Denture edge line determination method and apparatus, medium, and device

Abstract

The present application provides a denture edge line determination method and apparatus, a medium, and a device. The method comprises: acquiring several image frames obtained by oral cavity scanning performed under the condition that the oral cavity is pulled; performing data fusion on oral cavity data in the image frames to generate a non-rigid body region of an overall model; determining corresponding scanning points of each three-dimensional point in the non-rigid body region of the overall model across all of the image frames; determining, on the basis of each three-dimensional point in the non-rigid body region of the overall model and the corresponding scanning points thereof, the position change amplitude of the three-dimensional point; and taking the three-dimensional point whose position change amplitude falls within a preset range as an edge point, and determining a denture edge line according to the edge point. By means of acquiring the oral cavity data obtained in the oral cavity traction scanning process, the present application automatically calculates the position change of each scanning point and thereby automatically determines the denture edge line. Compared to traditional manual impression taking methods, the present application greatly improves the efficiency and precision of obtaining the denture edge line, and effectively avoids the influence of human subjective factors.

Description

A method, apparatus, medium and equipment for determining the edge line of a denture.

[0001] This application claims priority to Chinese Patent Application No. 202410668470.9, filed on May 27, 2024, entitled "A method, apparatus, medium and device for determining the edge line of a denture", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This specification relates to the field of denture fabrication technology, and in particular to a method, apparatus, medium and equipment for determining the edge line of a denture. Background Technology

[0003] Currently, in clinical dentistry, when fabricating complete dentures or removable partial dentures, the dentist typically uses manual impression taking to shape the margins and obtain the denture's edge lines. However, this manual impression taking method has some drawbacks. For example, it may cause discomfort to the patient, and the impression taking efficiency is relatively low. It also requires a high level of skill from the dentist, who needs to manually draw lines based on the impression, leading to significant uncertainty in the edge lines obtained by different dentists and being greatly influenced by subjective human factors. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this specification provides a method, apparatus, medium and equipment for determining the edge line of a denture.

[0005] According to a first aspect of the embodiments of this specification, a method for determining the edge line of a denture is provided. The method includes: acquiring a plurality of image frames obtained by scanning the oral cavity while the oral cavity is being pulled; fusing the oral cavity data in the image frames to generate a non-rigid region of an overall model; determining the scanning point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame; determining the positional variation range of each three-dimensional point based on each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning point; and taking the three-dimensional points whose positional variation range meets a preset range as edge points, and determining the denture edge line based on the edge points.

[0006] According to a second aspect of the embodiments of this specification, a denture edge line determination device is provided, comprising: a scan image frame acquisition module configured to acquire a plurality of image frames obtained by scanning the oral cavity while the oral cavity is being pulled; a data fusion module configured to fuse oral cavity data in the image frames to generate a non-rigid region of an overall model; a corresponding scan point determination module configured to determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame; a position change amplitude determination module configured to determine the position change amplitude of each three-dimensional point in the non-rigid region of the overall model based on each corresponding scan point; and an edge line determination module configured to take three-dimensional points whose position change amplitude meets a preset range as edge points and determine the denture edge line based on the edge points.

[0007] According to a third aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described method for determining the edge line of a denture.

[0008] According to a fourth aspect of the embodiments of this specification, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for determining the edge line of a denture.

[0009] The technical solutions provided in the embodiments of this specification may include the following beneficial effects:

[0010] In the embodiments of this specification, oral data obtained during oral traction scanning is acquired to generate the non-rigid region of the overall model. The positional changes of each three-dimensional point in the non-rigid region of the overall model are automatically calculated, and the edge line of the denture is automatically determined accordingly. Compared with the traditional manual impression method, this method greatly improves the efficiency and accuracy of obtaining the edge line of the denture and effectively avoids the influence of human subjective factors.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0013] Figure 1 is a flowchart illustrating a method for determining the edge line of a denture according to an exemplary embodiment of this specification.

[0014] Figure 2 is a schematic diagram illustrating the positional change of a three-dimensional point in a non-rigid region under tension, according to an exemplary embodiment of this specification.

[0015] Figure 3 is a flowchart illustrating the steps of determining the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame in a method for determining the edge line of a denture according to an exemplary embodiment of this specification.

[0016] Figure 4 is a flowchart illustrating the steps of determining the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame in another method for determining the edge line of a denture according to an exemplary embodiment of this specification.

