Systems, Methods, and Devices for Intraoral Scanning

Abstract

Some embodiments of the present invention provide a system, method, and apparatus for intraoral scanning. A computing device coupled to an intraoral scanner obtains a point cloud representing a three-dimensional geometric surface of an oral cavity in which an implant has been implanted. The computing device then, based on the obtained point cloud, identifies reliable data regions and unreliable data regions of the geometric surface, where the reliable data regions are associated with regions where the amount of deformation that occurs when pressure is applied is less than a deformation threshold, and the unreliable data regions are associated with regions where the amount of deformation that occurs when pressure is applied is greater than or equal to the deformation threshold. In addition, a point cloud of the reliable data regions is selected for storage to form first scan data, and second scan data of the three-dimensional geometric surface of the oral cavity in which the implant and a scanning rod have been implanted is obtained, and the first scan data and the second scan data are registered; and based on the registration result, position information of the scanning rod is determined.

Description

Technical Field

[0001] Embodiments of the present invention mainly relate to the field of dental implant, and more specifically, to a system, method and device for intraoral scanning used in dental implant. Background Art

[0002] Intraoral scanning refers to the process of digitally capturing detailed three-dimensional (3D) images of the internal oral structures (including teeth, gums, and surrounding tissues) using specialized optical technologies. Different from traditional dental impressions that involve using physical molds or trays filled with impression materials, intraoral scanning provides a non-invasive and comfortable option for patients and dental professionals.

[0003] During intraoral scanning, a dental professional uses a handheld device (i.e., an intraoral scanner) equipped with a camera and sensors to capture multiple images of the oral cavity from different angles. These images are transmitted to a computer station and then quickly stitched together using complex algorithms to create a 3D representation of the patient's teeth and soft tissues, which can be visualized at the computer station and viewed by the dental professional.

[0004] For example, when performing dental implant, an oral scanner is required for implant scanning. The implant scanning is achieved in two steps. In the first step, the arch data of the user with the implant exposed is obtained, and the obtained three-dimensional arch data will be used to define the three-dimensional shape of the dental crown or denture. The implant has been implanted on the dental arch before the first scan. In the second step, after fastening the scanning rod to the implant, the three-dimensional data of the scanning rod including the dental arch is scanned to obtain the relative position information of the scanning rod on the dental arch for fitting calculation, so as to be used for abutment positioning. However, during the first and second scans, some parts in the patient's oral cavity may change, resulting in a large registration error when fusing or registering the data scanned twice. Summary of the Invention

[0005] According to an exemplary embodiment of the present invention, a system, method and device for intraoral scanning are provided. When the system for intraoral scanning according to an embodiment of the present invention enters the second scan, after copying or reusing the scan data of the first time, certain data screening processing is performed, and only reliable data is used. The system and method can isolate or remove unreliable data during the first scan, that is, avoid the registration error caused by the change of the data at the same position during the second scan compared with the data during the first scan, thereby improving the data registration accuracy and scanning accuracy.

[0006] In a first aspect of the present invention, a system for intraoral scanning is provided. The system includes an intraoral scanner; and a computing device coupled to the intraoral scanner. The computing device is configured to: obtain, from a scan of the oral cavity in which implants have been implanted by the intraoral scanner, a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which implants have been implanted; based on the obtained point cloud, identify a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity, wherein the reliable data region is associated with a region where the amount of deformation occurring when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the amount of deformation occurring when pressure is applied is greater than or equal to the deformation threshold; select the point cloud of the reliable data region for storage to form first scan data; obtain second scan data of the three-dimensional geometric surface of the oral cavity in which implants and a scanning rod have been implanted from a scan of the oral cavity in which the scanning rod has been implanted on the implant by the intraoral scanner; register the first scan data and the second scan data; and based on the registration result, determine the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity.

[0007] In some embodiments, in order to identify a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity based on the obtained point cloud, the computing device is configured to: based on the color difference between the tooth region and the non-tooth region, label the point cloud as a tooth point cloud or a non-tooth point cloud on the point cloud in at least one frame of the obtained three-dimensional geometric surface of the oral cavity; based on the labeled tooth point cloud and non-tooth point cloud, identify the tooth region and the non-tooth region; and identify the tooth region as the reliable data region and the non-tooth region as the unreliable data region.

[0008] In some embodiments, in order to identify a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity based on the obtained point cloud, the computing device is configured to: based on a deep learning model, assign a corresponding classification to the point cloud on the point cloud in at least one frame of the obtained three-dimensional geometric surface of the oral cavity to label the point cloud as a tooth point cloud or a non-tooth point cloud; based on the labeled tooth point cloud and non-tooth point cloud, identify the tooth region and the non-tooth region; and identify the tooth region as the reliable data region and the non-tooth region as the unreliable data region.

[0009] In some embodiments, in order to identify the tooth region and the non-tooth region based on the labeled tooth point cloud and non-tooth point cloud, the computing device is configured to: in each frame of at least one frame, assign the point cloud labeled as a tooth point cloud to the tooth region, and assign the point cloud labeled as a non-tooth point cloud to the non-tooth region; or in each frame of at least one frame, regard the frame in which the number ratio of the tooth point cloud is higher than or equal to a ratio threshold as a tooth frame, and regard the frame in which the number ratio of the tooth point cloud is lower than the ratio threshold as a non-tooth frame.

[0010] In some embodiments, the computing device is further configured to: based on the acquired point cloud, identify a region of interest on the three-dimensional oral geometric surface, where the region of interest is associated with a region where an implant has been implanted, and where at least one frame includes one or more frames that fall within the region of interest.

[0011] In some embodiments, in order to identify a reliable data region and an unreliable data region on the three-dimensional oral geometric surface based on the acquired point cloud, the computing device is configured to: based on the acquired point cloud, identify the free region and / or edentulous region of the three-dimensional oral geometric surface as the unreliable data region, and identify the region outside the free region and the edentulous region as the reliable data region.

