CN115619773B - Three-dimensional tooth multi-mode data registration method and system - Google Patents
Three-dimensional tooth multi-mode data registration method and system Download PDFInfo
- Publication number
- CN115619773B CN115619773B CN202211451737.6A CN202211451737A CN115619773B CN 115619773 B CN115619773 B CN 115619773B CN 202211451737 A CN202211451737 A CN 202211451737A CN 115619773 B CN115619773 B CN 115619773B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- model
- tooth
- crown
- dental
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000009466 transformation Effects 0.000 claims abstract description 74
- 238000010606 normalization Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 210000000332 tooth crown Anatomy 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 27
- 238000005070 sampling Methods 0.000 claims description 22
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 15
- 230000005484 gravity Effects 0.000 claims description 9
- 230000001131 transforming effect Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 21
- 239000000126 substance Substances 0.000 description 17
- 210000004746 tooth root Anatomy 0.000 description 17
- 230000006870 function Effects 0.000 description 15
- 239000013598 vector Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 230000000694 effects Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000007408 cone-beam computed tomography Methods 0.000 description 6
- 210000000988 bone and bone Anatomy 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 210000000214 mouth Anatomy 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004763 bicuspid Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 210000004283 incisor Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 210000003464 cuspid Anatomy 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 210000004357 third molar Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
- A61C7/002—Orthodontic computer assisted systems
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- General Engineering & Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a three-dimensional tooth multi-mode data registration method and a three-dimensional tooth multi-mode data registration system, and belongs to the technical field of three-dimensional point cloud and grid processing. Acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining crown information and constructing a three-dimensional crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model; sequentially carrying out initial pose normalization, rough registration and fine registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary fine registration on each single crown model in the three-dimensional dental crown model to obtain a rigidly transformed single crown model; according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information; the limitation of single data is made up, and more comprehensive tooth information is obtained; the problem of exist among the prior art "can't show the comprehensive information of tooth" is solved.
Description
Technical Field
The application relates to the technical field of three-dimensional point cloud and grid processing, in particular to a three-dimensional tooth multi-mode data registration method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The method has the advantages that the method is suitable for the oral medical market, and the new computer-assisted medical technology based on the Internet, big data and artificial intelligence technology is developed, so that the treatment of the oral medical is more accurate and efficient, and a foundation is laid for adapting to the ever-increasing market demand. Among them, the digital scanning technology has become a computer-aided medical technology which is gradually popularized in clinical medicine, and the digital imaging precision is significantly improved and multi-modal.
When describing the same object, multi-mode refers to multiple types of data acquired through different views or fields, wherein each view or field is called a mode, and multi-mode fusion refers to integrating information of multiple modes to exert the advantages of each mode to the maximum extent, and the information loss in fusion needs to be reduced to a certain extent.
Because the diagnosis purpose and the data acquisition mode are different, the oral cavity has a multi-mode data form, including oral scan data, CBCT (Cone-Beam Computed Tomography) data, an oral X-ray panoramic image, a head shadow lateral image, a tooth photo and the like, and the difference between various data is large and the data has both advantages and disadvantages. For example, although the CBCT data can obtain three-dimensional information of a complete tooth including a tooth root, the boundary is fuzzy and the resolution is low due to problems of adhesion of adjacent teeth, low contrast with surrounding alveolar bones and the like, and it is difficult to accurately describe the occlusal relationship of the tooth; the oral scan data provides high-resolution dental crown geometric characteristic information, but the dental root state cannot be checked; the head shadow side position diagram can clearly understand the structures of soft and hard tissues and the relative position relationship of the soft and hard tissues; the oral cavity X-ray panoramic image can provide insight into potential tooth problems such as wisdom teeth and malposition.
With the development of the oral data acquisition technology, the orthodontic industry has become the leading position of digital application in the oral field, the most core part in orthodontic treatment is to predict the tooth movement trend, the digital orthodontic treatment can realize accurate correction through a digital scanning device, and the personalized intermediate correction step and the final correction result suitable for a patient can be intuitively generated by tooth arrangement and movement path planning through 3D tooth modeling. In clinical orthodontic treatment, the operation is generally performed by using dental crown information obtained from oral scanning data, but because of the influences of variable alveolar bone anatomical conditions, wrong tooth position judgment, lack of tooth root information and the like, the tooth moving speed in an orthodontic treatment scheme is higher than the reconstruction speed of an alveolar bone, and the hazards of bone windowing, bone cracking and the like are caused.
For orthodontic problems, operation is far from enough performed by means of dental crown information obtained by mouth scanning data, and multi-modal data are required to be combined for multi-modal data registration. The multi-modal data registration is generally divided into two steps of coarse registration and fine registration, wherein the coarse registration refers to approximately aligned transformation of data, a good initial pose is provided, and the fine registration focuses on detail differences among data, so that registration errors can be further reduced. Various multi-modal registration algorithms can obtain considerable registration results on a data set with good quality, but for tooth data which contains more noise points, has unobvious geometric features and has missing information, a relatively ideal registration result can not be obtained by a mature algorithm.
Disclosure of Invention
In order to solve the defects of the prior art, the application provides a three-dimensional tooth multi-mode data registration method, which makes full use of complementarity among tooth multi-mode data, and registers data with similar expression forms to make up respective advantages and disadvantages, so that comprehensive information of teeth is presented to the greatest extent.
In a first aspect, the application provides a three-dimensional dental multi-modal data registration method;
a three-dimensional dental multi-modality data registration method, comprising:
acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
sequentially carrying out initial pose normalization, rough registration and fine registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary fine registration on each single crown model in the three-dimensional dental crown model to obtain a rigidly transformed single crown model;
and according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information.
