Proposal for dental restorative material parameters

A machine learning-based system addresses the challenge of selecting dental restoration colors by suggesting user-specific parameters, improving accuracy and efficiency in restoration color selection.

JP2024542736APending Publication Date: 2024-11-15DENTSPLY SIRONA INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024532731
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-01
Filing Date
2022-11-22
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Current dental restoration tools require significant user expertise and trial-and-error to select restoration colors, leading to time-consuming and suboptimal results due to the lack of user-specific parameters and dependencies on physical factors.

Method used

A machine learning-based system that uses a trained restorative parameter recommendation module to suggest restoration colors and structures, considering factors like adjacent teeth, underlying roots, scanner calibration, and fabrication devices, to achieve a defined observable color.

Benefits of technology

The system provides accurate and efficient selection of restoration colors and structures, reducing errors and costs by automating the process and considering multiple influencing factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024542736000001_ABST
    Figure 2024542736000001_ABST
Patent Text Reader

Abstract

A parameter recommendation module is used to suggest dental restorative parameter recommendations that take into account influencing factors of final tooth color, such as underlying stump color and restorative anchor color, such that at least one output restoration feature value required to achieve the final user-specific tooth color for at least one tooth layer of the restoration is suggested.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This patent application claims the benefit of and priority to U.S. Patent Application No. 17 / 539,285, filed December 1, 2021, which is incorporated by reference herein for all purposes.

[0002] The present invention relates generally to methods, systems, and computer program products for suggesting parameters of dental restorative materials, and more particularly, to methods, systems, and computer program products for automatically suggesting restoration color and structure selections to achieve a defined viewable color. [Background technology]

[0003] Currently, technology exists to design restorations and aid in their fabrication. For example, dental software may be routinely used to fabricate restorations using input from a dental professional. The process includes an administration phase where the type of restoration is selected for the patient, such as a single tooth restoration, a bridge restoration, and an implant. The tooth formula to be restored, the restoration material, and the color of the restoration are then selected. After administration, in an acquisition phase, a three-dimensional (3D) scan of the patient's dental cavity is obtained with a dental scanner. In the next phase, a buccal registration of the patient's bite is obtained and the restoration is digitally designed. After design, the digital restoration is fabricated based on the selected fabrication process. Summary of the Invention

[0004] Exemplary embodiments provide a method, system, and computer program product for proposing dental restorative parameters. In one aspect of the present specification, a computer-implemented method is disclosed. The computer-implemented method includes receiving a three-dimensional (3D) scan of a patient's tooth cavity; identifying input data including at least one final tooth color influencing factor for a trained restorative parameter recommendation module by an input resource; extracting one or more features representing completion requirements of a restoration design and / or machining process from the input data in response to the identification; and proposing at least one output restoration feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration using the trained restorative parameter recommendation module. The final user-specific tooth color represents an observed color of the restoration after being placed in the patient's oral cavity, and the observed color is influenced by the at least one final tooth color influencing factor. Furthermore, the trained restorative parameter recommendation module can operate as a machine learning engine.

[0005] The method for selecting at least one final tooth color influencing factor in the input data is selected from the list consisting of physical characteristics of one or more parts of the restorative block or restorative material, physical characteristics of one or more parts of the oral cavity, scanner characteristics, customer color preferences, and available production devices.

[0006] The method may also include training an untrained version of the component machine learning model of the restorative parameter recommendation module, which is subsequently trained, using a training input data set including training input images and / or shades obtained from a plurality of training restorative blocks and / or 3D printer materials selected to have characteristics that result in a plurality of final user-specific training tooth colors, and the corresponding stored training output restorative feature values. Other technical features will be readily apparent to one skilled in the art from the following drawings, description, and claims.

[0007] In another aspect, a computer system is disclosed. The computer system may include a processor configured to execute the steps of receiving a three-dimensional (3D) scan of a patient's tooth cavity, identifying input data including at least one final tooth color influencing factor for a trained restorative parameter recommendation module by an input resource, and in response to the identification, extracting from the input data one or more features representative of completion requirements for the design and / or machining process of the restoration, and proposing, using the trained restorative parameter recommendation module, at least one output restoration feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration. The final user-specific tooth color represents an observed color of the restoration after being placed in the patient's mouth, the observed color being influenced by the at least one final tooth color influencing factor.

[0008] In yet another aspect, a non-transitory computer-readable storage medium is disclosed. The non-transitory computer-readable storage medium can store a program that, when executed by a computer system, causes the computer system to execute a procedure including: receiving a three-dimensional (3D) scan of a patient's tooth cavity; identifying, by an input resource, input data including at least one final tooth color influencing factor for a trained restorative parameter recommendation module; in response to the identification, extracting from the input data one or more features representing completion requirements for the design and / or machining process of the restoration; and using the trained restorative parameter recommendation module to propose at least one output restoration feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration, the final user-specific tooth color representing an observed color of the restoration after being placed in the patient's oral cavity.

[0009] Certain novel features which are believed to be characteristic of the present invention are set forth in the appended claims, however the invention itself, together with its preferred mode of use, further objects and advantages, will best be understood by reference to the following detailed description of illustrative embodiments when read in connection with the accompanying drawings. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram of a network of data processing systems in which illustrative embodiments may be implemented; [Diagram 2] 1 is a block diagram of a data processing system in which illustrative embodiments may be implemented; [Diagram 3] FIG. 1 is a block diagram of an example configuration for intelligently suggesting dental / workflow parameters for restorations and machining according to one or more example embodiments. [Figure 4] FIG. 2 illustrates a repair block in accordance with one or more exemplary embodiments. [Diagram 5] FIG. 1 is a block diagram of an example training architecture for a machine learning based recommendation engine according to one or more example embodiments. [Figure 6] FIG. 1 illustrates a method according to one or more exemplary embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The exemplary embodiments recognize that a user of dental CAD / CAM software for designing and fabricating restorations needs to determine what color the restoration should have. The user needs to be experienced enough to select the colors (e.g., color A2) to use to result in the final color A1 that can be observed after being influenced by other fabrication and physical factors. This is essentially guesswork, requiring significant specialized skill and trial and error, and may not be suitable or appropriate for long-term practice.

