A computer-readable recording medium that stores instructions for improving the results of intraoral scanning.

Abstract

A method for distinguishing between different types of oral cavity areas of interest (AOIs) is provided. [Solution] A method for distinguishing between multiple oral areas of interest (AOIs) of different types, comprising: receiving a first virtual three-dimensional (3D) model; receiving a second virtual 3D model; determining a first difference between the first virtual 3D model and the second virtual 3D model as a result of comparing the first virtual 3D model with the second virtual 3D model; determining a first oral AOI; determining whether the first difference includes a change indicative of the first type of oral AOI or a change indicative of the second type of oral AOI; determining that the first oral AOI is the first type of oral AOI; and generating a first indicator of the first type of oral AOI for a first tooth.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intraoral scanning, and more particularly to a computer-readable recording medium storing instructions for improving the results of intraoral scanning.

[0002] Related Applications This patent application claims the benefit of U.S. Provisional Patent Application No. 61 / 990,004, filed on May 7, 2014, under 35 U.S.C. § 119(e), and the above provisional patent application is hereby incorporated by reference into this application.

Background Art

[0003] In prosthodontic procedures designed to implant dental prostheses in the oral cavity, in order to properly design and dimension a prosthesis, such as a crown, denture or bridge, to fit in a predetermined position, the dental site where the prosthesis is to be implanted often has to be accurately measured and carefully considered. A good fit allows for proper transmission of mechanical stress between the prosthesis and the jaw, and can also prevent, for example, gum infection through the interface between the prosthesis and the dental site.

[0004] Depending on the procedure, it may be necessary to fabricate a removable prosthesis, such as a partial or complete denture, to replace one or more missing teeth. In this case, the resulting prosthesis needs to accurately reproduce the surface contour of the toothless area so that the pressure on the soft tissue is uniform and it fits over the entire edentulous area.

[0005] The dental site is prepared by the dentist, and a male physical model of the dental site may be constructed using known methods. Alternatively, the dental site may be scanned to provide 3D data of the dental site. In either case, a virtual or physical model of the dental site is sent to the dental laboratory, which fabricates the prosthesis based on the model. However, if the model is insufficient or ambiguous in certain areas, or if the preparation is not optimally configured to accept the prosthesis, the design of the prosthesis may be suboptimal. For example, if the insertion path included in the preparation for a tightly fitting coping results in collision of the prosthesis with an adjacent tooth, the geometric shape of the coping must be changed to avoid the collision, which may result in a suboptimal coping design. Furthermore, if the preparation area including the finished line lacks detail, the finished line may not be properly determined, and therefore the lower edge of the coping cannot be properly designed. In practice, in some situations, the model may be rejected, and the dentist may rescan the dental site or repeat the preparation so that a suitable prosthesis can be fabricated.

[0006] In orthodontic treatment, it may be important to provide a model of one or both jaws. If such orthodontic treatment is designed in a virtual manner, a virtual model of the oral cavity is also beneficial. Such a virtual model can be obtained by directly scanning the oral cavity, or by first forming a physical model of the dentition and then scanning that model using a suitable scanner.

[0007] Thus, in both prosthetic and orthodontic treatments, obtaining a three-dimensional (3D) model of the dental site in the oral cavity is the first step taken. If the 3D model is a virtual model, the more complete and accurate the scanning of the dental site, the higher the quality of the virtual model and, consequently, the greater the ability to design the optimal prosthesis or one or more orthodontic appliances.

[0008] The present invention is illustrated in the figures in the attached drawings as an example, not an limitation. [Brief explanation of the drawing]

[0009] [Figure 1] This is one embodiment of a system for performing intraoral scanning and forming a virtual three-dimensional model of the dental area. [Figure 2A] This is a flowchart of a method for determining an oral region of interest during an intraoral scanning session according to an embodiment of the present invention. [Figure 2B] This is a flowchart of a method for setting indicators in areas of interest within the oral cavity according to an embodiment of the present invention. [Figure 3A] This is a flowchart of a method for providing data indicators of defective scanning data from an intraoral scanning session, according to an embodiment of the present invention. [Figure 3B] This is a flowchart of a method for providing data indicators for oral areas of interest according to an embodiment of the present invention. [Figure 3C] This is a flowchart of a method for performing an intraoral scan according to an embodiment of the present invention. [Figure 4A] This is a diagram of an exemplary portion of the dental arch during an intraoral scanning session. [Figure 4B] Figure 4A shows an example of the dental arch during an intraoral scanning session after further intraoral image generation. [Figure 5A] This is a diagram of an exemplary dental arch, illustrating the oral region of interest. [Figure 5B] This diagram shows an exemplary dental arch representing an oral region of interest, and an indicator that points to that region. [Figure 5C] Another diagram shows an exemplary dental arch representing an oral region of interest, and an indicator that points to the oral region of interest. [Figure 6] This is a screenshot of an intraoral scanning application according to an embodiment of the present invention. [Figure 7] This is a block diagram of an exemplary computing device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0010] This specification describes methods and apparatus for improving the quality of scans, such as intraoral scans, performed on the dental areas of a patient. During a scanning session, the scanner user (e.g., a dentist) can generate multiple different images (also called scans), models of the dental areas, or other objects of interest of the dental area. These images may be individual images (e.g., auto-exposed images) or frames from a video (e.g., continuous scan). These images may not capture the entire area of ​​the dental area, and / or there may be collision data between multiple images. In embodiments described herein, such missing areas and / or collision areas may be identified as areas of interest. This identification may be performed during the scanning session. Thus, immediately after the scanner user has generated one or more images, the user can be notified of areas of interest that need to be rescanned. The user may then rescan the areas of interest during the scanning session. This makes the scanning session easy, fast, and accurate.

[0011] Furthermore, indicators or metrics for the area of ​​interest can be generated during or after a scanning session. These metrics may indicate the classification associated with the area of ​​interest, its severity, its size, and additional information. These metrics may be visible when viewing the dental area or other scanned objects that conceal the actual area of ​​interest. This ensures that the user is aware of the area of ​​interest regardless of their current field of view.

[0012] The embodiments described herein discuss intraoral scanners, intraoral images, intraoral scanning sessions, etc. However, it should be understood that these embodiments can also be applied to types of scanners other than intraoral scanners. The embodiments can be applied to any type of scanner that takes multiple images and stitches these images together to form a composite image or virtual model. For example, the embodiments can be applied to desktop model scanners, computed tomography (CT) scanners, etc. Furthermore, it should be understood that intraoral scanners or other scanners may 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 object. Accordingly, embodiments describing intraoral images should be understood as being broadly applicable to any type of image generated by the scanner, embodiments describing intraoral scanning sessions should be understood as being applicable to scanning sessions concerning any type of object, and embodiments describing intraoral scanners should be understood as being broadly applicable to many types of scanners.

[0013] Figure 1 shows one embodiment of system 100 for performing intraoral scanning and / or generating a virtual three-dimensional model of a dental site. In one embodiment, system 100 performs one or more operations described later in methods 200, 250, 300, 340 and / or 370. System 100 includes a computing device 105 which may be connected to a scanner 150 and / or a data store 110.

[0014] The computing device 105 may include a processing device, memory, auxiliary storage, one or more input devices (e.g., keyboard, mouse, tablet, etc.), one or more output devices (e.g., display, printer, etc.), and / or other hardware components. The computing device 105 may be connected to the data store 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 personal WAN (e.g., an intranet), or a combination thereof. In some embodiments, the computing device 105 may be integrated with the scanner 150 to improve performance and portability.

[0015] The datastore 110 may be an internal datastore or an external datastore connected to the computing device 105 directly or via a network. Examples of network datastores include storage area networks (SANs), network-attached storage (NAS), and storage services provided by cloud computing service providers. The datastore 110 may include file systems, databases, or other data storage configurations.

[0016] In some embodiments, a scanner 150 for obtaining three-dimensional (3D) data of dental sites within a patient's oral cavity is operably connected to a computing device 105. The scanner 150 may include a probe (e.g., a handheld probe) for optically capturing the three-dimensional structure (e.g., by confocal focusing of an array of multiple rays). An example of such a scanner 150 is the iTero® intraoral digital scanner manufactured by Align Technology, Inc. Other examples of intraoral scanners include the 3M® True Definition Scanner and the Apollo DI intraoral scanner and CEREC AC intraoral scanner manufactured by Sirona®.

[0017] The scanner 150 can be used to perform an intraoral scan of the patient's oral cavity. An intraoral scanning application 108 running on the computing device 105 can communicate with the scanner 150 to enable the intraoral scan. The result of the intraoral scan may be a sequence of separately generated intraoral images (for example, by pressing the scanner's "generate image" button for each image). Alternatively, the result of the intraoral scan may be one or more videos of the patient's oral cavity. The operator may start recording a video using the scanner 150 at a first position in the oral cavity, move the scanner 150 to a second position in the oral cavity while recording the video, and then stop recording the video. In some embodiments, recording may start automatically when the scanner identifies each tooth. The scanner 150 may transmit separate 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 store 110. Alternatively, the scanner 150 may be connected to another system that stores image data in the data store 110. In such an embodiment, the scanner 150 does not need to be connected to the computing device 105.

[0018] According to one example, a user (e.g., a dentist) may subject a patient to an intraoral scan. When performing this, the user may apply the scanner 150 to the intraoral position of one or more patients. The scan can be divided into one or more segments. As an example, the segments may include the submandibular region of the patient, the sublingual region of the patient, the supramaxillary region of the patient, the supralingual region of the patient, one or more prepared teeth of the patient (e.g., teeth of a patient to which a dental device such as a crown or an orthodontic alignment device will be applied), one or more teeth in contact with the prepared teeth (e.g., teeth that are not themselves to be applied with a dental device but are located adjacent to one or more of the above-described teeth or interfere with one or more of the above-described teeth when the mouth is closed), and / or the patient's occlusion (e.g., a scan performed with the scanner oriented towards the interface region between the upper and lower teeth of the patient with the patient's mouth closed). With such a scanning application, the scanner 150 can also provide image data 135 (also referred to as scan data). The image data 135 may include 2D intraoral images and / or 3D intraoral images. Such images can be provided from the scanner to the computing device 105 in the form of one or more points (e.g., 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 sets.

[0019] The method of scanning the patient's oral cavity may depend on the procedure to be applied to the oral cavity. For example, when forming an upper or lower denture, a complete scan of the edentulous mandibular or maxillary arch may be performed. In contrast, when forming a bridge, only a portion of the entire jaw arch, including the edentulous area, the adjacent abutting teeth, and the opposing jaw arch and dentition, may be scanned. Accordingly, the dentist may input identifying information of the procedure to be performed into the intraoral scanning application 108. For this purpose, the dentist may select the procedure from a number of pre-configured options on a drop-down menu, from icons, or via any other preferred image input interface. Alternatively, identifying information of the procedure may be entered in any other preferred format, for example, using a pre-configured code, symbolism, or any other preferred format, where the intraoral scanning application 108 is suitably programmed to recognize the selection made by the user.

[0020] As a non-limiting example, dental procedures can be broadly divided into dental prosthetic (restorative) procedures and orthodontic procedures, and further divided into specific forms of these procedures. Furthermore, dental procedures may include the identification and treatment of gingival diseases, sleep apnea, and oral conditions. The term "prosthodontic procedure" specifically refers to any procedure relating to the oral cavity, which involves the design, fabrication, or placement of dental prostheses or their physical or virtual models in dental sites within the oral cavity, or which involves the design and preparation of dental sites to receive such prostheses. Examples of prostheses include any restoration such as crowns, inlays, onlays, and bridges, as well as any other artificial partial or complete dentures. The term "orthodontic procedure" specifically refers to any procedure relating to the oral cavity, including the design, fabrication, or placement of orthodontic elements or their physical or virtual models in dental sites within the oral cavity, or the design and preparation of dental sites to receive such orthodontic elements. These elements may include, but are not limited to, brackets and wires, retainers, clear alignment appliances, or functional appliances.

