Maxillofacial region soft tissue model generation method for orthodontic process

Abstract

The invention belongs to the technical field of maxillofacial region image analysis, and provides a maxillofacial region soft tissue model generation method for an orthodontic process. Respectively constructing a current finite element data block and a reference finite element data block, and analyzing the distribution condition of various soft tissues of the reference finite element data block corresponding to the current finite element data block to obtain a distribution probability set of the various soft tissues in the current finite element data block; segmenting the current finite element data block based on the distribution probability set to obtain a plurality of sub-finite element data blocks and a sub-distribution probability set; and finally, on the basis of the sub-distribution probability set, soft tissue distribution consistency between the sub-finite element data blocks and all neighborhood sub-finite element data blocks is analyzed, the sub-finite element data blocks are combined, and a more accurate soft tissue model structure of the current patient can be obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of maxillofacial image analysis, and in particular to a maxillofacial soft tissue model generation method for orthodontic treatment. BACKGROUND

[0002] In the process of orthodontic treatment, the change of maxillofacial soft tissue is a key factor affecting the patient's appearance and treatment effect. Traditional soft tissue prediction relies on experience judgment or static model, and lacks accurate modeling and dynamic prediction for individual differences. Establishing an accurate maxillofacial soft tissue and bone tissue coupling modeling method has become an important research direction in the cross fields of oral medicine, maxillofacial surgery and biomechanics. In the process of orthodontic and orthognathic treatment, doctors need to accurately predict the response of facial soft tissue caused by tooth movement and jaw reconstruction, in order to assist in treatment planning, simulation, postoperative evaluation and patient communication.

[0003] The clinical application of CBCT (Cone Beam Computed Tomography, Cone Beam X-ray Computed Tomography) mainly focuses on dental systems and radiotherapy departments, and the CBCT in dental application is sometimes specially called oral CBCT, which is mainly used for three-dimensional display of the overall appearance of teeth and diseased tissues. CBCT uses cone beam X-ray scanning to significantly improve the utilization rate of X-rays, and only needs to rotate 360° (one circle) to obtain all the original data required for reconstruction, without the need for axial scanning or spiral scanning like traditional CT, which collects data in multiple layers. In the process of generating maxillofacial soft tissue in orthodontic treatment, the prior art generally first obtains patient facial bone data and facial surface data through CBCT and 3D scanning technology (three-dimensional scanning technology); however, CBCT and 3D scanning technology cannot directly reconstruct the maxillofacial soft tissue model according to the patient's facial information and bone data, so it is necessary to combine MBI (Magnetic Resonance Imaging, Magnetic Resonance Imaging) to obtain maxillofacial soft tissue model data. However, MBI has the characteristics of long time and large amount of calculation when acquiring soft tissue information data, which is not suitable for clinical application, and is more inclined to laboratory research.

[0004] Therefore, an efficient and accurate method is needed for generating a three-dimensional model of maxillofacial soft tissue in the process of orthodontic treatment to achieve more accurate, intuitive and personalized orthodontic treatment planning and orthodontic prediction effect. SUMMARY

[0005] In order to solve the above technical problems, the present application provides a maxillofacial soft tissue model generation method for orthodontic treatment.

[0006] A method for generating a maxillofacial soft tissue model for orthodontic procedures, provided by the present invention, the method comprising: Obtain the current patient's facial bone data and historical model dataset; Based on the reference attachment points in the historical model dataset, the facial bone data is matched with the facial bone information in the historical model dataset to obtain the simulated attachment points of the facial bone data. Based on the simulated attachment point and the reference attachment point, a current finite metadata block and a reference finite metadata block are constructed respectively, and the corresponding reference finite metadata block of the current finite metadata block is obtained; Analyze the distribution of various soft tissues in the corresponding reference finite metadata block to obtain the distribution probability set of various soft tissues in the current finite metadata block; Based on the set of probability distributions, the current finite metadata block is divided to obtain several sub-finite metadata blocks and sub-sets of probability distributions; Based on the sub-distribution probability set, the consistency of soft tissue distribution between the sub-finite metadata block and all its neighboring sub-finite metadata blocks is analyzed, and the sub-finite metadata blocks are merged to obtain the soft tissue model structure of the current patient.

[0007] In some embodiments of the present invention, based on reference attachment points in the historical model dataset, the facial bone data is matched with the historical model dataset to obtain simulated attachment points of the facial bone data, including: Based on the facial bone data, a current bone model of the current patient is constructed; The current skeletal model is registered with the historical skeletal models in the historical model dataset, and the reference attachment points in the historical model dataset are mapped to the current skeletal model to obtain the inheritance mapping points of the current skeletal model. Analyze the referenceability of the reference attachment point corresponding to the inherited mapping point; The shape feature matching degree between the inherited mapping point and the reference attachment point is analyzed, and the reliability of the inherited mapping point is obtained by combining the referenceability degree. A preset confidence threshold is used to obtain the simulated attachment points of the facial bone data based on the confidence level.

