Method, system and computer-readable storage medium for determining articulation parameters

Abstract

To provide a method, system and computer-readable storage medium for determining articulation parameters.SOLUTION: A dentist may use a mobile device such as a smartphone to quickly and inexpensively visualize a 3D model of a patient's face and jaw, where a depth sensor is used to detect depth information. Articulator parameters may then be obtained to be used for treatment planning based on an analysis of the correct functioning of the patient's teeth.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This patent application claims the benefit of and priority to U.S. Patent Application No. 16 / 431,830, filed June 5, 2019, which is incorporated by reference herein for all purposes.

[0002] The present application relates generally to methods, systems, and computer-readable storage media for determining occlusal parameters, and more particularly to methods, systems, and computer-readable storage media for determining occlusal parameters of a patient using 3D face detection methods. [Background technology]

[0003] Dentists may use an articulator having upper and lower components to which casts of the upper and lower jaws may be attached to recreate the static relationship of a patient's upper and lower jaws. This may be used to study individual teeth and entire dental arches for diagnostic and / or treatment planning purposes, as well as to allow for the adjustment of fixed and removable prostheses and dental restorations.

[0004] A facebow may be used to position the articulator and measurements of the patient's temporomandibular joint movement may be taken. The facebow may then be placed at the ear to communicate any hinge axis position by referencing approximations using the patient's ear. The facebow may be aligned with the patient's face at the mouthpiece. A fixed frame with adjustable pivot joints to support the facebow may be used, along with an active drive positioning mechanism to adjust the pivot joints to provide the desired position and aspect of the facebow.

[0005] The facebow can transfer the relationship of the maxillary arch to the temporomandibular joint to the cast. It records the relationship of the maxilla to the ear canal at the hinge axis and assists in mounting the maxillary cast on the articulator.

[0006] The patient may also perform various chewing movements (lateral, anterior / posterior jaw movements, etc.) and the dentist may read certain values ​​on the facebow for use with, for example, a commercial articulator.

[0007] This is a time consuming and uncomfortable procedure for the patient.It would therefore be useful to quickly and automatically determine the occlusion parameters without the use of a physical facebow or physical articulators.

[0008] US Patent No. 9336336B2 discloses using face detection in a "smile" design application, where a dental restoration for a patient may be designed by providing one or more 2D images, at least one of the 2D images including at least one facial feature, providing a 3D virtual model of a portion of the patient's oral cavity, and positioning one of the 2D images relative to the 3D virtual model. Both the 3D virtual model and the 2D images are visualized in 3D space, and a restoration is modeled in the 3D virtual model to fit the facial feature of the at least one 2D image.

[0009] US Patent No. 9,642,686B1 discloses a method and system for recording features of a patient's occlusal arch using a portable computing device, where a virtual facebow is used to record features of the patient's occlusal arch using a facial alignment image with a set of crosshairs. The recorded features can then be used to recreate the alignment of the patient's occlusal arch and the maxillary cast on a lab stand, and the maxillary cast can be moved to an articulator to produce a customized dental prosthesis for the patient.

[0010] PCT Application No. WO201367606 discloses the use of digital elements to articulate a model onto a physical articulator, where a physical study model is placed into the articulator and the canine line direction and occlusal plane are determined on the study model.

[0011] U.S. Patent Application No. 8706672B2 discloses a computer-aided method for creating custom teeth using facial analysis, which includes obtaining data regarding the area to be treated and data regarding the patient's face, performing an analysis of the data to determine at least facial characteristics of the patient, and creating a modified tooth configuration using a set of stored rules utilizing the determined facial characteristics. Summary of the Invention [Problem to be solved by the invention]

[0012] These methods either do not use depth information or use X-ray images, which may not be ideal. [Means for solving the problem]

[0013] The above-mentioned and other existing limitations may be overcome by a method, system, and computer-readable storage medium for determining occlusion parameters.

[0014] In one aspect herein, the present invention may provide a method for determining occlusion parameters, the method including receiving an image of a patient's face, determining fixation and / or movement points of the patient's face based on the received image, and calculating the occlusion parameters based on the determined fixation and / or movement points.

