Dental User Interface

Abstract

The present teachings relate to a method for improving the usefulness of dental imaging data, comprising providing imaging data including a plurality of different images of at least one dental imaging modality of a patient, providing metadata for each of the images, selecting one or more of the images, and retrieving at least one other image in response to the selection, where the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images. The present teachings also relate to a system, a software product, and a storage medium.

Description

[Technical field]

[0001] The present teachings relate generally to computer-implemented methods and products for dental imaging. [Background technology]

[0002] Modern dentistry is developing in the digital domain. Although the output of most diagnostic systems on the market is already in digital form, there is now a trend to exploit data-driven tools in order to capture insights and make the work of dental practitioners as easy as possible. Data-driven techniques depend on the availability of huge amounts of data. Data from multiple sources is collected for analysis via data-driven logic and / or to be used as training data. This trend is made possible not only by the steady reduction in the cost of processing power, but also in the reduction of the costs of storing data. Thus, ever-increasing amounts of data, i.e. the so-called big data, are stored and archived. These data can be highly beneficial for exploiting data-driven techniques.

[0003] It also has other aspects, for example, large amounts of data may remain underutilized. This problem is further exacerbated by the fact that it is difficult to know what exactly is available. For example, there may be a large number of images available from different scans stored in a database, but even knowing whether to look for them may require prior knowledge that they are available. Even if known, it is difficult to find them in the vast amount of data stored.

[0004] Applicants have recognized that there is a need for improved methods and products that can better assist dental health practitioners by leveraging data more efficiently. Summary of the Invention

[0005] At least some of the limitations associated with the foregoing may be overcome by the subject matter of the attached independent claims. At least some of the further advantageous alternatives will be outlined in the dependent claims.

[0006] Viewed from a first aspect, there can be provided a computer-implemented method for improving the usability of dental imaging data, the method comprising: - providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; providing metadata for each of the images, where the metadata associated with a particular image comprises semantic information related to one or more anatomical features recorded in that image; - selecting one or several of the images from the imaging data; - retrieving at least one further image from the imaging data in response to the selection, wherein the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0007] Applicant has recognized that by doing so, imaging data related to at least one different image can be automatically retrieved without the user having to find out what is available in the provided imaging data. The present teachings achieve this by establishing links between specific images in the imaging data. These links are utilized to retrieve at least one other image or retrieved imaging data based on one or several selected images or selected imaging data. More specifically, the links are advantageously established using semantic information related to anatomical features in different images in the imaging data. Thus, the present teachings establish and maintain semantic correspondence between different images in the imaging data regardless of the number of imaging modalities the imaging data may have.

[0008] For ease of understanding, and without limiting the scope or generality of the present teachings, the terms "selected imaging data," "selected one or more images," or "selected image" shall be used synonymously in this disclosure. Similarly, the terms "retrieved imaging data," "retrieved image," or "at least one other image" may be used interchangeably in this disclosure.

[0009] Thus, the semantic information may be correlated to select imaging data and / or to retrieve imaging data related to at least one other image. Different implementations of the present teachings are discussed in this disclosure along with their technical advantages. The selected imaging data is a subset of the provided imaging data, i.e., at least one image. Similarly, the retrieved imaging data is another subset of the provided imaging data, i.e., at least one other image different from the selected image that is retrieved in response to a comparison of metadata.

[0010] "Metadata" for a particular image or for a particular portion of imaging data refers to data that contains information about the image or portion of imaging data. More specifically, metadata for an image includes semantic information related to anatomical features of that image.

[0011] "Semantic information" in this context refers to interpreted or inferred data related to one or more anatomical features. When related to a particular portion of imaging data, e.g., an image, the semantic information may be an interpretation of what may be observed or found from the image. The semantic information is related to one or more anatomical features. As some non-limiting examples, the semantic information may include any one or more of the following anatomical features, i.e., a specific tooth number or reference, a specific nerve, a specific bone, a type of jaw, a specific lesion, a specific replacement, a specific treatment or procedure, etc. Advantageously, the semantic information also includes information of the location where the tooth can be found in the image. For example, the semantic information may include information of most or all pixels or voxels of the image related to a particular tooth. Thus, using the semantic information, that particular tooth may be highlighted or outlined. Alternatively or additionally, the semantic information may provide a general location of that tooth. Thus, using the semantic information, that particular tooth may be pointed to, for example, by placing a point or tag in the center or around the tooth.