In a second aspect, the present application provides a three-dimensional dental multi-modal data registration system;
a three-dimensional dental multi-modality data registration system, comprising:
a data pre-processing module configured to: acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
a rigid transformation module configured to: sequentially carrying out initial pose normalization, rough registration and fine registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary fine registration on each single tooth model in the three-dimensional dental crown model to obtain a rigidly transformed single tooth crown model;
a non-rigid transformation module configured to: and according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information.
Compared with the prior art, the beneficial effects of this application are:
1. the invention focuses on two data of CBCT data and oral scan data, extracts three-dimensional tooth information and three-dimensional dental crown information, analyzes different characteristics of multi-modal data of teeth, develops research around a key link in orthodontic and repairing processes, namely multi-modal data registration, and effectively utilizes and fuses advantageous characteristics, thereby making up the limitation of single-class data, being a basic data processing process of digital orthodontic and playing an important role in the development of digital dentistry;
2. the invention provides global rigidity transformation before local rigidity transformation, which can keep the arrangement pose of original teeth by transforming the whole upper/lower jaw teeth and avoid great error pose transformation of a single tooth;
3. compared with the common rigid transformation, the non-rigid transformation constrained by the distance term and the rigidity term can obtain a more accurate transformation result;
4. the method can reconstruct and generate a high-precision model, acquire more comprehensive tooth information, and analyze various problems such as tooth arrangement, characteristic detection, tooth root generation and the like by using the reconstructed model;
5. the invention provides the problem of registration based on three-dimensional model data, and the method can be popularized to other model data and can meet the data processing requirements in other industrial fields.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a schematic flow chart diagram provided by an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating the preprocessing effect of the three-dimensional tooth model according to the embodiment of the present application;
FIG. 3 is a schematic diagram illustrating the pretreatment effect of the three-dimensional dental crown model according to the embodiment of the present application;
fig. 4 is a schematic flow chart of initial pose normalization provided in the embodiment of the present application;
fig. 5 is a schematic diagram of an initial pose normalization effect provided in the embodiment of the present application;
fig. 6 is a schematic diagram illustrating an effect of global coarse registration provided in an embodiment of the present application;
fig. 7 is a schematic diagram illustrating an effect of another angle of global coarse registration provided in an embodiment of the present application;
fig. 8 is a schematic diagram illustrating an effect of global fine registration provided in an embodiment of the present application;
fig. 9 is a schematic diagram illustrating an effect of another angle of global fine registration provided in an embodiment of the present application;
FIG. 10 is a schematic diagram of a non-rigid transformation process provided in an embodiment of the present application;
FIG. 11 is a schematic diagram of the effect of a three-dimensional tooth model with high-precision crown information provided by an embodiment of the present application;
fig. 12 is a schematic diagram illustrating another angle effect of the three-dimensional tooth model with high-precision crown information according to the embodiment of the present application.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
In the prior art, the oral cavity has a multi-mode data form, and various data have large difference and are beneficial and disadvantageous, so that tooth information cannot be comprehensively and accurately displayed; therefore, the three-dimensional tooth multi-mode data registration method provided by the application fully utilizes complementarity among tooth multi-mode data, and registers data with similar expression forms to make up respective advantages and disadvantages, so that comprehensive information of teeth is presented to the maximum extent.
A three-dimensional dental multi-modality data registration method, comprising:
acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
sequentially carrying out initial pose normalization, rough registration and precise registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary precise registration on each single dental crown model in the three-dimensional dental crown model to obtain a rigidly transformed single dental crown model;
and according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information.
Further, the specific steps of preprocessing the three-dimensional tooth model and the three-dimensional dental crown model are as follows:
segmenting the three-dimensional tooth model to obtain a plurality of single tooth models; segmenting the three-dimensional dental crown model to obtain a plurality of single dental crown models;
carrying out grid encryption processing on each single tooth model in the three-dimensional tooth model, and carrying out smooth boundary processing on each single tooth crown model in the three-dimensional tooth crown model;
each single tooth model and each single crown model are numbered.
Further, the specific steps of carrying out initial pose normalization on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model are as follows:
rotating the three-dimensional tooth model and the three-dimensional dental crown model to be parallel to an XOY plane, and removing the root part of the three-dimensional tooth model according to the gravity center of the rotated three-dimensional tooth model;
and normalizing the positions of the three-dimensional tooth crown model after rotation and the three-dimensional tooth model after the root part is removed.
Further, the specific steps of roughly registering the three-dimensional tooth model and the three-dimensional dental crown model after the normalization processing of the initial pose are as follows:
sampling farthest points of the normalized three-dimensional dental crown model and the normalized three-dimensional dental model to obtain a fast point characteristic histogram of the three-dimensional dental model and a fast point characteristic histogram of the three-dimensional dental crown model;
and according to the fast point characteristic histogram of the three-dimensional tooth model and the fast point characteristic histogram of the three-dimensional tooth crown model, estimating corresponding points of the three-dimensional tooth crown model in the three-dimensional tooth model, removing error point pairs, and reducing the distance between the corresponding points through loop iteration to realize global coarse registration.
Further, the specific steps of carrying out fine registration on the three-dimensional tooth model and the three-dimensional dental crown model after coarse registration comprise:
and according to the three-dimensional tooth model and the three-dimensional dental crown model after the global rough registration, calculating the closest point of each point in the three-dimensional dental crown model in the three-dimensional tooth model, acquiring a transformation matrix which enables the distance between the corresponding closest points to be minimum, and transforming the three-dimensional dental crown model before sampling the farthest point to realize the global precise registration.
