Method for using anatomical landmarks of balance organ to construct three-dimensional cephalometric coordinate system

Through deep learning, training the craniofacial key anatomical point recognition model, automatically identifying and determining key points such as the clonal dentate apex, establishing a three-dimensional head shadow measurement coordinate system, solving the asymmetry problem of traditional two-dimensional measurement methods, and achieving more accurate craniofacial surgery and correction treatment.

WO2025161076A1PCT designated stage Publication Date: 2025-08-07INST OF AUTOMATION CHINESE ACAD OF SCI +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/078726
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-01-30
Filing Date
2024-02-27
Publication Date
2025-08-07

AI Technical Summary

Technical Problem

Traditional two-dimensional cephalogram measurement methods cannot meet clinical needs when facing facial asymmetry problems, and the selection of anatomical markers in existing three-dimensional cephalogram measurements is unstable, resulting in large errors in the three-dimensional coordinates and cannot provide accurate craniofacial surgery and correction treatment guidance.

Method used

Through deep learning, the identification model of the craniofacial key anatomical point is trained, and key anatomical points such as the apical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical anatomical through deep learning is automatically identified, and the horizontal plane, coronal plane and mediansagittal plane are determined based on these points, and a three-dimensional head shadow measurement coordinate system is established, using these surface intersections as the origin.

Benefits of technology

The stable coordinate value of each point in the CT data is achieved, which improves the quantitative evaluation and guidance accuracy of craniofacial surgery and correction treatment, reduces measurement errors, and makes diagnosis and planning easier.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024078726_07082025_PF_FP_ABST
    Figure CN2024078726_07082025_PF_FP_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of medical treatment, and provides a method for using anatomical landmarks of a balance organ to construct a three-dimensional cephalometric coordinate system. The method comprises: acquiring a CT image of a craniofacial region to be measured; determining an apex of odontoid process of the axis (AODA), an anterior nasal spine (ANS), a left helicotrema (HtL), a right helicotrema (HtR) and a sphenoid rostrum (SR) of the CT image; on the basis of the AODA, the ANS, the HtL, the HtR and the SR, determining a horizontal plane, and then determining a coronal plane and a median sagittal plane, wherein the horizontal plane is a plane formed by intersecting a parallel line of a line connecting the AODA and the ANS with a line connecting the HtL and the HtR, the coronal plane passes through the line connecting the HtL and the HtR and is perpendicular to the horizontal plane, and the median sagittal plane passes through the SR and is perpendicular to both the horizontal and coronal planes; and using an intersection point of the coronal plane, the median sagittal plane and the horizontal plane in the CT image of said craniofacial region as the origin of a three-dimensional cephalometric coordinate system, to establish the three-dimensional cephalometric coordinate system.
Need to check novelty before this filing date? Find Prior Art

Description

Method of constructing three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 2024101261892, filed on January 30, 2024, entitled “Method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs”, which is incorporated herein by reference in its entirety. Technical Field

[0003] The present application relates to the field of medical technology, and in particular to a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs. Background Art

[0004] Craniofacial plastic surgery and orthodontic treatment often rely on cephalometrics. However, traditional two-dimensional cephalometrics are no longer sufficient for addressing facial asymmetry. To address this issue, a precise three-dimensional coordinate system of craniofacial anatomical landmarks is required to guide and assist surgery.

[0005] While computed tomography (CT) data provides this coordinate system, there's no direct connection between this traditional coordinate system and the object being imaged. This means that when the patient's posture changes, the 3D coordinates of each point in the CT data also change, leading to significant 3D coordinate errors.

[0006] The anatomical landmarks used in 3D cephalometrics still follow the traditional 2D cephalometric approach, selecting relatively superficial landmarks with large growth variations and blurred boundaries. Due to facial asymmetry, it is currently impossible to define a unique horizontal plane. Furthermore, these defined planes have no direct relationship to physiological balance and, therefore, still cannot meet clinical needs.

[0007] Summary of the Invention

[0008] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, which can accurately determine the three-dimensional coordinate information of craniofacial anatomical landmarks to provide quantitative evaluation and guidance for craniofacial surgery and corrective treatment.

