Correcting target position generation method and system based on craniomaxillofacial skeleton coordination

Abstract

The invention relates to the technical field of crossing of orthodontics and digital medical treatment, and provides an orthodontic target position generation method based on cranio-maxillofacial skeleton harmony, which comprises the following steps: S1, acquiring multi-modal oral data of a patient, performing registration fusion, and constructing a three-dimensional integrated virtual model containing jaw bones and teeth; s2, performing bone form quantitative analysis, and automatically identifying the bone type and main bony limitation characteristics of the patient; s3, on the basis of the skeleton constraint conditions, solving and generating an individualized skeleton coordination correction target position matched with the skeleton form of the patient through a preset coordination degree evaluation function and a multi-objective optimization algorithm; s4, presenting the individualized bone coordination correction target position and an analysis basis through a visual interaction interface; and S5, by taking the confirmed individualized bone coordination correction target position as a reference, finishing tooth movement sequence planning of invisible correction and correction related component design. The defect of excessive or improper compensation caused by neglecting the skeleton basis in the prior art is overcome.

Description

Technical Field

[0001] This invention relates to the technical field of intersection between orthodontics and digital medicine, and particularly to a method and system for generating treatment target positions based on the coordination of craniofacial skeleton. By using the patient's inherent craniofacial skeletal morphology as an immutable framework, and calculating the "optimal compensatory position" of the teeth within this framework, an invisible orthodontic system and design scheme that generates individualized treatment target positions that balance aesthetics, function, and long-term stability can be generated. Background Technology

[0002] In the field of orthodontics, with the rapid development of digital technology, invisible orthodontics, with its unique advantages such as aesthetics, comfort, and removability, has become the preferred treatment method for an increasing number of patients with dental malocclusions. Digital invisible orthodontic technology is also gradually becoming a core application direction for the deep integration of orthodontics and digital medicine. The design of the treatment target position, as the core link in the formulation of the invisible orthodontic treatment plan, directly determines the final treatment effect due to its scientific validity and rationality. It not only relates to the alignment of teeth and the restoration of occlusal function, but also to the optimization of facial aesthetics and the long-term stability of treatment results, making it crucial to ensuring the clinical efficacy of invisible orthodontics. Currently, the target position design of existing digital invisible orthodontic technologies mainly follows two mainstream paradigms, but both have significant limitations.

[0003] The first approach is the standardized ideal dental arch paradigm. The core idea of ​​this paradigm is to align and adjust the patient's dentition towards a pre-existing "ideal" dental arch shape or occlusal relationship (such as Class I occlusion). Its key drawback is that it completely ignores the patient's unique skeletal foundation. For cases with significant skeletal discrepancies, such as Class II convex or Class III concave profiles, forcibly pursuing a pre-defined ideal dental relationship often results in overcompensation of the teeth. This overcompensation can easily lead to a series of clinical problems, including alveolar bone fracture and gingival recession. This not only leads to a lack of long-term stability in treatment results but may also cause facial aesthetic imbalance, affecting the patient's overall facial harmony.

[0004] The second approach is the technician experience-driven paradigm, which relies on the personal clinical experience of digital designers (technicians) for visual tooth alignment. Due to the lack of quantitative analysis methods for assessing patient skeletal limitations, the entire design process is highly subjective; different technicians may arrive at significantly different designs for the same patient, resulting in poor repeatability. More importantly, this experience-based approach struggles to scientifically define the "biomechanical safety boundaries" of tooth movement, failing to provide precise safety guidance for tooth repositioning.

[0005] A thorough analysis of existing technologies reveals a fundamental flaw: they fail to correctly understand the intrinsic connection between teeth and the skeletal base, treating teeth as individuals capable of arranging themselves freely independent of their skeletal base. Consequently, they fail to establish a quantitative coordination relationship between the "target tooth position" and the "host skeletal morphology." This core deficiency directly leads to inherent shortcomings in treatment plans designed with existing technologies: either they are not biomechanically feasible, with tooth movement exceeding the physiological limits of the bone, causing various tissue damages; or they are aesthetically and stably unacceptable, even if short-term tooth alignment is achieved, long-term stability is difficult to maintain, and the natural aesthetic form of the face may be disrupted, failing to meet patients' core demands for treatment effectiveness. Summary of the Invention

[0006] To address the aforementioned problems, the present invention aims to provide a method and system for generating orthodontic target positions based on craniofacial skeletal coordination, overcoming the shortcomings of existing technologies that neglect the skeletal basis, leading to over- or under-compensation. By establishing a quantitative coordination model of tooth position and skeletal morphology, within the patient's inherent skeletal framework, the "optimal tooth alignment target position" is found that maximizes improvement in occlusion and facial profile while conforming to biomechanical limits and ensuring long-term stability.

[0007] The above-mentioned objective of this invention is achieved through the following technical solutions: A method for generating orthodontic target positions based on craniofacial skeletal coordination includes the following steps: S1: Acquire multimodal oral data of patients and perform registration and fusion to construct a three-dimensional integrated virtual model including jawbone and teeth; S2: Perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model to automatically identify the patient's bone type and main bony limiting features; S3: Based on skeletal constraints, the system uses a pre-defined coordination evaluation function and a multi-objective optimization algorithm to generate an individualized skeletal coordination correction target position that matches the patient's skeletal morphology. S4: The individualized skeletal coordination correction target position and analysis basis are presented through a visual interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results; S5: Based on the confirmed individualized skeletal coordination treatment target position, complete the planning of the tooth movement sequence for invisible orthodontics and the design of orthodontic-related components.