Further, the specific steps of performing secondary fine registration on each single crown model in the three-dimensional crown model are as follows:
according to the single tooth model in the three-dimensional tooth model, calculating the nearest point of each point in each single tooth crown model in the three-dimensional tooth crown model after precise registration in the corresponding single tooth model, acquiring a transformation matrix which enables the distance between the corresponding nearest points to be minimum, and transforming the single tooth crown model before sampling the farthest points to realize local precise registration.
Further, according to each single crown model after rigid transformation, the specific steps of performing non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model are as follows:
allocating an affine transformation to each point of the three-dimensional tooth model, and setting a distance term and a rigidity term according to the rigidly transformed single crown model and the three-dimensional tooth model;
setting regularization constraints on the distance term and the rigidity term to obtain an optimal affine transformation matrix;
and transforming each point of the three-dimensional tooth model through the optimal affine transformation matrix to obtain the three-dimensional tooth model with high-precision dental crown information.
Further, after setting the distance term, before setting the stiffness term, the method further includes:
searching boundary points of the three-dimensional dental crown model, and setting the boundary points of the three-dimensional dental crown model as the closest points which can not be found by the three-dimensional dental model;
and calculating the F norm of each point normal after the three-dimensional dental crown model is transformed each time and the normal of the corresponding point in the three-dimensional dental model, and carrying out normal constraint.
Further, the three-dimensional tooth model and the three-dimensional dental crown model are three-dimensional mesh models.
Next, a three-dimensional dental multi-modal data registration method disclosed in this embodiment will be described in detail with reference to fig. 1 to 12. The three-dimensional tooth multi-modal data registration method comprises the following steps:
step 1, obtaining three-dimensional tooth information, constructing a three-dimensional tooth model, obtaining dental crown information and constructing a three-dimensional dental crown model, wherein the three-dimensional tooth model and the three-dimensional dental crown model are three-dimensional mesh models; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model; the method comprises the following specific steps:
step 1.1, acquiring three-dimensional tooth information through CBCT data, and constructing a three-dimensional tooth model; and obtaining the information of the dental crown through the oral scan data to construct a three-dimensional dental crown model.
Specifically, when reading CBCT data, directly reading a dental DICOM (Digital Imaging and Communications in Medicine) file and performing file format conversion, obtaining a bitmap file corresponding to each slice, reconstructing three-dimensional volume data based on the bitmap file, obtaining complete dental three-dimensional information based on the three-dimensional volume data through a topoenet network model, and reconstructing a three-dimensional dental model; and reading the oral scanning data, directly reading an STL (Stereolithography) file acquired by an oral scanning scanner, and acquiring a three-dimensional dental crown model with the same point cloud quantity through a sampling algorithm, wherein the three-dimensional dental crown model and the three-dimensional dental crown model are unified into an obj format.
Step 1.2, segmenting the three-dimensional tooth model to obtain a plurality of single tooth models; the three-dimensional dental crown model is segmented to obtain a plurality of single dental crown models; in this embodiment, the three-dimensional tooth model is divided into 28 single tooth models, and the three-dimensional crown model is divided into 28 single crown models.
And step 1.3, carrying out grid encryption processing on each single tooth model in the three-dimensional tooth model.
Specifically, each single tooth model is subjected to grid subdivision, and the number of points and surfaces is increased by adding edge points and updating original points.
Because the meshes of the segmented three-dimensional dental crown model and the three-dimensional dental model are different in density, wherein the meshes of the three-dimensional dental model are sparse, in order to ensure the precision of the three-dimensional dental model at the gully of the dental crown in the subsequent non-rigid transformation, the mesh subdivision is carried out on the three-dimensional dental model based on the LOOP subdivision idea, namely, a vertex is added on each edge of the mesh, the vertices in the same triangular face are connected by using a newly added vertex to form a new triangular face patch, and the positions of the vertices are adjusted simultaneously, and the following four adjustment modes are provided according to whether the points are newly added points and whether the points are boundary points:
(1) For vertices already existing inside the mesh
New position
The calculation is as follows:
wherein the content of the first and second substances,
is a vertex
The degree of (a) to (b),
is composed of
The adjacent vertex of (a) is,
the weights of the neighboring vertices.
（2）For vertices where the mesh boundary already exists
New position
The calculation is as follows:
wherein the content of the first and second substances,
and
is prepared by reacting with
Two adjacent vertices.
(3) For newly added vertexes in the grid
New position
The calculation is as follows:
wherein the content of the first and second substances,
is located at the position of
And
the edge of the structure is provided with a plurality of grooves,
and
to be shared
Two other points of the two triangular patches of the edge.
(4) Adding new vertex to grid boundary
New position
The calculation is as follows:
wherein the content of the first and second substances,
and
two vertices that form a boundary.
In this embodiment, a corresponding adjustment mode is selected for adjustment according to the positions of different points, whether the points are newly added points, and whether the points are boundary points.
And step 1.4, performing smooth boundary treatment on each single crown model in the three-dimensional crown model, and removing crown curl information.
Specifically, a low-pass filter constructed by using a windowed sinc function is used for smoothing the single-particle crown model, and the process of constructing the low-pass filter is as follows:
(1) Carrying out inverse Fourier transform on the ideal low-pass filter to obtain a sinc function;
(2) Intercepting a segment of sinc function to obtain a new sinc function with discontinuous break points;
(3) Selecting and generating window functions with the same size;
(4) Multiplying the window function by the new sinc function to enable the windowed signal obtained by multiplication to better meet the periodicity requirement of Fourier transform;
(5) And carrying out Fourier forward transform on the windowed signal to obtain a final low-pass filter, and avoiding overlarge shrinkage in the smoothing process so as to reduce detail loss.
