Systems, methods, and devices for intraoral scanning

Abstract

Some embodiments of the present invention provide systems, methods, and devices for intraoral scanning. A computing device coupled with the intraoral scanner acquires a point cloud representing a three-dimensional geometric surface of the oral cavity where the implant has been implanted. The computing device then identifies a reliable data region and an unreliable data region of the geometric surface based on the acquired point cloud, where the reliable data region is associated with a region where a deformation amount occurring when applied is less than a deformation threshold, and where the unreliable data region is associated with a region where the deformation amount is less than the deformation threshold. And the unreliable data region is associated with a region in which the deformation quantity generated when the pressure is applied is greater than or equal to a deformation threshold value. Besides, the point cloud of the reliable data area is selected and stored to form first scanning data, second scanning data of the oral cavity three-dimensional geometric surface where the implant and the scanning rod are implanted are obtained, and registration is conducted on the first scanning data and the second scanning data; and determining position information of the scanning rod based on the registration result.

Description

Technical Field

[0001] Embodiments of the present invention generally relate to the field of dental implants, and more particularly, to systems, methods, and apparatus for intraoral scanning used in dental implants. Background Art

[0002] Intraoral scanning is the process of using specialized optical technology to digitally capture detailed three-dimensional (3D) images of the internal structures of the oral cavity, including the teeth, gums, and surrounding tissues. Unlike traditional dental impressions, which involve the use of physical molds or trays filled with impression material, intraoral scanning offers a non-invasive and comfortable option for patients and dental professionals.

[0003] During an intraoral scan, a dental professional uses a handheld device equipped with a camera and sensors (i.e., an intraoral scanner) 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 implanting teeth, an oral scanner is required for implant scanning. Implant scanning is implemented in two steps. In the first step, the dental arch data of the user exposing the implant is obtained. The three-dimensional data of the dental arch obtained will be used to define the three-dimensional shape of the crown or denture. The implant has been implanted in the dental arch before the first scan. In the second step, after the scanning rod is fastened to the implant, the three-dimensional data of the scanning rod including the dental arch is scanned to fit and calculate the relative position information of the scanning rod on the dental arch, which is used for base positioning. However, during the first and second scanning processes, some parts of the patient's mouth may change, resulting in a large registration error when the data from the two scans are fused or registered. Summary of the invention

[0005] According to an exemplary embodiment of the present invention, a system, method and apparatus 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 first scan data, it performs certain data screening processing and only uses reliable data. The system and method can isolate or remove unreliable data in the first scan, that is, avoid the registration error caused by the change of the data in the second scan compared with the data in the first scan at the same position, 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 a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity where the implant has been implanted from a scan of the oral cavity where the implant has been implanted by the intraoral scanner; 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, wherein the reliable data region is associated with a region where the deformation amount generated when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the deformation amount generated 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 scanning data; obtain second scanning data of the three-dimensional geometric surface of the oral cavity where the implant and the scanning rod have been implanted from a scan of the oral cavity where the scanning rod is implanted by the intraoral scanner; align the first scanning data and the second scanning data; and determine the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity based on the alignment result.

[0007] In some embodiments, in order to identify reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, the computing device is configured to: mark 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 three-dimensional geometric surface of the oral cavity based on the color difference between the tooth area and the non-tooth area; identify the tooth area and the non-tooth area based on the marked tooth point cloud and the non-tooth point cloud; and identify the tooth area as a reliable data area and the non-tooth area as an unreliable data area.

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

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

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

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

[0012] In some embodiments, in order to identify the free area of ​​the three-dimensional geometric surface of the oral cavity, the computing device is configured to: determine the dental arch curve for the three-dimensional geometric surface of the oral cavity; 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 point between each endpoint and the vertex; if there are no teeth in the molar area between each endpoint and the segmentation point, identify the molar area as a free area.

[0013] In some embodiments, in order to identify edentulous areas on the three-dimensional geometric surface of the oral cavity, the computing device is configured to: sample on the dental arch curve at certain intervals to obtain a series of ordered discrete points; identify the given discrete point as a non-tooth point when there is no tooth near the given discrete point; connect multiple continuous and ordered non-tooth points in a given area to form a connecting line; and identify the given area as an edentulous area when the length of the connecting line is greater than or equal to a length threshold.

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

[0015] In some embodiments, identifying reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity based on the acquired point cloud includes: marking 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 three-dimensional geometric surface of the oral cavity based on the color difference between the tooth area and the non-tooth area; identifying the tooth area and the non-tooth area based on the marked tooth point cloud and the non-tooth point cloud; and identifying the tooth area as a reliable data area and identifying the non-tooth area as an unreliable data area.

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

[0017] In some embodiments, identifying tooth areas and non-tooth areas based on labeled tooth point clouds and non-tooth point clouds includes: in each of at least one frame, attributing point clouds labeled as tooth point clouds to tooth areas, and attributing point clouds labeled as non-tooth point clouds to non-tooth areas; or in each of at least one frame, considering frames in which the ratio of the number of tooth point clouds is higher than or equal to a ratio threshold as tooth frames, and considering frames in which the ratio of the number of tooth point clouds is lower than the ratio threshold as non-tooth frames.

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

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

[0020] In some embodiments, identifying a free area of ​​a three-dimensional geometric surface of the oral cavity includes: 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 endpoints of the dental arch curve; based on the two endpoints and the vertex, determining a segmentation point between each endpoint and the vertex; and in the case where no teeth exist in the molar area between each endpoint and the segmentation point, identifying the molar area as a free area.

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

[0022] According to a third aspect of the present invention, there is provided a device for intraoral scanning, comprising: a processor; and a memory storing executable instructions, wherein in response to being executed by the processor, the instructions cause the device to at least: obtain a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity where the implant has been implanted from a scan of the oral cavity where the implant has been implanted by an intraoral scanner; identify reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, wherein the reliable data areas are associated with areas where a deformation amount less than a deformation threshold occurs when pressure is applied, and the unreliable data areas are associated with areas where a deformation amount greater than or equal to the deformation threshold occurs when pressure is applied; select the point cloud of the reliable data area for storage to form first scanning data; obtain second scanning data of the three-dimensional geometric surface of the oral cavity where the implant and the scanning rod have been implanted from a scan of the oral cavity where the scanning rod is implanted by the intraoral scanner; align the first scanning data and the second scanning data; and based on the alignment result, obtain position information of the scanning rod on the three-dimensional geometric surface of the oral cavity.

[0023] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended 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] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 An intraoral scanning system according to some example embodiments of the present invention is shown; Figure 2 A schematic diagram showing an implantation case according to some embodiments of the present invention; Figure 3A A method for intraoral scanning according to some embodiments of the present invention is shown; Figure 3B A schematic diagram showing a three-dimensional geometric surface model of an oral cavity based on the dental arch scanning in the first step according to some embodiments of the present invention; Figure 3CA schematic diagram showing a three-dimensional geometric surface model of an oral cavity after deleting unreliable data areas according to some embodiments of the present invention; Figure 3D A schematic diagram showing a model of a three-dimensional geometric surface of an oral cavity after registration of first scan data and second scan data according to some embodiments of the present invention; Figure 4 An exemplary method for identifying reliable data regions and unreliable data regions of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown; Figure 5 An exemplary method for identifying reliable data regions and unreliable data regions of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown; Figure 6 An exemplary method for identifying reliable data areas and unreliable data areas of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown; Fig. 7A shows an initial dental arch posture according to some embodiments of the present invention; Figure 7B The maximum visible area posture of the dental arch according to some embodiments of the present invention is shown; Figure 7C A schematic diagram of a dental arch model including a dental arch curve according to some embodiments of the present invention is shown; Fig.7D A schematic diagram showing a dental arch model with free areas identified according to some embodiments of the present invention; Fig. 7E A schematic diagram showing a dental arch model with edentulous areas identified according to some embodiments of the present invention; Figure 8 A block diagram of a computing device capable of implementing various embodiments of the present invention is shown. DETAILED DESCRIPTION

[0025] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0026] In the description of the embodiments of the present invention, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should 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 below.

[0027] 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 (e.g., a laptop computer, a desktop computer, etc.) coupled together. Such a communication link between the intraoral scanner 110 and the computing device 120 allows the captured images and control commands to be transferred 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 wireless fidelity (Wi-Fi). It should be understood that other communication implementations are also possible.

[0028] The intraoral scanner 110 can be a handheld device that a dentist (or dental assistant) can insert into a patient's mouth to capture images. As shown, the intraoral scanner 110 includes a tip 101 and a body 102. The tip 101 can be a pluggable component or can be integrated with the intraoral scanner 100. At the top of the tip 101, there is a camera or 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 (one or more) buttons to control the system 100, including but not limited to capturing images of the patient's mouth, starting or stopping scanning, selecting a mode of the system, or controlling the view of a 3D image of the oral structure.