[0021] The type of scanner used may also typically be input into the intraoral scanning application 108 by a dentist selecting one of a plurality of options. Even if the intraoral scanning application 108 cannot recognize the scanner 150 being used, the operating parameters of the scanner can be input into the scanner. For example, an optimal distance between the head of the scanner and the surface being scanned can be provided, and also a capture area (and its shape) of the dental surface that can be scanned at this distance can be provided. Alternatively, other suitable scanning parameters may be provided.

[0022] The intraoral scanning application 108 can identify suitable spatial relationships for scanning dental sites so as to obtain perfect and accurate image data for the treatment in question. The intraoral scanning application 108 can establish an optimal pattern for scanning a target area of a dental site.

[0023] The intraoral scanning application 108 can identify or determine a scanning protocol, such as by associating the type of scanner, the resolution of the scanner, and the capture area at an optimal distance between the scanner head and the dental surface with the target area. For the automatic exposure scanning mode, the scanning protocol comprises a series of scanning stations spatially associated with the dental surface of the target area. Preferably, overlapping of a plurality of images or scans obtainable at adjacent scanning stations is designed for the scanning protocol to enable accurate image registration, whereby a plurality of intraoral images can be stitched to provide a composite 3D virtual model. For the continuous scanning mode (video scanning), the scanning stations may not need to be identified. Instead, the dentist can activate the scanner and continue to move the scanner within the oral cavity to capture videos of the target area from a plurality of different viewpoints.

[0024] In one embodiment, the intraoral scanning application 108 includes a region of interest (AOI) identification module 115, a flagging module 118, and a model generation module 125. Alternatively, one or more operations of the AOI identification module 115, the flagging module 118, and / or the model generation module 125 may be integrated into a single module and / or divided into multiple modules.

[0025] The AOI identification module 115 is responsible for identifying regions of interest (AOIs) from intraoral scanning data (e.g., intraoral images) and / or virtual 3D models generated from intraoral scanning data. Examples of such regions of interest include voids (e.g., areas with missing scanning data), collisions or defective scanning data (e.g., areas where overlapping surfaces of multiple intraoral images do not fit together), foreign bodies (e.g., studs, bridges, etc.), areas showing tooth wear, areas showing tooth decay, areas showing gingival recession, blurred gingival lines, blurred patient bite, and blurred boundary lines (e.g., boundary lines of one or more prepared teeth). Identified voids may be voids on the surface of the image. Examples of surface collisions include doubled incisal margins and / or other physiologically unlikely tooth margins, and / or changes in the occlusal line. The AOI identification module 115 may, in identifying AOIs, analyze patient image data 135 (e.g., a set of points in a 3D image) and / or one or more virtual 3D models of the patient, individually and / or against reference data 138. This 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. The reference data 138 mentioned above may include historical data on recent patients (e.g., intraoral images and / or virtual 3D models), pooled patient data, and / or educational patient data, some or all of which may be stored in the data store 110.

[0026] Recent patient data may include X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models corresponding to the patient's visit in which the scan occurs. Recent patient data may further include past X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models of the patient (corresponding, for example, to the patient's past visits and / or the patient's dental records).

[0027] Pooled patient data may include X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models of a large number of patients. Such a large number of patients may or may not include recent patients. Pooled patient data may be anonymized and / or used in accordance with local medical record privacy regulations (e.g., Health Insurance Portability and Accountability Act (HIPAA)). Pooled patient data may include data corresponding to the types of scans discussed herein and / or other data. Educational patient data may include X-rays, 2D intraoral images, 3D intraoral images, 2D models, virtual 3D models, and / or medical illustrations (e.g., medical illustrations and / or other images) used in an educational context. Educational patient data may include applicant data and / or cadaver data.

[0028] The AOI identification module 115 may analyze patient scan data from later in the patient's visit when scanning occurs (e.g., one or more late-visit 3D image point sets and / or one or more late-visit 3D models of the patient) against additional patient scan data in the form of data from earlier in the patient's visit. Furthermore, or alternatively, the AOI identification module 115 may analyze patient scan data against reference data in the form of patient dental record data and / or patient data from before the patient's visit (e.g., one or more pre-visit 3D image point sets and / or one or more pre-visit virtual 3D models of the patient). Furthermore, or alternatively, the AOI identification module 115 may analyze patient scan data against pooled patient data and / or educational patient data.

[0029] In one example, the AOI identification module 115 may generate a first virtual model of the dental area based on a first scanning session of the dental area performed once, and a second virtual model of the dental area based on a second scanning session of the dental area performed twice. Subsequently, the AOI identification module 115 can compare the first virtual model and the second virtual model to determine changes in the dental area, identify AOIs, and indicate these changes.

[0030] The step of identifying regions of interest related to missing and / or defective scan data may involve the AOI identification module 115 performing a direct analysis, for example, determining one or more pixels or other points that will be missing from the patient scan data and / or one or more virtual 3D models of the patient. Furthermore, or otherwise, the step of identifying regions of interest related to missing and / or defective scan data may involve using pooled patient data and / or educational patient data to verify that the patient scan data and / or virtual 3D models are incomplete (e.g., have discontinuities) with respect to what the pooled patient data and / or educational patient data indicate.

[0031] The flagging module 118 is responsible for determining how to present and / or invoke identified regions of interest. The flagging module 118 may provide metric or indicators related to scanning assistance, diagnostic assistance, and / or foreign body recognition assistance. Regions of interest may be determined and indicators of regions of interest may be provided during and / or after an intraoral scanning session. Such metric can be provided before and / or without configuring the intraoral virtual 3D model. Alternatively, the metric may be provided after the configuration of the intraoral virtual 3D model of the dental area.

[0032] An example of a flagging module 118 that provides indicators related to scanning assistance, diagnostic assistance, and / or foreign body recognition assistance will now be discussed. The flagging module 118 may provide indicators during and / or after an intraoral scanning session. The indicators may be presented to the user (e.g., a dentist) (e.g., via a user interface) in conjunction with and / or separately from depictions of one or more of the patient's teeth and / or gums (e.g., in conjunction with one or more X-rays, 2D intraoral images, 3D intraoral images, 2D models, and / or virtual 3D models of the patient). Presentation of indicators in conjunction with depictions of the patient's teeth and / or gums may involve the step of arranging the indicators so that a certain indicator correlates with a corresponding part of the tooth and / or gum. As an example, diagnostic assistance indicators for a damaged tooth may be arranged to identify the damaged tooth.

[0033] Indicators may be provided in the form of flags, markings, outlines, text, images, and / or audio (e.g., in the form of speech). Such outlines may be positioned (e.g., by outline fitting) to follow the outlines of the remaining teeth and / or gingiva. For example, an outline corresponding to a diagnostic support indicator for tooth wear may be positioned to follow the outline of the worn tooth. Such outlines may be positioned relative to the outlines of missing teeth and / or gingiva to follow the projection trajectory of the missing outline (e.g., by extrapolation of the outline). For example, an outline corresponding to scanning data of a missing tooth may be positioned to follow the projection trajectory of the missing tooth portion, or an outline corresponding to scanning data of a missing gingiva may be positioned to follow the projection trajectory of the missing gingiva portion.

[0034] When an indicator (e.g., a flag) is presented, the flagging module 118 may perform one or more actions to display the appropriate indicator. For example, when displaying an indicator in association with one or more depictions of teeth and / or gums (e.g., corresponding virtual 3D models), such actions may work to display a single indicator rather than multiple indicators for a single AOI. Furthermore, the processing logic may select the position in 3D space for the placement of the indicator.

[0035] When displaying indicators in relation to a 3D rendering of teeth and / or gums (for example, in relation to a virtual 3D model), the flagging module 118 may divide the 3D space into cubes (for example, voxels corresponding to one or more pixels in the 3D space). The flagging module 118 then considers the voxels with respect to the voxels of the determined AOI, tags the voxels, and can indicate the indicators (e.g., flags) that these voxels correspond to.

[0036] For example, consider two indicators: a first indicator related to missing scan data and a second indicator related to tooth decay, which can attract the user's attention through flagging. With respect to the missing scan data indicator, the flagging module 118 may consider the pixels corresponding to the missing scan data in relation to the cube and tag each cube that contains one or more of these pixels. The flagging module 118 may do the same with respect to the tooth decay indicator.

[0037] If two or more cubes are tagged with respect to one of the above indicators, the flagging module 118 can act so that only one of the tagged voxels receives the flag placement. Furthermore, the flagging module 118 may select certain voxels to provide ease of viewing to the user. For example, such voxel selection may take into consideration the completeness of the indicators being flagged, and attempts may be made to avoid, where possible, overcrowding of a single cube with multiple flags.

[0038] When placing indicators (e.g., flags), the flagging module 118 may or may not consider factors other than avoiding overcrowding. For example, the flagging module 118 may consider available lighting, available angles, available zoom, available rotation axes, and / or other factors corresponding to how the user views the depiction of teeth and / or gums (e.g., a virtual 3D model), and may pursue an indicator (e.g., flag) placement that attempts to optimize user viewing in light of these factors.

[0039] The flagging module 118 may key indicators (for example, by color, symbol, icon, size, text, and / or number). Keying indicators can serve to convey information about the indicator. This information may include the classification of the AOI, the size of the AOI, and / or the importance rank of the AOI. Therefore, different types of AOIs may be identified using different flags or indicators. For example, a pink indicator can be used to indicate gingival recession, and a white indicator can be used to indicate tooth wear. The flagging module 118 can determine the classification, size, and / or importance rank of an AOI, and then, based on the classification, size, and / or importance rank, can determine the color, symbol, icon, text, etc., for the indicator of that AOI.

[0040] Moving on to keying for communicating metric sizes, the processing logic may employ one or more size thresholds when implementing such size-oriented keying. The baseline for these thresholds may be set during configuration (e.g., by a dental professional) and / or pre-set. The baseline for the thresholds may be set by processing logic accessing pooled patient data and / or educational patient data that correlates with size information relating to predictable metrics for scanning assistance (e.g., information regarding the size of oral anatomical parts that were not imaged or were poorly imaged by missing and / or defective scanning data), and the degree of success of the treatment outcome (e.g., the degree of orthodontic alignment device configuration and / or the degree of the orthodontic alignment device's fit to the patient). Larger sizes may be indicators of greater clinical importance. For example, some large voids may impair the manufacture of an accurate orthodontic alignment device, while others may not. As an example, three thresholds may be set with respect to missing data and / or caries areas. The implementation may be carried out such that the metric corresponding to the largest of the three size thresholds is keyed in red and / or the number "1", the metric corresponding to the smallest of the three size thresholds is keyed in purple and / or the number "3", and / or the metric corresponding to the medium size of the three size thresholds is keyed in yellow and / or the number "2".

[0041] Moving on to keying for communicating AOI classifications, indicators may identify classifications assigned to oral areas of interest. For example, AOIs may be classified as voids, changes, collisions, foreign bodies, or other types of AOIs. AOIs indicating changes in a patient's dentition may include caries, gingival recession, tooth wear, tooth fracture, gingival disease, gingival discoloration, bruises, lesions, tooth shade, tooth color, improvement in orthodontic alignment, deterioration in orthodontic alignment, etc. Different criteria may be used to identify each of these classes of AOIs. For example, voids may be identified by the absence of image data, collisions by the collision surface in the image data, changes may be identified based on differences in image data, and so on.

[0042] In the example of surface impact AOI, the first occlusal line component may correspond to a portion of the patient's teeth (e.g., the maxilla or the right side of the jaw). The second occlusal line component may correspond to another portion of the patient's teeth (e.g., the mandible or the left side of the jaw). The AOI identification module 115 may compare the first and second occlusal line components to check for deviations. Such deviations may suggest that the patient moved their jaw during scanning (e.g., between the dentist's scanning of the mandible and the dentist's scanning of the maxilla, or between the dentist's scanning of the left side of the jaw and the dentist's scanning of the right side of the jaw).

[0043] When performing the occlusal line shift surface collision operation, the AOI identification module 115 may or may not consider a deviation threshold (e.g., set during the configuration operation). The flagging module 118 may or may not provide an index for the discovered deviation if it satisfies the threshold, and may not provide an index if it does not. The intraoral scanning application 108 may or may not apply corrective measures (e.g., averaging) to the deviations discovered as described above that do not satisfy the threshold. If such a threshold is not considered, the flagging module 118 may provide an index for all discovered deviations. The above description focuses on occlusal line shift surface collision for the sake of clarity, but similar operations may be performed for other surface collision indices, for example.

[0044] Keying may include importance rankings, which will be discussed in more detail with reference to Figure 3B.

[0045] Once the scanning session is complete (for example, when all images relating to a dental area have been captured), the model generation module 125 may generate a virtual 3D model of the scanned dental area. The AOI identification module 115 and / or flagging module 118 may perform actions to identify and / or indicate AOIs before or after generating the virtual 3D model.

[0046] To generate a virtual model, the model generation module 125 may register (i.e., "stitch") intraoral images generated from an intraoral scanning session. In one embodiment, the step of performing image registration includes capturing 3D data of various points on the surface in multiple images (multiple fields of view from one camera) and registering these images by calculating deformations between the images. The images may then be integrated into a common reference frame by applying appropriate deformations to multiple points in each of the registered images. In one embodiment, the processing logic performs image registration in the manner discussed in Japanese Patent Application No. 6,542,249, filed July 20, 1999. The aforementioned patent application is incorporated herein by reference.

[0047] 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 executed to register two adjacent intraoral images, which essentially involves determining a deformation to align one image with the other. Each registration between pairs of images may have an accuracy of 10 to 15 micrometers. Image registration may involve the steps of identifying multiple points within each image (e.g., a set of points) of the image pair, and fitting multiple points in two adjacent images using a local search on the multiple points. For example, the model generation module 125 may iteratively minimize the distance between fitted points by fitting multiple points in one image with the nearest points interpolated on the surface of another image. The model generation module 125 can also find the best fit between curved feature portions at multiple points in one image and curved feature portions at points interpolated on the surface of another image without iteration. The model generation module 125 can also find the best fit between the point feature portion of the spin image at a point in one image and the point feature portion of the spin image at a point interpolated on the surface of another image, without iteration. Other techniques that can be used for image registration include, for example, those based on a step of determining point-to-point correspondences using other feature portions, and minimizing the point-to-surface distance. Other image registration techniques may also be used.

[0048] Many image registration algorithms perform surface fitting to points in adjacent images, and this can be done in numerous ways. Parametric surfaces such as Bézier surfaces and B-spline surfaces are the most common, but others may also be used. A single surface patch may be fitted to all points in an image, or multiple separate surface patches may be fitted to any number of subsets of points in the image. Multiple separate surface patches may be fitted to have a common boundary, or they may be fitted to overlap. A surface or surface patch may be fitted to interpolate multiple points using a control network with the same number of points as the grid of points to be fitted, or the surface may approximate points using a control network with fewer points than the grid of points to be fitted. Image registration algorithms may employ a variety of fitting techniques.

[0049] In one embodiment, the model generation module 125 may determine the fit of points between images, which may be in the form of a two-dimensional (2D) curved array. A local search for fitting point features in corresponding surface patches of adjacent images is performed by computing features at multiple points sampled in regions around parameterically similar points. Once a set of corresponding points is determined between the surface patches of the two images, the determination of the deformation between the two sets of corresponding points in the two coordinate frames can be resolved. Essentially, the image registration algorithm may compute a deformation between two adjacent images that minimizes the distance between a point on one surface and the point closest to that point found in an interpolation region on the surface of the other image.

[0050] The model generation module 125 repeatedly registers images for all adjacent pairs of images in a sequence of intraoral images, obtains deformations between each pair of images, and registers each image together with the previous image. The model generation module 125 then integrates all images into a single virtual 3D model by applying appropriately determined deformations to each image. Each deformation may include rotation around 1 to 3 axes and translation in 1 to 3 planes.

[0051] In one embodiment, the intraoral scanning application 108 includes a training module 120. The training module 120 may provide the user (e.g., a dentist) with training guidance on scanning techniques and / or highlight scanning support metrics of the type described above (e.g., corresponding to missing and / or defective scanning data) that have occurred in the past and / or have recurred for the user.

[0052] The training module 120 may consider, with respect to the training guidance data pool, scan data (e.g., a set of 3D image points) and / or one or more virtual 3D models that yielded scan-assistance indicators from scans performed by the user. The training guidance data pool may include, with respect to scans performed by multiple users (e.g., multiple dentists), scan data and / or one or more virtual 3D models (e.g., those that yield scan-assistance indicators), along with information describing changes in scanning techniques that may have prevented and / or mitigated the circumstances that resulted in the scan-assistance indicators. The scan data and / or one or more virtual 3D models in the training guidance data pool may be anonymized and / or used in accordance with local medical record privacy regulations. The training module 120 may adapt the scan data and / or one or more virtual 3D models obtained from scans performed by the user to the scan data and / or virtual 3D models in the training guidance data pool, access corresponding information describing changes in scanning techniques, and present such changes in scanning techniques to the user (via the user interface).

[0053] For example, with respect to scanning data and / or one or more virtual 3D models that provide scanning assistance indicators for a doubled incisor margin, such as those corresponding to a specific scanning angle, the training guidance data pool may include information indicating that performing scans with a specified angle change could have helped prevent and / or mitigate the condition. For example, such data may include information indicating that a 10° increase in the degree-to-surface angle could have helped prevent and / or treat a doubled incisor margin, with respect to scanning data and / or one or more virtual 3D models that provide scanning assistance indicators for a doubled incisor margin, such as those showing scans at a 35° degree-to-surface angle instead of the desired 45° angle. Furthermore, such data may include information indicating that a 5° increase in the degree-to-surface angle could have helped prevent and / or treat a doubled incisor margin, with respect to scanning data and / or one or more virtual 3D models that show scans at a 40° degree-to-surface angle instead of the desired 45° angle.

[0054] As another example, the training guidance data pool may include information indicating that performing scans at one or more specified speeds, cadences, angles, and / or distances from the surface could have helped prevent and / or mitigate scans of missing and / or defective scan data with respect to scan data and / or one or more virtual 3D models that yield scan-assistance metrics (e.g., corresponding to specific geometric regions, width-height dimensions, width-height or other dimensional relationships, and / or oral positions).

[0055] The training module 120 may maintain a time-series record of scanning assistance metrics (e.g., corresponding to a user identifier) ​​for a specific user (e.g., a dentist). The training module 120 can use this time-series record to highlight scanning assistance metrics that have occurred in the past and / or have recurred for a particular user, to identify improvements and / or deteriorations in user scanning technique over time, and / or to provide scanning technique training guidance that takes into account multiple scans performed by the user. The training module 120 may or may not take into account the aforementioned training guidance data pool information that describes changes in scanning technique that may help prevent and / or mitigate.

[0056] For example, when providing indicators (e.g., flagging) for missing and / or defective scan data, the training module 120 may identify if a particular user has received the same and / or similar indicators in the past. For example, the training module 120 may confirm that a 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 of a similar tendency multiple times (for example, the user has repeatedly received an indicator for re-selecting a doubled incisor margin, suggesting scanning at a surface angle other than 45°, at different locations). If the training module 120 discovers that a recent indicator is the same and / or similar indicator that has been received in the past, the training module 120 may highlight the indicator (for example, with a specific color).

[0057] As another example, with respect to a particular user and a scanning assistance index for a doubled incisor margin, the training module 120 may, by considering such time-series records and scanning technique change information in such a training guidance data pool, confirm that the user's scanning technique is changing in such a way that the adopted scanning angle is not yet the required surface angle of 45°, but is approaching the surface angle of 45° over time. In doing so, the training module 120 may perform fitting with the training guidance data pool information for the aforementioned different surface angles that result in the scanning assistance index for a doubled incisor margin (for example, fitting older user data to the pool data for a surface angle of 60°, and conversely, fitting more recent user data to the pool data for a surface angle of 40°).

[0058] Figures 2A to 2C show flowcharts of methods for performing intraoral scanning of a patient's dental area. These methods may be implemented by processing logic including hardware (e.g., circuit configuration, 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 the computing device 105 in Figure 1 (e.g., the computing device 105 that executes the intraoral scanning application 108).

[0059] Figure 2A shows a flowchart of a method 200 for determining an intraoral region of interest during an intraoral scanning session, according to an embodiment of the present invention. In block 205 of method 200, a dentist initiates an intraoral scanning session of a dental site. The scanning session may be for a partial or complete intraoral scan of the mandibular or maxillary arch, or for a partial or complete scan of both maxillary arches. The dentist may move the intraoral scanner to a first intraoral position to generate a first intraoral image. In block 210, processing logic receives the first intraoral image. The first intraoral image may be a separate image (e.g., taken in auto exposure mode) or a frame of intraoral video (e.g., taken in continuous scanning or video mode). The intraoral image may be a three-dimensional (3D) image having a specific height, width, and depth. In some embodiments, an intraoral scanner is used to generate a 3D image with a depth of 12-14 mm, a height of 13-15 mm, and a width of 17-19 mm (for example, in one particular embodiment, a depth of 13 mm, a height of 14 mm, and a width of 18 mm).

[0060] In block 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 that satisfy one or more criteria within the intraoral image. Different criteria may be used to identify different classes of intraoral regions of interest. In one embodiment, missing image data may be used to identify potentially void AOIs. For example, voxels in areas not captured by the intraoral image may be identified.

[0061] Next, the processing logic may determine one or more subsets of identified voxels that are close to each other. Two voxels may be considered close 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 through other identified voxels) are grouped into volumes that constitute candidate regions of interest. One or more candidate regions of interest may be identified. If the criterion used to identify voxels is missing data, the candidate regions of interest may represent voids. Other criteria may be used to identify other classes of AOI.

[0062] After the dentist generates the first intraoral image, the dentist moves the intraoral scanner to a second position and generates the next intraoral image. In block 220, the processing logic receives the next intraoral image. In block 230, the processing logic compares the second intraoral image with the first intraoral image. For the comparison of intraoral images, the processing logic determines alignment between the intraoral images based on the geometric features they share. The alignment determination may include steps of performing deformation and / or rotation of one or both of the intraoral images, and / or registering intraoral regions of interest with respect to each other. The processing logic may then display the aligned images. The processing logic may also compare the first intraoral image with a corresponding intraoral image taken during a previous scanning session. This allows for the identification of regions of interest such as tooth wear and cavities.

[0063] In block 232, the processing logic determines whether any new candidate intraoral region of interest exists based on the following images. In block 235, the processing logic determines whether candidate intraoral region of interest from the first intraoral image is approved as an intraoral region of interest. Such approval can be performed by testing the proximity and / or geometric conditions of the AOI to the surface of the meticulous intraoral image. In one embodiment, candidate intraoral region of interest from one intraoral image is rejected if they correspond to a surface (e.g., a dental area) from another intraoral image. Alternatively, if a candidate intraoral region of interest does not correspond to a region of a surface from another intraoral image, the candidate can be approved as an actual intraoral region of interest. Thus, candidate intraoral region of interest from the first intraoral image can be approved or rejected using the second intraoral image. If a portion of a candidate intraoral region of interest from the first intraoral image corresponds to (e.g., adjacent to) a portion of a surface from the second intraoral image, the shape and / or size of the candidate intraoral region of interest may be modified. If none of the candidate oral regions of interest are approved as oral regions of interest (for example, if subsequent oral images provide image data relating to the candidate oral regions of interest), the method proceeds to block 245. Otherwise, the method proceeds to block 240.

[0064] In block 240, the processing logic provides an indicator for one or more approved oral regions of interest. In one embodiment, the processing logic interpolates the shape of the oral region of interest based on the geometric features surrounding the oral region of interest and / or (if any) the geometric features of the oral region of interest. For example, if the oral region of interest is a void, the region surrounding the void may be used to interpolate the surface shape of the void. The shape of the oral region of interest may be displayed in a manner that makes the oral region of interest stand out from the surrounding image. For example, teeth may be shown in white, while the oral region of interest may be shown in red, black, blue, green, or another color. The indicator may be separate from the oral region of interest but may include a pointer to the oral region of interest. The oral region of interest may be hidden or not included in many of the fields of view of the dental area. However, the indicator may be visible in all or many of the fields of view. For example, the indicator may be visible in all fields of view of the scanned dental area unless the indicator is disabled. The provided indicators of oral areas of interest may be displayed during the oral scanning session.

[0065] In block 245, the processing logic determines whether the intraoral scanning session is complete. If it is, the method proceeds to block 248. If further intraoral images need to be captured and processed, the method returns to block 220.

[0066] In block 248, a virtual 3D model of the dental area is generated. The virtual 3D model may be generated as described above. The virtual 3D model may be a virtual or digital model that shows the surface features of the target region. With respect to the virtual 3D model of the entire dental arch, the arch width of the virtual 3D model may be accurate to within 200 micrometers of the actual arch width of the patient.

[0067] Figure 2B shows a flowchart of a method 250 for providing indicators to an oral region of interest according to an embodiment of the present invention. These indicators may be provided during an intraoral scanning session (e.g., before the generation of a virtual model of the dental site) or after the completion of an intraoral scanning session (e.g., based on the virtual model of the dental site).

[0068] Block 255 receives intraoral images of dental areas. These intraoral images may be received from an intraoral scanner, a data store, another computing device, or another source. The intraoral images may be from a single intraoral scanning session or from multiple intraoral scanning sessions. In addition, or separately, one or more virtual models of dental areas may be received. These virtual models may be calculated based on intraoral images from past intraoral scanning sessions.

[0069] In block 260, the processing logic identifies one or more voxels from intraoral images and / or a virtual model that satisfy certain criteria. These criteria may be missing data, collision data, or data with specific features. In one embodiment, a virtual model is first calculated using the intraoral images, and voxels are identified from the calculated virtual model. In another embodiment, voxels are identified from individual intraoral images.

[0070] Block 265 identifies one or more subsets of identified voxels that are adjacent to each other. Block 270 groups these subsets into candidate oral regions of interest.

[0071] In block 275, the processing logic determines whether any candidate oral region of interest is approved as an oral region of interest. If any candidate oral region of interest is approved as an actual oral region of interest, the method proceeds to block 280. Otherwise, the method proceeds to block 290.

[0072] Block 280 determines the classification of oral areas of interest. For example, AOIs may be classified as voids, impacting surfaces, dental site changes, foreign bodies, etc.

[0073] In block 285, the processing logic provides indicators for oral regions of interest. These indicators may include information that identifies a determined classification of the oral region of interest. For example, one indicator may identify an oral region of interest as representing a void or insufficient image data. Another indicator may identify an oral region of interest as representing a region where collision surfaces from different images exist.

[0074] In one embodiment, the indicator includes a flag that points to or otherwise directs the observer's attention to the oral region of interest, even though the indicator is located away from the oral region of interest. The indicator can be seen from the field of view of a dental site where the actual oral region of interest is hidden. In block 290, a dental site is displayed along with any of the indicators relating to the oral region of interest.

[0075] Figure 3A shows a flowchart of Method 300 for forming scanning support indices for missing and / or defective scanning data according to an embodiment of the present invention. According to a first embodiment, in block 305 of Method 300, the processing logic may receive scanning data from an intraoral scanner. In block 310, the processing logic may perform direct 3D point set analysis and / or direct virtual 3D model analysis. In block 315, the processing logic may determine one or more pixels and / or other points that will be missing from the patient's scanning data and / or from one or more virtual 3D models of patients. In block 330, the processing logic may form one or more corresponding indices for missing and / or defective scanning data.

[0076] According to the second aspect of Figure 3, in block 305, the processing logic may receive scanning data from the scanner in the same manner as described above. In block 320, the processing logic may consider patient scanning data and / or virtual 3D models of one or more patients for entities represented by pooled patient data and / or educational patient data to construct complete and / or flawless data.

[0077] In block 325, the processing logic may verify that the patient scan data and / or the virtual 3D models of one or more patients are incomplete. In block 330, the processing logic may, as above, form one or more corresponding indices regarding the missing and / or defective scan data. Diagnostic support indices provided by the processing logic may include indices regarding tooth occlusal contact, occlusal relationships, tooth fracture, tooth wear, gingival swelling, gingival recession, and / or caries. For ease of understanding, an example of the operation of the processing logic in relation to the provision of diagnostic support indices is discussed below.

[0078] Figure 3B shows a flowchart of Method 340 for performing keying and display to communicate index importance ranks for oral regions of interest, in accordance with the embodiments of the present invention already discussed. The processing logic may assign one importance rank to one index by a process in which the processing logic considers the index in light of the details of one or more patient cases and / or one or more weighting factors for rank variation. It should be noted that one or more of the above weighting factors for rank variation themselves may or may not take into account the details of the patient case. Such details of the patient case may include the treatments performed (e.g., preparation for the application of crowns, preparation for the application of orthodontic alignment devices, treatment of suspected caries and / or treatment of gingival swelling), the patient's age, the patient's sex, one or more treatments performed in the past (e.g., the patient's last visit was to address a crown affected by marginal leakage), and / or the patient's dental record.

[0079] In block 345 of Method 340, the processing logic may apply one or more weighting factors to each of the one or more metrics under consideration. The weighting factors may reveal one or more specific characteristics and may indicate one or more rank variations that can be performed if the characteristics are met. Rank variations may include increasing the rank of a metric by a given value, decreasing the rank of a metric by a given value, specifying that a metric is considered to have the highest rank, and / or specifying that a metric is considered to have the lowest rank. With respect to a given metric, the processing logic may begin by assigning a specific starting rank value (e.g., zero) to that metric. After applying these weighting factors, the processing logic may determine the final importance rank of the metric. The processing logic may then consider the final importance ranks for one or more other metrics in which the processing logic has performed a similar operation.

[0080] The baseline for the rank variation weighting factors considered by the processing logic may be set by the processing logic accessing pooled patient data and / or educational patient data, which includes correlations between predictable indicators related to diagnostic support (e.g., tooth wear and / or caries) and importance (e.g., the data may reveal importance information for tooth wear and caries, respectively, that conveys that caries is more important than tooth wear).

[0081] The processing logic sets a weighting factor for rank variation so that missing and / or defective scan data corresponding to a portion of a tooth and / or gingiva that is larger than a certain size has a higher rank. Missing and / or defective scan data corresponding to a portion of a tooth and / or gingiva that has certain dimensional characteristics (e.g., width greater than height, short and wide, or appearing square) is assigned the highest rank or a relatively high rank. Missing and / or defective scan data corresponding to a portion of a tooth and / or gingiva that has other dimensional characteristics (e.g., width less than height, or appearing long and narrow) is assigned the lowest rank or a relatively low rank.

[0082] The baseline for rank-variable weighting factors considered by the processing logic may be set by the processing logic accessing pooled patient data and / or educational patient data, which includes correlations between predictable indicators related to foreign body recognition support (e.g., those related to fillers and / or implants) and importance (e.g., the data may reveal importance information for each of the fillers and implants, indicating that the fillers are more important than the implants). By considering such correlations provided by the data—that is, that the data relates to scanning support, diagnostic support, or foreign body recognition support—the processing logic can draw conclusions to adopt when setting rank-variable weighting factors.

[0083] The settings to be implemented are performed during configuration or by processing logic, and may provide one or more weighting factors for predictable indicators. One such weighting factor may specify that an indicator related to the vicinity of one or more prepared teeth (e.g., the interproximal region of the tooth) has a rank increased by a specified value. Another such weighting factor may specify that an indicator relating to the clarity of the marginal lines of insufficiently prepared teeth has a rank increased by a specified value, or that such an indicator should have the highest rank. Yet another weighting factor may specify that an indicator relating to the occlusal line has a rank increased by a specified value. A further weighting factor may specify that an indicator relating to the occlusal line displacement has a rank increased by a specified value. Another weighting factor may specify that an indicator relating to a doubled incisal margin has a rank increased by a specified value. Another weighting factor may specify that the index for lack of clarity of the gingival margin has a rank that is increased by a first specified value if the most recent treatment was not related to gingival recession, but has a rank that is increased by a second specified value if the most recent treatment was related to gingival recession.

[0084] As an example, with respect to the first indicator, the processing logic may begin by assigning an importance rank of "zero" to the indicator: considering the first weighting factor, it is determined that the rank of the indicator increases by 3; considering the second weighting factor, it is determined that the rank of the indicator decreases by 1; and considering the third weighting factor, it is determined that the rank of the indicator increases by 5. The processing logic may then confirm that the final importance rank of the first indicator is 7.

[0085] Furthermore, with respect to the second indicator, the processing logic may begin by assigning an importance rank of "zero" to the indicator: considering the first weighting factor, it is determined that the rank of the indicator decreases by 2; considering the second weighting factor, it is determined that the rank of the indicator decreases by 3; and considering the third weighting factor, it is determined that the rank of the indicator increases by 6. Subsequently, the processing logic may confirm that the final importance rank of the second indicator is 1.

[0086] With respect to the third indicator, the processing logic may begin by assigning an importance rank of "zero" to the indicator. Next, the processing logic may determine that: considering the first weighting factor, the rank of the indicator increases by 4; considering the second weighting factor, the indicator is considered to have the highest rank; and considering the third weighting factor, the rank of the indicator decreases by 8. Subsequently, the processing logic may confirm that the final importance rank of the third indicator is the highest rank. Therefore, the second weighting factor can be considered to outperform the other two weighting factors by showing the highest rank. Conversely, if considering the second weighting factor, the indicator is considered to have the lowest rank, it should be noted that although the second weighting factor still outperforms the other two weighting factors, it results in a final importance rank of the lowest rank for the third indicator.

[0087] In block 350, the processing logic may determine the final importance rank for each of the one or more indicators under consideration. In block 355, the processing logic may consider the final importance ranks of the one or more indicators under consideration in relation to each other. Following the example above, the processing logic may consider the three final importance ranks, namely 7 for the first indicator, 1 for the second indicator, and the highest rank for the third indicator, in relation to each other. In doing so, the processing logic may conclude that the third indicator has the highest rank, the first indicator has the second highest rank, and the second indicator has the lowest rank.

[0088] In block 360, the processing logic may use the final importance rank to form a rescan sequence and / or a dentist attention sequence. The processing logic may use the final importance rank to propose a rescan sequence for one or more indicators (e.g., indicators relating to scan assistance, such as indicators relating to missing and / or defective scan data) and / or to propose a dentist attention sequence for one or more indicators (e.g., indicators relating to diagnostic assistance and / or indicators relating to foreign body recognition assistance). When forming such a rescan sequence and such a dentist attention sequence, the processing logic may suppress one or more indicators so that these indicators are excluded from the rescan sequence and the dentist attention sequence. For example, the processing logic may suppress indicators with a rank below a certain value (e.g., a value specified by the user and / or specified during configuration). As another example, the processing logic may suppress indicators with the lowest rank. Such suppression can serve to eliminate metrics that the processing logic has determined to lack clinical advantage (for example, with respect to recent treatment—e.g., preparation for the application of a crown or orthodontic alignment device). As an example, suppressed metrics may include missing and / or defective scanning data that can be compensated for (e.g., by extrapolation and / or general data filling). With respect to unsuppressed metrics, the processing logic may communicate importance ranks by keying the metrics (e.g., by color, symbol, icon, size, text and / or number key).

[0089] Next, in block 365, the processing logic may provide one or more keyed indicators (e.g., flags) that, along with a depiction of the teeth and / or gums (e.g., a 3D image or a virtual 3D model), convey the position of each indicator within the rescan sequence and / or the sequence of dentist's attention. The processing logic may provide flags containing numbers that each point to a specific portion of the depiction of the patient's teeth and / or gums (e.g., a 3D image or a virtual 3D model), and the numbers may convey the position of that oral portion within the sequence.

[0090] As an example, let's assume there are four scan support indicators that the processing logic can select to include in the rescan sequence: an indicator corresponding to teeth 15 and 16 (ISO 3950 notation), an indicator corresponding to tooth 32 (ISO 3950 notation), an indicator corresponding to teeth 18 and 17 (ISO 3950 notation), and an indicator corresponding to tooth 44 (ISO 3950 notation). Let's also assume that the indicators corresponding to teeth 18 and 17 have the lowest rank, and that the processing logic suppresses this indicator, thereby removing it from the rescan sequence. Furthermore, let's assume that the rescan sequence for the remaining three indicators is such that the indicator corresponding to the gingiva of tooth 32 has the highest importance rank among the remaining three and is the first in the rescan sequence, the indicators corresponding to teeth 15 and 16 have the second highest importance rank among the remaining three and are the second in the rescan sequence, and the indicator corresponding to tooth 44 has the lowest importance rank among the remaining three and is the third in the rescan sequence. The flags provided by the processing logic may be such that the index corresponding to the gingiva of tooth 32 is flagged "1", the index corresponding to teeth 15 and 16 is flagged "2", and the index corresponding to tooth 48 is flagged "3".

[0091] As another example, let's assume there are three indicators related to diagnostic support: an indicator corresponding to fracture of teeth 11 and 21 (ISO 3950 notation), an indicator corresponding to occlusal relationship, and an indicator corresponding to gingival recession at the base of tooth 27 (ISO 3950 notation). Furthermore, let's assume that the hierarchy of the dentist's attention is such that the indicator corresponding to occlusal relationship has the highest importance rank among the three and is the first in the hierarchy of dentist's attention, the indicator corresponding to fracture has the second highest importance rank among the three and is the second in the hierarchy of dentist's attention, and the indicator corresponding to gingival recession has the lowest importance rank among the three and is the third in the hierarchy of dentist's attention. The flagging by the processing logic may be such that the indicator corresponding to occlusal relationship is flagged as "1", the indicator corresponding to fracture is flagged as "2", and the indicator corresponding to gingival recession is flagged as "3".

[0092] As a further example, let's assume there are two indicators for foreign body recognition: one corresponding to the filling material of tooth 16 (ISO 3950 notation), and another corresponding to the expected anatomical position of teeth 35-37 (ISO 3950 notation). Furthermore, let's assume that the hierarchy of dentistry attention is such that the indicator corresponding to the filling material has the higher importance rank of the two and is the first in the hierarchy of dentistry attention, and the indicator corresponding to the bridge has the lower importance rank of the two and is the second in the hierarchy of dentistry attention. The flagging by the processing logic may be such that the indicator corresponding to the filling material is flagged as "1" and the indicator corresponding to the bridge is flagged as "2".

[0093] Figure 3C shows a flowchart of a method 370 that utilizes 3D intraoral images to provide indicators of a region of interest, according to an embodiment of the present invention. As described above, the processing logic may provide indicators related to scanning assistance, diagnostic assistance and / or foreign body recognition assistance. Also as described above, the processing logic may provide such indicators during the application of the scanner by the user (e.g., a dentist), after the application of the scanner by the user, and / or before and / or without the construction of the intraoral virtual 3D model. Furthermore, as described above, in forming such indicators, the processing logic may analyze intraoral scanning data (e.g., 3D intraoral images such as 3D intraoral images provided by the scanner as a set of 3D image points) and / or the intraoral virtual 3D model.

[0094] In block 372 of method 370, the processing logic may analyze one or more first 3D intraoral images to obtain candidate intraoral regions of interest. The processing logic may perform the analysis described above with respect to AOI formation, but may consider the analysis results to construct candidate intraoral regions of interest rather than actual intraoral regions of interest. The 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.

[0095] In block 374, the processing logic may identify one or more second 3D intraoral images that may be related to a candidate intraoral region of interest. The one or more second 3D intraoral images may be intraorally close to the first one or more 3D intraoral images and / or share a geometric relationship with the first one or more 3D intraoral images. The processing logic may determine the intraoral proximity described above by considering the intraoral position information provided by the scanner in conjunction with the 3D intraoral images. The scanner may generate such information by built-in accelerometers and / or other positioning hardware. The processing logic may determine the shared geometric relationship described above by identifying common surface features (e.g., common peaks and / or valleys).

[0096] In block 376, the processing logic may perform an analysis on one or more of the combined first and second 3D intraoral images. When performing this, the processing logic may or may not align one or more of the first 3D intraoral images with one or more of the second 3D intraoral images (for example, the processing logic may align one or more point sets corresponding to one or more of the first 3D intraoral images with one or more point sets corresponding to one or more of the second 3D intraoral images).

[0097] In block 378, the processing logic may determine whether the combined first 3D intraoral image and the second 3D intraoral image match, do not match, or partially match with respect to a candidate intraoral region of interest. For example, suppose the candidate index relates to a scanning support index associated with missing and / or defective scanning data. If no missing and / or defective scanning data is found by such a combined analysis, a mismatch may occur. For example, this may occur if all one or more points (e.g., one or more pixels and / or groups of pixels) corresponding to the missing scanning data with respect to the candidate index are provided by one or more second 3D intraoral images.

[0098] Partial matches may occur if, despite the discovery of further missing and / or defective scan data through the integrated analysis described above, the trends of the missing and / or defective scan data have changed (for example, the newly discovered missing and / or defective scan data are larger in size, smaller in size, in different locations, and / or in different forms). For example, this may occur if some points (e.g., one or more pixels and / or groups of pixels) corresponding to missing scan data for a candidate index are provided by one or more second 3D intraoral images, while other points of such missing scan data are not provided by one or more second 3D intraoral images, and therefore only a relatively small amount of missing and / or defective scan data is found.

[0099] Matches can occur if the integrated analysis described above reveals missing and / or defective scan data with the same trend (e.g., the same amount). For example, this can occur if points (e.g., one or more pixels and / or groups of pixels) corresponding to missing scan data for a candidate index are not provided at all by one or more second 3D intraoral images.

[0100] As another example, suppose the candidate indicators relate to diagnostic support indicators associated with tooth decay. A mismatch may occur if no tooth decay is found through such an integrated analysis. For example, this may occur if further consideration of one or more second 3D intraoral images—for example, one or more points (e.g., one or more pixels and / or groups of pixels) provided by one or more second 3D intraoral images—leads to a narrowed-down favorable point in the oral cavity where no tooth decay is found.

[0101] Even if caries are still found through the integrated analysis described above, partial matches may occur if the characteristics of the discovered caries have changed (for example, the caries found this time are smaller, larger, in different locations, and / or have different shapes). For example, this may occur if further consideration of one or more second 3D intraoral images—for example, one or more points (e.g., one or more pixels and / or groups of pixels) provided by one or more second 3D intraoral images—provides a narrowed-down favorable point in the oral cavity where the size and / or intraoral location of the discovered caries differs.

[0102] Matching may occur if, through the integrated analysis described above, caries exhibiting the same tendencies as those found in relation to candidate indicators are discovered. For example, this may occur if further consideration of one or more second 3D intraoral images—for example, one or more points (e.g., one or more pixels and / or groups of pixels) provided by one or more second 3D intraoral images—does not narrow down favorable points in the oral cavity such that the found caries are different in size and / or oral location.

[0103] If the processing logic finds a match, it may promote the candidate AOI to an index of the type described above (i.e., a completely non-candidate AOI) and use it as described above (for example, providing the user with an index of the AOI in the form of a flag). If the processing logic finds a partial match, it may obtain an AOI corresponding to the different trend described above (for example, an AOI reflecting a smaller amount of missing data, or an AOI reflecting a different form of tooth decay) and use it as described above. If the processing logic finds a mismatch, it may reject the candidate AOI.

[0104] If a match exists, the processing logic may proceed to block 380, where it promotes the candidate index to a complete non-candidate AOI and uses the promoted index as described above. If a partial match exists, the processing logic may proceed to block 382, ​​where it obtains an index corresponding to the tendency of the partial match and uses that index as described above. If a mismatch exists, the processing logic may proceed to block 384, where it rejects the candidate index.

[0105] The pooled patient data and / or educational patient data described above may include many different types of data and / or descriptions. Several examples of different pooled patient data and / or educational patient data, as well as some of their uses, will be discussed below.

[0106] Pooled patient data and / or educational patient data may include depictions of gingival margins, bites, and / or occlusal lines, along with corresponding identification information and / or clarity level indicators. Indicators for unclear gingival margins and / or unclear patient bites may involve a step in which the processing logic uses the pooled patient data and / or educational patient data to recognize that the patient's scan data and / or virtual 3D model contains unclearly imaged gingival margins or bites (e.g., deviating in a manner that suggests unclearness from gingival margins or bites indicated as having clarity by the pooled and / or educational data).

[0107] Pooled patient data and / or educational patient data may further include depictions of boundary lines, tooth roots, and / or accumulations (e.g., blood and / or saliva accumulations), along with corresponding identification information. Indicators of unclear boundary lines may involve a step in which the processing logic uses the pooled patient data and / or educational patient data to recognize that the patient's scan data and / or virtual 3D model constitutes a boundary line (e.g., the upper part of the root that will receive a prosthetic crown). Furthermore, or / or, the processing logic may detect changes in boundary lines that suggest the composition of blood, saliva, and / or similar accumulations at the boundary line by comparing the patient scan data and / or one or more virtual 3D models of the patient under consideration with the boundary lines of the early consultation and / or dental record data. The processing logic may consider the discovered boundary lines together with the discovered blood, saliva, and / or similar accumulations to determine the location of instances of such accumulations appearing near such boundary lines and conclude that such instances constitute unclear boundary lines.

[0108] Pooled patient data and / or educational patient data may include depictions of incisor margins and / or doubled incisor margins, along with corresponding identification information. An index for doubled incisor margin surface collisions may involve the processing logic using the pooled patient data and / or educational patient data to recognize that the patient's scan data and / or virtual 3D model contains one or more incisor margins, and further concluding that such incisor margins are deviated from the incisor margins that the pooled and / or educational data would indicate as appropriate incisor margins, in a manner that suggests doubled incisor margins.

[0109] Pooled patient data and / or educational patient data may include descriptions of tooth occlusal contact and / or occlusal relationships, along with corresponding identification information. Indicators of tooth occlusal contact and / or occlusal relationships may involve a step in which the processing logic uses the pooled patient data and / or educational patient data to recognize that the patient's scan data and / or virtual 3D model constitutes tooth occlusal contact and occlusal relationships. The processing logic may further access one or more treatment goals (e.g., a desired degree of occlusion for teeth with one or more indicators, and / or a desired occlusal relationship). Such goals may be provided by the dentist (e.g., via a user interface) and / or retrieved from an accessible data store. Next, the processing logic may detect the degree of change (which may be zero) in the relationship between the occlusal contact and / or occlusion of teeth by comparing the relationship between the occlusal contact and / or occlusion of teeth in the patient scan data and / or one or more virtual 3D models of the patient under consideration with the relationship between the occlusal contact and / or occlusion of teeth in the early consultation and / or dental record data. Next, the processing logic may compare the determined change with the treatment goal to confirm whether the change satisfies the treatment goal, or whether it plays a role in bringing the treatment goal closer to or further away from the treatment goal. The indicator may include a notification regarding whether the change brings the treatment goal closer to, further away from, satisfies, or does not result in any change to the treatment goal.

[0110] As an example, the above description regarding occlusal contact of teeth may correspond to a situation in which a dentist: instructs the processing logic on the treatment goal of occlusal contact of teeth; causes the processing logic to receive scanning data showing the patient's occlusal contact state at the start; performs a dental procedure that potentially alters the occlusal contact state; and causes the processing logic to receive scanning data showing the occlusal contact state after the procedure. Through the types of processing described above, the dentist may receive indicators regarding whether their procedure met the treatment goal, resulted in progress toward the treatment goal, resulted in a deviation from the treatment goal, or resulted in no change with respect to the treatment goal.

[0111] As another example, the above-mentioned content regarding occlusal relationships may correspond to a situation where a dentist: instructs the processing logic on the treatment goals for the occlusal relationships; causes the processing logic to receive scanning data showing the state of the patient's occlusal relationships at the start; applies an orthodontic alignment device to the patient; and sends the patient home at a later date. At that later date, the dentist causes the processing logic to receive scanning data showing the state of the occlusal relationships after the device has been applied. Through the types of processing described above, the dentist may receive indicators regarding whether their device application met the treatment goals, resulted in progress toward the treatment goals, resulted in a deviation from the treatment goals, or resulted in no change with respect to the treatment goals.