And step 1.5, labeling each single tooth model in the three-dimensional tooth model and each single crown model in the three-dimensional crown model so as to determine the corresponding relation.
Specifically, in order to conveniently find the corresponding relation, the single tooth model and the corresponding single crown model are respectively marked according to the FDI international dental union recording method. Illustratively, taking 28 teeth as an example, the upper and lower teeth are divided into 4 groups, each group comprises 7 teeth, each tooth is represented by a two-digit Arabic numeral, wherein the first digit represents the quadrant where the tooth is located, the upper right, upper left, lower left and lower right positions of the patient are respectively quadrants 1, 2, 3 and 4, the second digit represents the position where the tooth is located, and incisors, lateral incisors, cuspids, first premolars, second premolars, first posterior molars and second posterior molars from the middle to the edge are respectively marked as 1-7.
Step 2, global rigid transformation with the preprocessed three-dimensional tooth model as target data and the preprocessed three-dimensional tooth crown model as source data, specifically comprising:
step 2.1, carrying out initial pose normalization on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model; the method comprises the following specific steps:
and 2.11, fitting planes of the three-dimensional tooth model and the three-dimensional dental crown model.
Specifically, a RANSAC (Random Sample Consensus) algorithm is used for fitting the plane equations of the three-dimensional tooth model and the three-dimensional dental crown model, and the process is as follows:
(1) Randomly selecting three points in a given point set of the three-dimensional tooth model and the point set of the three-dimensional crown model, and calculating a corresponding plane equation:
wherein the content of the first and second substances,
is a normal vector of a plane, and is,
is a constant term.
(2) The distances of all points to this plane are calculated:
wherein the content of the first and second substances,
is a normal vector of a plane, and is,
is a constant term.
(3) Setting a distance threshold
If, if
If the local point is an in-office point (inerals), otherwise, the local point is an out-office point (outliers), the number of the in-office points is recorded, and the number of the in-office points is expressed as
(ii) a Wherein the content of the first and second substances,
=0.01。
(4) Repeating the above steps when
At maximum, the selected fitting parameters
Most preferred.
Step 2.12, the rotation axis and the rotation angle are obtained by utilizing the optimal fitting parameters to rotate the three-dimensional tooth model and the three-dimensional dental crown model to be parallel to the XOY plane, and the specific steps are as follows:
(1) Normalizing the plane normal vectors of the three-dimensional tooth model and the three-dimensional dental crown model, wherein the normalized plane normal vector of the three-dimensional tooth model is expressed as
Normalized planar normal vector representation of three-dimensional dental crown model as
The normal vector of the XOY plane is expressed as
。
(2) Will be provided with
And
are respectively connected with
And performing dot product operation, and obtaining an included angle serving as a rotation angle of the three-dimensional tooth model and the three-dimensional dental crown model.
(3) Will be provided with
And
are respectively connected with
And performing cross product operation, and normalizing the obtained vector to be used as a rotating shaft of the three-dimensional tooth model and the three-dimensional dental crown model.
(4) Solving rotation matrixes of the three-dimensional tooth model and the three-dimensional dental crown model respectively by utilizing a Rodrigues (Rodrigues) rotation equation in combination with the rotation axis and the rotation angle
. The Rodrigues (Rodrigues) rotation equation is as follows:
wherein the content of the first and second substances,
the unit matrix is represented by a matrix of units,
which indicates the angle of rotation of the disc,
showing the axis of rotation.
(5) Left multiplication rotation matrix for point cloud in three-dimensional tooth model and three-dimensional dental crown model
It can be rotated to be parallel to the XOY plane by transformation.
And 2.13, performing conditional filtering on the rotated three-dimensional tooth model to remove the tooth root.
Specifically, the center of gravity of the rotated three-dimensional tooth model is calculated, the center of gravity is taken as a boundary, the scope is set to be the z-axis because the center of gravity is parallel to the XOY plane, when the maxillary data is processed, a part smaller than the center of gravity is reserved, when the mandibular data is processed, a part larger than the center of gravity is reserved, and thus the tooth root is removed.
And 2.14, carrying out normalization treatment on the three-dimensional tooth model with the tooth root removed and the rotated three-dimensional tooth crown model.
Specifically, the centers of gravity of the three-dimensional tooth model with the tooth root removed and the three-dimensional tooth crown model after rotation are calculated, the three-dimensional tooth model with the tooth root removed is translated on the x axis, the y axis and the z axis respectively, the center of gravity of the three-dimensional tooth model with the tooth root removed is coincided with the origin of coordinates, the three-dimensional tooth crown model after rotation is translated on the x axis, the y axis and the z axis respectively, and the center of the three-dimensional tooth crown model after rotation is coincided with the origin of coordinates, so that the three-dimensional tooth model and the three-dimensional tooth crown model are basically located on the same plane.
2.2, in order to improve the calculation efficiency, carrying out rough registration on the three-dimensional tooth model and the three-dimensional dental crown model after the normalization processing of the initial pose; the method comprises the following specific steps:
2.21, respectively carrying out farthest point sampling on the three-dimensional tooth model with the tooth root removed and the three-dimensional dental crown model; for point cloud, the farthest point sampling can cover all points in the space to the greatest extent, uniform sampling can be realized, and the realization process is as follows:
(1) Point set in three-dimensional tooth model with root removed
Randomly selecting a point
As the initial point, sequentially calculating the distances between other points and the initial point and storing the distances in an array
In the method, the point with the farthest distance is selected
Adding to the set of sampling points
In (1).
(2) Selecting the next sampling point and calculating othersSet of point-to-sample points
Selecting the distance between each point, selecting the point with the closest distance, and storing the point into an array
Performing the following steps;
(3) From
Selecting the point corresponding to the farthest distance
Adding to the set of sampling points
In (1).
(4) Repeating the steps (2) and (3) until the number of the selected sampling points meets the set requirement, wherein the number of the points set in the embodiment is 5000.
The process of sampling the farthest point of the three-dimensional dental crown model is the same as the above, and is not described herein again.
And 2.22, respectively calculating normal line information of point cloud data in the three-dimensional tooth model and the three-dimensional dental crown model after sampling the farthest point.
Specifically, a Principal Component Analysis (PCA) method is adopted, and a kd-tree is used for searching
A plane normal vector fitted by each nearest point is used as a normal vector of a current query point, and as texture information in teeth is rich, K neighbor number is set to be 10, a fitting plane is calculated, namely, a feature vector and a feature value of a covariance matrix are analyzed, the covariance matrix is created from neighbor elements of the query points, and for each point
Corresponding protocolVariance matrix
The following were used:
wherein the content of the first and second substances,
indicating points
The number of the neighboring points is,
representing the three-dimensional centroid of the nearest neighbor element,
represents the second of the covariance matrix
The value of the characteristic is compared with the value of the characteristic,
is shown as
A feature vector.
And 2.23, respectively calculating the FPFH (Fast Point Feature Histograms) of the midpoints of the three-dimensional tooth model and the three-dimensional crown model by using the normal.
Specifically, as a Point cloud Feature descriptor, the FPFH is improved from a PFH (Point Feature Histogram), and by obtaining an optimal sample surface change condition by combining an included angle relationship between three-dimensional coordinate axis data and normal vectors, the complexity of Histogram Feature calculation can be Simplified, and only the SPFH (Simplified Point Feature Histogram) of each Point in the spatial neighborhood is calculated, so that the Point Feature straight line is SimplifiedBlock diagram) including
Compared with the PFH, the three characteristic elements reduce the interconnection among the field points, because the calculation amount of the FPFH is large, in order to ensure that the details are reflected and simultaneously improve the calculation efficiency, the Kd-tree is utilized to set the K neighbor number to be 20 so as to determine the nearest neighbor set of the points, and the SPFH is assigned to the FPFH through the following weight combination:
wherein the content of the first and second substances,
in order to be a point of inquiry,
in the form of a neighborhood of points, the points,
the distance weight between the query point and the neighboring points.
And 2.24, estimating corresponding points of the three-dimensional dental crown model after sampling the farthest points in the three-dimensional dental model after sampling the farthest points according to the fast point feature histogram of the three-dimensional dental model and the fast point feature histogram of the three-dimensional dental crown model, and reducing the distance between the corresponding points through cyclic iteration to realize global coarse registration.
Specifically, based on RANSAC (Random Sample Consensus) algorithm thought, the corresponding relation between the three-dimensional tooth model and the three-dimensional dental crown model is estimated according to the FPFH characteristics, corresponding point pairs are preliminarily estimated, error point pairs are removed, namely one or more points with similar FPFH characteristics in the three-dimensional dental crown model are randomly searched in the three-dimensional dental crown model, one point is randomly selected from the similar points to serve as the corresponding point of the three-dimensional dental crown model in the three-dimensional dental crown model, the distance between the corresponding points is reduced through cyclic iteration, a transformation matrix between the corresponding points is calculated, the performance of the transformation matrix is evaluated by using Huber and other distance errors and functions until the optimal measurement error result is achieved, and finally the obtained rigid transformation matrix is used as a global coarse registration result. The Huber penalty function is calculated as follows:
wherein the content of the first and second substances,
for the given value in advance,
is as follows
The set corresponds to the distance difference after the point transformation.
And 2.3, carrying out fine registration on the three-dimensional tooth model and the three-dimensional dental crown model after the coarse registration.
Specifically, in order to improve the registration efficiency, the three-dimensional dental crown model after sampling the farthest Point is used as the source data, the three-dimensional dental model before sampling the farthest Point is used as the target data, the global coarse registration result is used as the initial state, the ICP (Iterative Closest Point) algorithm is used for fine registration, that is, the Closest Point of each Point in the three-dimensional dental crown model in the three-dimensional dental model is calculated and used as the corresponding Point, the transformation which minimizes the error function is obtained according to the idea of the least square method, the Iterative calculation is carried out until the convergence condition is met, the convergence condition can also include the maximum iteration number, the difference value of two change matrixes and the like, and the aim is to find the rotation matrix between the source data and the target data
And translation vector
Transforming the three-dimensional dental crown model before sampling the farthest point by using the obtained transformation matrix,a global fine registration result can be obtained. The error function is expressed in terms of Mean Square Error (MSE) as follows:
wherein the content of the first and second substances,
is a data set of the point cloud to be registered,
for neutralization of a target point cloud
The closest corresponding point of (a) to (b),
is the number of point clouds in the three-dimensional crown model,
a matrix of rotations is represented, which is,
representing a translation vector.
And 2.4, performing secondary fine registration on each single crown model in the three-dimensional crown model.
Specifically, in order to further reduce the error, the ICP precise registration is continuously performed on the single three-dimensional dental crown model in sequence by taking the global precise registration result as an initial value.
And 3, according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information. The method specifically comprises the following steps:
and 3.1, taking the rigidly transformed single tooth crown model as target data and the single tooth model as source data, and determining an affine transformation for each point in each single tooth model.