[0008] In some embodiments of the present invention, analyzing the referability of the reference attachment point corresponding to the inherited mapping point includes: Based on the reference attachment points in the historical model dataset, the historical model data corresponding to different sampled specimens in the historical model dataset are matched to obtain the number of times the reference attachment points are matched for each inherited mapping point. According to the number of matching times, in combination with the number of sampling samples in the historical model data set, a reference degree of the reference attachment point corresponding to the inheritance mapping point is obtained.

[0009] In some embodiments of the present application, the shape feature matching degree of the inheritance mapping point and the reference attachment point is analyzed, including: The shape feature matching degree of the inheritance mapping point and the reference attachment point is analyzed by analyzing the bone curvature difference degree and the bone normal vector difference degree of the positions where the inheritance mapping point and the reference attachment point are located.

[0010] In some embodiments of the present application, based on the simulation attachment point and the reference attachment point, a current finite element data block and a reference finite element data block are respectively constructed, and the corresponding reference finite element data block of the current finite element data block is obtained, including: Obtaining the facial surface data of the current patient; Taking the simulation attachment point as the starting point, a current finite element data block is constructed, and the soft tissue region between the facial bone data and the facial surface data is segmented by the current finite element data block, to obtain the number of current finite element data blocks; Taking the reference attachment point as the starting point and the number of current finite element data blocks as the segmentation number, the soft tissue region in the historical model data set is segmented to obtain a reference finite element data block; The current finite element data block and the reference finite element data block are matched one by one to obtain the corresponding reference finite element data block of the current finite element data block.

[0011] In some embodiments of the present application, the distribution of various soft tissues in the corresponding reference finite element data block is analyzed to obtain a distribution probability set of various soft tissues in the current finite element data block, including: Obtaining the reference volume of the reference finite element data block and the reference tissue volume of various soft tissues in the reference finite element data block; Based on the reference tissue volume and the reference volume, the volume distribution of various soft tissues in the corresponding reference finite element data block of the current finite element data block is analyzed to obtain a distribution probability set of various soft tissues in the current finite element data block.

[0012] In some embodiments of the present application, based on the distribution probability set, the current finite element data block is segmented to obtain a plurality of sub finite element data blocks and sub distribution probability sets, including: Obtaining the maximum probability in the distribution probability set; A probability threshold is preset; Determine whether the maximum probability is less than the probability threshold; If yes, the current finite element data block is divided into two parts; The distribution probability set of each soft tissue in the segmented current finite element data block is re-acquired, the probability threshold judgment is continued, the finite element data block not meeting the probability threshold is continuously segmented, and the segmentation operation is stopped until the probability threshold is met, so as to obtain a plurality of sub finite element data blocks and a sub distribution probability set corresponding to the sub finite element data blocks.

[0013] In some embodiments of the present application, based on the sub distribution probability set, the soft tissue distribution consistency between the sub finite element data block and all neighboring sub finite element data blocks thereof is analyzed, the sub finite element data block is merged, and the soft tissue model structure of the current patient is obtained, including: Based on the sub distribution probability set, the information entropy of the soft tissue distribution between the sub finite element data block and all neighboring sub finite element data blocks thereof is acquired, the volume of the neighboring sub finite element data block is combined, and the identity between the soft tissue in the neighboring sub finite element data block and the soft tissue in the sub finite element data block is obtained, so as to obtain the soft tissue distribution consistency between the sub finite element data block and all neighboring sub finite element data blocks thereof; Based on the soft tissue distribution consistency, the sub finite element data block is merged, and the information entropy threshold is set to limit the merging, so as to obtain the soft tissue model structure of the current patient.

[0014] In some embodiments of the present application, the historical model data set is acquired, including: The historical maxillofacial soft tissue data of the sampling specimen is acquired through the MBI technology; The historical facial bone data of the sampling specimen is acquired through the CBCT technology; The historical facial surface data of the sampling specimen is acquired through the 3D technology; Based on the historical maxillofacial soft tissue data, the historical facial bone data and the historical facial surface data, the historical model data set of the sampling specimen is obtained.

[0015] In some embodiments of the present application, the reference attachment point acquisition method in the historical model data set includes: The historical bone model of each historical model data in the historical model data set is acquired through semantic segmentation; The reference attachment point on the historical bone model is acquired through artificial annotation.

