Intraoral scanning data correction method based on dynamic characteristic weight adjustment

Abstract

The invention discloses an intraoral scanning data correction method based on dynamic feature weight adjustment. The method comprises the following steps: S1, acquiring initial intraoral scanning data acquired by intraoral scanning equipment; s2, acquiring full oral cavity three-dimensional model data generated by cone beam computed tomography equipment; s3, extracting three-dimensional model information of a single tooth; s4, performing three-dimensional registration on the three-dimensional model information of the single tooth and a corresponding tooth model in the CBCT data based on a dynamic feature weight adjustment algorithm; s5, generating a full oral cavity correction model; s6, using a physical model generated by warehouse scanning as a verification standard; and S7, outputting the corrected full oral cavity three-dimensional model. According to the method, the problems of precision and consistency in oral three-dimensional scanning data are solved, the precision of the corrected whole oral model is remarkably improved, and the method has high practicability and clinical application value.

Description

Technical Field

[0001] The present invention relates to the field of oral technologies, and particularly to a method for correcting intraoral scan data based on dynamic feature weight adjustment. Background Art

[0002] With the development of digital medical technologies, digital scanning technologies in the oral diagnosis and treatment process have become important tools in oral restoration and treatment. In particular, intraoral scanning technology can quickly obtain three-dimensional point cloud data of a patient's teeth and oral soft and hard tissues, providing an efficient and non-invasive diagnosis and treatment method.

[0003] In the prior art, an intraoral scanning device can generate high-precision local three-dimensional point cloud data by scanning a patient's teeth and oral soft and hard tissues. However, due to the limitations of oral scanning and the complexity of the scanning environment, problems often occur where the local precision is high but the global consistency is poor. Specifically, intraoral scanning technology can accurately capture the detailed information of a single tooth. However, due to the limitation of the scanning range, it is impossible to maintain sufficient global consistency within the entire oral cavity. In particular, the correction of the global characteristics of the dental arch curvature often fails to be consistent with the actual oral structure.

[0004] To solve this problem, in recent years, cone beam computed tomography technology has been introduced into the field of oral three-dimensional imaging. CBCT can provide an oral three-dimensional model with high global precision, especially showing excellent performance in displaying complex anatomical structures. However, the resolution and detail capture ability of CBCT are relatively weak. It is difficult to meet the high requirements of the oral model for details and global precision by solely relying on CBCT data for the detailed parts of a single tooth.

[0005] Currently, there have been some studies on the fusion technology of intraoral scan data and CBCT data. However, most of these methods use a fixed weight strategy for data fusion and fail to effectively solve the balance problem between global and local information. When the existing fusion methods process complex tooth morphologies and oral structures, they usually do not dynamically adjust the precision of the scan data for different regions, resulting in the fused model possibly failing to achieve an ideal balance between details and global precision. In addition, the prior art usually relies on manual inspection and post-correction for the global correction and precision calibration of intraoral scan data, lacking automated correction and optimization means and being unable to quickly and efficiently provide correction results that meet clinical applications.

[0006] In summary, the prior art has significant deficiencies in the fusion of intraoral scan data and CBCT data and the precision calibration of full-oral cavity correction, making it difficult to meet the requirements of high precision, global consistency, and efficient correction in the oral medical process. Summary of the Invention

[0007] An object of the present invention is to propose a method for correcting intraoral scanning data based on dynamic feature weight adjustment. The present invention solves the problems of accuracy and consistency in oral three-dimensional scanning data, significantly improves the accuracy of the corrected full-oral cavity model, and has high practicality and clinical application value.

[0008] A method for correcting intraoral scanning data based on dynamic feature weight adjustment according to an embodiment of the present invention includes the following steps:

[0009] S1. Obtain initial intraoral scanning data collected by an intraoral scanning device, where the initial intraoral scanning data includes three-dimensional point cloud information of teeth and oral soft and hard tissues;

[0010] S2. Obtain full-oral cavity three-dimensional model data generated by a cone beam computed tomography device, and the full-oral cavity three-dimensional model has global accurate information with an overall arc;

[0011] S3. Perform segmentation processing on the intraoral scanning data to extract three-dimensional model information of a single tooth;

[0012] S4. Based on a dynamic feature weight adjustment algorithm, perform three-dimensional registration on the three-dimensional model information of a single tooth and the corresponding tooth model in the CBCT data, and use the method of minimizing the difference between the two to determine the matching relationship of each tooth;

[0013] S5. Construct a fusion model, fuse the global arc information in the CBCT data with the detailed information of a single tooth in the intraoral scanning data, and perform global correction on the intraoral scanning data by dynamically adjusting the feature weight distribution strategy to generate a full-oral cavity corrected model;

[0014] S6. Use the physical model generated by the intraoral scan as a verification standard to verify and calibrate the accuracy of the corrected full-oral cavity corrected model;

[0015] S7. Output the corrected full-oral cavity three-dimensional model, which has both the details of a single tooth and can maintain the integrity and consistency of the global dental arch arc.

[0016] Optionally, the S4 includes the following steps:

[0017] S41. Obtain the three-dimensional model information M of a single tooth in the intraoral scanning data tooth , and the three-dimensional model information includes the spatial coordinate information of each point:

[0018]

[0019] Wherein, is the coordinate of a single tooth in three-dimensional space, and n tooth is the number of points in the point cloud data of the single tooth model;

[0020] S42. Obtain the corresponding tooth model information M in the CBCT data CBCT , and the tooth model information includes the coordinates of each point:

[0021]

[0022] Among them, is the three-dimensional space coordinates of the corresponding tooth model in the CBCT, and n CBCT is the number of points in the point cloud model of the CBCT data;

[0023] S43. Perform preliminary registration on the three-dimensional model information M tooth and the tooth model information M CBCT , set the initial matching relationship, and use the rigid transformation method to align the three-dimensional model information to the corresponding tooth model in the CBCT data. The preliminary registration is performed through the rotation matrix R and the displacement vector t:

[0024]

[0025] Among them, R is a 3x3 rotation matrix, and t = (t x , t y , t z ) is the translation vector, M aligned is the preliminary aligned model after registration, are the coordinates of the tooth model points after rotation and translation;

[0026] S44. Based on the dynamic feature weight adjustment algorithm, perform registration on the preliminary aligned model M aligned and the tooth model information M CBCT , optimize the matching relationship between the two, and use the minimization error function to minimize the difference between the two:

[0027]

[0028] Among them, ω ij is the dynamic feature weight, which reflects the contribution degree of each matching point to the error. The dynamic adjustment of the weight coefficient is based on the local feature differences between the point clouds. The greater the weight, the greater the impact of the point cloud matching on the overall registration result;

[0029] S45. By minimizing the error function E, use the iterative optimization method to adjust the rotation matrix R and the translation vector t, optimize the difference between the preliminary aligned model after registration and the tooth model information, and make the three-dimensional space matching relationship of each tooth accurate:

[0030]

[0031] Among them, η is the learning rate, and They are the gradients of the rotation matrix and the displacement vector respectively, representing the rate of change of the error function with respect to the rotation matrix and the displacement vector;

[0032] S46. Determine the matching relationship of each tooth and generate the three-dimensional model of a single tooth for the final registration. The three-dimensional model of the single tooth after registration is aligned with the corresponding tooth part in the CBCT model to generate the corrected three-dimensional model M of the single tooth. final :

[0033]

[0034] Among them, is the point cloud data of the corrected and registered single tooth model, and n final is the number of points after registration.

[0035] Optionally, the S5 includes the following steps:

[0036] S53. Fuse the tooth model information and the three-dimensional model M of the single tooth after correction, and dynamically adjust the fusion method of the detailed information of the single tooth and the radian information of the whole oral cavity through the dynamic feature weight distribution strategy: final where ω

[0037]

[0038] is the feature weight of points k,i and and respectively, and and are the distances between the CBCT data points and the points of the three-dimensional model of the single tooth after correction respectively;

[0039] S54. Based on the dynamic feature weight ω k,i perform the fusion of the whole oral cavity correction model, and fuse the radian information of the whole oral cavity and the detailed information of the single tooth after correction through the weighted average method to generate the whole oral cavity correction model:

[0040]

[0041] where is the final whole oral cavity correction model, which contains the detailed information from the three-dimensional model of the single tooth after correction and the global radian information in the CBCT data;

[0042] S55. Optimize the generated whole oral cavity correction model to further adjust the accuracy of the correction model through the error function minimization method, so that the whole oral cavity correction model reaches the best balance between details and global consistency:

[0043]

[0044] Among them, to correct the error of the model, is the three-dimensional coordinate after correction from a single tooth, is the coordinate in the corresponding CBCT data, and minimizing results in a full-oral cavity correction model

[0045] Optionally, S6 includes the following steps:

[0046] S61. Obtain the physical model M generated by the intraoral scanner, physical where the physical model includes the real physical structure of the full oral cavity and provides a standard for verifying the corrected full-oral cavity correction model;

[0047] S62. Compare the corrected full-oral cavity correction model with the physical model M generated by the intraoral scanner physical and calculate the difference between the two;

[0048] S63. Verify and calibrate the accuracy of the corrected full-oral cavity correction model by minimizing the error function, and adjust the corrected full-oral cavity correction model to improve the fitting degree between the full-oral cavity correction model and the intraoral scanner physical model;

[0049] S64. When the error function meets the preset convergence threshold or after a set number of iterations, determine the final full-oral cavity correction model as the final corrected full-oral cavity three-dimensional model.

[0050] Optionally, S61 includes the following steps:

[0051] S611. Obtain the physical model M generated by the intraoral scanner physical :

[0052]

[0053] Among them, is the three-dimensional spatial coordinate of each point in the physical model generated by the intraoral scanner, and n physical is the total number of point clouds of the physical model;

[0054] S612. Preprocess the physical model M generated by the intraoral scanner physical to remove the noise points caused by the scanning device error or environmental factors, and calculate the standard deviation of the point cloud data according to the preset threshold to calculate the noise tolerance of each point:

[0055]

[0056] Among them, The Euclidean distance from the p-th point in the bin-scan physical model to the reference coordinates (x ref , y ref , z ref );

[0057] S613. Perform coordinate system transformation on the preprocessed physical model M physical to align its coordinate system with the coordinate system of the full oral cavity correction model . The coordinate system transformation process is carried out through the rotation matrix R physical and the displacement vector t physical :

[0058]

[0059] where, is the transformed physical model, R physical is the rotation matrix, and t physical is the translation vector.

[0060] Optionally, the S62 includes the following steps:

[0061] S621. Compare the corrected full oral cavity correction model with the physical model generated by bin-scan , ensure their alignment in the three-dimensional space by selecting corresponding point pairs, and make the points in the physical model correspond one-to-one with the points in the corrected full oral cavity correction model. The matching relationship of each pair of corresponding points is expressed as:

[0062]

[0063] S622. Calculate the distance difference between each pair of corresponding points between the physical model and the correction model, and evaluate the matching accuracy of the two based on this difference;

[0064] S623. Perform weighted summation on the distance differences between all pairs of corresponding points to obtain the overall difference between the full oral cavity correction model and the physical model:

[0065]

[0066] where, E compare is the total difference between the corrected full oral cavity correction model and the physical model, ω p,i is the weight of each pair of points, indicating the contribution of the point pair to the overall difference, is the distance difference of each pair of points;

[0067] S624. Evaluate the degree of fit between the corrected full oral cavity correction model and the physical model according to the calculated overall difference E compare .

[0068] The beneficial effects of the present invention are:

[0069] (1) The present invention adopts a fusion strategy based on dynamic feature weight adjustment, which can adaptively and automatically adjust the feature weights of different areas according to the characteristics of the scanning area, thereby achieving more accurate three-dimensional model correction. In the traditional fixed weight fusion method, due to the failure to dynamically adjust the weights according to the scanning quality of different areas, it is easy to cause an imbalance between local details and global consistency. The correction results in the matching between tooth details and the curvature of the entire oral cavity are often not accurate enough. The dynamic weight adjustment algorithm can efficiently balance between details and global structure, significantly improving the accuracy and consistency of the corrected three-dimensional model.

[0070] (2) The present invention introduces the physical model generated by the scan as a verification standard to calibrate the accuracy of the revised full-mouth correction model, so that the revised model maintains a higher degree of consistency with the actual oral structure. The present invention compares the revised full-mouth correction model with the physical model generated by the scan to calculate the difference between the two, and automatically improves the accuracy of the correction model by optimizing and adjusting the error function, ensuring that the revised full-mouth correction model is more realistic and reliable and suitable for actual clinical applications.

[0071] (3) The present invention adopts an automated dynamic optimization process when performing three-dimensional registration and whole-mouth correction, ensuring that the registered three-dimensional model can fully utilize the advantages of intraoral scanning data and CBCT data. The dynamic optimization method can accurately integrate the detailed information of a single tooth with the global curvature information of the whole mouth, and automatically calibrate the corrected whole-mouth correction model, thereby improving the accuracy and consistency of the model, reducing the need for manual operation and debugging, and improving the overall processing efficiency and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0073] Figure 1 This is a flow chart of a method for correcting intraoral scan data based on dynamic feature weight adjustment proposed by the present invention. DETAILED DESCRIPTION

[0074] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0075] refer to Figure 1, An intraoral scan data correction method based on dynamic feature weight adjustment, comprising the following steps:

[0076] S1. Obtain the initial intraoral scan data collected by an intraoral scanning device, where the initial intraoral scan data includes the three-dimensional point cloud information of teeth and the hard and soft tissues of the oral cavity;

[0077] S2. Obtain the full oral cavity three-dimensional model data generated by a cone beam computed tomography (CBCT) device, and the full oral cavity three-dimensional model has global accurate information with an overall curvature;

[0078] S3. Perform segmentation processing on the intraoral scan data to extract the three-dimensional model information of a single tooth;

[0079] S4. Based on the dynamic feature weight adjustment algorithm, perform three-dimensional registration on the three-dimensional model information of a single tooth and the corresponding tooth model in the CBCT data, and determine the matching relationship of each tooth by minimizing the difference between the two;

[0080] S5. Construct a fusion model, fuse the global curvature information in the CBCT data with the detailed information of a single tooth in the intraoral scan data, and globally correct the intraoral scan data by dynamically adjusting the feature weight allocation strategy to generate a full oral cavity correction model;

[0081] S6. Use the physical model generated by the intraoral scan as a verification standard to verify and calibrate the accuracy of the corrected full oral cavity correction model;

[0082] S7. Output the corrected full oral cavity three-dimensional model, which has both the details of a single tooth and can maintain the integrity and consistency of the global dental arch curvature.

[0083] In this embodiment, S4 includes the following steps:

[0084] S41. Obtain the three-dimensional model information M of a single tooth in the intraoral scan data tooth , and the three-dimensional model information includes the spatial coordinate information of each point:

[0085]

[0086] Among them, is the coordinate of a single tooth in three-dimensional space, and n tooth is the number of points in the point cloud data of the single tooth model;

[0087] S42. Obtain the corresponding tooth model information M in the CBCT data CBCT , and the tooth model information includes the coordinates of each point:

[0088]

[0089] Among them, are the three-dimensional spatial coordinates of the corresponding tooth model in CBCT, and n CBCT is the number of points in the point cloud model of the CBCT data;

[0090] S43. Perform preliminary registration on the three-dimensional model information M tooth and the tooth model information M CBCT to set the initial matching relationship, and use the rigid transformation method to align the three-dimensional model information to the corresponding tooth model in the CBCT data. The preliminary registration is carried out through the rotation matrix R and the displacement vector t:

[0091]

[0092] where R is a 3x3 rotation matrix, and t = (t x , t y , t z ) is the translation vector, and M aligned is the preliminary aligned model after registration, are the coordinates of the tooth model points after rotation and translation;

[0093] S44. Based on the dynamic feature weight adjustment algorithm, perform registration on the preliminary aligned model M aligned after registration and the tooth model information M CBCT to optimize their matching relationship, and use the minimum error function to minimize the difference between the two:

[0094]

[0095] where ω ij is the dynamic feature weight, which reflects the contribution degree of each matching point to the error. The dynamic adjustment of the weight coefficient is based on the local feature difference between the point clouds. The greater the weight, the greater the impact of the point cloud matching on the overall registration result;

[0096] S45. By minimizing the error function E, use the iterative optimization method to adjust the rotation matrix R and the translation vector t to optimize the difference between the preliminary aligned model after registration and the tooth model information, so that the three-dimensional spatial matching relationship of each tooth is accurate:

[0097]

[0098] where η is the learning rate, and are the gradients of the rotation matrix and the displacement vector respectively, representing the change rate of the error function with respect to the rotation matrix and the displacement vector;

[0099] S46. Determine the matching relationship of each tooth and generate a three-dimensional model of a single tooth with final registration. The three-dimensional model of the single tooth after registration is aligned with the corresponding tooth part in the CBCT model to generate a corrected three-dimensional model M of the single tooth final :

[0100]

[0101] Among them, is the point cloud data of the single tooth model after corrected registration, and n final is the number of points after registration.

[0102] In this embodiment, S5 includes the following steps:

[0103] S53. Fuse the tooth model information and the corrected three-dimensional model M of the single tooth final and dynamically adjust the fusion method of the detailed information of the single tooth and the radian information of the entire oral cavity through a dynamic feature weight distribution strategy:

[0104]

[0105] Among them, ω k,i is the feature weight of points and , and are the distances between the CBCT data points and the points of the corrected three-dimensional model of the single tooth respectively;

[0106] S54. Based on the dynamic feature weight ω k,i perform the fusion of the corrected model of the entire oral cavity, and fuse the radian information of the entire oral cavity with the detailed information of the corrected single tooth through the method of weighted average to generate a corrected model of the entire oral cavity:

[0107]

[0108] Among them, is the final corrected model of the entire oral cavity, which contains the detailed information from the corrected three-dimensional model of the single tooth and the global radian information in the CBCT data;

[0109] S55. Optimize the generated corrected model of the entire oral cavity and further adjust the accuracy of the corrected model through the method of minimizing the error function, so that the corrected model of the entire oral cavity reaches the best balance between details and global consistency:

[0110]

[0111] Among them, is the error of the corrected model, are the three-dimensional coordinates after correction for a single tooth, are the coordinates in the corresponding CBCT data, and after minimization the full oral cavity correction model is obtained

[0112] In this embodiment, S6 includes the following steps:

[0113] S61. Obtain the physical model M generated by the intraoral scanner physical , where the physical model includes the real physical structure of the full oral cavity and provides a standard for verifying the corrected full oral cavity correction model;

[0114] S62. Compare the corrected full oral cavity correction model with the physical model M generated by the intraoral scanner physical and calculate the difference between the two;

[0115] S63. Verify and calibrate the accuracy of the corrected full oral cavity correction model by minimizing the error function, and adjust the corrected full oral cavity correction model to improve the coincidence degree between the full oral cavity correction model and the intraoral scanner physical model;

[0116] S64. When the error function meets the preset convergence threshold or after a set number of iterations, determine the final full oral cavity correction model as the final corrected full oral cavity three-dimensional model.

[0117] In this embodiment, S61 includes the following steps:

[0118] S611. Obtain the physical model M generated by the intraoral scanner physical :

[0119]

[0120] where are the three-dimensional spatial coordinates of each point in the physical model generated by the intraoral scanner, and n physical is the total number of the physical model point cloud;

[0121] S612. Preprocess the physical model M generated by the intraoral scanner physical to remove the noise points caused by the scanning device error or environmental factors, and calculate the noise tolerance of each point according to the standard deviation of the point cloud data calculated by the preset threshold:

[0122]

[0123] where is the Euclidean distance from the p-th point in the intraoral scanner physical model to the reference coordinate (x ref , y ref , z ref );

[0124] S613. Perform coordinate system transformation on the preprocessed physical model M physical to align its coordinate system with that of the full oral cavity correction model through the rotation matrix R physical and the displacement vector t physical as follows:

[0125]

[0126] wherein, is the transformed physical model, R physical is the rotation matrix, and t physical is the translation vector.

[0127] In this embodiment, S62 includes the following steps:

[0128] S621. Compare the corrected full oral cavity correction model with the physical model generated by the warehouse scan, ensure their alignment in three-dimensional space by selecting corresponding point pairs, and make the points in the physical model correspond one by one with the points in the corrected full oral cavity correction model. The matching relationship of each pair of corresponding points is expressed as:

[0129]

[0130] S622. Calculate the distance difference between each pair of corresponding points between the physical model and the correction model, and evaluate the matching accuracy of the two based on this difference;

[0131] S623. Perform weighted summation on the distance differences between all pairs of corresponding points to obtain the overall difference between the full oral cavity correction model and the physical model:

[0132]

[0133] wherein, E compare is the total difference between the corrected full oral cavity correction model and the physical model, ω p,i is the weight of each pair of points, indicating the contribution of the point pair to the overall difference, is the distance difference of each pair of points;

[0134] S624. Evaluate the conformity of the corrected full oral cavity correction model and the physical model according to the calculated overall difference E compare .

[0135] Example 1:

[0136] The embodiment demonstrates a method for correcting intraoral scan data based on dynamic feature weight adjustment applied to the correction process of an oral three-dimensional model. In this embodiment, it shows how the present invention solves the problems in terms of accuracy and consistency of traditional methods by efficiently correcting intraoral scan data and CBCT data.

[0137] The application scenario of this embodiment is in the oral rehabilitation department of a dental hospital. The hospital uses advanced intraoral scanners and cone beam computed tomography equipment to obtain the three-dimensional oral data of patients. The patient is a 45-year-old male with a chief complaint of tooth loss and is preparing for full-mouth tooth restoration treatment. The patient's oral structure is complex, including multiple missing teeth and changes in the alveolar bone. The restoration treatment requires high precision in terms of details and global structure.

[0138] The patient first underwent an intraoral scan, and the scan results showed the three-dimensional point cloud data of single teeth and gums. The total number of data points in the scan results was approximately 350,000. However, due to the limitations of the equipment, the scanning range could only cover the teeth and part of the gums. Therefore, there were significant deviations in the global consistency of the intraoral scan data. Subsequently, the patient underwent a CBCT scan. The CBCT could provide a complete three-dimensional model of the entire oral cavity, with a total number of data points of approximately 1.2 million, covering the global structure of the alveolar bone, teeth, and oral soft and hard tissues. However, due to the limitation of the resolution, it was difficult to accurately capture the details of the tooth surface.

[0139] After the three-dimensional point cloud data obtained from the intraoral scan was acquired, it was first denoised. The denoising algorithm was based on the standard deviation method, and the noise points with a distance from the mean exceeding the threshold were removed. By calculating the standard deviation between each data point and the center point, the noise threshold was set at 3 millimeters, and approximately 20,000 noise points were removed. Finally, the number of effective data points was 330,000.

[0140] The preprocessing of the CBCT data was mainly to remove the low-quality point cloud caused by the scanning angle and equipment resolution. By comparing and removing the edge distortion area, approximately 50,000 data points were removed, and the remaining three-dimensional data points of the entire oral cavity were 1.15 million.

[0141] A three-dimensional registration algorithm based on dynamic feature weight adjustment was used to perform preliminary registration on the intraoral scan data and the CBCT data. The preliminary registration was performed using the rotation matrix R and the translation vector t, and the least squares method was used to minimize the preliminary registration error. The preliminary rotation matrix R and the displacement vector t were set as:

[0142]

[0143] This rotation matrix and displacement vector aligned the intraoral scan data with the CBCT data, and the error of the preliminary registration was 3.5 millimeters.

[0144] In traditional methods, fixed weights are usually used for data fusion, resulting in inconsistent details and global structures. In contrast, the present invention adopts dynamic feature weight adjustment, calculates the distance differences between each pair of points, and dynamically adjusts the weights according to the features of each point and the importance of the region. It is calculated that, in this example, the weight ω tooth of the tooth surface area is 0.8, while the weight ω CBCT of the global structure area is 0.2, and the error after final registration is reduced to 1.5 millimeters.

[0145] Based on the registration results adjusted by dynamic feature weights, the experimenters generated a full oral cavity correction model, and fused the detailed information in the intraoral scan data with the global information in the CBCT data through the weighted average method. The final full oral cavity correction model obtained has an accuracy of 0.9 millimeters. Compared with the traditional method, the details and global consistency of the model have been significantly improved.

[0146] To verify the accuracy of the correction model, the experimenters used the physical model generated by the warehouse scan as a standard for model comparison. By calculating the Euclidean distance between the corrected full oral cavity correction model and the warehouse scan physical model, the overall difference obtained is 1.0 millimeter. After further optimization, the error is reduced to 0.8 millimeter, meeting the clinical restoration requirements.

[0147]

[0148]

[0149] From the comparison data, it can be seen that the method of the present invention is superior to the traditional method in terms of correction accuracy, time efficiency, and model consistency. Especially in terms of the details and global consistency of the full oral cavity correction model, significant improvements have been achieved.

[0150] Through the application of this embodiment, the experimenters demonstrated the feasibility and effectiveness of the method for correcting intraoral scan data based on dynamic feature weight adjustment in the correction of oral three-dimensional models. The present invention effectively solves the problems of insufficient accuracy and poor consistency in traditional methods through automated three-dimensional registration and precise generation of full oral cavity correction models. The accuracy of the finally corrected model has been greatly improved, and the time efficiency of the correction process has also been significantly improved, meeting the high-precision requirements in clinical treatment.

[0151] The present invention adopts a fusion strategy based on dynamic feature weight adjustment, which can adaptively and automatically adjust the feature weights of different areas according to the characteristics of the scanning area, thereby achieving more accurate three-dimensional model correction. In the traditional fixed weight fusion method, due to the failure to dynamically adjust the weights according to the scanning quality of different areas, it is easy to cause an imbalance between local details and global consistency. The correction results in the matching between tooth details and the curvature of the entire mouth are often not accurate enough. The dynamic weight adjustment algorithm can efficiently balance between details and global structure, significantly improving the accuracy and consistency of the corrected three-dimensional model.

[0152] The present invention introduces the physical model generated by warehouse scanning as a verification standard to calibrate the accuracy of the revised full-mouth correction model, so that the revised model maintains a higher degree of consistency with the actual oral structure. The present invention automatically improves the accuracy of the correction model by comparing the revised full-mouth correction model with the physical model generated by warehouse scanning, and by optimizing and adjusting the error function, ensuring that the revised full-mouth correction model is more realistic and reliable and suitable for actual clinical applications.

[0153] The present invention adopts an automated dynamic optimization process when performing three-dimensional alignment and whole-mouth correction, ensuring that the aligned three-dimensional model can fully utilize the advantages of intraoral scanning data and CBCT data. The dynamic optimization method can accurately integrate the detail information of a single tooth with the global curvature information of the whole mouth, and automatically calibrate the corrected whole-mouth correction model, thereby improving the accuracy and consistency of the model, reducing the need for manual operation and debugging, and improving the overall processing efficiency and adaptability.

[0154] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for correcting intraoral scan data based on dynamic feature weight adjustment, characterized in that: The steps include: S1. Acquire initial intraoral scanning data collected by an intraoral scanning device, wherein the initial intraoral scanning data includes three-dimensional point cloud information of teeth and oral soft and hard tissues; S2. Acquire the full oral cavity three-dimensional model data generated by a cone beam computed tomography device, where the full oral cavity three-dimensional model has global and accurate information of the entire curvature; S3. Segmenting the intraoral scan data to extract the three-dimensional model information of a single tooth; S4. Perform three-dimensional registration of the three-dimensional model information of a single tooth with the corresponding tooth model in the CBCT data based on a dynamic feature weight adjustment algorithm, and determine the matching relationship of each tooth by minimizing the difference between the two; S5. Construct a fusion model to fuse the global curvature information in the CBCT data with the detail information of a single tooth in the intraoral scan data, and globally correct the intraoral scan data by dynamically adjusting the feature weight allocation strategy to generate a full-oral correction model; S6. Using the physical model generated by the warehouse scan as a verification standard, verifying and calibrating the accuracy of the corrected full-mouth correction model; S7. Output a corrected full-mouth 3D model that has the details of individual teeth while maintaining the integrity and consistency of the global dental arch curvature.

2. The method for correcting intraoral scan data based on dynamic feature weight adjustment according to claim 1, characterized in that: The S4 comprises the following steps: S41. Obtaining the three-dimensional model information M of a single tooth in the intraoral scan data tooth , the three-dimensional model information contains the spatial coordinate information of each point: in, is the coordinate of a single tooth in three-dimensional space, n tooth is the number of points in the point cloud data of a single tooth model; S42. Obtain the corresponding tooth model information M in the CBCT data CBCT , the tooth model information contains the coordinates of each point: in, is the three-dimensional spatial coordinate of the corresponding tooth model in CBCT, n CBCT is the number of points in the point cloud model in the CBCT data; S43. Three-dimensional model information M tooth and tooth model information M CBCT Perform preliminary registration, set the initial matching relationship, and use the rigid transformation method to align the 3D model information to the corresponding tooth model in the CBCT data. The preliminary registration is performed through the rotation matrix R and the displacement vector t: Where R is a 3x3 rotation matrix, t=(t x ,t y ,t z ) is the translation vector, M aligned is the preliminary alignment model after registration, is the coordinates of the tooth model points after rotation and translation; S44. Preliminary alignment model M after registration based on dynamic feature weight adjustment algorithm aligned and tooth model information M CBCT Perform registration, optimize the matching relationship between the two, and use the minimization error function to minimize the difference between the two: Among them, ω ij It is the dynamic feature weight, which reflects the contribution of each matching point to the error. The dynamic adjustment of the weight coefficient is based on the local feature differences between point clouds. The larger the weight, the greater the impact of the point cloud matching on the overall registration result. S45. By minimizing the error function E, the rotation matrix R and the translation vector t are adjusted by an iterative optimization method to optimize the difference between the preliminary alignment model and the tooth model information after registration, so that the three-dimensional spatial matching relationship of each tooth is accurate: Where η is the learning rate, and are the gradients of the rotation matrix and the displacement vector, respectively, indicating the rate of change of the error function relative to the rotation matrix and the displacement vector; S46. Determine the matching relationship of each tooth and generate a final registered single tooth three-dimensional model, align the registered single tooth three-dimensional model with the corresponding tooth part in the CBCT model, and generate a corrected single tooth three-dimensional model M final : in, is the point cloud data of the single tooth model after correction and registration, n final is the number of points after registration.

3. The method for correcting intraoral scan data based on dynamic feature weight adjustment according to claim 1, characterized in that: The S5 comprises the following steps: S53. The tooth model information and the three-dimensional model after the single tooth correction M final The fusion method of dynamically adjusting the fusion of the detail information of a single tooth and the curvature information of the entire mouth through the dynamic feature weight allocation strategy: Among them, ω k,i For point and The feature weights of and They are the distances between the CBCT data points and the corrected 3D model points of a single tooth; S54. Based on dynamic feature weight ω k,i The whole mouth correction model is fused. The curvature information of the whole mouth is fused with the detailed information of the single tooth after correction by the weighted average method to generate the whole mouth correction model: in, The final full-mouth correction model includes the detailed information from the corrected 3D model of a single tooth and the global curvature information from the CBCT data; S55. Correction of the generated full oral cavity model Optimization is performed and the accuracy of the correction model is further adjusted by the error function minimization method, so that the full-mouth correction model achieves the best balance between details and global consistency: in, To correct the model errors, is the corrected three-dimensional coordinate from a single tooth, To correspond to the coordinates in the CBCT data, minimize Then get the whole mouth correction model 4. The method for correcting intraoral scan data based on dynamic feature weight adjustment according to claim 1, characterized in that: The S6 comprises the following steps: S61. Obtain the physical model M generated by warehouse scanning physical , the physical model includes the real physical structure of the whole oral cavity and provides a standard for verifying the revised whole oral cavity revised model; S62. The modified full oral correction model The physical model M generated by warehouse scanning physical Compare and calculate the difference between the two; S63. Verify and calibrate the accuracy of the corrected full-mouth correction model by minimizing the error function, and adjust the corrected full-mouth correction model to improve the fit between the full-mouth correction model and the physical model of the warehouse scan; S64. When the error function meets the preset convergence threshold or after a set number of iterations, the final full-oral correction model is determined The final modified three-dimensional model of the entire oral cavity.

5. The method for correcting intraoral scan data based on dynamic feature weight adjustment according to claim 4, characterized in that: The S61 comprises the following steps: S611. Obtain the physical model M generated by warehouse scanning physical : in, The three-dimensional space coordinates of each point in the physical model generated by the bin scan, n physical is the total number of point clouds of the physical model; S612. Scan the physical model M generated by the warehouse physical Preprocessing is performed to remove noise points caused by scanning equipment errors or environmental factors, and the standard deviation of the point cloud data is calculated according to the preset threshold to calculate the noise tolerance of each point: in, is the distance from the pth point in the warehouse scanning physical model to the reference coordinate (x ref ,y ref ,z ref )’s Euclidean distance; S613. Preprocessing the physical model M physical Perform coordinate system conversion and align its coordinate system with the full oral correction model The coordinate system is aligned, and the coordinate system transformation process is performed by the rotation matrix R physical and displacement vector t physical conduct: in, is the physical model after transformation, R physical is the rotation matrix, t physical is the translation vector.

6. The method for correcting intraoral scan data based on dynamic feature weight adjustment according to claim 5, characterized in that: The S62 comprises the following steps: S621. The corrected full-oral correction model and the physical model generated by the warehouse scan are combined By selecting corresponding point pairs to ensure the alignment of the two in three-dimensional space, the points in the physical model are Compared with the points in the revised full-mouth correction model One-to-one correspondence, the matching relationship of each pair of corresponding points is expressed as: S622. Calculate the distance difference between each pair of corresponding points of the physical model and the modified model, and evaluate the matching accuracy of the two based on the difference; S623. Distance differences between all corresponding point pairs Perform a weighted sum to obtain the overall difference between the full-mouth modified model and the physical model: Among them, E compare is the total difference between the modified full-mouth model and the physical model, ω p,i is the weight of each pair of points, indicating the contribution of the point pair to the overall difference, is the distance difference between each pair of points; S624. Based on the calculated overall difference E compare , evaluate the degree of fit between the revised full-mouth correction model and the physical model.

Images