And 3.2, setting the weight of the distance item.
Specifically, to find the best deformation for a given stiffness, the same principle as ICP fine registration in the above step, needs to search the closest point in the three-dimensional crown model to the three-dimensional tooth model to find a set of preliminary correspondences while ensuring that the corresponding points are close, but the difference is that this step sets a weight to the distance
The distance term is as follows:
wherein the content of the first and second substances,
for each point in the three-dimensional tooth model,
for the weight corresponding to each point in the graph,
for the affine transformation corresponding to each point,
are corresponding points in the three-dimensional crown model.
Searching a Nearest point in the three-dimensional dental crown model for each query point in the three-dimensional dental model by utilizing KNN (K-Nearest Neighbor search), ascending the acquired distance values, setting a Gaussian kernel function for the sorted distances to obtain weights, wherein the smaller the distance is, the closer the point weight to the three-dimensional dental crown model is, and the larger the distance is, the closer the point weight to the three-dimensional dental crown model is, the larger the distance is, the closer the point weight to the three-dimensional dental crown model is. The gaussian kernel function is as follows:
wherein the content of the first and second substances,
in order to be the distance weight,
is the shortest distance between corresponding points of the three-dimensional tooth model and the three-dimensional dental crown model,
the degree of dispersion of the distance is described and set to 0.2 and 0.3 in two iterations, respectively.
And 3.3, searching boundary points of the three-dimensional dental crown model to process the missing tooth root data.
Specifically, in order to make the transformation effect of the tooth crown and the tooth root in the three-dimensional tooth model smooth, the boundary point with small three-dimensional circular massage needs to be searched; because the three-dimensional dental crown model lacks dental root information, corresponding points of a dental root part in the three-dimensional dental crown model are mostly boundary points of the three-dimensional dental crown model, and the phenomenon that the whole dental root part of the three-dimensional dental model moves to the boundary points of the three-dimensional dental crown model can occur through iteration, the invention only hopes that the dental crown part of the reconstructed three-dimensional dental model is attached to the three-dimensional dental crown model as much as possible, but the dental root part is kept as unchanged as much as possible, so the boundary points of the three-dimensional dental crown model are regarded as corresponding points which cannot be found in the three-dimensional dental crown model, and the distance term weight corresponding to the points is set to be 0.
And 3.4, solving the problem of surface overturning in the transformation process through normal constraint.
Specifically, an F-norm of the normal of each transformed point in the three-dimensional tooth model and the normal of the corresponding point in the three-dimensional dental crown model is calculated, and the F-norm of the normal of the midpoint of the three-dimensional tooth model and the normal of the corresponding point in the three-dimensional dental crown model are multiplied by the weight, wherein the formula is as follows:
wherein the content of the first and second substances,
for one point of a three-dimensional tooth model
The normal after each transformation is used for each time,
is composed of
Normal lines of corresponding points in the three-dimensional crown model,
is the sign of Frobenius norm.
And 3.5, setting a rigidity item, restraining the transformation amplitude of the midpoint of the three-dimensional tooth, performing cycle iteration by using continuously reduced rigidity parameters, and realizing that the point in the three-dimensional tooth model gradually moves to the corresponding point in the three-dimensional dental crown model so that the dental crown part of the three-dimensional tooth model is continuously attached to the three-dimensional dental crown model.
Specifically, because a single corresponding relation cannot uniquely determine affine transformation, a rigidity term is set for the affine transformation, the similar transformation of adjacent vertexes can be restrained, a transformed model is made to be as smooth as possible, and a series of decreasing rigidity term weights are set
The three-dimensional tooth model gradually moves to the three-dimensional dental crown model along with the cycle iteration to deform, the transformation freedom degree of adjacent points is higher and higher, and the effect of fitting the three-dimensional dental crown model better can be achieved. The stiffness term is as follows:
wherein the content of the first and second substances,
is an edge in the three-dimensional tooth model,
two vertexes on the same edge in the three-dimensional tooth model,
and
for the affine transformation of two adjacent vertices,
in order for the weighting matrix to constrain the weight of rotation and translation in the affine transformation, in this embodiment,
is a matrix of the units,
is the sign of Frobenius norm.
And 3.5, forming a loss function by the distance term and the rigidity term.
Specifically, the loss function is composed of the above-mentioned distance term and stiffness term, by pairing
Can obtain a matrix set which optimizes the transformation of each point in the three-dimensional tooth model
The loss function is as follows:
wherein the content of the first and second substances,
is a weight of the stiffness term and is,
in order to be the term of the stiffness,
is a distance term.
By applying sets of matrices
The method can correspondingly transform each point in the three-dimensional tooth model, thereby obtaining the complete three-dimensional tooth model with high-precision dental crown information.
Example two
The embodiment discloses a three-dimensional tooth multi-mode data registration system, which comprises:
a data pre-processing module configured to: acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
a rigid transformation module configured to: sequentially carrying out initial pose normalization, rough registration and precise registration on the preprocessed three-dimensional tooth model and the three-dimensional dental crown model, and carrying out secondary precise registration on each single tooth model in the three-dimensional dental crown model to obtain a rigidly transformed single tooth crown model;
a non-rigid transformation module configured to: and according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information.