[0012] For example, when a dentist scans a patient's jaw for a dental procedure, they manually set the restoration and fabrication parameters by modifying the default parameters proposed by the software, which is time-consuming, error-prone and often suboptimal for a particular patient due to a possible lack of knowledge about the user-specific parameters and their dependencies.

[0013] Thus, the exemplary embodiments recognize that currently available tools or approaches do not address the need to provide intelligent management of dental workflow configurations to provide timely optimized restorations. The exemplary embodiments used to describe the present invention generally use a machine learning engine to set dental restoration parameters in a patient and / or user specific manner through intelligent recommendations.

[0014] Such settings may include determining the final observable color of the restoration based on several factors, including but not limited to the color of the adjacent teeth, the color of the underlying root stump, the patient's tooth color preference, the shape of the various layers of the restoration block, the color of the mounting medium (such as glue), the thickness of the restoration, and the calibration of the camera used for imaging. Taking these factors and other factors such as the translucency, transparency, and reflective behavior of the objects in the workflow into account, the selection of materials and material layers may be determined. Furthermore, the device used for fabrication may also be taken into account. For example, by using a milling or grinding device, the layers of the restoration block and their colors and the positioning of the design restoration in the block may be fixedly preset before fabrication. Using a 3D printer, the shape and color of the layers may be precisely selected, such as voxel by voxel.

[0015] Thus, in one embodiment, an automatic selection of restoration color and restoration layer structure may be shown that allows observation of the final desired restoration properties after being influenced by other "influencing" properties. Deep neural networks may be used to generate suggestions based on images generated by an intraoral scanner, including, for example, the colors of adjacent restorations and underlying stumps and / or the shades of detected teeth. In doing so, the color of the restoration may be determined more accurately without relying on other devices or people, saving costs and reducing errors.

[0016] In one embodiment, increasing complexity of the desired restorative properties can be achieved based on the best-fit monochromatic color block, polychromatic color block, or automatic determination of the complete color and material structure required for an efficient result. For example, for monochromatic color blocks, the deep neural network can perform a calibration of color values ​​obtained from intraoral camera images with the color of the materials used to achieve the desired result. In doing so, the neural network can learn from the images which parts of the teeth are more likely to affect the color suggestion. Automatic tooth segmentation can be employed in a pre-processing step to limit the analysis to adjacent teeth and the remaining tooth regions near the preparation site. The automatic suggestions can be corrected by the user if inaccurate, and the deep neural network can be improved over time by backpropagation of the results. In another example, for polychromatic blocks, suggestions can also be generated regarding the positioning of digital restorations in a particular polychromatic block to achieve a tooth appearance that also takes into account external factors such as the thickness of the restorative material, the refraction of light by the restorative material, etc. Additionally, for 3D printing, where a repair block may not be used, the deep neural network can generate material structure and color suggestions for the printing or sintering process.

[0017] In a further embodiment, the deep neural network may be trained as follows: A large number of training images and scans of models of the resulting restoration structure may be provided, where restoration blocks of different colors and materials or internal structures made from 3D printed materials may be provided. A corresponding restoration may be fabricated and installed in a corresponding model or a corresponding oral cavity with the desired neighborhood characteristics. Scans of the model or oral cavity and / or installed restoration may provide an input training data set corresponding to known characteristics of said internal structures, which may act as an output training data set. By providing an input training data set, for example in the form of color values, to a deep neural network composed of respective input layers and / or hidden nodes, the obtained output probabilities, which indicate the ideal characteristics of the blocks / materials / internal structures required to observe the desired final tooth color, may be compared with the output training data set, and the weights in the deep neural network may be optimized to minimize the loss function. Furthermore, depending on the granularity of the output proposals from the deep neural network, thousands of such training data sets may be required. To obtain such a large number of training data sets economically, it may be necessary to obtain result data of various users and therefore to re-scan the installed restorations. By integrating rescanning into the dental restoration workflow, data can be returned from any use case for use in training.

[0018] After training, in the application phase, scans of the tooth to be restored and / or adjacent teeth are used as inputs from which the deep neural network may propose as output the internal structure of the tooth to be fabricated to obtain the final observable tooth properties, such as the final observable tooth color. In this specification, the term "final" generally refers to the property value observed after the restoration is placed, which may differ from the original value due to the influence of other factors. For example, a restoration may be fabricated using a block or 3D printer material with a monochromatic or multicolored color A1, but due to the thin thickness and translucency of the restoration, the placed restoration may be observed to have a monochromatic or multicolored color A2 different from A1 due to the stumps below the placed restoration. Thus, color A2 may be the "final" observable color.

[0019] Furthermore, since the volume data and their properties are obtained from the surface scan, for every surface point, all the contributions of the single camera images and their imaging directions can be stored and provided to the deep neural network. Furthermore, to take into account the refraction between air and dentin and / or enamel, the surface normal of each image point can be provided, since different imaging directions from the surface normal may result in different color information for the same surface point.

[0020] Furthermore, in another embodiment, the number of proposals may be limited in the realization step of the implementation of the deep neural network. Therefore, a limited number (e.g., several tens) of reference examples with empirically obtained meaningful characteristics of the internal structure / block / material and the applied scan may be generated to form an input-output training data set. This may act as a basis function over the solution space of possible internal structures. Each AI / deep neural network / machine learning model finds some weights of the basis functions that can be realized with a clearly reduced number of training examples. Alternatively, the weights of the basis functions are found directly by an optimization algorithm. Here, further training examples may not be necessary. By designing the basis functions of all teeth to be similar, missing or severely defective teeth may be concluded from the analysis of adjacent teeth.