[0008] Further, in step S1, multimodal oral data of the patient is acquired and registered and fused to construct a three-dimensional integrated virtual patient model including the jawbone and teeth, specifically: The patient's CBCT data and high-precision intraoral scan data are imported simultaneously, and a multimodal data registration algorithm is used to accurately align the two types of data, eliminating spatial deviations that may occur during data acquisition. Using medical image segmentation technology, the three-dimensional model of the jawbone and the three-dimensional structure of the temporomandibular joint are accurately extracted from the registered CBCT data. The three-dimensional model of the jawbone completely includes the alveolar bone contour, the morphology of the basal bone arch, and key bony landmarks including the orbital point, the root of the nose, and the mental point. The digital model of the teeth obtained from high-precision intraoral scan data is precisely registered to its corresponding alveolar socket based on the principle of anatomical positioning. The spatial position association between the jawbone and the teeth is realized through data fusion technology, and finally a three-dimensional integrated virtual patient model of teeth and jawbone is constructed. This model can completely restore the anatomical structure and spatial correspondence of the patient's craniofacial bones and teeth.

[0009] Further, in step S2, the skeletal morphology of the three-dimensional integrated virtual model is quantitatively analyzed to automatically identify the patient's bone type and main bony limiting features, specifically: Based on the completed three-dimensional integrated virtual patient model, an automated three-dimensional cephalometric analysis algorithm is launched. Through the precise identification and positioning of the craniofacial skeletal anatomy in the model, multiple key skeletal parameters are automatically calculated. These key skeletal parameters include core indicators such as ANB angle, Wits value, mandibular plane angle, alveolar bone thickness, and dental arch base width. Based on the key bone parameter data obtained by quantification, a preset bone type classification model is invoked. This model is trained and optimized on massive clinical bone data to automatically classify the patient's bone type into specific types including bone type I, type II high angle, and type III low angle. Simultaneously, by combining the numerical deviation ranges and interrelationships of the key skeletal parameters, the feature recognition algorithm accurately captures abnormal information in the development of the patient's craniofacial skeleton, automatically identifying major skeletal limiting features, including maxillary hypoplasia, mandibular overprotrusion, and abnormal vertical height, providing precise skeletal constraint basis for subsequent target location generation.

[0010] Further, in step S3, the coordination evaluation function is a mathematical function constructed through multi-dimensional feature fusion, used to quantitatively evaluate the degree of adaptation between any virtual tooth arrangement scheme and the host skeletal framework. The specific construction process is as follows: The core evaluation dimensions of mathematical functions should be clearly defined, including at least quantitative evaluation indicators of the root-bone relationship and crown-bone relationship for each tooth, while also incorporating the functional space adaptability evaluation dimension. The evaluation indicators of the root-bone relationship specifically include the three-dimensional spatial position of each tooth root in the alveolar bone, the axial angle of the tooth root, and the minimum distance between the tooth root surface and the surrounding cortical bone. The safe boundary standard for the tooth root is set as ≥1mm from the root apex to the cortical bone and the tooth root located in the center of the cancellous bone. The specific evaluation index for the crown-bone relationship is whether the labial / buccal-lingual inclination of the crown relative to the basal bone is within the physiological compensation range. The evaluation index of functional space adaptability is whether the tooth arrangement is coordinated with the inherent oral functional space determined by the skeletal relationship. The inherent oral functional space includes key functional areas such as the tongue movement space and airway gaps. The coordination between tooth arrangement and skeletal framework is accurately quantified through multi-dimensional evaluation mathematical functions.

[0011] Furthermore, in step S3, the skeletal constraint conditions are obtained by direct measurement based on the patient's CBCT data, specifically including at least one of alveolar bone thickness, basal arch width, and jawbone spatial relationship, forming an unbreakable hard constraint of skeletal coordination. The multi-objective optimization algorithm is based on the hard constraints of skeletal coordination. Its optimization objectives include maximizing the improvement of occlusal contact, optimizing the aesthetic guidance effect of anterior teeth, and minimizing the total tooth movement distance. Specifically, maximizing the improvement of occlusal contact is reflected in increasing the intercuspal area of ​​posterior teeth. One or more Pareto optimal solutions are obtained by solving a multi-objective optimization algorithm. The optimal solution is the individualized skeletal coordination orthodontic target position that conforms to the patient's skeletal characteristics. The target position is a functional occlusal state that is highly adapted to the patient's skeletal morphology, and is not necessarily Angle Class I relation.

[0012] Furthermore, in step S4, the individualized skeletal coordination correction target position and analysis basis are presented through a visual interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results, specifically: The visual interactive interface is a dedicated interface that integrates decision support and interactive adjustment functions. It adopts a multi-view side-by-side display mode, simultaneously presenting the patient's initial tooth position, the individualized skeletal coordination orthodontic suggested target position generated based on the skeletal coordination engine, and the traditional standardized ideal dental arch target position as a reference, so that doctors can intuitively compare the differences among the three. Visualization technology is used to visualize the basis of analysis, including a three-dimensional comparison of the tooth root position in the alveolar bone and an alveolar bone safety boundary warning mark. The alveolar bone safety boundary warning is achieved by highlighting high-risk areas that exceed physiological limits in red, providing a quantitative reference for doctors to assess the safety of the plan. The interface is set with compliant fine-tuning permissions, allowing physicians to make precise adjustments to the target position within the system's preset coordination envelope based on their clinical experience. During the adjustment process, the system calculates and provides feedback on the changes in coordination score in real time, ensuring that the fine-tuning operation does not exceed the adaptation constraints of the skeleton and teeth, while guaranteeing the coordination and stability of the target position.

[0013] Furthermore, in step S5, based on the confirmed individualized skeletal coordination treatment target position, the tooth movement sequence planning and treatment-related component design for invisible orthodontics are completed, specifically: Using the individualized skeletal coordination correction target position finally confirmed by the physician as the core benchmark, the target position-driven correction path planning process is initiated. By employing a reverse engineering planning algorithm, and combining the spatial position difference between the initial and target positions of the tooth, the skeletal constraint boundary, and the biomechanical principles of tooth movement, the complete movement trajectory of the tooth from the initial position to the target position is broken down step by step. A safe, efficient, and physiologically sound tooth movement sequence is planned in reverse, clearly defining the direction, distance, and priority of tooth movement at each step. Based on the planned tooth movement sequence and the anatomical requirements of the target position, the system automatically matches and generates the orthodontic components required to achieve the target position through parametric design technology. These orthodontic components include attachments to assist precise tooth movement and orthodontic appliances that conform to the tooth shape. Key parameters, including the type, installation position, shape and size of the attachments, and the curvature and thickness of the orthodontic appliances, are automatically optimized and designed by the system according to individualized skeletal and dental characteristics. This ensures that the attachments and appliances can accurately adapt to the patient's oral structure, provide continuous and stable orthodontic force for tooth movement, and guarantee the successful achievement of the final orthodontic goal.

[0014] A craniofacial skeleton-based orthodontic target position generation system for performing the above-described method for generating orthodontic target positions based on craniofacial skeleton coordination, comprising: The multimodal data fusion and skeletal framework extraction module is used to acquire patients' multimodal oral data and perform registration and fusion to construct a three-dimensional integrated virtual model including the jawbone and teeth. The skeletal morphology quantitative analysis and classification module is used to perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model and automatically identify the patient's bone type and main bony limiting features. The skeletal coordination target position generation engine module is used to solve and generate individualized skeletal coordination correction target positions that are adapted to the patient's skeletal morphology based on skeletal constraints, through a preset coordination degree evaluation function and a multi-objective optimization algorithm. The visualization decision support and interactive adjustment interface module is used to present the individualized skeletal coordination correction target position and analysis basis through a visualization interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results. The target-position driven orthodontic path planning module is used to complete the planning of tooth movement sequence and the design of orthodontic-related components for invisible orthodontics, based on the confirmed individualized skeletal coordination orthodontic target position.

[0015] A computer device, characterized in that it includes a memory and one or more processors, wherein the memory stores computer code, and when the computer code is executed by the one or more processors, causes the one or more processors to perform the method as described above.

[0016] 10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer code, which, when executed, performs the method described above.

[0017] Compared with the prior art, the present invention has at least one of the following beneficial effects: (1) Precision and scientific approach to treatment goals: Breakthrough in transforming the goal of invisible orthodontic treatment from the traditional subjective "ideal tooth arrangement" to the objective "optimal skeletal coordination" based on the anatomical features of the patient's craniofacial skeleton, so that the treatment plan is deeply rooted in the individual's unique anatomical reality, completely get rid of the limitations of the standardized paradigm, realize truly individualized medical treatment, and make the orthodontic goal more in line with the patient's physiological basis.

[0018] (2) Accurate prediction and effective avoidance of treatment risks: By establishing a quantitative assessment system for root-bone relationship, potential clinical risks such as root penetration of the cortical bone and alveolar bone cracking can be accurately predicted and warned during the orthodontic treatment design stage. This avoids tissue damage caused by unreasonable tooth movement from the source and greatly improves the biomechanical safety and clinical reliability of treatment.

[0019] (3) Significantly improve the long-term stability of treatment: With the highly coordinated and adaptive design of teeth and bone base, the teeth are eventually moved to a physiological position that naturally fits the soft and hard tissue environment, effectively reducing the tendency of teeth to relapse after orthodontic treatment, ensuring the long-term stability of treatment effect, and reducing the possibility of secondary orthodontic treatment.

[0020] (4) Optimize facial aesthetic presentation: The optimal compensatory design is carried out within the patient's inherent skeletal limits, avoiding the problem of facial aesthetic imbalance caused by forcibly pursuing an ideal dental arch. It can achieve a more harmonious, natural facial profile that conforms to individual characteristics, completely eliminating the embarrassing treatment result of "needles are straight but facial shape is strange", and realizing the synergistic optimization of tooth arrangement and facial aesthetics.

[0021] (5) Strong support for precise clinical decision-making: It provides orthodontists with a powerful decision-making tool that combines quantitative analysis and visualization support. In particular, when distinguishing the applicable boundaries of "simple orthodontic compensation treatment" and "orthodontic-orthognathic combined treatment", it can provide objective and accurate quantitative evidence to help doctors formulate more targeted optimal treatment plans and improve the efficiency of clinical diagnosis and treatment and the scientific nature of decision-making. Attached Figure Description

[0022] Figure 1 This is an overall flowchart of the method for generating treatment target positions based on craniofacial skeletal coordination according to the present invention; Figure 2 This is a schematic diagram of a case of maxillary hypoplasia, mandibular protrusion, and Angle Class III reverse occlusion according to the present invention; Figure 3 This is a schematic diagram of the target position for the coordination of the dental arch and skeleton in this invention; Figure 4 This is a schematic diagram illustrating how the target position of the jawbone was forcibly arranged into a Class I position, exceeding the physiological limits of the jawbone. Figure 5 This is a diagram of the overall structure of the orthodontic target position generation system based on craniofacial skeletal coordination of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0025] First Embodiment like Figure 1 As shown, this embodiment provides a method for generating treatment target positions based on craniofacial skeletal coordination, including the following steps: S1: Acquire multimodal oral data from patients and perform registration and fusion to construct a three-dimensional integrated virtual model including the jawbone and teeth.

[0026] In this embodiment, step S1 specifically includes: The patient's CBCT data and high-precision intraoral scan data are imported simultaneously, and a multimodal data registration algorithm is used to accurately align the two types of data, eliminating spatial deviations that may occur during data acquisition. Using medical image segmentation technology, the three-dimensional model of the jawbone and the three-dimensional structure of the temporomandibular joint are accurately extracted from the registered CBCT data. The three-dimensional model of the jawbone completely includes the alveolar bone contour, the morphology of the basal bone arch, and key bony landmarks including the orbital point, the root of the nose, and the mental point. The digital model of the teeth obtained from high-precision intraoral scan data is precisely registered to its corresponding alveolar socket based on the principle of anatomical positioning. The spatial position association between the jawbone and the teeth is realized through data fusion technology, and finally a three-dimensional integrated virtual patient model of teeth and jawbone is constructed. This model can completely restore the anatomical structure and spatial correspondence of the patient's craniofacial bones and teeth.

[0027] This step, through the integration and precise modeling of multimodal data, lays a solid foundation for subsequent skeletal analysis and target location generation: CBCT data (cone-beam CT) has excellent bone structure penetration and three-dimensional imaging capabilities, and can completely capture the anatomical details of hard tissues such as the jawbone and temporomandibular joint. The key bony landmarks extracted by it are the core basis for quantitative analysis of bone morphology; while high-precision intraoral scan data can realistically restore soft tissue correlation features such as tooth surface morphology and tooth alignment. The complementarity of the two provides data support for "tooth-bone synergistic analysis". Alignment using a multimodal data registration algorithm effectively solves the spatial misalignment problem that may occur when data is collected from different devices, ensuring that the relative positional relationship between teeth and jawbone matches the patient's actual oral condition. The application of medical image segmentation technology enables the precise separation of target structures such as jawbone and temporomandibular joint from redundant data, ensuring the integrity and accuracy of the skeletal model. Finally, the registration and data fusion of teeth and alveolar sockets are completed through anatomical positioning principles. The constructed three-dimensional integrated virtual model breaks through the limitations of traditional tooth and bone data separation, forming a complete anatomical visualization scene with "teeth-jawbone-joint" linkage. This not only provides a high-precision data carrier for subsequent quantitative analysis of skeletal morphology, but also realizes the digital replication of the patient's craniofacial anatomy. This allows all subsequent model-based analyses, calculations, and treatment plans to be tailored to the individual physiological characteristics of the patient, ensuring the individualization and scientific nature of the orthodontic plan from the source.

[0028] S2: Perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model to automatically identify the patient's bone type and main bony limiting features.

[0029] In this embodiment, step S2 specifically includes: Based on the completed three-dimensional integrated virtual patient model, an automated three-dimensional cephalometric analysis algorithm is launched. Through the precise identification and positioning of the craniofacial skeletal anatomy in the model, multiple key skeletal parameters are automatically calculated. These key skeletal parameters include core indicators such as ANB angle, Wits value, mandibular plane angle, alveolar bone thickness, and dental arch base width. Based on the key bone parameter data obtained by quantification, a preset bone type classification model is invoked. This model is trained and optimized on massive clinical bone data to automatically classify the patient's bone type into specific types including bone type I, type II high angle, and type III low angle. Simultaneously, by combining the numerical deviation ranges and interrelationships of the key skeletal parameters, the feature recognition algorithm accurately captures abnormal information in the development of the patient's craniofacial skeleton, automatically identifying major skeletal limiting features, including maxillary hypoplasia, mandibular overprotrusion, and abnormal vertical height, providing precise skeletal constraint basis for subsequent target location generation.

[0030] This step, through automated and quantitative skeletal analysis, breaks through the limitations of traditional reliance on manual experience to judge skeletal features, providing an objective and accurate core basis for subsequent target location generation. The application of automated three-dimensional cephalometric analysis algorithms replaces the inefficiency and subjectivity of traditional manual or two-dimensional cephalometric measurements. By accurately identifying the craniofacial skeletal anatomy in the three-dimensional integrated model, it can quickly and accurately calculate key skeletal parameters such as the ANB angle and Wits value. These parameters comprehensively characterize the patient's basic skeletal features from different dimensions, including sagittal relationships, vertical growth patterns, and bone reserve, forming the core data support for skeletal morphology analysis. The pre-set skeletal type classification model, after being trained and optimized with massive amounts of clinical data, has high classification accuracy and can automatically classify skeletal types such as Class I and Class II high-angle skeletal types based on quantitative parameters, avoiding the experience bias of manual classification. Meanwhile, the feature recognition algorithm, by mining the numerical deviation patterns and correlation logic of various parameters, can accurately locate skeletal limiting features such as maxillary hypoplasia and mandibular overprotrusion, clarifying the "physiological boundaries" of tooth movement. The entire process realizes the transformation of skeletal features from "qualitative description" to "quantitative analysis". The output skeletal type and limiting features are not only hard constraints for the generation of subsequent target locations, but also ensure that the subsequent treatment plan can strictly adapt to the patient's skeletal anatomy, fundamentally avoiding problems such as overcompensation or ineffective treatment caused by inaccurate judgment of skeletal features.

[0031] S3: Based on skeletal constraints, the system uses a pre-defined coordination evaluation function and a multi-objective optimization algorithm to generate an individualized skeletal coordination correction target position that matches the patient's skeletal morphology.

[0032] In step S3, the coordination evaluation function is a mathematical function constructed through multi-dimensional feature fusion, used to quantitatively evaluate the degree of adaptation between any virtual tooth arrangement scheme and the host skeletal framework. The specific construction process is as follows: The core evaluation dimensions of mathematical functions should be clearly defined, including at least quantitative evaluation indicators of the root-bone relationship and crown-bone relationship for each tooth, while also incorporating the functional space adaptability evaluation dimension. The evaluation indicators of the root-bone relationship specifically include the three-dimensional spatial position of each tooth root in the alveolar bone, the axial angle of the tooth root, and the minimum distance between the tooth root surface and the surrounding cortical bone. The safe boundary standard for the tooth root is set as ≥1mm from the root apex to the cortical bone and the tooth root located in the center of the cancellous bone. The specific evaluation index for the crown-bone relationship is whether the labial / buccal-lingual inclination of the crown relative to the basal bone is within the physiological compensation range (such as the compensatory labial inclination limit of the maxillary anterior teeth in skeletal Class II). The evaluation index of functional space adaptability is whether the tooth arrangement is coordinated with the inherent oral functional space determined by the skeletal relationship. The inherent oral functional space includes key functional areas such as the tongue movement space and airway gaps. The coordination between tooth arrangement and skeletal framework is accurately quantified through multi-dimensional evaluation mathematical functions.

[0033] In step S3, the skeletal constraint conditions are obtained by direct measurement based on the patient's CBCT data, specifically including at least one of alveolar bone thickness, basal arch width, and jawbone spatial relationship, forming an unbreakable hard constraint of skeletal coordination. The multi-objective optimization algorithm is based on the hard constraints of skeletal coordination. Its optimization objectives include maximizing the improvement of occlusal contact, optimizing the aesthetic guidance effect of anterior teeth, and minimizing the total tooth movement distance. Specifically, maximizing the improvement of occlusal contact is reflected in increasing the intercuspal area of ​​posterior teeth. One or more Pareto optimal solutions are obtained by solving the multi-objective optimization algorithm. The optimal solution is the individualized skeletal coordination orthodontic target position that conforms to the patient's skeletal characteristics. The target position is a functional occlusal state that is highly adapted to the patient's skeletal morphology, and is not necessarily Angle Class I relation (for example, for patients with severe skeletal Class III, the target position may be an anterior tooth with moderate compensatory lingual inclination and a cusp-fossa lock of the posterior teeth that achieves a complete Class III relation).

[0034] This step, as the core innovation of this invention, achieves a fundamental shift from "standardized ideal" to "individualized fit" in orthodontic target position through a closed-loop design of "hard constraint setting - multi-dimensional evaluation - multi-objective optimization": First, the skeletal constraints such as alveolar bone thickness and basal arch width, directly extracted from the patient's CBCT data, constitute the insurmountable physiological boundary for tooth movement, eliminating unreasonable designs that exceed the bone's load-bearing capacity from the source and ensuring the biomechanical feasibility of the target position; Second, the coordination evaluation function establishes a quantitative standard for the degree of fit between tooth arrangement and skeletal framework by integrating three core dimensions: root-bone relationship, crown-bone relationship, and functional space adaptability. Among them, the safe boundary setting of the root-bone relationship (root tip ≥ 1mm from the cortical bone, tooth root located in the center of the cancellous bone) directly ensures the tissue safety of tooth movement, the physiological compensation range of the crown-bone relationship limits the facial abnormalities caused by excessive tilting, and the functional space adaptability evaluation ensures that basic oral functions such as chewing and breathing are not affected after orthodontic treatment. The three work together to achieve a precise depiction of the "skeleton-teeth" coordination relationship. Based on this, the multi-objective optimization algorithm takes "maximizing occlusal contact, optimizing anterior tooth aesthetics, and minimizing movement distance" as its core objectives. It solves the Pareto optimal solution within the hard constraints of the skeleton, which not only avoids the imbalance of the solution under the guidance of a single objective, but also generates functional occlusion states that are not necessarily Angle Class I based on the patient's skeletal characteristics. For example, it can formulate Class III coordinated target positions for patients with severe skeletal Class III, with moderate compensatory lingual tipping of the anterior teeth and cusp-fossa locking of the posterior teeth. In the end, it achieves the design of orthodontic target positions that are "safe and feasible, functionally appropriate, aesthetically harmonious, and individualized", which completely overcomes the defects of traditional techniques such as overcompensation and poor stability caused by ignoring the skeletal basis.

[0035] S4: The individualized skeletal coordination correction target position and analysis basis are presented through a visual interactive interface, which supports physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results.

[0036] In this embodiment, step S4 specifically includes: The visual interactive interface is a dedicated interface that integrates decision support and interactive adjustment functions. It adopts a multi-view side-by-side display mode, simultaneously presenting the patient's initial tooth position, the individualized skeletal coordination orthodontic suggested target position generated based on the skeletal coordination engine, and the traditional standardized ideal dental arch target position as a reference, so that doctors can intuitively compare the differences among the three. Visualization technology is used to visualize the basis of analysis, including a three-dimensional comparison of the tooth root position in the alveolar bone and an alveolar bone safety boundary warning mark. The alveolar bone safety boundary warning is achieved by highlighting high-risk areas that exceed physiological limits in red, providing a quantitative reference for doctors to assess the safety of the plan. The interface is set with compliant fine-tuning permissions, allowing physicians to make precise adjustments to the target position within the system's preset coordination envelope based on their clinical experience. During the adjustment process, the system calculates and provides feedback on the changes in coordination score in real time, ensuring that the fine-tuning operation does not exceed the adaptation constraints of the skeleton and teeth, while guaranteeing the coordination and stability of the target position.

[0037] This step, through an integrated design of "visual presentation - quantitative support - compliance fine-tuning," builds an efficient bridge between technical algorithms and clinical decision-making. It ensures the scientific validity of the solution while fully respecting the clinical experience of physicians. The innovative multi-view side-by-side display mode presents the initial tooth position, the suggested target position for skeletal coordination, and the traditional ideal dental arch target position simultaneously, allowing physicians to intuitively compare the core differences between different solutions and clearly perceive the advantages of the present invention in skeletal adaptability, avoiding the decision-making limitations caused by traditional single-solution displays. Meanwhile, the visual analysis basis, such as the three-dimensional position comparison diagram of the tooth root and the alveolar bone safety boundary warning of the high-risk area highlighted in red, transforms the abstract skeletal constraints and coordination data into concrete image information, providing physicians with an intuitive and quantitative reference for evaluating the safety and rationality of the solution, solving the problems of "difficult data interpretation and difficult risk prediction" in traditional solutions. Meanwhile, the system's preset "coordination envelope" defines a safe boundary for physicians' fine-tuning, ensuring that adjustments are always made within the constraints of bone and teeth compatibility, avoiding deviations from the individualized skeletal coordination core due to experience bias. Real-time feedback on coordination score changes allows physicians to dynamically grasp the impact of fine-tuning on the coordination of the plan, achieving a real-time closed loop of "adjustment-evaluation-optimization," ultimately achieving an organic integration of "objectivity of technical algorithms" and "subjectivity of clinical experience," which not only improves the efficiency of clinical decision-making but also further ensures the accuracy and safety of the orthodontic target position.

[0038] S5: Based on the confirmed individualized skeletal coordination treatment target position, complete the planning of the tooth movement sequence for invisible orthodontics and the design of orthodontic-related components.

[0039] In this embodiment, step S5 specifically includes: Using the individualized skeletal coordination correction target position finally confirmed by the physician as the core benchmark, the target position-driven correction path planning process is initiated. By employing a reverse engineering planning algorithm, and combining the spatial position difference between the initial and target positions of the tooth, the skeletal constraint boundary, and the biomechanical principles of tooth movement, the complete movement trajectory of the tooth from the initial position to the target position is broken down step by step. A safe, efficient, and physiologically sound tooth movement sequence is planned in reverse, clearly defining the direction, distance, and priority of tooth movement at each step. Based on the planned tooth movement sequence and the anatomical requirements of the target position, the system automatically matches and generates the orthodontic components required to achieve the target position through parametric design technology. These orthodontic components include attachments to assist precise tooth movement and orthodontic appliances that conform to the tooth shape. Key parameters, including the type, installation position, shape and size of the attachments, and the curvature and thickness of the orthodontic appliances, are automatically optimized and designed by the system according to individualized skeletal and dental characteristics. This ensures that the attachments and appliances can accurately adapt to the patient's oral structure, provide continuous and stable orthodontic force for tooth movement, and guarantee the successful achievement of the final orthodontic goal.

[0040] This step, as a crucial link connecting treatment goals and clinical implementation, ensures the safe and efficient implementation of individualized skeletal coordination treatment goals through a comprehensive "goal-oriented - scientific planning - precise adaptation" design. The goal-driven orthodontic path planning model completely overcomes the limitations of traditional "experience-based path design," using the skeletal coordination target position confirmed by the physician as the sole core benchmark. This ensures that all planning steps revolve around "achieving individualized adaptation goals," avoiding path deviation. The application of reverse engineering planning algorithms is highly innovative. By accurately calculating the spatial difference between the initial and target tooth positions, combined with skeletal constraint boundaries and the biomechanical principles of tooth movement, it breaks down the complex tooth movement process into orderly and controllable step-by-step trajectories, clearly defining the direction, distance, and priority of each step. This design not only ensures the physiological rationality of tooth movement but also minimizes damage to the alveolar bone and surrounding tissues during movement, achieving "safe and efficient" movement path planning. Furthermore, the automatic generation of orthodontic components driven by parametric design technology enables personalized customization of attachments and appliances. Based on the patient's unique skeletal and dental characteristics, the system precisely optimizes key parameters such as the type, installation location, shape, size, and curvature and thickness of the attachments and appliances. This ensures a perfect fit between the components and the patient's oral structure, providing not only continuous and stable corrective force but also improved wearing comfort. This avoids the problems of poor fit and low treatment efficiency associated with traditional standardized components. The entire process forms a closed-loop adaptation system of "target location - movement path - orthodontic components," fundamentally guaranteeing the successful achievement of the final orthodontic goal and ensuring that the concept of personalized medicine permeates every detail of the orthodontic plan implementation.

[0041] Second Embodiment This embodiment uses an adult patient diagnosed with severe skeletal Class III hypoplasia with mandibular prognathism as the treatment subject to specifically illustrate the implementation process of the invisible orthodontic target location generation method based on craniofacial skeletal coordination of the present invention. Figure 2 This is a schematic diagram of a case of maxillary hypoplasia, mandibular protrusion, and Angle Class III reverse occlusion according to the present invention.

[0042] 1. Data integration and model building The system first synchronously imports the patient's cone-beam computed tomography (CBCT) data and high-precision intraoral scan data. A multimodal data registration algorithm is used to accurately align the two types of data, eliminating potential spatial deviations during data acquisition. Subsequently, medical image segmentation technology is employed to extract a 3D model of the jawbone, a 3D structure of the temporomandibular joint, and a digital model of the teeth from the registered CBCT data, constructing an integrated 3D virtual patient model of teeth and bone. Based on this model, a quantitative analysis of skeletal morphology is performed. The results show that the patient's ANB angle is -2°, the mandibular plane angle is horizontal, and the alveolar bone thickness in the mandibular anterior region is relatively thin. These parameters provide core skeletal feature basis for subsequent target location generation.

[0043] 2. Target position generation engine running (1) Setting constraints Based on the patient's skeletal characteristics, the algorithm sets clear hard constraints: first, "the thickness of the labial bone plate of the mandibular anterior tooth root is always ≥0.8mm" to avoid alveolar bone damage caused by tooth movement; second, "the mesial tilt of the mandibular posterior teeth avoids further mandibular reverse rotation" to prevent deterioration of the vertical skeletal relationship and ensure that the target position conforms to the physiological limits of the skeleton.

[0044] (2) Multi-objective optimization calculation Under the premise of strictly meeting the above-mentioned skeletal constraints, the system initiates a multi-objective optimization algorithm with the core optimization objectives of "maximizing the retraction of the mandibular anterior teeth, establishing appropriate anterior tooth overlay, and achieving maximum functional contact of the posterior teeth" to iteratively calculate the virtual tooth alignment scheme and balance the safety, functionality, and aesthetics of tooth movement.

[0045] (3) Output results The system ultimately generates individualized "skeleton coordination target positions". Figure 3 This is a schematic diagram illustrating the target position for dentition and skeletal coordination in this invention. Specifically, this target position is characterized by: overall retraction of the mandibular anterior teeth within their maximum physiological limits (distinct from the orthodontic logic of traditional simple reverse occlusion correction), and to maintain root-bone coordination, their final labial inclination is more inward than the standardized "ideal" value; the maxillary dentition position remains basically stable, with a stable occlusal relationship constructed through fine-tuning of cusp inclination. The final result is not a forced pursuit of Angle Class I occlusion, but rather a coordinated Class III occlusion state that is highly adapted to the patient's skeletal morphology and functionally stable.

[0046] 3. Clinical decision support Physicians can use a visual interactive interface to directly compare the skeletal coordination target positioning scheme generated by this invention with the traditional scheme that forcibly arranges targets into Class I. Figure 4This diagram illustrates how the forced alignment of the teeth into Class I target positions exceeds the physiological limits of the jawbone. The system uses a safety boundary warning function to highlight high-risk areas in red, clearly indicating the risk that traditional Class I approaches would lead to significant penetration of the maxillary anterior tooth roots through the labial cortex. Based on this quantitative warning and the comparison results of different approaches, physicians can scientifically select skeletal coordination methods for orthodontic compensation treatment, or accurately determine whether the patient needs to be referred to orthognathic surgery for combined treatment, providing an objective and reliable basis for clinical decision-making.

[0047] Third Embodiment like Figure 5 As shown, this embodiment provides a craniofacial skeleton coordination-based orthodontic target position generation system for executing the craniofacial skeleton coordination-based orthodontic target position generation method as described in the first embodiment, comprising: The multimodal data fusion and skeletal framework extraction module is used to acquire patients' multimodal oral data and perform registration and fusion to construct a three-dimensional integrated virtual model including the jawbone and teeth. The skeletal morphology quantitative analysis and classification module is used to perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model and automatically identify the patient's bone type and main bony limiting features. The skeletal coordination target position generation engine module is used to solve and generate individualized skeletal coordination correction target positions that are adapted to the patient's skeletal morphology based on skeletal constraints, through a preset coordination degree evaluation function and a multi-objective optimization algorithm. The visualization decision support and interactive adjustment interface module is used to present the individualized skeletal coordination correction target position and analysis basis through a visualization interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results. The target-position driven orthodontic path planning module is used to complete the planning of tooth movement sequence and the design of orthodontic-related components for invisible orthodontics, based on the confirmed individualized skeletal coordination orthodontic target position.

[0048] A computer-readable storage medium stores computer code that, when executed, performs the methods described above. Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. This program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0049] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

[0050] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0051] It should be noted that the above embodiments can be freely combined as needed. The above description is only a preferred embodiment of the present invention. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for generating a target position of orthodontic treatment based on coordination of craniofacial bones, characterized by, Includes the following steps: S1: Acquire multimodal oral data of patients and perform registration and fusion to construct a three-dimensional integrated virtual model including jawbone and teeth; S2: Perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model to automatically identify the patient's bone type and main bony limiting features; S3: Based on skeletal constraints, the system uses a pre-defined coordination evaluation function and a multi-objective optimization algorithm to generate an individualized skeletal coordination correction target position that matches the patient's skeletal morphology. S4: The individualized skeletal coordination correction target position and analysis basis are presented through a visual interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results; S5: Based on the confirmed individualized skeletal coordination treatment target position, complete the planning of the tooth movement sequence for invisible orthodontics and the design of orthodontic-related components.

2. The method of claim 1, wherein the method further comprises: determining a target position of the craniofacial bone based on the coordination of the craniofacial bone. In step S1, multimodal oral data of the patient is acquired and registered and fused to construct a three-dimensional integrated virtual patient model including the jawbone and teeth, specifically: The patient's CBCT data and high-precision intraoral scan data are imported simultaneously, and a multimodal data registration algorithm is used to accurately align the two types of data, eliminating spatial deviations that may occur during data acquisition. Using medical image segmentation technology, the three-dimensional model of the jawbone and the three-dimensional structure of the temporomandibular joint are accurately extracted from the registered CBCT data. The three-dimensional model of the jawbone completely includes the alveolar bone contour, the morphology of the basal bone arch, and key bony landmarks including the orbital point, the root of the nose, and the mental point. The digital model of the teeth obtained from high-precision intraoral scan data is precisely registered to its corresponding alveolar socket based on the principle of anatomical positioning. The spatial position association between the jawbone and the teeth is realized through data fusion technology, and finally a three-dimensional integrated virtual patient model of teeth and jawbone is constructed. This model can completely restore the anatomical structure and spatial correspondence of the patient's craniofacial bones and teeth.

3. The method of claim 1, wherein the method further comprises: determining a target position of the craniofacial bone based on the coordination of the craniofacial bone. In step S2, the skeletal morphology of the three-dimensional integrated virtual model is quantitatively analyzed to automatically identify the patient's bone type and main bony limiting features, specifically: Based on the completed three-dimensional integrated virtual patient model, an automated three-dimensional cephalometric analysis algorithm is launched. Through the precise identification and positioning of the craniofacial skeletal anatomy in the model, multiple key skeletal parameters are automatically calculated. These key skeletal parameters include core indicators such as ANB angle, Wits value, mandibular plane angle, alveolar bone thickness, and dental arch base width. Based on the key bone parameter data obtained by quantification, a preset bone type classification model is invoked. This model is trained and optimized on massive clinical bone data to automatically classify the patient's bone type into specific types including bone type I, type II high angle, and type III low angle. Simultaneously, by combining the numerical deviation ranges and interrelationships of the key skeletal parameters, the feature recognition algorithm accurately captures abnormal information in the development of the patient's craniofacial skeleton, automatically identifying major skeletal limiting features, including maxillary hypoplasia, mandibular overprotrusion, and abnormal vertical height, providing precise skeletal constraint basis for subsequent target location generation.

4. The method of claim 1, wherein the method further comprises: determining a target position of the craniofacial bone based on the coordination of the craniofacial bone. In step S3, the coordination evaluation function is a mathematical function constructed through multi-dimensional feature fusion, used to quantitatively evaluate the degree of adaptation between any virtual tooth arrangement scheme and the host skeletal framework. The specific construction process is as follows: The core evaluation dimensions of mathematical functions should be clearly defined, including at least quantitative evaluation indicators of the root-bone relationship and crown-bone relationship for each tooth, while also incorporating the functional space adaptability evaluation dimension. The evaluation indicators of the root-bone relationship specifically include the three-dimensional spatial position of each tooth root in the alveolar bone, the axial angle of the tooth root, and the minimum distance between the tooth root surface and the surrounding cortical bone. The safe boundary standard for the tooth root is set as ≥1mm from the root apex to the cortical bone and the tooth root located in the center of the cancellous bone. The specific evaluation index for the crown-bone relationship is whether the labial / buccal-lingual inclination of the crown relative to the basal bone is within the physiological compensation range. The evaluation index of functional space adaptability is whether the tooth arrangement is coordinated with the inherent oral functional space determined by the skeletal relationship. The inherent oral functional space includes key functional areas such as the tongue movement space and airway gaps. The coordination between tooth arrangement and skeletal framework is accurately quantified through multi-dimensional evaluation mathematical functions.

5. The method of claim 1, wherein the method further comprises: determining a target position of the craniofacial bone based on the coordination of the craniofacial bone. In step S3, the skeletal constraint conditions are obtained by direct measurement based on the patient's CBCT data, specifically including at least one of alveolar bone thickness, basal arch width, and jawbone spatial relationship, forming an unbreakable hard constraint of skeletal coordination. The multi-objective optimization algorithm is based on the hard constraints of skeletal coordination. Its optimization objectives include maximizing the improvement of occlusal contact, optimizing the aesthetic guidance effect of anterior teeth, and minimizing the total tooth movement distance. Specifically, maximizing the improvement of occlusal contact is reflected in increasing the intercuspal area of ​​posterior teeth. One or more Pareto optimal solutions are obtained by solving a multi-objective optimization algorithm. The optimal solution is the individualized skeletal coordination orthodontic target position that conforms to the patient's skeletal characteristics. The target position is a functional occlusal state that is highly adapted to the patient's skeletal morphology, and is not necessarily Angle Class I relation.

6. The method of claim 1, wherein the method further comprises: In step S4, the individualized skeletal coordination correction target positions and analysis basis are presented through a visual interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results. Specifically: The visual interactive interface is a dedicated interface that integrates decision support and interactive adjustment functions. It adopts a multi-view side-by-side display mode, simultaneously presenting the patient's initial tooth position, the individualized skeletal coordination orthodontic suggested target position generated based on the skeletal coordination engine, and the traditional standardized ideal dental arch target position as a reference, so that doctors can intuitively compare the differences among the three. Visualization technology is used to visualize the basis of analysis, including a three-dimensional comparison of the tooth root position in the alveolar bone and an alveolar bone safety boundary warning mark. The alveolar bone safety boundary warning is achieved by highlighting high-risk areas that exceed physiological limits in red, providing a quantitative reference for doctors to assess the safety of the plan. The interface is set with compliant fine-tuning permissions, allowing physicians to make precise adjustments to the target position within the system's preset coordination envelope based on their clinical experience. During the adjustment process, the system calculates and provides feedback on the changes in coordination score in real time, ensuring that the fine-tuning operation does not exceed the adaptation constraints of the skeleton and teeth, while guaranteeing the coordination and stability of the target position.

7. The method of claim 1, wherein the method further comprises: determining a target position of the craniofacial bone based on the coordination of the craniofacial bone. In step S5, based on the confirmed individualized skeletal coordination treatment target position, the tooth movement sequence planning and treatment-related component design for invisible orthodontics are completed, specifically: Using the individualized skeletal coordination correction target position finally confirmed by the physician as the core benchmark, the target position-driven correction path planning process is initiated. By employing a reverse engineering planning algorithm, and combining the spatial position difference between the initial and target positions of the tooth, the skeletal constraint boundary, and the biomechanical principles of tooth movement, the complete movement trajectory of the tooth from the initial position to the target position is broken down step by step. A safe, efficient, and physiologically sound tooth movement sequence is planned in reverse, clearly defining the direction, distance, and priority of tooth movement at each step. Based on the planned tooth movement sequence and the anatomical requirements of the target position, the system automatically matches and generates the orthodontic components required to achieve the target position through parametric design technology. These orthodontic components include attachments to assist precise tooth movement and orthodontic appliances that conform to the tooth shape. Key parameters, including the type, installation position, shape and size of the attachments, and the curvature and thickness of the orthodontic appliances, are automatically optimized and designed by the system according to individualized skeletal and dental characteristics. This ensures that the attachments and appliances can accurately adapt to the patient's oral structure, provide continuous and stable orthodontic force for tooth movement, and guarantee the successful achievement of the final orthodontic goal.

8. A system for generating a target position of orthodontic treatment based on craniofacial bone coordination, for performing the method for generating a target position of orthodontic treatment based on craniofacial bone coordination according to any one of claims 1 to 7, characterized in that, include: The multimodal data fusion and skeletal framework extraction module is used to acquire patients' multimodal oral data and perform registration and fusion to construct a three-dimensional integrated virtual model including the jawbone and teeth. The skeletal morphology quantitative analysis and classification module is used to perform skeletal morphology quantitative analysis on the three-dimensional integrated virtual model and automatically identify the patient's bone type and main bony limiting features. The skeletal coordination target position generation engine module is used to solve and generate individualized skeletal coordination correction target positions that are adapted to the patient's skeletal morphology based on skeletal constraints, through a preset coordination degree evaluation function and a multi-objective optimization algorithm. The visualization decision support and interactive adjustment interface module is used to present the individualized skeletal coordination correction target position and analysis basis through a visualization interactive interface, supporting physicians to make compliant fine-tuning based on clinical experience and provide feedback on the adjustment results. The target-position driven orthodontic path planning module is used to complete the planning of tooth movement sequence and the design of orthodontic-related components for invisible orthodontics, based on the confirmed individualized skeletal coordination orthodontic target position.

9. A computer device, comprising: The device includes a memory and one or more processors, wherein the memory stores computer code that, when executed by the one or more processors, causes the one or more processors to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer code, and when the computer code is executed, the method as described in any one of claims 1 to 7 is performed.

Images