CN112085740A - Tooth fast segmentation method based on three-dimensional tooth jaw model - Google Patents
Tooth fast segmentation method based on three-dimensional tooth jaw model Download PDFInfo
- Publication number
- CN112085740A CN112085740A CN202010847031.6A CN202010847031A CN112085740A CN 112085740 A CN112085740 A CN 112085740A CN 202010847031 A CN202010847031 A CN 202010847031A CN 112085740 A CN112085740 A CN 112085740A
- Authority
- CN
- China
- Prior art keywords
- tooth
- node
- dimensional
- lista
- value
- 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
- 230000011218 segmentation Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000004927 fusion Effects 0.000 claims abstract description 25
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 5
- 230000008439 repair process Effects 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 241001134453 Lista Species 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims 1
- 238000009499 grossing Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 210000000214 mouth Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000004195 gingiva Anatomy 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 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
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
Abstract
The invention provides a tooth rapid segmentation method based on a three-dimensional tooth jaw model, which comprises the following steps: s1, preprocessing the data of the input three-dimensional dental model; s2 re-modeling the shape on the three-dimensional dental model; s3 determining the grid maximum path search based on the Astar algorithm; s4, identifying the characteristics of the gingival margin line and the fusion area by using the convolutional neural network, and separating out a single tooth. The segmentation method can rapidly and accurately segment each tooth, and provides better reference value for doctors of subsequent false tooth repair.
Description
Technical Field
The invention relates to a tooth fast segmentation method based on a three-dimensional tooth jaw model, and belongs to the technical field of tooth model image processing.
Background
With the development of computer technology, the three-dimensional dental model can be conveniently digitized by an intraoral or extraoral measurement technology, so that the CAD/CAM technology is introduced into an oral cavity restoration system and has been successfully used in clinical applications (such as orthodontics, oral and collar surgery, etc.).
Tooth segmentation is an important step of a computer-aided orthodontic system, and the main task of the tooth segmentation is to accurately position, identify and extract teeth from a three-dimensional dental model of a patient. However, in the process of digitalizing the dental model, due to the influence of factors such as overlapping interference among teeth caused by oral deformity, low precision of measuring equipment, low resolution of a curved surface reconstruction method and the like, adjacent teeth of the three-dimensional dental model are adhered together without clear dental gaps, so that the local shape of the divided single tooth is lost. In the CAD/CAM system for dental restoration, individual tooth models having original shapes are required independently from each other in order to fabricate inlays, veneers, full crowns, partial crowns, simple bridges, and complete dentures. However, the current tooth segmentation method has the problems that the gum boundary of the tooth cannot be accurately positioned or the artificial interaction is excessively relied on, so that the tooth can not be rapidly and accurately segmented.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a tooth rapid segmentation method based on a three-dimensional tooth jaw model, which can rapidly and accurately segment each tooth and is convenient for dentists to treat.
In order to achieve the above object, the tooth fast segmentation method based on the three-dimensional tooth and jaw model of the present invention comprises the following steps:
s1, preprocessing the data of the input three-dimensional dental model;
s2 re-modeling the shape on the three-dimensional dental model;
s3 determining the grid maximum path search based on the Astar algorithm;
s4, identifying the characteristics of the gingival margin line and the fusion area by using the convolutional neural network, and separating out a single tooth.
Further, step S1 includes:
s11, discrete curvature analysis is carried out on the tooth three-dimensional model by adopting a local curved surface fitting method, and a curvature value k (p) of each vertex p on the dental jaw model is obtained based on the maximum principal curvature principle;
s12, stretching transformation based on histogram equalization is carried out on the curvature value, and threshold operation { k (p) > h (h is a threshold value) } is carried out on the transformed curvature value, so as to obtain an initial characteristic region;
some miscellaneous points and break points in the S13 area are processed by a three-dimensional morphological open-close operation method to obtain a final characteristic area of the boundary between the tooth and the gum.
Further, step S2 includes:
s21 detecting an interdental fusion area, realizing automatic identification of characteristic area characteristic lines by matching branch points, selecting another end point Jets (j) from the segmented characteristic lines taking any branch point Jets (i) in the branch point set as an end point according to the shortest distance principle to be used as a matching point to obtain a corresponding fusion area characteristic line, automatically identifying the corresponding fusion area characteristic line, and executing 3 times of morphological expansion operation on the identified fusion area characteristic line until the interdental fusion area is covered, namely realizing the automatic identification of the interdental fusion area;
s22, deleting the inter-dental fusion area to obtain inter-dental holes, and keeping the matched branch points to realize automatic bridging of hole repairing for subsequent tooth repair;
s23 restoring the tooth shape, constructing a curved surface corresponding to the missing part by adopting a curved surface energy constraint mode based on the vertex information of the boundary of the interdental cavity, and obtaining the tooth shape with higher approximation degree with the original tooth.
Further, in step S3, using the Astar algorithm on the curved surface where the three-dimensional dental model is effectively restored, storing the information of each abstracted vertex, and before searching the shortest distance from the starting point to the target point, creating two sets, i.e., a set ListA and a set ListB, where the set ListA is used to store the nodes that have not been processed yet, and the set ListB is used to store the nodes that have been visited, assuming that the starting node is P and the target node is Q, the specific steps of the algorithm are as follows:
s31 storing the starting node P into a ListA set;
s32 judges whether the ListA collection is empty, if the ListA collection is empty, it represents that there is no next node meeting the screening condition, i.e. there is no path, the search is finished, if there is node in the ListA collection, the next step is carried out;
s33, taking the node with the minimum cost value from the ListA set as the current optimal node, judging whether the node is the target node, if so, indicating that the shortest path is found, finishing the algorithm, and if not, continuing the next step;
s34 checking the neighborhood point of the current node, and if the neighborhood point fails or the neighboring node is in the ListB set, skipping to continue processing the next node in the neighborhood;
s35, calculating the f value of each adjacent node, if the current adjacent node is not in the ListA set or the ListB set, recording the f value of the adjacent node, then adding the current node into the path stack, then storing the adjacent node into the ListA set, if the current adjacent node is already in the ListA set, then comparing the newly calculated f value with the current f value, if the new value is smaller, replacing the old f value with the new f value, then adding the adjacent node into the path stack, if the new value is larger, not processing, processing the next adjacent node;
s36, all neighborhood nodes of the current node are processed, the current node is stored in a ListB set, and then the current node is removed from the ListA set;
s37, jump to S32 until an optimal path between P, Q points is found or no path exists.
Further, step S4 includes:
s41, inputting the dental data models provided in the steps S2 and S3 into a segmentation network for training, and respectively obtaining ca ffemodel models with network optimal weights set by 3 different parameters;
s42, completing the segmentation of the single tooth through the obtained ca ffemodel model in sequence, and performing boundary optimization processing on the gingival margin area and the interdental contact area by adopting a conditional random field model;
s43, finishing post-processing of the dental model through a back projection ray intersection algorithm and a point cloud reconstruction technology.
Further, in step S41, a tooth recognition network is constructed based on 2-level hierarchical feature learning, wherein a ReLU activation function is adopted to effectively alleviate the gradient diffusion phenomenon, and the three-dimensional convolution expression is:
wherein f () is an activation function, Pi×Qi×RiDotting at (p, q, r) for convolution kernelsWeight vector of, H(m)Is the feature vector of the mth channel, bi,jIn order to be a term of the offset,
are weights.
The tooth rapid segmentation method based on the three-dimensional tooth jaw model has the following beneficial effects:
(1) the segmentation speed is high, and compared with the traditional interactive mark control algorithm, the tooth segmentation speed of the algorithm provided by the invention is obviously improved;
(2) the segmentation precision is high, the traditional interactive labeling algorithm has under-segmentation, and the algorithm provided by the invention does not have under-segmentation;
(3) the method has strong adaptability, and can perform accurate segmentation on most three-dimensional tooth mesh models.
Drawings
The present invention will be further described and illustrated with reference to the following drawings.
FIG. 1 is a flowchart of a tooth fast segmentation method based on a three-dimensional dental model according to a preferred embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be more clearly and completely explained by the description of the preferred embodiments of the present invention with reference to the accompanying drawings.
As shown in FIG. 1, the tooth fast segmentation method based on the three-dimensional dental model in the preferred embodiment of the invention comprises the following steps:
s1, data preprocessing is carried out on the input three-dimensional dental model.
Specifically, step S1 further includes the steps of:
s11, discrete curvature analysis is carried out on the tooth three-dimensional model by adopting a local curved surface fitting method, and a curvature value k (p) of each vertex p on the dental jaw model is obtained based on the maximum principal curvature principle;
s12, stretching transformation based on histogram equalization is carried out on the curvature value, and threshold operation { k (p) > h (h is a threshold value) } is carried out on the transformed curvature value, so as to obtain an initial characteristic region;
some miscellaneous points and break points in the S13 area are processed by a three-dimensional morphological open-close operation method to obtain a final characteristic area of the boundary between the teeth and the gingiva,
opening operation:
and (3) closed operation:
s2 re-models the shape on the three-dimensional dental model.
In the process of digitalizing the dental model, because of the influence of factors such as overlapping interference between teeth, measurement equipment precision and the like caused by oral deformity, the adjacent teeth of the three-dimensional dental model are adhered together, and a clear characteristic region of a tooth and gum boundary is not available, so that the local shape of the divided single tooth is lost. It is therefore important to re-model the tooth shape of the three-dimensional dental model.
Specifically, step S2 further includes the steps of:
s21 detecting an interdental fusion area, realizing automatic identification of characteristic area characteristic lines by matching branch points, selecting another end point Jets (j) from segmented characteristic lines taking any branch point Jets (i) in a branch point set as an end point according to the shortest distance principle to be used as a matching point to obtain a corresponding fusion area characteristic line, automatically identifying the corresponding fusion area characteristic line, and performing 3 times of morphological expansion operation on the identified fusion area characteristic line until the interdental fusion area is covered, namely realizing the automatic identification of the interdental fusion area, and obtaining better results for most of dental models;
s22, deleting the inter-dental fusion area to obtain inter-dental holes, and keeping the matched branch points to realize automatic bridging of hole repairing for subsequent tooth repair;
s23 restoring the tooth shape, constructing a curved surface corresponding to the missing part by adopting a curved surface energy constraint mode based on the vertex information of the boundary of the interdental cavity, and obtaining the tooth shape with higher approximation degree with the original tooth.
By the method, higher approximation degree with the original teeth can be obtained, and an accurate three-dimensional dental model is provided for an oral cavity restoration and orthodontic system.
S3 determines a trellis-most path search based on the Astar algorithm.
Specifically, step S3 is to use the Astar algorithm to store the information of each abstracted vertex on the curved surface effectively restored by the three-dimensional dental model, and before searching the shortest distance from the starting point to the target point, create two sets, i.e., a set ListA for storing the nodes that have not been processed and a set ListB for storing the nodes that have been visited, assuming that the starting node is P and the target node is Q, the specific steps of the algorithm are as follows:
s31 storing the starting node P into a ListA set;
s32 judges whether the ListA collection is empty, if the ListA collection is empty, it represents that there is no next node meeting the screening condition, i.e. there is no path, the search is finished, if there is node in the ListA collection, the next step is carried out;
s33, taking the node with the minimum cost value from the ListA set as the current optimal node, judging whether the node is the target node, if so, indicating that the shortest path is found, finishing the algorithm, and if not, continuing the next step;
s34 checking the neighborhood point of the current node, and if the neighborhood point fails or the neighboring node is in the ListB set, skipping to continue processing the next node in the neighborhood;
s35, calculating the f value of each adjacent node, if the current adjacent node is not in the ListA set or the ListB set, recording the f value of the adjacent node, then adding the current node into the path stack, then storing the adjacent node into the ListA set, if the current adjacent node is already in the ListA set, then comparing the newly calculated f value with the current f value, if the new value is smaller, replacing the old f value with the new f value, then adding the adjacent node into the path stack, if the new value is larger, not processing, processing the next adjacent node;
s36, all neighborhood nodes of the current node are processed, the current node is stored in a ListB set, and then the current node is removed from the ListA set;
s37, jump to S32 until an optimal path between P, Q points is found or no path exists.
The Astar algorithm can finally obtain the shortest path search of an ideal gingival margin line and ensure the rapidity and the accuracy of the algorithm.
S4, identifying the characteristics of the gingival margin line and the fusion area by using the convolutional neural network, and separating out a single tooth.
Specifically, step S4 further includes the steps of:
s41, inputting the dental data models provided in the steps S2 and S3 into a segmentation network for training, and respectively obtaining ca ffemodel models with network optimal weights set by 3 different parameters;
s42, completing the segmentation of the single tooth through the obtained ca ffemodel model in sequence, and performing boundary optimization processing on the gingival margin area and the interdental contact area by adopting a conditional random field model;
s43, finishing post-processing of the dental model through a back projection ray intersection algorithm and a point cloud reconstruction technology.
More specifically, in step S41, a tooth recognition network is constructed based on 2-level feature learning, wherein a ReLU activation function is adopted to effectively alleviate the gradient diffusion phenomenon, and the three-dimensional convolution expression is:
wherein f () is an activation function, Pi×Qi×RiWeight vector, H, for the convolution kernel at (p, q, r)(m)Is the feature vector of the mth channel, bi,jIn order to be a term of the offset,
are weights.
The classifier layers are then connected in a maximally pooled and fully connected manner. In order to avoid training over-fitting and improve the generalization capability of the model, a random inactivation technology is adopted in the full connection layer, and finally the characteristic values transmitted to the output layer are input into a classifier for classification prediction, so that the extraction of the tooth characteristic region is realized, and the construction of the tooth recognition model is completed.
A CNN-based dental jaw segmentation network is established by adopting an encoder-decoder structure, a full-connection conditional random field is introduced into the dental segmentation network, and meanwhile, when an energy function is calculated, a gingival margin area and an interdental contact area are optimized by considering the correlation between any adjacent points in a dental jaw model, and local detail characteristics of a segmentation area are obtained. In order to improve the segmentation precision of a single tooth, in a constructed three-dimensional CRF (conditional random field) model, a bilateral Gaussian filter is adopted to mark adjacent point clouds in a space into a same label; and removing isolated point cloud data in the segmentation result by using a spatial smoothing Gaussian filter, further promoting continuous smoothing of the segmentation boundary by optimizing an energy function of the conditional random field, and simultaneously projecting the label result onto the original dental model by using a back projection ray intersection method and carrying out point cloud reconstruction on the original dental model. Based on the method, the single tooth can be effectively segmented finally, the accuracy and efficiency of tooth segmentation identification are improved, and a better reference value is improved for a doctor for subsequent false tooth repair.
The above detailed description merely describes preferred embodiments of the present invention and does not limit the scope of the invention. Without departing from the spirit and scope of the present invention, it should be understood that various changes, substitutions and alterations can be made herein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents. The scope of the invention is defined by the claims.
Claims (6)
1. A tooth fast segmentation method based on a three-dimensional tooth jaw model is characterized by comprising the following steps:
s1, preprocessing the data of the input three-dimensional dental model;
s2 re-modeling the shape on the three-dimensional dental model;
s3 determining the grid maximum path search based on the Astar algorithm;
s4, identifying the characteristics of the gingival margin line and the fusion area by using the convolutional neural network, and separating out a single tooth.
2. The method for rapid tooth segmentation based on three-dimensional dental model according to claim 1, wherein the step S1 includes:
s11, discrete curvature analysis is carried out on the tooth three-dimensional model by adopting a local curved surface fitting method, and a curvature value k (p) of each vertex p on the dental jaw model is obtained based on the maximum principal curvature principle;
s12, stretching transformation based on histogram equalization is carried out on the curvature value, and threshold operation { k (p) > h (h is a threshold value) } is carried out on the transformed curvature value, so as to obtain an initial characteristic region;
some miscellaneous points and break points in the S13 area are processed by a three-dimensional morphological open-close operation method to obtain a final characteristic area of the boundary between the tooth and the gum.
3. The method for rapid tooth segmentation based on three-dimensional dental model according to claim 2, wherein the step S2 includes:
s21 detecting an interdental fusion area, realizing automatic identification of characteristic area characteristic lines by matching branch points, selecting another end point Jets (j) from the segmented characteristic lines taking any branch point Jets (i) in the branch point set as an end point according to the shortest distance principle to be used as a matching point to obtain a corresponding fusion area characteristic line, automatically identifying the corresponding fusion area characteristic line, and executing 3 times of morphological expansion operation on the identified fusion area characteristic line until the interdental fusion area is covered, namely realizing the automatic identification of the interdental fusion area;
s22, deleting the inter-dental fusion area to obtain inter-dental holes, and keeping the matched branch points to realize automatic bridging of hole repairing for subsequent tooth repair;
s23 restoring the tooth shape, constructing a curved surface corresponding to the missing part by adopting a curved surface energy constraint mode based on the vertex information of the boundary of the interdental cavity, and obtaining the tooth shape with higher approximation degree with the original tooth.
4. The method for tooth fast segmentation based on three-dimensional dental model as claimed in claim 3, wherein in step S3, the Astar algorithm is used to store the information of each abstracted vertex on the curved surface of the three-dimensional dental model for effective restoration, and two sets of ListA and ListB are created before searching the shortest distance from the starting point to the target point, wherein the set ListA is used to store the nodes that have not been processed, and the set ListB is used to store the nodes that have been visited, and assuming that the starting node is P and the target node is Q, the algorithm comprises the following steps:
s31 storing the starting node P into a ListA set;
s32 judges whether the ListA collection is empty, if the ListA collection is empty, it represents that there is no next node meeting the screening condition, i.e. there is no path, the search is finished, if there is node in the ListA collection, the next step is carried out;
s33, taking the node with the minimum cost value from the ListA set as the current optimal node, judging whether the node is the target node, if so, indicating that the shortest path is found, finishing the algorithm, and if not, continuing the next step;
s34 checking the neighborhood point of the current node, and if the neighborhood point fails or the neighboring node is in the ListB set, skipping to continue processing the next node in the neighborhood;
s35, calculating the f value of each adjacent node, if the current adjacent node is not in the ListA set or the ListB set, recording the f value of the adjacent node, then adding the current node into the path stack, then storing the adjacent node into the ListA set, if the current adjacent node is already in the ListA set, then comparing the newly calculated f value with the current f value, if the new value is smaller, replacing the old f value with the new f value, then adding the adjacent node into the path stack, if the new value is larger, not processing, processing the next adjacent node;
s36: all neighborhood nodes of the current node are processed, the current node is stored in a ListB set, and then the current node is removed from the ListA set;
s37: and jumping to S32 until an optimal path between P and Q points is found or no path exists.
5. The method for rapid tooth segmentation based on three-dimensional dental model according to claim 4, wherein the step S4 includes:
s41, inputting the dental data models provided in the steps S2 and S3 into a segmentation network for training, and respectively obtaining ca ffemodel models with network optimal weights set by 3 different parameters;
s42, completing the segmentation of the single tooth through the obtained ca ffemodel model in sequence, and performing boundary optimization processing on the gingival margin area and the interdental contact area by adopting a conditional random field model;
s43, finishing post-processing of the dental model through a back projection ray intersection algorithm and a point cloud reconstruction technology.
6. The method for tooth fast segmentation based on three-dimensional dental model according to claim 5, wherein in the step S41, a tooth recognition network is constructed based on 2-level feature learning, wherein a ReLU activation function is adopted to effectively alleviate the gradient diffusion phenomenon, and the three-dimensional convolution expression is:
wherein f () is an activation function, Pi×Qi×RiWeight vector, H, for the convolution kernel at (p, q, r)(m)Is the feature vector of the mth channel, bi，jIn order to be a term of the offset,
are weights.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010847031.6A CN112085740A (en) | 2020-08-21 | 2020-08-21 | Tooth fast segmentation method based on three-dimensional tooth jaw model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010847031.6A CN112085740A (en) | 2020-08-21 | 2020-08-21 | Tooth fast segmentation method based on three-dimensional tooth jaw model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085740A true CN112085740A (en) | 2020-12-15 |
Family
ID=73729128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010847031.6A Pending CN112085740A (en) | 2020-08-21 | 2020-08-21 | Tooth fast segmentation method based on three-dimensional tooth jaw model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085740A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897924A (en) * | 2022-04-24 | 2022-08-12 | 雅客智慧（北京）科技有限公司 | Tooth model segmentation method and device |
| WO2022183852A1 (en) * | 2021-03-01 | 2022-09-09 | 杭州朝厚信息科技有限公司 | Method for segmenting dental three-dimensional digital model |
| CN116957857A (en) * | 2023-09-19 | 2023-10-27 | 中国建筑西南设计研究院有限公司 | Building restoration method and device and electronic equipment |
| CN117095145A (en) * | 2023-10-20 | 2023-11-21 | 福建理工大学 | Training method and terminal of tooth grid segmentation model |
| CN118411318A (en) * | 2024-06-27 | 2024-07-30 | 汉斯夫(杭州)医学科技有限公司 | Automatic interproximal restoration method of three-dimensional tooth model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604354A (en) * | 2009-07-17 | 2009-12-16 | 南京航空航天大学 | On three-dimensional dentognathic model, accurately recover the method for single tooth profile of tooth attitude |
| CN107622529A (en) * | 2016-07-15 | 2018-01-23 | 佛山市诺威科技有限公司 | Three-dimensional tooth model automatic segmentation method based on morphology |
-
2020
- 2020-08-21 CN CN202010847031.6A patent/CN112085740A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604354A (en) * | 2009-07-17 | 2009-12-16 | 南京航空航天大学 | On three-dimensional dentognathic model, accurately recover the method for single tooth profile of tooth attitude |
| CN107622529A (en) * | 2016-07-15 | 2018-01-23 | 佛山市诺威科技有限公司 | Three-dimensional tooth model automatic segmentation method based on morphology |
Non-Patent Citations (4)
| Title |
|---|
| SUKUN TIAN ET AL.: "Automatic Classification and Segmentation of Teeth on 3D Dental Model Using Hierarchical Deep Learning Networks", IEEE ACCESS, vol. 7, 21 June 2019 (2019-06-21), pages 84817 - 84828, XP011734278, DOI: 10.1109/ACCESS.2019.2924262 * |
| 吴婷 等: "3 维牙颌模型牙齿分割的路径规划方法", 中国图像图形学报, vol. 23, no. 1, 31 January 2018 (2018-01-31), pages 84 - 94 * |
| 孟宏伟: "三维模型分割技术在数字牙齿医疗领域的应用研究", 中国优秀硕士学位论文全文数据库 医疗卫生科技辑, 31 August 2018 (2018-08-31), pages 21 - 22 * |
| 肖兵 等: "基于特征线分段技术的牙齿分割算法", 计算机应用, no. 3, 10 March 2017 (2017-03-10), pages 844 - 848 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022183852A1 (en) * | 2021-03-01 | 2022-09-09 | 杭州朝厚信息科技有限公司 | Method for segmenting dental three-dimensional digital model |
| CN114897924A (en) * | 2022-04-24 | 2022-08-12 | 雅客智慧（北京）科技有限公司 | Tooth model segmentation method and device |
| CN114897924B (en) * | 2022-04-24 | 2023-10-17 | 雅客智慧（北京）科技有限公司 | Tooth model segmentation method and device |
| CN116957857A (en) * | 2023-09-19 | 2023-10-27 | 中国建筑西南设计研究院有限公司 | Building restoration method and device and electronic equipment |
| CN116957857B (en) * | 2023-09-19 | 2024-01-16 | 中国建筑西南设计研究院有限公司 | Building restoration method and device and electronic equipment |
| CN117095145A (en) * | 2023-10-20 | 2023-11-21 | 福建理工大学 | Training method and terminal of tooth grid segmentation model |
| CN117095145B (en) * | 2023-10-20 | 2023-12-19 | 福建理工大学 | Training method and terminal of tooth grid segmentation model |
| CN118411318A (en) * | 2024-06-27 | 2024-07-30 | 汉斯夫(杭州)医学科技有限公司 | Automatic interproximal restoration method of three-dimensional tooth model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112085740A (en) | Tooth fast segmentation method based on three-dimensional tooth jaw model | |
| US11790643B2 (en) | Deep learning for tooth detection and evaluation | |
| US11651494B2 (en) | Apparatuses and methods for three-dimensional dental segmentation using dental image data | |
| US11291532B2 (en) | Dental CAD automation using deep learning | |
| US11735306B2 (en) | Method, system and computer readable storage media for creating three-dimensional dental restorations from two dimensional sketches | |
| AU2015284524B2 (en) | Detecting tooth wear using intra-oral 3D scans | |
| US8803958B2 (en) | Global camera path optimization | |
| US20130329020A1 (en) | Hybrid stitching | |
| Zhao et al. | Interactive tooth segmentation of dental models | |
| US20210090272A1 (en) | Method, system and computer readable storage media for registering intraoral measurements | |
| CN111685899A (en) | Dental orthodontic treatment monitoring method based on intraoral images and three-dimensional models | |
| CN112991273B (en) | Orthodontic feature automatic detection method and system of three-dimensional tooth model | |
| CN112515787B (en) | Three-dimensional dental data analysis method | |
| CN112790879B (en) | Tooth axis coordinate system construction method and system of tooth model | |
| US20240058105A1 (en) | Augmentation of 3d surface of dental site using 2d images | |
| WO2022016294A1 (en) | Automatic generation of dental restorations using machine learning | |
| TW202409874A (en) | Dental restoration automation | |
| Broll et al. | Generative deep learning approaches for the design of dental restorations: A narrative review | |
| WO2024119612A1 (en) | Digital oral cavity model mark point recognition method and apparatus, and electronic device | |
| CN115761125A (en) | Dental digital orthodontic method based on point cloud attention and interdental collision loss | |
| CN117999615A (en) | Automatic tooth management in dental restoration workflow | |
| CN115311213A (en) | Incomplete tooth restoration information acquisition method based on deep learning | |
| CN118397026B (en) | Automatic extraction method and system for false tooth cervical margin line | |
| CN114463328B (en) | Automatic orthodontic difficulty coefficient evaluation method | |
| Dascalu et al. | Assignment Theory-Augmented Neural Network for Dental Arch Labeling |
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 |