[0021] These examples of settings, configurations, parameters, characteristics, etc. are not intended to be limiting, and from this disclosure, a person skilled in the art may conceive many other aspects applicable to similar purposes, which are considered to be within the scope of the exemplary embodiments.

[0022] The exemplary embodiments are described by way of example only with respect to particular types of data, functions, algorithms, formulas, model configurations, embodiment locations, further data, devices, data processing systems, environments, components, and applications. Any particular representation of these and other similar artifacts is not intended to limit the invention. Any suitable representation of these and other similar artifacts may be selected within the scope of the exemplary embodiments.

[0023] Furthermore, the exemplary embodiments may be implemented with respect to any type of data, data source, or access to a data source via a data network. Any type of data storage device may provide data to the embodiments of the present invention, either locally at a data processing system or via a data network, within the scope of the present invention.

[0024] Exemplary embodiments are described using specific code, designs, architectures, protocols, layouts, schematics, and tools as examples only and are not intended to be limiting to exemplary embodiments. Furthermore, exemplary embodiments may be described using specific software, tools, and data processing environments as examples only for clarity of explanation. Exemplary embodiments may be used in conjunction with other equivalent or similar purpose structures, systems, applications, or architectures. For example, other dental systems, structures, applications, or architectures thereof may be used in conjunction with such embodiments of the present invention within the scope of the present invention. Exemplary embodiments may be implemented in hardware, software, or a combination thereof.

[0025] The examples in this disclosure are used for clarity of explanation only and are not intended to be limiting of the exemplary embodiments. Additional data, operations, actions, tasks, activities, and operations are contemplated by this disclosure and are considered to be within the scope of the exemplary embodiments.

[0026] The advantages listed herein are merely examples and are not intended to be limiting of example embodiments. Additional or different advantages may be realized by certain example embodiments. Moreover, certain example embodiments may have some, all, or none of the above listed advantages.

[0027]

[0023] Referring now to the drawings, and in particular to Figures 1 and 2, which are exemplary diagrams of data processing environments in which illustrative embodiments may be implemented, Figures 1 and 2 are merely examples and are not intended to assert or imply any limitation with respect to the environments in which different embodiments may be implemented. In a particular implementation, many changes may be made to the depicted environments based on the following description.

[0028] 1 is a block diagram of a network of data processing systems in which exemplary embodiments may be implemented. The data processing environment is a network of computers in which exemplary embodiments may be implemented. Data processing environment 100 includes a network / communications infrastructure 102. Network / communications infrastructure 102 is the medium used to provide communications links between various devices, databases, and computers connected together in data processing environment 100. Network / communications infrastructure 102 may include connections such as wired, wireless communication links, or fiber optic cables.

[0029] Client or server are merely examples of roles of particular data processing systems connected to the network / communication infrastructure 102 and are not intended to exclude other configurations or roles of these data processing systems. Server 104 and server 106 are coupled to the network / communication infrastructure 102 along with storage unit 108. Software applications can run on any computer in the data processing environment 100. Client 110, client 112, client 114 are also coupled to the network / communication infrastructure 102. Client 110 can be a dental collection unit with a display. Data processing systems such as server 104 or server 106 or clients (client 110, client 112, client 114) can store data and can have software applications or software tools running thereon.

[0030] Merely by way of example, and without implying any limitation to such architecture, Figure 1 illustrates certain components that may be used in an exemplary implementation of one embodiment. For example, the servers and clients are merely examples and do not imply any limitation to a client-server architecture. As another example, one embodiment may be distributed across several data processing systems and data networks as shown, although another embodiment may be implemented in a single data processing system within the scope of the exemplary embodiment. The data processing systems (server 104, server 106, client 110, client 112, client 114) also represent exemplary nodes in clusters, partitions, and other configurations suitable for implementing an embodiment.

[0031] The dental scanner 122 includes one or more sensors that measure the geometry and / or color of the teeth by acquiring multiple images through projections and combining the projections to obtain a three-dimensional (3D) image. In one example, the dental scanner 122 captures data points thousands of times per second to automatically register the size and shape of each tooth. This data is continuously fed to software in a connected computer, which builds a 3D impression of the patient's mouth.

[0032] The most widely used digital format is the Standard Tessellation Language (STL) format. This format describes a set of triangular surfaces, where each triangle is defined by three points and a surface normal. STL files may only describe the surface geometry of a three-dimensional object, without any representation of color, texture, or other CAD model attributes. However, other file formats (polygon file format, PLY file, etc.) have been developed and may be used to record the color, transparency, or texture of dental tissue. Regardless of the type of imaging technology used, a scanner or camera projects light, which is recorded as individual images and compiled by software after the recognition of points of interest (POIs). For example, two coordinates (x and y) of each point on the image are evaluated, and then a third coordinate (z) is calculated depending on the distance from the scanner.

[0033] The client application 120 or any other application 116 implements the embodiments described herein. The client application 120 can use data from the dental scanner 122 to generate the restorative parameters necessary to achieve the final user-specific tooth color / structure. The client application 120 can also automatically derive input data from the input resource module 324 for use in proposing the restorative parameters. The client application 120 can suggest parameters of the restoration block 132 for the milling / grinding machine 126 or parameters of the 3D printer material 128 (e.g., resin) for the 3D printer 124. The proposed parameters can then be used to fabricate the user-specific restoration 130.

[0034] Client application 120 may also execute on any of the data processing systems (server 104 or server 106, client 110, client 112, client 114), such as client application 116 in server 104, and need not execute on the same system as client 110.

[0035] Server 104, server 106, storage unit 108, clients 110, 112, and 114 may be coupled to network / communications infrastructure 102 using wired connections, wireless communication protocols, or other suitable data connections. Clients 110, 112, and 114 may be, for example, personal computers or network computers.

[0036] In the illustrated example, server 104 may provide data such as boot files, operating system images, and applications to clients 110, 112, and 114. Clients 110, 112, and 114 may be clients to server 104 in this example. Clients 110, 112, and 114, or any combination thereof, may include their own data, boot files, operating system images, and applications. Data processing environment 100 may include additional servers, clients, and other devices not shown. Server 104 includes application 116, which may be configured to implement one or more of the functions described herein to display a live control view according to one or more embodiments.

[0037] The server 106 may include a search engine configured to search stored files, such as images, 3D models of patients, and dental clinic preferences, in response to requests from an operator, as described herein with respect to various embodiments.

[0038] In the depicted example, data processing environment 100 may be the Internet. Network / communications infrastructure 102 may represent a collection of networks and gateways that communicate with each other using TCP / IP (Transmission Control Protocol / Internet Protocol) and other protocols. At the core of the Internet is a backbone of data communications links between major nodes or host computers, including thousands of dental offices, commercial, government, educational institutions, and other computer systems that route data and messages. Of course, data processing environment 100 may also be implemented as a number of different types of networks, such as, for example, an intranet, a LAN (local area network), or a WAN (wide area network). FIG. 1 is intended as an example and not as an architectural limitation for the various illustrative embodiments.

[0039] Among other uses, the data processing environment 100 may be used to implement a client-server environment in which exemplary embodiments may be implemented. A client-server environment allows software applications and data to be distributed across a network such that the applications function by utilizing interactivity between client and server data processing systems. The data processing environment 100 may also employ a service-oriented architecture in which interoperable software components distributed across a network may be packaged as a coherent business application. The data processing environment 100 may also take the form of a cloud and employ a cloud computing model of service delivery to enable convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal administrative effort or interaction with a service provider.

[0040] Referring to Figure 2, a block diagram of a data processing system in which an exemplary embodiment may be implemented is shown. Data processing system 200 is an example of a computer, such as client 110, client 112, client 114, or server 104, server 106 of Figure 1, or another type of device in which computer usable program code or instructions implementing processes in an exemplary embodiment may be located.

[0041] Data processing system 200 is illustrated as a computer by way of example only, and not by way of limitation, as implementations of other device forms may modify data processing system 200, such as by adding a touch interface, or even omit certain illustrated components from data processing system 200, without departing from the general operational and functional aspects of data processing system 200 described herein.

[0042] In the illustrated example, data processing system 200 employs a hub architecture including a northbridge / memory controller hub (NB / MCH) 202 and a southbridge / input / output (I / O) controller hub (SB / ICH) 204. A processing unit 206, a main memory 208, and a graphics processor 210 are coupled to NB / MCH (northbridge / memory controller hub) 202. Processing unit 206 may include one or more processors and may be implemented using one or more heterogeneous processor systems. Processing unit 206 may be a multi-core processor. Graphics processor 210 may be coupled to NB / MCH (northbridge / memory controller hub) 202 through an accelerated graphics port (AGP) in a particular implementation.

[0043] In the illustrated example, a LAN (local area network) adapter 212 is coupled to a SB / ICH (southbridge / input / output (I / O) controller hub) 204. An audio adapter 216, a keyboard and mouse adapter 220, a modem 222, a ROM (read only memory) 224, a USB (universal serial bus) and other ports 232, and a PCI / PCIe device 234 are coupled to the SB / ICH (southbridge / input / output (I / O) controller hub) 204 through a bus 218. A HDD (hard disk drive) or SSD (solid state drive) 226a and a CD-ROM 230 are coupled to the SB / ICH (southbridge / input / output (I / O) controller hub) 204 through a bus 228. The PCI / PCIe device 234 may include, for example, an Ethernet adapter, an add-in card, and a PC card for a notebook computer. PCI uses a card bus controller, whereas PCIe does not. The ROM (Read Only Memory) 224 may be, for example, a BIOS (Flash Binary Input / Output System). The HDD (Hard Disk Drive) or SSD (Solid State Drive) 226a and the CD-ROM 230 may use, for example, an IDE (Integrated Drive Electronics), a SATA (Serial Advanced Technology Attachment) interface, or variations such as eSATA (external-SATA) and mSATA (micro-SATA). The SIO (Super I / O) device 236 may be coupled to the SB / ICH (South Bridge / Input / Output (I / O) Controller Hub) 204 through the bus 218.

[0044] Memory such as main memory 208, ROM (read only memory) 224, or flash memory (not shown) are some examples of storage devices available to the computer. Hard disk drives (HDD) or solid state drives (SSD) 226a, CD-ROM 230, and other similarly available devices are some examples of storage devices available to the computer, including storage media available to the computer.

[0045] An operating system runs on the processing unit 206. The operating system coordinates and provides control of various components within the data processing system 200 of FIG. 2. The operating system may be a commercially available operating system for any type of computing platform, including, but not limited to, server systems, personal computers, and mobile devices. An object-oriented or other type of programming system may work in conjunction with the operating system to provide calls to the operating system from programs or applications executing on the data processing system 200.

[0046] 1 may be located on a storage device, such as in the form of code 226b on a hard disk drive (HDD) or solid state drive (SSD) 226a, and loaded into at least one of one or more memories, such as main memory 208, for execution by the processing unit 206. The processes of the exemplary embodiments may be executed by the processing unit 206 using computer-implemented instructions, which may be located, for example, in a memory, such as the main memory 208, a read-only memory (ROM) 224, or in one or more peripheral devices.

[0047] Further, in one case, code 226b may be downloaded from a remote system 214b via network 214a and similar code 214c may be stored in storage device 214d, and in another case, code 226b may be downloaded to a remote system 214b via network 214a and the downloaded code 214c may be stored in storage device 214d.

[0048] The hardware in Figures 1 and 2 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, or optical disk drives, may be used in addition to or in place of the hardware depicted in Figures 1 and 2. Additionally, the processes of the illustrative embodiments may be applied to multiprocessor data processing systems.

[0049] In some examples, data processing system 200 may be a PDA (Personal Digital Assistant), which is typically configured with flash memory to provide non-volatile memory for storing operating system files and / or user generated data. The bus system may include one or more buses, such as a system bus, an I / O bus, and a PCI bus. Of course, the bus system may be implemented using any type of communications fabric or architecture that provides for a transfer of data between different components or devices attached to the fabric or architecture.

[0050] The communications unit may include one or more devices used to transmit and receive data, such as a modem or a network adapter. The memory may be, for example, main memory 208 or a cache, such as that found in NB / MCH (North Bridge / Memory Controller Hub) 202. The processing unit may include one or more processors or CPUs.

[0051] 1 and 2 and above-described examples are not meant to imply architectural limitations. For example, data processing system 200 may also be a tablet computer, a laptop computer, or a telephone device in addition to taking the form of a mobile or wearable device.

[0052] When a computer or data processing system is described as a virtual machine, virtual device, or virtual component, the virtual machine, virtual device, or virtual component operates in the manner of data processing system 200 using virtual representations of some or all of the components depicted in data processing system 200. For example, in a virtual machine, virtual device, or virtual component, processing unit 206 is represented as a virtual instance of all or some number of hardware processing units 206 available to the host data processing system, main memory 208 is represented as a virtual instance of all or a portion of main memory 208 available to the host data processing system, and HDD (hard disk drive) or SSD (solid state drive) 226a is represented as a virtual instance of all or a portion of HDD (hard disk drive) or SSD (solid state drive) 226a available to the host data processing system. The host data processing system in such a case is represented by data processing system 200.

[0053] 3, which illustrates a block diagram of an exemplary configuration for intelligently suggesting restoration and dental restorative parameters, according to an exemplary embodiment. Application 304 is an example of either server application 116 or client application 120 of FIG. 1, depending on the particular implementation.

[0054] In one aspect, the application 304 may receive a three-dimensional (3D) scan of a patient's tooth cavity and identify input data including at least one final tooth color influencing factor by the input resource module 324. The input data is used as an input for the trained restorative parameter recommendation module, which in response to the identification may extract one or more features from the input data that represent the completion requirements for the design and / or machining process of the restoration. The trained restorative parameter recommendation module may then suggest at least one output restoration feature value required to achieve the final user-specific tooth color for at least one tooth layer of the restoration. Herein, for example, the final user-specific tooth color may represent the observed color of the restoration after it is placed in the patient's mouth, since the initial color is influenced by the at least one final tooth color influencing factor described above. Furthermore, the trained restorative parameter recommendation module may operate as a machine learning engine.

[0055] The input resource module 324 may be a dental software component that obtains and / or prepares input data 302 from the dental scanner 122 and / or other sources. The input data 302 may represent at least one influencing factor of the final tooth color, such as physical characteristics of one or more parts of the restoration block or material (e.g., shape or color of the various layers of the restoration block, color of the mounting medium (e.g., glue), thickness of the restoration, translucency, transparency, and reflective behavior of the restoration block or material, etc.), physical characteristics of one or more parts of the oral cavity (e.g., color of the underlying stump, color of the adjacent teeth), scanner characteristics (e.g., camera color calibration such as color mapping, lighting conditions, etc.), customer color preferences, available fabrication devices (e.g., milling or grinding devices or 3D printers), etc. Knowledge of these characteristics may improve the accuracy of the suggestions. For example, not taking into account the thickness and material type of the veneer may cause the final observed color to differ from the original selected color due to light shining through a thin veneer, or not taking into account the color of the underlying stump may cause the appearance of the restoration or veneer to change due to the underlying dark yellow stump. In a specific example, the color input obtained from the dental scanner 122 is an array of color values ​​(such as a color mapping) or texture of 3D points within a 3D image or a segmented 3D image obtained based on the dental scanner 122. Additionally, the input data may include other factors that do not affect the final tooth color, such as the location of the preparation site in the oral cavity.

[0056] The input resource module 324 can automatically detect drill cavities or preparation sites in the image, for example by image analysis, and automatically segment parts of the teeth or oral cavity to limit subsequent analysis to parts of the preparation sites, such as adjacent teeth and / or stumps, by the deep neural network described herein. Thus, the input data can be selected to represent segments of teeth obtained from the segmentation process, i.e., the input data includes physical features of one or more parts of the oral cavity, the one or more parts of the oral cavity including the segmented parts of teeth obtained by the segmentation process, and at least one output restoration feature value can be proposed based on the segmented parts.

[0057] Furthermore, the input resource module 324 may detect from preferences 322 obtained, for example, from a patient profile, a doctor profile, a group profile, a connected device, etc. From a patient profile, a particular color of the restoration 130 may be preferred. The input data 302 obtained directly from the dental scanner 122 may be generally referred to herein as CAD / CAM input data 320, and input data 302 regarding the suitability of the output proposal based on a particular available device type, for example, which may be generally referred to herein as dependencies 326. Furthermore, individual parts of the input data 302 may be weighted or prioritized to bring about a corresponding change in the proposal. These dependencies may be complex and may require a high degree of skill when manually selected, and their importance to the final user-specific tooth color is not always clearly understood by all users. Thus, if said dependencies are not taken into account, this may result in suboptimal restoration results, processes, and costs.

[0058] In one embodiment, the feature extraction component 314 is configured to generate relevant features for the proposal based on data from all the different available features (e.g., CAD / CAM input data 320, preferences 322). In this embodiment, the feature extraction component 314 may be part of a restorative parameter recommendation module 316, which may include a deep neural network / m / l model 306 (machine learning model). In other embodiments, the feature extraction component 314 may be a feature selection component and separate from the restorative parameter recommendation module 316. In one embodiment, the feature extraction component 314 is a feature selection component external to the deep neural network and receives a request from the application 304 including at least an identification of the type of recommendation / suggestion required (e.g., a request to propose restorative parameters required to fabricate and install a restoration for user X, where the installed restoration will have a final color X). C1The feature extraction component 314 may process or use a combination of CAD / CAM input data 320 related to the required requirements or suggestions. In this embodiment, the feature extraction component 314 may use a predefined algorithm of prioritization or dependencies to generate features as input for the restorative parameter recommendation module 316. In another embodiment, the feature extraction component 314 is part of the restorative parameter recommendation module 316, and thus the input data 302 is provided to the restorative parameter recommendation module 316 to obtain a suggestion of output restoration feature values ​​312, which may be a matrix of probability values ​​representing one or more features of the restorative material to be used to obtain the final user-specific tooth color. The output restoration feature values ​​312 may include a suggestion of optimal positioning 410 of the restoration within the digital restoration block 402 to achieve the desired observed color for each different section of the restoration. This may be ideal when only a milling / grinding machine 126 is available to fabricate the restoration. The output restoration feature values ​​312 may also include a suggestion of the optimal initial color of the restoration block or the internal structure of the restoration block required to achieve the desired observed final color. Additionally, the output restoration feature values ​​312 may include a suggestion of at least one internal structure of the restoration block required to achieve the desired observed color for each different section of the final restoration. The output restoration feature values ​​312 may also include a suggestion of at least one fabrication process required to achieve the final user-specific tooth color (e.g., a suggestion that the user can use the 3D printer 124 instead of the milling / grinding machine 126 to achieve the best final color). The output restoration feature values ​​may also include a suggestion of at least one color of a 3D volume of material required for the 3D printer to achieve the final user-specific tooth color (e.g., in the case of the 3D printer 124, the color of each voxel of the restoration can be determined for printing by the 3D printer 124, thus allowing the user more control over the final user-specific tooth color).Furthermore, a set of output suggestion options regarding restoration parameters such as restorative material, positioning of the digital restoration in the Digital Restoration block 402 and corresponding fabrication device to be used, as well as the probability for each of the set of components of successfully achieving the final user-specific tooth color after placement of the restoration in the mouth may also be generated. This may be a matrix that is further processed to be presented in a user understandable manner as various confidence / percentage values ​​or interval options.

[0059] FIG. 4 illustrates a digital restoration block 402 according to one or more embodiments. The digital restoration block 402 may have multiple layers, such as a first layer 404, a second layer 406, and a third layer 408. The layers may have boundaries of any shape, such as straight or curved boundaries. The predefined layers provided in the 3D image of the restoration block or the 3D model of the restoration block may result in the shape or color of the various layers of the restoration block. By being able to suggest a specific digital restoration block 402 and a position 410 of a digital restoration 412 within the digital restoration block 402, the final user-specific tooth color may be reliably controlled by the restorative parameter recommendation module 316. Thus, in embodiments where a restoration block is used, the output restoration feature value 312 may include the tooth color or colors selected by determining the type of restoration block and positioning the restoration. This may allow for the observation of the corresponding desired final tooth color or colors after the restoration is fabricated and placed in the oral cavity.

[0060] The restorative parameter recommendation module 316 can be based on an artificial machine learning neural network, such as, for example, but not limited to, a Convolutional Neural Network (CNN), which is a feed-forward artificial neural network that in its classical form consists of a convolutional layer followed by a pooling layer. A CNN learns by learning the free parameters of the convolution kernels or classifiers for each layer and their weighting when computing the next layer.

[0061] Training of the m / l model 306 or restorative parameter recommendation module 316 according to an exemplary embodiment is described below.

[0062] In an exemplary embodiment, the presentation module 308 of the application 304 displays the suggestions obtained from the restorative parameter recommendation module 316. The presentation module 308 may display, for example, multiple options of 3D printer materials 128, 3D printers 124, restoration blocks 132, or milling / grinding machines 126, as well as the probability of achieving the desired color result after installation of the corresponding restoration. The adaptation module 310 may be configured to receive input from the practitioner to adapt the output restoration feature values ​​312 as needed. For example, changing the final user-specific tooth color may recalculate the proposed output restoration feature values ​​312 for presentation by the presentation module 308.

[0063] The proposed options may be pre-selected based on their corresponding probabilities.

[0064] When new tools and materials with specific instructions and requirements are added to the dental workflow, the restorative parameter recommendation module 316 can be retrained, significantly reducing the need for the practitioner to be aware of the detailed impact on the final user-specific tooth color. The feedback module 318 optionally collects user feedback 322 indicating the accuracy of the output restoration feature values ​​312. In one embodiment, the application 304 is configured to not only present recommendations, but also provide a way for the user to input feedback. The feedback module 318 applies the feedback in machine learning techniques to dependencies 326 or user profiles, etc. to modify the m / l model 306 used in the restorative parameter recommendation module 316.

[0065] The neural network m / l model 306 may be trained using various types of training data sets. Training may include using a training data set that includes training input images and / or corresponding shade / color mappings and corresponding training output inpainting feature values ​​obtained from a number of corresponding training inpainting blocks and / or 3D printer materials. The corresponding training output inpainting feature values ​​may represent properties of the training inpainting blocks and / or 3D printer materials.

[0066] More specifically, training may include preparing a plurality of training restorative blocks and / or 3D printer materials and fabricating a plurality of corresponding restorations using said plurality of training restorative blocks and / or 3D printer materials. The plurality of training restorative blocks and / or 3D printer materials may be selected by a professional to have certain known characteristics that provide an installed restoration with an observed color that matches a desired color after installation, an example of such a desired color being the color of an adjacent tooth. The known characteristics may be stored as corresponding saved training output restoration feature values. The fabricated restorations may be installed in a corresponding physical model or oral cavity. The corresponding physical model or oral cavity may be scanned to obtain corresponding images and / or shades for use as part of a training input dataset. The training input dataset may be used as an input to a machine learning model, and corresponding output restoration feature values ​​may be obtained from the machine learning model. The corresponding output restoration feature values ​​may then be compared to the corresponding saved training output restoration feature values.

[0067] FIG. 5 illustrates an exemplary training architecture 502. In one embodiment, upon receiving a request to provide suggestions, the application 304 creates an array of values ​​to be input to the input neurons of the m / l model 306 to generate an array containing the recommendation / output repair feature values ​​312. As shown in FIG. 5, which illustrates a block diagram of an exemplary training architecture 502 for machine learning based suggestion generation according to an exemplary embodiment, the program code extracts 506 various features / attributes from the training data 504 with training data entries having a label L. The features are used to develop a prediction function H(x) or hypothesis that the program code uses as the machine learning model 508. In identifying the various features / attributes of the training data 504, the program code may use various techniques including, but not limited to, mutual information, which is an example of a method that may be used to identify features in one embodiment. Other embodiments may use various techniques for selecting features including, but not limited to, principal component analysis, diffusion mapping, random forests, and / or recursive feature elimination (a brute force approach to selecting features) for selecting features. "P" is an output (e.g., restorative parameters and / or probabilities) that can be obtained, upon receipt of which the dental system can be further triggered to perform other steps, such as displaying an option to start the machining process. The program code can train the machine learning model 508 using a machine learning algorithm 512, including weighting the output, such that the program code can prioritize various modifications based on a predictive function that constitutes the machine learning model 508. The output can be evaluated by a quality metric 510.

[0068] By selecting different sets of training data 504, the program code trains a machine learning model 508 to identify and weight various attributes of patients, physicians, devices connected to the dental system, etc. To use the machine learning model 508, the program code obtains (or derives) input data or features to generate an array of values ​​to input to the input neurons of the neural network. In response to these inputs, the output neurons of the neural network generate an array including output repair feature values ​​312 that can be simultaneously presented on a display.

[0069] Moreover, in another embodiment, the number of proposals may be limited. Here, a limited number of reference examples with empirically obtained meaningful characteristics of the internal structures / blocks / materials and applied scans may be generated to form an input-output training data set. This may act as a basis function over the solution space of possible internal structures. The machine learning model then finds some weights of the basis functions that can be realized with a clearly reduced number of training examples. Alternatively, the weights of the basis functions are found directly by an optimization algorithm. Here, no further training examples may be necessary. By designing the basis functions of all teeth to be similar, missing or defective teeth may be concluded from the analysis of the adjacent teeth.

[0070] With reference to FIG. 6, a process 600 for suggesting dental restorative parameters is disclosed. In step 602, the process 600 may receive a three-dimensional (3D) scan of a patient's tooth cavity. In step 604, the process 600 may identify input data including at least one final tooth color influencing factor for the trained restorative parameter recommendation module by an input resource. In step 606, the process 600 may extract one or more features from the input data in response to the identification, which represent the completion requirements of the design and / or machining process of the restoration. In step 608, the process 600 may use the trained restorative parameter recommendation module to suggest at least one output restoration feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration. In this specification, the final user-specific tooth color represents the observed color of the restoration after being placed in the patient's mouth, and the observed color is influenced by at least one final tooth color influencing factor, such as the color of the underlying stump. The trained restorative parameter recommendation module may operate as a machine learning engine.

[0071] The process 600 may include scanning the patient's oral cavity with an intraoral scanner to obtain at least a portion of the input data.

[0072] Thus, computer-implemented methods, systems, or apparatus, and computer program products are provided in exemplary embodiments of intelligent suggestions and other related features, functions, or operations. Where an embodiment, or portions thereof, is described in terms of a certain type of device, the computer-implemented method, system, or apparatus, computer program product, or portions thereof, is adapted or configured for use with an appropriate equivalent representation of that type of device.

[0073] Where an embodiment is described as being implemented in an application, delivery of the application in a Software as a Service (SaaS) model is contemplated within the scope of the exemplary embodiment. In the SaaS model, the functionality of the application implementing the embodiment is provided to a user by executing the application in a cloud infrastructure. The user can access the application using a variety of client devices through a thin client interface, such as a web browser or other lightweight client application. The user does not manage or control the underlying cloud infrastructure, including the cloud infrastructure's network, servers, operating systems, or storage. In some cases, the user may not even manage or control the functionality of the SaaS application. In some other cases, the SaaS implementation of the application may allow for possible exceptions of limited user-specific application configuration settings.

[0074] The present invention may be a system, method, and / or computer program product integrated at any possible level of technical detail. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions for causing a processor to carry out aspects of the present invention.

[0075] A computer readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer readable storage media includes portable computer diskettes, hard disks, RAM (random access memory), ROM (read only memory), EPROM (erasable programmable read only memory) or flash memory, SRAM (static random access memory), CD-ROM (portable compact disk read only memory), DVD (digital versatile disk), memory sticks, floppy disks, punch cards or mechanically encoded devices such as ridge structures in grooves in which instructions are recorded, and any suitable combination of the above. Computer-readable storage media, including but not limited to computer-readable storage devices, as used herein should not be construed as being transitory signals per se, such as electric waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses through a fiber optic cable), or electrical signals transmitted over wires.

[0076] The computer-readable program instructions described herein can be downloaded from the computer-readable storage medium to each computing / processing device or to an external computer or storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface of each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium of the respective computing / processing device.

[0077] The computer readable program instructions for carrying out the operations of the present invention may be either source code or object code written in any combination of one or more programming languages, including assembler instructions, ISA (Instruction Set Architecture) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, object oriented programming languages ​​such as Smalltalk, C++, and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partially on the user's computer as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or the connection may be made to an external computer (e.g., through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, an FPGA (field programmable gate array), or a PLA (programmable logic array), may execute computer readable program instructions by using state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of the present invention.

[0078] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0079] These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce means for performing the functions / operations specified in one or more blocks of the flowchart illustrations and / or block diagrams. These computer readable program instructions may also be stored in a computer readable storage medium that can cause a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer readable storage medium having stored thereon instructions includes an article of manufacture having instructions that implement aspects of the functions / operations specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0080] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device such that a series of operational steps are performed by the computer, or other programmable apparatus, or other device to produce a computer-implemented process such that the instructions executing on the computer, or other programmable apparatus, or other device perform the functions / acts specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0081] The flowchart diagrams and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart diagrams or block diagrams may represent a module, segment, or portion of instructions comprising one or more executable instructions for implementing a particular logical function. In some alternative implementations, the functions shown in the blocks may occur out of the order shown in the drawings. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It is also noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a special-purpose hardware-based system that performs a particular function or operation or executes a combination of special-purpose hardware and computer instructions.

Claims

1. receiving a three-dimensional (3D) scan of a patient's dental cavity; Identifying input data including at least one final tooth color influencing factor for a restorative parameter recommendation module to be trained by an input resource; - in response to said identification, extracting from the input data one or more features representative of completion requirements for the design and / or machining process of the restoration; using a trained restorative parameter recommendation module to suggest at least one output restorative feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration; A method comprising: the final user-specific tooth color represents an observed color of the restoration after being placed in the patient's mouth, the observed color being influenced by the at least one final tooth color influencing factor; The trained restorative parameter recommendation module operates as a machine learning engine. method.

2. 2. The method of claim 1, wherein the at least one final tooth color influencing factor in the input data is selected from the list consisting of physical characteristics of one or more parts of the restorative block or restorative material, physical characteristics of one or more parts of the oral cavity, scanner characteristics, customer color preferences, and available production devices.

3. The method of claim 1 , wherein the input data is selected to represent tooth segments resulting from a segmentation process.

4. The method of claim 2 , wherein the input further includes at least one other factor that does not affect final tooth color.

5. The method of claim 2 , further comprising scanning the patient's oral cavity with an intraoral scanner to obtain at least a portion of the input data.

6. The method of claim 2 , wherein predefined layers are provided in the 3D image of the repair block or the 3D model of the repair block, resulting in shapes or colors of the various layers of the repair block.

7. The method of claim 6 , wherein the defined layers are indicated by straight or curved boundaries.

8. The method of claim 1 , wherein the user-specific tooth color comprises colors of multiple tooth layers of a restoration.

9. The method of claim 1 , wherein the at least one output restoration feature value comprises a suggestion for an optimal positioning of a restoration within a restoration block.

10. The method of claim 1 , wherein the at least one output repair feature value comprises an optimal color suggestion for a repair block.

11. The method of claim 1 , wherein the at least one output repair feature value comprises at least one internal structure suggestion for a repair block.

12. The method of claim 1 , wherein the at least one output restoration feature value includes a suggestion of at least one manufacturing process required to achieve a final user-specific tooth color.

13. 2. The method of claim 1, wherein the at least one output restoration feature value comprises at least one color suggestion for a 3D volume of material required for a 3D printer to achieve a final user-specific tooth color.

14. The method of claim 1 , further comprising providing feedback for the trained restorative parameter recommendation module indicating accuracy of suggestions to enhance the trained restorative parameter recommendation module.

15. 2. The method of claim 1, further comprising training an untrained version of the component machine learning model of the trained restorative parameter recommendation module using a training input dataset including training input images and / or shades and stored corresponding training output restorative feature values ​​obtained from a plurality of training restorative blocks and / or 3D printer materials selected to have characteristics that result in a plurality of final user-specific training tooth colors.

16. The training includes: Providing a plurality of training repair blocks and / or 3D printer materials; fabricating a plurality of corresponding restorations using said plurality of training restoration blocks and / or 3D printer material; placing said fabricated corresponding restorations in a corresponding physical model or in a corresponding oral cavity; scanning the physical model or the intraoral cavity to obtain corresponding images and / or shades for use as part of a training input dataset; providing the training input dataset as an input to a machine learning model; obtaining corresponding output inpainting feature values ​​from the machine learning model; and comparing the corresponding output inpainting feature values ​​with stored corresponding training output inpainting feature values; 16. The method of claim 15, comprising:

17. The method of claim 16 , wherein the characteristics include a desired internal structure of the repair block and / or a desired color of the 3D printer material.

18. The method of claim 16 , wherein the output inpainting features are probability values.

19. The method of claim 1 , wherein at least one final tooth color influencing factor in the input data is a 3D color scan of the patient's intraoral cavity.

20. receiving a three-dimensional (3D) scan of a patient's dental cavity; Identifying input data including at least one final tooth color influencing factor for a restorative parameter recommendation module to be trained by an input resource; - in response to said identification, extracting from the input data one or more features representative of completion requirements for the design and / or machining process of the restoration; using a trained restorative parameter recommendation module to suggest at least one output restorative feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration; 1. A computer system including a processor configured to execute the final user-specific tooth color represents an observed color of the restoration after being placed in the patient's mouth, the observed color being influenced by the at least one final tooth color influencing factor; The trained restorative parameter recommendation module operates as a machine learning engine. Computer system.

21. When executed by a computer system, receiving a three-dimensional (3D) scan of a patient's dental cavity; Identifying input data including at least one final tooth color influencing factor for a restorative parameter recommendation module to be trained by an input resource; - in response to said identification, extracting from the input data one or more features representative of completion requirements for the design and / or machining process of the restoration; using a trained restorative parameter recommendation module to suggest at least one output restorative feature value required to achieve a final user-specific tooth color for at least one tooth layer of the restoration; A non-transitory computer-readable storage medium storing a program for causing the computer system to execute a procedure including: the final user-specific tooth color represents an observed color of the restoration after being placed in the patient's mouth, the observed color being influenced by the at least one final tooth color influencing factor; The trained restorative parameter recommendation module operates as a machine learning engine. A non-transitory computer-readable storage medium.

Citation Information

Patent Citations

  • False tooth automatic matching production method and system based on cloud platform and big data

    CN112862072A

  • Data processing device, data generation device, scanner system, data processing method, program for data processing, data generation method, and program for data generation

    JP2020188988A

  • How the restoration is constructed

    JP2020508734A

  • How to design dental parts

    JP2021515684A

  • Multicolor dental blanks and related methods

    US20130065200A1