Identification of regions of interest during intraoral scans

Abstract

During an intraoral scanning session, a processing device receives a first intraoral image of a tooth site and identifies a candidate intraoral region of interest from the first intraoral image. The processing device receives a second intraoral image of the tooth site and verifies the first candidate intraoral region of interest as an intraoral region of interest based on a comparison of the second intraoral image to the first intraoral image. The processing device then provides an indication of the intra-oral region of interest during the intra-oral scan session.

Description

[0001] The present application is a divisional application of patent application number 202210530587.1 filed on May 7, 2015 and entitled “Identification of Regions of Interest During Intraoral Scanning”.

[0002] Related Applications

[0003] This application claims the benefit under 35 U.S.C. 119(e) of U.S. Provisional Application No. 61 / 990,004, filed May 7, 2014, which is incorporated herein by reference. Technical Field

[0004] Embodiments of the present invention relate to the field of intraoral scanning, and in particular to systems and methods for improving intraoral scanning results. Background Art

[0005] In oral rehabilitation procedures designed to implant a denture in the oral cavity, the tooth position where the prosthesis is to be implanted should in many cases be accurately measured and carefully studied so that a prosthesis such as, for example, a crown, denture or bridge can be appropriately designed and sized to fit the position. A good fit enables an appropriate transfer of mechanical stresses between the prosthesis and the jaw and prevents, for example, gum infection via the interface between the prosthesis and the tooth site.

[0006] Some procedures also require that a removable prosthesis be manufactured to replace more than one missing tooth, such as a partial or full denture, in which case the surface contours of the area where the teeth are missing need to be accurately reproduced so that the resulting prosthesis fits the edentulous area with uniform pressure on the soft tissue.

[0007] In some practices, the tooth site is prepared by a dentist, and a positive physical model of the tooth site is constructed using known methods. Alternatively, the tooth site can be scanned to provide 3D data of the tooth site. In either case, the virtual or real model of the tooth site is sent to a dental laboratory, which manufactures a prosthesis based on the model. However, if the model is defective or undefined in certain areas, or if the preparation is not optimally configured for receiving the prosthesis, the design of the prosthesis may not be optimal. For example, if the insertion path indicated by the preparation of a close-fitting base crown will cause the prosthesis to collide with adjacent teeth, the geometry of the base crown must be changed to avoid collision, which may cause the base crown design to be suboptimal. In addition, if the preparation area containing the finish line lacks clarity, the finish line may not be properly determined, so the lower edge of the base crown may not be properly designed. Indeed, in some cases, the model is rejected, and then the dentist rescans the tooth site or redoes the preparation so that a suitable prosthesis can be made.

[0008] In orthodontic procedures, it is important to provide a model of one or both jaws. In the case of virtually planning such orthodontic procedures, a virtual model of the oral cavity is also helpful. Such a virtual model can be obtained by directly scanning the oral cavity, or by making a physical model of the dentition and then scanning the model with a suitable scanner.

[0009] Therefore, in the process of oral rehabilitation and orthodontics, obtaining a three-dimensional (3D) model of the tooth sites in the mouth is the initial process performed. When the 3D model is a virtual model, the more complete and accurate the scan of the tooth sites is, the higher the quality of the virtual model is, and therefore the more optimal prosthesis or orthodontic treatment appliance can be designed. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The invention is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings.

[0011] Figure 1 One embodiment of a system for performing intraoral scans and generating virtual three-dimensional models of tooth sites is shown.

[0012] Figure 2A A flow chart illustrating a method of determining an intraoral region of interest during an intraoral scanning session according to an embodiment of the present invention.

[0013] Figure 2B A flow chart illustrating a method of setting an indication of an intra-oral region of interest according to an embodiment of the present invention.

[0014] Figure 3A A flow chart illustrating a method of setting data indications of defect scan data by an intra-oral scanning session according to an embodiment of the present invention.

[0015] Figure 3B A flow chart showing a method for setting data indication of an intra-oral region of interest according to an embodiment of the present invention.

[0016] Figure 3C A flow chart showing a method for performing intra-oral scanning according to an embodiment of the present invention.

[0017] Figure 4A A portion of an example dental arch is shown during an intraoral scanning session.

[0018] Figure 4B Shown during an intraoral scanning session after further intraoral images have been generated Figure 4A Example dental arch.

[0019] Figure 5A An example dental arch is shown with intraoral areas of interest shown.

[0020] Figure 5BAn example dental arch is shown with intra-oral areas of interest and indicators pointing thereto.

[0021] Figure 5C Another example dental arch is shown with intra-oral areas of interest and indicators pointing thereto.

[0022] Figure 6 Screen shot showing an intra-oral scanning application according to an embodiment of the present invention.

[0023] Figure 7 A block diagram of an example computing device is shown in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0024] A method and apparatus for improving the quality of scans, such as intraoral scans of a patient's dental sites, are described herein. During a scan session, a user of a scanner (e.g., a dentist) can generate multiple different images (also referred to as scans) of a dental site, a dental site model, or other object. The images can be discrete images (e.g., point-and-shoot images) or frames of a video (e.g., a continuous scan). These images may not capture all areas of a dental site and / or there may be areas where conflicting data exists between images. In embodiments described herein, such missing areas and / or conflicting areas can be identified as areas of interest. This identification can be performed during a scan session. Thus, shortly after a user of a scanner has generated more than one image, the user can be notified of areas of interest that should be rescanned. The user can then rescan the areas of interest during the scan session. This can facilitate a fast and accurate scanning session.

[0025] Additionally, indications or indicators of the areas of concern may be generated during the scanning session or after the scanning session is complete. These indications may indicate a classification related to the area of ​​concern, the severity of the area of ​​concern, the size of the area of ​​concern, and additional information. The indications may be visible in views of tooth sites or other scanned objects where the actual area of ​​concern is hidden. This may ensure that the user is aware of the area of ​​concern regardless of the current view.

[0026] The embodiments described herein are discussed with reference to intraoral scanners, intraoral images, intraoral scanning sessions, and the like. However, it should be understood that the embodiments are also applicable to other types of scanners in addition to intraoral scanners. The embodiments can be applied to any type of scanner that captures multiple images and stitches these images together to form a combined image or virtual model. For example, the embodiments can be applied to desktop model scanners, computed tomography (CT scanners), and the like. In addition, it should be understood that intraoral scanners or other scanners can be used to scan objects other than dental sites in the oral cavity. For example, the embodiments can be applied to scans performed on physical models of dental sites or any other objects. Therefore, the embodiments describing intraoral images should be understood to be generally applicable to any type of image generated by a scanner, the embodiments describing intraoral scanning sessions should be understood to be applicable to scanning sessions for any type of object, and the embodiments describing intraoral scanners should be understood to be generally applicable to many types of scanners.

[0027] Figure 1 An embodiment of a system 100 for performing intraoral scanning and / or generating a virtual three-dimensional model of a tooth site is shown. In one embodiment, the system 100 performs one or more operations described below in methods 200, 250, 300, 340, and / or 370. The system 100 includes a computing device 105 that can be coupled to a scanner 150 and / or a data store 110.

[0028] The computing device 105 may include a processing device, a memory, an auxiliary memory, one or more input devices (e.g., such as a keyboard, a mouse, an input board, etc.), one or more output devices (e.g., a display, a printer, etc.), and / or other hardware components. The computing device 105 may be connected to the data storage 110 directly or via a network. The network may be a local area network (LAN), a public wide area network (WAN) (e.g., the Internet), a private WAN (e.g., an intranet), or a combination thereof. In some embodiments, the computing device 105 may be integrated into the scanner 150 to improve performance and mobility.

[0029] Data storage 110 may be an internal data storage, or an external data storage connected to computing device 105 directly or via a network. Examples of network data storage include storage area networks (SANs), network attached storage (NASs), and storage services provided by cloud computing service providers. Data storage 110 may include a file system, a database, or other data storage arrangements.

[0030] In some embodiments, a scanner 150 for obtaining three-dimensional (3D) data of tooth sites in a patient's mouth is operably connected to the computing device 105. The scanner 150 may include a probe (e.g., a handheld probe) for optically capturing a three-dimensional structure (e.g., by confocal focusing of an array of light beams). An example of such a scanner 150 is manufactured by Align Technology, Inc. Intraoral digital scanner. Other examples of oral scanners include 1M TM TrueDefinition Scanner and Apollo DI intraoral scanner and CEREC AC intraoral scanner manufactured by.

[0031] The scanner 150 may be used to perform an intraoral scan of a patient's oral cavity. An intraoral scanning application 108 running on the computing device 105 may communicate with the scanner 150 to perform the intraoral scan. The result of the intraoral scan may be a series of intraoral images that are discretely generated (e.g., by pressing a "generate image" button of the scanner for each image). Alternatively, the result of the intraoral scan may be one or more videos of the patient's oral cavity. An operator may start recording a video at a first position in the oral cavity using the scanner 150, move the scanner 150 to a second position within the oral cavity while the video is being taken, and then stop recording the video. In some embodiments, recording may start automatically when the scanner identifies any tooth. The scanner 150 may send discrete intraoral images or intraoral videos (collectively referred to as intraoral image data 135) to the computing device 105. The computing device 105 may store the image data 135 in the data storage 110. Alternatively, the scanner 150 may be connected to another system that stores the image data in the data storage 110. In such an embodiment, the scanner 150 may not be connected to the computing device 105.

[0032] According to an example, a user (e.g., a doctor) can perform an intraoral scan on a patient. In doing so, the user can apply the scanner 150 to more than one intraoral position of the patient. The scan can be divided into more than one part. As an example, the part can include the patient's lower cheek area, the patient's lower tongue area, the patient's upper cheek area, the patient's upper tongue area, one or more prepared teeth of the patient (e.g., the patient's teeth to which a dental device such as a crown or an orthodontic device will be applied), one or more teeth in contact with the prepared teeth (e.g., a tooth that is not subject to the dental device itself but is located next to one or more teeth subject to the dental device, or a tooth that engages with one or more teeth subject to the dental device when the mouth is closed), and / or a patient's bite (e.g., a scan is performed with the patient's mouth closed, wherein the scan is directed to the interface area of ​​the patient's upper and lower teeth). Through this scanner application, the scanner 150 can provide image data (also referred to as scan data) 135 to the computing device 105. The image data 135 can include a 2D intraoral image and / or a 3D intraoral image. Such an image may be provided from the scanner to the computing device 105 in the form of one or more points (eg, one or more pixels and / or groups of pixels). For example, the scanner 150 may provide such a 3D image as one or more point clouds.

