CN114549540A - Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof - Google Patents
Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof Download PDFInfo
- Publication number
- CN114549540A CN114549540A CN202210196089.8A CN202210196089A CN114549540A CN 114549540 A CN114549540 A CN 114549540A CN 202210196089 A CN202210196089 A CN 202210196089A CN 114549540 A CN114549540 A CN 114549540A
- Authority
- CN
- China
- Prior art keywords
- data
- cbct
- oral
- dental
- scan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Abstract
The invention relates to a method for automatically fusing oral scanning tooth data and CBCT data, which comprises the following steps: s1 loading the raster grid data; s2, dividing raster grid data; s3 loading CBCT data; s4: segmenting CBCT data AI; s5: generating a CBCT data segmentation result in a gridding manner; s6 registration of the oral scan crown data with CBCT gridding data; s7, calculating the coordinate position information of the registered CBCT upper teeth and lower teeth, and generating new CBCT upper teeth and lower teeth grid data; s8 matching the upper dental crown with the associated point set; s9 lower tooth crown matching correlation point set; s10, deformation of the CBCT grid data; and S11, optimizing the reconstruction of the CBCT grid data. The method based on the automatic fusion of the oral scan tooth data and the CBCT data can integrate the advantages of high tooth crown precision of the oral scan data and complete tooth root form of the CBCT data, obtain the appearance form of the oral scan tooth crown and the CBCT tooth after the integral fusion, well guide the clinician to carry out work and improve the tooth treatment precision.
Description
Technical Field
The invention relates to the field of oral medical treatment, in particular to a method for automatically fusing oral scanning tooth data and CBCT data and application thereof.
Background
With the improvement of the living standard of people, the pursuit of the quality of oral medical service is more and more common, and the clinical application of the digital diagnosis and treatment equipment is wide. At present, CBCT (Cone-beam computed tomography) and oral scanners (oral scanners for short) are widely used in the outpatient department of the oral cavity, and doctors can conveniently obtain the tooth arrangement and specific structural information of patients. But has the defects of low accuracy of the dental crown obtained by CBCT and missing tooth root from the mouth scan data. Therefore, it is necessary to develop a method based on the oral scan dental data and the automatic fusion of the CBCT data.
Disclosure of Invention
The invention aims to solve the technical problem of designing a high-accuracy automatic fusion method based on oral-scanning tooth data and CBCT data, and solving the existing technical problem.
In order to solve the technical problem, the method for automatically fusing the mouth scan tooth data and the CBCT data comprises the following steps:
s1: load the portal scan grid data (mesh 1);
s2: segmenting teeth according to the oral scanning grid data loaded in the step S1;
s3: loading CBCT data;
s4: performing AI segmentation on the CBCT data loaded in the step S3;
s5: gridding and generating (mesh2) the CBCT data segmentation result obtained in the step S4;
s6: registering the oral-scanning dental crown data with CBCT gridding data;
s7: according to the CBCT matrix information of the oral scanning data, calculating the coordinate position information of the upper teeth and the lower teeth after the registration of the CBCT, and generating new CBCT grid data of the upper teeth and the lower teeth;
the point cloud registration process is to find a rotational translation matrix (rigid transform or iterative transform rigid transform or euclidean transform) between two point clouds, and transform the source point cloud (source cloud) into the same coordinate system as the target cloud (target cloud), which can be expressed as the following equation:
pt＝R·ps+T，
wherein p istAnd psNamely, a pair of corresponding points in the target cluster and the source cluster, and the times requirement is a rotation and translation matrix of R and T.
