KR102243185B1 - Method for planning implant surgery using artificial intelligence and medical image processing device for the same - Google Patents

Abstract

Disclosed are a method of establishing an implant surgery plan using artificial intelligence and a medical image processing apparatus therefor. An implant surgery plan establishment method using artificial intelligence according to an embodiment includes the steps of acquiring a learning result learned based on artificial intelligence for image data of patients who have previously established a fixture placement plan, and the acquired learning result. And determining and providing placement information including the position and angle of the fixture to be actually placed according to the oral environment.

Description

{Method for planning implant surgery using artificial intelligence and medical image processing device for the same}

The present invention relates to a medical image processing technology including a guide design technology for dental implant surgery.

In the implant surgery process using software, after establishing an implant placement plan in consideration of the implant structure (crown, abutment, fixture, etc.) and the patient's anatomical structure on the software, implant surgery is performed.

In the process of establishing an implant placement plan using the guide design software for dental implant surgery, the position of the crown for each tooth number to be operated is first determined, and the initial placement position of the fixture is determined with the same axis as the reference axis of the crown. do. After that, it is based on a method of determining the final position through user adjustment.

The currently commercialized general fixture positioning method is configured to determine and provide the initial position of the fixture only on the same axis as the crown reference axis, and to determine the final position of the fixture by manually correcting other operations.

Korean Patent Publication 10-2018-0106007 (published on October 1, 2018)

According to an embodiment, a method of establishing an implant surgery plan using artificial intelligence and a medical image processing apparatus therefor are proposed in order to minimize the user's guide design work time.

An implant surgery plan establishment method using artificial intelligence according to an embodiment includes the steps of acquiring a learning result learned based on artificial intelligence for image data of patients who have previously established a fixture placement plan, and the acquired learning result. And determining and providing placement information including the position and angle of the fixture to be actually placed according to the oral environment.

In the step of determining and providing placement information, based on the position of the fixture placed from the acquired learning result, the relationship information between the alveolar bone, the gingival margin, the adjacent teeth, the maxillary sinus, the neural tube, and the bone density is identified. It may include the step of determining and providing information on the placement of the fixture by reflecting the step and relationship information with the identified surrounding structures.

The step of determining and providing the placement information includes determining the initial position of the fixture so that it is located at the center of the crown with the same central axis based on the central axis of the crown, and the initial position of the fixture by reflecting the relationship information with the identified surrounding structures. It may include the step of determining and providing the final position of the fixture as the position is corrected.

The step of determining and providing the placement information includes distance information from the alveolar bone learned from the center point in the top direction of the fixture based on the position of the fixture placed by tooth number in the previous data, and the mesial plane of the fixture and the alveolar bone ( Mesial), distal, lingual, and buccal (Buccal) learning results including distance information to determine the relationship between the fixture and the alveolar bone, and the relationship between the identified fixture and alveolar bone. It may include the step of determining and providing a distance between the fixture and the alveolar bone based on the fixture.

In the step of determining and providing the placement information, the relationship between the fixture and the gum margin is obtained by acquiring the learning result including distance information from the gum margin in the top direction of the fixture based on the position of the fixture placed by tooth number from the previous data. The determining may include determining and providing a distance between the fixture and the gum margin based on the relationship between the identified fixture and the gum margin.

The step of determining and providing placement information includes the steps of acquiring the learning result including the angle between the fixture and the adjacent teeth based on the position of the fixture placed by tooth number from the previous data, and grasping the relationship between the fixture and the adjacent teeth. It may include the step of determining and providing an insertion angle of the fixture so as to be parallel to the adjacent value in the mesial direction based on the relationship between the fixture and the adjacent value.

In the step of determining and providing the placement information, the lowermost point and the maxillary sinus and lower teeth in the direction of the lower apex (Apex) of the fixture by checking whether there is a collision with the maxillary sinus or neural tube based on the position of the fixture placed by tooth number from the previous data. The step of acquiring the learning result including the distance to the jaw neural tube and the length information of the fixture by tooth number to determine the relationship between the maxillary sinus or the neural tube of the fixture, and the maxillary sinus invasion area of the fixture in case of a maxillary sinus collision is allowed to invade through the learning data. It may include the step of adjusting the length of the fixture when invasion exceeding the allowable invasion range occurs by defining a criterion or allowing a user to set an intrusion allowable range.

The step of determining and providing the placement information includes acquiring the learning result including the learned ossein information of the area in contact with the placed fixture or where the fixture is located, and grasping the bone quality information around the fixture, and the identified fixture. It may include the step of determining and enhancing the position of the fixture using the surrounding bone quality information.

The method of establishing an implant surgery plan using artificial intelligence may further include learning the previous data using artificial intelligence in order to determine the placement information of the fixture to be actually placed.

The learning step includes learning the patient's anatomical structure including at least one of alveolar bone, adjacent teeth information, maxillary sinus and neural tube information based on the fixtures placed for the CT data of a patient who has previously established a fixture placement plan, and , It may include learning the position and angle of the fixture and the gum margin line according to the crown for each tooth number for which the crown position is determined based on the oral model data of the patient who has previously established the fixture placement plan.

The method of establishing an implant surgery plan using artificial intelligence may further include testing a learning result, and reflecting the learning result in a fixture placement plan when the testing result is greater than or equal to a preset criterion.

A medical image processing apparatus according to another embodiment includes a data acquisition unit that acquires image data, and an oral environment using learning results learned based on artificial intelligence for image data of patients who have previously established a fixture placement plan. It includes a fixture determination unit that determines placement information including a position and angle of a fixture to be actually placed appropriately, and an output unit that displays placement information from the image data together on the screen.

The fixture determination unit grasps relational information with surrounding structures including at least one of alveolar bone, gingival margin, adjacent teeth, maxillary sinuses, neural tube, and bone density based on the position of the fixture placed from the acquired learning result, and It is possible to determine the placement information of the fixture by reflecting the relationship information of.

The fixture determination unit includes distance information from the alveolar bone learned from the center point in the top direction of the fixture based on the position of the fixture placed by tooth number in the previous data, the mesial surface of the fixture and the alveolar bone (Mesial), and the distal surface ( The relationship between the fixture and the alveolar bone is obtained by acquiring the learning result including distance information in the distal, lingual, and buccal directions, and the distance between the fixture and the alveolar bone based on the relationship between the identified fixture and the alveolar bone. Can be determined.

The fixture determiner acquires a learning result including distance information from the gum margin in the top direction of the fixture based on the position of the fixture placed by tooth number from the previous data, and grasps the relationship between the fixture and the gum margin, and identifies the fixture. The distance between the fixture and the gum margin can be determined based on the relationship between the and the gum margin.

The fixture determiner acquires the learning result including the angle between the fixture and the adjacent value based on the position of the fixture inserted by tooth number from the previous data to determine the relationship between the fixture and the adjacent value, and determines the relationship between the identified fixture and the adjacent value. Based on the basis, it is possible to determine the placement angle of the fixture so as to be parallel to the adjacent teeth in the mesial direction.

The fixture determination unit checks whether a collision with the maxillary sinus or neural tube is made based on the position of the fixture placed by tooth number in the previous data, and determines the distance between the lowest point and the maxillary sinus and inferior alveolar neural tube in the direction of the lower apex of the fixture. , By acquiring the learning result including the length information of the fixture by tooth number, the relationship between the maxillary sinus or the neural tube of the fixture is grasped.In the case of a maxillary sinus impact, the maxillary sinus invasion area of the fixture defines the invasion acceptance criteria through the learning data, or the invasion tolerance range. By allowing the user to set, it is possible to adjust the length of the fixture when invasion exceeds the permissible range of invasion.

The fixture determination unit obtains the learning result including the learned ossein information of the area where the fixture is in contact with or where the fixture is placed to determine the bone quality information around the fixture, and uses the bone quality information around the identified fixture to obtain the fixture. You can determine the location of.

The medical image processing apparatus uses artificial intelligence to learn image data of patients who have previously established a fixture placement plan in order to determine placement information of a fixture to be actually placed, and a learning unit that provides the learning result to the fixture determination unit. It may contain more. The learning unit learns the patient's anatomical structure including at least one of alveolar bone, adjacent teeth information, maxillary sinus and neural tube information based on the installed fixture based on the CT data of the patient who has previously established the fixture placement plan, and plans the previous fixture placement. It is possible to learn the placement position and angle of the fixture, and the gum margin line according to the crown for each tooth number for which the crown position is determined for the oral model data of the patient who has established.

The medical image processing apparatus may further include a testing unit that tests the learning result of the learning unit, and provides the learning result to the fixture determination unit when the testing result is greater than or equal to a preset reference.

According to a method for establishing an implant surgery plan using artificial intelligence and a medical image processing apparatus therefor according to an embodiment, it is possible to increase user convenience by minimizing manual manipulation by a user when determining a fixture placement position from image data.

1 is a diagram showing the configuration of a medical image processing apparatus according to an embodiment of the present invention;
2 is a diagram showing a detailed configuration of the control unit of FIG. 1 according to an embodiment of the present invention;
3 is a view showing image data used for fixture placement according to an embodiment of the present invention;
4 is a diagram illustrating an image screen for determining an actual fixture position using a result of learning a position between a crown and a fixture according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating an image screen for determining an actual fixture position using a result of learning a distance between a fixture and an alveolar bone according to an embodiment of the present invention;
6 is a diagram illustrating an image screen for determining a position of a fixture to be actually placed using a result of learning a distance between a fixture and a gum margin according to an embodiment of the present invention;
7 is a diagram illustrating an image screen for determining an angle of a fixture to be actually placed using data obtained by learning the angles of a fixture and an adjacent tooth according to an embodiment of the present invention;
8 is a diagram illustrating an image screen for determining a position of a fixture using a result of learning a relationship between a fixture and a maxillary sinus and an inferior alveolar neural tube according to an embodiment of the present invention;
9 is a view showing an image screen for determining fixture placement information using a result of learning bone density of an alveolar bone in contact with a fixture according to an embodiment of the present invention;
10 is a diagram illustrating a method of establishing an implant surgery plan using artificial intelligence according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments make the disclosure of the present invention complete, and the general knowledge in the technical field to which the present invention pertains. It is provided to completely inform the scope of the invention to the possessor, and the invention is only defined by the scope of the claims. The same reference numerals refer to the same elements throughout the specification.

In describing embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted, and terms to be described later are These terms are defined in consideration of the functions of the user and may vary according to the intention or custom of users or operators. Therefore, the definition should be made based on the contents throughout this specification.

Combinations of each block of the attached block diagram and each step of the flowchart may be executed by computer program instructions (execution engine), and these computer program instructions are used on a processor of a general-purpose computer, special purpose computer, or other programmable data processing device. As it may be mounted, its instructions executed by a processor of a computer or other programmable data processing device generate means for performing the functions described in each block of the block diagram or each step of the flowchart.

These computer program instructions may also be stored in a computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing device to implement a function in a particular manner, so that the computer-usable or computer-readable memory It is also possible to produce an article of manufacture in which the instructions stored in the block diagram contain instruction means for performing the functions described in each block of the block diagram or each step of the flowchart.

In addition, since computer program instructions can be mounted on a computer or other programmable data processing device, a series of operation steps are performed on a computer or other programmable data processing device to create a computer-executable process. It is also possible that the instructions for performing the data processing apparatus provide steps for executing the functions described in each block in the block diagram and in each step in the flowchart.

In addition, each block or each step may represent a module, segment, or part of code containing one or more executable instructions for executing specified logical functions, and in some alternative embodiments mentioned in the blocks or steps. It should be noted that it is also possible for functions to occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially simultaneously, and the blocks or steps may be performed in the reverse order of a corresponding function as necessary.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the embodiments of the present invention exemplified below may be modified in various other forms, and the scope of the present invention is not limited to the embodiments described below. Embodiments of the present invention are provided to more completely describe the present invention to those of ordinary skill in the art to which the present invention pertains.

1 is a diagram showing the configuration of a medical image processing apparatus according to an embodiment of the present invention.

The medical image processing apparatus 1 is an electronic device capable of executing a medical image processing program such as a guide design program for dental implant surgery. Electronic devices include computers, notebook computers, laptop computers, tablet PCs, smartphones, mobile phones, personal media players (PMPs), personal digital assistants (PDAs), and the like. Medical image processing programs include a scan program and a CAD program in addition to a guide design program. In addition, it can be applied to programs for general medical image processing other than for dental implant surgery.

The image processing process using a medical image processing program including a guide design program includes registration of surgical patients, acquisition of CT data and oral model data of the registered patient, registration of CT data and oral model data, and generation of arch lines and arches from the matched image data. This is a process that includes creating a panoramic image using lines, determining the position and size of the crown model from the patient's oral model data, determining the position of the implant structure including fixtures from the patient's CT data, designing the guide shape, and outputting the final guide. It is composed.

The present invention is configured to automatically provide the user with information on the placement of a fixture to be placed in the tooth region during the above process. The placement information includes the position, angle, depth, length, diameter, and features of the fixture. In particular, the present invention provides a user with information about the placement of a fixture using artificial intelligence (AI). Artificial intelligence is a field of computer engineering and information technology that studies how computers can do thinking, learning, and self-development that can be done with human intelligence, so that computers can imitate the intelligent behavior of humans. Say what to do. This artificial intelligence technique is applied to the guide design software so that the computer learns the installation information of the fixtures planned for surgery in advance in the software, and when this is applied for each operation plan case, the operation of the user to adjust the placement position and angle of the fixture is minimized. can do.

Hereinafter, a configuration of a medical image processing apparatus having the above-described characteristics will be described with reference to the configuration of FIG. 1.

Referring to FIG. 1, a medical image processing apparatus 1 according to an embodiment includes a data acquisition unit 10, a storage unit 12, a control unit 14, an input unit 16, and an output unit 18. .

The data acquisition unit 10 acquires image data from a patient. Image data necessary for fixture placement include CT data and oral model data. The data acquisition unit 10 may execute CT data and oral model data in a program or load data stored in a web page and a server.

The oral model data is data with information on actual teeth including damaged teeth. The oral model data may be obtained by scanning a plaster model created after a patient's oral cavity with a 3D scanner. As another example, it may be obtained by scanning the inside of the patient's oral cavity using a 3D intra-oral scanner. The obtained oral model data may be stored in the storage unit 12.

CT data can be obtained by generating a patient's head tomography images using computed tomography (CT), segmenting the boundary of the tooth from each tomography image, and then combining them into one. These oral model data and CT data are images obtained by photographing the maxillary teeth under the maxillary teeth with the patient's mouth open, the images obtained by photographing the mandibular teeth above the mandibular teeth with the mouth open, and the local area with the mouth closed. Includes images obtained, oral radiographs, etc. The acquired CT data may be stored in the storage unit 12.

The storage unit 12 stores various data such as information necessary for performing the operation of the dental implant surgery planning apparatus 3 and information generated according to the operation. In the storage unit 12 according to an embodiment, oral model data and CT data of an individual patient are stored, and user request for oral model data and CT data of a specific patient among all oral model data and CT data during dental treatment simulation. It can be provided to the control unit 14 according to. At this time, the storage unit 12 stores images of the upper and lower teeth of an individual patient, and images of the upper and lower teeth that match the oral model data and CT data of a specific patient are stored at the user's request. Accordingly, it can be provided to the control unit 14.

The control unit 14 controls each component while establishing an implant placement plan through control by a computer program. The controller 14 manages screen information displayed on the screen through the output unit 18, and performs a simulation of placing a virtual fixture object in the dental image. A dental image in which a virtual fixture object is placed refers to a multidimensional image, such as 2D or 3D, that shows the patient's tooth arrangement created to establish an implant surgery plan. Various types of images, such as X-ray, CT, MRI, panoramic images, oral scan images, images generated through reconstruction, and images that match multiple images, can be used for implant surgery planning.

The controller 14 according to an embodiment determines and provides placement information including the placement position and angle of a fixture object for the image data acquired through the data acquisition unit 10. At this time, by reflecting the learning result learned using artificial intelligence for the image data of the patient who has previously established the fixture placement plan, the placement information of the fixture to be actually placed is determined and provided according to the oral environment. The detailed configuration of the control unit 14 will be described later with reference to FIG. 2.

The input unit 16 receives a user manipulation signal. For example, when implantation information is determined by the control unit 14 and the image data including the fixture displayed on the screen through the output unit 18, a user operation for fine adjustment is input and the fixture position and angle are input. Can be adjusted.

The output unit 18 displays a screen. At this time, the output unit 18 displays image data (CT data, oral model data) on the screen. The CT image may be expressed as an axial view, a sagittal view, or a coronal view. In addition, the output unit 18 displays the fixture placement result on an image in the screen.

2 is a diagram showing a detailed configuration of the control unit of FIG. 1 according to an embodiment of the present invention.

1 and 2, the control unit 14 includes a fixture determination unit 144, and may further include a learning unit 140 and a testing unit 142.

The fixture determination unit 144 determines the placement information of the fixture to be actually placed according to the oral environment by using the learning result learned based on artificial intelligence for the image data of patients who have previously established a fixture placement plan. The placement information includes the position, angle, depth, length, diameter, and features of the fixture.

The fixture determination unit 144 according to an embodiment includes relationship information with surrounding structures including at least one of alveolar bone, gingival margin, adjacent teeth, maxillary sinus, neural tube, and bone density based on the position of the installed fixture from the acquired learning result. To grasp. And, by reflecting the relationship information with the identified surrounding structures, it determines the placement information of the fixture.

Determining the position of the actual fixture using the result of learning the distance between the fixture and the alveolar bone.For example, the fixture determination unit 144 is the center point in the top direction of the fixture based on the position of the fixture placed for each tooth number from the previous data. The learning results including distance information from the alveolar bone and distance information of the fixture and alveolar bone in the mesial, distal, lingual, and buccal directions are acquired, and Identify the relationship between the alveolar bones. Then, the distance between the fixture and the alveolar bone is determined based on the relationship between the identified fixture and the alveolar bone. An embodiment of this will be described later with reference to FIG. 5.

Determine the actual position of the fixture using the result of learning about the distance between the fixture and the gum margin.For example, the fixture determination unit 144 determines the gum margin in the top direction of the fixture based on the position of the fixture placed for each tooth number from the previous data. The relationship between the fixture and the gingival margin is grasped by acquiring the learning result including the distance information of the family. Then, the distance between the fixture and the gum margin is determined based on the relationship between the identified fixture and the gum margin. An embodiment of this will be described later with reference to FIG. 6.

Determine the angle of the actual fixture using the learning result of the angle between the fixture and the adjacent teeth.For example, the fixture determination unit 144 includes the angle between the fixture and the adjacent teeth based on the position of the fixture placed by tooth number from the previous data. Acquire the learning result and grasp the relationship between the fixture and the adjacent value. And, based on the relationship between the identified fixture and the adjacent value, the angle of the fixture is determined to be parallel to the adjacent value in the mesial direction. An embodiment of this will be described later with reference to FIG. 7.

Determine the position of the actual fixture using the result of learning about the maxillary sinus or neural tube.For example, the fixture determination unit 144 checks whether there is a collision with the maxillary sinus or neural tube based on the position of the fixture placed by tooth number from previous data. The relationship between the fixture's maxillary sinus or neural tube is acquired by acquiring the learning result including the distance between the lowermost point in the direction of the lower apex of the fixture and the maxillary sinus and inferior alveolar neural tube, and the length of the fixture by tooth number. The fixture determination unit 144 defines the invasion allowance criteria through learning data for the maxillary sinus invasion area of the fixture in case of a maxillary sinus collision, or allows the user to set the invasion allowable range, so that the length of the fixture when invasion exceeds the allowable invasion range Can be adjusted. An embodiment of this will be described later with reference to FIG. 8.

Determine the location of the actual fixture using the result of learning about the bone density of the alveolar bone in contact with the fixture.For example, the fixture determination unit 144 learns including learned ossein information of the area where the fixture is in contact with or where the fixture is placed. Acquire the result and grasp bone quality information around the fixture. Then, the location of the fixture is determined using bone quality information around the identified fixture. An embodiment of this will be described later with reference to FIG. 9.

The learning unit 140 learns by using artificial intelligence the image data of a patient who has previously established a fixture placement plan in order to determine the placement information of the fixture to be actually placed, and provides the learning result to the fixture determination unit 144 do. The learning unit 140 can learn the patient's anatomical structure, including the alveolar bone, adjacent teeth information, maxillary sinus, and mandibular neural tube information, based on the fixtures placed for the CT data of a patient who has previously established a fixture placement plan. I can. In addition, it is possible to learn the placement position and angle of the fixture, and the gum margin line according to the crown for each tooth number for which the crown position is determined for the oral model data of a patient who has previously established a fixture placement plan.

The testing unit 142 tests the learning result of the learning unit 140. In this case, when the testing result has an accuracy of more than a preset criterion, for example, 95% or more, the learning result is provided to the fixture determination unit 144.

3 is a diagram illustrating image data used for fixture placement according to an embodiment of the present invention.

The method of providing the location of the fixture to the user using artificial intelligence is based on utilizing the result of repetitive learning. To this end, data on which a fixture placement plan is established is accumulated on the CT data 300 or the oral model data 310 and undergoes repetitive training and testing through a machine learning algorithm. At this time, if the test result has a preset reference, for example, 95% or more accuracy, it is applied to provide placement information including the position and angle of the fixture in the actual implant placement plan.

The training data in the training process utilizes the placement information in which the fixture was placed in the image data using an image processing device. In this case, the image data includes CT data 300 and oral model data 310 as shown in FIG. 3. The oral model data 310 is obtained by scanning the patient's oral gypsum model or directly scanning the patient's oral cavity. The information that the image processing device learns during the training process is the patient's anatomical structure that can be checked from the patient's CT data 300, along with the alveolar bone and adjacent teeth information, as well as the maxillary sinus for the maxilla and the lower alveolar neural tube for the mandible Includes. The oral model data 310 includes information about the patient's gums. In addition, in the patient's oral model data 310, the placement position and angle of the fixture are learned according to the crown for each tooth number for which the crown position is determined.

4 is a diagram illustrating an image screen for determining an actual fixture position by using a result of learning a position between a crown and a fixture according to an embodiment of the present invention.

First, the position of the fixture 410 is determined using the position of the crown 400 disposed on the oral model data 310. As shown in FIG. 4, the initial position of the fixture 410 is determined based on the axis of the crown 400, and the angle between the crown 400 for each tooth number and the central axis of the fixture 410 in the training process and the crown 400 Study the positional relationship of fixtures according to the position of ). The initial position of the fixture 410 is determined to be located at the center of the crown 400 with the same central axis as the central axis of the crown 400, but the final position of the fixture 410 in consideration of other anatomical structures including alveolar bone In the case of determining, the central axis of the crown 400 and the central axis of the fixture 410 may be different. The location information of the fixture 410 for each tooth number including this case is learned by the medical image processing apparatus.

5 is a diagram illustrating an image screen for determining an actual fixture position using a result of learning a distance between a fixture and an alveolar bone according to an embodiment of the present invention.

The learning of information related to the location of the fixture in consideration of the alveolar bone is the distance from the center point in the top direction of the fixture to the alveolar bone, the mesial surface of the fixture and the alveolar bone (Mesial), distal surface (distal), and lingual side. It is possible to learn the distances in the (lingual) and buccal directions, and obtain fixture placement information considering the distance between the fixture and the alveolar bone from the learning results. For example, as shown in FIG. 5, the distance between the alveolar bone 500 and the fixture 410 in the top direction of the fixture 410 in the CT image 300 from the learning result is at least 1 mm, and the fixture 410 and the mesial Recognizing that the distance to the alveolar bone 500 should be at least 1.5mm in the direction of the Mesial, Distal, Linual, and Buccal, the position of the fixture 410 is adjusted accordingly.

6 is a diagram illustrating an image screen for determining a position of a fixture to be actually placed using a result of learning a distance between a fixture and a gum margin according to an embodiment of the present invention.

Using image data (eg, oral model data) of patients who have previously established a fixture placement plan, learn the distance between the gum margin 600 and the fixture 410, and use the learning result to learn the fixture 410 to be placed. Determine the distance from the gingival margin 600 of. At this time, the distance to the gum margin 600 is learned in the direction of the top of the fixture 410 based on the fixture 410. As shown in FIG. 6, it can be seen from the training data that the distance between the gum margin 600 and the fixture 410 is at least 3 mm.

7 is a diagram illustrating an image screen for determining an angle of a fixture to be actually placed using data obtained by learning the angles of a fixture and an adjacent tooth according to an embodiment of the present invention.

Using image data (eg, CT data) of a patient who has previously established a fixture placement plan, learns the angle between the patient's fixture 410 and the adjacent teeth 700, and uses the learning result to learn the fixture 410 to be placed. ) To determine the angle. At this time, the angle between the adjacent teeth 700 in the mesial direction and the fixture 410 of the tooth number to be placed is learned. As shown in FIG. 7, by reflecting the learning result from the CT data 300, the fixture placement angle is determined to be adjacent to the mesial direction or parallel to the installed or to be placed fixture.

8 is a diagram illustrating an image screen for determining a position of a fixture using a result of learning a relationship between a fixture and a maxillary sinus and an inferior alveolar neural tube according to an embodiment of the present invention.

When the patient's surgical site is the maxilla, the maxillary sinus 800, and the mandible, the collision between the inferior alveolar neural tube 810 and the fixture 410 should be additionally considered. 8, it is checked whether the maxillary sinus 800 and the inferior alveolar neural tube 810 collide in the direction of the lower apex (Apex) of the fixture 410, and the lowest point in the direction of the lower apex (Apex) of the fixture 410 And the distance of the maxillary sinus 800 and the inferior alveolar neural tube 810 and length information of the fixture 410 for each tooth number are learned.

In the medical image processing apparatus, when the maxillary sinus 800 collides, the maxillary sinus invasion area of the fixture 410 can be defined as an invasion acceptance criterion through learning data, or the invasion allowable range can be set by the user so that invasion beyond the invasion allowable range occurs In this case, the length of the fixture 410 can be adjusted. For example, as shown in FIG. 8, it is checked whether the maxillary sinus 800 and the inferior alveolar neural tube 810 collide in the direction of the lower apex (Apex) of the fixture 410, and the lower apex (Apex) of the fixture 410 In the direction, the distance between the lowermost point and the maxillary sinus 800 and the inferior alveolar neural tube 810, and length information of the fixture 410 for each tooth number may be learned to define an invasion acceptance criterion.

9 is a diagram illustrating an image screen for determining fixture placement information using a result of learning bone density of an alveolar bone in contact with a fixture according to an embodiment of the present invention.

Referring to FIG. 9, the medical image processing apparatus may additionally learn bone density information of an alveolar bone. Bone density is generally classified into D1~D5 according to bone quality and classified into Hard, Normal, Soft Bone, but sometimes classified into A1~D4 according to software and manufacturer's policy. Bone mineral density learns bone quality information of a region where the fixture 410 is placed or is in contact with the implanted fixture 410 as shown in FIG. 9. During testing, if the position of the fixture 410 is corrected according to the bone quality in the training data, or if the position is greatly deviated, information on the bone quality is displayed as a warning phrase and used so that the user can check it.

In this way, the relationship between the position of the fixture and the surrounding structures is learned and tested using artificial intelligence, targeting the image data for which the fixture placement plan was previously established. By reflecting the learning results derived based on learning and testing, we determine the placement information of the fixture to be actually placed, and propose it to the user. At this time, the testing is performed with image data in which the patient's CT data and oral model data are matched, and if the accuracy of the testing result is more than a preset criterion, for example, 95%, it is applied to the position of the fixture in the actual implant placement plan. Is proposed in the image processing apparatus. Furthermore, if correction is required according to the result, the user may fine-tune and determine the placement position of the final fixture.

10 is a diagram illustrating a method of establishing an implant surgery plan using artificial intelligence according to an embodiment of the present invention.

Referring to FIGS. 1 and 10, the medical image processing apparatus 1 acquires a learning result learned based on artificial intelligence for image data of patients who have previously established a fixture placement plan (S1000).

Subsequently, the medical image processing apparatus 1 determines and provides placement information including the position and angle of the fixture to be actually placed according to the oral environment using the acquired learning result (S1100).

In the step of determining and providing the placement information (S1100), the medical image processing apparatus 1 grasps the relationship information with the surrounding structures based on the position of the fixture placed from the acquired learning result, and By reflecting the relationship information, it is possible to determine the placement information of the fixture. The surrounding structures may be alveolar bone, gingival margin, adjacent teeth, maxillary sinus, neural tube and bone density.

In the step (S1100) of determining and providing implantation information, the medical image processing apparatus 1 determines the initial position of the fixture so that it is located at the center of the crown with the same central axis with respect to the central axis of the crown, and then The final position of the fixture may be determined by modifying the initial position of the fixture by reflecting the relationship information of.

In the step S1100 of determining and providing implantation information, the medical image processing apparatus 1 may determine the distance between the fixture and the alveolar bone by using learning about the alveolar bone. For example, the medical image processing apparatus 1 includes distance information from the alveolar bone learned from the center point in the top direction of the fixture based on the position of the fixture placed by tooth number in the previous data, and the mesial center of the fixture and the alveolar bone. The relationship between the fixture and the alveolar bone is grasped by acquiring the learning result including distance information in the directions of the mesial, distal, lingual, and buccal. Then, the distance between the fixture and the alveolar bone is determined based on the relationship between the identified fixture and the alveolar bone.

In step S1100 of determining and providing placement information, the medical image processing apparatus 1 may determine the distance between the fixture and the gum margin by using learning about the gum margin. For example, the medical image processing apparatus 1 acquires a learning result including distance information between the fixture and the gum margin in the top direction of the fixture based on the position of the fixture placed for each tooth number from the previous data. Figure out the relationship. Then, the distance between the fixture and the gum margin is determined based on the relationship between the identified fixture and the gum margin.

In the step S1100 of determining and providing placement information, the medical image processing apparatus 1 may determine an angle between the fixture and the adjacent teeth by using learning about the adjacent teeth. For example, the medical image processing apparatus 1 obtains a learning result including an angle between a fixture and an adjacent tooth based on the position of a fixture placed for each tooth number from previous data to grasp the relationship between the fixture and adjacent teeth. And, based on the relationship between the identified fixture and the adjacent value, the angle of the fixture is determined to be parallel to the adjacent value in the mesial direction.

In the step S1100 of determining and providing placement information, the medical image processing apparatus 1 may determine the position of the fixture by using the learning result of the maxillary sinus or neural tube. For example, in the case of a maxillary sinus impact, the maxillary sinus invasion area of the fixture can be defined through the learning data, or invasion, by checking whether there is a collision with the maxillary sinus or neural tube based on the position of the fixture placed by tooth number from the previous data. By allowing the user to set the permissible range, the length of the fixture can be adjusted when an invasion exceeds the permissible range.

In the step S1100 of determining and providing the placement information, the medical image processing apparatus 1 may determine the position of the fixture by using learning about bone quality information of the alveolar bone contacting the fixture. For example, by acquiring the learning result including the learned bone quality information of the area where the fixture is in contact with or where the fixture is placed, bone quality information around the fixture is identified. In addition, the location of the fixture may be determined using bone quality information around the identified fixture.

The method of establishing an implant surgery plan using artificial intelligence according to an embodiment is a step of learning using artificial intelligence on image data of a patient who has previously established a fixture placement plan in order to determine placement information of a fixture to be actually placed. It further includes (S1300). In the learning step (S1300), the medical image processing apparatus 1 learns the patient's anatomical structure including alveolar bone, adjacent teeth information, maxillary sinus, and neural tube information based on the fixtures placed from the previous CT data, and the previous oral model It is possible to learn the placement position and angle of the fixture and the gum margin line according to the crown for each tooth number for which the crown position is determined for the data.

So far, the present invention has been looked at around the embodiments. Those of ordinary skill in the art to which the present invention pertains will be able to understand that the present invention may be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered from an illustrative point of view rather than a limiting point of view. The scope of the present invention is shown in the claims rather than the above description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Claims (21)

In the method of establishing an implant surgery plan using a medical image processing device, the medical image processing device
Learning the image data of patients who have previously established a fixture placement plan using artificial intelligence;
Testing the learning result;
Obtaining a learning result in which the testing result is greater than or equal to a preset reference; And
Determining the initial position of the fixture based on the central axis of the crown, and correcting the initial position of the fixture by reflecting the relationship information with the surrounding structures identified from the learning result, determining and providing placement information including the position and angle of the fixture ;
Implant surgery plan establishment method comprising a. The method of claim 1, wherein the step of determining and providing implantation information
Based on the position of the fixture implanted from the acquired learning result, determining relationship information with surrounding structures including at least one of alveolar bone, gingival margin, adjacent teeth, maxillary sinus, neural tube, and bone density: and
Determining and providing information on placement of fixtures by reflecting the determined relationship information with surrounding structures;
Implant surgery plan establishment method comprising a. delete The method of claim 1, wherein the step of determining and providing implantation information
From previous data, distance information from the alveolar bone learned from the center point in the top direction of the fixture based on the position of the fixture placed by tooth number, and the mesial, distal, and lingual of the fixture and alveolar bone Acquiring a learning result including distance information in the (Lingual) and buccal directions to grasp the relationship between the fixture and the alveolar bone; And
Determining and providing a distance between the fixture and the alveolar bone based on the relationship between the identified fixture and the alveolar bone;
Implant surgery plan establishment method comprising a. The method of claim 1, wherein the step of determining and providing implantation information
Acquiring a learning result including distance information of a gingival margin in a top direction of the fixture based on the position of the fixture placed by tooth number from previous data to determine a relationship between the fixture and the gingival margin; And
Determining and providing a distance between the fixture and the gum margin on the basis of the relationship between the identified fixture and the gum margin;
Implant surgery plan establishment method comprising a. The method of claim 1, wherein the step of determining and providing implantation information
Acquiring a learning result including an angle between the fixture and the adjacent teeth based on the position of the fixture placed for each tooth number from the previous data to determine the relationship between the fixture and the adjacent teeth; And
Determining and providing an insertion angle of the fixture to be parallel to the adjacent value in the mesial direction based on the relationship between the identified fixture and the adjacent value;
Implant surgery plan establishment method comprising a. The method of claim 1, wherein the step of determining and providing implantation information
From the previous data, the distance between the lowermost point and the maxillary sinus and inferior alveolar neural tube in the direction of the lower apex (Apex) of the fixture by checking whether it collides with the maxillary sinus or neural tube based on the position of the fixture placed by tooth number, and by tooth number. Acquiring a learning result including information on the length of the fixture and determining a relationship between the fixture's maxillary sinus or a neural tube;
Determining and providing an actual fixture length and diameter based on a preset fixture specification; And
In the case of a maxillary sinus invasion region of the fixture in the case of a maxillary sinus collision, adjusting the length of the fixture when invasion exceeds the invasion allowable range by defining an invasion tolerance criterion through learning data or allowing a user to set an invasion tolerance;
Implant surgery plan establishment method comprising a. The method of claim 1, wherein the step of determining and providing implantation information
Acquiring a learning result including learned ossein information of a region in contact with the implanted fixture or where the fixture is located to grasp bone quality information around the fixture; And
Determining and providing a location of the fixture using bone quality information around the identified fixture;
Implant surgery plan establishment method comprising a. delete The method of claim 1, wherein the learning step
Learning a patient's anatomical structure including at least one of alveolar bone, adjacent teeth information, maxillary sinus and neural tube information based on the installed fixture based on the CT data of a patient who has previously established a fixture placement plan; And
Learning the placement position and angle of the fixture and the gum margin line according to the crown for each tooth number for which the crown position is determined based on the oral model data of the patient who has previously established the fixture placement plan;
Implant surgery plan establishment method comprising a. delete A data acquisition unit that acquires image data;
After determining the initial position of the fixture based on the central axis of the crown based on the image data of the patients who have previously established the fixture placement plan, the relationship information with the surrounding structures identified from the learning result learned based on artificial intelligence is reflected. A fixture determining unit configured to determine placement information including a position and angle of the fixture as the initial position is corrected;
An output unit for displaying the implantation information from the image data together on the screen;
A learning unit that learns image data of a patient who has previously established a fixture placement plan using artificial intelligence in order to determine placement information of a fixture to be actually placed, and provides the learning result to the fixture determination unit; And
A testing unit that tests the learning result of the learning unit, and provides the learning result to the fixture determination unit when the testing result is greater than or equal to a preset reference;
Medical image processing apparatus comprising a. The method of claim 12, wherein the fixture determination unit
Based on the position of the fixture placed from the obtained learning result, the relationship information with the surrounding structures including at least one of alveolar bone, gum margin, adjacent teeth, maxillary sinus, neural tube and bone density is grasped,
A medical image processing apparatus, characterized in that for determining the placement information of the fixture by reflecting the determined relationship information with the surrounding structures. The method of claim 12, wherein the fixture determination unit
From previous data, distance information from the alveolar bone learned from the center point in the top direction of the fixture based on the position of the fixture placed by tooth number, and the mesial, distal, and lingual of the fixture and alveolar bone By acquiring the learning results including distance information in the (Lingual) and buccal directions, the relationship between the fixture and the alveolar bone is grasped,
A medical image processing apparatus, characterized in that determining the distance between the fixture and the alveolar bone based on the relationship between the identified fixture and the alveolar bone. The method of claim 12, wherein the fixture determination unit
From the previous data, the relationship between the fixture and the gingival margin is grasped by acquiring the learning result including distance information from the gingival margin in the top direction of the fixture based on the position of the fixture placed by tooth number,
A medical image processing apparatus, characterized in that determining a distance between the fixture and the gum margin on the basis of the relationship between the identified fixture and the gum margin. The method of claim 12, wherein the fixture determination unit
Based on the position of the fixture placed by tooth number from the previous data, the learning result including the angle between the fixture and the adjacent teeth is acquired to understand the relationship between the fixture and the adjacent teeth,
A medical image processing apparatus, characterized in that, on the basis of the relationship between the identified fixture and the adjacent teeth, the placement angle of the fixture is determined to be parallel to the adjacent teeth in the mesial direction. The method of claim 12, wherein the fixture determination unit
From the previous data, the distance between the lowermost point and the maxillary sinus and inferior alveolar neural tube in the direction of the lower apex (Apex) of the fixture by checking whether it collides with the maxillary sinus or neural tube based on the position of the fixture placed by tooth number, and by tooth number. Acquires the learning result including the length information of the fixture to grasp the relationship with the maxillary sinus or neural tube of the fixture,
In the case of maxillary sinus impact, the fixture's maxillary sinus invasion area is characterized in that the length of the fixture is adjusted when invasion beyond the invasion allowable range occurs by defining an invasion tolerance criterion through learning data or allowing the user to set the invasion tolerance range. Medical image processing device. The method of claim 12, wherein the fixture determination unit
Acquires the learning result including the learned ossein information of the area in contact with the placed fixture or where the fixture is located, and grasps the bone quality information around the fixture,
A medical image processing apparatus, characterized in that the position of the fixture is determined using bone quality information around the identified fixture. delete The method of claim 12, wherein the learning unit
Learning the patient's anatomical structure including at least one of alveolar bone, adjacent teeth information, maxillary sinus and neural tube information based on the installed fixture based on the CT data of the patient who has previously established a fixture placement plan,
A medical image processing apparatus, characterized in that it learns the placement position and angle of the fixture, and the gum margin line according to the crown for each tooth number for which the crown position is determined, based on the oral model data of a patient who has previously established a fixture placement plan. delete

Images