[0009] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, comprising:

[0010] Obtaining computed tomography (CT) images of the craniofacial area to be measured;

[0011] Inputting the CT image of the craniofacial face to be measured into the trained craniofacial key anatomical point recognition model, obtaining the axis odontoid process AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the sphenoid bone coracoid process SR of the CT image of the craniofacial face to be measured output by the trained craniofacial key anatomical point recognition model;

[0012] Based on the AODA, ANS, HtL, HtR, and SR of the CT image of the craniofacial region to be measured, first determine the horizontal plane, then determine the coronal plane and the midsagittal plane, the horizontal plane being a plane formed by a line parallel to the line connecting the AODA and the ANS and intersecting with the line connecting the HtL and the HtR, the coronal plane passing through the line connecting the HtL and the HtR and being perpendicular to the horizontal plane, and the midsagittal plane passing through the SR and being perpendicular to both the horizontal plane and the coronal plane;

[0013] The intersection point of the coronal plane, the mid-sagittal plane and the horizontal plane of the CT image of the cranial face to be measured is used as the origin of the three-dimensional cephalometric coordinate system to establish the three-dimensional cephalometric coordinate system.

[0014] According to the method provided in this application for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, the training process of the craniofacial key anatomical point recognition model includes:

[0015] Combining biological anatomical characteristics, a deep neural network and a three-dimensional convolutional layer are used to design the model architecture of the craniofacial key anatomical point recognition model;

[0016] Acquiring a first data set, the first data set comprising a plurality of CT images of a human head with three-dimensional spatial resolution;

[0017] Marking AODA, ANS, HtL, HtR, and SR in the plurality of human head CT images with three-dimensional spatial resolution;

[0018] Based on the labeled first data set, the craniofacial key anatomical point recognition model is trained through deep learning until any craniofacial CT image is input into the craniofacial key anatomical point recognition model, and the craniofacial key anatomical point recognition model can output correct AODA, ANS, HtL, HtR and SR.

[0019] According to the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs provided by the present application, after acquiring the first data set, the method further includes:

[0020] Based on the multiple human head CT images with three-dimensional spatial resolution, three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution are obtained through a three-dimensional reconstruction algorithm.

[0021] According to the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs provided in the present application, the method includes respectively marking AODA, ANS, HtL, HtR, and SR in the plurality of human head CT images with three-dimensional spatial resolution, including:

[0022] AODA, ANS, HtL, HtR and SR are respectively marked on the three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution.

[0023] The present application also provides a device for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, comprising:

[0024] An acquisition module, used for acquiring a computed tomography CT image of the craniofacial region to be measured;

[0025] An input module is used to input the CT image of the craniofacial face to be measured into the trained craniofacial key anatomical point recognition model, and obtain the axis odontoid process AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid bone coracoid process SR of the CT image of the craniofacial face to be measured output by the trained craniofacial key anatomical point recognition model;

[0026] a determination module for first determining a horizontal plane, and then determining a coronal plane and a midsagittal plane based on the AODA, ANS, HtL, HtR, and SR of the CT image of the craniofacial region to be measured, wherein the horizontal plane is a plane formed by a line parallel to the line connecting the AODA and the ANS and intersecting with a line connecting the HtL and the HtR; the coronal plane passes through the line connecting the HtL and the HtR and is perpendicular to the horizontal plane; and the midsagittal plane passes through the SR and is perpendicular to both the horizontal plane and the coronal plane;

[0027] The establishment module is used to establish a three-dimensional cephalometric coordinate system by taking the intersection of the coronal plane, the mid-sagittal plane and the horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system.

[0028] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the above-described methods for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs.

[0029] The present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs as described in any one of the above methods is implemented.

[0030] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above methods for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs.

[0031] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance. By selecting key anatomical landmarks such as the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the coracoid process of the sphenoid bone SR in craniofacial CT images, and determining the coronal plane, midsagittal plane, and horizontal plane based on these landmarks, and then using the intersection point of the three planes as the origin of the three-dimensional cephalometric coordinate system to establish a three-dimensional cephalometric coordinate system, each point in the CT data can obtain a relatively stable coordinate value. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] FIG1 is a flow chart of a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs provided by the present application;

[0034] FIG2 is a schematic diagram of the structure of an apparatus for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs provided by the present application;

[0035] FIG3 is a schematic structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0037] The following describes the method provided by the present application for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs with reference to FIG1 .