The rough registration is to find a rotation and translation matrix approximate to the two point clouds under the conditions that the difference between the two point clouds is huge and the relative position relationship of the two point clouds is not clear at all. The fine registration is to further calculate a more accurate rotational-translational matrix when an initial value of the rotational-translational is known. The mode of fine registration has been largely fixed to use of the ICP algorithm and its various variants. The ICP algorithm is proposed by Besl and McKay 1992, Method for registration of 3-D maps. The algorithms mentioned herein take into account not only the registration between sets of points, but also the registration of sets of points to models, models to models, etc. The ICP algorithm core is to minimize an objective function:
s8: traversing each point A on the oral-scan upper dental crown grid data, and calculating the distance from each point in the CBCT upper dental grid data to the point A to obtain a point B with the closest distance, so that each point on the oral-scan upper dental crown grid data can find a matched point in the CBCT upper dental grid data;
s9: calculating each point on the dental scan lower dental crown mesh data and a matched point in the CBCT lower dental mesh data with reference to the step S8;
s10: matching point sets in upper teeth and lower teeth grids of the CBCT are selected, the upper teeth matching points are in a first group, the lower teeth matching points are in a second group, matched dental crown data of the oral scan are in a target point set, deformation is carried out on the grid point data selected by the CBCT, so that the whole CBCT tooth is correspondingly changed, and the deformed CBCT grid data is obtained;
s11: and performing grid reconstruction optimization on the CBCT grid data in the step S10, performing Delaunay remesh, and generating an updated grid with excellent quality.
Further, the raster grid data in step S1 is an object composed of a plurality of triangular patches.
Further, in step S2, AI intelligence segmentation is adopted, for example, a mesh segnet network or other mesh segmentation framework; or the traditional mesh segmentation method is used for manually editing and cutting the outline on the oral scanning integral mesh model to segment the teeth.
Further, the CBCT data in step S3 includes a series of two-dimensional slice data in dicom format.
Further, in step S4, a conventional AI medical image segmentation framework, such as nnUNet, VNet or other frameworks, is adopted.
Further, in step S5, the marching cube or Delaunay method is used to generate the mesh data.
Further, in step S6, three or more sets of corresponding points with matched positions are clicked on the oral scan crown data and the CBCT gridding data, respectively, to perform registration; or automatically calculating three or more groups of corresponding points to carry out registration based on the morphological characteristics or the position characteristics.
Further, the method for implementing deformation on the grid point data selected by the CBCT in step S10 includes: according to the calculation result in the step S8, a matching point B can be found on the CBCT mesh data for each point a on the oral crown mesh, the point set formed by B is used as a control point, the point set formed by a is used as a target position point after Deformation of the control point, and Deformation is performed Based on a Laplacian mesh Deformation algorithm (Laplacian-Based Deformation).
The invention also provides a system for automatically fusing the dental scan data and the CBCT data, which comprises the following steps:
one or more processors; and
one or more memories having stored therein a computer-executable program that, when executed by the processor, performs the method of automatically fusing the dental scan data with CBCT data according to the preceding claims.
The invention also provides a computer-readable storage medium having stored thereon computer-executable instructions, which when executed by a processor, are used to implement the aforementioned method for automatic fusion of the oral scan dental data and CBCT data.
The present invention also provides a computer program product comprising computer instructions which, when executed by a processor, cause a computer device to perform the aforementioned method of automated fusion of oral scan dental data with CBCT data.
The invention has the beneficial effects that:
the method based on the mouth-scan tooth data and the CBCT data automatic fusion can integrate the advantages of high tooth crown precision of the mouth-scan data and complete tooth root form of the CBCT data, obtain the appearance form of the mouth-scan tooth crown and the CBCT tooth after the integral fusion, and solve the defects of tooth root loss of the single-sided mouth-scan data and low tooth crown precision of the CBCT. The accurate anatomical structure of tooth can guide the clinician well to carry out work, improves the precision of tooth treatment.
Drawings
The following further illustrates embodiments of the present invention with reference to the drawings.
FIG. 1 is a block flow diagram of a method of the present invention based on automated fusion of dental scan data and CBCT data;
FIG. 2 is a schematic view of oral scan dental crown data;
FIG. 3 is a schematic diagram of CBCT gridding data;
FIG. 4 is a graph of the registration of the oral scan data and the CBCT data;
FIG. 5 is a graph showing the effect of fusion of the mouth scan data and the CBCT grid data.
Detailed Description
Referring to fig. 1, the method for automatically fusing the tooth-scanning data and the CBCT data of the present embodiment includes the following steps:
s1: load port scan mesh data (mesh1), as shown in FIG. 2; in this embodiment, the scan grid data is an object composed of a plurality of triangular patches;
s2: segmenting teeth according to the oral scanning grid data loaded in the step S1; in this embodiment, AI intelligent segmentation is adopted, for example, a frame of a MeshSegNet network or other grid segmentation; or the traditional mesh segmentation method is used for manually editing and cutting the outline on the oral scanning integral mesh model to segment the teeth.
S3: loading CBCT data; in this embodiment, the CBCT data comprises a series of two-dimensional slice data in dicom format.
S4: performing AI segmentation on the CBCT data loaded in the step S3; in the present embodiment, a conventional AI medical image segmentation framework, such as nnUNet, VNet or other framework, is adopted.
S5: the CBCT data segmentation result obtained in step S4 is generated by gridding (mesh2), as shown in fig. 3; in this embodiment, a marching cube or Delaunay method is used to generate the mesh data.
S6: registering the oral-scanning dental crown data with CBCT gridding data; in the embodiment, three or more groups of corresponding points matched in position are respectively clicked on the oral scan dental crown data and the CBCT gridding data to implement registration; or automatically calculating three or more groups of corresponding points to carry out registration based on the morphological characteristics or the position characteristics. The effect map of the registered oral scan data and CBCT data is shown in FIG. 4.
S7: according to the CBCT matrix information of the oral scanning data, calculating the coordinate position information of the upper teeth and the lower teeth after the registration of the CBCT, and generating new CBCT grid data of the upper teeth and the lower teeth;
s8: traversing each point A on the oral-scan upper dental crown grid data, and calculating the distance from each point in the CBCT upper dental grid data to the point A to obtain a point B with the closest distance, so that each point on the oral-scan upper dental crown grid data can find a matched point in the CBCT upper dental grid data;
s9: calculating each point on the dental scan lower dental crown mesh data and a matched point in the CBCT lower dental mesh data with reference to the step S8;
s10: matching point sets in upper teeth and lower teeth grids of the CBCT are selected, the upper teeth matching points are in a first group, the lower teeth matching points are in a second group, matched dental crown data of the oral scan are in a target point set, deformation is carried out on the grid point data selected by the CBCT, so that the whole CBCT tooth is correspondingly changed, and the deformed CBCT grid data is obtained; in this embodiment, the method for implementing deformation on the grid point data selected by CBCT includes: according to the calculation result in the step S8, a matching point B can be found on the CBCT mesh data for each point a on the oral crown mesh, the point set formed by B is used as a control point, the point set formed by a is used as a target position point after the Deformation of the control point, and the Deformation is performed Based on a Laplacian mesh Deformation algorithm (Laplacian-Based Deformation);
s11: and performing grid reconstruction optimization on the CBCT grid data in the step S10, performing Delaunay remesh, and generating an updated grid with excellent quality.
The effect map of the fused oral scan data and CBCT grid data is shown in FIG. 5.
The embodiment further provides a system for automatically fusing dental scan data and CBCT data, comprising:
one or more processors; and
one or more memories having stored therein a computer-executable program that, when executed by the processor, performs the method of automatically fusing the dental scan data with CBCT data according to the preceding claims.
The present embodiments also provide a computer-readable storage medium having stored thereon computer-executable instructions, which when executed by a processor, are used to implement the aforementioned method for automatic fusion of dental scan data and CBCT data.
The present embodiments also provide a computer program product comprising computer instructions which, when executed by a processor, cause a computer device to perform the aforementioned method of automatically fusing dental scan data with CBCT data.