[0012] In some embodiments, in order to identify the free region of the three-dimensional oral geometric surface, the computing device is configured to: determine the dental arch curve for the three-dimensional oral geometric surface; based on the determined dental arch curve, identify the vertex and two endpoints of the dental arch curve; based on the two endpoints and the vertex, determine the segmentation points between each endpoint and the vertex; and in the case where there are no teeth in the molar region between each endpoint and the segmentation point, identify the molar region as the free region.

[0013] In some embodiments, in order to identify the edentulous region of the three-dimensional oral geometric surface, the computing device is configured to: sample the dental arch curve at a certain interval to obtain a series of ordered discrete points; in the case where there are no teeth near a given discrete point, identify the given discrete point as a non-tooth point; connect a plurality of consecutive and ordered non-tooth points in a given region to form a connection line; and in the case where the length of the connection line is greater than or equal to a length threshold, identify the given region as the edentulous region.

[0014] According to a second aspect of the present invention, there is provided a method for intraoral scanning, including: acquiring, from a scan of an oral cavity in which an implant has been implanted by an intraoral scanner, a point cloud representing the three-dimensional (3D) geometric surface of the oral cavity in which the implant has been implanted; based on the acquired point cloud, identifying a reliable data region and an unreliable data region on the three-dimensional oral geometric surface, where the reliable data region is associated with a region where the amount of deformation that occurs when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the amount of deformation that occurs when pressure is applied is greater than or equal to the deformation threshold; selecting the point cloud of the reliable data region for storage to form first scan data; acquiring, from a scan of an oral cavity in which a scanning rod has been implanted in an implant by the intraoral scanner, second scan data of the three-dimensional geometric surface of the oral cavity in which the implant and the scanning rod have been implanted; registering the first scan data and the second scan data; and based on the registration result, acquiring the position information of the scanning rod on the three-dimensional oral geometric surface.

[0015] In some embodiments, identifying reliable data regions and unreliable data regions of the oral three-dimensional geometric surface based on the acquired point cloud includes: based on the color difference between the tooth region and the non-tooth region, marking the point cloud in at least one frame of the acquired oral three-dimensional geometric surface as a tooth point cloud or a non-tooth point cloud; identifying the tooth region and the non-tooth region based on the marked tooth point cloud and non-tooth point cloud; and identifying the tooth region as a reliable data region and the non-tooth region as an unreliable data region.

[0016] In some embodiments, identifying reliable data regions and unreliable data regions of the oral three-dimensional geometric surface based on the acquired point cloud includes: based on a deep learning model, assigning corresponding classifications to the point cloud in at least one frame of the acquired oral three-dimensional geometric surface to mark the point cloud as a tooth point cloud or a non-tooth point cloud; identifying the tooth region and the non-tooth region based on the marked tooth point cloud and non-tooth point cloud; and identifying the tooth region as a reliable data region and the non-tooth region as an unreliable data region.

[0017] In some embodiments, identifying the tooth region and the non-tooth region based on the marked tooth point cloud and non-tooth point cloud includes: in each frame of at least one frame, attributing the point cloud marked as a tooth point cloud to the tooth region and attributing the point cloud marked as a non-tooth point cloud to the non-tooth region; or in each frame of at least one frame, regarding the frame in which the quantity ratio of the tooth point cloud is higher than or equal to the ratio threshold as a tooth frame and regarding the frame in which the quantity ratio of the tooth point cloud is lower than the ratio threshold as a non-tooth frame.

[0018] In some embodiments, the method further includes: identifying a region of interest on the oral three-dimensional geometric surface based on the acquired point cloud, where the region of interest is associated with the region where an implant has been implanted, and where at least one frame includes multiple frames falling within the region of interest.

[0019] In some embodiments, identifying reliable data regions and unreliable data regions of the oral three-dimensional geometric surface based on the acquired point cloud includes: identifying the free region and / or edentulous region of the oral three-dimensional geometric surface as unreliable data regions based on the acquired point cloud, and regarding the region outside the free region and the edentulous region as reliable data regions.

[0020] In some embodiments, identifying the free region of the oral three-dimensional geometric surface includes: determining the dental arch curve for the oral three-dimensional geometric surface; identifying the vertex and two endpoints of the dental arch curve based on the acquired dental arch curve; determining the segmentation points between each endpoint and the vertex; and identifying the molar region as the free region when there are no teeth in the molar region between each endpoint and the segmentation point.

[0021] In some embodiments, identifying an edentulous area of the oral three-dimensional geometric surface includes: sampling at regular intervals on the dental arch curve to obtain a series of ordered discrete points; identifying a given discrete point as a non-tooth point if there are no teeth near the given discrete point; connecting multiple consecutive and ordered non-tooth points in a given area to form a connecting line; and identifying the given area as an edentulous area if the length of the connecting line is greater than or equal to a length threshold.

[0022] According to a third aspect of the present invention, there is provided an intraoral scanning device, including: a processor; and a memory storing executable instructions that, when executed by the processor, cause the device to at least: obtain, from a scan of the oral cavity with an implant already implanted by an intraoral scanner, a point cloud representing the three-dimensional (3D) geometric surface of the oral cavity with the implant already implanted; based on the obtained point cloud, identify a reliable data area and a non-reliable data area of the oral three-dimensional geometric surface, where the reliable data area is associated with an area where the amount of deformation occurring when pressure is applied is less than a deformation threshold, and the non-reliable data area is associated with an area where the amount of deformation occurring when pressure is applied is greater than or equal to the deformation threshold; select the point cloud of the reliable data area for storage to form first scan data; obtain, from a scan of the oral cavity with a scanning rod implanted in the implant by the intraoral scanner, second scan data of the three-dimensional geometric surface of the oral cavity with the implant and the scanning rod already implanted; register the first scan data and the second scan data; and based on the registration result, obtain the position information of the scanning rod on the oral three-dimensional geometric surface.

[0023] It should be understood that the content described in the summary of the invention section is not intended to limit the key or important features of the embodiments of the present invention, nor to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In combination with the drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present invention will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0025] Figure 1 An intraoral scanning system according to some example embodiments of the present invention is shown;

[0026] Figure 2 A schematic diagram of a dental implant case according to some embodiments of the present invention is shown;

[0027] Figure 3A A method for intraoral scanning according to some embodiments of the present invention is shown;

[0028] Figure 3BSchematic diagram of an oral three-dimensional geometric surface model based on the first-step dental arch scan according to some embodiments of the present invention;

[0029] Figure 3C Schematic diagram of an oral three-dimensional geometric surface model after deleting unreliable data regions according to some embodiments of the present invention;

[0030] Figure 3D Schematic diagram of a model of an oral three-dimensional geometric surface after registration of first scan data and second scan data according to some embodiments of the present invention;

[0031] Figure 4 Exemplary method for identifying reliable data regions and unreliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention;

[0032] Figure 5 Exemplary method for identifying reliable data regions and unreliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention;

[0033] Figure 6 Exemplary method for identifying reliable data regions and unreliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention;

[0034] Figure 7A Shows the initial dental arch pose according to some embodiments of the present invention;

[0035] Figure 7B Shows the pose of the maximum visible region of the dental arch according to some embodiments of the present invention;

[0036] Figure 7C Schematic diagram of a dental arch model including a dental arch curve according to some embodiments of the present invention;

[0037] Figure 7D Schematic diagram of a dental arch model with a free region identified according to some embodiments of the present invention;

[0038] Figure 7E Schematic diagram of a dental arch model with an edentulous region identified according to some embodiments of the present invention;

[0039] Figure 8 Block diagram of a computing device capable of implementing multiple embodiments of the present invention. Detailed implementation manners

[0040] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0041] In the description of the embodiments of the present invention, the term "comprising" and its like shall be understood as an open inclusion, i.e., "including but not limited to". The term "based on" shall be understood as "at least partially based on". The term "one embodiment" or "the embodiment" shall be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included hereinafter.

[0042] Figure 1 An intraoral scanning system 100 according to some example embodiments of the present invention is shown. The intraoral scanning system 100 includes an intraoral scanner 110 and a computing device 120 (such as a laptop, a desktop computer, etc.) coupled together. This communication link between the intraoral scanner 110 and the computing device 120 allows the captured images and control commands to be transmitted from the intraoral scanner 110 to the computing device 120 for further processing. The communication link can be implemented through a wired connection (such as a Universal Serial Bus (USB)) or a wireless connection (such as Wi-Fi (Wireless Fidelity)). It should be understood that other communication implementations are also possible.

[0043] The intraoral scanner 110 can be a handheld device that a dentist (or a dental assistant) can insert into a patient's oral cavity to capture images. As shown, the intraoral scanner 110 includes a tip 101 and a body 102. The tip 101 can be a detachable component or integrated with the intraoral scanner 100. At the top of the tip 101, there is a camera or an optical system 103 for capturing images of teeth and surrounding tissues (such as gums). In addition, the intraoral scanner 110 can include one or more buttons (not shown), and the dentist can press the (one or more) buttons to control the system 100, including but not limited to capturing images of the patient's oral cavity, starting or stopping scanning, selecting the mode of the system, or controlling the view of the 3D image of the oral structure.

[0044] The computing device 120 may include or be connected to a screen 115 for displaying a user interface such as a graphical user interface (GUI). The GUI may include a visualization of scanned data, such as a 3D representation of a patient's oral cavity, as well as UI elements such as menus or icons. A dentist may interact with the UI elements to control the intraoral scanning system 100 and examine the 3D representation displayed on the screen 115. Most commonly, the dentist uses an input device 125, such as a mouse or keyboard connected to the computing device 120, to interact with the UI elements.

[0045] As mentioned above, when implanting teeth, an oral scanner is required for implant scanning. Implant scanning is achieved in two steps. In the first step, the dental arch data of the user with the exposed implant (the area of the exposed implant can also be called the cuff area) is obtained, and the obtained 3D dental arch data will be used to define the 3D shape of the dental crown or denture. The implant has been implanted on the dental arch before the first step of scanning. In the second step, after fastening the scanning rod to the implant, the 3D data of the scanning rod containing the dental arch is scanned to be used for fitting and calculating the relative position information of the scanning rod on the dental arch, so as to be used for abutment positioning.

[0046] Currently, the mainstream intraoral scanners basically perform implant scanning according to the above two steps. Specifically, after completing the first step of scanning, in order to avoid repeated scanning and reduce unnecessary scanning time, usually all or part of the scanning data of the first step is directly copied, and then the second step of scanning is completed.

[0047] However, during the first and second steps of scanning, some parts of the patient's oral cavity may change, resulting in a large registration error when fusing or registering the data scanned twice. For example, for the implant area where data changes occur, it may have a certain negative impact on the registration result during the implant scanning registration process, increasing the registration error and resulting in inaccurate data quality.

[0048] For example, in the case of implant cases with free-end edentulousness, there will be a large problem of large registration errors in the second scan data caused by large data changes. Figure 2 Shows an implant case with free-end edentulousness according to some embodiments of the present invention.

[0049] In Figure 2 In the shown implant case, it can be considered that the teeth, scanning rod or implant are rigid objects, and their positions during the two scans are always unchanged; at the same time, the gums around these rigid objects or between the rigid objects are relatively stable and can be considered in a quasi-rigid state, which will not bring too large scanning registration errors. In addition to these areas, mainly the free area (edentulous area) is prone to deformation.

[0050] In Figure 2 In the shown implant case, two scanning rods or implants 201, 202 are located at the arch position with a free-end loss on one side. The gingiva at the end of the scanning rod or implant 201 on the side is in a free state, lacking the support of rigid objects such as teeth. The interval between the two scans is long, and the patient may open and close the dental arch multiple times. Therefore, it is very difficult to ensure that the free-end gingiva is in the same shape during the two scans. If the data of the first scan is directly substituted into the second scan and participates in data registration, due to the inconsistent data of the free-end gingiva during the two scans, it is very likely to cause deformation of the shape of the nearby scanning rod or implant. Therefore, the fitting error of the scanning rod position increases, making the finally designed crown or bridge unable to fully match the patient's dental arch.

[0051] In view of the above situation, an embodiment of the present invention provides an intraoral scanning system for reducing registration errors. A computing device coupled to an intraoral scanner obtains a point cloud representing the three-dimensional (3D) geometric surface of the oral cavity in which implants have been implanted from a scan of the oral cavity by the intraoral scanner. The computing device then identifies a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity based on the obtained point cloud, where the reliable data region is associated with a region where the amount of deformation occurring when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the amount of deformation occurring when pressure is applied is greater than or equal to the deformation threshold. In addition, the computing device selects the point cloud of the reliable data region for storage to form first scan data. Then, the computing device obtains second scan data of the three-dimensional geometric surface of the oral cavity in which implants and scanning rods have been implanted from a scan of the oral cavity by the intraoral scanner with the scanning rods implanted on the implants, and registers the first scan data and the second scan data. Finally, the computing device determines the position information of the scanning rods on the three-dimensional geometric surface of the oral cavity based on the registration result.

[0052] In this way, the computing device removes the data in the region where the deformation may be large before the second scan, and only uses the reliable data of the first dental arch scan and the data of the second implant scan for registration. Therefore, the data registration error is reduced, and the fitting error of the scanning rod position is also reduced, so that a crown or bridge that fully matches the patient's dental arch can be finally designed.

[0053] Figure 3A Method 300 for intraoral scanning according to some embodiments of the present invention is shown. Method 300 can be implemented at the computing device 120 of the intraoral scanning system 100 as shown in Figure 1 For better understanding, method 300 will be described with reference to Figure 1 description of method 300.

[0054] At 310, computing device 120 uses intraoral scanner 110 to obtain a point cloud representative of the three-dimensional (3D) geometric surface of the oral cavity in which implants have been implanted. That is, intraoral scanner 110 performs the first-step dental arch scan. During the intraoral scan, the dentist can use intraoral scanner 120 to capture multiple 2D images of the interior of the oral cavity by moving the scanner to different areas. Computing device 120 receives the 2D images from intraoral scanner 110, stitches the images together and converts them into a point cloud representing the oral cavity geometric surface model. Each point cloud can include spatial coordinates (e.g., X, Y, Z coordinates in 3D space using Cartesian coordinates), intensity values, color information, and normal vectors. The point cloud can optionally include point density, point distribution, range data, scan location information, and other additional attributes.

[0055] Figure 3B A schematic diagram of a three-dimensional geometric surface model of the oral cavity based on the first-step dental arch scan according to some embodiments of the present invention is shown. As Figure 3B shown, the model includes a tooth region 301, a gingival region 302, an implant region 303, etc. obtained after the first-step scan.

[0056] At 320, computing device 120 identifies a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, where the reliable data region is associated with a region where the amount of deformation that occurs when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the amount of deformation that occurs when pressure is applied is greater than or equal to the deformation threshold. Specifically, teeth are mainly composed of hard minerals such as enamel (the outermost layer), dentin, and dental pulp. Enamel is one of the hardest biological tissues, and under normal circumstances, teeth are not easily deformed, so teeth can be an example of a reliable data region. The gingiva is a soft tissue rich in water and elastic protein fibers, with high flexibility and compressibility. Gingival tissue is softer and relatively more easily deformed, and can gradually return to its original state as the pressure disappears, so the gingiva can be an example of an unreliable data region. Teeth and gingiva are only some examples of reliable data regions and unreliable data regions respectively. The reliable data region or the unreliable data region may change. For example, the edentulous gingival region between two teeth can also be considered a reliable data region, while the free area can be considered an unreliable data region. The deformation threshold can be set according to the user's needs.

[0057] At 330, computing device 120 selects the point cloud of the reliable data region for storage to form the first scan data.

[0058] In some embodiments, the reliable data region may include teeth and implants or cuffs as rigid objects, or the gingiva around the rigid objects, as well as the gingiva between the rigid objects, etc. The unreliable data region may include the gingiva at the free end, etc., because there may be no rigid object around the periphery of the free end. However, in other embodiments, the scope of the unreliable data region may be expanded to include all regions outside the tooth region.

[0059] Figure 3C A schematic diagram of an oral three-dimensional geometric surface model after deleting the unreliable data region according to some embodiments of the present invention is shown. As Figure 3C shown, for example, the implant region has been removed as an unreliable data region because there is no support of a rigid object around the implant region, and the deformation may exceed a threshold when pressure is applied. The threshold can be set according to the actual situation, and the embodiments of the present invention do not limit the range of the threshold.

[0060] At 340, the computing device 120 obtains second scan data of the oral three-dimensional geometric surface with the implant and the scanning rod implanted from the scan of the oral cavity by the intraoral scanner with the scanning rod implanted on the implant. At 350, the computing device 120 registers the first scan data and the second scan data.

[0061] In some embodiments, when registering, the computing device 120 may be based on feature matching. When matching feature points, the computing device 120 may search for points, lines or surfaces with obvious features, such as the edges of teeth, cusps, specific marks of implants or scanning rods, etc. These feature points are unique and stable and can be used as the key identifiers for data splicing. After determining the feature points, the computing device 120 may, for example, calculate the spatial relationships between the feature points in different data sets, such as distances, angles, etc., and then by comparing these relationships, find pairs of matching feature points to determine the relative positions and postures between the two data sets. Then, according to the matching feature point pairs, the computing device 120 performs transformations such as translation and rotation on the second-step scan data relative to the first-step scan data to make the feature points of the two data sets coincide as much as possible, thereby completing data splicing.

[0062] In some embodiments, when performing registration, the computing device 120 may be based on surface matching. When based on surface matching, the computing device 120 constructs the three-dimensional data obtained from the two-step scan into surface models respectively. Then, the computing device 120 searches for the best matching method between the two surface models through a specific algorithm, so that the two surfaces fit as closely as possible in space, which may involve multiple transformations and attempts on one of the surface models to find the position and orientation that minimizes the difference between the surfaces. Then, after finding the best match, the computing device 120 fuses the two surface models, merging the data surface of the scanning rod included in the second step scan with the dental arch data surface of the first step to form a complete and continuous three-dimensional model. When performing data registration, the computing device 120 may also use other methods to register the first scan data and the second scan data, such as using coordinate system matching, etc.