[0012] Often, after obtaining a scan, such as an X-ray image, the dentist tags or marks the image with its interpretation or observation. These data can be used as semantic information. Alternatively, or additionally, the semantic information may be provided automatically by fully or partially computationally processing the imaging data. The processing may advantageously use one or more data-driven logics to which the imaging data is provided as input, the logic providing semantic information for the imaging data. This semantic information may be used directly as metadata or may be further processed to provide metadata for each of the images processed via the logic. The logic may perform segmentation and / or localization operations on each image to provide the semantic information for the respective image.

[0013] Preferably, the semantic information is organized into different abstraction categories. Thus, the imaging data can provide semantic information or parts thereof at different categories, levels, or grades of abstraction. Also, preferably, each part or part of the semantic information can include relationship information with other parts, thus forming a network of related information across various abstraction levels. For example, some semantic information at lower levels of abstraction can include information such as the location of specific anatomical features, such as the location of specific implants, abutments, teeth, nerves, etc., while at higher levels of abstracted information there may be a categorical layer that includes information describing entities using dental terms such as the number or type of teeth, gums, bone, prosthesis, maxilla, etc. There can even be lesion level abstraction and / or treatment level abstraction that can link information at various abstraction levels. As some non-limiting examples, the lesion level can include information such as caries, fractures, osseointegration, etc., which can establish links to specific teeth at different positions in the oral anatomy, for example. Similarly, the treatment level can include information such as osteotomy, endodontic treatment, etc., which can be linked to specific parts of the lesion level and / or lower abstraction levels. There may even be other levels, below, above, at the same level, or between any of the levels or categories discussed above.

[0014] The advantage of locating semantic information is that the comparison between the metadata of the selected imaging data and their matching other imaging data can be improved for better retrieval of related data. Thus, the availability and usefulness of the imaging data is improved for the user even when there is no direct match between the image selected by the user from the imaging data and the retrieved image. In big data applications, it can be very difficult for the user to recognize what is available, much less searchable. Thus, the semantic correspondence between images in the imaging data is exploited to extract related images without the user knowing or recognizing the existence of the related images.

[0015] Another advantage may be that even if there is not an exact match, the search can still be performed if the linked paths between levels or layers are the same or similar. For example, when a selection is made based on endodontic treatment and maxillary side, the semantic information provided may still be related to the maxillary side, so image data associated with the endodontic treatment of a particular tooth may still be searched. In other cases, the semantic information may be used to filter out irrelevant data. Taking the same example, when a selection is made based on endodontic treatment and maxillary side, only image data related to the tooth in question after treatment may be searched. Since there may be other images of the tooth that are pre-treatment or even pre-lesion, these images may not be searched to prevent irrelevant data from being provided.

[0016] "Anatomical features" refer to information about a particular anatomical structure of a patient, more specifically about the patient's craniofacial anatomy. For example, an anatomical feature may be information related to a particular tooth or group of teeth. Thus, an anatomical feature may even refer to information related to any one or more intra-oral structures, such as dentition, gums, nerve channels, tooth extraction sites, jaw bones, and condyles. Alternatively or additionally, an anatomical feature may be one or more dental replacements, e.g., one or more artificial structures, such as crowns, braces, veneers, bridges, etc. Alternatively or additionally, an anatomical feature may be a scan body (or other natural and / or artificial structures) attached to the patient's jaw in some cases. Alternatively or additionally, an anatomical feature may be information related to a pathology or condition. As non-limiting examples, a pathology or condition may be any one or more of a tooth or bone fracture, caries, radiolucency, impaction, missing tooth, or any other characterizable condition of the oral anatomy or any part thereof.

[0017] "Imaging data" or "image data" in this context refers to data obtained at least in part from imaging a patient. The imaging data includes multiple different images of at least one dental imaging modality of the same patient. As some non-limiting examples, the dental imaging modality may be X-ray, orthopantomogram ("OPG"), cephalogram ("CEPH"), cone beam computed tomography ("CBCT"), optical intraoral photography, optical 3D surface scan, or the like. The images included in the imaging data may be of the same type and / or preferably of different types. As non-limiting examples, the images may be X-ray sinograms of the patient, DVT images, panoramic images, bitewing images, CEPH images, photographic images such as photographic dental arch images, radiographic projection images, or the like.