The method based on the mouth-scan tooth data and the CBCT data automatic fusion can integrate the advantages of high tooth crown precision of the mouth-scan data and complete tooth root form of the CBCT data, obtain the appearance form of the mouth-scan tooth crown and the CBCT tooth after the integral fusion, and solve the defects of tooth root loss of the single-side mouth-scan data and low tooth crown precision of the CBCT. The accurate anatomical structure of tooth can guide the clinician well to carry out work, improves the precision of tooth treatment.
In the previous description, numerous specific details were set forth in order to provide a thorough understanding of the present invention. The foregoing description is only a preferred embodiment of the invention, which can be embodied in many different forms than described herein, and therefore the invention is not limited to the specific embodiments disclosed above. And that those skilled in the art may, using the methods and techniques disclosed above, make numerous possible variations and modifications to the disclosed embodiments, or modify equivalents thereof, without departing from the scope of the claimed embodiments. Any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the scope of the technical solution of the present invention.
Claims (10)
1. A method for automatically fusing oral scan tooth data and CBCT data is characterized in that: the method comprises the following steps:
s1: loading the grid data scanned by the port;
s2: segmenting teeth according to the oral scanning grid data loaded in the step S1;
s3: loading CBCT data;
s4: performing AI segmentation on the CBCT data loaded in the step S3;
s5: the CBCT data segmentation result obtained in the step S4 is generated in a gridding mode;
s6: registering the oral-scanning dental crown data with CBCT gridding data;
s7: according to the CBCT matrix information of the oral scanning data, calculating the coordinate position information of the upper teeth and the lower teeth after the registration of the CBCT, and generating new CBCT grid data of the upper teeth and the lower teeth;
s8: traversing each point A on the oral-scan upper dental crown grid data, and calculating the distance from each point in the CBCT upper dental grid data to the point A to obtain a point B with the closest distance, so that each point on the oral-scan upper dental crown grid data can find a matched point in the CBCT upper dental grid data;
s9: calculating each point on the dental scan lower dental crown mesh data and a matched point in the CBCT lower dental mesh data with reference to the step S8;
s10: matching point sets in upper teeth and lower teeth grids of the CBCT are selected, the upper teeth matching points are in a first group, the lower teeth matching points are in a second group, matched dental crown data of the oral scan are in a target point set, deformation is carried out on the grid point data selected by the CBCT, so that the whole CBCT tooth is correspondingly changed, and the deformed CBCT grid data is obtained;
s11: and performing grid reconstruction optimization on the CBCT grid data in the step S10, performing Delaunay remesh, and generating an updated grid with excellent quality.
2. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: the raster grid data in step S1 is an object composed of a plurality of triangular patches.
3. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: in step S2, AI intelligent segmentation is adopted; or the traditional mesh segmentation method is used for manually editing and cutting the outline on the oral scanning integral mesh model to segment the teeth.
4. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: the CBCT data in step S3 includes a series of two-dimensional slice data in dicom format.
5. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: a conventional AI medical image segmentation framework is employed in step S4.
6. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: in step S5, the marching cube or Delaunay method is used to generate the mesh data.
7. The method for automatic fusion of the oral scan dental data and the CBCT data according to claim 1, wherein: in step S6, three or more groups of corresponding points with matched positions are clicked on the oral scan dental crown data and the CBCT gridding data, respectively, to perform registration; or automatically calculating three or more groups of corresponding points to carry out registration based on the morphological characteristics or the position characteristics.
8. A system for automatically fusing dental scan data and CBCT data is characterized in that: the method comprises the following steps:
one or more processors; and
one or more memories having stored therein a computer-executable program that, when executed by the processor, performs the method of automated fusion of oral dental scan data with CBCT data of any of claims 1-7.
9. A computer-readable storage medium characterized by: stored thereon computer executable instructions for implementing the method of automatic fusion of oral dental scan data with CBCT data according to any of claims 1-7 when executed by a processor.
