHE enhancement) are performed.

[0034] Read the intraoral scan S, and perform denoising, hole repair, and resampling (target edge length, e.g., 0.2-0.5 mm) on the mesh.

[0035] If there is a medical record E, it is uniformly mapped to the FDI tooth site index and checked for consistency (e.g., if the medical record is missing but the intraoral scan detects a crown, it is marked as "conflict to be checked").

[0036] In step S102, panoramic film tooth-by-tooth feature extraction and tooth-by-tooth RBL information calculation are performed, including: Step S1021, tooth site detection and segmentation: Any of the following implementations can be used: Deep learning: use U-Net / Mask R-CNN to output pixel masks for each tooth with confidence .

[0037] Or use threshold segmentation + morphology + connected component segmentation, and combine tooth sequence and width constraints to obtain .

[0038] Step S1022, apical point, CEJ reference point, and bone ridge point extraction: For each tooth mask : Tooth major axis estimation: Perform PCA on the mask pixels and take the first principal direction as the tooth major axis direction. ; Root tip :along The direction is determined by selecting the farthest boundary point of the mask as the candidate root tip. If a double-root morphology exists, the geometric center of the two root tips or the deepest root tip is selected as the root tip. .

[0039] CEJ Reference Point Draw equidistant cross-sections along the long axis of the tooth, calculate the length of the intersection between each cross-section and the mask, and take the position where the intersection length changes the most rapidly from large to small as the position of the narrow neck of the crown-root transition. Take the center point of the mask on this section line as... .

[0040] mesial / distal bony ridges Define a Region of Interest (ROI) on both the mesial and distal sides of the tooth (the area adjacent to the interdental space, within 2–6 mm of the tooth boundary); perform edge detection within the ROI to obtain candidate bone ridge curves; Choose the option that satisfies: located at and Between, and along perpendicular to The point with the largest local gradient intensity is taken as the bone ridge; respectively... .

[0041] Distance calculation: Root length ; Near-to-medium height (Projected onto the major axis unit vector) ); Far-to-mid altitude ; Proportion of mesial bone loss: ; Distal bone loss percentage: ; Overall RBL: ,in ∈[0,1], the larger the value, the more severe the degree of bone loss.

[0042] Step S1023, Image Confidence Component : Segmentation confidence Confidence level The output can be obtained directly using ke; alternatively, it can be obtained by fitting edge sharpness. Edge sharpness The mean gradient magnitude within the ROI is normalized to [0,1]. Overlapping scores If the ratio of the overlap between the tooth mask and the adjacent tooth mask is high, the overlap score is high High; Definition: .

[0043] In step S103, intraoral scanning three-dimensional modeling and tooth entity construction, comprising: Step S1031, tooth / gum segmentation and single tooth grid extraction: the 3D segmentation network can output each vertex label (tooth / gum / noise) and each tooth instance. The tooth crown can also be segmented based on curvature + normal change + terrain watershed, and the single tooth instance grid is obtained by combining the adjacency graph clustering .

[0044] Step S1032, tooth FDI labeling: extract the centroid of each tooth crown , and sort the sequence according to the dental arch center line; map the sequence to FDI (use placeholder to skip for missing teeth) through the center line (incisor area) and quadrant division rule; output the tooth entity data structure.

[0045] Step S1033, 3D key point extraction (for registration): Extract for each tooth : the highest point of the tooth crown (the maximum value along the occlusal plane normal) as the tooth tip / gingival margin approximation point ; tooth crown boundary contour point set (intersection line with gum or neck margin).

[0046] In step S104, 2D-3D cross-modal registration, an implementable panoramic projection approximation model can be implemented. The panoramic imaging exists nonlinear scanning and distortion. The embodiment provides an engineering implementable arc parameter projection model, taking the arc length of the dental arch as the horizontal axis to establish 3D to 2D mapping, and fitting the parameters through robust optimization, specifically comprising: Step S1041, establish 3D dental arch parameter coordinates: Take all tooth crown centroids Fit a three-dimensional spline curve as the dental arch center line ; define the arc length parameter (the projection arc length on ) for each tooth, and the vertical coordinate (the relative occlusal plane height).