[0029] 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 the scan data, such as a 3D representation of the patient's mouth, and UI elements, such as menus or icons. The 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 interacts with the UI elements using an input device 125, such as a mouse or keyboard connected to the computing device 120.

[0030] As mentioned above, when implanting teeth, an oral scanner is required for implant scanning. Implant scanning is implemented in two steps. In the first step, the dental arch data of the user exposing the implant (the area exposing the implant can also be called the cuff area) is obtained. The three-dimensional data of the dental arch obtained will be used to define the three-dimensional shape of the crown or denture. The implant has been implanted on the dental arch before the first scan. In the second step, after the scanning rod is fastened to the implant, the three-dimensional data of the scanning rod including the dental arch is scanned for fitting and calculating the relative position information of the scanning rod on the dental arch, which is used for abutment positioning.

[0031] At present, the mainstream scanning is basically performed according to the above two steps. In practice, after completing the first step of scanning, in order to avoid repeated scanning and reduce unnecessary scanning time, all or part of the scanning data of the first step is usually directly copied, and then the second step of scanning is completed.

[0032] However, during the first and second scanning steps, some parts of the patient's mouth may change, resulting in large registration errors when the two scanned data are fused or registered. For example, for implant areas where data changes occur, the registration results may be negatively affected during the implant scanning registration process, increasing the registration error and resulting in inaccurate data quality.

[0033] For example, when faced with implant cases with missing free ends, there will be large data changes that will cause large errors in the second scan data registration. Figure 2 An implant case with free end loss according to some embodiments of the present invention is shown.

[0034] exist Figure 2 In the implant case shown, the teeth, scanning rods or implants can be considered as rigid objects, and the positions of the two scans are always unchanged; at the same time, the gums around or between these rigid objects are relatively stable and can be considered as quasi-rigid, which will not cause too much scanning registration error. Other areas, mainly free areas (toothless areas), are prone to deformation.

[0035] exist Figure 2In the implant case shown, two scanning rods or implants 201, 202 are located at the dental arch position where the free end is missing on one side. The gums at the end of the scanning rod or implant 201 near the side are 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 many times, so it is difficult to ensure that the free end gums are in a consistent shape during the two scans. If the data of the first scan is directly substituted into the second scan and used for data registration, the shape of the nearby scanning rod or implant is likely to be deformed due to the inconsistency of the data of the free end gums during the two scans. Therefore, the fitting error of the scanning rod position increases, so that the crown or bridge designed in the end cannot completely match the patient's dental arch.

[0036] 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 a three-dimensional (3D) geometric surface of the oral cavity where the implant has been implanted from a scan of the oral cavity where the implant has been implanted 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 acquired point cloud, wherein the reliable data region is associated with a region where the deformation amount generated when pressure is applied is less than a deformation threshold, and the unreliable data region is associated with a region where the deformation amount generated 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. Next, the computing device obtains second scan data of the three-dimensional geometric surface of the oral cavity where the implant and the scan rod have been implanted from a scan of the oral cavity where the scan rod is implanted by the intraoral scanner, and registers the first scan data and the second scan data. Finally, the computing device determines the position information of the scan rod on the three-dimensional geometric surface of the oral cavity based on the registration result.

[0037] In this way, the computing device removes the data in areas where deformation may be greater before the second scanning step, and only uses the reliable data from the dental arch scan in the first step to align with the data from the implant scan in the second step. Therefore, the data alignment error is reduced, and the fitting error of the scanning rod position is also reduced. In this way, a crown or bridge can be designed that completely matches the patient's dental arch.

[0038] Figure 3A A method 300 for intraoral scanning according to some embodiments of the present invention is shown. The method 300 may be used in Figure 1 The intraoral scanning system 100 is implemented at the computing device 120 shown. For better understanding, reference will be made to Figure 1 Method 300 is described.