10. A computer program product, characterized in that: the computer program product comprises computer instructions which, when executed by a processor, cause a computer device to perform a method of automatic fusion of oral scan dental data with CBCT data as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210196089.8A CN114549540A (en) | 2022-03-01 | 2022-03-01 | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210196089.8A CN114549540A (en) | 2022-03-01 | 2022-03-01 | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114549540A true CN114549540A (en) | 2022-05-27 |
Family
ID=81661243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210196089.8A Pending CN114549540A (en) | 2022-03-01 | 2022-03-01 | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114549540A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115830287A (en) * | 2023-02-20 | 2023-03-21 | 汉斯夫(杭州)医学科技有限公司 | Tooth point cloud fusion method, equipment and medium based on laser oral scanning and CBCT reconstruction |
| CN116671956A (en) * | 2023-07-17 | 2023-09-01 | 广州医思信息科技有限公司 | Oral cavity data acquisition method based on comparison model |
-
2022
- 2022-03-01 CN CN202210196089.8A patent/CN114549540A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115830287A (en) * | 2023-02-20 | 2023-03-21 | 汉斯夫(杭州)医学科技有限公司 | Tooth point cloud fusion method, equipment and medium based on laser oral scanning and CBCT reconstruction |
| CN115830287B (en) * | 2023-02-20 | 2023-12-12 | 汉斯夫(杭州)医学科技有限公司 | Tooth point cloud fusion method, device and medium based on laser mouth scanning and CBCT reconstruction |
| CN116671956A (en) * | 2023-07-17 | 2023-09-01 | 广州医思信息科技有限公司 | Oral cavity data acquisition method based on comparison model |
| CN116671956B (en) * | 2023-07-17 | 2023-10-03 | 广州医思信息科技有限公司 | Oral cavity data acquisition method based on comparison model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363858B (en) | Three-dimensional face reconstruction method and system | |
| CN112200843B (en) | Super-voxel-based CBCT and laser scanning point cloud data tooth registration method | |
| CN105447908B (en) | Dental arch model generation method based on oral cavity scan data and CBCT data | |
| CN110189352B (en) | Tooth root extraction method based on oral cavity CBCT image | |
| CN111862171B (en) | CBCT and laser scanning point cloud data tooth registration method based on multi-view fusion | |
| CN106327535B (en) | Fusion method of tooth root and intraoral scanned dental crown of CBCT (cone beam computed tomography) | |
| CN108765474A (en) | A kind of efficient method for registering for CT and optical scanner tooth model | |
| CN111415419B (en) | Method and system for making tooth restoration model based on multi-source image | |
| JP2022000211A (en) | Method and device for removing teeth row mesh braces | |
| CN107808156A (en) | Area-of-interest exacting method | |
| CN114549540A (en) | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof | |
| CN108648283B (en) | Tooth segmentation method and device | |
| CN106570859B (en) | Tooth image analysis system | |
| GB2505936A (en) | 3D modelling of scanned body | |
| US11704819B2 (en) | Apparatus and method for aligning 3-dimensional data | |
| CN104978440B (en) | Method for establishing and registering heart model and multi-plane reconstruction | |
| TW201725554A (en) | Single chamber mapization system and method for cardiac medical image reconstructing a sequential sectional image of this chamber and performing mapization expansion | |
| CN102254317A (en) | Method for automatically extracting dental arch curved surface in dental implantation navigation | |
| CN112515787B (en) | Three-dimensional dental data analysis method | |
| CN115619773B (en) | Three-dimensional tooth multi-mode data registration method and system | |
| CN112785609B (en) | CBCT tooth segmentation method based on deep learning | |
| WO2024046400A1 (en) | Tooth model generation method and apparatus, and electronic device and storage medium | |
| CN116205956A (en) | Point cloud registration method and device and medical imaging equipment | |
| CN113393470A (en) | Full-automatic tooth segmentation method | |
| Ben-Hamadou et al. | 3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |