Dental impression

Abstract

A method for optical intraoral imaging of oral anatomical structures via an intraoral scanner, the method comprising providing initial data related to the oral anatomical structures and / or the intraoral scanner, using the initial data to calculate the number of intraoral images to be captured via the intraoral scanner, obtaining the number of intraoral images at a given location in the oral anatomical structure via the intraoral scanner, and rendering a two-dimensional intraoral image that is more optimally exposed from at least one of the obtained intraoral images and the initial data, or from a plurality of the obtained intraoral images. The present teachings also relate to a system, a dental scanner, a software product, a use, and a storage medium.

Description

Technical Field

[0001] The present disclosure generally relates to computer-implemented methods and systems for dental scanning and the resulting 3D models.

Background Art

[0002] For example, an intraoral dental scanner, or simply a dental scanner, is used to capture a digital dental impression of a patient. The impression is typically in the form of a three-dimensional (“3D”) model and can relate to features of interest of oral anatomical structures such as the patient's teeth and / or soft and / or hard tissues within the oral cavity. The impression can be stored digitally and / or transmitted to a dental healthcare provider. The digital impression can also be used for other purposes such as the production of dental restorations and the planning or execution of dental treatment.

[0003] Most dental scanners are based on the principle of structured light. Such scanners include means for projecting a light pattern onto the intraoral geometry. When the pattern is projected onto the intraoral geometry, it appears contoured according to the shape of the geometry. The scanner also includes a camera for capturing the light reflected from the geometry that is associated with the contours formed in the projected pattern. The signal from the camera is then sent to a computing unit for extracting the shape information of the intraoral geometry. Thereafter, a digital impression or 3D model of the intraoral geometry can be reconstructed from the shape information, which can be in the form of a point cloud, a mesh, or an alternative shape representation.

[0004] US2021267461A1 discloses an optical measurement method for three-dimensionally detecting the surface of an object using an optical recording unit. The optical recording unit is moved relative to the object during a measurement time interval, a height map is continuously detected by the recording unit at a recording frequency, and the detected height maps are each added to the overall height map and displayed.

[0005] Recently, self-scanning or self-using dental scanners have also been proposed. Such scanners can enable patients to scan their own oral cavities or generally enable non-medical personnel to perform scanning operations. This can save the user's cost compared to having a dentist or specialist perform the scan and / or improve dental health monitoring by performing more accurate and / or faster scans at home. When targeting the customer market directly, lower-cost solutions are generally more attractive.

[0006] From this, the need for improved scanning methods and devices has been recognized. SUMMARY OF THE INVENTION

[0007] At least some of the limitations associated with the foregoing can be overcome by the subject matter of the appended independent claims. At least some of the additional advantageous alternatives will be outlined in the dependent claims.

[0008] The applicant has recognized, through inventive efforts, that the image acquisition quality can be made at least partially independent of the intraoral light conditions at the time of acquisition. Advantageously, for higher acquisition quality, a number of intraoral images can be traded in. More advantageously, a number value can be determined prior to performing the acquisition, which can have the advantage of saving time by capturing only the number of intraoral images necessary to obtain a predetermined exposure quality for a particular acquisition. Another advantage of doing so can be that the requirements for the light source in the intraoral scanner can be at least partially eliminated. In most intraoral scanners, a light source is essential to irradiate the oral anatomical structures so that intraoral images are captured with appropriate exposure. However, this can cause problems such as unwanted reflections on the teeth, images with locally overexposed areas, shadows, scattering, and translucent effects. Moreover, the light source can cause additional heat generation in the scanner and an increase in the cost and size of the scanner. In particular, in optical intraoral imaging, such problems can be overly prominent. The present teachings can mitigate these problems.

[0009] More specifically, from a first aspect, a computer-implemented method for optical intraoral imaging of oral anatomical structures via an intraoral scanner can be provided, the method comprising - providing initial data related to the oral anatomical structures and / or the intraoral scanner, and - using the initial data to calculate the number of intraoral images to be captured via the intraoral scanner, and - acquiring, via the intraoral scanner, the number of intraoral images at a given location in the oral anatomical structures or of a given location, and - rendering a two-dimensional intraoral image that is more optimally exposed from at least one of the acquired intraoral images and the initial data, or from a plurality of acquired intraoral images and comprising.

[0010] From this, it is possible to utilize a combination of the initial data and at least one or a plurality of the acquired intraoral images among the acquired intraoral images to provide a more optimally exposed two-dimensional intraoral image. The rendered image is, from this, more optimally exposed compared to any of the intraoral images captured via the intraoral scanner. The present teachings can, from this, substantially reduce the requirements for artificial light sources in the intraoral scanner in a minimal sense. From this, a weaker light source may be sufficient to provide a rendered image that is at least similar to a high-quality intraoral image captured by a scanner that requires a brighter light source. This substantially reduces the heat generated and, from this, can reduce the power consumption of the intraoral scanner. Moreover, the intraoral scanner can be made less expensive and more compact compared to a scanner having a brighter light source. Another advantage of the present teachings can be that it is possible to reduce or substantially eliminate the undesirable effects associated with bright light sources. For example, in conventional intraoral scanners, the bright light from the light source can cause undesirable effects such as reflection, translucency of the dentition, and shadow effects. Such undesirable effects can be at least partially avoided using the present teachings. Additionally or alternatively, the intraoral scanner can be equipped with a general-purpose camera that is not optimized for dental use. A general-purpose camera means a sensor used in household electrical appliances such as mobile phones, laptops, or tablets. The present teachings can, from this, enable the use of off-the-shelf components, which can result in cost savings in the production of such intraoral scanners. Preferably, the intraoral scanner is not equipped with any light source at all. From this, the intraoral scanner either uses any ambient light available within the oral cavity or performs either rendering a more optimally exposed 2D intraoral image from an intraoral image with insufficient exposure.