[0039] At 310, the computing device 120 uses the intraoral scanner 110 to obtain a point cloud representing the three-dimensional (3D) geometric surface of the oral cavity where the implant has been implanted. That is, the intraoral scanner 110 is to perform a first step of scanning the dental arch. During the intraoral scan, the dentist can use the intraoral scanner 120 to capture multiple 2D images of the inside of the oral cavity by moving the scanner to different areas. The computing device 120 receives the 2D images from the intraoral scanner 110, stitches the images together and converts them into a point cloud representing a model of the geometric surface of the oral cavity. Each point cloud may include spatial coordinates (e.g., X, Y, Z coordinates in a 3D space using Cartesian coordinates), intensity values, color information, and normal vectors. The point cloud may optionally include point density, point distribution, range data, scan position information, and other additional attributes.

[0040] Figure 3B A schematic diagram of a three-dimensional geometric surface model of an oral cavity based on a dental arch scan in the first step according to some embodiments of the present invention is shown. Figure 3B As shown, the model includes a tooth region 301, a gum region 302, and an implant region 303 obtained after the first scanning step.

[0041] At 320, the computing device 120 identifies reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity based on the acquired point cloud, wherein the reliable data area is associated with an area where the deformation amount when pressure is applied is less than the deformation threshold, and the unreliable data area is associated with an area where the deformation amount when pressure is applied is greater than or equal to the deformation threshold. Specifically, teeth are mainly composed of hard minerals, such as enamel (outermost layer), dentin and pulp. Enamel is one of the hardest biological tissues. Under normal circumstances, teeth are not easily deformed, so teeth can be used as an example of a reliable data area. Gum is a soft tissue rich in water and elastin fibers, with high flexibility and compressibility. Gum tissue is softer, relatively easier to deform, and can gradually return to its original state as the pressure disappears, so gum can be used as an example of an unreliable data area. Teeth and gums are just some examples of reliable data areas and unreliable data areas, respectively. Reliable data areas or unreliable data areas may change, for example, the toothless gum area between two teeth can also be considered as a reliable data area, while the free area can be considered as an unreliable data area. The deformation threshold can be set according to user needs.

[0042] At 330 , the computing device 120 selects a point cloud of a reliable data area to store to form first scan data.

[0043] In some embodiments, the reliable data area may include teeth and implants or cuffs as rigid objects, or gums around rigid objects, and gums between rigid objects, etc. The unreliable data area may include gums at free ends, etc., because there may be no rigid objects around the free ends, but in other embodiments, the range of the unreliable data area can be expanded to include all areas outside the tooth area.

[0044] Figure 3C FIG. 1 is a schematic diagram showing a three-dimensional geometric surface model of an oral cavity after deleting unreliable data areas according to some embodiments of the present invention. Figure 3C As shown, for example, the implant area has been removed as an unreliable data area because there is no rigid object support around the implant area, and the deformation may exceed the threshold when pressure is applied. The threshold can be set according to actual conditions, and the embodiment of the present invention does not limit the range of the threshold.

[0045] At 340 , the computing device 120 acquires second scan data of the three-dimensional geometric surface of the oral cavity where the implant and the scanbar are implanted from the intraoral scanner scanning the oral cavity where the scanbar is implanted on the implant. At 350 , the computing device 120 registers the first scan data with the second scan data.

[0046] In some embodiments, when performing registration, the computing device 120 can be based on feature matching. When matching feature points, the computing device 120 can look for points, lines or surfaces with obvious features, such as the edge of a tooth, a cusp, a specific mark of an implant or a scanning rod, etc. These feature points are unique and stable and can be used as key identifiers for data splicing. After determining the feature points, the computing device 120 can, for example, calculate the spatial relationship between feature points in different data sets, such as distance, angle, etc., and then find matching feature point pairs by comparing these relationships to determine the relative position and posture between the two data sets. Then, based on the matching feature point pairs, the computing device 120 translates, rotates, and other transformations on the second step scan data relative to the first step scan data, so that the feature points of the two data sets overlap as much as possible, thereby completing data splicing.

[0047] 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 scans into surface models respectively. Then, the computing device 120 searches for the best matching method between the two surface models through a specific algorithm to make the two surfaces fit as closely as possible in space. This may involve multiple transformations and attempts on one of the surface models to find the position and posture 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 containing the scanning rod scanned in the second step 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 can also use other methods to perform registration of the first scan data and the second scan data, such as using coordinate system matching.

[0048] At 350, the computing device 120 determines the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity based on the registration result. In other words, the position information of the scanning rod on the three-dimensional geometric surface of the oral cavity is determined based on the data of the three-dimensional geometric surface of the oral cavity after the two-step scanning fusion.

[0049] Figure 3D A schematic diagram of a model of a three-dimensional geometric surface of an oral cavity after registration of first scan data and second scan data according to some embodiments of the present invention is shown. Figure 3D As shown, based on the first scan data of the first step of scanning, the data of the scanning rod 304 is added. It can be seen that after the data registration, Figure 3C The removed implant area is precisely matched with the first scan data to be accurately registered in the appropriate position.

[0050] In method 300, when entering the second step of scanning, after copying the scan data of the first step, a certain data screening process is automatically performed, and reliable data is retained and unreliable data can be optionally eliminated, so as to ensure that the user continues to scan on the basis of the reliable data of the first step. Since the first scan data does not include the scan results of the area with large deformation when pressure is applied (i.e., the unreliable data area), this part of the unreliable data does not participate in the registration, thereby avoiding the registration error caused by the change of the data of the second scan compared with the data of the first scan at the same position (e.g., the unreliable data area, such as the free end, etc.), thereby improving the registration accuracy and scanning accuracy.

[0051] 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, some embodiments of the present invention provide multiple ways to perform the identification. The various ways described below can be used alone or in combination.

[0052] Figure 4 An exemplary method 400 for identifying reliable data regions and unreliable data regions of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown. The method 400 is Figure 3A An example implementation of step 320 in .

[0053] exist Figure 4 In the method 400 shown, in order to identify reliable data areas and unreliable data areas on the three-dimensional geometric surface of the oral cavity, the computing device 120 may distinguish between reliable data areas and unreliable data areas by color recognition, for example, distinguishing between tooth areas and non-tooth areas.

[0054] At 410, the computing device 120 may mark 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 three-dimensional geometric surface of the oral cavity based on the color difference between the tooth area and the non-tooth area. Specifically, the tooth area (high white component), the gum area (high red component), and other areas are marked on the point cloud.

[0055] At 420, based on the labeled tooth point cloud and non-tooth point cloud, the computing device 120 may 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 identifies 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 may attribute the point cloud labeled as the tooth point cloud to the tooth region and the point cloud labeled as the non-tooth point cloud to the non-tooth region in each frame of at least one frame. For example, based on the point cloud labeling, the computing device 120 may retain all point clouds labeled as tooth regions as reliable data; and remove all point clouds of non-tooth regions as unreliable data.

[0056] Alternatively, in some embodiments, in each frame of at least one frame, the computing device 120 regards the frame in which the ratio of the number of tooth point clouds is higher than or equal to the ratio threshold as a tooth frame, and regards the frame in which the ratio of the number of tooth point clouds is lower than the ratio threshold as a non-tooth frame. For example, based on the point cloud labeling, the computing device performs labeling information statistics for all single-frame three-dimensional point clouds scanned and acquired under different viewing angles. If the number of tooth point clouds is higher than or equal to a certain threshold, the three-dimensional point cloud of the frame is considered to be a tooth frame, otherwise the point cloud of the frame is considered to be a non-tooth frame. All tooth frame three-dimensional point clouds are retained as reliable data; all non-tooth frame three-dimensional point clouds are discarded as unreliable data. In some examples, the ratio threshold can be 75%, that is, if the ratio of the number of tooth point clouds exceeds 75%, the frame can be considered to be a tooth frame.

[0057] In some embodiments, the at least one frame includes every frame obtained by scanning. In some embodiments, the at least one frame includes only frames falling into a region of interest ROI, rather than all frames, and the region of interest may include an implant region.

[0058] Figure 5 An exemplary method 500 for identifying reliable data regions and unreliable data regions of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown. The method 500 is Figure 3A An example implementation of step 320 in .

[0059] exist Figure 5 In the method 500 shown, in order to identify reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity, the computing device 120 can identify reliable data areas and unreliable data areas based on a deep learning model, such as identifying tooth areas and non-tooth areas.

[0060] At 510 , the computing device 120 assigns corresponding classifications to the point clouds in at least one frame of the acquired three-dimensional geometric surface of the oral cavity based on the deep learning model, so as to mark the point clouds as tooth point clouds or non-tooth point clouds.

[0061] When classifying point cloud data based on a deep learning model, the computing device 120 can 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 normal, restored and implanted dental arch scan data. The three-dimensional point cloud data may include normal teeth, special teeth or scanned bodies, and these point cloud data are manually annotated. Experienced dentists can use manual annotation technology to perform semantic segmentation of the dental arch and assign appropriate classifications to each point in the point cloud. For example, the following labels can be assigned: gums are marked with a value of 0, normal teeth are marked with a value of 0, scanned bodies are marked with a value of 1, and prepared teeth are marked with a value of 2.

[0062] The labeled data can then 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 minimum-maximum normalization or mean normalization. Minimum-maximum normalization can scale the data to a fixed range, usually [0,1], while mean normalization adjusts the data to a mean of 0 and a standard deviation of 1. This helps to eliminate the impact 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 impact of translation and rotation.

[0063] Then, data enhancement can be performed. The purpose of data enhancement is to increase the amount of data in the training data set. In some embodiments, the computing device can combine data points corresponding to the prepared teeth or scanned volume with normal tooth data from a different point cloud. This is because there is less data containing the prepared teeth or 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 enhance the training data set. Applying the rotation matrix to each dental arch can provide various orientations for the dental arches. This enhances the robustness of the deep learning model.

[0064] Semantic segmentation can then be performed. After training, the deep learning model can be used to perform semantic segmentation, which can assign classifications to the data points of the point cloud. In some embodiments, the deep learning model can capture different levels of geometric features 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 with a large annotated dataset, normal teeth, gums, implants, scans, etc. can be identified from the point cloud. Through these operations, the computing device 120 can classify the point cloud into tooth point clouds and non-tooth point clouds based on the deep learning model.

[0065] At 520, the computing device 120 identifies the tooth region and the non-tooth region based on the marked tooth point cloud and the non-tooth point cloud. In box 530, the tooth region is identified as a reliable data region, and the non-tooth region is identified as an unreliable data region. For example, the computing device 120 can use a deep learning model to classify and mark the point cloud, and based on the point cloud marking, perform labeling information statistics for the three-dimensional point cloud of a single frame scanned and acquired under all different viewing angles. If the number of tooth point clouds is higher than or equal to a certain threshold, the frame of the three-dimensional point cloud is considered to be a tooth frame, otherwise the frame of the point cloud is considered to be a non-tooth frame.

[0066] 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 process, 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 data points with the same classification (for example, points marked as prepared teeth or scan rods), and then filter the connected domains with a predetermined size. After size filtering, the connected domains that meet the size standards can be identified as ROIs (for example, implants, prepared teeth, or scan bodies) to determine their exact locations. By automatically identifying the ROI, users can avoid manually selecting the area of ​​the ROI, avoid unnecessary user interaction, and provide a better user experience.

[0067] In addition, because unreliable data usually appears in the ROI area, the processing workload can be reduced by only deleting the frames corresponding to the ROI. Therefore, in some embodiments, the ROI can be identified first, and then the reliable data and unreliable data can be identified for the data in the ROI. That is to say, only the unreliable data area is identified in the ROI, because relatively large deformations will occur in the ROI (such as the implant area). For example, all single-frame point clouds that fall into the cuff area can be found out in units of single-frame three-dimensional point clouds. Taking these single-frame point clouds as units, the neighborhood of the single-frame three-dimensional point cloud is traversed outward step by step, 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 traversed non-tooth frame three-dimensional point clouds are eliminated as unreliable data; all remaining single-frame three-dimensional point clouds are reliable data and will be retained.

[0068] Figure 6 An exemplary method 600 for identifying reliable data regions and unreliable data regions of a three-dimensional geometric surface of an oral cavity according to some embodiments of the present invention is shown. The method 600 is Figure 3A An example implementation of step 320 in .

[0069] exist Figure 6 In the method 600 shown, in order to identify reliable data areas and unreliable data areas of the three-dimensional geometric surface of the oral cavity, at 610, the computing device 120 can identify the free area and / or the missing tooth area of ​​the three-dimensional geometric surface of the oral cavity as unreliable data areas, and the area outside the free area and the missing tooth area as a reliable data area.

[0070] The following will refer to 7A to 7E To explain how to identify the free area and missing teeth area of ​​the three-dimensional geometric surface of the oral cavity; Fig. 7A shows an initial dental arch posture according to some embodiments of the present invention; Figure 7B The maximum visible area posture of the dental arch according to some embodiments of the present invention is shown; Figure 7C A schematic diagram of a dental arch model including a dental arch curve according to some embodiments of the present invention is shown; Fig.7D A schematic diagram showing a dental arch model with free areas identified according to some embodiments of the present invention; and Fig. 7E A schematic diagram of a dental arch model with edentulous areas identified according to some embodiments of the present invention is shown.

[0071] In order to identify the free area of ​​the three-dimensional geometric surface of the oral cavity, the computing device may perform multiple operations. For example, a dental arch curve for the three-dimensional geometric surface of the oral cavity is determined. Then, based on the determined dental arch curve, the vertex and two endpoints of the dental arch curve are identified. Next, based on the two endpoints and the vertex, a segmentation point between each endpoint and the vertex is determined. Finally, in the case where there is no tooth in the molar area between each endpoint and the segmentation point, the molar area is identified as a free area.

[0072] In order to determine the dental arch curve of the three-dimensional geometric surface of the oral cavity, the dental arch is first placed in the position with the maximum visible area; then, within the maximum visible area of ​​the dental arch, only the three-dimensional points on the outer edge of the dental arch are retained, and these three-dimensional points are used to fit a parabola, namely the dental arch curve.

[0073] In order to place the dental arch in the position with the maximum visible area, first obtain all the three-dimensional point clouds of the first scan and perform a certain proportion of downsampling. Then, the dental arch contains the coordinate information of the three axes x, y, and z in the three-dimensional space. Take one of the axes as the orthographic axis, such as the z axis as the orthographic axis; the other two axes construct a plane, such as the xoy plane. Then, rotate the dental arch around the x-axis and y-axis respectively, and find the angle with the largest visible area on the orthographic axis, so as to convert the dental arch position to the maximum visible area.

[0074] Then, if Figure 7C As shown, within the maximum visible area of ​​the dental arch, only the three-dimensional points of the outer edge of the dental arch are retained, and a parabola, namely the dental arch curve, is fitted using these three-dimensional points. As shown by the parabola in the figure, the dental arch curve may include two endpoints 701 and a vertex 702.

[0075] like Fig.7D As shown, the dental arch curve may include two endpoints 701 and a vertex 702, and then based on the two endpoints and the vertex, a segmentation point 703 between each endpoint and the vertex is determined. The area between each endpoint and the segmentation point may be called a molar area. In the case where there is no tooth in the molar area, the molar area is identified as a free area, such as Fig.7D The area 704 shown is the free area, i.e., the area covered by the gray square. For example, a dividing line is drawn at 1 / 3 of the distance from the endpoints on both sides of the parabola to the vertex, and the area between the endpoints on the left and right sides of the parabola to the dividing line is defined as the molar area. If there are no teeth in the molar area, the molar area is a free area.

[0076] In order to identify the edentulous area on the three-dimensional geometric surface of the oral cavity, the computing device can perform multiple operations, such as sampling on the dental arch curve at a certain interval to obtain a series of ordered discrete points. Then, if there is no tooth near the given discrete point, the given discrete point is identified as a non-tooth point. Next, multiple continuous and ordered non-tooth points in a given area are connected to form a connecting line. Finally, if the length of the connecting line is greater than or equal to a length threshold, the given area is identified as a edentulous area. The length threshold can have different values ​​depending on the area where the teeth are located. In one example, the length threshold can be 5 mm, which is slightly less than the length of a tooth.

[0077] For example, sampling is performed at certain intervals on the dental arch curve to obtain a group of ordered discrete points. If there is no tooth near a discrete point, it is defined as a non-tooth point. All continuous non-tooth points are connected. If the length of the connecting line is greater than or equal to a certain threshold, the area is a missing tooth area. Fig. 7E As shown, region 705 is identified as the edentulous area, ie, the area defined by the black frame.

[0078] Figure 8 800 is a schematic block diagram of an example device 800 that can be used to implement an embodiment of the present invention. Figure 1 The computing device 120 of the present invention. As shown in the figure, the device 800 includes a central processing unit (CPU) 801, which can perform 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 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0079] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0080] The processing unit 801 performs 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, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on 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 perform any of the above processes in any other appropriate manner (e.g., by means of firmware).

[0081] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary 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 chip systems (SOCs), load programmable logic devices (CPLDs), and the like.

[0082] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be 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, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0084] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions 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; 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: Obtaining a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which the implant has been implanted from a scan of the oral cavity in which the implant has been implanted by an intraoral scanner; 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: Obtaining a point cloud representing a three-dimensional (3D) geometric surface of the oral cavity in which the implant has been implanted from a scan of the oral cavity in which the implant has been implanted by an intraoral scanner; 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