Method and device for intelligently generating implant anchorage position

Abstract

The invention discloses a method and device for intelligently achieving implant anchorage position generation, and the method comprises the steps: carrying out the fusion of oral cavity CBCT data and oral scanning model data, obtaining a fusion three-dimensional model, and carrying out the registration of the oral cavity CBCT data and the oral scanning data based on a non-rigid I CP algorithm during the fusion; performing feature point extraction on the fused three-dimensional model to obtain a feature point heat map, performing risk region division on the fused three-dimensional model to obtain a risk region, determining a bone mineral density grading map based on the fused three-dimensional model, and dividing a tooth root three-dimensional safety boundary; determining at least one target feature point based on the feature point heat map, the risk area, the bone mineral density grading map and the tooth root three-dimensional safety boundary, and determining implant anchorage position information corresponding to the target feature point based on the target feature point; and screening out an optimal implant anchorage target position from the implant anchorage position information. The purpose of intelligently determining the position of the implant anchorage is achieved, and the defects in the related technology are overcome.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence information processing technology, and in particular to a method and device for intelligently generating implant support positions. Background Art

[0002] In the related art, vertical management has always been an issue that needs to be paid attention to in dental orthodontic clinics. For patients with skeletal Class II high angles, they often seek orthodontic treatment because they need to improve the protruding facial shape. The position of the mandible of such patients is downwardly and backwardly rotated relative to the maxilla, and their occlusal plane is steeper (FOP-FH>18°, POP-FH>16°). For such patients, not only do they need to extract the premolars and retract the teeth to solve the protruding facial shape, but during the correction process, in addition to retracting the teeth to solve the protruding facial shape, special attention should be paid to the vertical management of the maxillofacial area during treatment. If the vertical height is not effectively controlled, although the teeth can be aligned during correction, the ideal facial aesthetics may not be achieved, and the mandible may continue to rotate backward after correction, and the facial height may increase.

[0003] When facing such patients, traditional fixed orthodontics often requires the implantation of implant support (an efficient and stable auxiliary tool in orthodontics, which provides precise and powerful support for tooth movement by implanting micro titanium alloy nails into specific positions of the jaw) to assist in the lowering of the dentition, so as to obtain vertical space for adjustment of the upper and lower dentitions, thereby adjusting the angle of the occlusal plane, and then achieving the forward and upward counterclockwise rotation of the mandible, referred to as mandibular reverse rotation. However, in many cases, more patients who have high requirements for beauty and comfort during the correction process often choose invisible orthodontic treatment. The existing invisible orthodontic extraction scheme, due to the limitations of the braces force system, although it can achieve the retraction of protruding teeth and the alignment of teeth, it is difficult to form effective management of the height of the lower 1 / 3 of the face and the vertical direction of the mandibular angle only through the braces force system, and the soft tissue facial shape cannot be fully improved. At the same time, the long-term stability of the steep occlusal plane is also challenged.

[0004] One of the limitations that causes the above shortcomings is that the position of the implant anchorage cannot be accurately determined, resulting in the inability to accurately adjust the position of the implant anchorage pins and the distribution of the correction force, and unable to ensure that the force transmission and tooth movement achieve the best effect in different correction stages. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method and device for intelligently generating implant support positions, so as to solve the deficiencies existing in the related art.

[0006] In order to achieve the above-mentioned purpose, according to a first aspect of the present invention, a method for intelligently generating implant support positions is provided, comprising: fusing oral CBCT data and oral scan model data to obtain a fused three-dimensional model, wherein, during the fusion, the oral CBCT data and the oral scan data are aligned based on a non-rigid ICP algorithm; extracting feature points from the fused three-dimensional model to obtain a feature point heat map, dividing the fused three-dimensional model into risk areas to obtain risk areas, determining a bone density grading map based on the fused three-dimensional model, and dividing the three-dimensional safety boundary of the tooth root; determining at least one target feature point based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of the tooth root, and determining the implant support position information corresponding to the target feature point based on the target feature point; and screening out the optimal implant support target position from each implant support position information.

[0007] Optionally, before selecting the optimal implant anchorage target position from each implant anchorage position information, the method includes: for each target feature point, simulating the anchorage force required for different tooth movement directions through a pre-constructed biomechanical model, and calculating the depression impedance center of each posterior tooth area; based on the anchorage force, depression impedance center and the reverse rotation angle of the target occlusal plane, determining the mechanical vector corresponding to the required depression amount for each target feature point.