[0018] The step of selecting the imaging data associated with the one or more images may be performed in response to a user input or may be performed automatically in response to a preceding process. Thus, according to one aspect, the selection of the imaging data is performed in response to a user input. For example, the user input may provide one or more diagnostic parameters. Thus, the selection is performed by matching any one or more of the diagnostic parameters with the metadata of the images in the imaging data. The diagnostic parameters may be references to one or more anatomical features. Alternatively, or additionally, any of the diagnostic parameters may be based on any one or more of workflow, direct text, treatment, lesion, or the like. As a non-limiting example, the one or more diagnostic parameters may be related to the progression of periodontal bone loss. A user may select or provide an input, such as, for example, the string periodontal bone loss.

[0019] Thus, in accordance with the present teachings, imaging data for patient images (such as x-rays and digital impressions) depicting the bone crest in the region of interest are automatically retrieved by comparing metadata, thus enabling the dentist to make a more complete diagnosis without having to expend additional effort to know if other images exist, or to manually search for them even if known.

[0020] More advantageously, the selected and retrieved imaging data is presented on a display device with image views in such a manner as to make it easier for the user to make a relevant diagnosis. For example, the image views may be automatically arranged in chronological order (e.g., by date of capture). Even more advantageously, the view of each image is automatically adapted using semantic information to aid the user in making a diagnosis. For example, the orientation and / or magnification of each or some of the images may be adjusted so that each view presents a comparable view of the bone crest, which facilitates comparison of bone crest heights at different time points.

[0021] In this context, an image view refers to a single image selected or retrieved from the imaging data and adapted with any one or more of additional properties defining the visible portion of the image shown on the HMI, such as the level of magnification, the 3D orientation and center of the displayed data, or any other configuration such as a mapping of data values ​​to the displayed brightness or view interpolation. The additional properties are applied in response to a comparison of the semantic data and / or metadata of the images. In some cases, the additional properties of one of the image views may be provided via user input. As a result, according to the present teachings, the corresponding additional properties are automatically applied to at least a portion of the other image views in the display device. It is also possible that parts of the image views are removed and / or additional image views are added to the display device by retrieving additional imaging data as proposed. The additional image views are also adapted by applying the corresponding additional properties as proposed.

[0022] Thus, the retrieved imaging data is preferably included in the display device together with the imaging data selected for the user as a plurality of image views. For example, based on the selection of the imaging data, which may be automatic, or based on a specific user input, a specific image view of the imaging data may be provided in a user interface or human machine interface ("HMI"). The image view may be, for example, a view of a specific portion of the oral anatomy selected from one or more different imaging modalities. Preferably, the image view is configured with one or more additional properties based on comparison and / or semantic information. Thus, an image view is formed from the retrieved imaging data set, preferably configured with additional properties such as the displayed portion of the data.

[0023] The display device is automatically configured to support the user's diagnostic task or interest based on the semantic data and / or the comparison.

[0024] In contrast to conventional image registration methods that establish spatial correspondence between images based on locally similar luminance or color distribution, the proposed use of semantic information works at a higher level of abstraction. Thus, the present teachings can make it possible to relate representations of anatomical features present in visually very different modalities. The present teachings can also compensate for the changed position / orientation of the patient, non-rigid movements (mouth opening and closing positions), and distortions due to the (projection) imaging techniques used in the different images, which is a clear advantage over conventional image registration approaches when composing image views to show similar semantic content.

[0025] Thus, according to one embodiment, at least a portion of the selected imaging data and at least a portion of the retrieved imaging data may be provided in an interface, such as an HMI and / or an application programming interface ("API"). Depending on the application, the interface may be a software and / or hardware interface. An advantage of providing said data to an HMI is that by establishing and maintaining a semantic correspondence between the selected imaging data and the retrieved imaging data, the user is automatically shown relevant data. Thus, the retrieved imaging data is interactively adapted accordingly. Such changes may be responsive to user inputs on any of the imaging data shown on the HMI. Thus, the user is continuously and automatically provided with data that may be useful for arriving at a correct diagnosis or conclusion. This also aids in early detection of underlying health conditions. Thus, the method includes: - updating a selected portion of the imaging data; - removing at least a portion of the retrieved imaging data in response to the update; and / or - retrieving further different imaging data in response to the update.

[0026] Thus, when the selected imaging data changes, the retrieved imaging data is adapted accordingly. Thus, the portion of the retrieved imaging data in the interface may also be updated.

[0027] According to an embodiment, the method also includes: - updating a part of a display device or an image view of a display device; removing at least one of the image views in response to an update; and / or - retrieving at least one further image from the imaging data in response to the update, to provide at least one new image view on the display device.

[0028] Thus, when the display device is updated, for example when one of the image views in the device is manipulated by scrolling, zooming, panning, etc., one or more of the imaging views may be automatically removed from the device in response to the update. Additionally or alternatively, one or more different or additional image views may be added to or included in the device by performing a search step as previously proposed. Thus, the removal and search are performed in response to the comparison and / or semantic data, as required. As shown in the bone loss example above, the diagnostic parameters can be utilized to configure the retrieved imaging data provided to the interface. For example, the magnification and / or perspective and / or temporal aspect in which the imaging data is arranged can be determined depending on any one or more of the diagnostic parameters. Thus, further advantageously, the display device may be automatically configured depending on any one or more of the diagnostic parameters and / or metadata of the retrieved images.

[0029] As discussed above, the metadata may be based on user-provided and / or automatically provided annotations. Thus, according to one aspect, at least a portion of the metadata is provided via data-driven logic. The data-driven logic may perform semantic processing on the imaging data to provide at least a portion of the metadata.

[0030] "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 specific logical tasks, data-driven logic can make it possible to form such instructions at least in part automatically using training data. The use of data-driven logic can make it possible to describe logical and / or mathematical relationships without explicit manual algorithm design. This can reduce computational requirements and / or improve speed. Additionally, data-driven logic can be capable of detecting patterns or instructions (e.g., in inputs or input data provided to the data-driven logic) that may not otherwise be known or may be difficult to implement as an analytical logic form.

[0031] The data driven logic may be in the form of, for example, software and / or hardware executable via one or more computing units.

[0032] In the present context, it should be understood that data-driven logic refers to trained mathematical logic that is parameterized according to a respective training data set. For example, an 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 cannot perform the desired detection. Therefore, feature engineering and training with the respective training data set allows parameterization of the untrained logic. The result of such a training phase is a respective data-driven model, which preferably provides interrelationships and logical capabilities relevant to the purpose for which the respective data-driven logic is used only as a result of the training process. In this case, the data-driven logic may be trained with a training data set that includes a plurality of images and their corresponding semantic information.

[0033] When data-driven logic is used for inference, the imaging data is provided to its input and the data-driven logic provides at least a portion of the metadata as an output.

[0034] Either the imaging data and / or the metadata may be provided in the same memory storage device or in different memory storage devices.

[0035] Viewed from another perspective, there can also be provided a system comprising means for performing any of the method steps disclosed herein.

[0036] For example, a system for improving the usability of dental imaging data may be provided, the system comprising one or more computing units, wherein any of the computing units comprises: providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; providing metadata for each of the images, the metadata associated with a particular image including semantic information related to one or more anatomical features recorded in that image; - selecting one or several of the images from the imaging data; - configured to retrieve at least one further image from the imaging data in response to a selection, wherein the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0037] The system may be an add-on to or part of a diagnostic system, such as an imaging system. In some cases, the system may be implemented at least in part as a cloud computing service. When implemented as an add-on, the diagnostic system and the proposed system may be interconnected via a connection interface and / or a network interface. Any two or more of the connection interface and / or network interface and / or interfaces may be the same device or they may be different.

[0038] From another perspective, there may also be provided a non-transitory computer readable storage medium storing a computer software product, or a program, comprising instructions that, when executed by a suitable computing unit, cause the computing unit to perform any one of the steps of the methods disclosed herein.

[0039] For example, when executed by one or more suitable computing units, the providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; - providing metadata for each of the images, where the metadata associated with a particular image comprises semantic information related to one or more anatomical features recorded in that image; - selecting one or several of the images from the imaging data; A non-transitory computer readable storage medium may be provided that stores a computer software product, or a program, comprising instructions for retrieving at least one further image from the imaging data in response to a selection, where the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0040] A "computing unit", "computing device", "processing unit" or "processing device" may comprise or be a processing means or computer processor, such as a microprocessor, microcontroller, etc., having one or more computer processing cores.

[0041] A "computer processor" refers to any logic circuitry configured to perform basic operations of a computer or system, and / or generally a device configured to perform calculations or logical operations. In particular, the processing means or computer processor may be configured to process basic instructions that run the computer or system. By way of example, the processing means or computer processor may comprise at least one arithmetic logic unit ("ALU"), at least one floating point unit ("FPU"), such as a mathematical coprocessor or numeric coprocessor, a number of registers, in particular registers configured to supply operands to the ALU and to store results of operations, and memories, such as L1 and L2 cache memories. In particular, the processing means or computer processor may be a multi-core processor. In particular, the processing means or computer processor may be or comprise 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 an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a digital signal processor (DSP), a network processor, etc. The methods, systems, and devices disclosed herein may be implemented as software in a DSP, a microcontroller, or any other side processor such as a hardware unit in an ASIC, a CPLD, or an FPGA. It should be understood that 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 is not limited to a single device unless otherwise specified.

[0042] A "network" as discussed herein may 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 may thus refer to any suitable interconnection between at least one communication endpoint and another communication endpoint. A network may comprise one or more distribution points, routers, or other types of communication hardware. Network interconnections may be formed by physical hard wiring, optical and / or wireless radio frequency ("RF") methods. A network may specifically be or comprise a physical network made entirely or partially by hard wiring, such as an optical fiber network, or a network made entirely or partially by conductive cables, or a combination thereof. A network may comprise, at least in part, the Internet.

[0043] "Network interface" refers to a device or grouping of one or more hardware and / or software components that enables an operative connection to a network.

[0044] A "connection interface" or a "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 is preferably based on or supports one or more communication protocols. The communication protocol connection can be a wireless protocol, e.g., a short-range communication protocol such as Bluetooth or Wi-Fi, or a long-range communication protocol such as a cellular or mobile network, e.g., a second generation cellular network ("2G"), 3G, 4G, Long Term Evolution ("LTE"), or 5G. Alternatively or additionally, 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.

[0045] A "memory storage device" may refer to a device for storing information in the form of data in a suitable storage medium. Preferably, the memory storage device is a digital storage device suitable for storing information in a machine-readable digital form, e.g., digital data that is readable via a computer processor. The memory storage device may thus be realized as a digital memory storage device that is readable by a computer processor. More preferably, the memory storage device on the digital memory storage device may also be operated by a computer processor. For example, any part of the data recorded on the digital memory storage device may be written and / or erased and / or overwritten, partially or entirely, with new data by the computer processor.

[0046] It will be apparent to one skilled in the art that two or more components are "operably" coupled or connected. Without limitation, this means that there may be at least one communication connection between the coupled or connected components, e.g., they may be a network interface or any suitable interface. The communication connection may be either fixed or removable. Moreover, the communication connection may be either unidirectional or bidirectional. Furthermore, the communication connection may be wired and / or wireless. In some cases, the communication connection may also be used to provide control signals. [Brief description of the drawings]

[0047] Certain aspects of the present teachings will now be discussed with reference to the accompanying drawings, which illustrate said aspects by way of example. The drawings may not be to scale, as the generality of the present teachings does not depend thereon. Method and system aspects may be described together for ease of understanding. Certain specific features shown in the drawings may be logical features shown together with physical features for understanding, without affecting the generality or scope of the present teachings. [Figure 1] FIG. 1 illustrates a graphical embodiment of the present teachings. [Diagram 2] FIG. 2 illustrates another graphical embodiment of the present teachings. [Diagram 3] FIG. 3 illustrates an embodiment for providing metadata in accordance with the present teachings. [Figure 4] FIG. 4 illustrates a flow chart of one embodiment of the present teachings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0048] In accordance with example aspects described herein, methods, systems, and computer-readable storage media can be provided for improving the usefulness of dental imaging data, for example.