[0033] The manner in which the patient's mouth is scanned may depend on the procedure to be applied thereto. For example, if an upper or lower denture is to be created, a full scan of the mandibular or maxillary edentulous dental arch may be performed. Conversely, if a dental bridge is to be created, only a portion of the total dental arch may be scanned, including the edentulous area, adjacent adjacent teeth, and the opposing arch and dentition. Thus, the dentist may input the characteristics of the procedure to be performed into the intraoral scanning application 108. To this end, the dentist may select the procedure from a plurality of preset options on a drop-down menu or the like, by an icon or via any other suitable graphical input interface. Alternatively, the procedure characteristics may be input in any other suitable manner, such as by means of preset codes, symbols, or any other suitable manner, so that the intraoral scanning application 108 is appropriately programmed to recognize the selection made by the user.

[0034] As a non-limiting example, dental procedures can be roughly divided into oral rehabilitation (restoration) and orthodontic procedures, which are then further subdivided into specific forms of these procedures. In addition, dental procedures can include the identification and treatment of gum disease, sleep apnea, and intraoral conditions. The term oral rehabilitation procedure refers in particular to any procedure involving the design, manufacture, or installation of dental prostheses on the oral cavity and on the tooth sites in the oral cavity or on their real or virtual models, or on the design and preparation of the tooth sites for receiving such prostheses. The prosthesis can include any restoration, such as crowns, veneers, inlays, veneers, and bridges, as well as any other artificial partial or complete dentures. The term orthodontic procedure refers in particular to any process involving the design, manufacture, or installation of orthodontic elements on the oral cavity and on the tooth sites in the oral cavity or on their real or virtual models, or on the design and preparation of the tooth sites for receiving such orthodontic elements. These elements can be appliances including, but not limited to, brackets and wires, retainers, transparent aligners, or functional appliances.

[0035] The type of scanner being used may also be input into the intraoral scanning application 108, typically by the dentist selecting one from a number of options. If the scanner 150 being used is not recognized by the intraoral scanning application 108, the operating parameters of the scanner may still be input into it. For example, the optimal spacing between the scanner head and the surface being scanned may be set, as well as the capture area (and its shape) of the tooth surface that can be scanned at that distance. Alternatively, other suitable scanning parameters may be set.

[0036] The intraoral scanning application 108 may identify spatial relationships suitable for scanning the dental sites so that complete and accurate image data may be obtained for the procedure in question. The intraoral scanning application 108 may establish an optimal manner for scanning a target area of ​​the dental sites.

[0037] The intraoral scanning application 108 can identify or determine the scanning protocol by associating the type of scanner, its resolution, the capture area at the optimal spacing between the scanner head and the tooth surface with the target area, etc. For the point-and-shoot scanning mode, the scanning protocol includes a series of scanning sites that are spatially associated with the tooth surface of the target area. Preferably, the overlap of images or scans that can be obtained at adjacent scanning sites is designed into the scanning protocol to enable accurate image registration so that the intraoral images can be stitched together to provide a composite 3D virtual model. For the continuous scanning mode (video scanning), the scanning sites may not be determined. Instead, the doctor can start the scanner and continuously move the scanner inside the mouth to capture video of the target area from multiple different perspectives.

[0038] In one embodiment, the intraoral scanning application 108 includes an area of ​​interest (AOI) identification module 115, a marking module 118, and a model generation module 125. Alternatively, operations in more than one AOI identification module 115, marking module 118, and / or model generation module 125 may be combined into a single module and / or divided into multiple modules.

[0039] The AOI identification module 115 is responsible for identifying areas of interest (AOIs) from intraoral scan data (e.g., intraoral images) and / or virtual 3D models generated from the intraoral scan data. Such areas of interest may include voids (e.g., areas where scan data is missing), areas where scan data conflicts or defects (e.g., areas where overlapping surfaces of multiple intraoral images do not match), areas indicating foreign matter (e.g., studs, bridges, etc.), areas indicating tooth wear, areas indicating tooth decay, areas indicating gum recession, unclear gum lines, unclear patient bites, unclear margin lines (e.g., margin lines of more than one prepared tooth), and the like. The identified voids may be voids in the image surface. Examples of surface conflicts include double tooth incisors and / or other physiologically impossible tooth margins and / or bite line shifts. The AOI identification module 115 may analyze the patient image data 135 (e.g., 3D image point clouds) and / or more than one virtual 3D models of the patient when identifying AOIs, either alone and / or relative to the reference data 138. The analysis may involve direct analysis (e.g., pixel-based and / or other point-based analysis), application of machine learning, and / or application of image recognition. Such reference data 138 may include past data about the current patient (e.g., intraoral images and / or virtual 3D models), summary patient data, and / or teaching patient data, some or all of which may be stored in the data store 110.

[0040] The data about the current patient may include X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models corresponding to the patient visit during which the scanning occurred. The data about the current patient may additionally include past X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models of the patient (e.g., corresponding to past visits of the patient and / or the patient's dental records).

[0041] Aggregate patient data may include X-rays, 2D intraoral images, 3D intraoral images, 2D models and / or virtual 3D models about multiple patients. Multiple patients may include or not include current patients in this way. Aggregate patient data may be anonymized and / or adopted according to regional medical record privacy regulations (e.g., Health Insurance Portability and Accountability Act (HIPAA)). Aggregate patient data may include scanned data and / or other data corresponding to the classification discussed herein. Teaching patient data may include X-rays, 2D intraoral images, 3D intraoral images, 2D models, virtual 3D models and / or medical illustrations (e.g., medical illustration pictures and / or other images) adopted in a teaching environment. Teaching patient data may include volunteer data and / or cadaver data.

[0042] The AOI identification module 115 may analyze recent patient scan data in a patient visit during which scanning occurred (e.g., 3D image point clouds of one or more recent visits of the patient and / or virtual 3D models of one or more recent visits) relative to additional patient scan data in the form of data from earlier in the patient visit (e.g., 3D image point clouds of one or more earlier visits of the patient and / or virtual 3D models of one or more earlier visits). The AOI identification module 115 may additionally or alternatively analyze the patient scan data relative to reference data in the form of patient dental record data and / or data of the patient prior to the patient visit (e.g., one or more pre-visit 3D image point clouds of the patient and / or one or more pre-visit virtual 3D models). The AOI identification module 115 may additionally or alternatively analyze the patient scan data relative to aggregated patient data and / or teaching patient data.

[0043] In one example, the AOI identification module 115 can generate a first virtual model of the tooth site based on a first scanning session of the tooth site taken at a first time, and later generate a second virtual model of the tooth site based on a second scanning session of the tooth site taken at a second time. The AOI identification module 115 can then compare the first virtual model with the second virtual model to determine changes in the tooth site and identify AOIs that represent the changes.

[0044] Identifying areas of interest related to missing and / or defective scan data may involve the AOI identification module 115 performing a direct analysis, such as determining one or more pixels or other points that are missing from the patient scan data and / or one or more patient virtual 3D models. Identification of areas of interest related to missing and / or defective scan data may additionally or alternatively involve employing the aggregated patient data and / or the teaching patient data to determine that the patient scan data and / or the virtual 3D model is incomplete (e.g., has discontinuities) relative to what is indicated by the aggregated patient data and / or the teaching patient data.

[0045] The marking module 118 is responsible for determining how to present and / or mark the identified areas of interest. The marking module 118 can set indications or indicators related to scanning assistance, diagnosis assistance and / or foreign body identification assistance. Areas of interest can be determined and indicators of the areas of interest can be set during and / or after the intraoral scanning session. Such indications can be set before the construction of the intraoral virtual 3D model and / or when the intraoral virtual 3D model is not constructed. Alternatively, the indicators can be set after the construction of the intraoral virtual 3D model of the tooth site.

[0046] An example of a marking module 118 for setting indications regarding scanning assistance, diagnostic assistance, and / or foreign body identification assistance will now be discussed. The marking module 118 can set indications during and / or after an intraoral scanning session. Indications can be presented to a user (e.g., a physician) (e.g., via a user interface) in association with and / or separately from one or more depictions of the patient's teeth and / or gums (e.g., in association with one or more X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models of the patient). Presentation of indications associated with a depiction of the patient's teeth and / or gums can involve indications that are placed so that the indications are associated with corresponding portions of the teeth and / or gums. As an example, a diagnostic assistance indication regarding a broken tooth can be placed in order to identify the broken tooth.

[0047] The indication may be provided in the form of a mark, logo, outline, text, image and / or sound (e.g., in the form of speech). Such an outline may be placed (e.g., by outline fitting) so as to follow an existing tooth outline and / or gum outline. As an example, an outline corresponding to a tooth wear diagnostic auxiliary indication may be placed so as to follow the outline of a worn tooth. Such an outline may be placed relative to a missing tooth outline and / or gum outline (e.g., by outline extension) so as to follow the predicted path of the missing outline. As an example, an outline corresponding to missing tooth scan data may be placed so as to follow the predicted path of a missing tooth portion, or an outline corresponding to missing gum scan data may be placed so as to follow the predicted path of a missing gum portion.

[0048] When presenting an indication (e.g., a marker), the marking module 118 may perform one or more operations to display the indication appropriately. For example, an indication may be displayed in association with more than one depiction of teeth and / or gums (e.g., corresponding virtual 3D models), such an operation may be used to display a single indication, rather than, for example, multiple indications for a single AOI. Additionally, the processing logic may select a location in 3D space for placement of the indication.

[0049] In the case where the indication is displayed in association with the 3D teeth and / or gums depiction (e.g., in association with the virtual 3D model), the marking module 118 can divide the 3D space into cubes (e.g., voxels corresponding to more than one pixel of the 3D space). The marking module 118 can then consider the voxels associated with the voxels of the determined AOI and mark the voxels to indicate their corresponding indications (e.g., labels).

[0050] As an illustration, assume that the following two indications are brought to the user's attention through marking: a first indication regarding missing scan data and a second indication regarding dental caries. Regarding the indication regarding missing scan data, marking module 118 may consider pixels corresponding to missing scan data relative to a cube and mark each cube that contains more than one of those pixels. Marking module 118 may similarly perform the indication regarding dental caries.

[0051] When more than one cube is marked with respect to a given indication, the marking module 118 can cause the marked voxel to have only one receiving mark placed. In addition, the marking module 118 can select specific voxels that it determines are easy for the user to view. For example, such selection of voxels can take into account the integrity of the indication to be marked, and can strive to avoid multiple marks crowding a single cube, which can be avoided.

[0052] In placing the indication (e.g., marking), the marking module 118 may or may not consider factors other than seeking to avoid crowding. For example, the marking module 118 may consider available lighting, available angles, available zooms, available rotation axes, and / or other factors corresponding to the user's viewing of the teeth and / or gingival depiction (e.g., virtual 3D model), and may seek to optimize the placement of the indication (e.g., marking) for user viewing in view of these factors.

[0053] The marking module 118 can key the indication (e.g., by color, symbol, icon, size, text, and / or number). The index of the indication can be used to convey information about the indication. The information conveyed can include the classification of the AOI, the size of the AOI, and / or the importance level of the AOI. Therefore, different markings or indicators can be used to identify different types of AOIs. For example, a pink indicator can be used to indicate gum recession, and a white indicator can be used to indicate tooth wear. The marking module 118 can determine the classification, size, and / or importance level of the AOI, and then determine the color, symbol, icon, text, etc. of the indicator of the AOI based on the classification, size, and / or importance level.

[0054] With respect to conveying an index indicating a size, processing logic may employ more than one size threshold when implementing such an index pointing to a size. The source of the threshold may be set during a configuration operation (e.g., by a dental professional) and / or may be preset. The source of the threshold may be set by processing logic that accesses aggregated patient data and / or teaching patient data related to predictive indications regarding scan assistance (e.g., size information regarding portions of oral anatomy that are not imaged or poorly imaged due to missing and / or defective scan data) and the degree of success of a process outcome (e.g., the degree of success of the construction of an orthopedic device and / or the patient's fit of an orthopedic device). Larger sizes may indicate greater clinical importance. For example, a large blank may compromise the manufacture of an accurate orthodontic appliance, while a large blank may not. As an example, three thresholds may be set for areas of missing data and / or caries. During implementation, the indication falling within the largest threshold among the three size thresholds can be indexed as red and / or the number "1", the indication falling within the smallest threshold among the three size thresholds can be indexed as purple and / or the number "3", and / or the indication falling within the middle size of the three thresholds can be indexed as yellow and / or the number "2".

[0055] With respect to the index conveying the AOI classification, the indicator can identify the classification assigned to the intra-oral area of ​​interest. For example, the AOI can be classified as a blank, a change, a conflict, a foreign body, or another type of AOI. The AOI representing a change in the patient's dentition can represent tooth decay, gum recession, tooth wear, broken teeth, gum disease, gum staining, moles, lesions, tooth shadows, tooth staining, orthodontic improvement, orthodontic degradation, etc. Different criteria can be used to identify each such AOI classification. For example, a blank can be identified by a lack of image data, a conflict can be identified by a conflicting surface in the image data, a change can be identified based on a difference in the image data, and the like.

[0056] In the example of a surface conflict AOI, a first bite line component may correspond to one portion of the patient's teeth (e.g., the upper jaw or right side of the jaw). A second bite line component may correspond to another portion of the patient's teeth (e.g., the lower jaw or left side of the jaw). The AOI identification module 115 may compare the first bite line component to the second bite line component to check for deviations. Such deviations may be a hint that the patient moved his jaw during the scan (e.g., the patient moved his jaw midway between a doctor's scan of the lower jaw and a doctor's scan of the upper jaw or midway between a doctor's scan of the left side of the jaw and a doctor's scan of the right side of the jaw).

[0057] In performing bite line displacement surface conflict operations, the AOI identification module 115 may or may not consider a deviation threshold (e.g., set during a configuration operation). The marking module 118 may or may not set an indication of a found deviation if the found deviation meets the threshold, and may not set an indication otherwise. The intraoral scanning application 108 may or may not apply a corrective measure (e.g., averaging) to such found deviations that do not meet the threshold. Without considering such a threshold, the marking module 118 may set an indication of all found deviations. Although the foregoing is for ease of discussion, similar operations may be performed, for example, with respect to other surface conflict indications, with respect to bite line displacement surface conflicts.

[0058] The index may also include an importance rating, which will be referenced by Figure 3B Discuss in more detail.

[0059] When the scanning session is complete (e.g., all images of the tooth site have been captured), the model generation module 125 can generate a virtual 3D model of the scanned tooth site. The AOI identification module 115 and / or the marking module 118 can perform operations to identify AOIs and / or indicate such AOIs before or after generating the virtual 3D model.

[0060] To generate the virtual model, the model generation module 125 may register (i.e., "stitch" together) the intraoral images generated from the intraoral scanning session. In one embodiment, performing image registration includes capturing 3D data for various points of the surface in multiple images (views from cameras), and registering the images by computing transformations between the images. The images may then be integrated into a common reference frame by applying appropriate transformations to the points of each registered image. In one embodiment, processing logic performs image registration in the manner discussed in patent application 6,542,249 filed on July 20, 1999, which is incorporated herein by reference.

[0061] In one embodiment, image registration is performed for each pair of adjacent or overlapping intraoral images (e.g., each consecutive frame of an intraoral video). An image registration algorithm is performed to register two adjacent intraoral images, which essentially involves determining a transformation that aligns one image with the other. The registration between each pair of images can be accurate to 10-15 microns. Image registration can involve identifying multiple points in each image of the image pair (e.g., a point cloud), surface fitting the points of each image, and matching the points of two adjacent images using a local search around the points. For example, the model generation module 125 can match a point of one image with the nearest point interpolated on the surface of the other image, and iteratively minimize the distance between the matching points. The model generation module 125 can also find the optimal match of a curvature feature at a point of one image with a curvature feature at a point interpolated on the surface of the other image without iteration. The model generation module 125 can also find the optimal match of a rotated image point feature at a point of one image with a rotated image point feature at a point interpolated on the surface of the other image without iteration. Other techniques that may be used for image registration include, for example, techniques based on using other features to determine point-to-point correspondences and minimizing point-to-plane distances. Other image registration techniques may also be used.

[0062] Many image registration algorithms perform the fitting of surfaces to points in adjacent images, which can be done in a variety of ways. Parametric surfaces such as Bezier curves and B-spline surfaces are the most common, although other parametric curves can be used. A single surface patch can be fitted to all points of an image, or alternatively, separate surface patches can be fitted to any number of subsets of the points of an image. Separate surface patches can be fitted to have common boundaries, or they can be fitted to overlap. Surfaces or surface patches can be fitted to interpolate multiple points using a control point mesh that has the same number of points as the mesh of points to be fitted, or surfaces can be approximated using a control point mesh that has a smaller number of control points than the mesh of points to be fitted. Image registration algorithms can also employ a variety of matching techniques.

[0063] In one embodiment, the model generation module 125 can determine point matches between images, which can take the form of a two-dimensional (2D) curvature array. A local search for matching point features in corresponding surface patches of adjacent images is performed by calculating features at points sampled in an area around parametric similarity points. Once a set of corresponding points is determined between the surface patches of the two images, the determination of the transformation between the two sets of corresponding points in the two coordinate systems can be solved. Basically, the image registration algorithm can calculate a transformation between two adjacent images that will minimize the distance between a point on one surface and the nearest point to it found in an interpolated area on the surface of the other image used as a reference.

[0064] The model generation module 125 repeatedly performs image registration for all adjacent pairs of a series of intraoral image sequences to obtain a transformation between each pair of images, thereby registering each image with the previous image. The model generation module 125 then integrates all images into a single virtual 3D model by applying an appropriately determined transformation to each image. Each transformation can include rotations around one to three axes and translations in one to three planes.

[0065] In one embodiment, the intraoral scanning application 108 includes a training module 120. The training module 120 can provide training instructions to a user (e.g., a physician) regarding scanning techniques, and / or can highlight scanning-aid indications of the type discussed above that have occurred and / or recurred in the past for the user (e.g., scanning-aid indications corresponding to missing and / or defective scan data).

[0066] The training module 120 may consider scan data (e.g., 3D image point clouds) and / or one or more virtual 3D models generated by a scan performed by a user that resulted in a scan assistance indication relative to a training guidance data pool. The training guidance data pool may include scan data and / or one or more virtual 3D models (e.g., virtual 3D models that resulted in a scan assistance indication) relative to scan performances of multiple users (e.g., multiple doctors) and information describing scan technology changes that may have prevented and / or mitigated the situation that resulted in the scan assistance indication. The scan data and / or one or more virtual 3D models of the training guidance data pool may be anonymized and / or adopted in accordance with regional medical record privacy regulations. The training module 120 may match the scan data and / or one or more virtual 3D models generated by a scan performed by a user with the scan data and / or virtual 3D models of the training guidance data pool, access corresponding information describing the scan technology changes, and present (e.g., via a user interface) such scan change technology information to the user.

[0067] As an example, for scan data and / or one or more virtual 3D models that result in a double incisor edge scan aid indication (e.g., a scan aid indication corresponding to a particular scan angle), the training guidance data pool may include information indicating that a scan that has been performed with a specified angle change may be preventive and / or mitigating. For example, for scan data and / or one or more virtual 3D models that would result in a double incisor edge scan aid indication at a 35-degree to-surface angle instead of the desired 45-degree to-surface angle, such data may include information indicating that a ten-degree increase in the to-surface angle may be preventive and / or curative. In addition, for scan data and / or one or more virtual 3D models that would result in a double incisor edge scan aid indication at a 40-degree to-surface angle instead of the desired 45-degree to-surface angle, such data may include information indicating that a five-degree increase in the to-surface angle may be preventive and / or curative.

[0068] As another example, for scan data and / or one or more virtual 3D models that result in missing and / or defective scan data scan-aid indications (e.g., scan-aid indications corresponding to specific geometric areas, width-height dimensions, width-height ratios, or other dimensional relationships and / or oral locations), the training guidance data pool may include indicative information that scanning performed at one or more specified speeds, rhythms, angles, and / or distances from a surface may be preventive and / or mitigating.

[0069] The training module 120 may maintain a history of scan-assistance instructions for a particular user (e.g., a physician) over time (e.g., according to a user identifier). The training module 120 may use the history to highlight scan-assistance instructions that have occurred and / or recurred in the past for a particular user, to identify improvements and / or declines in the user's scanning technique over time, and / or to provide scanning technique training guidance that takes into account multiple scanning performances of the user. The training module 120 may or may not consider the training guidance data pool information that describes the changes in scanning technique as being preventative and / or mitigating.

[0070] As an example, the training module 120 may recognize that a particular user has received the same and / or similar indications in the past when providing an indication (e.g., a mark) regarding missing and / or defective scan data. For example, the training module 120 may determine that the user has received missing and / or defective scan data multiple times at a given location, and / or has received missing and / or defective scan data with a similar tenor multiple times (e.g., the user has repeatedly received instructions prompting to reselect the bilateral incisor edges that scan at an angle other than 45 degrees to the surface, albeit at different locations). In the event that the training module 120 finds that the current indication is the same and / or similar indication that has been received in the past, the training module 120 may act to highlight the indication (e.g., via a particular color).

[0071] As another example, with respect to a particular user and a bi-incisor edge scan aid indication, the training module 120 may determine, by considering such historical records and such training guidance data pool scanning technique change information, that the user's scanning technique is changing in a manner such that the scans employed are not yet so-called 45 degrees to the surface, but the scan angles employed are becoming closer and closer to 45 degrees to the surface over time. In doing so, the training module 120 may perform a match with the training guidance data pool information in view of the noted changes in the scan angle to the surface that resulted in the bi-incisor edge scan aid indication (e.g., matching older user data with pool data regarding a scan angle to the surface of 60 degrees, and matching newer user data with pool data regarding a scan angle to the surface of 40 degrees).

[0072] Figures 2A-3C A flow chart showing a method of performing an intraoral scan of a patient's dental sites. These methods may be performed by processing logic comprising hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., instructions executed on a processing device), or a combination thereof. In one embodiment, the processing logic corresponds to Figure 1 A computing device 105 (e.g., corresponding to a computing device 105 executing an intraoral scanning application 108).

[0073] Figure 2AA flow chart of a method 200 for determining an intraoral area of ​​interest during an intraoral scanning session according to an embodiment of the present invention is shown. At box 205 of method 200, the dentist begins an intraoral scanning session of a tooth site. The scanning session can be an intraoral scan of a portion or all of a mandibular or maxillary dental arch, or a partial or complete scan of both arches. The dentist can move the intraoral scanner to a first intraoral position and generate a first intraoral image. At box 210, processing logic receives the first intraoral image. The first intraoral image can be a discrete image (e.g., captured from a click-to-shoot mode) or a frame of an intraoral video (e.g., captured in a continuous scan or video mode). The intraoral image can be a three-dimensional (3D) image with a specific height, width, and depth. In some embodiments, an intraoral scanner is used that generates a 3D image with a depth of 12-14 mm, a height of 13-15 mm, and a width of 17-19 mm (e.g., a depth of 13 mm, a height of 14 mm, and a width of 18 mm in a specific embodiment).

[0074] At box 215, processing logic identifies one or more candidate intraoral regions of interest from the first intraoral image. In one embodiment, candidate intraoral regions of interest are identified by processing the intraoral image to identify voxels in the intraoral image that meet one or more criteria. Different criteria can be used to identify different categories of intraoral regions of interest. In one embodiment, missing image data a is used to identify AOIs that may be blank. For example, voxels at areas that are not captured by the intraoral image can be identified.

[0075] The processing logic can then determine one or more subsets of the identified voxels that are close to each other. Two voxels can be considered close to each other if they are within a threshold distance of each other. In one embodiment, two voxels are close if they are adjacent to each other. All voxels in the determined subset (e.g., all voxels connected directly or via other identified voxels) are grouped into volumes that constitute candidate regions of interest. One or more candidate regions of interest can be identified. If the criterion used to identify the voxels is missing data, the candidate intra-oral region of interest may represent a blank. Other criteria can be used to identify other categories of AOIs.

[0076] After the dentist generates the first intraoral image, he or she moves the intraoral scanner to a second position and generates the next intraoral image. At box 220, the processing logic receives the next intraoral image. At box 230, the processing logic compares the second intraoral image to the first intraoral image. In order to compare the intraoral images, the processing logic determines the alignment between the intraoral images based on geometric features shared by these intraoral images. Determining the alignment can include performing a transformation and / or rotation on one or both of the intraoral images and / or aligning intraoral areas of interest with each other. The calibrated image can be displayed by the processing logic. The processing logic can also compare the first intraoral image with a corresponding intraoral image taken during a previous scanning session. This can identify areas of concern, such as tooth wear, cavities, etc.

[0077] At box 232, processing logic determines whether there is a new candidate intraoral region of interest based on the next intraoral image. At box 235, processing logic determines whether the candidate intraoral region of interest from the first intraoral image is verified as an intraoral region of interest. This verification can be performed by testing the proximity and / or geometric conditions of the AOI relative to the surface of the latest intraoral image. In one embodiment, if the candidate intraoral region of interest from the intraoral image corresponds to a surface (e.g., a surface of a tooth site) from another intraoral image, it is excluded. Alternatively, if the candidate intraoral region of interest does not correspond to a surface area from another intraoral image, the candidate intraoral image can be verified as an actual intraoral region of interest. Therefore, the second intraoral image can be used to confirm or exclude the candidate intraoral region of interest from the first intraoral image. If a portion of the candidate intraoral region of interest from the first intraoral image corresponds to (e.g., aligns) a portion of the surface from the second intraoral image, the shape and / or size of the candidate intraoral region of interest can be modified. If no candidate intraoral region of interest is verified as an intraoral region of interest (e.g., if a subsequent intraoral image provides image data for the candidate intraoral region of interest), the method proceeds to box 245. Otherwise, the method continues to block 240 .

[0078] At box 240, the processing logic sets an indication of one or more verified intraoral regions of interest. In one embodiment, the processing logic interpolates the shape of the intraoral region of interest based on geometric features surrounding the intraoral region of interest and / or based on geometric features of the intraoral region of interest (if such features exist). For example, if the intraoral region of interest is blank, the area surrounding the blank can be used to interpolate the surface shape of the blank. The shape of the intraoral region of interest can be displayed in a manner that contrasts the surrounding image with the intraoral region of interest. For example, the teeth can be displayed in white, while the intraoral region of interest can be displayed in red, black, blue, green, or other colors. In addition or alternatively, an indicator such as a marker can be used as an indication of the intraoral region of interest. The indicator can be away from the intraoral region of interest, but includes a pointer to the intraoral region of interest. In many views of the tooth site, the intraoral region of interest can be hidden or obscured. However, the indicator can be visible in all or many such views. For example, the indicator can be visible in all views of the scanned tooth site unless the indicator is disabled. The indication of the set intraoral region of interest can be displayed while the intraoral scanning session is in progress.

[0079] At block 245, processing logic determines whether the intraoral scanning session is complete. If so, the method continues to block 248. If additional intraoral images are to be captured and processed, the method returns to block 220.

[0080] At block 248, a virtual 3D model of the tooth site is generated. The virtual model 3D may be generated as described above. The virtual 3D model may be a virtual or digital model showing the surface features of the target area. For a virtual 3D model of a complete dental arch, the arch width of the virtual 3D model may be accurate to within 200 microns of the arch width of the patient's actual dental arch.

[0081] Figure 2B A flow chart of a method 250 for setting indications for intraoral areas of interest according to an embodiment of the present invention is shown. Indications can be set during an intraoral scanning session (e.g., before a virtual model of a dental site is generated) or after the intraoral scanning session is completed (e.g., based on a virtual model of a dental site).

[0082] At box 255, an intraoral image of the tooth site is received. The intraoral image may be received from an intraoral scanner, from a data store, from another computing device, or from another source. The intraoral image may be from a single intraoral scanning session or from multiple intraoral scanning sessions. Additionally or alternatively, more than one virtual model of the tooth site may be received. The virtual model may be calculated based on intraoral images from past intraoral scanning sessions.

[0083] At block 260, processing logic identifies one or more voxels from the intraoral image and / or virtual model that meet a criterion. The criterion may be missing data, conflicting data, or data with a particular characteristic. In one embodiment, the intraoral image is first used to compute a virtual model, and the voxels are identified from the computed virtual model. In another embodiment, the voxels are identified from a separate intraoral image.

[0084] At block 265, one or more subsets of the identified voxels that are close to each other are identified. At block 270, the subsets are grouped into candidate intra-oral regions of interest.

[0085] At block 275 , processing logic determines whether the candidate region of interest is verified as an intra-oral region of interest. If any candidate intra-oral region of interest is verified as an actual intra-oral region of interest, the method continues to block 280 . Otherwise, the method proceeds to block 290 .

[0086] At block 280, a classification is determined for the intra-oral area of ​​interest. For example, the AOI may be classified as blank, conflicting surface, variation in tooth position, foreign matter, and others.

[0087] At block 285, processing logic sets an indication of the intraoral region of interest. The indication may include information identifying a classification of the determined intraoral region of interest. For example, an indicator may identify the intraoral region of interest as representing a blank or incomplete image data. Another indicator may identify the intraoral region of interest as representing an area with conflicting surfaces in different images.

[0088] In one embodiment, the indication includes a mark that is away from the intra-oral region of interest and points to or otherwise directs the viewer's attention to the intra-oral region of interest. The indication can be seen from a view of the tooth site in which the actual intra-oral region of interest is hidden. At box 290, the tooth site and any indication of the intra-oral region of interest are displayed.

[0089] Figure 3A A flow chart of a method 300 for developing scan-aid indications regarding missing and / or defective scan data is shown in accordance with an embodiment of the present invention. According to a first aspect, at box 305 of method 300, processing logic may receive scan data from an intraoral scanner. At box 310, processing logic may perform direct 3D point cloud analysis and / or direct virtual 3D model analysis. At box 315, processing logic may determine one or more pixels and / or other points that are missing from the patient scan data and / or from one or more patient virtual 3D models. At box 330, processing logic may develop one or more corresponding indications regarding the missing and / or defective scan data.

[0090] 3 , processing logic may also receive scan data from a scanner at block 305. At block 320, processing logic may consider the patient scan data and / or one or more patient virtual 3D models relative to entities indicated by the aggregated patient data and / or the teaching patient data to form complete and / or flawless data.

[0091] At block 325, processing logic may determine that the patient scan data and / or one or more patient virtual 3D models are incomplete. At block 330, processing logic may similarly formulate one or more corresponding indications regarding missing and / or defective scan data. Indications set by processing logic regarding diagnostic aids may include indications regarding tooth closure contacts, occlusal relationships, tooth fractures, tooth wear, gingival swelling, gingival depression, and / or caries. For ease of understanding, examples of performing processing logic operations in conjunction with setting diagnostic aid indications are now discussed.

[0092] Figure 3B A flow chart of a method 340 for performing indexing and displaying importance levels of indications conveying intra-oral areas of concern is shown in accordance with the examples discussed above and in conjunction with the present invention. Processing logic may assign importance levels to indications via processing in which the processing logic considers the indications in light of one or more patient case details and / or one or more level change weighting factors. It is noted that the one or more level change weighting factors themselves may or may not be associated with patient case details. Such patient case details may include ongoing procedures (e.g., preparation for application of a crown, preparation for application of an orthodontic device, treatment of suspected caries, and / or treatment of gingival swelling), patient age, patient gender, one or more previously performed procedures (e.g., the patient's last visit was for treatment of a crown affected by marginal leakage), and / or patient dental records.

[0093] At block 345 of method 340, processing logic may apply one or more weighting factors to each of one or more considered indications. The weighting factors may describe one or more specific attributes and indicate one or more level changes to be performed when such attributes are met. Level changes may include increasing the level of an indication by a given value, decreasing the level of an indication by a given value, specifying that an indication is considered to have a vertex level, and / or indicating that an indication is considered to have a bottom level. With respect to a given indication, processing logic may begin by assigning a specific starting level value (e.g., zero) to the indication. Then, processing logic may consider one or more weighting factors. After applying these weighting factors, processing logic may determine the final importance level of the indication. Processing logic may consider the final importance level of the indication relative to one or more other indications that have performed similar operations.

[0094] The source of the grade change weight factor considered by the processing logic can be set by the processing logic, which accesses aggregate patient data and / or teaching patient data that includes correlations between predictive indications regarding diagnostic aids (e.g., tooth wear and / or caries) and importance (e.g., the data may set forth importance information regarding each tooth wear and caries, conveying that caries is more important than tooth wear).

[0095] The processing logic may set a grade change weight factor so that scan data corresponding to a portion of teeth and / or gums that is greater than or equal to a certain size and that is missing and / or defective has an increased grade. For example, the weight factor for the grade change of scan data corresponding to a portion of teeth and / or gums that has certain size characteristics (e.g., the width size is greater than or equal to the height size, which is considered to be short and wide or square) is assigned a vertex grade or higher. Scan data corresponding to a portion of teeth and / or gums that has other size characteristics (e.g., the width size is less than the height size, which can be considered to be long and narrow) may be assigned a base grade or lower.

[0096] The source of the grade change weighting factor considered by the processing logic can be set by the processing logic, which accesses summary patient data and / or teaching patient data that includes correlations between predictive indications regarding foreign body identification assistance (e.g., regarding fillings and / or implants) and importance (e.g., the data may illustrate importance information about each filling and implant that conveys that fillers are more important than implants). By considering the correlations provided by such data - regarding scanning assistance, diagnostic assistance, or foreign body identification assistance - the processing logic can draw conclusions that it uses in setting the grade change weighting factors.

[0097] One or more weight factors for predictive indications may be set during a configuration operation or by an executed setting performed by processing logic. One such weight factor may specify that an indication associated with the periphery (e.g., a neighboring area) of one or more prepared teeth is ranked higher by a specified value. Another such weight factor may specify that an indication associated with insufficient tooth boundary line clarity is ranked higher by a specified value, or that such an indication should have a vertex grade. Yet another weight factor may specify that an indication associated with an unclear bite is ranked higher by a specific value. Yet another weight factor may specify that an indication associated with a shifted bite line is ranked higher by a specific value. Yet another weight factor may specify that an indication associated with a bilateral incisor edge is ranked higher by a specific value. Yet another weight factor may specify that an indication associated with insufficient gingival clarity is ranked higher by a first specified value when the current process does not involve gingival depression, but is ranked higher by a second specified value when the current process does involve gingival depression.

[0098] As an example, with respect to a first indication, processing logic may start by assigning an importance level of zero to the indication, determine the following scenarios: considering the first weight factor finds an indication that the indication's level is increased by three, considering the second weight factor finds an indication that the indication's level is decreased by one, and considering the third weight factor finds an indication that the indication's level is increased by five. Processing logic may then determine that the final importance level of the first indication is seven.

[0099] Furthermore, with respect to the second indication, the processing logic may start by assigning an importance level of zero to the indication, determine the following scenarios: considering the first weighting factor, finding an indication whose level is reduced by two, considering the second weighting factor, finding an indication whose level is reduced by three, and considering the third weighting factor, finding an indication whose level is increased by six. The processing logic may then determine that the final importance level of the second indication is one.

[0100] With respect to the third indication, the processing logic may again begin by assigning an importance level of zero. The processing logic may then find that consideration of the first weighting factor finds an indication that the level of the indication is increased by four, consideration of the second weighting factor finds an indication that the indication is considered to have vertex level, and consideration of the third weighting factor finds an indication that the level of the indication is decreased by eight. The processing logic may then determine that the final importance level of the third indication is vertex level. Thus, by indicating vertex level, the second weighting factor may be viewed as having outperformed the indications of the other two weighting factors. Note that, alternatively, if consideration of the second weighting factor finds an indication that the indication is considered to have bottom level, the second weighting factor will again outperform the other two weighting factors, but will be done in a manner that produces a final importance level of bottom level for the third indication.

[0101] At block 350, processing logic may determine a final importance level for each of the one or more considered indications. At block 355, processing logic may consider the final importance levels of the one or more indications relative to each other. Continuing with the above example, processing logic may consider three final importance levels relative to each other, namely, seven for the first indication, one for the second indication, and a peak level for the third indication. In doing so, processing logic may conclude that the third indication is the highest level, the first indication is the second highest level, and the second indication is the lowest level.

[0102] At box 360, processing logic may employ the final importance level in formulating a rescan order and / or a physician attention order. Processing logic may employ the importance level of the indication in a rescan order that suggests one or more indications (e.g., indications regarding scan assistance, such as indications regarding missing and / or defective scan data) and / or a physician attention order that suggests one or more indications (e.g., indications regarding diagnostic assistance and / or indications regarding foreign body identification assistance). In formulating such a rescan order and such a physician attention order, processing logic may suppress or not suppress one or more indications such that those indications are excluded from the rescan order or the physician attention order. As an example, processing logic may suppress indications having a level below a certain value (e.g., a value specified by a user and / or specified during configuration). As another example, processing logic may suppress indications having a bottom point level. Such suppression may be used to eliminate indications that are determined by processing logic to lack clinical significance (e.g., relative to a current process, such as preparation for application of a crown or orthopedic device). As an example, suppressed indications may include missing and / or defective scan data for which compensation can be performed (e.g., by using extrapolation and / or common data filling). Processing logic may convey the level of importance to those indications that are not suppressed by indexing the indicators (e.g., by color, symbol, icon, size, text, and / or numeric keypad).

[0103] Then, at block 365, processing logic may set one or more indexed indications (e.g., markers) in conjunction with the depiction of teeth and / or gums (e.g., 3D image or virtual 3D model) to communicate the position of each indication in the rescanning sequence and / or the physician's attention sequence. Processing logic may set the markers to include numbers, each number pointing to a specific portion of the depiction (e.g., 3D image or virtual 3D model) of the patient's teeth and / or gums, and communicating the sequential position of the oral cavity portion by number.

[0104] As an example, assume that there are four indications regarding scanning aids that can be selected by processing logic for inclusion in the rescan order - an indication corresponding to teeth 15 and 16 (ISO 3950 notation), an indication corresponding to the gingiva of tooth 32 (ISO 3950 notation), an indication corresponding to teeth 18 and 17 (ISO 3950 notation), and an indication corresponding to tooth 44 (ISO 3950 notation). Then assume that the indication corresponding to teeth 18 and 17 has a bottom point level, and that processing logic suppresses that indication, thereby removing it from the rescan order. Further assume that the rescan order of the remaining three indications is such that the indication corresponding to the gingiva of tooth 32 has the highest importance level of the remaining three and is first in the rescan order, the indication corresponding to teeth 15 and 16 has the second highest importance level of the remaining three and is second in the rescan order, and the indication corresponding to tooth 44 has the lowest importance level of the remaining three and is third in the rescan order. The flags may be set by processing logic such that the indication corresponding to the gums of tooth 32 is marked as "1", the indication corresponding to teeth 15 and 16 is marked as "2", and the indication corresponding to tooth 48 is marked as "3".

[0105] As another example, assume that there are three indications regarding diagnostic aids - an indication corresponding to fractures of teeth 11 and 21 (ISO 3950 notation), an indication corresponding to an occlusal relationship, and an indication corresponding to a gingival recess at the base of tooth 27 (ISO 3950 notation). Further assume that the physician attention order is such that the indication corresponding to the occlusal relationship has the highest importance level of the three, being first in the physician attention order, the indication corresponding to the fracture has the second highest importance level of the three, being second in the physician attention order, and the indication corresponding to the gingival recess has the lowest importance level of the three, being third in the physician attention order. Setting the flags by the processing logic may cause the indication corresponding to the occlusal relationship to be flagged as "1", the indication corresponding to the fracture to be flagged as "2", and the indication corresponding to the gingival recess to be flagged as "3".

[0106] As an additional example, assume that there are two indications regarding a foreign body identification aid - an indication corresponding to a filling in tooth 16 (ISO3950 notation) and an indication corresponding to a bridge at the intended anatomical location of teeth 35-37 (ISO3950 notation). Further assume that the physician attention order is such that the indication corresponding to the filling has the higher importance level of the two, being first in the physician attention order, and the indication corresponding to the bridge has the lower importance level of the two, being second in the physician attention order. Setting the flags by the processing logic may cause the indication corresponding to the filling to be flagged as "1" and the indication corresponding to the bridge to be flagged as "2".