[0017] Figure 5 is a flowchart illustrating the steps of determining the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame in another method for determining the edge line of a denture according to an exemplary embodiment of this specification.

[0018] Figure 6 is a schematic diagram illustrating the positional variation of three-dimensional points at different locations in a non-rigid region during the stretching process, according to an exemplary embodiment of this specification.

[0019] Figure 7 is a schematic diagram illustrating a myostatic line in a non-rigid region according to an exemplary embodiment of this specification.

[0020] Figure 8 is a hardware structure diagram of a computer device containing a denture edge line determination device according to an exemplary embodiment of this specification.

[0021] Figure 9 is a block diagram of a denture edge line determining device according to an exemplary embodiment of this specification. Detailed Implementation

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0023] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0025] Currently, in clinical dentistry, when fabricating complete dentures or removable partial dentures, the dentist typically uses manual impression taking to shape the margins and obtain the denture's edge lines. However, this manual impression taking method has some drawbacks. For example, it may cause discomfort to the patient, and the impression taking efficiency is relatively low. It also requires a high level of skill from the dentist, who needs to manually draw lines based on the impression, leading to significant uncertainty in the edge lines obtained by different dentists and being greatly influenced by subjective human factors.

[0026] In view of the above problems, this application provides a new method for determining the edge line of a denture. By acquiring oral data obtained during oral traction scanning, a non-rigid region of the overall model is generated. The positional changes of each three-dimensional point in the non-rigid region of the overall model are automatically calculated, and the edge line of the denture (edge ​​line of the denture base) is automatically determined accordingly. Compared with the traditional manual impression taking method, this method greatly improves the efficiency and accuracy of obtaining the denture edge line and effectively avoids the influence of subjective human factors.

[0027] The embodiments of this specification will now be described in detail with reference to the accompanying drawings.

[0028] Figure 1 is a flowchart illustrating a method for determining the edge line of a denture according to an exemplary embodiment of this specification. The method for determining the edge line of a denture can be performed in real time during the scanning process or after the scanning is completed. As shown in Figure 1, the method for determining the edge line of a denture includes: S101-S105.

[0029] S101. Acquire several image frames obtained by scanning the oral cavity while the oral cavity is being pulled.

[0030] Specifically, in this embodiment, the traction method can be to use a mouth diffuser to pull the oral cavity, such as using two different sized mouth diffusers, or using a mouth diffuser once and not using a mouth diffuser once, or it can be done directly by hand, etc. This embodiment does not limit this. Each image frame contains image data of a local area of ​​the oral cavity scanned at various moments during the traction process, which can be used to characterize the morphology of the scan points at each scan moment, such as position coordinates, etc. The number of image frames depends on the scanning frequency.

[0031] S102. Perform data fusion on the oral cavity data in the image frame to generate the non-rigid region of the overall model.

[0032] To ensure the stability and fit of dentures fabricated based on their edge lines, the edge lines are typically positioned based on the myostatic line, which represents the dynamic-static interface between the teeth, gums, and muscle mucosa in the oral cavity. This line extends further into the oral muscle mucosa tissue, allowing the denture to flexibly adapt to the movement of the oral muscle mucosa and utilizing the natural support of the muscle mucosa to enhance its stability. In other words, the denture edge lines should be located in non-rigid regions of the teeth, such as the vestibule, frenulum, or edge region. Points in these regions can move with the movement of the oral muscle mucosa. Figure 2 illustrates the positional changes of three-dimensional points in non-rigid regions during traction. Therefore, to determine the denture edge lines, a non-rigid region of a complete tooth model can be generated based on scanned oral data. Then, by analyzing the changes in three-dimensional points in the non-rigid region during traction, the denture edge lines can be determined.

[0033] Since each image frame obtained in the aforementioned steps only contains oral cavity data of a local area scanned at each moment, it cannot reflect the changes of three-dimensional points in the region throughout the entire traction process. Therefore, it is necessary to perform data fusion on the oral cavity data of all image frames to generate the non-rigid region of the overall tooth model. The data fusion method for the image frames is not limited. The non-rigid region of the generated overall model can include a point cloud model or a mesh model, and the three-dimensional points can be points in the point cloud model, vertices in the mesh model, or a region.

[0034] It should be noted that: data fusion is performed on the oral cavity data in the image frame, wherein the image frame for data fusion can be all or part of the image frame obtained in step S101.

[0035] S103. Determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame.