[0011] According to an aspect, a more optimally exposed 2D intraoral image or 2D rendering image is provided to a human machine interface (HMI) device. From this, the user can be provided with a more realistic image of the intraoral anatomical structure despite insufficient light conditions in the oral cavity. Preferably, a plurality of rendered images are provided to the HMI as a data stream. Thus, a realistic video or animation can be provided to the user despite insufficient illumination in the patient's oral cavity.

[0012] According to an aspect, the method also - providing a plurality of more optimally exposed two-dimensional intraoral images that capture different locations of the intraoral anatomical structure, - using the plurality of more optimally exposed two-dimensional intraoral images to reconstruct a three-dimensional digital impression of the intraoral anatomical structure comprises.

[0013] From this, a plurality of rendered images, or more optimally exposed two-dimensional intraoral images, are used to provide a 3D digital impression of the intraoral anatomical structure. The reconstruction operation thus analyzes the rendered 2D images and converts them into a 3D digital impression, for example, a surface model or any other suitable format. Thus, a 3D model of the intraoral anatomical structure can be provided. The 3D model can thus reduce gaps caused by the undesirable effects of bright light sources or reduce inaccurate parts. The digital impression can be used to perform dental procedures and / or to manufacture dental objects for the patient.

[0014] Preferably, the reconstruction of the 3D digital impression is performed via data-driven reconstruction logic.

[0015] "More optimally exposed 2D intraoral image" refers to a 2D color image of a patient's oral cavity that is of higher quality in terms of noise and / or contrast and / or color rendition and / or brightness and / or sharpness compared to a single image of the same situation generated by a camera using the same level of irradiation.

[0016] "More optimally exposed" thus refers to a higher image quality in terms of noise and / or contrast and / or color rendition and / or brightness and / or sharpness compared to an image obtained via an intraoral scanner, especially in difficult environments such as low light environments. More advantageously, a more optimally exposed 2D intraoral image as generated herein enables the reduction of artifacts introduced by the optical properties of the materials visible within the image. Depending on the lighting conditions, artifacts such as translucency and / or reflectivity that may be present in conventional images can be substantially reduced in a more optimally exposed 2D intraoral image.

[0017] "Data-driven reconstruction logic" refers to logic that is trained with a teacher using reconstruction training data. According to an aspect, the reconstruction training data may comprise past rendered images and their corresponding reconstructed digital impressions or 3D models. As discussed, the data-driven reconstruction logic can reconstruct a 3D surface model from a 2D rendered image that is an optical imaging type.

[0018] Alternatively or additionally, the data-driven reconstruction logic can be trained without a teacher.

[0019] The data-driven reconstruction logic is provided with a rendered image as an input. The data-driven reconstruction logic provides a digital impression as an output.

[0020] "Initial data" in this context refers to data related to oral anatomical structures and / or data related to an intraoral scanner. In particular, the initial data comprises information related to oral anatomical structures and / or an intraoral scanner that can be used to at least determine the light conditions within the oral cavity and / or the movement of the intraoral scanner at or around the location of the intraoral scanner. Therefore, the initial data can comprise, for example, the aperture and / or exposure settings of the intraoral scanner, light measurements (e.g., intensity) in the oral anatomical structure, kinematic data measured via one or more sensors of the intraoral scanner, and / or any one or more of the data from one or more of the intraoral images previously captured within the oral cavity. The sensors can be any one or more of inertial sensors such as accelerometers and / or gyroscopes and / or magnetometers and / or light meters and / or position sensors (absolute and / or relative), and / or proximity sensors.

[0021] The initial data is used to determine how many intraoral images should be captured at a given location where the intraoral scanner is present within the oral cavity. In some cases, the number can be determined from the initial data, which can be either a fixed value or not. From this, in some cases, the number of intraoral images captured is the same at different locations within the oral cavity. In other cases, the number can be a dynamic value that varies at different locations where the intraoral images are captured. From this, the intraoral scanner can record from one to several intraoral images at a given location within the patient's oral cavity. From this, the number of images is determined from the initial data or, alternatively, from the burst parameters within the initial data. "Burst parameters" refer to a predefined specification of the number of intraoral images to be captured at a given location, which can be either part of the initial data or not and is used in situations where the number is not calculated based on the remaining initial data.

[0022] In some cases, the kinematic data can be used to determine how many intraoral images should be captured and / or to correct or compensate for artifacts induced by movement in one or more of the acquired intraoral images. For example, due to low light conditions and long exposure times in the oral cavity, even a slight movement of the intraoral scanner can introduce artifacts such as blurring in one or more of the intraoral images. According to the present teachings, information regarding the movement, such as the direction and / or type and / or amount of movement, is determined from the kinematic data and corrected or compensated for in the rendered 2D image. Alternatively or additionally, in some cases, the kinematic data can be used to determine the image acquisition settings for capturing the intraoral images such that any artifacts can be avoided or minimized. In some cases, the kinematic data can be at least partially derived by visual odometry via the intraoral scanner.