[0038] FIG1 is a flow chart of a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs provided in the present application. As shown in FIG1 , the method includes the following steps.

[0039] Step 100: Obtain a computed tomography (CT) image of the craniofacial region to be measured.

[0040] Optionally, in order to establish a three-dimensional cephalometric coordinate system of the cranial face to be measured, a CT image of the cranial face to be measured may be acquired first.

[0041] Optionally, a CT imaging device may be used to photograph the human head to obtain a CT image of the craniofacial area to be measured.

[0042] Optionally, existing craniofacial CT images to be measured stored in a hospital or research institution may be obtained.

[0043] Optionally, the CT image of the craniofacial area to be measured may have three-dimensional spatial resolution.

[0044] Step 110: input the CT image of the craniofacial surface to be measured into the trained craniofacial key anatomical point recognition model, and obtain the apex of the dens axis (AODA), the anterior nasal spine (ANS), the left cochlear foramen (HtL), the right cochlear foramen (HtR), and the sphenoidal rostrum (SR) of the CT image of the craniofacial surface to be measured output by the trained craniofacial key anatomical point recognition model.

[0045] Optionally, in order to establish a relatively stable three-dimensional coordinate system for craniofacial images, some anatomical landmarks that are relatively stable, clear, and naturally single during development can be selected from the craniofacial CT images, namely, the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the coracoid process of the sphenoid bone SR. Based on these anatomical landmarks, a three-dimensional cephalometric coordinate system can be established, which can avoid the defect of lack of left-right symmetry in two-dimensional measurement while conforming to the natural physiological head position of the human body.

[0046] Optionally, the anatomical points selected in this application are physiologically consistent, and the head position established by the balance organ is horizontal. This application uses the balance organ as a reference plane and selects the cochlear foramen to represent the inner ear, which is an important component of the balance organ; the line connecting the anterior nasal spine and the top of the odontoid process of the axis represents this horizontal plane, and the midline of the skull passes through the coracoid process of the sphenoid bone, which is the relatively most stable part of the skull.

[0047] Optionally, in order to achieve accurate and automatic determination of the apex of the odontoid process of the axis vertebra AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid coracoid process SR in the CT image of the craniofacial surface to be measured, a craniofacial key anatomical point recognition model can be trained by deep learning, and the apex of the odontoid process of the axis vertebra AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid coracoid process SR in the input CT image of the craniofacial surface to be measured can be automatically determined by the trained craniofacial key anatomical point recognition model.

[0048] Optionally, the CT image of the craniofacial area to be measured can be input into the trained craniofacial key anatomical point recognition model to obtain the CT image output by the trained craniofacial key anatomical point recognition model with the points marked with AODA, ANS, HtL, HtR and SR, so as to facilitate the subsequent construction of the coronal plane, midsagittal plane and horizontal plane.

[0049] Optionally, the odontoid process of the axis is a bony protrusion located at the posterior and superior part of the axis, which is aligned with the posterior median depression of the first cervical vertebra.

[0050] Alternatively, the anterior nasal spine is a sharp bony protuberance between the lower edge of the piriform aperture of the nose and the maxilla.

[0051] Optionally, the left and right modal foramina are small holes connecting the scala tympani and scala vestibuli, located at the center top of the cochlea.

[0052] Alternatively, the sphenoid coracoid process is a triangular spine on the inferior surface of the sphenoid bone that articulates with the sphenoid ridge on the anterior surface of the sphenoid bone and is received by the vomerine groove of the vomer.

[0053] Step 120, based on the AODA, ANS, HtL, HtR and SR of the CT image of the craniofacial area to be measured, first determine the horizontal plane, then determine the coronal plane and the midsagittal plane. The horizontal plane is a plane formed by a line parallel to the line connecting AODA and ANS and intersecting with the line connecting HtL and HtR. The coronal plane passes through the line connecting HtL and HtR and is perpendicular to the horizontal plane. The midsagittal plane passes through the SR and is perpendicular to both the horizontal plane and the coronal plane.

[0054] Optionally, after determining the positions of AODA, ANS, HtL, HtR and SR of the CT image of the craniofacial region to be measured, the coronal plane, midsagittal plane and horizontal plane may be constructed based on these positions.

[0055] Specifically, the horizontal plane is a plane formed by a line parallel to the line connecting AODA and ANS and intersecting the line connecting HtL and HtR.

[0056] Specifically, the coronal plane passes through the line connecting HtL and HtR and is perpendicular to the horizontal plane.

[0057] Specifically, the midsagittal plane passes through the SR and is perpendicular to both the horizontal and coronal planes.

[0058] Step 130 : Establishing a three-dimensional cephalometric coordinate system by using the intersection of the coronal plane, the mid-sagittal plane, and the horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system.

[0059] Optionally, after determining the horizontal plane, coronal plane and midsagittal plane of the CT image of the cranial face to be measured, the three planes will produce an intersection point, which can be used as the origin of the three-dimensional cephalometric coordinate system to establish a three-dimensional cephalometric coordinate system. Based on this three-dimensional coordinate system, each point in the existing craniofacial CT data can obtain a relatively stable coordinate value, making the measurement data required for the diagnosis and plan planning of orthodontics, orthognathic surgery, implants, etc. for each case more simple, intuitive and accurate, avoiding the errors caused by projection angles and measurement habits in traditional two-dimensional measurements.

[0060] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance. By selecting key anatomical landmarks such as the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the coracoid process of the sphenoid bone SR in the craniofacial CT image, and determining the horizontal plane, coronal plane, and mid-sagittal plane based on these landmarks, and then using the intersection of the three planes as the origin of the three-dimensional cephalometric coordinate system to establish a three-dimensional cephalometric coordinate system, each point in the CT data can obtain a relatively stable coordinate value.

[0061] Optionally, the training process of the craniofacial key anatomical point recognition model includes:

[0062] Combining biological anatomical characteristics, a deep neural network and a three-dimensional convolutional layer are used to design the model architecture of the craniofacial key anatomical point recognition model;

[0063] Acquiring a first data set, the first data set comprising a plurality of CT images of a human head with three-dimensional spatial resolution;

[0064] Marking AODA, ANS, HtL, HtR, and SR in the plurality of human head CT images with three-dimensional spatial resolution;

[0065] Based on the labeled first data set, the craniofacial key anatomical point recognition model is trained through deep learning until any craniofacial CT image is input into the craniofacial key anatomical point recognition model, and the craniofacial key anatomical point recognition model can output correct AODA, ANS, HtL, HtR and SR.

[0066] Optionally, in order to train the craniofacial key anatomical point recognition model, the model architecture of the craniofacial key anatomical point recognition model can be designed by first combining biological anatomical characteristics, using deep neural networks and three-dimensional convolutional layers.

[0067] Optionally, a data set may be acquired, and the data set may include a plurality of CT images of a human head with three-dimensional spatial resolution.

[0068] Optionally, multiple existing human head CT images with three-dimensional spatial resolution can be obtained from a hospital or research institution, or multiple human head CT images with three-dimensional spatial resolution can be artificially produced, or the first data set can be obtained in other ways, which is not limited in this application.

[0069] Optionally, after acquiring the first data set, the axis odontoid process AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the sphenoid coracoid process SR can be marked in each human head CT image so that the craniofacial key anatomical point recognition model can recognize these key anatomical points.

[0070] Optionally, multiple modalities such as CT images, RGB-D sensor information, and expert annotation information can be fused to train a craniofacial key anatomical point recognition model.

[0071] Optionally, the craniofacial key anatomical point recognition model can be trained by deep learning based on the annotated first data set until any craniofacial CT image is input into the craniofacial key anatomical point recognition model, and the craniofacial key anatomical point recognition model can output the correct axis odontoid process AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid coracoid process SR.

[0072] Optionally, prior knowledge of craniofacial shape and structure can be combined to introduce set constraints on bone structure and optimize the loss function to ensure that the key craniofacial anatomical points generated by the model conform to the actual anatomy.

[0073] Optionally, the algorithm used in deep learning may be a back-propagation algorithm, or a convolutional neural network, or a recurrent neural network, or other algorithms that can achieve training effects, which is not limited in this application.

[0074] Optionally, after the training of the craniofacial key anatomical point recognition model is completed, the CT image of the craniofacial face to be measured is input into the trained craniofacial key anatomical point recognition model, which can automatically and accurately determine the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the coracoid process of the sphenoid bone SR in the CT image.