[0036] To analyze the positional changes of points in the non-rigid regions of the generated overall model during the stretching process, we can first match each three-dimensional point in the non-rigid regions of the overall model with the scans of each image frame. By determining the positional differences between the three-dimensional points and their corresponding points, we can obtain the positional changes of the three-dimensional points during the stretching process.

[0037] Specifically, there are several ways to determine the corresponding scan point of each 3D point in the non-rigid region of the overall model in each image frame.

[0038] In some embodiments, as shown in FIG3, determining the scanning point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame may include: S301-S303.

[0039] S301. Determine the normal of each three-dimensional point in the non-rigid region of the overall model;

[0040] S302. Project all scan points in each image frame into the three-dimensional space where the non-rigid body region of the overall model is located;

[0041] S303. Several scan points falling on the same three-dimensional point normal line are determined as the scan points corresponding to the three-dimensional point in each image frame in the non-rigid region of the overall model.

[0042] When performing traction scans on the oral cavity, the traction is mostly performed in the same direction. This causes the three-dimensional points in the non-rigid region to move along the same trajectory even if their positions change. Therefore, in this embodiment, to simplify the calculation and improve the efficiency, it can be assumed that the three-dimensional points in the non-rigid region move along their respective normal directions during traction. Thus, after determining the normal of each three-dimensional point in the non-rigid region of the overall model and projecting the scan points in each image frame into the three-dimensional space where the non-rigid region of the overall model is located, several scan points that fall on the same normal line of the three-dimensional point are simply determined as the scan points corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame. The normal line can be understood as a straight line extending along the normal direction. When determining the correspondence between 3D points and scan points, the following specific implementation methods can be adopted: The scan points in each image frame can be matched by intersecting the 3D voxel regions traversed by the normal lines of the 3D points, and the matched points are considered as the corresponding scan points of each 3D point in the non-rigid region of the overall model in each image frame; alternatively, when a scan point in an image frame falls within the 3D voxel region traversed by the normal line of a certain 3D point, that scan point is determined to be the corresponding scan point of that 3D point; or, using existing search algorithms, the search starts from the normal of the 3D point, and when a scan point located on the normal line of the 3D point is found, that scan point is determined to correspond to that 3D point. As for the specific method of determining the normal of the 3D point, various existing algorithms or technologies can be used, such as surface normal estimation algorithms or surface fitting methods, etc., and this embodiment does not limit this.

[0043] In other embodiments, as shown in FIG4, determining the scanning point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame may further include: S401-S402.

[0044] S401. Determine the non-rigid body regions of the overall model and the non-rigid body transformation relationships of each image frame;

[0045] S402. Using non-rigid body transformation relationships, determine the scanning point corresponding to each three-dimensional point in the non-rigid body region of the overall model in each image frame.

[0046] In this embodiment, by performing non-rigid registration on the non-rigid regions of the overall model and each image frame, the non-rigid transformation relationship between the non-rigid regions and each image frame is determined, thereby accurately and comprehensively determining the corresponding scanning point of each three-dimensional point in each image frame, which is beneficial to improving the accuracy of subsequent determination of the denture edge line.

[0047] In some other embodiments, as shown in FIG5, determining the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame may include: S501-S503.

[0048] S501. Determine the camera pose when acquiring each image frame based on the camera intrinsic and extrinsic parameters of each image frame.

[0049] S502: Reproject the 3D points onto each image frame according to the camera pose;

[0050] S503. Determine the scanning points in each image frame that coincide with the projected 3D point as the corresponding scanning points of the 3D point in each image frame in the non-rigid region of the overall model.

[0051] In this embodiment, the intrinsic and extrinsic parameters of each image frame are used to reproject the three-dimensional points onto the relevant image frames, thereby determining the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame.

[0052] S104. Based on each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning points, determine the positional change range of the three-dimensional point.

[0053] The positional change of a three-dimensional point can be specifically measured by the magnitude of the change. By calculating and comparing the magnitude of the positional change of three-dimensional points at different locations, three-dimensional points that may be edge points on the denture edge line can be identified, thereby determining the denture edge line. Figure 6 illustrates the magnitude of the positional change of three-dimensional points at different locations in a non-rigid region during the traction process, using different shades of gray to represent different magnitudes of positional change. In some embodiments, different colors can also be used to represent different magnitudes of positional change.

[0054] Specifically, the position change range of a three-dimensional point can be determined in various ways. For example, in some embodiments, the maximum distance can be determined as the position change range of the three-dimensional point by calculating the distance between each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning point.