[0008] Optionally, screening out the optimal implant support target position from each implant support position information includes: calculating the support efficiency based on the required depression amount and mechanical vector of the target feature point; performing stability assessment based on the golden triangle area of the zygomatic alveolar ridge in the fused three-dimensional model to obtain a stability score; and maximizing the sum of the support efficiency and stability score based on a genetic algorithm or a gradient descent algorithm.

[0009] Optionally, extracting feature points from the fused three-dimensional model to obtain a feature point heat map includes: extracting feature points from the fused three-dimensional model to obtain a feature point heat map includes locating coarse feature points from the registered and downsampled CBCT image based on a 3D faster R-CNN network; intercepting a local 3D image from the original CBCT image based on the coarse feature points; and inputting the local 3D image into a multi-scale UNet for processing to obtain a feature point heat map.

[0010] Optionally, dividing the fused three-dimensional model into risk areas to obtain risk areas includes: inputting the aligned image, the target occlusal plane angle, and the amount of tooth depression in different areas into a neural network model, and outputting a heat map corresponding to the risk area, wherein the target occlusal plane is pre-generated.

[0011] Optionally, determining at least one target feature point as the location point of the implant support based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of the tooth root includes: eliminating feature points in the feature point heat map that belong to the risk area, whose corresponding bone density belongs to the specified bone density range, and which are outside the three-dimensional safety boundary of the tooth root.

[0012] According to a second aspect of the present invention, a device for intelligently generating implant support positions is provided, comprising: a data fusion unit, for fusing oral CBCT data and oral scan model data to obtain a fused three-dimensional model, wherein the oral CBCT data and the oral scan data are registered based on a non-rigid ICP algorithm during fusion; a preprocessing unit, for extracting feature points from the fused three-dimensional model to obtain a feature point heat map, for dividing the fused three-dimensional model into risk areas to obtain risk areas, for determining a bone density grading map based on the fused three-dimensional model, and for dividing a three-dimensional safety boundary of a tooth root; a position determination unit, for determining at least one target feature point based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of the tooth root, and for determining implant support position information corresponding to the target feature point based on the target feature point; and for screening out the optimal implant support target position from each piece of implant support position information.

[0013] Optionally, before selecting the optimal implant anchorage target position from each implant anchorage position information, the method includes: for each target feature point, simulating the anchorage force required for different tooth movement directions through a pre-constructed biomechanical model, and calculating the depression impedance center of each posterior tooth area; based on the anchorage force, depression impedance center and the reverse rotation angle of the target occlusal plane, determining the mechanical vector corresponding to the required depression amount for each target feature point.

[0014] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute any one of the methods described in the first aspect.

[0015] According to a fourth aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one implementation of the first aspect.

[0016] According to the technical solution of the present invention, oral CBCT data and oral scan model data are fused to obtain a fused three-dimensional model, wherein during the fusion, the oral CBCT data and oral scan data are aligned based on a non-rigid ICP algorithm; feature points are extracted from the fused three-dimensional model to obtain a feature point heat map, the fused three-dimensional model is divided into risk areas to obtain risk areas, a bone density grading map is determined based on the fused three-dimensional model, and a three-dimensional safety boundary of the tooth root is divided; at least one target feature point is determined based on the feature point heat map, risk areas, bone density grading map, and three-dimensional safety boundary of the tooth root, and the implant support position information corresponding to the target feature point is determined based on the target feature point; and the optimal implant support target position is screened from each implant support position information. This achieves the purpose of intelligently determining the implant support position and solves the defect in the related art that the implant support position cannot be determined in a more optimal manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of a method for intelligently generating implant anchorage positions according to an embodiment of the present invention;

[0019] Figure 2 2 is a schematic diagram of an application of a method for intelligently generating an implant anchorage position according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," and the like in the specification and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the embodiments of the present invention described herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0023] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] According to an embodiment of the present invention, a method for intelligently generating an implant support position is provided. Figure 1 As shown, it includes the following steps 101 to 103:

[0025] Step 101: Fusing the oral CBCT data and the oral scan model data, wherein during the fusion, the oral CBCT data and the oral scan data are registered based on a non-rigid ICP algorithm.

[0026] In this step, CBCT images contain information about hard tissues such as tooth roots and jawbone, but have low soft tissue resolution and are prone to ring artifacts. Oral scan data accurately captures crown morphology but cannot display root and jawbone structures. Therefore, a non-rigid ICP algorithm is used to register the oral CBCT and oral scan data. For example, this registration can be performed based on jaw surface feature points, such as occlusal plane landmarks, to produce a multimodal 3D fusion model.