It should be noted here that the data preprocessing module, the rigid transformation module, and the non-rigid transformation module correspond to the steps in the first embodiment, and the modules are the same as the corresponding steps in the example and application scenarios, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer executable instructions.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (7)
1. A three-dimensional tooth multi-mode data registration method is characterized by comprising the following steps:
acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
sequentially carrying out initial pose normalization, rough registration and precise registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary precise registration on each single dental crown model in the three-dimensional dental crown model to obtain a rigidly transformed single dental crown model;
according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model to obtain the three-dimensional tooth model with high-precision crown information;
the method comprises the following specific steps of performing secondary precise registration on each single crown model in the three-dimensional crown model:
according to a single tooth model in the three-dimensional tooth model, calculating the closest point of each point in each single tooth crown model in the three-dimensional tooth crown model after precise registration in the corresponding single tooth model, acquiring a transformation matrix which enables the distance between the corresponding closest points to be minimum, and transforming the single tooth crown model before sampling the farthest point to realize local precise registration;
the specific steps of carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model according to each single tooth crown model after rigid transformation are as follows:
distributing affine transformation for each point of the three-dimensional tooth model, and setting a distance term and a rigidity term according to the rigidly transformed single crown model and the three-dimensional tooth model;
setting regularization on the distance term and the rigidity term for constraint to obtain an optimal affine transformation matrix;
transforming each point of the three-dimensional tooth model through the optimal affine transformation matrix to obtain the three-dimensional tooth model with high-precision dental crown information;
setting the distance term further includes:
searching boundary points of the three-dimensional dental crown model, and setting the boundary points of the three-dimensional dental crown model as the closest points which can not be found by the three-dimensional dental model;
and calculating the F norm of each point normal after the three-dimensional dental crown model is transformed each time and the normal of the corresponding point in the three-dimensional dental model, and carrying out normal constraint.
2. The method for multi-modal data registration of three-dimensional teeth as claimed in claim 1, wherein the pre-processing of the three-dimensional tooth model and the three-dimensional crown model comprises the following specific steps:
segmenting the three-dimensional tooth model to obtain a plurality of single tooth models; segmenting the three-dimensional dental crown model to obtain a plurality of single dental crown models;
carrying out grid encryption processing on each single tooth model in the three-dimensional tooth model, and carrying out smooth boundary processing on each single crown model in the three-dimensional crown model;
each single tooth model and each single crown model are numbered.
3. The three-dimensional multi-modal dental data registration method of claim 1, wherein the initial pose normalization of the preprocessed three-dimensional dental model and the three-dimensional dental crown model comprises the following specific steps:
rotating the three-dimensional tooth model and the three-dimensional dental crown model to be parallel to an XOY plane, and removing the root part of the three-dimensional tooth model according to the gravity center of the rotated three-dimensional tooth model;
and normalizing the positions of the three-dimensional tooth crown model after rotation and the three-dimensional tooth model after the root part is removed.
4. The three-dimensional multi-modal dental data registration method of claim 3, wherein the step of coarsely registering the three-dimensional dental model and the three-dimensional dental crown model after the initial pose normalization processing comprises the steps of:
sampling farthest points of the normalized three-dimensional dental crown model and the normalized three-dimensional dental model to obtain a fast point characteristic histogram of the three-dimensional dental model and a fast point characteristic histogram of the three-dimensional dental crown model;
and estimating corresponding points of the three-dimensional dental crown model in the three-dimensional dental model and removing error point pairs according to the fast point characteristic histogram of the three-dimensional dental model and the fast point characteristic histogram of the three-dimensional dental crown model, and circularly iterating to reduce the distance between the corresponding points to realize global rough registration.
5. The method for multi-modal data registration of three-dimensional teeth according to claim 4, wherein the step of performing the fine registration of the coarsely registered three-dimensional tooth model and the three-dimensional crown model comprises the steps of:
and according to the three-dimensional tooth model and the three-dimensional dental crown model after the global rough registration, calculating the closest point of each point in the three-dimensional dental crown model in the three-dimensional tooth model, acquiring a transformation matrix which enables the distance between the corresponding closest points to be minimum, and transforming the three-dimensional dental crown model before sampling the farthest point to realize the global precise registration.
6. The three-dimensional dental multi-modal data registration method of claim 1, wherein the three-dimensional dental model and the three-dimensional crown model are each a three-dimensional mesh model.