[0055] Alternatively, in other embodiments, the maximum curvature change can be determined as the positional change of a three-dimensional point by calculating the curvature change between each three-dimensional point and its corresponding scan point in the non-rigid region of the overall model.

[0056] Displacement can characterize the actual distance the scanning point moves in space, and can simply and directly reflect the change in the position of the scanning point during the entire traction process. Therefore, it is preferable to use the maximum displacement of each three-dimensional point during the traction process as a way to measure the position change amplitude, so as to simplify the calculation process of the position change amplitude and improve the accuracy and efficiency of determining the denture edge line.

[0057] In the specific implementation process, an oral cavity scan is performed during traction, resulting in multiple image frames in chronological order of the scan time. These frames record oral cavity data from different regions scanned by the scanner at different times. To determine the maximum displacement of each three-dimensional point during the traction process, the following two specific implementation methods can be used:

[0058] The first approach is to fuse the data of all image frames obtained during the traction scanning process after the entire traction scanning process is completed, generate the non-rigid region of the overall model corresponding to the entire traction scanning process, and then map each three-dimensional point in the non-rigid region of the overall model to the scanning point in each image frame. By calculating the distance between each three-dimensional point in the non-rigid region of the overall model and the corresponding scanning point in each image frame, the maximum distance is determined, and the maximum distance is determined as the maximum displacement of the scanning point during the traction process.

[0059] The second approach is to fuse the data of the current image frame with the data of the previous image frame at each scanning moment to generate the current non-rigid region corresponding to the current moment. Then, map each three-dimensional point in the current non-rigid region to a scanning point in the previous image frame. By calculating the distance between each three-dimensional point in the current non-rigid region and the corresponding scanning point in the previous image frame, the maximum distance at the current moment is determined. At the next scanning moment, the previous steps are repeated, and the maximum distance determined at the next moment is used to update the maximum distance determined at the previous moment. This process continues until the scanning is completed, and the maximum distance determined at the final moment is determined as the maximum displacement of the scanning point during the traction process.

[0060] The maximum displacement of the determined scanning point, that is, the magnitude of the positional change of the scanning point during the traction process, can accurately quantify the morphological changes of the oral cavity during traction, providing a reliable data basis for the subsequent determination of the denture edge line. The method for calculating the distance or curvature change between the three-dimensional point and the corresponding scanning point can be any existing method for calculating the distance or curvature change of all points; this embodiment does not limit this method.

[0061] S105. Take the three-dimensional points whose positional change range meets the preset range as edge points, and determine the denture edge line based on the edge points.

[0062] Because the positions of points on the denture margin typically change significantly during traction, directly using the magnitude of these changes as the selection range for 3D points in non-rigid regions could result in a large number of selected points, making subsequent determination of the denture margin line more difficult. The myostatic line, however, is the boundary between the moving and stationary parts of the tooth and the muscle / mucosa. Ideally, points on the myostatic line have zero positional change. Therefore, a smaller selection range can be used to quickly identify 3D points on the myostatic line. Once the myostatic line is determined, its distance from the denture margin line can be used to determine the actual margin line, simplifying the determination process and improving efficiency.

[0063] Therefore, in some embodiments, scanning points whose positional change range meets a preset range are used as edge points, and the denture edge line is determined based on the edge points, including:

[0064] The scanning points whose positional changes satisfy a first preset range are taken as the first edge points. The myostatic line is determined based on the first edge points, and the denture edge line is determined based on the myostatic line; or,

[0065] The scanning point whose positional change range meets the second preset range is taken as the second edge point, and the denture edge line is determined based on the second edge point;

[0066] The first preset range is smaller than the second preset range.

[0067] The first preset range for determining the myostatic line and the second preset range for determining the denture edge line can both be obtained through doctor's experience or through learning and training by a machine learning model. The first preset range can preferably be set to 0mm or 0-0.2mm (greater than or equal to 0, less than or equal to 0.2mm), and the second preset range can preferably be set to 0.4-0.6mm (greater than or equal to 0.4mm, less than or equal to 0.6mm).

[0068] One way to determine the denture edge line based on the myostatic line is to define the denture edge line as an equidistant line about 2mm-5mm (greater than or equal to 2mm, less than or equal to 5mm) from the myostatic line towards the gum line.

[0069] Specifically, determining the myostatic line based on the first edge point includes:

[0070] The first edge point is fitted and smoothed according to the direction of the dental arch to obtain the first curve, which is then determined as the myostatic line.

[0071] Determining the denture edge line based on the second edge point includes:

[0072] The second edge point is fitted and smoothed according to the direction of the dental arch to obtain the second curve, which is then determined as the edge line of the denture.

[0073] The smoothing process for fitting the myostatic line or the denture edge line is as follows:

[0074] Using the threshold ranges set for either the myostatic line or the denture edge line, a continuous contour line of positional variation is determined in the non-rigid region of the overall model; this is the corresponding myostatic line or denture edge line. Specifically: taking the positional variation amplitude of each vertex on the generated non-rigid region mesh of the overall model as input, starting from a given threshold point in the buccal posterior region of the dentition, the curve is collected along the direction of the dental arch, passing through points where the positional variation amplitude is close to the threshold (here, passing through the given threshold point is not strictly required; the smoothness of the curve and the difference between the positional variation amplitude and the threshold are considered), and the straight path reaches the buccal posterior region on the other side of the dentition, thus forming an ordered, smooth, non-closed myostatic line or denture edge line.

[0075] Furthermore, in some embodiments, after determining the myostatic line and / or the denture edge line, it can also be determined whether the myostatic line and / or the denture edge line are correct based on deep learning and / or empirical values;

[0076] If the myostatic line and / or denture edge line are incorrect, a prompt message will be issued to prompt the user to adjust the myostatic line and / or denture edge line, or the myostatic line and / or denture edge line will be automatically adjusted and the adjusted myostatic line and / or denture edge line will be displayed.

[0077] Among them, incorrect myostatic lines may be caused by situations such as the determined myostatic line being too close or too far from the alveolar ridge region in the overall tooth model, or the line being too wavy, such as having too large a bend, or the score given to the determined myostatic line by the trained deep learning model being too low.

[0078] In some embodiments, the myostatic line and / or denture edge line can be adjusted interactively, including: after determining the myostatic line and / or denture edge line, displaying the initial myostatic line and / or denture edge line on the interactive interface;

[0079] Based on the user's interaction, determine the user's modification request;

[0080] Based on the user's modification requests and the magnitude of changes in the position of the three-dimensional points, the initial myostatic line and / or denture edge line are locally recalculated and fitted and smoothed to generate and display the adjusted myostatic line and / or denture edge line.

[0081] Specifically, two interactive methods can be used to adjust the local line shape of myostatic lines and / or denture edge lines: drawing method and control point method. The drawing method involves the user drawing a line on the non-rigid body mesh surface of the overall model using the mouse; a preset algorithm will use this line to locally replace adjacent myostatic lines and / or denture edge lines. The control point method samples several control points from the myostatic lines and / or denture edge lines, and drags these control points using spline interpolation to obtain new curves, thereby changing the relationship between adjacent control points and the myostatic lines and / or denture edge lines.

[0082] To more intuitively observe the position of the myostatic line and the denture edge line in the non-rigid body region, the myostatic line and / or the denture edge line can be displayed on the non-rigid body region of the overall model. A schematic diagram of the display of the myostatic line in the non-rigid body region is shown in Figure 7.

[0083] Furthermore, since the ultimate goal of determining the denture edge line is to create a denture that matches the user's actual dental condition, in order to ensure the accuracy of the denture edge line and to visually observe the fit between the denture edge line and the user's actual dental condition, fine adjustments can be made subsequently to improve the efficiency and quality of subsequent denture fabrication. This helps to improve patient comfort and satisfaction, and provides more personalized and precise treatment plans. In some embodiments, rigid body data obtained from rigid body region scanning can be acquired before the steps of acquiring several image frames obtained from oral scanning under traction conditions. Based on the rigid body data, the rigid body region of the overall model can be generated and displayed. Furthermore, during the scanning process, the non-rigid body region and the rigid body region of the overall model can be stitched and fused in real time to generate the overall model and displayed on the interactive interface.

[0084] The rigid body region refers to the teeth and gums in the oral cavity. The scanning process to obtain rigid body data can be completed before oral traction is performed, that is, the rigid body region is scanned first, and then the non-rigid body region is scanned after oral traction, and the scans are performed separately. Alternatively, the rigid body region and the non-rigid body region can be scanned at the same time while the oral cavity is being pulled, such as with a mouth diffuser.

[0085] When the rigid and non-rigid regions are scanned separately in two separate scans or sequentially, the rigid region of the overall model is generated based on rigid data obtained from scans performed when the oral cavity is not under traction. However, the process of determining the denture edge line in this application is based on scan data obtained when the user's oral cavity is under traction. During traction, to ensure accurate and complete determination of the entire denture edge line, the traction scan range often exceeds the scan range when the denture is not under traction. Therefore, to ensure that the alveolar ridge region, which is directly related to denture installation, within the rigid region is not affected by deformation of the non-rigid region during traction, the alveolar ridge region can be identified and locked within the rigid region of the overall model first to provide a stable reference frame. Then, based on this stability, the denture edge line can be determined through traction scanning.

[0086] Specifically, the alveolar ridge region can be identified manually or through AI-powered intelligent recognition. Locking the alveolar ridge region involves keeping this region unchanged within the computer model, preventing new data obtained during traction scanning from altering its data, thus allowing this region to serve as the basis for subsequent denture design. The locking process can be executed automatically by computer AI or through a prompt box for manual selection. The specific implementation of locking can be displayed on the computer interface using different colors or boundary indicators, or it can be implicitly implemented without displaying the lock.

[0087] More specifically, in some embodiments, the steps of generating the non-rigid region of the overall model or generating the overall model, or after the steps of generating the non-rigid region of the overall model or generating the overall model, include:

[0088] In all image frames, the regions with the highest probability of occurrence and those that are continuous are selected for fusion to make the non-rigid regions of the overall model complete and smooth.

[0089] The data source for the non-rigid regions of the overall model is when the oral cavity is being pulled. At this time, the scanned object is dynamic. If all image frame data are fused together, a coarse multi-layer model data corresponding to multiple motion states of the oral cavity will be formed. The processing speed is fast, but it may not be conducive to the user viewing the scan situation, and it may not be conducive to determining the myostatic line and / or the denture edge line.

[0090] Therefore, optionally, this embodiment filters the image frames during the scanning process, after the scanning is completed, or after the scanning is paused, selecting the regions with the highest probability of occurrence and continuous fusion, thereby fusing them to form a complete, smooth, static single-layer model data. This makes the non-rigid areas of the overall model complete and smooth. Based on this, it is not only beneficial for users to view the scanning situation, but also beneficial for determining the myostatic line and / or the denture edge line, and improving the accuracy of the final determination result.

[0091] If image frames are filtered during the generation of the overall model in non-rigid regions or during the generation of the overall model, and the regions with the highest probability of occurrence and continuous appearance are selected for fusion, then the interactive interface can continuously display complete, smooth, and static single-layer model data in real time.

[0092] If image frames are filtered during the generation of the non-rigid regions of the overall model or after the overall model generation step, selecting the regions with the highest probability of occurrence and continuous flow for fusion—meaning all image frame data is used for full fusion during the scanning process, and automatically filtered after the scan is completed or paused to select the regions with the highest probability of occurrence and continuous flow for fusion—then the non-rigid regions of the overall model can be completely smooth. The interactive interface can then initially display coarse, multi-layered model data corresponding to multiple motion states of the oral cavity in real time, and then, after post-processing optimization, display complete, smooth, static single-layered model data.

[0093] Corresponding to the embodiments of the aforementioned methods, this specification also provides embodiments of a denture edge line determining device and the terminal to which it is applied.

[0094] The embodiments of the denture edge line determination device described in this specification can be applied to computer devices, such as servers or terminal devices. The device embodiments can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of the electronic device in which it resides reading the corresponding computer program instructions from non-volatile memory into memory and executing them. From a hardware perspective, as shown in Figure 8, it is a hardware structure diagram of a computer device where the denture edge line determination device of this specification is located. In addition to the processor 801, memory 802, network interface 803, and non-volatile memory 804 shown in Figure 8, the server or electronic device where the denture edge line determination device is located in the embodiment may also include other hardware depending on the actual function of the computer device, which will not be elaborated further.

[0095] As shown in Figure 9, Figure 9 is a block diagram of a denture edge line determining device according to an exemplary embodiment of this specification. The device includes:

[0096] The scan image frame acquisition module 901 is configured to acquire several image frames obtained by performing an oral scan while the oral cavity is being pulled.

[0097] The data fusion module 902 is configured to fuse oral cavity data in image frames to generate the non-rigid region of the overall model.

[0098] The corresponding scan point determination module 903 is configured to determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame;

[0099] The position change amplitude determination module 904 is configured to determine the position change amplitude of the three-dimensional point based on each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning points.

[0100] The edge line determination module 905 is configured to take three-dimensional points whose position change range meets the preset range as edge points, and determine the denture edge line based on the edge points.

[0101] Accordingly, this specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for determining the edge line of a denture.

[0102] Accordingly, this specification also provides a computer device, including: a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-described method for determining the edge line of a denture.

[0103] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0104] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative, and the modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0105] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0106] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this specification are indicated by the following claims.

[0107] It should be understood that this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this specification is limited only by the appended claims.

[0108] The above are merely preferred embodiments of this specification and are not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification shall be included within the scope of protection of this specification. Industrial applicability

[0109] In the method for determining the edge line of dentures provided in this disclosure, oral data obtained during oral traction scanning is acquired to generate the non-rigid region of the overall model. The positional changes of each three-dimensional point in the non-rigid region of the overall model are automatically calculated, and the edge line of the denture is automatically determined accordingly. Compared with the traditional manual impression method, this method greatly improves the efficiency and accuracy of obtaining the edge line of the denture, effectively avoids the influence of human subjective factors, and has strong industrial applicability.

Claims

1. A method of determining a denture margin line, wherein, include: Acquire several image frames obtained by scanning the oral cavity while the oral cavity is being pulled; The oral cavity data in the image frame is fused to generate the non-rigid region of the overall model; Determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame; Based on each three-dimensional point and its corresponding scanning point in the non-rigid region of the overall model, the positional change range of the three-dimensional point is determined. The three-dimensional points whose positional change range meets the preset range are taken as edge points, and the denture edge line is determined based on the edge points.

2. The method of claim 1, wherein, Based on each 3D point in the non-rigid region of the overall model and its corresponding scan points, the positional change range of the 3D point is determined, including: Calculate the distance between each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning point, and determine the maximum distance as the positional change range of that three-dimensional point.

3. The method of claim 1, wherein, Based on each 3D point in the non-rigid region of the overall model and its corresponding scan points, the positional change range of the 3D point is determined, including: Calculate the curvature change between each three-dimensional point and its corresponding scan point in the non-rigid region of the overall model, and determine the maximum curvature change as the position change amplitude of that three-dimensional point.

4. The method according to claim 1, wherein, Determining the scan point corresponding to each 3D point in the non-rigid region of the overall model in each image frame includes: Determine the normal of each 3D point in the non-rigid region of the overall model; Project all scan points in each image frame into the three-dimensional space where the non-rigid region of the overall model is located; Several scan points that fall on the same three-dimensional point normal line are determined as the scan points corresponding to the three-dimensional point in each image frame in the non-rigid region of the overall model.

5. The method according to claim 1, wherein, Determining the scan point corresponding to each 3D point in the non-rigid region of the overall model in each image frame includes: Determine the non-rigid regions of the overall model and the non-rigid transformation relationships of each image frame; Using the non-rigid transformation relationship, the scanning point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame is determined.

6. The method according to claim 1, wherein, Determining the scan point corresponding to each 3D point in the non-rigid region of the overall model in each image frame includes: The camera pose at the time of acquiring each image frame is determined based on the camera intrinsic and extrinsic parameters of each image frame. The three-dimensional points are reprojected onto each image frame according to the camera pose. The scan points that coincide with the projected 3D point in each image frame are determined as the scan points corresponding to the 3D point in each image frame in the non-rigid region of the overall model.

7. The method according to any one of claims 1 to 6, wherein, The scanning points whose positional change range meets the preset range are taken as edge points, and the denture edge line is determined based on the edge points, including: The scanning points whose positional change range meets the first preset range are taken as the first edge points. The myostatic line is determined based on the first edge points, and the denture edge line is determined based on the myostatic line; or... The scanning point whose positional change range meets the second preset range is taken as the second edge point, and the denture edge line is determined based on the second edge point; The first preset range is smaller than the second preset range.

8. The method according to claim 7, wherein, Determining the myostatic line based on the first edge point includes: The first edge point is fitted and smoothed according to the direction of the dental arch to obtain the first curve, and the first curve is determined as the myostatic line. Determining the denture edge line based on the second edge point includes: The second edge point is fitted and smoothed according to the direction of the dental arch to obtain a second curve, which is then determined as the edge line of the denture.

9. The method according to claim 7, wherein, Also includes: After determining the myostatic line and / or denture edge line, the correctness of the myostatic line and / or denture edge line is judged based on the deep learning model and / or empirical values. If the myostatic line and / or denture edge line are incorrect, a prompt message is issued to prompt the user to adjust the myostatic line and / or denture edge line, or the myostatic line and / or denture edge line are automatically adjusted and the adjusted myostatic line and / or denture edge line is displayed.

10. The method according to claim 7, wherein, Also includes: After determining the myostatic line and / or denture edge line, the initial myostatic line and / or denture edge line are displayed on the interactive interface. Based on the user's interaction, determine the user's modification request; Based on the user's modification request and the magnitude of the positional change of the three-dimensional points, the initial myostatic line and / or denture edge line are locally recalculated and fitted and smoothed to generate and display the adjusted myostatic line and / or denture edge line.

11. The method according to claim 7, wherein, Also includes: Display the myostatic lines and / or denture edge lines on the non-rigid areas of the overall model.

12. The method according to claim 7, wherein, Before acquiring several image frames obtained from an oral cavity scan while the oral cavity is being pulled, the process also includes: Acquire rigid body data obtained from rigid body region scanning, and generate and display the rigid body region of the overall model based on the rigid body data; The method further includes: during the scanning process, the non-rigid regions and rigid regions of the overall model are spliced ​​and merged in real time to generate the overall model and displayed on the interactive interface; In the rigid body region of the overall model, the alveolar ridge region is identified and locked, which does not change during the generation of the overall model.

13. The method according to claim 12, wherein, The steps of generating the non-rigid region of the overall model or generating the overall model, or after the steps of generating the non-rigid region of the overall model or generating the overall model, include: In all image frames, the regions with the highest probability of occurrence and those that are continuous are selected for fusion to make the non-rigid regions of the overall model complete and smooth.

14. A device for determining the edge line of a denture, wherein, include: The scan image frame acquisition module is configured to acquire several image frames obtained by performing an oral scan while the oral cavity is being pulled. The data fusion module is configured to fuse oral cavity data in the image frame to generate the non-rigid region of the overall model; The corresponding scan point determination module is configured to determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame; The position change amplitude determination module is configured to determine the position change amplitude of the three-dimensional point based on each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning points. The edge line determination module is configured to use three-dimensional points whose positional change range meets a preset range as edge points, and determine the denture edge line based on the edge points.

15. A computer-readable storage medium storing a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 13.

16. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the processor executes the computer program, it performs the following steps: Acquire several image frames obtained by scanning the oral cavity while the oral cavity is being pulled; The oral cavity data in the image frame is fused to generate the non-rigid region of the overall model; Determine the scan point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame; Based on each three-dimensional point and its corresponding scanning point in the non-rigid region of the overall model, the positional change range of the three-dimensional point is determined. The three-dimensional points whose positional change range meets the preset range are taken as edge points, and the denture edge line is determined based on the edge points.

17. The computer device according to claim 16, wherein, When determining the positional change range of each three-dimensional point and its corresponding scan point in a non-rigid region based on the overall model, the processor executes the following steps when running the computer program: Calculate the distance between each three-dimensional point in the non-rigid region of the overall model and its corresponding scanning point, and determine the maximum distance as the positional change range of that three-dimensional point.

18. The computer device according to claim 16, wherein, When determining the positional change range of each three-dimensional point and its corresponding scan point in a non-rigid region based on the overall model, the processor executes the following steps when running the computer program: Calculate the curvature change between each three-dimensional point and its corresponding scan point in the non-rigid region of the overall model, and determine the maximum curvature change as the position change amplitude of that three-dimensional point.

19. The computer device according to claim 16, wherein, When determining the scan point corresponding to each 3D point in the non-rigid region of the overall model in each image frame, the processor executes the computer program to perform the following steps: Determine the normal of each 3D point in the non-rigid region of the overall model; Project all scan points in each image frame into the three-dimensional space where the non-rigid region of the overall model is located; Several scan points that fall on the same three-dimensional point normal line are determined as the scan points corresponding to the three-dimensional point in each image frame in the non-rigid region of the overall model.

20. The computer device according to claim 16, wherein, When determining the scan point corresponding to each 3D point in the non-rigid region of the overall model in each image frame, the processor executes the computer program to perform the following steps: Determine the non-rigid regions of the overall model and the non-rigid transformation relationships of each image frame; Using the non-rigid transformation relationship, the scanning point corresponding to each three-dimensional point in the non-rigid region of the overall model in each image frame is determined.

Images