[0027] Step 102: extracting feature points from the fused 3D model to obtain a feature point heat map, dividing the fused 3D model into risk areas to obtain risk areas, determining a bone density grading map based on the fused 3D model, and dividing the 3D safety boundary of the tooth root.

[0028] In this step, risk areas include high-risk areas such as the floor of the maxillary sinus, the three-dimensional contour of the tooth root, and the nasopalatine canal; high-density areas such as the zygomatic alveolar ridge cortex and the palatal suture bone plate can be identified in the bone density grading map; and the three-dimensional safety boundary of the tooth root can be divided using a dynamic buffering algorithm.

[0029] Step 103: Determine at least one target feature point based on the feature point heat map, risk area, bone density grading map, and three-dimensional safety boundary of the tooth root, and determine the implant support position information corresponding to the target feature point based on the target feature point; and select the optimal implant support target position from each implant support position information.

[0030] In this step, according to the required degree of adjustment of the maxillary occlusal plane and the amount of tooth depression in different areas, appropriate positions are selected to implant anchorage pins to provide stable support for tooth movement. It is designed from a biomechanical perspective to increase the expression rate of invisible orthodontics.

[0031] When determining the position information of each implant support, an implant channel is generated based on the direction of the trabeculae in the fusion model, and a gradient distance is maintained with the tooth root / maxillary sinus through a dynamic safety spacing algorithm; then multi-dimensional coordinate matching is performed, including: mapping the target depression amount to the alveolar bone area of the corresponding tooth position, and generating candidate coordinate points (spacing ≥ 2mm, avoiding risk areas). Specified anatomical parameters such as the three-dimensional coordinates of the zygomatic alveolar ridge, the gradient of the cortical bone thickness, the spatial topological relationship of the tooth root, and other 18 anatomical parameters are incorporated into the fitness function of the genetic algorithm. An anatomical fitness score is generated for the coordinate point (cortical bone coverage ≥ 30%) and an approach feasibility test is performed (avoiding buccal corridor / frenulum attachment). The implant position information is determined if the score meets the preset rules.

[0032] Before selecting the optimal implant anchorage target position from the information of various implant anchorage positions, the anchorage force required for different tooth movement directions can be simulated for each implant anchorage position point through a pre-constructed biomechanical model, and the depression impedance center of each posterior tooth area can be calculated; then, based on the anchorage force, depression impedance center and the counter-rotation angle of the target occlusal plane, the mechanical vector corresponding to the required depression amount for each implant anchorage position point can be determined.

[0033] When performing finite element modeling based on anatomical features, an anisotropic material model can be established for the zygomatic alveolar ridge area, and a viscoelastic material model can be established for the alveolar septum area. The mechanical performance of different positions is different, so a dynamic coordinate system can be established first. Using the palatal plane as the reference plane, a long axis coordinate system of the alveolar bone (mesiodistal, buccal-palatal, and vertical) can be established. Based on this coordinate system, finite element analysis can be used to simulate the support forces required for different tooth movement directions, calculate the intrusion impedance center for each posterior tooth area (premolar area, molar area), and then dynamically predict the impedance center. Based on the target occlusal plane counterrotation angle, the mechanical vector (direction, magnitude) corresponding to the required intrusion amount for each tooth position can be derived.

[0034] Furthermore, when determining the target occlusal plane, the target position of the patient's anterior teeth after correction was determined through cephalometric measurement and model analysis, and the target occlusal plane (mandibular reverse rotation angle) was designed based on the difference between the patient's functional occlusal plane (FOP) angle and the normal value, as well as the maxillary complex resistance center.

[0035] Specifically, the target position of the upper central incisor is determined by the TVL line (upper lip retraction: upper incisor retraction amount ≈ 2:3) and ∠U1-PP and ∠U1-L1; the difference between the value of ∠FOP-FH obtained by lateral skull radiograph and the normal value of 18° is the angle at which the occlusal plane needs to be rotated counterclockwise. For the determination of the target jaw plane (target maxillary occlusal plane), the final target maxillary occlusal plane MxOP (Maxillary occlusal plane) requires the following steps: a. With the incisal edge point of the target anterior tooth as the rotation center, rotate counterclockwise by the corresponding angle according to the patient's initial maxillary plane angle; b. Determine the target position of the upper and lower posterior teeth according to the following principles: With the target jaw plane as the reference, the long axis of the upper and lower posterior teeth needs to be perpendicular to this plane, and a good occlusal contact relationship between the upper and lower posterior teeth needs to be achieved. That is, the axial inclination of the upper and lower molars and premolars is adjusted according to the target occlusal plane, or the upper and lower molars are appropriately intruded or distalized. The target axial inclination is perpendicular to the target occlusal plane to ensure the maximization of the chewing force transmission efficiency and the stability of the occlusal function after orthodontic surgery.

[0036] As an optional implementation method of this embodiment, when selecting the optimal implant support target position from various implant support position information, the support efficiency can be first calculated based on the depression amount and mechanical vector required for each implant support position point; then, a stability assessment is performed based on the golden triangle area of the zygomatico-alveolar ridge in the fused three-dimensional model to obtain a stability score; finally, based on a genetic algorithm or a gradient descent algorithm, the sum of the support efficiency and the stability score is maximized.

[0037] In this optional implementation, during the mechanical-anatomical coupling evaluation, the support efficiency of each candidate target feature point is calculated. The candidate point must have an angle of ≤15° with the main direction of the trabeculae, and the formula is: support efficiency = cosine of the angle between the force direction and the target depression vector × bone density score. During the stability assessment, the golden triangle of the zygomatic alveolar ridge is prioritized, and high-risk points are filtered based on the cortical bone thickness (CBCT grayscale value) and the inter-root distance (>1.5mm). The implant stability index (ISI) is developed: ISI = 0.6 × (bone density / 800HU) + 0.3 × (cortical bone thickness / 1.2mm) + 0.1 × (inter-root distance / 2mm). During multi-objective optimization, a genetic algorithm or gradient descent method is used to maximize the sum of the support efficiency and stability score. Based on the above method, the optimal implant support position can be obtained.

[0038] The implant position can be further verified by overlaying a cortical "safety window" head image, outputting a 3D implant navigation map, and noting the anchor pin angle (usually perpendicular to the bone surface, with a deviation of <5°). Virtual implant verification is performed by overlaying virtual force direction arrows to verify the match with the target depression vector and conduct compliance testing. Verification criteria include anatomical recognition accuracy: Dice coefficient >0.93 (maxillary sinus); path planning time: <3 minutes (RTX 4090); and clinical compatibility: >88% agreement with the expert planning plan.

[0039] As an optional implementation method of this embodiment, extracting feature points from the fused three-dimensional model to obtain a feature point heat map includes: extracting feature points from the fused three-dimensional model to obtain a feature point heat map includes locating coarse feature points from the aligned and downsampled CBCT image based on a 3D faster R-CNN network; intercepting a local 3D image from the original CBCT based on the coarse feature points; and inputting the local 3D image into a multi-scale UNet for processing to obtain a feature point heat map.

[0040] In this optional implementation, refer to Figure 2 , we can use the 3D Faster R-CNN network to roughly locate feature points (coarse feature points) in the downsampled CBCT image. Based on the approximate feature point locations, we extract a local 3D image from the original high-resolution CBCT image. This local 3D image is then fed into a multi-scale UNet (MS-UNet) to generate a feature point heatmap.

[0041] As an optional implementation method of this embodiment, the patient's fused 3D model, target occlusal plane angle, and tooth depression amount (quantified by region) are input. A heat map of the risk area is automatically generated through MS-UNet (confidence level > 95%): a peak detection algorithm is used to parse the final coordinates from the heat map to achieve sub-pixel accuracy. When training the model, the fused model sample, target occlusal plane angle, and tooth depression amount (quantified by region) are used as the input of the model, and the anatomic risk areas (such as the maxillary sinus and tooth root position) are marked as output to train the model.

[0042] Determining at least one target feature point as the location point of the implant support based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of the tooth root includes: eliminating the feature points in the feature point heat map that belong to the risk area, the corresponding bone density that belongs to the specified bone density range, and the feature points outside the three-dimensional safety boundary of the tooth root.

[0043] This embodiment can accurately determine the position information of the implant support, overcoming the defect in the related art that the position of the implant support cannot be accurately determined.

[0044] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0045] According to an embodiment of the present invention, a device for intelligently generating an implant support position is also provided, comprising a data fusion unit for fusing oral CBCT data and oral scan model data to obtain a fused three-dimensional model, wherein the oral CBCT data and the oral scan data are aligned based on a non-rigid ICP algorithm during fusion; a preprocessing unit for extracting feature points from the fused three-dimensional model to obtain a feature point heat map, dividing the fused three-dimensional model into risk areas to obtain risk areas, determining a bone density grading map based on the fused three-dimensional model, and dividing a three-dimensional safety boundary of a tooth root; a position determination unit for determining at least one target feature point based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of a tooth root, and determining the implant support position information corresponding to the target feature point based on the target feature point; and screening out the optimal implant support target position from each implant support position information.

[0046] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the method described in any of the above embodiments when executing.

[0047] According to an embodiment of the present invention, the present invention further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the method described in any of the above embodiments when executed.

[0048] According to an embodiment of the present invention, the present invention further provides a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.

[0049] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0050] like Figure 3As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 can also be stored in the RAM 303. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0051] Multiple components in the electronic device 300 are connected to the I / O interface 305, including an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0052] The computing unit 301 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above can be performed.

[0053] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0054] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0055] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

Claims

1. A method for intelligently generating implant anchorage positions, characterized in that: include: Fusing the oral CBCT data and the oral scan model data to obtain a fused three-dimensional model, wherein the oral CBCT data and the oral scan data are registered based on the non-rigid ICP algorithm during the fusion process; Extract feature points from the fused 3D model to obtain a feature point heat map, divide the fused 3D model into risk areas to obtain risk areas, determine a bone density grading map based on the fused 3D model, and divide the 3D safety boundary of the tooth root; At least one target feature point is determined based on the feature point heat map, risk area, bone density grading map, and three-dimensional safety boundary of the tooth root, and the implant support position information corresponding to the target feature point is determined based on the target feature point; the optimal implant support target position is screened out from each implant support position information.

2. The method for intelligently generating implant anchorage positions according to claim 1, characterized in that: Before selecting the optimal implant support target location from various implant support location information, the method includes: For each target feature point, the pre-built biomechanical model is used to simulate the anchorage force required for different tooth movement directions, and the center of intrusion resistance in each posterior tooth area is calculated; Based on the anchorage force, the depression impedance center, and the counter-rotation angle of the target occlusal plane, a mechanical vector corresponding to the required depression amount of each target feature point is determined.

3. The method for intelligently generating implant anchorage positions according to claim 2, characterized in that: The optimal implant support target position is selected from various implant support position information, including: Calculate support efficiency based on the required depression amount and mechanical vector of the target feature point; The stability of the zygomatic alveolar ridge golden triangle in the fused three-dimensional model was evaluated to obtain a stability score. Based on genetic algorithm or gradient descent algorithm, the sum of anchorage efficiency and stability score is maximized.

4. The method for intelligently generating implant anchorage positions according to claim 1, characterized in that: Feature point heat maps obtained by extracting feature points from the fused 3D model include: Extracting feature points from the fused 3D model to obtain a feature point heat map includes locating coarse feature points from the registered and downsampled CBCT image based on the 3D Faster R-CNN network; extracting a local 3D image from the original CBCT image based on the coarse feature points; The local 3D image is input into the multi-scale UNet to obtain a feature point heat map.

5. The method for intelligently generating implant anchorage positions according to claim 1, characterized in that: The risk areas obtained by dividing the fused 3D model include: The registered image, target occlusal plane angle, and tooth intrusion in different areas are input into the neural network model, and a heat map corresponding to the risk area is output, wherein the target occlusal plane is pre-generated.

6. The method for intelligently generating implant anchorage positions according to claim 5, characterized in that: Determining at least one target feature point as a location point for implant anchorage based on the feature point heat map, the risk area, the bone density grading map, and the three-dimensional safety boundary of the tooth root includes: The feature points in the feature point heat map that belong to the risk area, whose corresponding bone density belongs to the specified bone density range, and which are outside the three-dimensional safety boundary of the tooth root are eliminated.

7. A device for intelligently generating implant support positions, characterized in that: include: A data fusion unit is used to fuse the oral CBCT data and the oral scan model data to obtain a fused three-dimensional model. During the fusion process, the oral CBCT data and the oral scan data are registered based on a non-rigid ICP algorithm. a preprocessing unit, configured to extract feature points from the fused 3D model to obtain a feature point heat map, divide the fused 3D model into risk areas to obtain risk areas, determine a bone density grading map based on the fused 3D model, and divide the tooth root into three-dimensional safety boundaries; A position determination unit is used to determine at least one target feature point based on the feature point heat map, risk area, bone density grading map, and three-dimensional safety boundary of the tooth root, and to determine the implant support position information corresponding to the target feature point based on the target feature point; and to screen out the optimal implant support target position from each implant support position information.

8. The device for intelligently generating implant anchorage positions according to claim 7, characterized in that: Before selecting the optimal implant support target position from various implant support position information, For each target feature point, the pre-built biomechanical model is used to simulate the anchorage force required for different tooth movement directions, and the center of intrusion resistance in each posterior tooth area is calculated; Based on the anchorage force, the depression impedance center, and the counter-rotation angle of the target occlusal plane, a mechanical vector corresponding to the required depression amount of each target feature point is determined.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 6.

10. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

Images