[0107] Figure 3C A flowchart of a method 370 for using a 3D intraoral image when setting indications of intraoral areas of interest according to an embodiment of the present invention is shown. As described above, the processing logic can set indications regarding scanning assistance, diagnosis assistance, and / or foreign body identification assistance. As also described above, the processing logic can set such indications during application of a scanner by a user (e.g., a doctor), after application of a scanner by a user, and / or before construction of an intraoral virtual 3D model and / or when the intraoral virtual 3D model is not constructed. As discussed further above, in formulating such indications, the processing logic can analyze intraoral scan data (e.g., a 3D intraoral image, such as a 3D intraoral image provided by a scanner as a 3D image point cloud) and / or an intraoral virtual 3D model.

[0108] At block 372 of method 370, processing logic may analyze the one or more first 3D intraoral images to generate candidate intraoral regions of interest. Processing logic may perform analysis as discussed above with respect to AOI formulation, but consider using the analysis results for constructing candidate intraoral regions of interest rather than actual intraoral regions of interest. Processing logic may identify one or more points (e.g., one or more pixels and / or groups of pixels) corresponding to the candidate intraoral regions of interest.

[0109] At box 374, processing logic can identify one or more second 3D intraoral images that may be associated with the candidate intraoral area of ​​interest. The one or more second 3D intraoral images can be images that are close to one or more first 3D intraoral images in the mouth and / or share a geometric relationship with one or more first 3D intraoral images. The processing logic can determine this intraoral proximity by considering the intraoral position information provided by the scanner in combination with the 3D intraoral images. The scanner can generate such information through an incorporated accelerometer and / or other positioning hardware. The processing logic can determine this shared geometric relationship by identifying common surface features (e.g., common peak and / or valley surface features).

[0110] At block 376, the processing logic may combine the one or more first 3D intra-oral images and the second 3D intra-oral images for analysis. In doing so, the processing logic may or may not align the one or more first 3D intra-oral images with the one or more second 3D intra-oral images (e.g., the processing logic may align one or more point clouds corresponding to the one or more first 3D intra-oral images with one or more point clouds corresponding to the one or more second 3D intra-oral images).

[0111] At box 378, processing logic can determine whether the first 3D intraoral image merged with the second 3D intraoral image is consistent, inconsistent, or partially consistent with the candidate intraoral area of ​​interest. As an example, assume that the candidate indication relates to a scan-assisted indication regarding missing and / or defective scan data. Inconsistency may occur in the event that such merged analysis finds that there is no missing and / or defective scan data. As an example, such a situation may occur in which all of one or more points (e.g., one or more pixels and / or pixel groups) corresponding to missing scan data for the candidate indication are provided by one or more second 3D intraoral images.

[0112] Partial agreement may occur in cases where such merged analysis still finds missing and / or defective scan data but the trend of the missing and / or defective scan data changes (e.g., the currently found missing and / or defective scan data has a larger size, a smaller size, a different location, and / or a different morphology). As an example, this may occur in a case where some points (e.g., one or more pixels and / or pixel groups) of the missing scan data corresponding to the candidate indication are provided by one or more second 3D intra-oral images, while other points of the missing scan data are not provided by one or more second 3D intra-oral images, so that a smaller amount of missing and / or defective scan data is found.

[0113] A consensus may occur where such merged analysis finds the same trend (e.g., the same amount) of missing and / or defective scan data. As an example, a situation may occur where points (e.g., one or more pixels and / or groups of pixels) corresponding to missing scan data for a candidate indication are not provided by one or more second 3D intraoral images.

[0114] As another example, assume that the candidate indication relates to a diagnostic aid indication related to caries. Inconsistency may occur in the case where such merged analysis no longer finds caries. As an example, such a situation may occur in which further consideration of one or more second 3D intra-oral images - for example, further consideration of one or more points (e.g., one or more pixels and / or pixel groups) provided by one or more second 3D intra-oral images - results in a refined intra-oral vantage point in which caries are no longer found.

[0115] Partial agreement may occur where such a merged analysis still finds caries but the trend of the found caries changes (e.g., caries are now found to be smaller, larger, in different locations and / or in different morphology). As an example, such a situation may occur where further consideration of one or more second 3D intra-oral images - for example, further consideration of one or more points (e.g., one or more pixels and / or pixel groups) provided by one or more second 3D intra-oral images - produces a refined intra-oral vantage point where caries of different sizes and / or intra-oral locations are found.

[0116] Agreement may occur where such a merged analysis finds caries with the same trend as that found with the combined candidate indications. As an illustration, a situation may occur where further consideration of one or more second 3D intra-oral images - e.g., further consideration of one or more points (e.g., one or more pixels and / or groups of pixels) provided by one or more second 3D intra-oral images - does not refine the intra-oral vantage point in a manner that would result in a different size and / or intra-oral location of the found caries.

[0117] In the event that processing logic finds a match, processing logic may promote the candidate AOI to an indication of the type discussed above (i.e., a complete non-candidate AOI) and use as described above (e.g., provide an indication of the AOI to a user in the form of a marker). In the event that processing logic finds a partial match, processing logic may generate an AOI corresponding to a different trend discussed above (e.g., an AOI reflecting a smaller amount of missing data or an AOI reflecting a different form of caries) and use as discussed. In the event that processing logic finds a disagreement, processing logic may reject the candidate AOI.

[0118] In the event of a coincidence, processing logic may proceed to block 380, where processing logic promotes the candidate indication to a complete non-candidate indication, and adopts the promoted indication as described above. In the event of a partial coincidence, processing logic may proceed to block 382, ​​where processing logic generates an indication corresponding to a trend of partial coincidence, and adopts the indication as described above. In the event of an inconsistency, processing logic may proceed to block 384, where processing rejects the candidate indication.

[0119] The previously discussed aggregated patient data and / or teaching patient data can include many different types of data and / or depictions. Some examples of different aggregated patient data and / or teaching patient data and their use are now discussed.

[0120] The aggregated patient data and / or the teaching patient data may include a depiction of a gum line, bite, and / or bite line, and corresponding identifications thereof and / or indications of their clarity levels. Indications of an unclear gum line and / or unclear patient bite may involve processing logic that employs the aggregated patient data and / or the teaching patient data to identify patient scan data and / or virtual 3D models that include an unclearly imaged gum line or bite (e.g., deviates from the gum line or bite indicated by the aggregated and / or teaching data to have clarity in a manner indicated as unclear).

[0121] The aggregated patient data and / or the teaching patient data may additionally include depictions of margin lines, roots, and / or accumulations (e.g., blood and / or saliva accumulations) and their corresponding identifiers. Indications regarding unclear margin lines may involve processing logic that employs the aggregated patient data and / or the teaching patient data to identify that patient scan data and / or virtual 3D models constitute margin lines (e.g., the upper portion of a root receiving a denture crown). Additionally or alternatively, the processing logic may compare the margin lines of the considered patient scan data and / or one or more virtual 3D models of the patient with the margin lines of earlier visits and / or dental record data to detect margin line changes that indicate accumulation of blood, saliva, and / or similar accumulations on the margins. The processing logic may consider the found margin lines in conjunction with the found blood, saliva, and / or similar accumulations to locate situations where such accumulations appear near such margin lines, and conclude that such situations constitute unclear margin lines.

[0122] The aggregated patient data and / or didactic patient data may include depictions of incisor edges and / or bi-incisor edges and their corresponding identifications. Indications of bi-incisor edge surface conflicts may involve processing logic that employs the aggregated patient data and / or didactic patient data to identify that the patient scan data and / or virtual 3D model includes more than one incisor edge, and further infers that these incisor edges deviate from the incisor edges indicated by the aggregated and / or didactic data as being suitable incisor edges in a manner suggestive of bi-incisor edges.

[0123] Aggregated patient data and / or teaching patient data may include a depiction of tooth closure contact and / or occlusal relationship and its corresponding identification. Indications of tooth closure contact and / or occlusal relationship may involve processing logic that uses aggregated patient data and / or teaching patient data to identify patient scan data and / or virtual 3D models to form tooth closure contact and / or occlusal relationship. The processing logic may further approach one or more treatment goals (e.g., the desired degree of occlusion and / or desired occlusal relationship relative to one or more indicated teeth). Such goals may be set by a physician (e.g., via a user interface) and / or retrieved from an accessible data store. The processing logic may then compare the tooth closure contact and / or occlusal relationship of the patient scan data under consideration and / or one or more virtual 3D models of the patient with the tooth closure contact and / or occlusal relationship of earlier visits and / or dental record data to detect the degree of change (possibly zero) in the tooth closure contact and / or occlusal relationship. The processing logic may then compare the determined changes with the treatment goals and determine whether the changes result in meeting the treatment goals, or whether the changes are close to or deviate from the goals. The indication may include notification of whether the change is approaching, deviating from, meeting the treatment goal, or there is no change relative to the treatment goal.

[0124] As an example, the above-mentioned tooth closure contact can correspond to a situation where a physician indicates to processing logic a tooth closure contact treatment goal, the processing logic receives scan data depicting a patient's initial closure contact state, performs a dental procedure for potentially changing the closure contact state, and causes the processing logic to receive scan data depicting the closure contact state after the procedure. Through the processing discussed above, the physician can receive an indication as to whether his or her procedure has met the treatment goal, resulted in progress toward the treatment goal, resulted in deviation from the treatment goal, or resulted in no change relative to the treatment goal.

[0125] As another example, the above with respect to occlusion may correspond to a situation where a physician indicates an occlusion treatment goal to processing logic, the processing logic receives scan data depicting a patient's starting occlusion state, applies an orthopedic device to the patient, and has the patient return for a visit at a later date. Then, at a later date, the physician causes the processing logic to receive scan data depicting the occlusion state after the device application. Through the processing discussed above, the physician may receive an indication as to whether his or her device application has met the treatment goal, resulted in progress toward the treatment goal, resulted in a deviation from the treatment goal, or resulted in no change relative to the treatment goal.