[0112] Pooled patient data and / or educational patient data may include descriptions of tooth damage, tooth wear, gingival swelling, gingival recession, and / or caries, along with corresponding identification information. Indicators relating to tooth damage, tooth wear, gingival swelling, gingival recession, and / or caries may involve a step in which the processing logic uses the pooled patient data and / or educational patient data to recognize that patient scan data and / or one or more virtual 3D models constitute tooth damage, tooth wear, gingival swelling, gingival recession, and / or caries. For example, the processing logic may use the pooled patient data and / or educational patient data to recognize teeth and / or gums in intraoral images and / or virtual 3D models. Next, the processing logic may detect changes indicating tooth damage, tooth wear, gingival swelling, gingival recession, and / or tooth decay by comparing the teeth and / or gums of the intraoral images and / or virtual 3D models with the teeth and / or gums of earlier intraoral images, virtual 3D models, and / or dental record data. When performing such detection, the processing logic may or may not perform image analysis (for example, if the detected change has jagged edges, the change may be considered to indicate tooth damage), and may or may not examine the patient data and / or educational patient data (for example, if the detected change matches one or more items that the patient data and / or educational patient data indicate as constituting damage, the change may be considered to indicate tooth damage).

[0113] Indicators of tooth damage and / or caries may include a step in which the processing logic directly performs the analysis. The processing logic may further, or otherwise, use pooled patient data and / or educational patient data to recognize that the patient's scan data and / or virtual 3D model includes areas that constitute teeth. The processing logic may determine (e.g., by margin recognition) that one or more of such teeth have one or more jagged edges. The processing logic may consider such jagged edges to indicate tooth damage. The processing logic may determine (e.g., by shape recognition) that one or more of such teeth have spots and / or depressions. The processing logic may consider such spots and / or depressions to indicate caries.

[0114] The foreign body recognition support indicators provided by the processing logic may include indicators for fillings, implants, and / or bridges. Pooled patient data and / or educational patient data may include depictions of fillings, implants, and / or bridges, along with corresponding identification information. The indicators for fillings, implants, and / or bridges may involve a step in which the processing logic uses the pooled patient data and / or educational patient data to recognize scan data and / or one or more virtual 3D models of the patient constituting the filling, implant, and / or bridge. The indicators for fillings, implants, and / or bridges may involve a step in which the processing logic compares the scan data and / or one or more virtual 3D models of the patient under consideration with early patient visit data, patient dental record data, and / or patient data from before the patient's most recent visit. The processing logic may consider objects that appear in the scan data of the patient under consideration and / or one or more virtual 3D models of the patient, but do not appear in the patient's early consultation data, the patient's dental record data, and / or the patient's data prior to the most recent consultation, as potentially foreign bodies. Such functionality can be implemented, for example, from the perspective that a new object appearing in the patient's mouth has a certain possibility of being a foreign body rather than occurring naturally. The processing logic may prompt the dentist (e.g., via a user interface) to respond to such indicators with agreement or disagreement that the object identified by the processing logic is a foreign body.

[0115] Figure 4A shows an exemplary scanned portion of the dental arch 400 during an intraoral scanning session. The dental arch 400 includes the gingiva 404 and several teeth 410, 420. Multiple intraoral images 425, 430, 435, and 440 of a particular dental site in a patient were taken. Each intraoral image 425-440 may be generated by an intraoral scanner at a specific distance from the imaged dental surface. At the aforementioned specific distance, intraoral images 425-440 have a specific scanning area and scanning depth. The shape and size of the scanning area generally depend on the scanner and are represented here as a rectangle. Each image may have its own reference coordinate system and origin. Each intraoral image may be generated by the scanner at a specific position (scanning station). The position and orientation of the scanning station may be selected so that the multiple intraoral images together adequately cover the entire target area. Preferably, the scanning station may be selected so that there is overlap between intraoral images 425-440 as shown in the figure. Typically, when using different scanners for the same target area, the selected scanning stations will differ depending on the capture characteristics of the scanners used. Therefore, scanners that can scan a larger dental area with each scan (e.g., those with a larger field of view) will require fewer scanning stations than scanners that can only capture 3D data of relatively small dental surfaces. Similarly, the number and arrangement of scanning stations for scanners with a rectangular scanning grid (and thus providing a corresponding rectangular projection scanning area) will typically differ from those for scanners with a circular or triangular scanning grid (and thus providing a corresponding circular or triangular projection scanning area).

[0116] The oral regions of interest 448 and 447 are calculated as previously described herein. In the illustrated embodiments, the oral regions of interest 447 and 448 represent the portion of the patient's dental area for which image data is missing.

[0117] Figure 4B shows the scanned portion of dental arch 402, which is the latest version of dental arch 400. Additional intraoral images 458 and 459 were taken to provide image data corresponding to intraoral regions of interest 447 and 448. Therefore, intraoral regions of interest 447 and 448 are not shown in dental arch 402. Additional intraoral images 460, 462, 464 and 466 were also generated. These additional intraoral images 460–466 reveal teeth 450, 452, 454 and 456. Based on the additional intraoral images 460–466, new intraoral regions of interest 470 and 472 are also determined. The dentist may resolve the intraoral regions of interest 470 and 472 by generating further intraoral images and provide complete data on the dental arch.

[0118] Figure 5A shows an exemplary image of the dental arch 500 indicating a region of interest. The image of the dental arch 500 may consist of one or more intraoral scans before the generation of the virtual 3D model. Alternatively, the image of the dental arch 500 may consist of one or more scans of the physical model of the dental arch. The image of the dental arch 500 includes the gingiva 509 and several teeth 505-508. Several regions of interest 509, 515, and 525 are also shown in the image of the dental arch 500. These regions of interest 509, 515, and 525 represent missing scan data that meet the criteria of clinical importance.

[0119] Figure 5B shows an exemplary image of the dental arch 550 showing regions of interest and indicators pointing to these regions of interest. The image of the dental arch 550 may consist of one or more intraoral scans, or it may consist of one or more scans of a physical model of the dental arch. The image of the dental arch 550 includes the gingiva and several teeth. Several regions of interest 562, 564, 566, 568, 570, and 572 are also shown in the image of the dental arch 550. These regions of interest 562, 564, 566, 568, 570, and 572 represent missing scan data that meet the criteria of clinical importance (e.g., intraoral regions of interest that exceed a certain threshold size or have one or more dimensions that deviate from certain geometric criteria). However, some regions of interest 562 and 570 are largely excluded from the exemplary image of the dental arch 550. Furthermore, there are other regions of interest that are completely hidden. To ensure that dentists are aware of these areas of interest, indicators such as flags are placed for each area of ​​interest. For example, an image of the dental arch 550 includes flags 552-559. These flags direct the dentist's attention to areas of interest that need to be addressed, regardless of their current field of view.

[0120] Figure 5C shows another exemplary image of the dental arch 575 showing regions of interest and indicators pointing to those regions of interest. The image of the dental arch 575 may consist of one or more intraoral scans, or it may consist of one or more scans of a physical model of the dental arch. The image of the dental arch 575 includes the gingiva and several teeth. Several regions of interest 576-584 are also shown in the image of the dental arch 575. These regions of interest 576-584 represent tooth wear, identified based on a comparison between the image and / or virtual 3D model generated on a first date and the image and / or virtual 3D model generated on a second date. However, some regions of interest 576, 578 are largely excluded from the exemplary image of the dental arch 575. To ensure that dentists are aware of these regions of interest, indicators such as flags are placed for each region of interest. For example, the image of the dental arch 575 includes flags 586-594. These flags direct dentists to areas of interest that should be addressed, regardless of their current field of vision.

[0121] Figure 6 shows a screenshot 600 of an intraoral scanning application (e.g., intraoral scanning application 108 in Figure 1) according to an embodiment of the present invention. Screenshot 600 shows several menus 602, 604, and 606 for performing various operations. Menu 602 provides icons that can be selected to perform operations such as setting bias, saving data, obtaining assistance, generating a virtual 3D model from collected intraoral images, and switching to viewing mode. Menu 604 provides icons for adjusting the field of view 607 of the scanned dental area 608. Menu 604 may include icons for pan, zoom, rotate, etc. The field of view 607 of the scanned dental area 608 includes a dental arch consisting of one or more past intraoral images that are registered and / or aligned with each other. The field of view 607 further includes indicators of the most recent intraoral image 610 added to the dental arch.

[0122] The dental arch described above contains multiple voids based on incomplete scan data. Such voids are oral regions of interest of the type referred to by flags 612-624. Menu 606 includes scan commands that allow the user to perform actions such as proceeding to the next scan, retrying the last scan, or rescanning a particular segment. By rescanning one or more segments, the user can provide scan data that fills the voids referred to by flags 612-624. This ensures that the final virtual 3D model generated based on the intraoral image is of high quality.

[0123] Figure 7 shows a schematic diagram of an exemplary embodiment of the computing device 700, which may execute a set of instructions to cause the machine to perform one or more of the methods described herein. In alternative embodiments, the machine may be connected to other machines in a local area network (LAN), intranet, extranet, or internet (e.g., network connection). The machine may operate as a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), mobile phone, web electronic device, server, network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or non-sequential) specifying the actions the machine should perform.

[0124] An exemplary computing device 700 includes a processing device 702, main memory 704 (e.g., read-only memory (ROM), flash memory, synchronous DRAM (SDRAM), and other dynamic random access memory (DRAM), static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and auxiliary memory (e.g., data storage device 728), which communicate with each other via a bus 708.

[0125] The processing device 702 represents one or more general-purpose processors, such as a microprocessor or a central processing unit. More specifically, the processing device 702 may be a composite instruction set compute (CISC) microprocessor, a reduced instruction set compute (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing another instruction set, or a microprocessor implementing a combination of instruction sets. The 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), or a network processor. The processing device 702 is configured to execute processing logic (instruction 726) in order to perform the operations and steps described herein.

[0126] The computing device 700 may further include a network interface device 722 for communicating with the network 764. The computing device 700 may also include a video display unit 710 (e.g., a liquid crystal display (LCD) or 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 generation device 720 (e.g., a speaker).

[0127] The data storage device 728 may include a machine-readable storage medium (or more specifically, a non-temporary computer-readable storage medium) 724 storing one or more sets of instructions 726 that embody one or more of the methods or functions described herein. A non-temporary storage medium refers to a storage medium other than a carrier wave. The instructions 726 may also be in the main memory 704 and / or the processing device 702, in whole or at least in part, while the computer device 700 is executing the instructions 726, and the main memory 704 and the processing device 702 also constitute computer-readable storage media.

[0128] The computer-readable storage medium 724 may also be used to store an intraoral scanning application 750, which may correspond to the component of the same name in Figure 1. The computer-readable storage medium 724 may also store a software library containing methods relating to the intraoral scanning application 750. In one exemplary embodiment, the computer-readable storage medium 724 is shown as a single medium, but the term “computer-readable storage medium” shall be interpreted to include a single medium or multiple mediums (e.g., centralized or distributed databases, and / or associated caches and servers) that store one or more sets of instructions. The term “computer-readable storage medium” shall also be interpreted to include any medium other than a carrier wave that can store or encode a set of instructions for a machine to execute and cause the machine to perform one or more of the methods of the present invention. Accordingly, the term “computer-readable storage medium” shall be interpreted to include solid-state memory and optical and magnetic media.

[0129] It should be understood that the above description is for illustrative purposes only and not for limitation. A reading and understanding of the above description will reveal numerous other embodiments. While embodiments of the present invention have been described with reference to specific exemplary embodiments, it will be recognized that the present invention is not limited to the embodiments described and can be implemented with modifications and alterations within the spirit and scope of the appended claims. Therefore, this specification and drawings should be considered illustrative and not limiting. Accordingly, the scope of the present invention shall be determined by reference to the entire scope of the appended claims and the equivalents qualified thereby.

[0130] [Note 1] A method for operating a system for intraoral scanning, The processing device of the system receives a first intraoral image of a dental area during an intraoral scanning session; The processing device identifies a candidate first oral region of interest from the first oral image; The processing device determines a value related to the first candidate oral region of interest; The processing device receives a second intraoral image of the dental area during the intraoral scanning session; The processing device compares the first intraoral image with the second intraoral image; The processing device determines that a) the second intraoral image recognizes the first intraoral region of interest candidate as an intraoral region of interest candidate, and b) the value exceeds a threshold, thereby confirming the first intraoral region of interest candidate as an intraoral region of interest; and The processing device performs the step of providing an index of the oral region of interest during the oral scanning session. How to operate a system for intraoral scanning. [Note 2] The step of confirming the first candidate oral region of interest as the oral region of interest is: A step of determining the alignment between the first intraoral image and the second intraoral image based on the geometric features shared by the first intraoral image and the second intraoral image; and The step of determining that the second intraoral image does not include a surface corresponding to the first intraoral region of interest candidate. A method for operating the system for intraoral scanning described in Appendix 1, including the method described in Appendix 1. [Note 3] The processing device identifies a candidate second oral region of interest from the first oral image; The processing device determines, based on a comparison of the second intraoral image with the first intraoral image, that the candidate second intraoral region of interest corresponds to the surface of the second intraoral image; and The processing device, in response to the execution of the decision, performs the step of concluding that the second candidate oral region of interest is not an additional oral region of interest. A method for operating the system for intraoral scanning described in Appendix 1 or 2. [Note 4] The step of identifying the first candidate oral region of interest is: A step of identifying multiple voxels in the first intraoral image that meet certain criteria; The step of determining a subset of the plurality of voxels that are in close proximity to each other; and The step of grouping the subset of the plurality of voxels into a volume that includes the first candidate oral region of interest. A method for operating a system for intraoral scanning as described in any one of the appendices 1 to 3, including the method described in any one of the appendices 1 to 3. [Note 5] The aforementioned criteria include the absence of image data, The method of operating the system for intraoral scanning described in Appendix 4, wherein the first candidate intraoral region of interest includes a void in the first intraoral image. [Note 6] A method for operating a system for intraoral scanning as described in Appendix 5, wherein the processing device performs the step of interpolating a shape relating to the void in at least one of the first intraoral image or the second intraoral image based on geometric features surrounding the void, wherein the index of the intraoral region of interest includes the shape of the void. [Note 7] A method for operating a system for oral scanning according to any one of the appendices 1 to 6, wherein the processing device performs the step of calculating a virtual model of the dental site based on a plurality of oral images after the completion of the oral scanning session, wherein the plurality of oral images include the first oral image and the second oral image. [Note 8] The processing device receives a new intraoral image that includes a region corresponding to the intraoral region of interest; The processing device determines the alignment between the new intraoral image and at least one of the first intraoral image or the second intraoral image; The processing device determines that the oral region of interest corresponds to the surface of the region in the novel oral image; and The processing device performs the step of removing the indicators of the oral region of interest. A method for operating the system for intraoral scanning described in any one of the appendices 1 to 7. [Note 9] The indicator for the oral region of interest includes a flag that indicates the oral region of interest, The aforementioned oral region of interest is hidden from the field of view of one or more of the dental areas. The method of operating the system for intraoral scanning according to any one of the appendices 1 to 8, wherein the flag is visible in the one or more fields of view. [Note 10] A method for operating a system for oral scanning according to any one of Annex 1 to 9, wherein the processing device provides feedback to the user of the oral scanner that has generated the first oral image and the second oral image, the feedback indicating a change in at least one of the movement of the oral scanner or the speed of the oral scanner that improves the quality of the oral scanning session. [Note 11] A method for operating a system for intraoral scanning according to any one of appendices 1 to 10, wherein the intraoral region of interest includes a collision surface between the first intraoral image and the second intraoral image. [Note 12] The step of confirming the first candidate oral region of interest as an oral region of interest is: The step of determining whether the candidate oral region of interest has one or more dimensions that deviate from geometric criteria. A method for operating a system for intraoral scanning as described in any one of the appendices 1 to 11, further including the above. [Note 13] A method for operating a system for intraoral scanning, The processing device of the system receives multiple intraoral images of dental areas; The processing device identifies a plurality of voxels that meet a certain criterion based on the plurality of intraoral images; The processing device determines a subset of the plurality of voxels that are in close proximity to each other; The processing device performs the steps of grouping the subset of the plurality of voxels into an oral region of interest; and The processing device performs the step of generating an index of the oral region of interest, wherein the oral region of interest is hidden in one or more fields of view of the dental area, and the index of the oral region of interest is visible in the one or more fields of view. How to operate a system for intraoral scanning. [Note 14] The processing device determines the classification of the oral region of interest; The processing device determines at least one of a sentence, a color, or an icon based on the classification; and The processing device performs the step of presenting the classification relating to the oral image in the index using at least one of the sentence, the color, or the icon. The method of operating the system for intraoral scanning described in Appendix 13. [Note 15] The processing device generates a first virtual model of the dental area based on a first scanning session of the dental area that was initially performed; The processing device generates a second virtual model of the dental area based on a second scanning session of the dental area performed a second time, wherein the plurality of intraoral images of the dental area are related to the second scanning session; and The processing device performs a step of determining a change in the dental area based on a comparison of the second virtual model with respect to the first virtual model, wherein the oral region of interest includes the change. A method for operating the system for intraoral scanning as described in Appendix 13 or 14. [Note 16] A method of operating the system for intraoral scanning as described in Appendix 15, wherein the change includes at least one of the following: tooth decay, gingival recession, tooth wear, tooth fracture, gingival disease, gingival discoloration, bruises, lesions, tooth tone, tooth color, improvement of or deterioration of orthodontic alignment. [Note 17] A method for operating a system for intraoral scanning according to any one of appendices 13 to 16, wherein the processing device performs the step of generating a virtual model of the dental area based on the plurality of intraoral images, wherein the intraoral region of interest is determined from the virtual model. [Note 18] The processing device determines the alignment of two or more of the plurality of intraoral images without generating a virtual model; and The processing device performs the step of identifying the oral region of interest based on a comparison of the two or more oral images. A method for operating the system for intraoral scanning described in any one of the appendices 13 to 16. [Note 19] The step of grouping the subset of the plurality of voxels into the oral region of interest is: A step of grouping the aforementioned multiple voxels into candidate areas of interest in the oral cavity; A step of determining whether the candidate oral region of interest has clinical importance based on the geometric characteristics of the candidate oral region of interest; and In response to the determination that the candidate oral region of interest has clinical importance, the step of confirming the candidate oral region of interest as the oral region of interest. A method of operating a system for intraoral scanning as described in any one of the appendices 13 to 18, including the method described in any one of the appendices 13 to 18. [Note 20] A method for operating a system for oral scanning according to any one of the appendices 13 to 19, wherein the oral region of interest includes at least one of the following: an oral region to be rescanned, an oral region suggesting a dental lesion, an oral region suggesting dental improvement, an oral region suggesting dental deterioration, or an oral region suggesting a foreign body. [Note 21] A method of operating a system for oral scanning according to any one of Appendix 13 to 20, wherein the indicator of the oral region of interest includes at least one of a rescan sequence, clinical importance, or size. [Note 22] The method of operating the system for intraoral scanning as described in Appendix 1, wherein the processing device performs the step of selecting the threshold based on the details of one or more patient cases, the details of one or more patient cases include treatment of the dental site. [Note 23] The aforementioned value is determined at least in part based on the size of the candidate oral region of interest, and the step of selecting the threshold is: A step of determining whether the procedure is an orthodontic procedure or a dental prosthetic procedure; A step of selecting a first threshold in accordance with the determination that the procedure is an orthodontic procedure; and A method for operating the system for intraoral scanning according to Appendix 22, comprising the step of selecting a second threshold in response to determining that the procedure is a dental prosthetic procedure. [Explanation of symbols]

[0131] 100 System for performing intraoral scanning and / or generating a virtual 3D model of the dental area 105 Computing Devices 108 Intraoral Scanning Applications 110 Datastores 115 Region of Interest Identification Module 118 Flagging Module 120 training modules 125 Model Generation Modules 135 Intraoral image data 138 Reference Data 150 Scanners 700 Computer Devices 702 Processing Device 704 Main Memory 706 Static Memory 708 Bus 710 Video Display Unit 712 Alphanumeric input devices 714 Cursor control device 720 Signal Generating Devices 722 Network Interface Devices 724 Computer-readable storage media 726 Command 728 data storage devices 750 Intraoral Scanning Applications 764 Network

Claims

1. A computer-readable storage medium containing instructions that, when executed by a processing device, cause the processing device to perform an action related to the detection of tooth decay, wherein the action is: A step of receiving first oral scan data generated in a first time, The steps include analyzing the first oral scan data and determining a first spot or depression at a first time from the first oral scan data, The steps include receiving second oral scan data generated at a second time, The steps include analyzing the second oral scan data and determining a second spot or depression at the second time from the second oral scan data, A step of comparing the second spot or depression at the second time with the first spot or depression at the first time, A step of tracking multiple caries over time based on the difference between the second spot or depression at the second time and the first spot or depression at the first time, A step of determining the importance rank of each of the aforementioned multiple caries based on multiple criteria, A step of suppressing the indicator for the first caries in the plurality of caries based on the importance rank of the first caries, A step of providing a second indicator of caries in the plurality of caries, wherein the indicator is provided as the contour of the remaining tooth, and the first indicator of caries is not provided. Computer-readable storage medium.

2. The aforementioned operation is, The steps include identifying the teeth represented in the first oral scan data, The steps include identifying at least one of a first spot or a first depression on the tooth from the first oral scan data, The steps include determining that at least one of the first spot or the first depression indicates the second caries in the first oral scan data, The steps include identifying the teeth represented in the second oral scan data, The steps include identifying at least one of a second spot or a second depression on the tooth from the second oral scan data, The further step includes determining that at least one of the second spot or the second depression indicates the second caries in the second oral scan data, The computer-readable storage medium according to claim 1.

3. The computer-readable storage medium according to claim 2, wherein the steps of identifying at least one of a first spot or a first depression on the tooth from the first oral scan data and determining that at least one of the first spot or the first depression indicates a second tooth decay are performed via shape recognition.

4. The aforementioned operation is, The steps include determining the shape of the oral region of interest representing the second caries, The steps include generating the contour of the shape of the oral region of interest representing the second tooth decay, A computer-readable storage medium according to claim 1, further comprising:

5. The aforementioned operation is, The step of displaying the second area of ​​oral interest representing tooth decay in comparison with the surrounding image, A computer-readable storage medium according to claim 1, further comprising:

6. The aforementioned operation involves the step of identifying the multiple caries by applying machine learning, A computer-readable storage medium according to claim 1, further comprising:

7. The computer-readable storage medium according to claim 6, wherein at least one of pooled patient data or educational patient data, including descriptions of teeth and corresponding indicators, is used to identify the plurality of caries.

8. The aforementioned operation is, A step of generating a first virtual three-dimensional (3D) model including one or more teeth of a patient using the first oral scan data, wherein the step of analyzing the first oral scan data and determining the first spot or depression from the first oral scan data includes a step of analyzing the first virtual 3D model generated using the first oral scan data, wherein the first spot or depression is identified on the first virtual 3D model, A step of generating a second virtual three-dimensional 3D model including one or more teeth of the patient using the second oral scan data, wherein the step of analyzing the second oral scan data and determining the second spot or depression from the second oral scan data includes a step of analyzing the second virtual 3D model generated using the second oral scan data, wherein the second spot or depression is identified on the second virtual 3D model, A computer-readable storage medium according to claim 1, further comprising:

9. The computer-readable storage medium according to claim 8, wherein the step of comparing the second spot or recess with the first spot or recess includes the step of comparing the second virtual 3D model with the first virtual 3D model.

10. The computer-readable storage medium according to claim 9, wherein the step of comparing the second virtual 3D model with the first virtual 3D model includes the step of determining the alignment between the first virtual 3D model and the second virtual 3D model based on geometric features shared by the first virtual 3D model and the second virtual 3D model.

11. The aforementioned operation is, A step of generating a virtual three-dimensional (3D) model including one or more teeth of a patient using at least one of the first oral scan data or the second oral scan data, The steps include determining the oral area of ​​interest, including the second caries-related area, A step of generating an index for the oral region of interest, including the second caries, wherein the index includes a flag that points to the oral region of interest on the virtual 3D model, the oral region of interest is hidden in one or more views of the virtual 3D model, and the flag is visible in the one or more views; A computer-readable storage medium according to claim 1, further comprising:

12. The step of determining the oral area of ​​interest is: The steps include identifying a plurality of voxels that satisfy a first criterion in the virtual 3D model, The steps include determining a subset of the aforementioned voxels that are close to each other, The steps include: grouping the subset of the plurality of voxels into a volume; A computer-readable storage medium according to claim 11, including the following:

13. The computer-readable storage medium according to claim 11, wherein the aforementioned criteria include the size of the tooth decay.

14. A computer-readable storage medium containing instructions for performing tooth decay detection, A computer device comprising a processing device that executes the instructions of the computer-readable storage medium, wherein, upon execution of the instructions, the processing device The first oral scan data generated in the first time period is received, The first oral scan data is analyzed, and the first spot or depression at the first time is determined from the first oral scan data. Receive the second oral scan data generated in the second time period. The second oral scan data is analyzed, and the second spot or depression at the second time is determined from the second oral scan data. The second spot or depression at the second time is compared with the first spot or depression at the first time, Based on the difference between the second spot or depression at the second time and the first spot or depression at the first time, multiple caries are tracked over time. Based on multiple criteria, the importance ranking of each of the aforementioned multiple caries is determined, Based on the importance ranking of the first tooth decay, the indicator for the first tooth decay in the plurality of tooth decays is suppressed. A second indicator of tooth decay is provided in the aforementioned plurality of caries, the indicator is provided as the outline of the remaining tooth, and the first indicator of tooth decay is not provided. Computer device.

15. The processing device further, Identifying the teeth represented in the first oral scan data, From the first oral scan data, at least one of the first spot or first depression on the tooth is identified. It is determined that at least one of the first spot or the first depression indicates the second caries in the first oral scan data. Identifying the teeth represented in the second oral scan data, From the second oral scan data, at least one of the second spot or second depression on the tooth is identified. It is determined that at least one of the second spot or the second depression indicates the second caries in the second oral scan data. The computer device according to claim 14.

16. A computer-readable storage medium containing instructions that, when executed by a processing device, cause the processing device to perform an action related to the detection of tooth decay, wherein the action is: A step of receiving first oral scan data generated in a first time, The steps include receiving second oral scan data generated at a second time, The steps include comparing the second oral scan data with the first oral scan data, Based on the results of the comparison, the step of determining an oral area of ​​interest that represents multiple caries that occurred in one or more teeth between the first time and the second time, A step of determining the importance rank of each of the aforementioned multiple caries based on multiple criteria, A step of suppressing the indicator for the first caries in the plurality of caries based on the importance rank of the first caries, A step of determining an indicator of an oral area of ​​interest representing a second caries in the plurality of caries, wherein the indicator includes the contour of the remaining tooth; A step of outputting the indicator that shows the oral region of interest representing the second caries of the tooth, wherein no indicator for the first caries is provided. and, including Computer-readable storage medium.

17. The aforementioned operation is, The steps include analyzing the first oral scan data to determine that the tooth in the first oral scan data does not have the second cavity, The steps include analyzing the second oral scan data to determine whether the tooth in the second oral scan data contains the second caries, This also includes, The computer-readable storage medium according to claim 16.

18. The aforementioned operation is, The steps include identifying at least one of the spots or depressions on the teeth from the second oral scan data, The further step includes determining that at least one of the spot or the depression indicates the second tooth decay, The computer-readable storage medium according to claim 17.

19. The computer-readable storage medium according to claim 18, wherein the steps of identifying at least one of the spot or the depression on the tooth and determining that at least one of the spot or the depression indicates the second tooth decay are performed via shape recognition.

20. The aforementioned operation is, The steps include determining the shape of the oral region of interest representing the second caries, The process further includes the step of generating the contour of the shape of the oral region of interest representing the second tooth decay, The computer-readable storage medium according to claim 16.

21. The aforementioned operation is, The steps include generating a first virtual three-dimensional (3D) model including one or more teeth of the patient using the first oral scan data, The method further includes the step of generating a second virtual three-dimensional 3D model including one or more teeth of the patient using the second oral scan data, The computer-readable storage medium according to claim 16, wherein the step of comparing the second oral scan data with the first oral scan data includes the step of comparing the second virtual 3D model with the first virtual 3D model.

22. The aforementioned operation is, As a result of the above comparison, a step of determining a first difference between the first virtual 3D model and the second virtual 3D model in a first dental area including the first tooth among the one or more teeth, A step of determining that the first difference indicates the second tooth decay, A computer-readable storage medium according to claim 21, further comprising:

23. The aforementioned operation is, As a result of the above comparison, a step is to determine a first difference between the second oral scan data and the first oral scan data in a first dental area including the first tooth, A step of determining that the first difference indicates the second tooth decay, A computer-readable storage medium according to claim 21, further comprising:

24. The aforementioned operation is, The method further includes the step of generating a virtual three-dimensional (3D) model including one or more teeth of the patient using at least one of the first or second oral scan data, The indicator includes a flag that points to the oral region of interest of the second caries on the virtual 3D model, wherein the oral region of interest of the second caries is hidden in one or more views of the virtual 3D model, and the flag is visible in the one or more views. The computer-readable storage medium according to claim 21.

25. A computer-readable storage medium containing instructions for performing tooth decay detection, A computer device comprising a processing device that executes the instructions of the computer-readable storage medium, wherein the processing device is The first oral scan data generated in the first time period is received, Receive the second oral scan data generated in the second time period. The first oral scan data and the second oral scan data are compared, Based on the results of the comparison, an oral region of interest is determined that represents multiple caries that occurred in one or more teeth between the first time and the second time. Based on multiple criteria, the importance ranking of each of the aforementioned multiple caries is determined, Based on the importance ranking of the first tooth decay, the indicator for the first tooth decay in the plurality of tooth decays is suppressed. An index for the oral region of interest representing the second caries in the aforementioned plurality of caries is determined, and the index includes the contour of the remaining tooth. The system outputs the indicator showing the oral area of ​​interest representing the second caries of the tooth, and does not provide an indicator for the first caries. Computer device.

26. The processing device is The first oral scan data is analyzed, and it is determined that there are no cavities in the teeth in the first oral scan data. The second oral scan data is analyzed, and it is determined that the tooth in the second oral scan data contains the second caries. The computer device according to claim 25.

27. Memory and A computer device comprising a processor operably connected to the memory, wherein the processor is The first oral scan data of the dental area generated in the first time is received. The second oral scan data of the dental area generated in the second time is received. Based on the difference between the first spot or depression at the first time from the first oral scan data and the second spot or depression at the second time from the second oral scan data, multiple caries in the dental area are tracked over time. Based on multiple criteria, the importance ranking of each of the aforementioned multiple caries is determined, Based on the importance ranking of the first tooth decay, the indicator for the first tooth decay in the plurality of tooth decays is suppressed. A second indicator of tooth decay is provided in the aforementioned plurality of caries, the indicator is provided as the outline of the remaining tooth, and the first indicator of tooth decay is not provided. Computer device.

28. The aforementioned processor further, By analyzing the first oral scan data, a first example of a dental area without cavities is determined. The second oral scan data is analyzed to determine a second example of the dental area including the second caries. The computer device according to claim 27.

29. The aforementioned dental area is a tooth. The aforementioned processor further, From the second oral scan data, at least one of the spots or depressions on the teeth is identified. The presence of at least one of the spot or the depression indicates the second tooth decay. The computer device according to claim 27.

30. The computer device according to claim 29, wherein the steps of identifying at least one of the spot or the depression on the tooth and determining that at least one of the spot or the depression indicates the second tooth decay are performed via shape recognition.

31. The aforementioned processor further, The shape of the oral region of interest representing the second caries is determined, To generate the outline of the shape of the oral region of interest representing the second tooth decay, The computer device according to claim 27.

32. The aforementioned processor further, Using the first oral scan data, a first virtual three-dimensional (3D) model including one or more teeth of the patient is generated. Using the second oral scan data, a second virtual three-dimensional 3D model including one or more of the patient's teeth is generated. The second oral scan data and the first oral scan data are compared. The computer device according to claim 27.

33. The aforementioned processor further, As a result of the above comparison, a first difference is determined between the first virtual 3D model and the second virtual 3D model in the first dental region including the dental region. The first difference is determined to indicate the second tooth decay. The computer device according to claim 32.

34. The aforementioned processor further, A first difference is determined between the second oral scan data and the first oral scan data in the dental region, and the dental region includes the first tooth. The first difference is determined to indicate the second tooth decay. The computer device according to claim 27.

35. The aforementioned processor further, Using at least one of the first or second oral scan data, a virtual three-dimensional (3D) model including one or more teeth of the patient is generated. A flag is generated that points to the second carious tooth on the virtual 3D model. The computer device according to claim 27.

36. When executed by a processing device, A step of receiving first oral scan data of a dental area generated in a first time, The steps include receiving second oral scan data of the dental area generated at a second time, A step of tracking multiple caries in the dental area over time based on the difference between a first spot or depression at a first time from the first oral scan data and a second spot or depression at a second time from the second oral scan data, A step of determining the importance rank of each of the aforementioned multiple caries based on multiple criteria, A step of suppressing the indicator for the first caries in the plurality of caries based on the importance rank of the first caries, A step of providing a second indicator of caries in the plurality of caries, wherein the indicator is provided as the contour of the remaining tooth, and the first indicator of caries is not provided. Includes an instruction that causes the processing device to perform an operation including, Computer-readable storage medium.

37. The aforementioned operation is, The first oral scan data is analyzed to determine that there are no cavities in the dental area, The procedure further includes the step of analyzing the second oral scan data to determine that the dental area includes the second caries, The computer-readable storage medium according to claim 36.

38. The aforementioned dental area is a tooth. The aforementioned operation is, The steps include identifying at least one of the spots or depressions on the teeth from the second oral scan data, The further step includes determining that at least one of the spot or the depression indicates the second tooth decay, The computer-readable storage medium according to claim 36.

39. The computer-readable storage medium according to claim 38, wherein the steps of identifying at least one of the spot or the depression on the tooth and determining that at least one of the spot or the depression indicates the second tooth decay are performed via shape recognition.

40. The aforementioned operation is, The steps include determining the shape of the oral region of interest representing the second caries, The step of generating the contour of the shape of the oral region of interest representing the second tooth decay, further comprising: The computer-readable storage medium according to claim 36.

41. The aforementioned operation is, The steps include generating a first virtual three-dimensional (3D) model including one or more teeth of the patient using the first oral scan data, The steps include generating a second virtual three-dimensional 3D model including one or more teeth of the patient using the second oral scan data, The procedure further includes the step of comparing the second oral scan data with the first oral scan data. The computer-readable storage medium according to claim 36.

42. The aforementioned operation is, As a result of the above comparison, a step is to determine a first difference between the first virtual 3D model and the second virtual 3D model in the first dental region including the dental region, The step of determining that the first difference indicates the second caries, further comprising: The computer-readable storage medium according to claim 41.

43. The aforementioned operation is, A step of determining a first difference between the second oral scan data and the first oral scan data in the dental region, wherein the dental region includes a first tooth, The step of determining that the first difference indicates the second caries, further comprising: The computer-readable storage medium according to claim 36.

44. The aforementioned operation is, A step of generating a virtual three-dimensional (3D) model including one or more teeth of a patient using at least one of the first oral scan data or the second oral scan data, The further step includes generating a flag that points to the second caries on the virtual 3D model, The computer-readable storage medium according to claim 36.

Images