[0063] At 350, the computing device 120 determines the position information of the scanning rod on the three-dimensional oral geometric surface based on the registration result. That is, based on the data of the three-dimensional oral geometric surface after the two-step scan fusion, the position information of the scanning rod on the three-dimensional oral geometric surface is determined.

[0064] Figure 3D A schematic diagram of a model of the three-dimensional oral geometric surface after registering the first scan data and the second scan data according to some embodiments of the present invention is shown. As Figure 3D shown, based on the first scan data of the first step scan, the data of the scanning rod 304 is added. It can be seen that after data registration, in Figure 3C the implant area deleted in is precisely matched with the first scan data and is precisely registered in the appropriate position.

[0065] In method 300, when entering the second step scan, after copying the scan data of the first step, a certain data screening process is automatically performed to retain reliable data and optionally eliminate unreliable data, ensuring that the user continues to scan based on the reliable data of the first step. Since the first scan data does not include the scan results of the areas with large deformation when pressure is applied (i.e., non-reliable data areas), this part of non-reliable data does not participate in the registration, avoiding registration errors caused by changes in the data during the second scan compared to the first scan at the same position (for example, non-reliable data areas, such as free ends, etc.), thereby improving the registration accuracy and scan accuracy.

[0066] In order to identify the reliable data areas and non-reliable data areas of the three-dimensional oral geometric surface based on the acquired point cloud, some embodiments of the present invention provide various ways to perform the identification. The various ways described below can be used alone or in combination.

[0067] Figure 4 An exemplary method 400 for identifying reliable data regions and unreliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention is shown. Method 400 is Figure 3A an example implementation of step 320 in

[0068] In Figure 4 the method 400 shown, in order to identify reliable data regions and unreliable data regions of an oral three-dimensional geometric surface, the computing device 120 can distinguish reliable data regions and unreliable data regions by a color recognition method, such as distinguishing a tooth region and a non-tooth region.

[0069] At 410, the computing device 120 can label the point cloud as a tooth point cloud or a non-tooth point cloud on the point cloud in at least one frame of the acquired oral three-dimensional geometric surface based on the color difference between the tooth region and the non-tooth region. Specifically, the tooth region (high white component), the gum region (high red component), and other regions are labeled on the point cloud.

[0070] At 420, based on the labeled tooth point cloud and non-tooth point cloud, the computing device 120 can identify the tooth region and the non-tooth region. At 430, the computing device 120 identifies the tooth region as a reliable data region and the non-tooth region as an unreliable data region. In some embodiments, in order to identify the tooth region and the non-tooth region, the computing device 120 can, in each frame of at least one frame, assign the point cloud labeled as a tooth point cloud to the tooth region and the point cloud labeled as a non-tooth point cloud to the non-tooth region. For example, based on the point cloud labeling, the computing device 120 can retain all the point clouds labeled as the tooth region as reliable data; all the point clouds of the non-tooth region are excluded as unreliable data.

[0071] Alternatively, in some embodiments, in each frame of at least one frame, the computing device 120 regards the frame in which the number ratio of the tooth point cloud is higher than or equal to a ratio threshold as a tooth frame, and regards the frame in which the number ratio of the tooth point cloud is lower than the ratio threshold as a non-tooth frame. For example, based on the point cloud labeling, the computing device performs label information statistics on the three-dimensional point clouds of single frames scanned from different perspectives. If the number of tooth point clouds is higher than or equal to a certain threshold, it is considered that the three-dimensional point cloud of this frame is a tooth frame, otherwise it is considered that the point cloud of this frame is a non-tooth frame. Retain all the three-dimensional point clouds of the tooth frames as reliable data; all the three-dimensional point clouds of the non-tooth frames are excluded as unreliable data. In some examples, the ratio threshold can be 75%, that is, if the number ratio of the tooth point cloud exceeds 75%, it can be considered that this frame is a tooth frame.

[0072] In some embodiments, the at least one frame includes each frame obtained by scanning. In some embodiments, the at least one frame only includes the frames falling within the region of interest (ROI), rather than all frames, and the region of interest may include the implant region.

[0073] Figure 5 An exemplary method 500 for identifying reliable data regions and unreliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention is shown. Method 500 is Figure 3A an example implementation of step 320 in

[0074] In Figure 5 the shown method 500, in order to identify reliable data regions and unreliable data regions of the oral three-dimensional geometric surface, the computing device 120 may identify reliable data regions and unreliable data regions based on a deep learning model, such as identifying tooth regions and non-tooth regions.

[0075] At 510, the computing device 120 assigns corresponding classifications to the point cloud on the point cloud in at least one frame of the obtained oral three-dimensional geometric surface based on the deep learning model, so as to label the point cloud as a tooth point cloud or a non-tooth point cloud.

[0076] When classifying point cloud data based on the deep learning model, the computing device 120 may perform multiple steps. For example, data annotation is performed to generate a training data set for the model. During the data annotation process, a large amount of oral three-dimensional point cloud data is collected, including scanned data of normal, restored, and implanted dental arches. The three-dimensional point cloud data may include normal teeth, special teeth, or scanned objects, and all these point cloud data are manually annotated. Experienced dentists can use manual annotation techniques to perform semantic segmentation on the dental arch and assign appropriate classifications to each point in the point cloud. For example, the following labels can be assigned: the gingiva is labeled with a value of 0, normal teeth are labeled with a value of 0, scanned objects are labeled with a value of 1, and prepared teeth are labeled with a value of 2.

[0077] Then the labeled data can be preprocessed. During the preprocessing process, the dental arch point cloud data can be normalized. For example, the coordinates and normal vectors of the point cloud can be normalized by min-max normalization or mean normalization. Min-max normalization can scale the data to a fixed range, usually [0,1], while mean normalization adjusts the data to have a mean of 0 and a standard deviation of 1. This helps to eliminate the influence of data scale differences on the network. In some embodiments, the center of the point cloud can be set to the origin to eliminate the influence of translation and rotation.

[0078] Then, data augmentation can be performed. The purpose of data augmentation is to increase the amount of data in the training dataset. In some embodiments, the computing device can combine the data points corresponding to the prepared tooth or the scanned volume with the normal tooth data from different point clouds. This is because there is less data containing the prepared tooth or the scanned volume compared to the normal tooth data. In some embodiments, the computing device applies at least one rotation matrix to the original point cloud to augment the training dataset. Applying the rotation matrix to each dental arch can provide various orientations for the dental arch. This enhances the robustness of the deep learning model.

[0079] Subsequently, semantic segmentation can be carried out. After training, the deep learning model can be used for semantic segmentation, which can assign classifications to the data points of the point cloud. In some embodiments, the deep learning model can capture geometric features at different levels through multi-scale feature extraction. Based on these features extracted from the 3D point cloud, the deep learning model can accurately distinguish different types of tooth shapes on the dental arch. By training the model using a large annotated dataset, normal teeth, gums, implants, and scanned volumes, etc. can be identified from the point cloud. Through these operations, the computing device 120 can classify and label the point cloud as a tooth point cloud and a non-tooth point cloud based on the deep learning model.

[0080] At 520, the computing device 120 identifies the tooth region and the non-tooth region based on the labeled tooth point cloud and non-tooth point cloud. In block 530, the tooth region is identified as a reliable data region, and the non-tooth region is identified as a non-reliable data region. For example, the computing device 120 can use the deep learning model to classify and label the point cloud, and based on the point cloud labeling, perform label information statistics for the single-frame 3D point clouds scanned from all different perspectives. If the number of tooth point clouds is higher than or equal to a certain threshold, then this frame of 3D point cloud is considered a tooth frame, otherwise this frame of point cloud is considered a non-tooth frame.

[0081] Based on the results of the above point cloud classification, the region of interest ROI can also be identified. For example, the classified point cloud can be post-processed. During the post-processing, the computing device can analyze the results of semantic segmentation to determine the connected domains in the 3D point cloud. In some embodiments, the computing device can determine multiple connected domains based on the data points with the same classification (such as the points labeled as prepared teeth or scanning rods), and then filter the connected domains by a predetermined size. After size filtering, the connected domains that meet the size criteria can be identified as the ROI (such as implants, prepared teeth, or scanned volumes), thereby determining their accurate positions. By automatically identifying the ROI, it is possible to avoid the user manually selecting the ROI region, avoid unnecessary user interaction, and provide a better user experience.

[0082] In addition, since non-reliable data usually appears in the ROI region, by only screening the frames corresponding to the ROI, the processing workload can be reasonably reduced. Therefore, in some embodiments, the ROI can be identified first, and then reliable data and non-reliable data can be identified from the data in the ROI. That is, only the non-reliable data region is identified in the ROI because relatively large deformations will occur in this ROI (such as the implant region). For example, taking the three-dimensional point cloud of a single frame as a unit, all single-frame point clouds falling into the cuff region can be found. Taking these single-frame point clouds as a unit, the neighborhood traversal of the single-frame three-dimensional point cloud is gradually carried out outward, and the traversal termination condition is that the traversed single-frame three-dimensional point cloud is a tooth frame. After the traversal is completed, all the traversed non-tooth frame three-dimensional point clouds are removed as non-reliable data; the remaining single-frame three-dimensional point clouds are reliable data and will be retained.

[0083] Figure 6 An exemplary method 600 for identifying reliable data regions and non-reliable data regions of an oral three-dimensional geometric surface according to some embodiments of the present invention is shown. Method 600 is Figure 3A An exemplary implementation of step 320 in

[0084] In Figure 6 In the shown method 600, in order to identify reliable data regions and non-reliable data regions of the oral three-dimensional geometric surface, at 610, the computing device 120 can identify the free region and / or edentulous region of the oral three-dimensional geometric surface as non-reliable data regions, and regard the regions outside the free region and edentulous region as reliable data regions.

[0085] The following will refer to Figures 7A to 7E to illustrate how to identify the free region and edentulous region of the oral three-dimensional geometric surface; where Figure 7A shows the initial dental arch pose according to some embodiments of the present invention; Figure 7B shows the maximum visible region pose of the dental arch according to some embodiments of the present invention; Figure 7C shows a schematic diagram of a dental arch model including a dental arch curve according to some embodiments of the present invention; Figure 7D shows a schematic diagram of a dental arch model with the free region identified according to some embodiments of the present invention; and Figure 7E shows a schematic diagram of a dental arch model with the edentulous region identified according to some embodiments of the present invention.

[0086] To identify the free areas of the three-dimensional geometric surface of the oral cavity, a computing device may perform multiple operations. For example, determine the dental arch curve for the three-dimensional geometric surface of the oral cavity. Then, based on the determined dental arch curve, identify the vertices and two endpoints of the dental arch curve. Next, based on the two endpoints and the vertex, determine the segmentation points between each endpoint and the vertex. Finally, when there are no teeth in the molar area between each endpoint and the segmentation point, identify the molar area as a free area.

[0087] To determine the dental arch curve of the three-dimensional geometric surface of the oral cavity, first place the dental arch in the pose of the maximum visible area; then, within the maximum visible area of the dental arch, only retain the three-dimensional points on the outer edge of the dental arch, and use these three-dimensional points to fit a parabola, which is the dental arch curve.

[0088] To place the dental arch in the pose of the maximum visible area, first obtain all the three-dimensional point clouds of the first scan and perform downsampling at a certain ratio. Then, the dental arch contains coordinate information of the x, y, and z axes in three-dimensional space. Select one of the axes as the front-view axis, for example, use the z axis as the front-view axis; construct a plane with the other two axes, such as the xoy plane. Next, rotate the dental arch around the x axis and the y axis respectively, and find the angles with the maximum visible area in the upward direction of the front-view axis, so as to transform the pose of the dental arch to the maximum visible area.

[0089] Then, as Figure 7C shown, within the maximum visible area of the dental arch, only retain the three-dimensional points on the outer edge of the dental arch, and use these three-dimensional points to fit a parabola, which is the dental arch curve. As shown by the parabola in the figure, the dental arch curve may include two endpoints 701 and a vertex 702.

[0090] As Figure 7D shown, the dental arch curve may include two endpoints 701 and a vertex 702. Then, based on the two endpoints and the vertex, determine the segmentation points 703 between each endpoint and the vertex. The area between each endpoint and the segmentation point can be called the molar area. When there are no teeth in the molar area, identify the molar area as a free area. As Figure 7D shown, the area 704 is the free area, that is, the area covered by the gray squares. For example, draw a segmentation line at the 1 / 3 position of the distance from the two endpoints on both sides of the parabola to the vertex, and define the area between the two endpoints on the left and right sides of the parabola to the segmentation line as the molar area. If there are no teeth in the molar area, then the molar area is a free area.

[0091] To identify the toothless area on the three-dimensional geometric surface of the oral cavity, a computing device can perform multiple operations. For example, it can sample at regular intervals on the dental arch curve to obtain a series of ordered discrete points. Then, when there are no teeth near a given discrete point, the given discrete point is identified as a non-tooth point. Next, multiple consecutive and ordered non-tooth points in the given area are connected to form a connecting line. Finally, when the length of the connecting line is greater than or equal to a length threshold, the given area is identified as a toothless area. This length threshold can have different values according to the area where the teeth are located. In one example, the length threshold can be 5 mm, slightly less than the length of a tooth.

[0092] For example, sample at regular intervals on the dental arch curve to obtain a group of ordered discrete points. If there are no teeth near a certain discrete point, it is defined as a non-tooth point. Connect all consecutive non-tooth points. If the length of the connecting line is greater than or equal to a certain threshold, then this area is a toothless area. As Figure 7E shown, area 705 is identified as a toothless area, that is, the area defined by the black frame.

[0093] Figure 8 FIG. shows a schematic block diagram of an exemplary device 800 that can be used to implement an embodiment of the present invention. Device 800 can be used to implement Figure 1 computing device 120. As shown in the figure, device 800 includes a central processing unit (CPU) 801, which can execute various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or computer program instructions loaded from a storage unit 808 into a random access memory (RAM) 803. In RAM 803, various programs and data required for the operation of device 800 can also be stored. CPU 801, ROM 802, and RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to bus 804.

[0094] Multiple components in device 800 are connected to I / O interface 805, including: an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, optical disc, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0095] The processing unit 801 executes the various methods and processes described above. For example, in some embodiments, any of the above processes may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the CPU 801, one or more steps of any of the processes described above may be performed. Alternatively, in other embodiments, the CPU 801 may be configured to execute any of the above processes by any other suitable means (e.g., by means of firmware).

[0096] The functions described above in this document may be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, the types of hardware logic components that may be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0097] In the context of this invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be either a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] Moreover, although the operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed to achieve the desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the invention. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation may also be implemented separately or in any suitable sub-combination in multiple implementations.

[0099] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A system for intraoral scanning, comprising: Intraoral scanner; as well as A computing device coupled to the intraoral scanner, configured to: Acquire a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which the implant is implanted from a scan of the oral cavity in which the implant is implanted by the intraoral scanner, wherein the three-dimensional geometric surface of the oral cavity is a three-dimensional geometric surface for a dental arch; Based on the acquired point cloud, identifying a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity, wherein the reliable data region is associated with a region where a deformation amount when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where a deformation amount when pressure is applied is greater than or equal to the deformation threshold; Selecting a point cloud of the reliable data area to store to form first scanning data; Acquire second scanning data of the three-dimensional geometric surface of the oral cavity where the implant and the scanning rod are implanted, by scanning the oral cavity where the scanning rod is implanted on the implant, using the intraoral scanner; registering the first scan data and the second scan data; as well as Based on the registration result, the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity is determined.

2. The system according to claim 1, wherein in order to identify the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, the computing device is configured to: Based on the color difference between the tooth area and the non-tooth area, on the point cloud in at least one frame of the acquired three-dimensional geometric surface of the oral cavity, marking the point cloud as a tooth point cloud or a non-tooth point cloud; Based on the marked tooth point cloud and non-tooth point cloud, identifying the tooth area and the non-tooth area; as well as The tooth region is identified as the reliable data region, and the non-tooth region is identified as the unreliable data region.

3. The system according to claim 1, wherein in order to identify the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, the computing device is configured to: Based on the deep learning model, on the point cloud in at least one frame of the acquired three-dimensional geometric surface of the oral cavity, assigning a corresponding classification to the point cloud to mark the point cloud as a tooth point cloud or a non-tooth point cloud; Based on the marked tooth point cloud and non-tooth point cloud, identifying the tooth area and the non-tooth area; as well as The tooth region is identified as the reliable data region, and the non-tooth region is identified as the unreliable data region.

4. The system according to claim 2 or 3, wherein in order to identify the tooth region and the non-tooth region based on the labeled tooth point cloud and the non-tooth point cloud, the computing device is configured to: In each of the at least one frame, the point cloud marked as the tooth point cloud is attributed to the tooth region, and the point cloud marked as the non-tooth point cloud is attributed to the non-tooth region; or In each of the at least one frame, a frame whose number ratio of the tooth point cloud is higher than or equal to a ratio threshold is regarded as a tooth frame, and a frame whose number ratio of the tooth point cloud is lower than the ratio threshold is regarded as a non-tooth frame.

5. The system according to claim 2 or 3, wherein the computing device is further configured to: Based on the acquired point cloud, a region of interest on the three-dimensional geometric surface of the oral cavity is identified, wherein the region of interest is associated with a region where the implant has been implanted, The at least one frame includes one or more frames falling within the region of interest.

6. The system according to claim 1, wherein in order to identify the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, the computing device is configured to: Based on the acquired point cloud, the free area and / or the edentulous area of ​​the three-dimensional geometric surface of the oral cavity are identified as the unreliable data area, and the area outside the free area and the edentulous area is identified as the reliable data area.

7. The system according to claim 6, wherein in order to identify the free area of ​​the three-dimensional geometric surface of the oral cavity, the computing device is configured to: determining a dental arch curve for the three-dimensional geometric surface of the oral cavity; Based on the determined dental arch curve, identifying a vertex and two end points of the dental arch curve; Based on the two endpoints and the vertex, determining a split point between each endpoint and the vertex; In the case where no teeth exist in the molar region between each of the end points and the segmentation point, the molar region is identified as a free area.

8. The system of claim 7, wherein in order to identify the edentulous area of ​​the three-dimensional geometric surface of the oral cavity, the computing device is configured to: Sampling is performed on the dental arch curve at certain intervals to obtain a series of orderly discrete points; In the case where there is no tooth near the given discrete point, identifying the given discrete point as a non-tooth point; connecting a plurality of continuous and ordered non-tooth points in a given area to form a connection line; as well as In the case where the length of the connecting line is greater than or equal to a length threshold, the given area is identified as the edentulous area.

9. A method for intraoral scanning, comprising: Scanning the oral cavity in which the implant is implanted with an intraoral scanner to obtain a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which the implant is implanted, wherein the three-dimensional geometric surface of the oral cavity is a three-dimensional geometric surface for a dental arch; Based on the acquired point cloud, identifying a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity, wherein the reliable data region is associated with a region where a deformation amount when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where a deformation amount when pressure is applied is greater than or equal to the deformation threshold; Selecting a point cloud of the reliable data area to store to form first scanning data; Acquire second scanning data of the three-dimensional geometric surface of the oral cavity where the implant and the scanning rod are implanted from scanning of the oral cavity where the scanning rod is implanted by the intraoral scanner; registering the first scan data and the second scan data; as well as Based on the registration result, the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity is obtained.

10. The method according to claim 9, wherein identifying the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity based on the acquired point cloud comprises: Based on the color difference between the tooth area and the non-tooth area, on the point cloud in at least one frame of the acquired three-dimensional geometric surface of the oral cavity, marking the point cloud as a tooth point cloud or a non-tooth point cloud; Based on the marked tooth point cloud and non-tooth point cloud, identifying the tooth area and the non-tooth area; as well as The tooth region is identified as the reliable data region, and the non-tooth region is identified as the unreliable data region.

11. The method according to claim 9, wherein identifying the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity based on the acquired point cloud comprises: Based on the deep learning model, on the point cloud in at least one frame of the acquired three-dimensional geometric surface of the oral cavity, assigning a corresponding classification to the point cloud to mark the point cloud as a tooth point cloud or a non-tooth point cloud; Based on the marked tooth point cloud and non-tooth point cloud, identifying the tooth area and the non-tooth area; as well as The tooth region is identified as the reliable data region, and the non-tooth region is identified as the unreliable data region.

12. The method according to claim 10 or 11, wherein identifying the tooth region and the non-tooth region based on the labeled tooth point cloud and the non-tooth point cloud comprises: In each of the at least one frame, the point cloud marked as the tooth point cloud is attributed to the tooth region, and the point cloud marked as the non-tooth point cloud is attributed to the non-tooth region; or In each of the at least one frame, a frame whose number ratio of the tooth point cloud is higher than or equal to a ratio threshold is regarded as a tooth frame, and a frame whose number ratio of the tooth point cloud is lower than the ratio threshold is regarded as a non-tooth frame.

13. The method according to claim 10 or 11, further comprising: Based on the acquired point cloud, a region of interest on the three-dimensional geometric surface of the oral cavity is identified, wherein the region of interest is associated with a region where the implant has been implanted, The at least one frame includes a plurality of frames falling within the region of interest.

14. The method according to claim 9, wherein based on the acquired point cloud, identifying the reliable data area and the unreliable data area of ​​the three-dimensional geometric surface of the oral cavity comprises: Based on the acquired point cloud, the free area and / or the edentulous area of ​​the three-dimensional geometric surface of the oral cavity are identified as the unreliable data area, and the area outside the free area and the edentulous area is identified as the reliable data area.

15. The method according to claim 14, wherein identifying the free area of ​​the three-dimensional geometric surface of the oral cavity comprises: determining a dental arch curve for the three-dimensional geometric surface of the oral cavity; Based on the acquired dental arch curve, identifying the vertex and two end points of the dental arch curve; Based on the two endpoints and the vertex, determining a split point between each endpoint and the vertex; In the case where no teeth exist in the molar region between each of the end points and the segmentation point, the molar region is identified as a free area.

16. The method according to claim 15, wherein identifying the edentulous area of ​​the three-dimensional geometric surface of the oral cavity comprises: Sampling is performed on the dental arch curve at certain intervals to obtain a series of orderly discrete points; In the case where there is no tooth near the given discrete point, identifying the given discrete point as a non-tooth point; connecting a plurality of continuous and ordered non-tooth points in a given area to form a connection line; as well as In the case where the length of the connecting line is greater than or equal to a length threshold, the given area is identified as the edentulous area.

17. A device for intraoral scanning, comprising: processor; as well as A memory storing executable instructions, which, in response to being executed by the processor, cause the apparatus to at least: Scanning the oral cavity in which the implant is implanted with an intraoral scanner to obtain a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which the implant is implanted, wherein the three-dimensional geometric surface of the oral cavity is a three-dimensional geometric surface for a dental arch; Based on the acquired point cloud, identifying a reliable data region and an unreliable data region of the three-dimensional geometric surface of the oral cavity, wherein the reliable data region is associated with a region where a deformation amount when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where a deformation amount when pressure is applied is greater than or equal to the deformation threshold; Selecting a point cloud of the reliable data area to store to form first scanning data; Acquire second scanning data of the three-dimensional geometric surface of the oral cavity where the implant and the scanning rod are implanted from scanning of the oral cavity where the scanning rod is implanted by the intraoral scanner; registering the first scan data and the second scan data; as well as Based on the registration result, the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity is obtained.

Images