[0075] The method provided in this application for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance can automatically and accurately determine the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the coracoid process of the sphenoid bone SR in the CT image by inputting the CT image of the craniofacial face to be measured into the trained craniofacial key anatomical point recognition model, thereby facilitating the subsequent establishment of a three-dimensional cephalometric coordinate system and improving the establishment efficiency.

[0076] Optionally, after obtaining the first data set, the method further includes:

[0077] Based on the multiple human head CT images with three-dimensional spatial resolution, three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution are obtained through a three-dimensional reconstruction algorithm.

[0078] Optionally, since the human head CT image is a two-dimensional image, in order to mark the specific three-dimensional positions of the axis odontoid process AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the sphenoid coracoid process SR in the CT image, a three-dimensional reconstruction algorithm can be used to first obtain a plurality of three-dimensional brain models corresponding to the human head CT images with three-dimensional spatial resolution.

[0079] Optionally, the three-dimensional reconstruction algorithm may be a triangulation method, a monocular vision method, a structured light method, or other three-dimensional reconstruction algorithms, which are not limited in this application.

[0080] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance, and obtains a corresponding three-dimensional model of the brain based on CT images of the human head through a three-dimensional reconstruction algorithm, which facilitates the subsequent marking of the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the coracoid process SR of the sphenoid bone in the three-dimensional model.

[0081] Optionally, the marking of AODA, ANS, HtL, HtR and SR in the plurality of human head CT images with three-dimensional spatial resolution includes:

[0082] AODA, ANS, HtL, HtR and SR are respectively marked on the three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution.

[0083] Optionally, after obtaining a three-dimensional brain model corresponding to multiple human head CT images with three-dimensional spatial resolution, the top of the axis odontoid process AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the coracoid process SR of the sphenoid bone can be accurately marked on the three-dimensional brain model to facilitate subsequent training of the craniofacial key anatomical point recognition model.

[0084] Alternatively, this application has been manually tested on a large number of real-world clinical cases. This coordinate system can be used for diagnosis and treatment planning, facilitating the discovery of difficult clinical causes. This process allows for both qualitative and quantitative analysis, in line with scientific principles. It also allows patients to intuitively understand their condition and its cause, facilitating communication with patients. This coordinate system helps form clear treatment plans, particularly for guiding invisible orthodontic tooth alignment, orthognathic surgery, plastic surgery, bone setting, and temporomandibular joint occlusal reconstruction.

[0085] The present application provides a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance, in which the apex of the odontoid process of the axis AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR and the coracoid process of the sphenoid bone SR are respectively marked on three-dimensional models of the brain corresponding to multiple human head CT images with three-dimensional spatial resolution, to facilitate subsequent training of a model for recognizing key anatomical points of the craniofacial region.

[0086] The following describes the device provided in this application for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs.

[0087] Figure 2 is a structural schematic diagram of the device provided in this application for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs. As shown in Figure 2, the device includes an acquisition module 210, an input module 220, a determination module 230 and an establishment module 240.

[0088] The acquisition module 210 is used to acquire a computed tomography (CT) image of the craniofacial region to be measured.

[0089] The input module 220 is used to input the CT image of the craniofacial surface to be measured into the trained craniofacial key anatomical point recognition model, and obtain the axis odontoid process AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid coracoid process SR of the CT image of the craniofacial surface to be measured output by the trained craniofacial key anatomical point recognition model.

[0090] Determination module 230 is used to first determine the horizontal plane, and then determine the coronal plane and the midsagittal plane based on the AODA, ANS, HtL, HtR and SR of the CT image of the craniofacial surface to be measured. The horizontal plane is a plane formed by a line parallel to the line connecting AODA and ANS and intersecting with the line connecting HtL and HtR. The coronal plane passes through the line connecting HtL and HtR and is perpendicular to the horizontal plane. The midsagittal plane passes through the SR and is perpendicular to both the horizontal plane and the coronal plane.

[0091] The establishing module 240 is used to establish a three-dimensional cephalometric coordinate system by using the intersection of the coronal plane, the mid-sagittal plane and the horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system.