[0126] Aggregate patient data and / or teach patient data can include the depiction of tooth fracture, tooth wear, gingival swelling, gingival depression and / or dental caries and its corresponding identification. Indication about tooth fracture, tooth wear, gingival swelling, gingival depression and / or dental caries can involve using aggregate patient data and / or teach patient data to identify patient scan data and / or more than one virtual 3D model to constitute the processing logic of tooth fracture, tooth wear, gingival swelling, gingival depression and / or dental caries. For example, processing logic can use aggregate patient data and / or teach patient data to identify teeth and / or gums in intraoral image and / or virtual 3D model. Then, processing logic can compare teeth and / or gums of intraoral image and / or virtual 3D model with teeth and / or gums of earlier intraoral image, virtual 3D model and / or dental record data to detect changes indicating tooth fracture, tooth wear, gingival swelling, gingival depression and / or dental caries. In performing such detection, the processing logic may or may not perform image analysis (e.g., considering the detected change to be indicative of a tooth fracture where the change has jagged edges) and / or reference patient data and / or teaching patient data (e.g., considering the detected change to be indicative of a tooth fracture where the change matches one or more items that constitute a breakage indicated by the patient data and / or teaching patient data).

[0127] Indications regarding tooth fracture and / or caries may involve processing logic performing a direct analysis. Processing logic may additionally or alternatively employ aggregated patient data and / or teaching patient data to identify that patient scan data and / or one or more virtual 3D models include regions constituting teeth. Processing logic may determine (e.g., via edge recognition) that one or more such teeth have one or more jagged edges. Processing logic may deem such jagged edges to indicate tooth fracture. Processing logic may determine (e.g., via shape recognition) that one or more such teeth have spots and / or pits. Processing logic may deem such spots and / or pits to indicate caries.

[0128] The instructions provided by the processing logic for assisting in foreign body identification may include instructions for fillers, implants and / or bridges. Aggregated patient data and / or teaching patient data may include depictions of fillers, implants and / or bridges and their corresponding identifications. Instructions for fillers, implants and / or bridges may involve processing logic that uses aggregated patient data and / or teaching patient data to identify patient scan data and / or virtual 3D models that constitute fillers, implants and / or bridges. Instructions for fillers, implants and / or bridges may involve processing logic comparing the patient scan data and / or virtual 3D models of more than one patient under consideration with early patient visit data, patient dental record data, and / or data from the patient's current patient visit before the visit. The processing logic may consider that an object that appears in the patient scan data and / or more than one virtual 3D models of the patient under consideration, but does not appear in the early patient visit data, patient dental record data and / or data from the patient's current patient visit before the visit may be a foreign body. For example, such a function may be realized from the perspective that a new object that appears in the patient's mouth is more likely to be a foreign body than a naturally occurring object. The processing logic may allow the physician to respond (eg, via a user interface) to such an indication by approving and / or disapproving that the object identified by the processing logic is a foreign body.

[0129] Figure 4A An example scanned portion of a dental arch 400 during an intraoral scanning session is shown. The dental arch 400 includes gums 404 and a plurality of teeth 410, 420. A plurality of intraoral images 425, 430, 435, 440 are taken of the patient's dental sites. Each of the intraoral images 425-440 can be generated by an intraoral scanner at a specific distance from the imaged tooth surface. At a specific distance, the intraoral images 425-440 have a specific scan area and scan depth. The shape and size of the scan area will generally depend on the scanner and are represented here by a rectangle. Each image can have its own reference coordinate system and origin. Each intraoral image can be generated by a scanner at a specific location (scanning site). The location and orientation of the scanning site can be selected so that the intraoral images are combined to cover the entire target area. Preferably, the scanning site is selected so that there is overlap between the intraoral images 425-440, as shown in the figure. Typically, depending on the capture characteristics of the scanner used, when different scanners are used for the same target area, the selected scanning site will be different. Thus, a scanner capable of scanning a larger tooth area per scan (e.g., having a larger field of view) will use fewer scanning sites than a scanner capable of only capturing 3D data of a relatively small tooth surface. Similarly, a scanner having a rectangular scanning grid (and thus providing a projected scanning area in the form of a corresponding rectangle) will typically have a different number and arrangement of scanning sites than a scanner having a circular or triangular scanning grid (which will provide a projected scanning area in the form of a corresponding circle or triangle, respectively).

[0130] The intra-oral regions of interest 448 and 447 have been calculated as discussed above. In the illustrated embodiment, the intra-oral regions of interest 447, 448 represent portions of the patient's dental sites for which image data is lacking.

[0131] Figure 4B A scanned portion of a dental arch 402 is shown as an update of the dental arch 400. Additional intraoral images 458, 459 have been obtained to provide image data corresponding to the intraoral regions of interest 447, 448. Therefore, the intraoral regions of interest 447, 448 are no longer displayed in the dental arch 402. Additional intraoral images 460, 462, 464, 466 have also been generated. These additional intraoral images 460-466 reveal the teeth 450, 452, 454, 456. New intraoral regions of interest 470, 472 are also determined based on the additional intraoral images 460-466. The physician may generate more intraoral images to resolve the intraoral regions of interest 470, 472 and provide data for the complete dental arch.

[0132] Figure 5A An example diagram of a dental arch 500 showing regions of interest is shown. An image of the dental arch 500 can be constructed from one or more intraoral scans prior to generating a virtual 3D model. Alternatively, an image of the dental arch 500 can be constructed from one or more scans of a physical model of the dental arch. The image of the dental arch 500 includes gums 509 and a plurality of teeth 505-508. Also shown in the image of the dental arch 500 are a plurality of regions of interest 509, 515, 525. These regions of interest 509, 515, 525 represent missing scan data that meet clinical importance criteria.

[0133] Figure 5B An example image of a dental arch 550 showing areas of interest and indications pointing to the areas of interest is shown. The image of the dental arch 550 can be constructed from more than one intraoral scan. Alternatively, the image of the dental arch 550 can be constructed from more than one scan of a physical model of the dental arch. The image of the dental arch 550 includes gums and a plurality of teeth. A plurality of areas of interest 562, 564, 566, 568, 570, 572 are also shown in the image of the dental arch 550. These areas of interest 562, 564, 566, 568, 570, 572 represent missing scan data that meet clinical importance criteria (e.g., the intraoral area of ​​interest is larger than a threshold size or has more than one dimension that violates a geometric criterion). However, some areas of interest 562, 570 are largely obscured in the example image of the dental arch 550. In addition, there are other areas of interest that are completely hidden. In order to ensure that the dentist is aware of these areas of interest, indicators such as markers are presented for each area of ​​interest. For example, the image of the dental arch 550 includes markers 552-559. These markings alert the dentist to areas of concern that should be noted regardless of the current view.

[0134] Figure 5C Another example image of a dental arch 575 showing areas of interest and indications pointing to the areas of interest is shown. The image of the dental arch 575 can be constructed from more than one intraoral scan. Alternatively, the image of the dental arch 575 can be constructed from more than one scan of a physical model of the dental arch. The image of the dental arch 575 includes gums and a plurality of teeth. A plurality of areas of interest 576-584 are also shown in the image of the dental arch 575. These areas of interest 576-584 represent tooth wear identified based on a comparison between an image and / or virtual 3D model generated on a first date and an image and / or virtual 3D model generated on a second date. However, some areas of interest 576, 578 are largely obscured in the example image of the dental arch 575. In order to ensure that the dentist is aware of these areas of interest, indicators such as markings are presented for each area of ​​interest. For example, the image of the dental arch 575 includes markings 586-594. These markings remind the dentist of the areas of interest that should be noted regardless of the current view.

[0135] Figure 6 An intraoral scanning application according to an embodiment of the present invention is shown (for example, Figure 1 6 . The screenshot 600 shows a plurality of menus 602, 604, 606 for performing various operations. The menu 602 provides icons that can be selected to perform global operations, such as changing settings, saving data, getting help, generating a virtual 3D model from the collected intraoral images, switching to a viewing mode, etc. The menu 604 provides icons for adjusting a view 607 of a scanned tooth site 608. The menu 604 may include icons for translating, zooming, rotating, etc. The view 607 of the scanned tooth site 608 includes a dental arch comprised of one or more previous intraoral images that have been registered and / or calibrated with respect to each other. The view 607 also includes an indication of the latest intraoral image 610 that has been added to the dental arch.

[0136] The dental arch includes a plurality of gaps based on incomplete scan data. Such gaps are a type of intraoral region of interest marked by markers 612-624. Menu 606 includes scanning instructions that enable the user to advance to the next scan, redo the last scan, rescan a segment, etc. The user can rescan more than one segment to provide scan data that can fill in the gaps marked by markers 612-624. This can ensure that the final virtual 3D model generated based on the intraoral image is of high quality.

[0137] Figure 7A graphical representation of a machine in the form of an example is shown with a computing device 700, which can execute a set of instructions for making the machine perform any one or more of the methods discussed herein. In an alternative embodiment, the machine can be connected (i.e., networked) to other machines in a local area network (LAN), an intranet, an extranet, or the Internet. The machine can operate with the authority of a server or client machine in a client-server network environment, or operate as a peer machine in a point-to-point (or distributed) network environment. The machine can be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a network device, a server, a network router, a switch or a bridge, or any machine capable of executing a set of instructions (continuous or other) to be performed by the machine to perform a prescribed action. In addition, although only a single machine is shown, the term "machine" will also be considered to include a set of any one or more machines (e.g., computers) that execute a set (or multiple sets) of instructions to perform the method discussed herein individually or jointly.

[0138] The example computing device 700 includes a processing device 702, a main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), etc.), a static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., a data storage device 728) that communicate with each other via a bus 708.

[0139] Processing device 702 represents one or more general-purpose processors, such as a microprocessor, a central processing unit, etc. More specifically, processing device 702 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor set implementing a combination of instructions. Processing device 702 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. Processing device 702 is configured to execute processing logic (instructions 726) for performing the operations and steps discussed herein.

[0140] The computing device 700 may also include a network interface device 722 for communicating with a network 764. The computing device 700 may also include a video display unit 710 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and a signal generating device 720 (e.g., a speaker).

[0141] The data storage device 728 may include a machine-readable storage medium (or more specifically, a non-transitory computer-readable storage medium) 724 having stored thereon one or more sets of instructions 726, the instructions 726 embodying any one or more of the methods or functions described herein. Non-transitory storage media refers to storage media other than carrier waves. The instructions 726 may also reside completely or at least partially in the main memory 704 and / or the processing device 702 during execution of the instructions by the computer device 700, the main memory 704 and the processing device 702 also constituting computer-readable storage media.

[0142] The computer readable storage medium 724 may also be used to store an intraoral scanning application 750, which may correspond to Figure 1 . The computer-readable storage medium 724 may also store a software library containing methods for the intraoral scanning application 750. Although the computer-readable storage medium 724 is shown as a single medium in the example embodiment, the term "computer-readable storage medium" should be considered to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store more than one instruction set. The term "computer-readable storage medium" will also be considered to include any medium other than a carrier wave that is capable of storing or encoding a set of instructions for execution by a machine and causing the machine to perform any one of the methods of the present invention. Therefore, the term "computer-readable storage medium" should be understood to include, but is not limited to, solid-state memory, and optical and magnetic media.

[0143] It should be understood that the above description is intended to be illustrative rather than restrictive. After reading and understanding the above description, many other embodiments will be apparent. Although embodiments of the present invention have been described with reference to specific exemplary embodiments, it will be appreciated that the present invention is not limited to the described embodiments, but can be implemented with modifications and changes within the spirit and scope of the appended claims. Therefore, the description and drawings are to be considered illustrative rather than restrictive. Therefore, the scope of the present invention should be determined with reference to the appended claims and the full scope of equivalents to which these claims claim rights.

Claims

1. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: receiving first intraoral scan data of a tooth site; receiving second intraoral scan data of the tooth site; comparing the second intra-oral scan data with the first intra-oral scan data; Based on the results of the comparison, identifying an intra-oral region of interest, wherein the intra-oral region of interest represents at least one of an unclear area, an area with conflicting scan data, an area with defective scan data, or an area indicating a foreign object; determining that the intraoral area of ​​interest requires rescanning; and An indication of the intra-oral region of interest to be rescanned is set.

2. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: receiving intraoral scan data of prepared teeth; generating a virtual three-dimensional model of the prepared tooth from the intraoral scan data; determining that the virtual three-dimensional model of the prepared tooth includes an intraoral region of interest representing an unclear margin line; generating an indication of the intraoral region of concern representing the unclear margin line; Together with the virtual three-dimensional model of the prepared tooth, the indication of the intra-oral region of interest representing the unclear margin line is presented.

3. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations for a caries detection method, the operations comprising: receiving first intra-oral scan data generated at a first time; analyzing the first intra-oral scan data to determine a first representation of caries from the first intra-oral scan data; receiving second intra-oral scan data generated at a second time; analyzing the second intra-oral scan data to determine a second representation of the caries from the second intra-oral scan data; comparing the second representation of the caries to the first representation of the caries; as well as The caries is tracked in time based on a difference between the second representation of the caries and the first representation of the caries.

4. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations for a caries detection method, the operations comprising: receiving first intra-oral scan data generated at a first time; receiving second intra-oral scan data generated at a second time; comparing the second intra-oral scan data with the first intra-oral scan data; Based on the comparison result, determining an intra-oral area of ​​interest, wherein the intra-oral area of ​​interest represents caries that has developed on the tooth between the first time and the second time; as well as An indication of the intra-oral area of ​​concern representing the caries on the tooth is output.

5. A system comprising: Memory; as well as a processing device operatively connected to the memory, the processing device: receiving first intra-oral scan data of a tooth site generated at a first time; receiving second intra-oral scan data of the tooth site generated at a second time; as well as Caries at the tooth site is tracked in time based on a difference between a first representation of the caries from the first intra-oral scan data and the second representation of the caries from the second intra-oral scan data.

6. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: Receiving intraoral scan data of tooth sites; Based on the intraoral scan data, identifying a plurality of intraoral regions of interest at the tooth sites; for each of the plurality of intra-oral regions of interest, determining whether the intra-oral region of interest satisfies a criterion, wherein more than one of the plurality of intra-oral regions of interest does not satisfy the criterion; generating a virtual three-dimensional model of the tooth site based on the intraoral scan data; and The virtual three-dimensional model of the tooth site is displayed together with those of the plurality of intra-oral regions of interest that satisfy the criteria, wherein the one or more intra-oral regions of interest that do not satisfy the criteria are not displayed.

7. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: Scan registration between multiple intraoral scans of a patient's dental sites; identifying the intra-oral region of interest by identifying candidate intra-oral regions of interest from the plurality of intra-oral scans and determining whether the identified candidate intra-oral regions of interest are verified as intra-oral regions of interest; identifying different categories of the intraoral areas of concern using different criteria; instructions to suppress specific intraoral areas of concern; as well as A view of the tooth sites and an indication of one or more of the intra-oral regions of interest is displayed to a display, wherein the displayed indication provides the identified category of each displayed intra-oral region of interest.

8. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: receiving a plurality of intraoral images of tooth sites; Performing image registration between the plurality of intraoral images identifying, using the processing device and based on the plurality of intraoral images that have been image-registered, a plurality of voxels that meet a criterion; determining a subset of the plurality of voxels that are proximal to one another; grouping the subset of the plurality of voxels into an intra-oral volume of interest; as well as With the processing device, an indication of the intra-oral volume of interest is generated, wherein the intra-oral area of ​​interest is hidden in more than one views of the tooth site, and wherein the indication of the intra-oral area of ​​interest is visible in the more than one views.

9. A system comprising: a scanner that generates a plurality of intraoral images of the dental sites; as well as a computing device operably connected to the scanner, the computing device: receiving the plurality of intra-oral images of the tooth sites; performing image registration between the plurality of intraoral images; identifying a plurality of voxels that meet a criterion based on the plurality of intraoral images that have been image-registered; determining a subset of the plurality of voxels that are proximal to one another; grouping the subset of the plurality of voxels into an intra-oral volume of interest; as well as An indication of the intra-oral volume of interest is generated, wherein the intra-oral area of ​​interest is hidden in more than one views of the tooth site, and wherein the indication of the intra-oral area of ​​interest is visible in the more than one views.

10. A method for detecting tooth wear during orthodontic treatment, comprising: receiving a first virtual three-dimensional model including one or more teeth of a patient, wherein the first virtual three-dimensional model is based on a first intra-oral scan of the patient obtained at a first time; receiving a second virtual three-dimensional model including the one or more teeth of the patient, wherein the second virtual three-dimensional model is based on a second intra-oral scan of the patient obtained at a second time; using a processing device, comparing the first virtual three-dimensional model with the second virtual three-dimensional model; determining a first difference between the first virtual three-dimensional model and the second virtual three-dimensional model at a first tooth site including a first tooth of the one or more teeth as a result of the comparison; determining whether the first difference comprises a first type of change to the first tooth indicative of tooth wear or a second type of change to the first tooth indicative of tooth movement; and In response to determining that the first difference includes the first type of change to the first tooth that is indicative of tooth wear, a first indicator of the tooth wear for the first tooth is generated.

11. A system comprising: Memory; as well as a processing device operatively connected to the memory, the processing device: receiving a first virtual three-dimensional model including one or more teeth of a patient, wherein the first virtual three-dimensional model is based on a first intra-oral scan of the patient obtained at a first time; receiving a second virtual three-dimensional model including the one or more teeth of the patient, wherein the second virtual three-dimensional model is based on a second intra-oral scan of the patient obtained at a second time; comparing the first virtual three-dimensional model with the second virtual three-dimensional model; determining a first difference between the first virtual three-dimensional model and the second virtual three-dimensional model at a first tooth site including a first tooth of the one or more teeth as a result of comparing the first virtual three-dimensional model to the second virtual three-dimensional model; determining whether the first difference comprises a first type of change to the first tooth indicative of tooth wear or a second type of change to the first tooth indicative of tooth movement; and In response to determining that the first difference includes the first type of change to the first tooth that is indicative of tooth wear, a first indicator of the tooth wear for the first tooth is generated.

12. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations comprising: receiving intraoral scan data generated by an intraoral scanner operated by a user; analyzing the scanning technique of the user based on the intraoral scan data; determining one or more improvements to the scanning technique; and Feedback is provided showing the one or more improvements to the scanning technique.

13. A computer-readable storage medium comprising instructions, which, when executed by a processing device, cause the processing device to perform operations for identifying an intra-oral area of ​​interest (AOI), the operations comprising: receiving or generating a first virtual three-dimensional model including teeth of a patient, wherein the first virtual three-dimensional model is based on a first intra-oral scan of the patient acquired at a first time; processing the first virtual three-dimensional model to identify the tooth in the first virtual three-dimensional model; receiving or generating a second virtual three-dimensional model including teeth of the patient, wherein the second virtual three-dimensional model is based on a second intra-oral scan of the patient acquired at a second time; processing the second virtual three-dimensional model to identify the tooth in the second virtual three-dimensional model; comparing, by the processing device, the first virtual three-dimensional model with the second virtual three-dimensional model; Determining a plurality of AOIs in the second virtual three-dimensional model representing at least one of tooth wear, broken teeth, tooth movement, gum recession, or gum swelling based on comparing the first virtual three-dimensional model with the second virtual three-dimensional model; comparing teeth identified in the first virtual three-dimensional model with teeth identified in the second virtual three-dimensional model; and Based on comparing the teeth identified in the first virtual three-dimensional model with the teeth identified in the second virtual three-dimensional model, one or more AOIs in the second virtual three-dimensional model representing tooth wear or broken teeth are determined.

14. A computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to perform operations for distinguishing between different types of intra-oral areas of interest (AOIs), the operations comprising: receiving or generating a first virtual three-dimensional model including one or more teeth of a patient, wherein the first virtual three-dimensional model is based on an image of the patient acquired at a first time; receiving or generating a second virtual three-dimensional model including one or more teeth of the patient, wherein the second virtual three-dimensional model is based on an image of the patient acquired at a second time; comparing, by the processing device, the first virtual three-dimensional model with the second virtual three-dimensional model; determining, based on the comparison, a first difference between the first virtual three-dimensional model and the second virtual three-dimensional model at a first tooth site of a first tooth including the one tooth; determining a first intra-oral AOI including the first tooth site associated with the first difference; determining whether the first difference includes a first type of change for the first tooth representing a first type of intra-oral AOI or a second type of change for the first tooth representing a second type of intra-oral AOI; and In response to determining that the first difference includes a first type of change for the first tooth representing a first type of intra-oral AOI, determining that the first intra-oral AOI is the first type of intra-oral AOI, and generating a first indicator of the first type of intra-oral AOI of the first tooth.

Images