[0049] FIG. 1 shows a block diagram 102 illustrating a graphical aspect of the present teachings. A display device 104 is shown including a plurality of dental image views 108-120. The dental image views 108-120 are image views of imaging data that may be stored in a memory storage 106. The memory storage 106 may be a single unit or may be distributed across different units located in the same or different geographic locations. The imaging data includes a plurality of different images (including 108-120) of a patient. As can be seen in this example, the imaging data relates to different imaging modalities of the patient. The display device 104 may be provided to an interface, such as an HMI or a graphical user interface.

[0050] The display device 104 in this example includes a coronal slice through a CBCT volume 116, an intraoral optical image 110, an X-ray intraoral image 108, an X-ray panoramic image 114, a surface scan image 118 having a view from a given perspective or orientation, and another surface scan image 120 having a view from a different perspective or orientation compared to the surface scan image 118.

[0051] The intraoral x-ray image 108 is shown with a marker or circle 122 in this example. The circle 122 is positioned to indicate a common feature exhibited by the different views 108, 110, 112, 114, 116, 118, and 120. Thus, the display device 104 is automatically adapted to show related imaging data to a user, such as a dentist, in accordance with the present teachings. For example, the display device 104 may be triggered by a selection made by the dentist while viewing the image 108. Thus, the x-ray intraoral image 108 may represent the selected image or the selected imaging data. In response to the selection, another imaging data or another image 110-120 is automatically retrieved. The retrieval is performed by comparing the metadata of the x-ray intraoral image 108 with the metadata of the other images in the imaging data. As a result, the retrieved images 110-120 are included in the display device 104. As shown, the retrieved image data views 110-120 are adapted according to relevance by using semantic information and / or metadata comparison. For example, it can be detected from the metadata or semantic information which features or contexts are relevant to the displayed portion of the x-ray intraoral image 108, and based thereon the semantic information of the other views 110-120 can be analyzed to adapt the displayed portions of each of the views 110-120. Thus, the user can be automatically provided with the most relevant imaging data.

[0052] The selected image view 108 shows a molar 124 indicated by a marker 122. Other anatomical features such as a bicuspid 126 with a filled root are also visible in the CBCT image view 108. By comparing the metadata of the X-ray intraoral image 108, the views of the retrieved images 110 to 120 have been automatically adapted accordingly so that the practitioner sees the features of the molar 124 in a different form. For example, 110 is zoomed and panned to the molar 124, and images 118 and 120 similarly show the molar 124 from a different perspective. The views and adaptations may be further influenced by one or more diagnostic parameters that may be provided by the dentist.

[0053] FIG. 2 shows another block diagram 202 of a display device 104 where a selection has been changed by a user through interaction with an image 108, for example, where in this example the user may have panned the view 108 to the right of the image 108.

[0054] Thus, in this case, the dentist has decided to focus on the root-filled bicuspid 126 rather than the molar 124. Thus, the panning operation performed by the user is shown here as an arrow 204. Each of the alternative views 110-120 has therefore been adapted according to the updated graphical content visible in the image 108. In some cases, even other images in the imaging data may match the metadata of the new selection of the x-ray intraoral image 108, in which case such matching views or images may also be included in the display device 104. Alternatively, if any of the other views 110-120 do not match the new selection, those views may be removed from the display device 104.

[0055] The dentist is thus interactively assisted in focusing on the relevant data, thus helping to provide a more accurate diagnosis and treatment.

[0056] 3 shows a flow diagram 302 illustrating a method for providing metadata for imaging data 304. Here, imaging data 304 is shown that includes multiple dental views 310-320 of different imaging modalities. In this example, imaging data 304 includes a sagittal slice 310 of a CBCT volume, an X-ray intraoral image 318, a panoramic image 312, a 3D volume 314, a surface scan 316, and an intraoral optical image 320. The imaging data 304 is processed through image analysis logic 308, which is preferably at least partially data-driven logic. The image analysis logic 308 can perform an automatic semantic analysis of the imaging data 304.

[0057] The result of the processing is imaging data having metadata 306 including semantic information. The metadata may or may not be stored with the imaging data. Thus, the metadata may be stored in a memory storage device separate from that storing the imaging data 304. The output of the processing may be, for example, a first annotated panoramic image 322 including annotations 324. The annotations 324 may provide the location of each anatomical feature in the first annotated panoramic image 322 and / or segment the image according to the anatomical features present in the image 322. The metadata of the image includes semantic information associated with one or more anatomical features recorded in the image, such as tooth numbers, root names, viewing direction, etc. Thus, the metadata may include any one or more of contours, voxel masks, semantic labels, and the like.

[0058] Similar to the first annotated panoramic image 322, the second annotated panoramic image 326 and the annotated 3D volume 328 also comprise respective metadata that includes semantic information. For example, the metadata of the annotated 3D volume 328 includes a volume annotation 330 that may specify that a particular voxel is associated with an unerupted, developing molar tooth having an FDI 38 on the patient's left labial side.

[0059] These metadata may then be leveraged in accordance with the present teachings, for example, in response to user selection of an initial image, task, or workflow.

[0060] Upon user interaction with any one of the images present in the display device 104, semantically consistent updates can be provided across the display device 104. For interactive continuous motion, non-linear interpolation of intermediate display positions, e.g., using 2D / 3D thin-plate splines as the displacement field, can be calculated from the semantic information of the imaging data. If an optimal workflow requires specific modifications of the one-to-one spatial correspondence, this can also be incorporated during the transfer of the interaction.

[0061] 4 shows a flowchart 400 demonstrating aspects of the present teachings. Flowchart 400 can be implemented, for example, as a routine executable by one or more computing units operably connected to a diagnostic system, such as a dental imaging system.

[0062] At block 402, imaging data including a plurality of different images of at least one dental imaging modality of a patient is provided.

[0063] At block 404, metadata is provided for each of the images, the metadata associated with a particular image including semantic information related to one or more anatomical features recorded in that image.

[0064] At block 406, one or some of the imaging data, images are selected. Thus, at least one, but not all, images are selected from the imaging data.

[0065] In response to the selection, at least one additional image is retrieved from the imaging data at block 408. The retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0066] The steps of the method may be performed in the order as enumerated and shown in the examples or aspects. However, it should be noted that under certain circumstances, a different order may be possible. Furthermore, it is also possible to perform one or more of the steps of the method once or repeatedly. These steps may be repeated at regular or irregular time periods. Furthermore, two or more of the steps of the method may be performed simultaneously or overlapping in time, particularly when some or more of the steps of the method are performed repeatedly. The method may comprise further steps not enumerated.

[0067] 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 may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Any different signs in the claims should not be interpreted as limiting the scope.

[0068] Furthermore, it should be noted that in this disclosure, the terms "at least one," "one or more," or similar expressions indicating that a feature or element may be present one or more times may typically be used only once when introducing each feature or element. Thus, in some cases, unless expressly stated otherwise, when referring to each feature or element, the expressions "at least one" or "one or more" may not be repeated, despite the fact that each feature or element may be present one or more times.

[0069] Furthermore, the terms "preferably", "more preferably", "particularly", "more particularly", "particularly", "more particularly" or similar terms are used in conjunction with optional features without limiting the possibilities of substitution. From this, any features introduced by these terms are optional features and are not intended to limit the scope of the claims in any way. The present teachings can be implemented by using alternative features, as the skilled artisan will recognize. Similarly, features introduced by "according to one embodiment" or similar expressions are intended to be optional features, without any limitations on the alternative forms of the present teachings, without any limitations on the scope of the present teachings, and without any limitations on the possibilities of combining the features so introduced with other optional or non-optional features of the present teachings.

[0070] 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 invention belongs.

[0071] Various examples have been disclosed above for methods, systems, devices, uses, software programs, and computing units with computer program codes for implementing the methods disclosed herein. For example, a method for improving the usefulness of dental imaging data has been disclosed, comprising providing imaging data including a plurality of different images of at least one dental imaging modality of a patient, providing metadata for each of the images, selecting one or some of the images, and retrieving at least one other image in response to the selection, the retrieval being performed by comparing at least one metadata of the selected image with at least one metadata of the retrieved image. The present teaching also relates to systems, software products, and storage media. 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 will be further recognized that aspects from the method and product embodiments discussed herein can be freely combined.

[0072] Any headings used within the description are for convenience only and have no legal or limiting effect. Certain aspects of the present teachings are summarized in the following sections.

[0073] Section 1: A computer-implemented method for improving the usability of dental imaging data, comprising: - providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; providing metadata for each of said images, where said metadata relating to a particular image comprises semantic information relating to one or more anatomical features recorded in that image; - selecting one or some of said images from said imaging data; - retrieving at least one further image from the imaging data in response to said selection, wherein said retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0074] Clause 2: The method of clause 1, wherein the selection of the image is performed in response to a user output.

[0075] Clause 3: The method of clause 2, wherein the user input provides one or more diagnostic parameters, and the selection is performed by matching any one or more of the diagnostic parameters with the metadata.

[0076] Clause 4: The method of any one of clauses 1 to 3, wherein at least one of the selected images and at least one of the retrieved images are provided in an interface, such as a human-machine interface, in the form of multiple image views.

[0077] Clause 5: The method of clause 4, wherein the image views displayed on the human machine interface are positioned on a display device depending on any one or more of the diagnostic parameters and / or the metadata of the retrieved images.

[0078] Verse 6: - updating a part of the display device or an image view of the display device; removing at least one of the image views in response to said updating; and / or - retrieving further images from said imaging data in response to said updating, to provide at least one new image view on said display device.

[0079] Clause 7: The method of any one of clauses 1 to 6, wherein at least a portion of the metadata is provided via data-driven logic.

[0080] Clause 8: The method of clause 7, wherein the data-driven logic performs semantic processing on the imaging data to provide the metadata.

[0081] Clause 9: The method of any one of clauses 1 to 8, wherein the semantic information includes a hierarchical structure and / or a parallel structure.

[0082] Clause 10: A system comprising means for performing any of the steps of the method clauses above.

[0083] Clause 11: A non-transitory computer readable storage medium storing a computer software product, or a program, comprising instructions that, when executed by one or more suitable computing units, cause any of the computing units to perform the steps described in any of the method clauses above.

[0084] Clause 12: A system for improving the usability of dental imaging data, the system comprising one or more computing units, any of the computing units comprising: providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; providing metadata for each of said images, where said metadata relating to a particular image comprises semantic information relating to one or more anatomical features recorded in that image; - selecting one or some of said images from said imaging data, - configured to retrieve at least one further image from the imaging data in response to the selection, wherein the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

[0085] Clause 13: When executed by one or more appropriate computing units, causes any of the computing units to providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; - providing metadata for each of the images, where the metadata associated with a particular image comprises semantic information related to one or more anatomical features recorded in that image; - selecting one or several of the images from the imaging data; - A non-transitory computer readable storage medium storing a computer software product or program comprising instructions for retrieving at least one other image from the imaging data in response to a selection, wherein the retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

Claims

1. 1. A computer-implemented method for improving the usability of dental imaging data, comprising: - providing imaging data comprising a plurality of different images of at least one dental imaging modality of a patient; providing metadata for each of said images, where said metadata relating to a particular image comprises semantic information relating to one or more anatomical features recorded in that image; - selecting one or some of said images from said imaging data; - retrieving at least one further image from the imaging data in response to said selection, wherein said retrieval is performed by comparing metadata of at least one of the selected images with metadata of at least one of the retrieved images.

2. The method of claim 1 , wherein the selection of the image is performed in response to user input.

3. The method of claim 2 , wherein the user input provides one or more diagnostic parameters, and the selection is performed by matching any one or more of the diagnostic parameters with the metadata.

4. 4. The method according to claim 1, wherein at least one of the selected images and at least one of the retrieved images are provided in an interface, such as a human-machine interface, in the form of multiple image views.

5. The method of claim 4 , wherein the image views displayed on the human machine interface are positioned on a display device depending on any one or more of diagnostic parameters and / or the metadata of the retrieved images.

6. - updating a part of the display device or an image view of the display device; - removing at least one of the image views in response to said updating; and / or The method of claim 5 , further comprising: - retrieving further images from said imaging data in response to said updating, to provide at least one new image view on said display device.

7. The method of claim 1 , wherein at least a portion of the metadata is provided via data-driven logic.

8. The method of claim 7 , wherein the data-driven logic performs semantic processing on the imaging data to provide the metadata.

9. The method according to claim 1 , wherein the semantic information comprises a hierarchical and / or parallel structure.

10. A system comprising means for carrying out the steps of any of the above method claims 1 to 9.

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

Images