7. A three-dimensional dental multi-modality data registration system, comprising:
a data pre-processing module configured to: acquiring three-dimensional tooth information and constructing a three-dimensional tooth model; obtaining information of the dental crown and constructing a three-dimensional dental crown model; preprocessing a three-dimensional tooth model and a three-dimensional dental crown model;
a rigid transformation module configured to: sequentially carrying out initial pose normalization, rough registration and fine registration on the preprocessed three-dimensional tooth model and the preprocessed three-dimensional dental crown model, and carrying out secondary fine registration on each single tooth model in the three-dimensional dental crown model to obtain a rigidly transformed single tooth crown model; the method comprises the following specific steps of performing secondary precise registration on each single crown model in the three-dimensional crown model:
calculating the closest point of each point in each single tooth crown model in the three-dimensional tooth crown model after precise registration in the corresponding single tooth model according to the single tooth model in the three-dimensional tooth model, acquiring a transformation matrix which enables the distance between the corresponding closest points to be minimum, and transforming the single tooth crown model before sampling the farthest points to realize local precise registration;
a non-rigid transformation module configured to: according to each single crown model after rigid transformation, carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth models to obtain the three-dimensional tooth model with high-precision crown information; the specific steps of carrying out non-rigid transformation on the corresponding single three-dimensional tooth model in the three-dimensional tooth model according to each single tooth crown model after rigid transformation are as follows:
allocating an affine transformation to each point of the three-dimensional tooth model, and setting a distance term and a rigidity term according to the rigidly transformed single crown model and the three-dimensional tooth model;
setting regularization on the distance term and the rigidity term for constraint to obtain an optimal affine transformation matrix;
transforming each point of the three-dimensional tooth model through the optimal affine transformation matrix to obtain the three-dimensional tooth model with high-precision dental crown information;
setting the distance term further includes:
searching boundary points of the three-dimensional dental crown model, and setting the boundary points of the three-dimensional dental crown model as the closest points which cannot be found by the three-dimensional dental model;
and calculating the F norm of each point normal after the three-dimensional dental crown model is transformed each time and the corresponding point normal in the three-dimensional dental model, and carrying out normal constraint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211451737.6A CN115619773B (en) | 2022-11-21 | 2022-11-21 | Three-dimensional tooth multi-mode data registration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211451737.6A CN115619773B (en) | 2022-11-21 | 2022-11-21 | Three-dimensional tooth multi-mode data registration method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115619773A CN115619773A (en) | 2023-01-17 |
| CN115619773B true CN115619773B (en) | 2023-03-21 |
Family
ID=84878936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211451737.6A Active CN115619773B (en) | 2022-11-21 | 2022-11-21 | Three-dimensional tooth multi-mode data registration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619773B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN115965771B (en) * | 2023-03-16 | 2023-05-16 | 信艺(广州)义齿研制有限公司 | Detection screening method for false tooth restoration based on non-human natural tooth color |
| CN117253011B (en) * | 2023-07-26 | 2024-04-02 | 山东大学 | Digital orthodontic-oriented virtual gum grid model generation method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112120810A (en) * | 2020-09-29 | 2020-12-25 | 深圳市深图医学影像设备有限公司 | Three-dimensional data generation method of tooth orthodontic concealed appliance |
| CN113052902A (en) * | 2020-12-29 | 2021-06-29 | 上海银马科技有限公司 | Dental treatment monitoring method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392492A (en) * | 2014-11-24 | 2015-03-04 | 中南大学 | Computer interaction type method for segmenting single tooth crown from three-dimensional jaw model |
| CN105761252B (en) * | 2016-02-02 | 2017-03-29 | 北京正齐口腔医疗技术有限公司 | The method and device of image segmentation |
| CN108765474A (en) * | 2018-04-17 | 2018-11-06 | 天津工业大学 | A kind of efficient method for registering for CT and optical scanner tooth model |
| CN113272861A (en) * | 2018-12-31 | 2021-08-17 | 3M创新有限公司 | Combining data from multiple dental anatomy scans |
| CN112991273B (en) * | 2021-02-18 | 2022-12-16 | 山东大学 | Orthodontic feature automatic detection method and system of three-dimensional tooth model |
| CN114219897B (en) * | 2021-12-20 | 2024-04-30 | 山东大学 | Tooth orthodontic result prediction method and system based on feature point identification |
| CN115349881A (en) * | 2022-07-01 | 2022-11-18 | 有研医疗器械（北京）有限公司 | Tooth crown fusion method and device combining CBCT and intraoral scanning technology |
-
2022
- 2022-11-21 CN CN202211451737.6A patent/CN115619773B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112120810A (en) * | 2020-09-29 | 2020-12-25 | 深圳市深图医学影像设备有限公司 | Three-dimensional data generation method of tooth orthodontic concealed appliance |
| CN113052902A (en) * | 2020-12-29 | 2021-06-29 | 上海银马科技有限公司 | Dental treatment monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115619773A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115619773B (en) | Three-dimensional tooth multi-mode data registration method and system | |
| CN112200843B (en) | Super-voxel-based CBCT and laser scanning point cloud data tooth registration method | |
| US11735306B2 (en) | Method, system and computer readable storage media for creating three-dimensional dental restorations from two dimensional sketches | |
| CN111862171B (en) | CBCT and laser scanning point cloud data tooth registration method based on multi-view fusion | |
| Zanjani et al. | Mask-MCNet: Tooth instance segmentation in 3D point clouds of intra-oral scans | |
| CN111784754B (en) | Tooth orthodontic method, device, equipment and storage medium based on computer vision | |
| WO2019098887A1 (en) | Dental image processing protocol for dental aligners | |
| US10346504B2 (en) | 3D modelling of bodies | |
| CN108648283B (en) | Tooth segmentation method and device | |
| US20220008175A1 (en) | Method for generating dental models based on an objective function | |
| CN111968146B (en) | Three-dimensional dental mesh model segmentation method | |
| CN112562082A (en) | Three-dimensional face reconstruction method and system | |
| Zhang et al. | Computer-aided design of dental inlay restoration based on dual-factor constrained deformation | |
| CN105528807A (en) | Teeth arrangement design method and device | |
| CN106548476A (en) | Using medical image statistics pulmonary three-dimensional feature Method On Shape | |
| Ben-Hamadou et al. | 3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge | |
| CN115546444B (en) | Tooth reconstruction method, system and terminal based on three-dimensional tooth and crown registration | |
| Qian et al. | An automatic tooth reconstruction method based on multimodal data | |
| CN115409811A (en) | Tooth model reconstruction method, device, equipment and medium based on curvature enhancement | |
| CN114758073A (en) | Oral cavity digital system based on RGBD input and flexible registration | |
| Knyaz et al. | Machine learning for approximating unknown face | |
| EP4307229A1 (en) | Method and system for tooth pose estimation | |
| EP4365855A1 (en) | Method, system, and computer program for generating 3d models of dentures in occlusion conditions | |
| CN117253011B (en) | Digital orthodontic-oriented virtual gum grid model generation method and system | |
| CN116524118B (en) | Multi-mode rendering method based on three-dimensional tooth CBCT data and oral cavity scanning model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |