CBCT-oral scanning data real-time interaction layered registration system and method for dental precise diagnosis and treatment

Abstract

The invention relates to the technical field of dental digital diagnosis and treatment, in particular to a CBCT-oral scanning data real-time interaction layered registration system and method for dental precise diagnosis and treatment, and the method comprises the steps of data reading and initial processing, global registration, layered registration and real-time interaction correction. According to the CBCT-oral scanning data real-time interaction hierarchical registration system and method for dental precise diagnosis and treatment, through a hierarchical registration strategy and a real-time interaction mechanism, rapid and precise alignment of CBCT and oral scanning data is achieved, a doctor is supported to conduct real-time interaction adjustment in the diagnosis and treatment process, the diagnosis and treatment efficiency is remarkably improved, the treatment precision is further enhanced, and the clinical application prospect is wide. More comfortable and safer treatment experience is provided for a patient, an efficient and accurate solution is provided for dental diagnosis and treatment, and important clinical application value is achieved.

Description

Technical Field

[0001] This invention relates to the field of digital dental diagnosis and treatment technology, specifically to a real-time interactive hierarchical registration system and method for CBCT-oral scan data for precision dental diagnosis and treatment. Background Technology

[0002] In the field of precision dental diagnosis and treatment, CBCT (cone-beam computed tomography) and intraoral scan data are two important three-dimensional imaging technologies. CBCT can provide high-resolution images of the oral cavity and maxillofacial structure, which is of great significance for diagnosing the condition of teeth, bones and soft tissues. Intraoral scan data, on the other hand, obtains a three-dimensional model of the inside of the patient's mouth through an oral scanner and is widely used in the fields of tooth alignment and dental implant planning.

[0003] However, the registration process between CBCT and intraoral scan data still faces many challenges in clinical practice. Existing registration techniques usually require complex procedures and long processing times, which not only affects the efficiency of diagnosis and treatment but may also lead to deviations in treatment plans due to inaccurate data. Especially when real-time interactive adjustments are required, existing methods are difficult to meet the dual clinical demands for efficiency and accuracy. Existing registration methods suffer from insufficient registration accuracy, inconvenient operation, and the need for large amounts of training data, resulting in high hardware requirements.

[0004] To address the aforementioned issues, we have made improvements by proposing a real-time interactive hierarchical registration system and method for CBCT-oral scan data for precision dental diagnosis and treatment. Summary of the Invention

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] This invention provides a real-time interactive layered registration system and method for CBCT-intraoral scan data for precision dental diagnosis and treatment, comprising the following steps:

[0007] S1. Data acquisition and initial processing: acquire cone-beam computed tomography (CBCT) data and oral cavity scan data; perform surface reconstruction on CBCT data to provide a basis for subsequent operations;

[0008] S2. Global Registration:

[0009] Feature point selection: The user manually selects at least 3 corresponding feature points from both CBCT and intraoral scan data. Let the set of feature points selected from the CBCT data be P = {p1, p2, ..., p...}. n}(n>=3), the corresponding feature point set selected from the oral scan data is Q={q1,q2,...,q...} n}(n>=3);

[0010] Global registration calculation: The Iterative Closest Point (ICP) algorithm is applied to solve the optimization problem. Where R is the rotation matrix and t is the translation vector, thus obtaining the matrix transformation relationship from intraoral scan data to CBCT data;

[0011] Data coordinate transformation: Based on the obtained matrix transformation relationship, any point q in the corresponding CT scan data is transformed to the coordinate system of the CBCT data using the formula p = R * q + t, thus achieving preliminary registration and alignment.

[0012] S3. Layered registration and real-time interactive correction:

[0013] User interaction trigger: The user clicks on the CBCT surface data with the mouse, let the click position be c;

[0014] Local data construction: Construct a spherical implicit function polygon with radius r = 2 centered at the click position c. For point x, if the inequality ||xc|| ≤ r is satisfied, then include it in the clipping range, and obtain the clipped oral scan data point set Q. local and CBCT data point set P local ;

[0015] Local registration calculation: Calculate Q local center of gravity and P local center of gravity And obtain the set of points after removing the centroid. (i = 1, 2, ... m);

[0016] Construct matrix W: Perform singular value decomposition on W: W = U∑V T The rotation matrix R is obtained. local ;

[0017] Calculate the translation vector t local ,

[0018] Registration evaluation and iterative correction.

[0019] As a preferred embodiment of the present invention, the calculation of the translation vector can be iteratively optimized as needed, based on the current R. local and t local Re-determine the point cloud correspondences and repeat the above calculations until the objective function is achieved. The change is less than the threshold or reaches the preset number of iterations.

[0020] As a preferred technical solution of the present invention, the registration evaluation and cyclic correction means determining whether the current registration result meets the preset requirements. If it does, the registration process ends; if it does not, the user returns to the step of clicking the CBCT surface data with the mouse and repeats the subsequent operations until the registration requirements are met.

[0021] The beneficial effects of this invention are as follows: This CBCT-intraoral scan data real-time interactive layered registration system and method for precision dental diagnosis and treatment has the following key beneficial effects:

[0022] 1. Real-time interactive layered registration: Users can click on CBCT surface data with the mouse to trigger the local registration process, enabling fine registration of specific areas, improving the accuracy and flexibility of registration, and meeting the high requirements for local detail registration in precision dental diagnosis and treatment;

[0023] 2. Combining global and local registration: First, global registration is performed by manually selecting feature points and using the Iterative Closest Point (ICP) algorithm to achieve preliminary coarse registration. Then, layered local registration is performed on this basis. Combining the two methods ensures the overall alignment effect while optimizing local areas, thus improving the accuracy and efficiency of registration.

[0024] 3. Local data construction based on implicit function polygon data: Taking the click position as the center, the data range of local registration is determined by constructing spherical implicit function polygon data. This method can more flexibly select local areas according to user needs and can effectively handle complex 3D data. It is more adaptable than the traditional fixed area selection method.

[0025] 4. Enhance patient experience: Real-time interactive registration allows doctors to adjust the registration effect in a timely manner according to the actual situation during the operation, reducing patients' waiting time and discomfort. At the same time, accurate diagnosis and treatment also help improve treatment results, thereby increasing patient satisfaction and medical experience.

[0026] The hierarchical registration strategy and real-time interaction mechanism of this system enable rapid and accurate alignment of CBCT and intraoral scan data, and support doctors to make real-time interactive adjustments during the diagnosis and treatment process. This not only significantly improves the efficiency of diagnosis and treatment, but also enhances the accuracy of treatment, providing patients with a more comfortable and safer treatment experience. It provides an efficient and accurate solution for dental diagnosis and treatment and has important clinical application value. Attached Figure Description

[0027] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0028] In the attached diagram:

[0029] Figure 1 This is a system flowchart of the CBCT-oral scan data real-time interactive hierarchical registration system and method for precision dental diagnosis and treatment according to the present invention; Detailed Implementation

[0030] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0031] Example: Figure 1 As shown, a real-time interactive hierarchical registration system and method for CBCT-intraoral scan data for precision dental diagnosis and treatment includes the following steps:

[0032] S1. Data acquisition and initial processing: acquire cone-beam computed tomography (CBCT) data and oral cavity scan data; perform surface reconstruction on CBCT data to provide a basis for subsequent operations;

[0033] S2. Global Registration:

[0034] Feature point selection: The user manually selects at least 3 corresponding feature points from both CBCT and intraoral scan data. Let the set of feature points selected from the CBCT data be P = {p1, p2, ..., p...}. n}(n>=3), the corresponding feature point set selected from the oral scan data is Q={q1,q2,...,q...} n}(n>=3);

[0035] Global registration calculation: The Iterative Closest Point (ICP) algorithm is applied to solve the optimization problem. Where R is the rotation matrix and t is the translation vector, thus obtaining the matrix transformation relationship from intraoral scan data to CBCT data;

[0036] Data coordinate transformation: Based on the obtained matrix transformation relationship, any point q in the corresponding CT scan data is transformed to the coordinate system of the CBCT data using the formula p = R * q + t, thus achieving preliminary registration and alignment.

[0037] S3. Layered registration and real-time interactive correction:

[0038] User interaction trigger: The user clicks on the CBCT surface data with the mouse, let the click position be c;

[0039] Local data construction: Construct a spherical implicit function polygon with radius r = 2 centered at the click position c. For point x, if the inequality ||xc|| ≤ r is satisfied, then include it in the clipping range, and obtain the clipped oral scan data point set Q. local and CBCT data point set P local ;

[0040] Local registration calculation: Calculate Q local center of gravity and P local center of gravity And obtain the set of points after removing the centroid. (i = 1, 2, ... m);

[0041] Construct matrix W: Perform singular value decomposition on W: W = U∑V T The rotation matrix R is obtained. local ;

[0042] Calculate the translation vector t local ,

[0043] Registration evaluation and iterative correction.

[0044] The calculation of the translation vector can be iteratively optimized as needed, based on the current R... local and t local Re-determine the point cloud correspondences and repeat the above calculations until the objective function is achieved. The change is less than the threshold or reaches the preset number of iterations.

[0045] Registration evaluation and iterative correction determine whether the current registration result meets the preset requirements. If it does, the registration process ends; if it does not, the user returns to the step of clicking on the CBCT surface data and repeats the subsequent operations until the registration requirements are met.

[0046] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A real-time interactive hierarchical registration system and method for CBCT-intraoral scan data for precision dental diagnosis and treatment, characterized in that, Includes the following steps: S1. Data acquisition and initial processing: acquire cone-beam computed tomography (CBCT) data and oral cavity scan data; perform surface reconstruction on CBCT data to provide a basis for subsequent operations; S2. Global Registration: Feature point selection: The user manually selects at least 3 corresponding feature points from both CBCT and intraoral scan data. Let the set of feature points selected from the CBCT data be P = {p1, p2, ..., p...}. n }(n>=3), the corresponding feature point set selected from the oral scan data is Q={q1,q2,...,q...} n }(n>=3); Global registration calculation: The Iterative Closest Point (ICP) algorithm is applied to solve the optimization problem. Where R is the rotation matrix and t is the translation vector, thus obtaining the matrix transformation relationship from intraoral scan data to CBCT data; Data coordinate transformation: Based on the obtained matrix transformation relationship, any point q in the corresponding CT scan data is transformed to the coordinate system of the CBCT data using the formula p = R * q + t, thus achieving preliminary registration and alignment. S3. Layered registration and real-time interactive correction: User interaction trigger: The user clicks on the CBCT surface data with the mouse, let the click position be c; Local data construction: Construct a spherical implicit function polygon with radius r = 2 centered at the click position c. For point x, if the inequality ||xc|| ≤ r is satisfied, then include it in the clipping range, and obtain the clipped oral scan data point set Q. local and CBCT data point set P local ; Local registration calculation: Calculate Q local center of gravity and P local center of gravity And obtain the set of points after removing the centroid. Construct matrix W: Perform singular value decomposition on W: W = U∑V T The rotation matrix R is obtained. local ; Calculate the translation vector t local , Registration evaluation and iterative correction.

2. The CBCT-intraoral scan data real-time interactive hierarchical registration system and method for precision dental diagnosis and treatment according to claim 1, characterized in that, The calculation of the translation vector can be iteratively optimized as needed, based on the current R... local and t local Re-determine the point cloud correspondences and repeat the above calculations until the objective function is achieved. The change is less than the threshold or reaches the preset number of iterations.

3. The CBCT-intraoral scan data real-time interactive hierarchical registration system and method for precision dental diagnosis and treatment according to claim 1, characterized in that, Registration evaluation and iterative correction determine whether the current registration result meets the preset requirements. If it does, the registration process ends; if it does not, the user returns to the step of clicking on the CBCT surface data and repeats the subsequent operations until the registration requirements are met.

Images