[0015] In another aspect herein, the method may further include one or more of the following steps: (i) the occlusal parameters are selected from the group consisting of: (1) sides of Bonwill triangle, (2) intercondylar distance, (3) Balkwill angle, (4) sagittal condylar inclination, (5) Bennett angle, (6) initial Bennett movement, and (7) curve of Spee; (ii) further comprising reconstructing a 3D model of the patient's face from the received images; (iii) further comprising overlaying a scan of the patient's intraoral cavity onto the 3D model; (iv) the determining step comprises determining the occlusal parameters by feature analysis. (v) the feature analysis includes determining fixed points and / or movement points using deep learning; (vi) the fixed points include the position of the temporomandibular joint; (vii) the calculating step is achieved using geometric distances and / or angles measured using the fixed points and / or movement points; (viii) further includes inputting occlusal values ​​into a virtual articulator using the calculated occlusal parameters; (ix) further includes analyzing tooth function based on the occlusal parameters; (x) further includes creating a restoration or treatment plan based on the occlusal parameters.

[0016] In yet another aspect, the invention may provide a computer-implemented method for determining occlusion parameters, the method including: training a deep neural network using one or more computing devices and a plurality of training images to map one or more fixation points and / or movement points in at least a portion of each training image to one or more highest position probability values ​​of a position probability vector; receiving, by the one or more computing devices, an image of a patient's face including at least one jaw; identifying, using the trained neural network, the fixation points and / or movement points based on the one or more output position probability values ​​of the deep neural network; and calculating the occlusion parameters based on the determined fixation points and / or movement points.

[0017] In another aspect herein, the computer-implemented method may further provide, wherein the deep neural network is a convolutional neural network.

[0018] In yet another aspect herein, there may be provided a system for determining occlusion parameters, the system comprising at least one processor configured to perform the steps of receiving an image of a patient's face, determining fixation points and / or movement points of the patient's face based on the received image, and calculating occlusion parameters based on the determined fixation points and / or movement points.

[0019] The system may also provide a combination of one or more of the following: (i) the processor is further configured to select occlusal parameters from the group consisting of: (1) sides of Bonwill triangle, (2) intercondylar distance, (3) Balkwill angle, (4) sagittal condylar inclination, (5) Bennett angle, (6) initial Bennett movement, and (7) curve of Spee; (ii) the processor is further configured to reconstruct a 3D model of the patient's face from the received images; (iii) the processor is further configured to overlay a scan of the patient's intraoral cavity onto the 3D model; (iv) the processor is further configured to determine fixation and / or movement points by feature analysis; (v) the feature analysis includes determining the fixation and / or movement points using deep learning; (vi) the fixation points include positions of the temporomandibular joints; and (vii) the processor is further configured to generate a restoration or treatment plan based on the occlusal parameters.

[0020] In yet another aspect of the invention, a non-transitory computer readable storage medium may be provided for storing a program that, when executed by a computer system, causes the computer system to perform a procedure including receiving an image of a patient's face, determining fixation points and / or movement points of the patient's face based on the received image, and calculating occlusion parameters based on the determined fixation points and / or movement points.

[0021] Example embodiments will become more fully understood from the detailed description given herein below and the accompanying drawings, in which like elements are represented with like reference characters, and which are given by way of illustration only and therefore not by way of limitation of the example embodiments herein. [Brief description of the drawings]

[0022] [Figure 1] FIG. 2 is a perspective view of a patient's face illustrating the relationship to three spatial planes. [Diagram 2] FIG. 1 is a perspective view of a jaw illustrating Bonwill's triangle according to an exemplary embodiment of the present invention; [Figure 3a] FIG. 1 is a perspective view of a jaw illustrating a Bennett angle according to an exemplary embodiment of the present invention; [Figure 3b] 1 is a sketch illustrating the movement of a patient's mouth and lips according to an exemplary embodiment of the present invention; [Figure 4] FIG. 13 is a side view of a jaw illustrating the Curvature of Spee according to an exemplary embodiment of the present invention. [Diagram 5] FIG. 1 is a top view of a jaw illustrating intercondylar distance according to an exemplary embodiment of the present invention. [Figure 6] FIG. 2 is a side view of a jaw showing sagittal condylar inclination according to an embodiment of the present invention. [Figure 7] FIG. 13 is a perspective view of a jaw illustrating the Bulkwill angle according to an exemplary embodiment of the present invention; [Figure 8] 4 is a flow chart illustrating a method according to an exemplary embodiment of the present invention. [Figure 9] FIG. 1 is a side view of a system illustrating fixed and moving points according to an exemplary embodiment of the present invention. [Figure 10a] 1 is a side view of a jaw illustrating a first movement of a patient's oral cavity according to an exemplary embodiment of the present invention; [Figure 10b] 11 is a side view of the jaw illustrating a second movement of the patient's oral cavity according to an exemplary embodiment of the present invention. [Figure 11] FIG. 1 is a block diagram illustrating a computer system according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Different drawings may have at least some reference numbers that may be the same to identify the same components, although a detailed description of each such component may not be provided below with respect to each drawing.

[0024] According to example aspects described herein, a method, system, and computer readable storage medium for determining occlusion parameters may be provided.

[0025] Method for determining occlusal parameters - Patent application Determining the occlusal parameters of a particular patient, such as the intercondylar distance and Bennett angle, is essential for the manufacture of the restoration. The various occlusal parameters, which are described in more detail below, provide important information regarding the natural and proper process of jaw movement during the chewing process. The information obtained allows for the proper occlusion of the jaws and the indication of the cusp and groove positions of the teeth. This saves the dentist and patient time and eliminates the inconvenience of subsequent fitting of the restoration.

[0026] The objective of the present invention is to relate portions of a patient's oral cavity, such as the maxillary arch, mandibular arch, and / or temporomandibular joints, to the face in a spatial plane through the use of images taken with a depth sensor. This can be done for maxillofacial analysis of the maxillary arch as well as for establishing its functional relationship with the mandibular arch. The process of determining occlusal parameters can be digitized through the use of images taken with a depth sensor, thereby eliminating the need for complex structures such as a physical facebow.

[0027] FIG. 1 illustrates imaginary planes through a 3D reconstruction of a patient's face 10, preferably including the jaw, the planes being a sagittal plane S, a frontal plane F, and a horizontal plane H. The sagittal plane S is an anatomical plane that can divide the patient's head into two parts. Thus, the sagittal plane that divides the head into two equal parts is the mid-sagittal plane. The frontal plane F is perpendicular to the sagittal plane S and can divide the head into an anterior region and a posterior region. The horizontal plane H is also perpendicular to the sagittal plane and can divide the head into an upper region and a lower region.

[0028] The virtual articulator may, for example, enable the orthodontist to construct restorations and / or analyze tooth function based on the determined positions of virtual contact points between the upper and lower jaws of the patient's oral cavity. It may also, among other things, enable the orthodontist to detect tooth-tooth collisions when moving / shifting the teeth and thus to detect differences between the normal bite before the movement and the bite after the movement. To construct the virtual articulator, patient-specific input (patient-specific occlusion parameters) may be obtained from images of the patient's head, said images including geometric information that can be used to determine the relative distances between parts of the patient's dentition and from the temporomandibular joint.

[0029] The occlusal parameters may include, but are not limited to, (i) sides 11a (arms) of Bonwill triangle 11, (ii) intercondylar distance 15 (base of Bonwill triangle), (iii) Balkwill angle 17, (iv) sagittal condylar inclination β, (v) Bennett angle α, (vi) initial Bennett movement (immediate side shift left / right), and (vii) curvature of Spee 18. These parameters may be determined by tracking fixed points 20 and / or moving points 21 on the patient's face using a camera system 22 with a depth sensor 24 and determining the geometric distances and angles between these points and specific portions of the patient's dentition as described below.