[0047] Step S1042, panoramic projection model: define the projection function : for 3D point , first do rigid transformation , then map to panoramic pixel coordinates : , , where is the point corresponding dental arch parameter coordinate; parameter set , The model provides nonlinear lateral scanning with slight tilting fitting ability, which can cover most engineering errors of panoramic images.

[0048] Step S1043, registration optimization objective function, including robust items and sequential constraints: In 2D panoramic images, take the centroid of each tooth mask as the 2D key point ; in 3D, take each tooth key point ; Key point item: ; where is the Huber robust loss, threshold pixels.

[0049] Contour item: do distance transformation on each tooth 2D mask to get , sample several points from the 3D cervical contour point set : ; Tooth position sequence constraint item: keep the monotonicity along the dental arch sequence: where is the minimum interval (such as 2 pixels).

[0050] Total objective: ; the weight can be set as: .

[0051] Step S1044, solution strategy and stopping condition: Initialization: , Align with dental arch plane (align occlusal plane with PCA), and then roughly align according to the dental arch midline; estimate the center alignment using the length of the dental arch and the height-width ratio of the image, Initial value is 0; Iteration: use Levenberg-Marquardt or gradient descent iterative minimization ; Termination: iteration number ≥ 50 or relative drop .

[0052] Step S1045, registration reliability component : calculate the tooth key point residual error​ Definition of overall residual mean Residual per tooth Executable mapping is given: where pixel, pixel.

[0053] When or , the system flags the registration for review and triggers a conservative design strategy.

[0054] Synthesis and propagation of CRI in step S105: In the automatic design process of removable partial denture, the panoramic image quality and the reliability of 2D-3D cross-modal registration are considered simultaneously, and the image reliability component and the registration reliability component are synthesized into the image and registration reliability index of each tooth , which is used to represent the overall reliability of the radiological bone loss (RBL) result of the tooth in engineering and clinical application.

[0055] Step S1051, synthesis method of reliability index: for each tooth , the comprehensive reliability index is defined as: ; Wherein: represents the quantitative result of image layer unreliability; represents the quantitative result of cross-modal registration layer unreliability; ∈[0,1], the larger the value, the lower the reliability of the tooth corresponding to the RBL result.

[0056] The above synthesis method adopts the risk union model, which is used to ensure that as long as there is significant unreliability in any link of image or registration, the overall reliability of the tooth is determined to be low.

[0057] Step S1052, engineering semantics of reliability index: In the present application, the image and registration reliability index has the following engineering semantics: 1) It is not a statistical measure of error or confidence interval; 2) It is not used to smooth, correct or regress the RBL value; 3) It is used to represent the risk degree faced when the RBL result is used for automatic denture design decision.

[0058] When is low, it indicates that the image quality of this tooth site is good and the registration is stable, and the RBL result of this tooth site can be used as a regular design constraint input; when is high, it indicates that the RBL result of this tooth site has high uncertainty and is not suitable for high-risk design decisions.

[0059] Step S1053, credibility propagation and directional risk expression: In an optional embodiment, the present application allows the credibility index to be further refined into directional credibility components to support more detailed design constraints: Mesial Credibility CRI: calculated from mesial RBL measurement instability and corresponding mapping residual; Distal Credibility CRI: calculated from distal RBL measurement instability and corresponding mapping residual.

[0060] The directional credibility can be used to limit the use of specific direction undercut or the arrangement of the retainer in subsequent design, thereby avoiding the application of excessive retention force in the high-risk direction.

[0061] Step S1054, credibility threshold and design triggering mechanism: In order to facilitate engineering implementation, the present application sets at least one set of exemplary threshold values for the credibility index to trigger different design strategies: When , for example is 0.3: it is considered that the RBL result of this tooth site is reliable, and it can participate in the abutment screening and retention design according to the regular strategy; when ≤ < ， For example is 0.6: it is considered that there is a moderate credibility risk in this tooth site, and the system automatically adopts a conservative design strategy, including reducing the depth of undercut utilization, limiting the type of retainer or increasing the share of the support and base; when ≥ : mark this tooth site as needing review, and its RBL result is not directly used for key design decisions, and prompt additional inspection or manual confirmation in the electronic design sheet.

[0062] The above threshold values can be adjusted according to clinical preferences or system configurations, and the present embodiment is an exemplary description and is not limited to 0.3 and 0.6.

[0063] Step S1055, the role of the credibility index in the design process: Image and registration credibility index The role in the system of the present application includes but is not limited to: As a risk penalty factor in abutment suitability score; As a constraint factor for the upper limit of undercut utilization depth; As a criterion for retention type selection and combination restriction; As a basis for risk prompt and review mark in electronic prescription.

[0064] By explicitly propagating the credibility information in the design process, the present invention avoids outputting overly confident automatic design results in the case of insufficient image quality or unstable registration.

[0065] In step S106, the RPD design is driven by the constraints based on radiological bone loss and credibility indicators, After completing the radiological bone loss (RBL) evaluation for each tooth position and the image and registration credibility indicator (CRI) calculation, RBL+CRI is input as the core constraint to drive the selection of the abutment of the removable partial denture (RPD), the control of the undercut utilization, and the configuration of the retention, so as to balance stability and clinical safety in the automatic design process.

[0066] Step S1061, abutment suitability score: For tooth position , define the normalized variables: radiological bone loss indicator ∈[0,1]; image and registration credibility indicator ∈[0,1]; mobility , normalized ; inclination angle (degree), normalized ; medical record risk flag , presence of caries, periapical, severe restoration, etc. , then 1.

[0067] Abutment score: , Output category: contraindicated abutment: RBL and or and .

[0068] Need review: (image or registration unreliable), the system can give suggestions for additional examination / artificial confirmation.

[0069] Recommended abutment: and no need for review.

[0070] Optional abutment: in other cases.

[0071] When the tooth position is marked as needing review, its corresponding RBL result is not directly used for high-risk design decisions, and a prompt is given in the electronic prescription.

[0072] Step S1062, utilize the upper limit of the undercut depth: For each candidate abutment tooth, define an upper limit for the undercut utilization depth. (Unit: mm) , Unit: mm. Forced verification is required when necessary. (Conservative strategy).

[0073] Step S1063, Ring Type Restriction Rule Table: Based on the combined states of RBL and CRI, explicit restrictions are imposed on the type and strength of the retainer, as shown in Table 1. Table 1. Restriction Rules Table The specific name of the retainer is provided by the component library. In this embodiment, the retention strength and type are limited by RBL+CRI, rather than by a specific structural name.

[0074] Step S1064, Kennedy Classification and Structural Constraints: The Kennedy class (I / II / III / IV) is automatically identified based on the position of the missing tooth. For the free end (Class I / II), the following rule is added: if the RBL or CRI of the main abutment tooth on the free end side is high, the coverage area of ​​the denture base is expanded first, and the stress relief retention strategy is used first.

[0075] Step S1065, Basement Coverage and Connector Selection, depends on intraoral scan soft tissue parameters: Extracted from intraoral scan: alveolar crest line Boundary of the vestibular ditch , tethered activity area Denture base boundary formation: offset towards the buccal and lingual sides from the alveolar ridge crest line until approaching the vestibular sulcus boundary. Maintain a safety margin (e.g., 2mm) ahead; avoid the tethered area. ;Free end region according to Weighted Expanded Coverage: Coverage Factor: , in This represents the average radiographic bone loss index of the abutment teeth adjacent to the defect.

[0076] Connector selection rules: If the thickness of the palatal mucosa and the area of ​​mobility allow, the form of connector that covers more stable areas should be preferred; if there is a highly mobile area, the avoidance form should be used instead.

[0077] The method disclosed in the embodiment further comprises the following step S107: performing compliance verification and automatic repair on the automatic design result based on manufacturing rules and clinical safety to obtain an electronic design sheet and processable design data of the removable partial denture.

[0078] The compliance verification and automatic repair in step S107 are used to prevent output of unmanufacturable and unsafe solutions, Performing verification on the solution: interference verification: minimum gap between components and tooth body / soft tissue >= 0.2mm; minimum thickness: connector / retaining ring arm thickness >= manufacturing threshold (such as >= 1.0mm or according to process configuration); retention strength verification: the depth of undercut should not exceed ; credibility index conservative verification: if the key abutment , output the solution that needs to be reviewed and automatically degrade the retention strength.

[0079] The automatic repair strategy adopts the principle of minimum change: preferentially reducing the depth of undercut; then replacing the type of retainer with a more conservative type; then expanding the coverage of the base or adding a support share; if it still does not meet the requirements, output the failure reason and the prompt that needs manual processing.

[0080] Output electronic design sheet and processing data: The output content includes: design sheet (PDF / HTML / editable form): 2D dental arch diagram, component labeling, textual description, risk prompt (including contraindications / review reasons), key parameter table; design data package (JSON or equivalent structure): component topology (connection relationship), component parameters for each tooth site, boundary curve control point, depth and direction of undercut utilization, etc.; optional export of software interface format for subsequent CAD / manufacturing.

[0081] The data structure of the embodiment is as follows: ToothRecord (each tooth site record): tooth_id (FDI); presence (0 / 1); mobility_grade (0-3); tilt_angle_deg (0-90) / tilt_direction; disease_flag (0 / 1); RBL_mesial, RBL_distal, RBL (0-1); CRI_img (0-1), CRI_reg (0-1), CRI (0-1); score (0-100); status (recommended / optional / contraindicated / review required); d_max_mm (0.10 - 0.50).

[0082] ComponentRecord (component): component_type (clasp / rest / connector / base / teeth); anchor_tooth_id (FDI); orientation (mesial / distal / buccal / lingual); curve_ctrl_pts (spline control point array); undercut_depth_mm; connectivity (connection relationship).

[0083] In one specific scenario, such as missing distal end (Kennedy I): Panoramic film measurement: tooth position 36: RBL , CRI → Recommended abutment; tooth position 35: RBL , CRI → Contraindicated abutment.

[0084] Design engine: The abutment set is preferentially selected for tooth position 35 and the opposite side support good tooth; The undercut upper limit of tooth position 35 ; The retention type is selected as conservative / stress release type in the 0.45-0.65 interval; The distal end of the base cover factor >1 to expand the coverage and reduce the abutment load.

[0085] Output: The design sheet clearly indicates that "tooth position 36 is contraindicated: Output: The design sheet clearly indicates that "tooth position 36 is contraindicated: bone support is insufficient and confidence is high".

[0086] In another scenario, image overlap leads to high reliability index: The segmentation confidence of a tooth position is low, and the registration residual is high: .

[0087] System output: The tooth position "needs to be reviewed", and the undercut upper limit is forced to be ≤0.25mm, and the design sheet is prompted to supplement the inspection or manual confirmation.

[0088] The technical effects of the embodiment are as follows: 1. Quantify the panoramic film bone support information for each tooth and map it to 3D tooth position, reducing the dependence on subjective records; 2. Reduce the risk of misjudgment caused by image distortion / overlap through uncertainty propagation and conservative strategy; 3. Upper limit of retention strength and type restriction based on bone support constraint, make the automatic design output more controllable; 4. Output design sheet with basis, improve interpretability and clinical usability; 5. Reduce the risk of abutment overload and reduce the probability of rework (can be verified by the index of "adjustment times / rework rate" in the clinical or technician process).

[0089] The above description has been presented for the purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present disclosure to forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

Claims

1. A method for designing removable partial dentures with cross-modal registration, characterized in that, include: Acquire two-dimensional panoramic radiographs and three-dimensional intraoral scans of the patient; The panoramic film is subjected to tooth-by-tooth detection and segmentation. Based on the segmentation results, the reference point of the cementoenamel junction, the apex point, and the mesial and distal ridge apex of each tooth are extracted. The radiographic bone loss ratio of each tooth is calculated based on the reference point, the apex point, and the ridge apex. Based on the segmentation results, the image confidence component of each tooth position in the panoramic film is obtained. The intraoral scan data is segmented into tooth structure and gingiva to construct a three-dimensional tooth position entity, and the three-dimensional key points and cervical margin contour point set of each tooth are extracted. A parametric projection model of the dental arch is established based on the three-dimensional key points and cervical margin contour point set of each tooth. Cross-modal registration is performed on the panoramic radiograph and intraoral scan data. The registration residual is obtained by solving the projection model parameters through optimization algorithm, and the registration confidence component of each tooth position is calculated based on the registration residual. The image confidence component of each tooth position in the panoramic film is fused with the registration confidence component to generate an image and registration confidence index. The proportion of radiographic bone loss and the reliability index of each tooth position are used as design constraints to automate the design of removable partial dentures.

2. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, The calculation of the radiographic bone loss percentage for each tooth includes: Based on formula Calculate the root length of the tooth; Based on formula Calculate the near-center height; Based on formula Calculate the distance to mid-distance; The proportions of mesial and distal bone loss are calculated based on the root length, mesial height, and distal height of the tooth position. The larger of the mesial and distal bone loss proportions is selected as the radiographic bone loss proportion of the tooth; in, For root length, For the root tip, As a reference point for the cementoenamel junction, Near to medium altitude, At a distance of medium altitude, To project onto the unit vector of the major axis, It is the proximal bony ridge. It is the distal ridge of the bone.

3. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, The factors used to calculate the image confidence component in the panoramic film for each tooth position based on the segmentation results include: Confidence of tooth segmentation, clarity of tooth margin gradient, and overlap score of adjacent tooth masking; The formula for calculating the image credibility component is as follows: ,in, For image credibility components, The confidence level for tooth position segmentation. For the clarity of the gradient at the tooth margin, The overlap score is given for masks of adjacent teeth.

4. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, The establishment of a parametric projection model of the dental arch based on the three-dimensional key points and cervical margin contour point set of each tooth includes: 3D points Using formula Perform a rigid body transformation, and then convert the transformation result... Mapped to panoramic pixel coordinates ; The mapping function is: ， ， in and For point The corresponding dental arch parameter coordinates, For arc length parameters, For height parameters, Let be a rotation matrix. It is a translation vector. This is the offset. The coefficient of the linear term, The coefficient of the quadratic term, As the vertical baseline, This is the vertical scaling factor. For coupling term coefficients, parameter set .

5. The method for designing removable partial dentures with cross-modal registration according to claim 4, characterized in that, The objective function for obtaining the registration residual by solving the projection model parameters through an optimization algorithm includes: ， in, , and All are weighting coefficients. For key point error, For contour error, As a constraint used to maintain the monotonicity of tooth position sequence; ， ， ， in, The total error of the keypoint matching items. This represents the total error of the contour matching item. This is the total error of the constraint term used to maintain the monotonicity of tooth position order. For Huber's robustness loss, For collection points, For the minimum interval, For the first The coordinates of the two-dimensional key points corresponding to each tooth on a two-dimensional panoramic image. For the parameterized projection function of the dental arch, For the first The coordinates of the three-dimensional key points corresponding to each tooth on the three-dimensional intraoral scan model. For the first The signed distance field function of a tooth on a two-dimensional panoramic film. For the first The coordinates of the three-dimensional key points corresponding to each tooth on the three-dimensional intraoral scan model. These are the horizontal coordinates of the two-dimensional points after projection.

6. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, The formula for calculating the credibility index is as follows: ， in, As a credibility indicator, This is a quantification of the unreliability at the image level. This is the quantification result of the unreliability at the cross-modal registration level. The larger the value, the lower the reliability of the RBL result corresponding to that tooth position.

7. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, The role of the image and registration reliability index includes: Risk penalty factor used in abutment tooth suitability scoring; Constraint factors used for calculating the upper limit of the depth for undercutting; Criteria used for the selection and combination restrictions of fixation body types; Used as the basis for risk warnings and review markings in electronic design sheets.

8. The method for designing removable partial dentures with cross-modal registration according to claim 7, characterized in that, The formula for calculating the suitability score of the abutment teeth is as follows: ， in, For radiographic indicators of bone loss, As a credibility indicator, The normalized result for looseness, This is the normalized result for the tilt angle. This serves as a risk marker for medical records.

9. The method for designing removable partial dentures with cross-modal registration according to claim 8, characterized in that, The constraint factor calculated using the upper limit of depth for the indentation is: 。 10. The method for designing removable partial dentures with cross-modal registration according to claim 1, characterized in that, Following the step of automating the design of removable partial dentures using the proportion of radiographic bone loss and reliability indices for each tooth position as design constraints, the procedure further includes: The steps involve verifying and automatically repairing the automated design results based on manufacturing rules and clinical safety to obtain an electronic design sheet and manufacturable design data for removable partial dentures.

Images