[0023] "Obtaining the intraoral images of the number at a given location in the oral anatomical structure" means including images captured at locations with or without the same field of view. From this, the field of view of the intraoral scanner can change during the capture of more than one intraoral image. A small movement of the position and / or angle of the intraoral scanner is thus included in the acquisition at a given location. In other words, intraoral images having at least some common imaging portion of the oral anatomical structure within a given time period can be considered as intraoral images obtained at a given location in the oral anatomical structure. This time period can be several seconds, but in some cases, it can be less than 1 second, for example, less than 1 / 2 second. From this, it can also be said that these intraoral images can be obtained at or around a given location in the oral anatomical structure.

[0024] According to an aspect, the initial data comprises any one or more of the light intensity, aperture, and / or exposure settings measured in the oral anatomical structure, the kinematic data measured via one or more sensors of the intraoral sensor, and / or the data from previously acquired intraoral images, which may include any one or more of intraoral images, rendered images, reconstructed digital impressions, or 3D models.

[0025] According to an aspect, at least some of the image acquisition settings of the intraoral scanner are determined using the initial data. The acquisition settings can be any one or more of exposure time, aperture, depth of focus, lens configuration, and sensor sensitivity or gain.

[0026] According to another aspect, rendering a more optimally exposed two-dimensional intraoral image comprises - analyzing each of the acquired intraoral images to select one or more regions of a desired exposure, and - combining the selected regions to provide a more optimally exposed two-dimensional intraoral image. This is included.

[0027] Therefore, the acquired intraoral images can be analyzed and scored for quality and / or lighting conditions, either as a whole or in part for each of the intraoral images. Combining high-score intraoral images or parts thereof can provide a rendered image. For example, each of the images can be divided into parts such as regions or groups of pixels, and each part of each image can be analyzed or compared with corresponding parts of other intraoral images. From this, the desired parts, for example, the parts with the highest scores, can be selected and combined to provide a rendered image. Therefore, according to an aspect, the rendering of a more optimally exposed 2D intraoral image comprises adjusting at least one image characteristic of at least one of the acquired intraoral images and / or at least one of the selected regions. The image characteristics to be adjusted can be any one or more of brightness, color, noise, contrast, saturation, intensity, and transformation and / or distortion to compensate for any movement during the burst. From this, adjustments can be made to achieve improvements such as any one or more of reducing reflection, reducing shadow, reducing overexposure, and reducing the translucent effect, to achieve harmony with one or more other intraoral images (e.g., to emphasize consistency), and to achieve distinction from one or more other intraoral images (e.g., to emphasize differences). From this, it can combine all the pixels of all the acquired images using pixel-based weights. Alternatively, only one of the images can be used to select the desired region, then the regions corresponding to the desired region can be selected from every other image, and these regions can be combined to provide an optimally exposed 2D intraoral image. As a further alternative, a group or all of the acquired images can be used to select the desired region, and then the desired regions can be combined to provide an optimally exposed 2D intraoral image.

[0028] Preferably, the rendering is performed at least in part via data-driven rendering logic.

[0029] "Data-driven rendering logic" refers to data-driven logic that is trained with supervision using rendering training data. According to an aspect, the rendering training data comprises a plurality of past intraoral images and their corresponding rendered images. Preferably, the rendering training dataset comprises a plurality of sets of past intraoral images and their corresponding past rendered images. Alternatively or additionally, the data-driven rendering logic can be trained without supervision.

[0030] From this, the data-driven rendering logic generates, as output, a two-dimensional intraoral image or a rendered image that is more optimally exposed when the acquired intraoral image, and preferably the initial data, is provided as its input. As previously discussed, the acquired intraoral image can in some cases be a single image.

[0031] In some cases, there can be more than one data-driven logic used to perform different operations. Any two or more of the data-driven logics can be combined as one or more combined logics. According to an aspect, all of the data-driven logics are in the form of the same combined logic that is trained end-to-end using end-to-end training data comprising past upstream inputs and their corresponding desired past results downstream of the output of the combined logic.

[0032] According to an aspect, at least some of the parts or regions are selected via segmentation logic. The segmentation logic is preferably at least partly data-driven logic, or the segmentation logic can be at least partly data-driven segmentation logic. The segmentation logic can perform segmentation and / or location-specific operations for each of the intraoral images.

[0033] As used herein, the "segmentation operation" refers to a computerized processing operation that ends with the boundary setting of at least one anatomical feature of an intraoral structure having a computer-generated feature boundary and / or an intraoral region. The intraoral region can be, for example, a region that is typically difficult to capture during imaging. These regions can depend on not only the material (anatomical features) but also the illumination and the viewing angle.

[0034] Segmentation logic can perform a segmentation operation to detect one or more preselected anatomical features. From this, the segmentation logic can segment each intraoral image for detection. From this, the segmentation logic can extract an attribute or one or more objects of interest from at least one of the intraoral images. The segmentation logic can classify all the pixels in each intraoral image into objects according to their context such that each pixel is assigned to a specific object. Alternatively or in addition, the segmentation logic can classify all the pixels in each intraoral image into classes according to their context such that each pixel is assigned to a specific class. Non-limiting examples of segmentation operations when applied using the present teachings can be the contours around preselected anatomical features such as a specific tooth or even a group of teeth. Another non-limiting example is the contour around a specific lesion. The segmented contours correspond to the shape of each anatomical feature visible in each intraoral image.

[0035] There can be a plurality of segmented objects in any given intraoral image.

[0036] The segmentation logic can comprise an analysis model that uses any suitable segmentation algorithm, such as point and line detection, edge linking, and / or thresholding methods, histograms, adaptive types, and the like.

[0037] Preferably, the segmentation logic is at least partially a data-driven logic trained with supervision using a segmentation training dataset comprising a plurality of pre-segmented past intraoral images. Alternatively or additionally, the data-driven segmentation logic is trained without supervision. The data-driven segmentation logic thus receives the acquired intraoral image as input and provides the segmented intraoral image as output.

[0038] In some cases, the segmentation logic or another logic may also perform a location-specifying operation, which may be performed via the analysis unit and / or the data-driven unit.

[0039] The “location-specifying” operation in this context refers to a computerized processing operation that ends at a more general area or location where a particular anatomical feature is located in the intraoral image. Location-specifying may also result in a boundary where the anatomical feature is located, but unlike the segmentation operation, pixel-by-pixel evaluation is not performed. Thus, the location-specifying boundary, if generated, may be wider than the segmented boundary around a given anatomical feature. Additionally or alternatively, the location-specifying operation may end by annotating or tagging a particular anatomical feature and / or an intraoral area of an oral anatomical structure in the intraoral image, for example, at any location on the anatomical feature. The intraoral area may be an area that is typically difficult to capture during imaging. These areas may depend not only on the material (anatomical feature) but also on illumination and the viewing angle.

[0040] Viewed from another perspective, the use of 3D digital impressions as generated herein for performing medical procedures such as dental procedures and / or for manufacturing dental objects and / or for display on an HMI device can also be provided.

[0041] Viewed from yet another perspective, one or more of the more optimally exposed two-dimensional intraoral images as generated herein can also be used to reconstruct digital dental impressions and / or display them in a human-machine interface device and / or train and / or validate data-driven logic.

[0042] Viewed from another perspective, a system can also be provided that comprises means for performing any of the steps of the methods disclosed herein.

[0043] For example, a system can be provided that comprises an interface for operably connecting to an intraoral scanner and one or more computing units, any of the computing units being - to provide initial data related to oral anatomical structures and / or the intraoral scanner, and - to use the initial data to calculate the number of intraoral images to be captured via the intraoral scanner, and - to acquire the number of intraoral images at a given location in the oral anatomical structure via the intraoral scanner, and - to render a more optimally exposed two-dimensional intraoral image from at least one of the acquired intraoral images and the initial data or from a plurality of acquired intraoral images and is configured to perform.

[0044] The system can be, for example, a scanning system or an add-on to a scanning system. According to an aspect, the system can be implemented on a distributed system such as on a cloud computing platform. Intraoral images and / or rendered images and / or digital impressions may or may not be provided to the same memory storage device. The intraoral scanner can comprise at least one of the computing units and / or can be operably connected, either wired or wirelessly, to some of the computing units, for example, via a connection interface and / or a network interface. Intraoral images and / or rendered images and / or digital impressions may or may not be provided to the same memory storage device. The memory storage device can be local to the intraoral scanner and / or can be part of a remote service or a cloud-based service.

[0045] Viewed from another perspective, a non-transitory computer-readable storage medium storing a computer software product or program comprising instructions for causing any of the computing units to execute any of the steps of the methods disclosed herein can also be provided when executed by one or more suitable computing units.

[0046] Also provided can be a data storage medium storing thereon one or more of the more optimally exposed two-dimensional intraoral images and / or digital impressions as generated herein.

[0047] "Oral anatomical structures" refer to regions and anatomical parts within a patient's oral cavity. As such, oral anatomical structures comprise structures such as dentition and / or gums and / or other parts. In some cases, at least some of the oral structures can be artificial structures such as one or more dental replacements or prostheses, for example, dental crowns, bridges, veneers, implants, etc. Alternatively or in addition, those parts can in some cases be a scan body (or scan bodies) or even any other natural and / or artificial structures.

[0048] "Anatomical features" or dental features refer to information related to oral structures such as the patient's dentition and / or gums and / or other features of the oral anatomical structures. Alternatively or in addition, at least some of the oral structures in which anatomical features are recorded can be one or more dental replacements, such as one or more artificial structures such as dental crowns, bridges, veneers, implants, etc. Alternatively or in addition, anatomical features can in some cases even be scan bodies (or scan bodies), or other natural and / or artificial structures. Anatomical features, which are usually in the form of surface data, are recorded to construct a digital impression of the patient's oral anatomical structure. Usually, structures that are firmly attached to the patient's jaw are more interesting for producing digital impressions.

[0049] Alternatively or in addition, anatomical features can even be information related to lesions or conditions. As non-limiting examples, lesions or conditions can be any one or more of tooth fractures or cracks or caries, impactions, or any other visually characterizable condition of the oral anatomical structure or any part thereof. Some non-limiting examples of oral features or dental features are any one or more of the shape, contour, or boundary of any one or group of teeth, their arrangement, sequence in any direction, presence or absence of expected features such as the type of a given tooth. Alternatively or in addition, anatomical features can also be shapes, regions, or physical properties detected within an area of interest such as a contour or boundary. Alternatively or in addition, anatomical features can also be the interrelationship between two different anatomical features or can be detected through that interrelationship. For example, the boundary between a tooth and the gum.

[0050] "Intraoral scanner" refers to a device or system used to acquire intraoral images of a patient's oral cavity. The intraoral scanner can be in the form of a wand or can include a wand portion for insertion into the patient's mouth to acquire intraoral images. In some cases, the intraoral scanner can be part of a configuration that includes a camera unit that can be coupled or attached to another device. This coupling can be a removable or permanent physical attachment or can be a flexible coupling, such as via a connectivity interface, e.g., wired or wireless. The camera unit can be positioned inside or in front of the mouth.

[0051] "Intraoral image" refers to an optical image of oral anatomical structures captured within a patient's oral cavity. Intraoral images are acquired via an intraoral scanner. Intraoral images are optical or visible light images captured via the camera of an intraoral scanner. Intraoral images can even be images acquired under low light conditions.

[0052] In some cases, the intraoral image can be in the form of a data stream provided via the intraoral scanner or can be provided via a data stream.

[0053] In this context, "digital impression" or "3D model" refers to a digital model obtained via reconstruction using a plurality of rendered images of a patient or 2D intraoral images that are more optimally exposed.

[0054] A digital impression is a digital surface representation of a patient's oral anatomical structure. Thus, a 3D model comprises information related to a plurality of anatomical features of a patient's oral anatomical structure.

[0055] A digital impression may include a representation of a patient's dentition and / or hard and / or soft tissues in and around the patient's gums. A digital impression may be used to provide a patient with any one or more of dental treatments or procedures, surgical templates, custom devices, prosthetic restorations, and dental orthodontic aligners. The terms 3D model and digital impression may be used interchangeably in this disclosure.

[0056] "Optical imaging" refers to the process of generating a visual or photographic image of an object. More specifically, optical imaging refers to imaging that can generate an image with information about the natural or near-natural color and / or texture of the object being imaged. Therefore, optical imaging can be performed using white light, or light that enables the resulting visual image to exhibit a natural or near-natural color and / or texture to humans. Thus, when an optical image with optimal exposure is presented via an HMI, the user can be provided with a natural reproduction of the object, at least with respect to color and / or texture. In the case of a grayscale visual image, texture may be a more central feature, whereas in the case of a color image, it should be understood that at least the color should be natural, preferably both color and texture. The optical image can be captured using visible light and / or light outside the visible spectrum. The reproduction of natural color depends on light conditions, the material and / or texture of the object being imaged, and the characteristics of the sensor used.

[0057] Therefore, "optical intraoral imaging" relates to using optical imaging to generate an optical image of a patient's oral anatomical structure. Therefore, the rendered image is also an optical intraoral image of the patient's oral anatomical structure.

[0058] "Structured light" in the context of "structured light imaging" refers to projected light with a predetermined pattern. The structured light or pattern is projected onto a target surface to determine the topography of the surface. The surface topography induces distortion in the pattern projected thereon. The distortion is recorded via an imaging sensor or camera, further analyzed to extract surface information, and ultimately to construct a digital model of the surface. In the context of intraoral scanning, it should be recognized that the target surface is typically the patient's oral anatomical structure. As a dental scanner is moved along an area or location adjacent to the surface, the digital impression of the oral anatomical structure is extended by stitching together surface data from different locations. The term "structured light imaging" thus refers to the process of projecting a structured light pattern and extracting surface data from the reflection of the pattern.

[0059] "Data-driven logic" refers to logic that derives its functionality at least in part from training data. In contrast to strict or analytical logic based on programmed instructions to perform a specific logical task, data-driven logic can enable the formation of such instructions at least in part automatically using training data. Data-driven logic may be able to detect patterns or indications (e.g., within the input or input data provided to the data-driven logic) that might otherwise not be known or might be difficult to implement in an analytical logic form.

[0060] Data-driven logic can be in the form of software and / or hardware executable via, for example, one or more computing units.

[0061] In this context, it should be recognized that data-driven logic refers to trained mathematical logic parameterized according to each training dataset. For example, anatomical data-driven logic is parameterized via its respective training data to detect one or more anatomical features. Untrained logic lacks this information. Thus, untrained logic or models are unable to perform the desired detection. Feature engineering and training using each training dataset thus enable the parameterization of untrained logic. The result of such a training stage is each data-driven model, and each data-driven model provides the correlations and logical capabilities relevant to the purpose for which each data-driven logic should be used, preferably as a result of the training process and only as a result of the training process.

[0062] Data-driven logic preferably comprises, or is, regression logic. In some cases, data-driven logic may be combined with, or further include, analytical logic. Analytical logic may describe the relationship between its input and output as a function or one or more mathematical formulas or logical criteria. From this, any of the data-driven logics described herein may even be hybrid logic. Hybrid logic refers to logic comprising a white box described via a set of first principles, i.e., formulas, such as mathematical formulas, and a data-driven part as previously described. The data-driven part may also be referred to as black box logic or a model. Thus, data-driven logic may, in some cases, be a combination of white box logic or analytical logic and black box logic. In some cases, data-driven logic may be, or even have, a gray box part. Gray box logic in this context refers to logic or a model that combines a partial analytical structure with a data-driven part using training data to complete the model.

[0063] "Composite logic" refers to a logic that comprises at least one of two different data-driven logics disclosed herein. The combined logic can be pre-trained with a teacher using an end-to-end training process. The end-to-end training process in this context can refer to at least partially annotated data comprising inputs and their corresponding desired outputs. In some cases, the combined logic can be fully or partially trained without a teacher.

[0064] "Human-machine interface" or "HMI" refers to a device or system comprising at least one video unit or display screen for displaying acquired intraoral images or rendered images and / or reconstructed 3D models to a user.

[0065] From this, the HMI system can comprise a visual display or screen for displaying visual images or videos. Optionally, the HMI system can also comprise an audio device. For example, the HMI system can also comprise a loudspeaker for outputting sound. The video unit can comprise an active or passive video screen, such as an LCD screen, an OLED screen, or a projection-based video system. Alternatively or additionally, the video unit can comprise an augmented reality ("AR") device.

[0066] The HMI can even comprise one or more input devices for receiving user input.

[0067] The terms "computing unit", "computing device", "processing unit", or "processing device" can be used interchangeably in this disclosure. The computing unit can comprise processing means or a computer processor, such as a microprocessor, a microcontroller, or the like, having one or more computer processing cores, or can be in those forms.

[0068] "Computer processor" refers to any logic circuit configuration configured to perform basic operations of a computer or system, and / or generally, a device configured to perform arithmetic or logical operations. In particular, the processing means or computer processor may be configured to process basic instructions that drive a computer or system. By way of example, the processing means or computer processor may include at least one arithmetic logic unit ("ALU"), at least one floating point unit ("FPU") such as a math coprocessor or numeric coprocessor, a plurality of registers, specifically, registers configured to supply operands to the ALU and store the results of operations, and memory such as L1 and L2 cache memories. In particular, the processing means or computer processor may be a multi-core processor. Specifically, the processing means or computer processor may be or include a central processing unit ("CPU"). The processing means or computer processor may be a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing microprocessor ("RISC"), a very long instruction word ("VLIW") microprocessor, a processor implementing other instruction sets, or a processor implementing a combination of instruction sets. The processing means may also be one or more dedicated processing devices such as application specific integrated circuits ("ASICs"), field programmable gate arrays ("FPGAs"), complex programmable logic devices ("CPLDs"), digital signal processors ("DSPs"), network processors, or the like. The methods, systems, and devices disclosed herein may be implemented as software in any other side processor such as a DSP, microcontroller, or a hardware unit within an ASIC, CPLD, or FPGA. The term processing means or processor may also refer to one or more processing devices, such as a distributed system of processing devices located across multiple computer systems (such as cloud computing), and it should be understood that it is not limited to a single device unless otherwise specified.

[0069] The "network" discussed in this specification can be any suitable type of data transmission medium, wired, wireless, or a combination thereof. A particular type of network does not limit the scope or generality of the present teachings. A network can thus refer to any suitable arbitrary interconnection between at least one communication endpoint and another communication endpoint. A network can include one or more distribution points, routers, or other types of communication hardware. The interconnection of a network can be formed physically by hard wiring, optical, and / or wireless radio frequency ("RF") methods. A network can specifically be a physical network made entirely or in part by hard wiring such as an optical fiber network, or a network made entirely or in part by conductive cables, or a combination thereof, or can include them. A network can include at least in part the Internet.

[0070] "Network interface" refers to a group or device of one or more hardware and / or software components that enable an operable connection to a network. For example, a network interface can be used to connect to a remote server or cloud service. In some cases, a network interface can be part of a connection interface.

[0071] A "memory storage device" can refer to a device for storing information in a suitable storage medium in the form of data. Preferably, the memory storage device is a digital storage device suitable for storing information in a digital format that is machine-readable, for example, digital data that is readable via a computer processor. From this, the memory storage device can be realized as a digital memory storage device readable by a computer processor. More preferably, the memory storage device on the digital memory storage device can also be operated by a computer processor. For example, any part of the data recorded on the digital memory storage device can be written, and / or erased, and / or overwritten, partially or entirely, with new data by a computer processor.

[0072] A "connection interface" or "communication interface" refers to a software and / or hardware interface for establishing communication such as the transfer or exchange of signals or data. The communication can be either wired or wireless. The connection interface can be used to connect one or more devices, such as a dental scanner, to a computing unit and / or a memory storage device. The connection interface preferably is based on or supports one or more communication protocols. The communication protocol can be a wireless protocol, such as a short-range communication protocol like Bluetooth® or Wi-Fi, or a long-range communication protocol like a cellular or mobile network, such as a second-generation cellular network ("2G"), 3G, 4G, Long-Term Evolution ("LTE®"), or 5G. Alternatively or in addition, the connection interface can even be based on a proprietary short-range or long-range protocol. The connection interface can support any one or more standard and / or proprietary protocols.

[0073] It will be apparent to those skilled in the art that the two or more components are "operably" coupled or connected. Non-limitingly, this means that there may be at least one communication connection between the coupled or connected components, for example, they are connection interfaces, network interfaces, or any suitable interfaces. The communication connection can be either fixed or removable. Moreover, the communication connection can be either unidirectional or bidirectional. Further, the communication connection can be wired and / or wireless. In some cases, the communication connection can also be used to provide control signals.

[0074] Here, certain aspects of the present teachings are discussed with reference to the accompanying drawings that illustrate the aspects as examples. Since the generality of the present teachings does not depend thereon, the drawings may not be to scale. Aspects of the method and system may be discussed together for ease of understanding. Certain features shown in the drawings may be logical features shown together with physical features without affecting the generality or scope of the present teachings for purposes of understanding.

Brief Description of the Drawings

[0075]

Figure 1

Figure 2

Modes for Carrying Out the Invention

[0076] According to the exemplary aspects described herein, for example, a method, a system, and a computer-readable storage medium for optical intraoral imaging of oral anatomical structures can be provided.

[0077] FIG. 1 shows a block diagram 102 of a system that illustrates a particular aspect of the present teachings. The system includes an intraoral scanner 104 shown in FIG. 1, which is used for intraoral scanning of a patient's oral anatomical structure 108 by being introduced into the patient's oral cavity 106. The intraoral scanner 104 is operably connected to a computing module 112, which includes at least one computing unit. In some cases, the computing module 112 may be at least partially located within the intraoral scanner 104. In some cases, the computing module 112 may be at least partially part of a cloud service 114. From this, the computing module 112 can be a local device at the location of the intraoral scanner 104 and / or a device or system that is at least partially remotely located, such as one or more cloud services 114 and / or a remote server. The computing module 112 is also operably connected to a memory storage device 116, which may be at least partially part of a cloud service 114. In this case, the memory storage device 116 is shown as part of the cloud service 114. The intraoral scanner 104 can be connected to an external computing module 112 via a connection interface (not explicitly shown in FIG. 1). Any local device, such as the intraoral scanner 104 and / or the local computing module 112, can be connected to the cloud service 114 via one or more networks 118. A network interface (not explicitly shown in FIG. 1) can be used to connect a local device to a remote device, such as the cloud service 114. In some cases, the network interface and the connection interface can be the same unit.

[0078] Optionally, the calculation module 112 can be operably connected to the HMI 120, which is shown as a computer screen in FIG. 1. The connection between the calculation module 112 and the HMI 120 can be through an output interface (not explicitly shown in FIG. 1), and the output interface can be, for example, a computer port or bus, such as a display port, HDMI (registered trademark), USB, or the like. However, the output interface can even be an API for providing data to one or more computing units on the HMI 120 side. In some cases, the output interface can be part of a network interface and / or a connection interface. Therefore, it is possible for the three interfaces to be the same device.

[0079] The intraoral scanner 104 includes a camera (not explicitly shown in FIG. 1) for optically imaging the oral anatomical structure 108. Optionally, the intraoral scanner 104 can include a visible light source (not explicitly shown in FIG. 1) for assisting in optical imaging. According to an aspect of the present teachings, the light source can be at least substantially weaker than conventional light sources required for visible light imaging of the oral cavity 106. Preferably, the present teachings completely offset the requirements of the light source. The present teachings can even be applied to conventional visible light imaging intraoral scanners that can control the deployment of the light source through a computing unit such that, in some cases, the light source is used only under substantially dark or completely dark conditions.

[0080] The calculation module 112 determines or calculates from the initial data how many intraoral images are to be captured via the intraoral scanner 104, or more specifically via the camera. At least a portion of the initial data can be provided via the camera. Alternatively or additionally, at least a portion of the initial data is provided from previously captured intraoral images or preceding intraoral images. Thus, the initial data can comprise any one or more of the light intensity, aperture, and / or exposure settings measured at a particular location within the oral cavity 106, kinematic data measured via one or more sensors of the intraoral scanner 104, data from previously acquired intraoral images.

[0081] The camera is then used to acquire the determined number of intraoral images at or around that location. At least one better-exposed two-dimensional intraoral image 122, or a rendered image, is provided from at least one of the acquired intraoral images and the initial data, or from a plurality of acquired intraoral images. The rendered intraoral image 122 can be provided at the HMI 120, preferably as a plurality of rendered intraoral images 124 such as a video stream or an animation.

[0082] According to an aspect, a plurality of rendered intraoral images 124 captured at different locations within the oral cavity 106 can be used to reconstruct a 3D digital impression 126 of the oral anatomical structure 108 of the patient 110. The digital impression 126 is any suitable digital representation of the oral anatomical structure 108, and the digital representation can comprise natural anatomical features and artificial anatomical features such as the intraoral scan body 128 shown in FIG. 1.

[0083] In some cases, light is projected onto the oral anatomical structure 108. A plurality of intraoral images of the oral anatomical structure 108 are generated in response to receiving reflections. From this, during scanning, the intraoral scanner 104 is operated to capture a plurality of intraoral images of the oral anatomical structure 108. The intraoral images can be in the form of a data stream. These intraoral images are provided to the computing module 112. The computing module 112 is configured to provide a plurality of rendered intraoral images 124 from the intraoral images. Advantageously, data-driven reconstruction logic can be used to reconstruct a plurality of rendered intraoral images 124 from the intraoral images.

[0084] The digital impression 126 can be used to manufacture dental objects such as aligners and / or the digital impression 126 can be used to perform dental procedures such as restorations.

[0085] FIG. 2 shows a flowchart 200 that can be implemented as one or more routines executed by one or more computing units. At least certain related system aspects will also become apparent from the following. Flowchart 200 can be implemented as one or more routines in a system such as a dental scanner and / or scanning system, for example, shown in FIG. 1.

[0086] In block 202, initial data related to the oral anatomical structure 108 and / or the intraoral scanner 104 is provided.

[0087] In block 204, using the initial data, the number of intraoral images to be captured via the intraoral scanner 104 is calculated.

[0088] In block 206, the intraoral scanner 104 is used to obtain the number of intraoral images at a given location in the oral anatomical structure 108.

[0089] In block 208, a rendered intraoral image 122 is rendered from at least one of the acquired intraoral images and the initial data, or from a plurality of acquired intraoral images.

[0090] The plurality of rendered intraoral images 124 can be used to reconstruct a digital impression 126 of the oral anatomical structure 108.

[0091] The steps of the method can be executed in the order as listed in the examples or aspects. However, it should be noted that in certain situations, different orders may also be possible. Furthermore, it is also possible to execute one or more of the steps of the method once or repeatedly. These steps can be repeated at regular or irregular time intervals. Additionally, when two or more of the steps of the method are executed simultaneously, or specifically when some or more of the steps of the method are repeatedly executed, it is possible to execute them overlapping in time. The method may comprise additional steps not listed.

[0092] The word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processing means, processor or controller, or other similar unit can perform the functions of several items described in the claims. The mere fact that certain means are described in different dependent claims does not indicate that a combination of these means cannot be used advantageously. Any different reference signs in the claims should not be construed as limiting the scope.

[0093] Furthermore, in the present disclosure, it should be noted that terms such as "at least one", "one or more", or similar expressions indicating that a feature or element may be present one or more times are typically only used once when introducing each feature or element. From this, in some cases, unless otherwise specified, when referring to each feature or element, despite the fact that each feature or element may be present one or more times, the expressions "at least one" or "one or more" may not be repeated.

[0094] Furthermore, terms such as "preferably", "more preferably", "particularly", "more specifically", "specifically", "even more specifically", or similar terms are used in conjunction with optional features without limiting the possibility of alternatives. From this, any feature introduced by these terms is an optional feature and is never intended to limit the scope of the claims. As will be recognized by those skilled in the art, the present teachings can be implemented by using alternative features. Similarly, features introduced by expressions such as "according to an aspect" or similar expressions are intended to be optional features without any limitation regarding any alternative form of the present teachings, without any limitation regarding the scope of the present teachings, and without any limitation regarding the possibility of combining such introduced features with any other optional or non-optional features of the present teachings.

[0095] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this teaching belongs.

[0096] Various examples have been disclosed above with respect to a computing unit comprising a method, a system, a device, a use, a software program, and computer program code for implementing the methods disclosed herein. For example, a method for optical intraoral imaging of an oral anatomical structure via an intraoral scanner, the method comprising providing initial data related to the oral anatomical structure and / or the intraoral scanner, using the initial data to calculate the number of intraoral images to be captured via the intraoral scanner, acquiring the number of intraoral images at a given location in the oral anatomical structure via the intraoral scanner, and rendering a two-dimensional intraoral image that is more optimally exposed from at least one of the acquired intraoral images and the initial data, or from a plurality of acquired intraoral images, has been disclosed. The present teachings also relate to a system, a software product, a use, and a storage medium. However, those skilled in the art will understand that changes and modifications can be made to those examples without departing from the spirit and scope of the appended claims and their equivalents. It should further be recognized that aspects from the embodiments of the methods and products discussed herein can be freely combined.

[0097] Any headings used within the description are for convenience only and have no legal or limiting effect.

Claims

1. A computer-implemented method for optical intraoral imaging of an oral anatomical structure via an intraoral scanner, the method comprising: - providing initial data related to the oral anatomical structure and / or initial data related to the intraoral scanner; - using the initial data to calculate the number of intraoral images to be captured via the intraoral scanner; - obtaining, via the intraoral scanner, the number of intraoral images at a given location of the oral anatomical structure; - rendering a two-dimensional intraoral image that is more optimally exposed from at least one of the obtained intraoral images and the initial data, or from a plurality of the obtained intraoral images. A method comprising the above.

2. - providing a plurality of two-dimensional intraoral images that are more optimally exposed and capture different locations of the oral anatomical structure; - using the plurality of two-dimensional intraoral images that are more optimally exposed to reconstruct a three-dimensional digital impression of the oral anatomical structure. The method according to claim 1, further comprising the above.

3. The initial data comprises any one or more of the light intensity, aperture and / or exposure settings measured in the oral anatomical structure, the kinematic data measured via one or more sensors of the intraoral scanner, and data from previously acquired intraoral images. The method according to claim 1 or 2.

4. The rendering of the two-dimensional intraoral image that is more optimally exposed comprises: - analyzing each of the obtained intraoral images to select one or more regions of a desired exposure; - combining the selected regions to provide the two-dimensional intraoral image that is more optimally exposed. The method according to any one of claims 1 to 3, comprising the above.

5. The method according to claim 4, wherein at least some of said areas are selected via segmentation logic, said segmentation logic being preferably at least partly data-driven logic.

6. The rendering of the more optimally exposed two-dimensional intraoral image comprises adjusting the image characteristics of at least one of the acquired intraoral images and / or at least one of the selected areas, according to any one of claims 1 to 5.

7. The rendering of the more optimally exposed two-dimensional intraoral image is at least partly performed via data-driven rendering logic, according to any one of claims 1 to 6.

8. The image acquisition settings of the intraoral scanner are determined using said initial data, according to any one of claims 1 to 7.

9. The reconstruction of the three-dimensional digital impression is performed via data-driven reconstruction logic, according to any one of claims 2 to 8.

10. A computer software product, or a non-transitory computer-readable storage medium storing a program, comprising instructions for causing any of the computing units to perform the steps according to any one of claims 1 to 9 when executed by one or more suitable computing units.

11. A system comprising means for performing the steps according to any one of claims 1 to 10.

12. Use of one or more of the more optimally exposed two-dimensional intraoral images generated by the method according to any one of claims 1 to 9, for reconstructing digital dental impressions and / or displays and / or training and / or validating data training logic in a human-machine interface device.

13. Use of a three-dimensional digital impression generated by the method according to any one of claims 2 to 9 for performing a dental procedure and / or manufacturing a dental object. **Claim 14** A data storage medium storing a three-dimensional digital impression generated by the method according to any one of claims 2 to 9. **Claim 15** A data storage medium storing one or more of the more optimally exposed two-dimensional intraoral images and / or digital impressions generated by the method according to any one of claims 1 to 9.

Images