[0092] The present application provides a device for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the organs of balance. By selecting key anatomical landmarks such as the apex of the odontoid process of the axis vertebra AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the coracoid process of the sphenoid bone SR in the craniofacial CT image, and determining the horizontal plane, coronal plane, and mid-sagittal plane based on these landmarks, and then using the intersection point of the three planes as the origin of the three-dimensional cephalometric coordinate system to establish a three-dimensional cephalometric coordinate system, each point in the CT data can obtain a relatively stable coordinate value.

[0093] It can be understood that the device for constructing a three-dimensional cephalometric coordinate system using the anatomical landmarks of the balance organs provided in the present application corresponds to the method for constructing a three-dimensional cephalometric coordinate system using the anatomical landmarks of the balance organs provided in the above-mentioned embodiments. The relevant technical features of the device for constructing a three-dimensional cephalometric coordinate system using the anatomical landmarks of the balance organs provided in the present application can refer to the relevant technical features of the method for constructing a three-dimensional cephalometric coordinate system using the anatomical landmarks of the balance organs provided in the above-mentioned embodiments, and will not be repeated here.

[0094] FIG3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in FIG3 , the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the balance organs, the method comprising: obtaining a computed tomography CT image of the cranial face to be measured; inputting the CT image of the cranial face to be measured into a trained cranial face key anatomical point recognition model, obtaining the axis odontoid process AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR, and sphenoid coracoid process SR of the CT image of the cranial face to be measured output by the trained cranial face key anatomical point recognition model; based on the CT image of the cranial face to be measured, Measure the AODA, ANS, HtL, HtR, and SR of the cranial CT image, first determine the horizontal plane, then determine the coronal plane and the midsagittal plane, the horizontal plane being a line parallel to the line connecting the AODA and the ANS, and intersecting with the line connecting the HtL and the HtR, the coronal plane passing through the line connecting the HtL and the HtR and being perpendicular to the horizontal plane, and the midsagittal plane passing through the SR and being perpendicular to both the horizontal and coronal planes; establish a three-dimensional cephalometric coordinate system using the intersection point of the coronal, midsagittal, and horizontal planes of the CT image of the cranial face to be measured as the origin of the system.

[0095] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0096] On the other hand, the present application also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method provided by the above-mentioned methods for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, the method including: obtaining a computer tomography CT image of the cranial face to be measured; inputting the CT image of the cranial face to be measured into a trained craniofacial key anatomical point recognition model; obtaining the axis odontoid process top AODA, anterior cephalometric coordinate system of the CT image of the cranial face to be measured output by the trained craniofacial key anatomical point recognition model; Nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid coracoid process SR; based on AODA, ANS, HtL, HtR and SR of the CT image of the cranial face to be measured, first determine the horizontal plane, then determine the coronal plane and the mid-sagittal plane, the horizontal plane is a line parallel to the line connecting AODA and ANS, and is a plane formed by the intersection with the line connecting HtL and HtR, the coronal plane passes through the line connecting HtL and HtR and is perpendicular to the horizontal plane, the mid-sagittal plane passes through SR and is perpendicular to both the horizontal plane and the coronal plane; with the intersection point of the coronal plane, mid-sagittal plane and horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system, a three-dimensional cephalometric coordinate system is established.

[0097] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented by a processor to execute the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of the balance organs provided by the above methods, the method comprising: obtaining a computer tomography CT image of the cranial face to be measured; inputting the CT image of the cranial face to be measured into a trained cranial face key anatomical point recognition model, and obtaining the axis odontoid process top AODA, anterior nasal spine ANS, left cochlear foramen HtL, right The cochlear foramen HtR and the coracoid process SR of the sphenoid bone; based on the AODA, ANS, HtL, HtR and SR of the CT image of the cranial face to be measured, first determine the horizontal plane, then determine the coronal plane and the midsagittal plane, the horizontal plane is a line parallel to the line connecting AODA and ANS, and is a plane formed by the intersection with the line connecting HtL and HtR, the coronal plane passes through the line connecting HtL and HtR and is perpendicular to the horizontal plane, the midsagittal plane passes through SR and is perpendicular to both the horizontal plane and the coronal plane; with the intersection point of the coronal plane, midsagittal plane and horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system, a three-dimensional cephalometric coordinate system is established.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0099] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, comprising: Obtaining computed tomography (CT) images of the craniofacial area to be measured; Inputting the CT image of the craniofacial face to be measured into the trained craniofacial key anatomical point recognition model, obtaining the axis odontoid process AODA, the anterior nasal spine ANS, the left cochlear foramen HtL, the right cochlear foramen HtR, and the sphenoid bone coracoid process SR of the CT image of the craniofacial face to be measured output by the trained craniofacial key anatomical point recognition model; Based on the AODA, ANS, HtL, HtR, and SR of the CT image of the craniofacial region to be measured, first determine the horizontal plane, then determine the coronal plane and the midsagittal plane, the horizontal plane being a plane formed by a line parallel to the line connecting the AODA and the ANS and intersecting with the line connecting the HtL and the HtR, the coronal plane passing through the line connecting the HtL and the HtR and being perpendicular to the horizontal plane, and the midsagittal plane passing through the SR and being perpendicular to both the horizontal plane and the coronal plane; The intersection point of the coronal plane, the mid-sagittal plane and the horizontal plane of the CT image of the cranial face to be measured is used as the origin of the three-dimensional cephalometric coordinate system to establish the three-dimensional cephalometric coordinate system.

2. The method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs according to claim 1, wherein: The training process of the craniofacial key anatomical point recognition model includes: Combining biological anatomical characteristics, a deep neural network and a three-dimensional convolutional layer are used to design the model architecture of the craniofacial key anatomical point recognition model; Acquiring a first data set, the first data set comprising a plurality of CT images of a human head with three-dimensional spatial resolution; Marking AODA, ANS, HtL, HtR, and SR in the plurality of human head CT images with three-dimensional spatial resolution; Based on the labeled first data set, the craniofacial key anatomical point recognition model is trained through deep learning until any craniofacial CT image is input into the craniofacial key anatomical point recognition model, and the craniofacial key anatomical point recognition model can output correct AODA, ANS, HtL, HtR and SR.

3. The method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs according to claim 2, wherein: After obtaining the first data set, the method further includes: Based on the multiple human head CT images with three-dimensional spatial resolution, An algorithm is constructed to obtain three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution.

4. The method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs according to claim 3, wherein: The method of marking AODA, ANS, HtL, HtR and SR in the plurality of human head CT images with three-dimensional spatial resolution includes: AODA, ANS, HtL, HtR and SR are respectively marked on the three-dimensional brain models corresponding to the multiple human head CT images with three-dimensional spatial resolution.

5. A device for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs, comprising: An acquisition module, used for acquiring a computed tomography CT image of the craniofacial region to be measured; An input module is used to input the CT image of the craniofacial face to be measured into the trained craniofacial key anatomical point recognition model, and obtain the axis odontoid process AODA, anterior nasal spine ANS, left cochlear foramen HtL, right cochlear foramen HtR and sphenoid bone coracoid process SR of the CT image of the craniofacial face to be measured output by the trained craniofacial key anatomical point recognition model; a determination module for first determining a horizontal plane, and then determining a coronal plane and a midsagittal plane based on the AODA, ANS, HtL, HtR, and SR of the CT image of the craniofacial region to be measured, wherein the horizontal plane is a plane formed by a line parallel to the line connecting the AODA and the ANS and intersecting with a line connecting the HtL and the HtR; the coronal plane passes through the line connecting the HtL and the HtR and is perpendicular to the horizontal plane; and the midsagittal plane passes through the SR and is perpendicular to both the horizontal plane and the coronal plane; The establishment module is used to establish a three-dimensional cephalometric coordinate system by taking the intersection of the coronal plane, the mid-sagittal plane and the horizontal plane of the CT image of the cranial face to be measured as the origin of the three-dimensional cephalometric coordinate system.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs as described in any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs as claimed in any one of claims 1 to 4 is implemented.

8. A computer program product comprising a computer program, wherein When the computer program is executed by a processor, the method for constructing a three-dimensional cephalometric coordinate system using anatomical landmarks of balance organs as claimed in any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • Automatic tooth arrangement method and device

    CN105769353A

  • Three-dimensional dental craniofacial deformity auxiliary recognition method and system based on machine learning

    CN114022477A

  • Head measurement three-dimensional coordinate system and establishment method and application thereof

    CN114680911A

  • Model training method and device, and head shadow measurement key point positioning method and device

    CN115797730A

  • Method for automatic detection of anatomical landmarks in volumetric data

    US20160203604A1