[0030] 2 illustrates Bonwill's triangle 11, which is an equilateral triangle that connects the contact points of the incisal edges of the mandibular central incisors 14 (or the midline of the residual mandibular alveolar ridge) to the midpoint of each condyle 13 and from one condyle 13 to the other. Because it is an equilateral triangle, the lengths of the sides 11a are approximately equal (usually 4 inches). Knowing the locations or approximate locations of the right and left temporomandibular joints 23 based on the anatomical feature extraction methods described herein, the sides of Bonwill's triangle 11 can be calculated.

[0031] FIG. 3a illustrates the Bennett angle α, which is the angle formed between the sagittal plane S and the path of the advancing condyle 13 as the mandible moves laterally when viewed on the horizontal plane H. As the mandible moves from the initial position (M0) to the left (M1), the angle α is formed between the sagittal plane S and the path of the advancing condyle 13a, and the point p on the condyle 13a moves from position P1 to position P2, as shown in FIGS. 3a and 3b. The initial Bennett movement (also known as immediate side shift) refers to a movement in which both condyles may be displaced laterally at the beginning of the lateral movement of the mandible, i.e., the entire mandible may undergo a lateral movement parallel to the hinge axis before the non-functioning condyle moves forward, downward, and inward. This lateral shift may occur with difficulty as an independent movement and may be interpreted as evidence of joint damage, e.g., fatigue of the joint capsule or ligaments.

[0032] Figure 4 shows the curve of Spee, which is the curvature of the mandibular occlusal plane beginning at the premolars, continuing to the buccal cusps of the molars, and continuing to the last molar.

[0033] Figure 5 illustrates the intercondylar distance 15, which is the distance between the patient's two temporomandibular joints 23 (i.e., the distance between the mandibular condyles 13). Figure 6 is a diagram showing the sagittal condylar path inclination β, which is the angle formed by the condylar path path (path PC followed by the mandibular condyle 13 of the temporomandibular joint 23) and the horizontal reference plane H1, which may occur during protrusion (forward movement) of the patient's mandible.

[0034] FIG. 7 shows the Bulkwill angle 17, which is the angle between the Bonwill triangle 11 and the Bulkwill / occlusion triangle 16 defined by the horizontal plane of the mandibular dentition. Knowing these and other similar parameters of a virtual articulator without the use of a physical facebow or physical articulator may help reduce treatment time in the dental clinic.

[0035] Having described the exemplary occlusion parameters, reference is now made to FIGS. 8-10, which illustrate a process S1000 that may be employed in accordance with at least some of the exemplary embodiments herein. The process S1000 begins with step S100, which takes multiple images of a patient performing a predetermined chewing / chewing motion. The images may be taken using a camera system 22 having a depth sensor 24. For example, a smartphone with a depth sensor (such as a Lenovo Phab2 Pro with Google Tango technology) or an independent combination of a color camera and a depth camera may be used to capture the patient's face. As shown in step S200, the depth information may be used to reconstruct a 3D model of the face 10, including the jaw. Additionally, a series of 2D images may be captured while the patient performs a predetermined chewing motion, and a corresponding 3D model of the face 10 may be reconstructed for each motion. The reconstruction may be done in real time, or when needed, and may be used for measurements. Alternatively, knowing how the 2D images are related in terms of position, scale, distance, and angle, these images may be calculated without 3D reconstruction. Additionally, the movements can be recorded and / or tracked by identifying relevant points and comparing them frame by frame. The images / recordings can be stored in a database. In an exemplary embodiment, the images can be stored in a database and tagged with respect to specific occlusal positions. Movements can include pushing the lower jaw (mandibular arch) in front of the upper jaw (maxillary arch) and moving the lower jaw side to side with the upper jaw in contact with the lower jaw. Movements can be determined to correspond to the natural movements of a patient chewing as well as movements that can allow for the collection of geometric distances and angles required for occlusion.

[0036] In step S300, the fixed points 20 and / or moving points 21 can be determined by feature analysis. This may include using natural markers of dental and facial anatomy, preferably without using predefined artificial markers. However, in some embodiments, the fixed points 20 and / or moving points can be determined by attaching predefined artificial markers at predefined locations on the face and / or oral cavity and recognizing the predefined artificial markers. These fixed points 20 and / or moving points 21 can be determined to assist in the calculation of various distances and angles. The fixed points 20 can assist in determining the orientation of the face during the movement. The fixed points 20 and / or moving points 21 can preferably be points on the face or oral cavity that include little or no soft tissue, such as, for example, the top of the forehead 20a, the bottom of the nose 20b, and points 20c on either side of the head where the temporomandibular joint 23 is fixed and from which the movement occurs. However, some moving points 21 may include soft tissue (e.g., lips).

[0037] Other natural markers include ridges, fissures, tooth locations, and their relationship to each other artificial markers may include stickers, colored dots with a pen, glue on geometric shapes, and the like.

[0038] The moving point 21 may indicate a point where the displacement and / or maximum distance corresponding to a particular chewing movement can be measured. For example, when the patient moves the jaw to a required position (depending on which occlusal parameter is measured), an image of the jaw in a first position (e.g. closed jaw) can be recorded and another image of the jaw in a second position (e.g. moved jaw) can be obtained. For example, when the patient moves the mandible with movement M4 as shown in FIG. 9, the moving point 21 moves from position 1 to position 2. Thus, the distance between position 1 and position 2 can be obtained from the image. Furthermore, when the mandible moves away from the maxilla with movement M3 as shown in FIG. 10a and FIG. 10b, the displacement d1 between points P3 and P4 can be identified and measured. Points P3 and P4 are any points of interest and are not limited to molars only. For example, they may define the contact points of the incisal edge of the mandibular central incisor or the midline of the mandibular residual alveolar ridge. Said points can also be determined by feature analysis / extraction since they may be in similar positions in humans.

[0039] In embodiments that do not use predefined artificial markers, the fixation points 20 and / or the moving points 21 can be determined through feature analysis of the anatomical structures. The feature analysis can include defining features of the dentition that can be recognized and used in detecting larger structures. The features can include smaller points on the image, edges, objects, and / or curves or boundaries that define various regions of the image. In exemplary embodiments herein, the feature analysis can include machine / deep learning methods that can train a computer to recognize the fixation points 20 and the moving points 21 based on previously classified facial images. For example, starting with multiple images of a human face, a dentist can label the pixels of the images used for training by marking the areas of interest, e.g., the fixation points 20 and / or the moving points 21. The marking of the training images can be done digitally, for example, by setting dots on the images that correspond to the points of interest. This set of labeled or classified images can be used to build a network architecture / deep neural network, such as a convolutional neural network (CNN), and fed the labeled pictures so that the network can "learn" from them, thus generating network wiring that can classify new images independently. After training, the network is presented with previously unseen images and an output, such as a location probability vector containing location probability values, the highest location probability value defining the resulting fixed point 20 and / or moving point 21 location, and corresponding feedback is provided, such that the network can eventually operate independently to classify images, preferably without human assistance. Images used for training may also be derived from or based on ongoing patient treatment, past patient treatment, patient treatment results, or other treatment information.

[0040] After acquiring the fixed points 20 and / or moving points 21, the values ​​of the occlusion parameters can be obtained using the geometric distances and angles measured using the acquired fixed points 20 and / or moving points 21, as shown in step S400. Some occlusion parameters can be measured using only the fixed points 20 or a single image, while other occlusion parameters can be acquired using the fixed points 20 and moving points 21 or multiple images. For example, when determining the maximum displacement of the displacement d1 during the movement M3, there may be multiple images depicting multiple positions of the mandible. The image with the maximum difference for the points of interest can be acquired, and the Euclidean distance between these points can be calculated. Using the extracted or recognized points representing the position of the temporomandibular joint 23 together with the displacement d1 and / or other fixed points 20 and moving points 21, Euclidean geometry employing lines, angles, and triangles or spatial coordinates obtained, for example, from a 3D reconstruction or image, can be used to measure the values ​​of the occlusion parameters. Thus, the computer system 100 can be programmed to perform these steps iteratively using algorithms that combine deep learning feature extraction or more simple object recognition methods such as gradient matching or template matching with methods that involve associated distance and angle measurements.

[0041] Other systems and methods for dental measurements may include those taught in U.S. Pat. No. 8,126,726 B2 to Matov et al., entitled "System and method for facilitating automated dental measurements and diagnostics," which is incorporated by reference in its entirety as if fully set forth herein.

[0042] After obtaining the values ​​of the occlusal parameters, the values ​​can be input into a virtual articulator, as shown in step S500. The virtual articulator with the inputted values ​​can then be used to complete a treatment procedure, such as making a restoration or analyzing the proper functioning of the patient's teeth 12, in step S600. Furthermore, the obtained values ​​can be transmitted, for example wirelessly, to CAD / CAM software, where the values ​​can be integrated and used to calculate a functionally appropriate proposal for a restoration or other dental or orthodontic appliance.

[0043] Additionally, the 3D reconstruction of the face 10 can be overlaid with an intraoral data recording, such as a 3D measurement / scan of the patient's mouth taken with an intraoral scanner, for example to visualize the restoration or treatment plan and / or the results of the treatment plan. The overlay can be done by identifying common areas in both data, such as the teeth, and overlaying the data together along the common areas.

[0044] Preferably, the process S1000 can be completed in a short time (e.g., seconds to 2 minutes) compared to approximately 45 minutes using a physical facebow and / or a physical virtual articulator. Moreover, potentially greater accuracy is achieved, and the process may also preferably significantly reduce articulation costs and user errors, leading to higher adoption rates. In addition, the process may also be more comfortable for the patient, resulting in higher customer satisfaction with the dentist.

[0045] System for determining occlusal parameters - Patent application Having described system 1 of Figure 9, reference is now made to Figure 11, which illustrates a block diagram of a computer system 100 that may be employed in accordance with at least some of the example embodiments herein. Although various embodiments are described herein with respect to this example computer system 100, it will become apparent to one skilled in the art after reading this description how to implement the disclosure using other computer systems and / or architectures.

[0046] In one exemplary embodiment, the computer system may include a camera system 22 that may operate under one of several depth sensing principles, including, for example, (i) structured light principle, (ii) time-of-flight (ToF) principle, and / or (iii) stereoscopic principle. For cameras employing structured light, a light source may be used to project a known pattern onto the patient or the patient's head, a receiver may detect distortions in the reflected pattern, and a depth map may be calculated based on the geometry. For cameras employing time-of-flight (ToF) principle, a light source may send out a pulse, a sensor may detect the reflection of the pulse from the patient, and record the time of flight. Knowing the time of flight and the constant speed of light, the system may calculate how far away a point on the patient's head is. Alternatively, a light source may send out modulated light and detect a phase change in the light reflected from the patient. For cameras employing stereoscopic principle, multiple cameras may be placed at different positions to capture multiple images of the patient's head, and a depth map may be calculated based on the geometry. This depth information may be used to track the patient's head during treatment.

[0047] The computer system 100 may also include at least one computer processor 122, a user interface 126, and an input unit 130. In one exemplary embodiment, the input unit 130 may be used by the dentist together with a display unit 128, such as a monitor, to transmit commands or requests regarding capturing an image of the face, reconstructing a 3D image of the face 10, determining the fixed points 20 and moving points 21, and / or calculating occlusion values. They may be used, for example, for treatment planning, including the creation of restorations. In another exemplary embodiment herein, the input unit 130 is a finger or a stylus used on a touch screen interface (not shown). The input unit 130 may alternatively be a gesture / voice recognition device, a trackball, a mouse, or other input device such as a keyboard or a stylus. In one example, the display unit 128, the input unit 130, and the computer processor 122 may collectively form a user interface 126.

[0048] The computer processor 122 may include, for example, a central processing unit, multiple processing units, an application specific integrated circuit ("ASIC"), a field programmable gate array ("FPGA"), or the like. The processor 122 may be connected to a communication infrastructure 124 (e.g., a communication bus or network). In one embodiment herein, the processor 122 may receive a request to automatically capture an image of a face, automatically store the image in a database, automatically reconstruct a 3D model of the face 10, automatically determine the fixed points 20 and the moving points 21, automatically calculate and input occlusal parameters, and / or automatically perform a treatment plan, automatically create a restoration, or automatically perform an analysis of the function of the teeth 12. The processor 122 may then load the instructions, execute the loaded instructions using a database or artificial intelligence (AI), or the like, and retrieve the treatment for display.

[0049] One or more steps / procedures for determining occlusion parameters may be stored in a non-transitory storage device in the form of computer readable program instructions. To execute a procedure, the processor 122 loads the appropriate instructions stored in the storage device into memory and then executes the loaded instructions.

[0050] Additionally, computer system 100 may include main memory 132, which may be random access memory ("RAM"), and may also include secondary memory 134. Secondary memory 134 may include, for example, a hard disk drive 136 and / or a removable storage drive 138 (e.g., a floppy disk drive, a magnetic tape drive, an optical disk drive, a flash memory drive, etc.). Removable storage drive 138 may read from and / or write to removable storage unit 140 in a well-known manner. Removable storage unit 140 may be, for example, a floppy disk, a magnetic tape, an optical disk, a flash memory device, etc., that is written to and read by removable storage drive 138. Removable storage unit 140 may include a non-transitory computer-readable storage medium that stores computer-executable software instructions and / or data.

[0051] In yet alternative embodiments, secondary memory 134 may include other computer-readable media that store computer-executable programs or other instructions that are loaded into computer system 100. Such devices may include removable storage units 144 and interfaces 142 (e.g., program cartridges and cartridge interfaces); removable memory chips (e.g., erasable programmable read-only memory ("EPROM") or programmable read-only memory ("PROM")) and associated memory sockets; and other removable storage units 144 and interfaces 142 that allow software and data to be transferred from removable storage unit 144 to other portions of computer system 100.

[0052] Computer system 100 may also include a communications interface 146 that allows software and data to be transferred between computer system 100 and external devices. Such interfaces may include a modem, a network interface (e.g., an Ethernet card or a wireless interface), a communications port (e.g., a Universal Serial Bus ("USB") port or a FireWire® port), a Personal Computer Memory Card International Association ("PCMCIA") interface, Bluetooth®, and the like. The software and data transferred through communications interface 146 may be in the form of signals, which may be electronic, electromagnetic, optical, or another type of signal capable of being transmitted and / or received by communications interface 146. The signals may be provided to communications interface 146 over communications paths 148 (e.g., channels). Communications paths 148 carry signals and may be implemented using wire or cable, optical fibers, telephone lines, cellular links, radio frequency ("RF") links, and the like. Communications interface 146 may be used to transfer software, data or other information between computer system 100 and a remote server or cloud-based storage (not shown).

[0053] One or more computer programs or computer control logic may be stored in main memory 132 and / or secondary memory 134. Computer programs may also be received via communications interface 146. The computer programs may include computer-executable instructions that, when executed by computer processor 122, cause computer system 100 to perform the methods described below.

[0054] In another embodiment, the software is stored on a non-transitory computer readable storage medium and can be loaded into the main memory 132 and / or secondary memory 134 of the computer system 100 using the removable storage drive 138, the hard disk drive 136, and / or the communication interface 146. The control logic (software), when executed by the processor 122, causes the computer system 100, and more generally the system for determining occlusion parameters, to perform all or some of the methods described herein.

[0055] In another exemplary embodiment, the computer system 100 may be a mobile device, such as a smart phone, having applications that a user can use to suggest and visualize dental and orthodontic treatments.

[0056] The implementation of other hardware configurations for performing the functions described herein will be apparent to those skilled in the art in light of this description.

Claims

1. 1. A method for determining occlusion parameters, comprising: receiving an image of a patient's face; determining defined fixed and / or moving points of the image of the patient's face using a trained neural network for calculating occlusion parameters, the trained neural network being based on a set of training images labeled by marking areas of interest corresponding to one or more fixed and / or moving points and trained to map the one or more fixed and / or moving points in the training images to one or more highest position probability values ​​of a position probability vector, the one or more highest position probability values ​​defining positions of the fixed and / or moving points; calculating a set of geometric distances and angles between said determined fixed and / or moving points; - corresponding to said determining step, calculating said occlusion parameters based on said geometric distances and / or angles measured using said determined fixed points and / or moving points; inputting occlusion values ​​into a virtual articulator using said calculated occlusion parameters; A method comprising:

2. 2. The method of claim 1, wherein the occlusion parameters are selected from the group consisting of: (i) sides of Bonnwill's triangle, (ii) intercondylar distance, (iii) Balkwill's angle, (iv) sagittal condylar inclination, (v) Bennett's angle, (vi) initial Bennett's motion, and (vii) curvature of Spee.

3. The method of claim 1 , further comprising reconstructing a 3D model of the patient's face from the received images.

4. The method of claim 1 , further comprising overlaying a scan of the patient's intraoral cavity onto the 3D model.

5. The method of claim 1 , wherein the fixed point comprises a position of the temporomandibular joint.

6. The method of claim 1 , further comprising analyzing dental function based on the occlusal parameters.

7. The method of claim 1 , further comprising generating a restoration or treatment plan based on the occlusal parameters.

8. The method of claim 1 , wherein the trained network is a convolutional neural network.

9. 1. A system for determining occlusion parameters, comprising: receiving an image of a patient's face; determining defined fixed and / or moving points of the image of the patient's face using a trained neural network for calculating occlusion parameters, the trained neural network being based on a set of training images labeled by marking areas of interest corresponding to one or more fixed and / or moving points and trained to map the one or more fixed and / or moving points in the training images to one or more highest position probability values ​​of a position probability vector, the one or more highest position probability values ​​defining positions of the fixed and / or moving points; calculating a set of geometric distances and angles between said determined fixed and / or moving points; - corresponding to said determining step, calculating said occlusion parameters based on said geometric distances and / or angles measured using said determined fixed points and / or moving points; inputting occlusion values ​​into a virtual articulator using said calculated occlusion parameters; 16. A system comprising: at least one processor configured to:

10. 10. The system of claim 9, wherein the processor is further configured to select an occlusion parameter from the group consisting of: (i) sides of Bonnwill's triangle, (ii) intercondylar distance, (iii) Balkwill's angle, (iv) sagittal condylar inclination, (v) Bennett angle, (vi) initial Bennett motion, and (vii) curve of Spee.

11. The system of claim 9 , wherein the processor is further configured to reconstruct a 3D model of the patient's face from the received images.

12. 10. The system of claim 9, wherein the processor is further configured to overlay an intraoral scan of the patient onto the 3D model.

13. The system of claim 9 , wherein the fixed point comprises a position of the temporomandibular joint.

14. The system of claim 9 , wherein the processor is further configured to generate a restoration or treatment plan based on the occlusal parameters.

15. When executed by a computer system, the computer system: receiving an image of a patient's face; determining defined fixed and / or moving points of the image of the patient's face using a trained neural network for calculating occlusion parameters, the trained neural network being based on a set of training images labeled by marking areas of interest corresponding to one or more fixed and / or moving points and trained to map the one or more fixed and / or moving points in the training images to one or more highest position probability values ​​of a position probability vector, the one or more highest position probability values ​​defining positions of the fixed and / or moving points; calculating a set of geometric distances and angles between said determined fixed and / or moving points; corresponding to said determining, calculating said occlusion parameters based on said geometric distances and / or angles measured using said fixed points and / or moving points; inputting occlusion values ​​into a virtual articulator using said calculated occlusion parameters; A non-transitory computer-readable storage medium storing a program for causing the computer to carry out the steps including:

Images