[0016] As can be seen from the above embodiments, the jaw and facial soft tissue model generation method for the orthodontic process provided by the embodiments of the present application has the following beneficial effects: The application firstly matches the facial bone data of the current patient with the historical model data set to obtain the simulation attachment points of the facial bone data; then, based on the simulation attachment points and the reference attachment points in the historical model data set, the current finite element data block and the reference finite element data block are respectively constructed, and the corresponding reference finite element data block of the current finite element data block is obtained; the distribution of various soft tissues in the corresponding reference finite element data block is analyzed to obtain the distribution probability set of various soft tissues in the current finite element data block; then, based on the distribution probability set, the current finite element data block is segmented to obtain a plurality of sub finite element data blocks and sub distribution probability sets; finally, based on the sub distribution probability sets, the soft tissue distribution consistency between the sub finite element data block and all neighboring sub finite element data blocks thereof is analyzed, the sub finite element data block is merged, and the soft tissue model structure of the current patient is obtained. That is, the matching degree between the data of the current patient and the historical data is analyzed to realize the construction of the finite element data block of the current patient data; the organization distribution of the historical data itself is combined to realize the analysis of the soft tissue distribution probability in the corresponding finite element data block of the current patient; then, according to the soft tissue distribution probability, the segmentation and recombination of the corresponding finite element data block of the current patient are realized, and finally, the more accurate soft tissue model structure of the current patient is obtained.

[0017] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the application. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0019] Figure 1 A basic flowchart of a jaw and facial soft tissue model generation method for an orthodontic process provided by an embodiment of the present application is shown in the figure. Figure 2 A reference attachment point diagram of a historical bone model provided by an embodiment of the present application is shown in the figure. Figure 3 Another reference attachment point diagram of a historical bone model provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0020] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the following describes in detail the specific implementation, structure, features and effects of a jaw and facial soft tissue model generation method for an orthodontic process according to the present application, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms such as "comprise", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, so that the circuit structure, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such article or device. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the article or device comprising the element.

[0022] The jaw and facial soft tissue model generation method for an orthodontic process provided by the present embodiment will be described in detail below with reference to the accompanying drawings.

[0023] Please refer to Figure 1 , which shows the basic flow of a jaw and facial soft tissue model generation method for an orthodontic process provided by one embodiment of the present application.

[0024] As shown in Figure 1 , the jaw and facial soft tissue model generation method for an orthodontic process provided by one embodiment of the present application specifically includes the following steps: S100: Obtain the facial bone data and historical model data set of the current patient.

[0025] Obtain the facial bone data and historical model data set of the current patient. Specifically, the facial bone data of the current patient is collected by CBCT (Cone Beam Computed Tomography, Cone Beam X-ray Computed Tomography), and the collected CBCT data is subjected to Otsu threshold segmentation to obtain the facial bone data of the current patient. At the same time, the facial surface data of the current patient is obtained by 3D scanning technology, and the basic data for constructing the jaw and facial soft tissue model for the current patient's orthodontic process is obtained.

[0026] Under laboratory conditions, historical maxillofacial soft tissue data of a plurality of sampling specimens is acquired by MBI (Magnetic Resonance Imaging) technology, and historical facial bone data of the plurality of sampling specimens is acquired by CBCT technology; at the same time, historical facial surface data of the plurality of sampling specimens is acquired by 3D scanning technology; then, based on the historical maxillofacial soft tissue data, the historical facial bone data and the historical facial surface data, historical model data of the sampling specimens is obtained, and specifically, the historical maxillofacial soft tissue data, the historical facial bone data and the historical facial surface data can be imported into 3D Slicer software (3D Slicer software provides a variety of tools and modules, which can be used for processing and analyzing medical image data, including construction of a facial model), and the historical model data of the sampling specimens is output. The historical model data includes a historical bone model and a historical soft tissue model, and the historical model data of the plurality of sampling specimens forms a historical model data set. The historical model data set can provide data support for subsequent construction of a maxillofacial soft tissue model of a current patient.

[0027] At this point, the facial bone data of the current patient and the historical model data set of the sampling specimens are acquired.

[0028] S200: Based on a reference attachment point in the historical model data set, facial bone data is matched with the historical model data set for facial bone information, and a simulated attachment point of the facial bone data is obtained.

[0029] The bone model data serves as a support structure in the process of constructing a soft tissue model, and therefore, the generation of the soft tissue model can be realized by matching the known bone model data of the current patient and the sampling specimens. The purpose of the matching is to align the acquired bone model data due to the diversity of the morphology of the collected bone model data, and the matching process can be completed by aligning the key points in the bone model data in terms of mechanics.

[0030] Based on the above analysis, in some embodiments of the present application, based on a reference attachment point in the historical model data set, facial bone data is matched with the historical model data set for facial bone information, and a simulated attachment point of the facial bone data is obtained. Further, it includes: First, the reference attachment point in the historical model data set is acquired. Specifically, the historical model data is removed from other interference conditions in the historical model data by semantic segmentation, and the historical bone model is acquired. Then, the mechanical point data (the mechanical point is also called an attachment point, and the annotation of the mechanical point is necessary knowledge of anatomical dissection for medical students) on the historical bone model is acquired by manual annotation, and the reference attachment point of the historical bone model is obtained, such as Figure 2 and Figure 3The historical model data set is analyzed according to the above operation, and the historical skeletal model and the reference attachment point of each historical model data in the historical model data set are obtained.

[0031] Meanwhile, based on the facial skeletal data, the current skeletal model of the current patient is constructed. Specifically, the facial skeletal data of the current patient is matched with all the historical skeletal models in the historical model data set, the skeletal network information of the current patient is obtained, and the skeletal network information is filtered by using a smoothing filter to remove noise but keep the boundary clear, so that the current skeletal model of the current patient can be obtained.

[0032] Then, since the current skeletal model of the current patient is obtained by using an artificial labeling method, the efficiency is low, and the requirement for doctors is high, so it is necessary to automatically label by using the historical model data set as a reference template. Therefore, in some embodiments of the present application, the current skeletal model is registered with the historical skeletal models in the historical model data set, and the reference attachment points in the historical model data set are mapped to the current skeletal model to obtain the inherited mapping points of the current skeletal model. Specifically, the position and scale of the current skeletal model of the current patient are aligned with each historical skeletal model in the historical template data set by using rigid registration (ICP algorithm); and then the historical skeletal model is deformed to the shape of the current skeletal model by using non-rigid deformation registration, at this time the attachment point or attachment region label of each historical skeletal model in the historical template data set is mapped to the current skeletal model by registration deformation, then the attachment point of the current skeletal model is automatically inherited from the historical skeletal model, and the inherited mapping points of the current skeletal model are obtained without artificial labeling.

[0033] Then, the reference degree of the reference attachment points in the historical model data set is analyzed. Specifically, based on the reference attachment points in the historical model data set, any two-to-two matching of the historical model data corresponding to different sampling specimens in the historical model data set is performed by projection, and different morphological sample data can be aligned by this method. At the same time, the matching times of each reference attachment point (in the matching process of a certain historical model data and any other historical model data, the reference attachment point in the historical model data can be matched successfully with the reference attachment point in the other historical model data) are obtained, that is, the matching times of the reference attachment point corresponding to each inherited mapping point are obtained. Further, according to the matching times, the number of sampling specimens in the historical model data set is combined to obtain the reference degree of the reference attachment point corresponding to the inherited mapping point. And the reference degree of the reference attachment point corresponding to the inherited mapping point In the first historical model data, the reference degree calculation formula of the reference attachment point corresponding to the inherited mapping point is: In the formula, represents the inherited mapping point in the first historical model data corresponding to the reference attachment point ; represents the inherited mapping point in the first historical model data corresponding to the reference attachment point ; represents the number of times that the inherited mapping point in the first historical model data corresponding to the reference attachment point ; represents the number of times that the inherited mapping point in the first historical model data corresponding to the reference attachment point ;

[0034] represents the number of historical model data (sample specimens) in the historical model data set. In the formula, represents the confidence of the inherited mapping point ; represents the reference degree of the inherited mapping point in the first historical model data corresponding to the reference attachment point ; represents the bone curvature of the current bone model position of the inherited mapping point ; represents the bone curvature average value of all reference attachment point corresponding positions in the historical model data matched with the position of the inherited mapping point ; represents the inherited mapping point a bone normal vector at the current skeletal model position; a bone normal vector at the position of the reference attachment point matched with the inheritance mapping point a mean value of bone normal vectors at positions of all reference attachment points matched with the inheritance mapping point denotes a vector denotes an angle between a vector denotes a vector denotes a sine value of an angle between a vector denotes a vector denotes a sine value of an angle between a vector denotes an exponential function with a natural constant as a base; denotes taking an absolute value; denotes taking a modulus length value of a vector.

[0035] denotes a difference degree of bone curvatures at positions of the inheritance mapping point and the reference attachment point, the smaller the value is, the more similar the bone curvatures at positions of the inheritance mapping point and the reference attachment point are, and the higher the credibility of the inheritance mapping point is; denotes a difference degree of bone normal vectors at positions of the inheritance mapping point and the reference attachment point, the smaller the value is, the more similar the bone normal vectors at positions of the inheritance mapping point and the reference attachment point are, and the higher the credibility of the inheritance mapping point is.

[0036] Finally, a preset credibility threshold is set, and a simulated attachment point of the facial skeletal data is obtained according to the credibility. Specifically, the preset credibility threshold is 0.8, the inheritance mapping points are screened according to the credibility of the inheritance mapping points, and the inheritance mapping points with a credibility greater than the credibility threshold are set as the simulated attachment points of the facial skeletal data of the current patient, that is, the corresponding inheritance mapping points are set as the simulated attachment points of the facial skeletal data of the current patient.

[0037] At this point, the simulated attachment points of the facial skeletal data of the current patient are obtained.

[0038] The step S200 completes the matching of the patient's bone model and the bone model in the historical model data set. When further constructing the soft tissue model of the current patient by using the distribution of the soft tissue attached to the bone in the historical model data set, the differences between different populations (different sampling specimens) also need to be considered, such as the differences in their scales (there may be certain differences in the size between each soft tissue). Therefore, the reference attachment points of the historical bone model and the simulation attachment points of the current bone model can be used to respectively construct finite element data blocks, and then based on the distribution of various soft tissues in the finite element data blocks in the historical model data set, the probability distribution of various soft tissues in the finite element data blocks is analyzed, the finite element data blocks are segmented and combined, and the size of the finite element data blocks is reconstructed, so that the distribution of the obtained soft tissue model is more fine. Specifically, it includes steps S300 to S600.

[0039] S300: Based on the simulation attachment points and the reference attachment points, respectively construct the current finite element data block and the reference finite element data block, and obtain the corresponding reference finite element data block of the current finite element data block.

[0040] Based on the simulation attachment points and the reference attachment points, respectively construct the current finite element data block and the reference finite element data block, and obtain the corresponding reference finite element data block of the current finite element data block, further including: First, the facial surface data of the current patient is obtained. The specific method of obtaining the facial surface data has been described in detail in step S100, which will not be repeated here. Further, the soft tissue domain between the facial bone data and the facial surface data of the current patient is obtained, wherein the soft tissue domain refers to the skin, fat, muscle, blood vessels, nerves and connective tissue covering the facial bone. Specifically, a 3D model import library (such as assimp) can be used to import and process 3D model data (facial bone data and facial surface data) to obtain the soft tissue domain, and the prior art will not be repeated here.

[0041] Then, taking the simulation attachment points in the current bone model of the current patient as the starting point, 128 128 128 (preset, need to be set to a cube) size of the current finite element data block is constructed, and the soft tissue domain between the facial bone data and the facial surface data is segmented by the current finite element data block, and the number of current finite element data blocks is obtained.

[0042] Simultaneously, starting from the reference attachment point in the historical skeletal model of the sampled specimen, and using the number of current finite metadata blocks as the segmentation number, the soft tissue domain in the historical model dataset is segmented to obtain reference finite metadata blocks; that is, when segmenting the soft tissue domain in the historical model dataset, the number of reference finite metadata blocks after final segmentation is the same as the number of current finite metadata blocks. The size of the reference finite metadata blocks needs to be changed according to the registration situation between the current skeletal model and the historical skeletal model in step S100, that is, the size of each reference finite metadata block is not the same and is not the same as the size of the current finite metadata block.

[0043] Then, by using attachment point matching (data blocks are segmented by attachment points), the current finite metadata block and the reference finite metadata block are matched one by one according to the positional relationship between the two golden attachment points of the data blocks to obtain the corresponding reference finite metadata block of the current finite metadata block.

[0044] S400: Analyze the distribution of various soft tissues in the corresponding reference finite metadata block to obtain the distribution probability set of various soft tissues in the current finite metadata block.

[0045] The distribution of various soft tissues in the corresponding reference finite data block is analyzed to obtain the probability set of various soft tissue distributions in the current finite data block. Specifically, this includes: First, obtaining the reference volume of the reference finite data block, and annotating the soft tissue structures in the historical soft tissue model using prior anatomical knowledge. The annotated soft tissue structures include the frontalis muscle, orbicularis oculi muscle, dorsum nasalis muscle, alar expander muscle, masseter muscle, levator labii superioris muscle, depressor labii superioris muscle, mandibular muscle, corrugator supercilii muscle, temporalis muscle, levator nasal septum muscle, suprazygomaticus major muscle, infrazygomaticus major muscle, orbicularis oris muscle, buccinator muscle, platysma muscle, sternocleidomastoid muscle, and trapezius muscle. Then, the type names and corresponding volumes of various soft tissues in the reference finite data block are obtained, denoted as the reference tissue volume. Next, based on the reference tissue volume and the reference volume, the volume distribution of various soft tissues in the reference finite data block corresponding to the current finite data block is analyzed to obtain the probability set of various soft tissue distributions in the current finite data block. The construction of the first... In the current finite metadata block, the first The formula for calculating the probability distribution of a soft tissue is: In the formula, Indicates the first In the current finite metadata block, the first The probability distribution of each soft tissue; This indicates the number of historical model data (samples) in the historical model dataset; Indicates the first In the current finite metadata block, the first a soft tissue in the first reference volume of a corresponding reference finite element data block (corresponding reference finite element data block) in the historical model data corresponding to the soft tissue in the first reference volume of a corresponding reference finite element data block (corresponding reference finite element data block) in the historical model data corresponding to the soft tissue in the first reference volume of a corresponding reference finite element data block (corresponding reference finite element data block) in the historical model data corresponding to the soft tissue in the first reference volume of a corresponding reference finite element data block (corresponding reference finite element data block) in the historical model data corresponding to the soft tissue in the first

[0046] By analyzing the proportion of the material volume (the proportion of the soft tissue volume to the total volume) of the corresponding reference finite element data block corresponding to the current finite element data block in the historical model data set, the proportion of the corresponding soft tissue in the current finite element data block can be determined, that is, the probability information of the existence of other materials in the current finite element data block is determined, and when the is closer to 1, it indicates that the segmentation effect of the current finite element data block is good, and the material content in the current finite element data block is relatively accurate.

[0047] Similarly, according to the above operation, the probability distribution of various soft tissues contained in the first current finite element data block can be quantified, and a distribution probability set of various soft tissues in the first current finite element data block is obtained, denoted as Similarly, the distribution probability set corresponding to all current finite element data blocks of the current patient is obtained.

[0048] S500: Based on the distribution probability set, the current finite element data block is segmented to obtain a plurality of sub-finite element data blocks and sub-distribution probability sets.

[0049] After obtaining the distribution probability set corresponding to all current finite element data blocks of the current patient, the current finite element data block is segmented based on the distribution probability set to obtain a plurality of sub-finite element data blocks and sub-distribution probability sets. Specifically, first, the maximum probability in the distribution probability set is obtained, denoted as , and a probability threshold (the value can be 0.85) is preset; then it is judged whether the maximum probability is less than the probability threshold; if yes, that is, , it is judged that the segmentation effect of the current finite element data block is poor, so the current finite element data block is segmented, that is, the current finite element data block is divided into two; then the distribution probability set of various soft tissues in the segmented current finite element data block is re-obtained (the obtaining method is the same as step S400), and the probability threshold judgment is continued, and the finite element data block that does not satisfy the probability threshold is continuously segmented until the segmentation operation is stopped after satisfying the probability threshold.

[0050] Through the above segmentation operation, the soft tissue body region of the current patient can be segmented into sub-finite element data blocks of different sizes, and each sub-finite element data block has a distribution probability of various substances, that is, a plurality of sub-finite element data blocks corresponding to the current patient and a sub-distribution probability set corresponding to the sub-finite element data blocks are obtained.

[0051] S600: Based on the sub-distribution probability set, the soft tissue distribution consistency between the sub-finite element data block and all neighboring sub-finite element data blocks thereof is analyzed, the sub-finite element data block is merged, and a soft tissue model structure of the current patient is obtained.

[0052] The sub-finite element data block obtained by the step S500 also has a large amount of noise (caused by the diversity of the historical model data itself), and the segmented soft tissue body region of the current patient needs to be merged and removed. For example, there is a small fat tissue data block in the muscle tissue, and the current fat tissue data block may be noise. When the sub-finite element data block obtained after segmentation is merged and optimized, the consistency of the distribution of various tissues between the sub-finite element data block and the surrounding sub-finite element data block needs to be analyzed, and the loss when the merged sub-finite element data block is taken as a single tissue is also considered.

[0053] Based on the above analysis, in the embodiments of the present application, based on the sub-distribution probability set, the soft tissue distribution consistency between the sub-finite element data block and all neighboring sub-finite element data blocks thereof is analyzed, the sub-finite element data block is merged, and a soft tissue model structure of the current patient is obtained. Further, comprising: Firstly, based on the sub-distribution probability set, the information entropy of soft tissue distribution between the sub-finite element data block and all neighboring sub-finite element data blocks in the spatial eight neighborhoods of the sub-finite element data block is obtained, combined with the volume of the neighboring sub-finite element data blocks and the identity between the soft tissue in the neighboring sub-finite element data blocks and the soft tissue in the sub-finite element data block, to obtain the soft tissue distribution consistency between the sub-finite element data block and all neighboring sub-finite element data blocks. Specifically, based on the sub-distribution probability set, the information entropy of soft tissue distribution between the sub-finite element data block and all neighboring sub-finite element data blocks in the spatial eight neighborhoods of the sub-finite element data block is obtained; wherein the information entropy is a measure of the uncertainty of a discrete random variable, the greater the probability of an event occurring, the smaller the information entropy, and vice versa, the smaller the probability, the greater the entropy; the information entropy of soft tissue distribution here represents the discrete degree of soft tissue distribution between the sub-finite element data block and all neighboring sub-finite element data blocks, the greater the information entropy of soft tissue distribution, the greater the soft tissue distribution consistency, the greater the need to merge the sub-finite element data block with its neighboring sub-finite element data blocks; the smaller the information entropy of soft tissue distribution, the smaller the soft tissue distribution consistency. In addition, the greater the volume of the neighboring sub-finite element data blocks, the more likely it is that the larger organization is within the same organization, that is, the greater the soft tissue distribution consistency of the neighboring sub-finite element data blocks themselves; the identity between the soft tissue in the neighboring sub-finite element data blocks and the soft tissue in the sub-finite element data block, that is, whether the soft tissue in the neighboring sub-finite element data blocks is the same soft tissue data as the soft tissue in the current neighboring sub-finite element data block, which takes the value of 0 and 1, 0 represents not a kind of soft tissue, 1 represents the same kind of soft tissue, that is, the greater the identity between the soft tissue in the neighboring sub-finite element data blocks and the soft tissue in the sub-finite element data block, the greater the soft tissue distribution consistency between the sub-finite element data block and all neighboring sub-finite element data blocks. Therefore, by combining the information entropy of soft tissue distribution with the volume of the neighboring sub-finite element data blocks and the identity between the soft tissue in the neighboring sub-finite element data blocks and the soft tissue in the sub-finite element data block, the soft tissue distribution consistency between the sub-finite element data block and all neighboring sub-finite element data blocks is obtained. The soft tissue distribution consistency calculation formula between the first sub-finite element data block and all neighboring sub-finite element data blocks is constructed as follows: In the formula, S8i represents the soft tissue distribution consistency between the first sub-finite element data block and all neighboring sub-finite element data blocks in the spatial eight neighborhoods of the first sub-finite element data block; S8i represents the information entropy of soft tissue distribution between the first sub-finite element data block and all neighboring sub-finite element data blocks in the spatial eight neighborhoods of the first sub-finite element data block; N8i represents the number of all neighboring sub-finite element data blocks in the spatial eight neighborhoods of the first sub-finite element data block.​​​​​ Indicates the first The first of the sub-finite metadata blocks The volume of a finite number of neighborhood sub-metadata blocks; Indicates the first The finite metadata block and its first The soft organization distribution consistency among the finite metadata blocks of the neighborhood sub-domains (its value is 0 or 1, where 0 indicates that they are not the same type of soft organization, i.e., the soft organization distribution is inconsistent; and 1 indicates that they are the same type of soft organization, i.e., the soft organization distribution is consistent). This represents the linear normalization function.

[0054] Based on the consistency of soft tissue distribution, sub-finite data blocks are merged, and an information entropy threshold is set to limit the merging process, resulting in the current patient's soft tissue model structure. Specifically, a consistency threshold (which can be 0.6) is preset, and sub-finite data blocks with soft tissue distribution consistency greater than the consistency threshold are merged with all neighboring sub-finite data blocks within their eight spatial neighborhoods. Furthermore, to avoid excessive merging leading to the loss of noise information, an information entropy threshold (which can be 0.8) is set, and the normalized information entropy of various soft tissue probabilities within each merged finite data block is calculated (the information entropy is normalized). Merged finite data blocks with an information entropy greater than the information entropy threshold are not merged.

[0055] Based on the above operations, the segmented finite metadata blocks can be merged and removed to obtain the mesh structure of the current patient's soft tissue. The mesh structure of the soft tissue can be simulated using existing algorithms such as meshlab (Mesh Laboratory) and DiffTaichi (differentiable programming for physical simulation) to obtain the soft tissue model structure of the current patient.

[0056] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for generating a maxillofacial soft tissue model for the orthodontic process, characterized in that, The method includes: Obtain the current patient's facial bone data and historical model dataset; Based on the reference attachment points in the historical model dataset, the facial bone data is matched with the facial bone information in the historical model dataset to obtain the simulated attachment points of the facial bone data. Based on the simulated attachment point and the reference attachment point, a current finite metadata block and a reference finite metadata block are constructed respectively, and the corresponding reference finite metadata block of the current finite metadata block is obtained; Analyze the distribution of various soft tissues in the corresponding reference finite metadata block to obtain the distribution probability set of various soft tissues in the current finite metadata block; Based on the set of probability distributions, the current finite metadata block is divided to obtain several sub-finite metadata blocks and sub-sets of probability distributions; Based on the sub-distribution probability set, the consistency of soft tissue distribution between the sub-finite metadata block and all its neighboring sub-finite metadata blocks is analyzed, and the sub-finite metadata blocks are merged to obtain the soft tissue model structure of the current patient.

2. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Based on the reference attachment points in the historical model dataset, the facial bone data is matched with the facial bone information in the historical model dataset to obtain the simulated attachment points of the facial bone data, including: Based on the facial bone data, a current bone model of the current patient is constructed; The current skeleton model is registered with the historical skeleton model in the historical model dataset, and the reference attachment points in the historical model dataset are mapped to the current skeleton model to obtain the inheritance mapping points of the current skeleton model. Analyze the referenceability of the reference attachment point corresponding to the inherited mapping point; The shape feature matching degree between the inherited mapping point and the reference attachment point is analyzed, and the reliability of the inherited mapping point is obtained by combining the referenceability degree. A preset confidence threshold is used to obtain the simulated attachment points of the facial bone data based on the confidence level.

3. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 2, characterized in that, Analyzing the referability of the reference attachment point corresponding to the inherited mapping point includes: Based on the reference attachment points in the historical model dataset, the historical model data corresponding to different sampled specimens in the historical model dataset are matched to obtain the number of times the reference attachment points are matched for each inherited mapping point. Based on the number of matching occurrences and the number of sampled specimens in the historical model dataset, the referenceability of the reference attachment point corresponding to the inherited mapping point is obtained.

4. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 2, characterized in that, Analyzing the shape feature matching degree between the inherited mapping point and the reference attachment point includes: By analyzing the degree of difference in bone curvature and bone normal vector between the inherited mapping point and the reference attachment point, the shape feature matching degree between the inherited mapping point and the reference attachment point is obtained.

5. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Based on the simulated attachment point and the reference attachment point, a current finite metadata block and a reference finite metadata block are constructed respectively, and the corresponding reference finite metadata block of the current finite metadata block is obtained, including: Obtain the current patient's facial surface data; Starting from the simulated attachment point, a current finite metadata block is constructed. The soft tissue domain between the facial bone data and the facial surface data is segmented using the current finite metadata block to obtain the number of the current finite metadata blocks. Starting from the reference attachment point and using the number of current finite metadata blocks as the segmentation number, the soft tissue domain in the historical model dataset is segmented to obtain the reference finite metadata blocks; The current finite metadata block and the reference finite metadata block are matched one by one to obtain the corresponding reference finite metadata block of the current finite metadata block.

6. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Analyzing the distribution of various soft tissues in the corresponding reference finite metadata block yields a set of distribution probabilities for various soft tissues in the current finite metadata block, including: Obtain the reference volume of the reference finite metadata block and the reference tissue volume of various soft tissues in the reference finite metadata block; Based on the reference tissue volume and the reference volume, the volume distribution of various soft tissues in the reference finite metadata block corresponding to the current finite metadata block is analyzed to obtain the distribution probability set of various soft tissues in the current finite metadata block.

7. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Based on the aforementioned probability distribution set, the current finite metadata block is segmented to obtain several sub-finite metadata blocks and sub-probability distribution sets, including: Obtain the maximum probability in the set of probability distributions; Preset probability threshold; Determine whether the maximum probability is less than the probability threshold; If so, the current finite metadata block is divided into two. The distribution probability set of various soft tissues in the segmented current finite metadata block is re-acquired, and the probability threshold judgment is continued. The finite metadata block that does not meet the probability threshold is further segmented until the probability threshold is met, and then the segmentation operation is stopped, resulting in several sub-finite metadata blocks and the sub-distribution probability set corresponding to the sub-finite metadata blocks.

8. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Based on the sub-distribution probability set, the consistency of soft tissue distribution between the sub-finite metadata block and all its neighboring sub-finite metadata blocks is analyzed. The sub-finite metadata blocks are then merged to obtain the soft tissue model structure of the current patient, including: Based on the sub-distribution probability set, the information entropy of the soft tissue distribution between the sub-finite metadata block and all its neighboring sub-finite metadata blocks is obtained. Combining the volume of the neighboring sub-finite metadata block and the identity between the soft tissue in the neighboring sub-finite metadata block and the soft tissue in the sub-finite metadata block, the consistency of the soft tissue distribution between the sub-finite metadata block and all its neighboring sub-finite metadata blocks is obtained. Based on the consistency of the soft tissue distribution, the sub-finite metadata blocks are merged, and an information entropy threshold is set to limit the merging, so as to obtain the soft tissue model structure of the current patient.

9. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, Obtain the historical model dataset, including: Historical maxillofacial soft tissue data of the sampled specimens were obtained using MBI technology; Historical facial bone data of the sampled specimens were obtained using CBCT technology. Historical facial surface data of the sampled specimens were obtained using 3D technology. Based on the historical maxillofacial soft tissue data, the historical facial bone data, and the historical facial surface data, a historical model dataset of the sampled specimens is obtained.

10. The method for generating a maxillofacial soft tissue model for the orthodontic process according to claim 1, characterized in that, The method for obtaining reference attachment points in the historical model dataset includes: By semantic segmentation, the historical skeletal model of each historical model data in the historical model dataset is obtained; Reference attachment points on the historical skeletal model are obtained through manual annotation.

Images