CN108022247B - Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features - Google Patents
Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features Download PDFInfo
- Publication number
- CN108022247B CN108022247B CN201610967846.1A CN201610967846A CN108022247B CN 108022247 B CN108022247 B CN 108022247B CN 201610967846 A CN201610967846 A CN 201610967846A CN 108022247 B CN108022247 B CN 108022247B
- Authority
- CN
- China
- Prior art keywords
- mask
- tooth
- root
- seed
- periodontal ligament
- 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
Classifications
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to a method for extracting a three-dimensional tooth root form of a living tooth based on periodontal ligament imaging anatomical features, which comprises the following steps: the patient imaging scanning is stored as DICOM format layer data; importing patient DICOM (digital imaging and communications in medicine) format layer data into Mimics19.0 software, and extracting non-continuously distributed periodontal ligament masks from image data; expanding the discontinuous distribution into continuous distribution to obtain a seed mask of the tooth root; the seed mask is used as a seed area to be expanded outwards to a root bone boundary, and the maximum expansion step length does not exceed an artificially set maximum step length parameter; and reconstructing a three-dimensional model of the corresponding tooth, storing and outputting in an STL format, and completing the segmentation and extraction of the living tooth. The invention is simple and easy to use, and can rapidly realize the division of the tooth root tissue of the living body.
Description
Technical Field
The invention relates to a tooth root three-dimensional digital model, in particular to a method for extracting a three-dimensional tooth root form of a living tooth based on periodontal ligament imaging anatomical features.
Background
With the development of digital technology in oral medicine, Cone Beam Computed Tomography (CBCT) technology is more and more widely applied to diagnosis and analysis of oral diseases, and especially combined with image segmentation and three-dimensional reconstruction technology of digital software, so that three-dimensional measurement of living tooth form becomes possible. The individualized tooth root three-dimensional anatomical morphology of a patient is important information concerned by an oral cavity doctor, particularly an orthodontic doctor, and the three-dimensional virtual tooth arrangement technology with the tooth root information can assist the orthodontic doctor to realize more accurate and precise disease diagnosis and treatment scheme design. In addition, the acquisition of accurate three-dimensional morphology of living roots is also of great importance in the aspects of CAD/CAM personalized root implants, periodontal and implant surgical design, complex root canal treatment, and the like.
Unlike the method that the three-dimensional form of the dental crown can be directly obtained in an oral or external digital impression mode, the three-dimensional form information of the tooth root of the living body can only be obtained in the current stage by acquiring the tomographic image data of the tooth root sequence in a radiographic image mode and then indirectly obtained by the gray segmentation and three-dimensional reconstruction technology of professional imaging software. In the process, the outline of the tooth root is separated from the sequential gray-scale CBCT image, which is a very critical step. However, the extraction of the tooth root is a very challenging task due to the following features in the image of the living tooth tissue: firstly, the tooth density is gradually changed from a crown part to a root part, so that the tooth root tissues at different positions in a CBCT sequence image have different gray levels, and the extraction and the segmentation are difficult to be carried out in software by using a uniform threshold range; secondly, the density of the tooth root and the alveolar bone is similar, the two are close in gray level in the CBCT image with relatively small radiation dose, and the boundary is difficult to clearly identify due to the adjacent physical positions.
In order to solve the above problems, the prior literature reports that two solutions are mainly adopted for image segmentation and extraction of a living tooth root: a manual segmentation method: based on the subjective experience of dentists, the gray level images of the tooth roots are edited and modified layer by layer in software, and the boundaries of the roots and bones are determined. The manual segmentation method has the advantages that the extraction accuracy is ensured by human intervention, but the workload is large, the time consumption is long, and the extraction efficiency is low. Secondly, developing a special algorithm: the existing algorithm researches mainly comprise an adaptive threshold segmentation method, a parameter curve evolution segmentation method and a level set segmentation method. The algorithms are realized based on professional software programming, the clinical application effect is yet to be evaluated, and the algorithms are not popularized and popularized yet. The research aims at exploring a simple and easy-to-use method capable of quickly realizing the division of living tooth root tissues based on the common Mimics imaging software functions of the oral medicine.
Disclosure of Invention
Technical problem to be solved
The invention aims to provide a method for extracting a three-dimensional tooth root shape of a living tooth based on anatomical features of periodontal ligament imaging, and aims to obtain a method which is simple and easy to use and can quickly realize the division of living tooth root tissues based on the functions of Mimics imaging software commonly used in oral medicine.
(II) technical scheme
The invention discloses a method for extracting a three-dimensional tooth root form of a living tooth based on periodontal ligament imaging anatomical features, which comprises the following steps of:
1) the patient receives New TomVGi cone beam CT scanning before orthodontic treatment, large-view shooting is carried out according to the conventional head position requirement of orthodontic treatment, tube voltage is 110V, tube current is 2mA, exposure time is 10s, and the data is stored as DICOM format layer data with the voxel resolution of 0.3 mm;
2) importing patient DICOM (digital imaging and communications in medicine) format layer data into Mimics19.0 software, setting a hard tissue threshold range according to the gray level expression of soft and hard tissues in corresponding subtracted tooth areas of a patient by applying a Segmentation threshold function, so that a Mask area can cover corresponding dental crowns, tooth roots, peripheral alveolar bones and periodontal membranes, and is named as a root bone Mask; establishing a new threshold mask, and adjusting the threshold range to enable the new mask region to conform to the distribution characteristics of the periodontal ligament, which is named as 'periodontal ligament mask'; in the small-dose CBCT image, the periodontal ligament mask is discontinuously distributed;
3) using a 26-Connectivity space Connectivity expansion mode in a Morphology operation function to perform space expansion of 1-2 voxels on the periodontal ligament mask, so that the discontinuous distribution is expanded into a continuous distribution, and the model is named as a periodontal ligament expansion mask; using Boolean Operations Boolean operation function to subtract periodontal membrane expansion mask from root mask to obtain seed mask of root;
4) obtaining a seed mask of a tooth root, then performing Region growth on the seed mask, extracting an independent seed Region of a corresponding tooth, performing three-dimensional voxel expansion on the seed mask of a single tooth under the control of a parameter of maximum step length by using a Smart expanded intelligent expansion function and a boundary identification algorithm based on gray gradient change, and enabling the mask range to be intelligently expanded from the seed Region to the whole tooth Region, wherein the realization effect can be understood that the seed mask is used as the seed Region to be expanded outwards to the root bone boundary, and the maximum expansion step length is not more than the artificially set maximum step length parameter;
5) based on the expanded tooth mask, three-dimensionally reconstructing a three-dimensional geometric model of the corresponding tooth, storing and outputting the three-dimensional geometric model in an STL format, and completing the segmentation and extraction of the living tooth;
wherein, the area range of the dental root seed mask in the step 3) needs to meet the following requirements:
firstly, disconnecting a small amount of connection with adjacent teeth still existing in the root seed mask;
secondly, disconnecting the still existing small amount of connection with the alveolar bone;
and thirdly, making the boundary of the root seed mask smaller than the boundary contour of the root bone as much as possible.
(III) advantageous effects
The invention has the advantages that: the method is based on natural physiological image representation of periodontal ligament, realizes the segmentation of tooth root and alveolar bone tissue by means of Boolean operation and 'intelligent' expansion algorithm, simplifies manual operation steps, and improves the efficiency and the degree of automation of tooth root extraction.
Detailed Description
The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The invention discloses a method for extracting a three-dimensional tooth root form of a living tooth based on periodontal ligament imaging anatomical features, which comprises the following steps of:
1) the patient receives New TomVGi cone beam CT scanning before orthodontic treatment, large-view shooting is carried out according to the conventional head position requirement of orthodontic treatment, tube voltage is 110V, tube current is 2mA, exposure time is 10s, and the data is stored as DICOM format layer data with the voxel resolution of 0.3 mm;
2) importing patient DICOM (digital imaging and communications in medicine) format layer data into Mimics19.0 software, setting a hard tissue threshold range according to the gray level expression of soft and hard tissues in corresponding subtracted tooth areas of a patient by applying a Segmentation threshold function, so that a Mask area can cover corresponding dental crowns, tooth roots, peripheral alveolar bones and periodontal membranes, and is named as a root bone Mask; establishing a new threshold mask, and adjusting the threshold range to enable the new mask region to conform to the distribution characteristics of the periodontal ligament, which is named as 'periodontal ligament mask'; in the small-dose CBCT image, the periodontal ligament mask is discontinuously distributed;
3) using a 26-Connectivity space Connectivity expansion mode in a Morphology operation function to perform space expansion of 1-2 voxels on the periodontal ligament mask, so that the discontinuous distribution is expanded into a continuous distribution, and the model is named as a periodontal ligament expansion mask; using Boolean Operations Boolean operation function to subtract periodontal membrane expansion mask from root mask to obtain seed mask of root;
4) obtaining a seed mask of a tooth root, then performing Region growth on the seed mask, extracting an independent seed Region of a corresponding tooth, performing three-dimensional voxel expansion on the seed mask of a single tooth under the control of a parameter of maximum step length by using a Smart expanded intelligent expansion function and a boundary identification algorithm based on gray gradient change, and enabling the mask range to be intelligently expanded from the seed Region to the whole tooth Region, wherein the realization effect can be understood that the seed mask is used as the seed Region to be expanded outwards to the root bone boundary, and the maximum expansion step length is not more than the artificially set maximum step length parameter;
5) based on the expanded tooth mask, three-dimensionally reconstructing a three-dimensional geometric model of the corresponding tooth, storing and outputting the three-dimensional geometric model in an STL format, and completing the segmentation and extraction of the living tooth;
wherein, the area range of the dental root seed mask in the step 3) needs to meet the following requirements:
firstly, disconnecting a small amount of connection with adjacent teeth still existing in the root seed mask;
secondly, disconnecting the still existing small amount of connection with the alveolar bone;
and thirdly, making the boundary of the root seed mask smaller than the boundary contour of the root bone as much as possible.
The 3D shape deviation of the 11 living single tooth root models obtained by the invention and the scanned isolated tooth root is averagely 0.22 +/-0.07 mm, the average error of the near and far median diameters is 0.50 +/-0.09 mm, the average error of the buccal and lingual diameters is 0.33 +/-0.24 mm, and the average error of the root length is-0.53 +/-0.61 mm. The precision level can basically meet the requirement of dental root extraction and reconstruction precision in oral clinic.
In the aspect of tooth root extraction efficiency, 3 clinicians extract 15 living tooth roots in average 2-3 minutes, and the extraction process is mainly realized by adopting a software algorithm, so that the influence of the complexity of the teeth is small, and the extraction time of a single tooth is not obviously different from that of a plurality of teeth.
Further description of the invention:
1. the periodontal ligament distribution characteristic can be used as the extraction basis of the tooth root of the living body, and the extraction efficiency of the whole dentition is expected to be higher.
The tomography image records the absorption degree of oral craniomaxillofacial tissues to X rays through gray information, and the information recording mode can reflect the density of human tissues to a certain degree but cannot reflect other differences of the tissue texture. CBCT is a small-dose radiographic imaging device commonly used in stomatology department, can obtain image information of the range of upper and lower jaw complete dentitions (including crowns, roots and alveolar bones) under a large visual field resolution, but is always a very challenging work in clinic aiming at the problem of extraction of living roots which is particularly concerned in orthodontic treatment. The reason is that the physiological imaging gray scales of dentin and alveolar bone are very similar, and the root of the tooth and the alveolar bone boundary on the gray scale image always have the problem that partial areas are difficult to clearly identify due to the physical adjacency relation of the dentin and the alveolar bone. Therefore, the automatic and accurate extraction of the tooth roots is difficult to realize by the algorithm function of the existing imaging software based on the gray information difference segmentation organization, the manual editing of the layer-by-layer gray level image under the intervention of a doctor becomes the necessary tedious steps for extracting the living tooth roots, and the workload is undoubtedly huge for the extraction of the whole dentition teeth required by the digital orthodontic diagnosis.
Periodontal ligament is a natural physical existence separating the root from the alveolar bone, and is a fibrous tissue with a thickness of about 0.15 to 0.38mm, which is visualized as a very narrow low-brightness dark-image region between the root and the alveolar bone. However, because the physical size of the periodontal ligament is smaller than or equal to the voxel resolution of the oral cavity CBCT in the large visual field, the periodontal ligament image generally presents a strip-shaped dark image which is continuous in time and is broken around the tooth root, and the effect of completely separating the tooth root from the alveolar bone on the image cannot be realized. The present invention contemplates that the CBCT image of periodontal ligament tissue, although lacking continuity, has a three-dimensional spatial distribution in the imaged region that represents, to some extent, the three-dimensional morphological characteristics of the periodontal ligament, i.e., the three-dimensional contour of the tooth root. Therefore, the invention utilizes the algorithm function of 'morphological expansion' to artificially make the periodontal ligament images which are connected in time and time break as a space expansion 1 voxel unit to realize three-dimensional through continuity, and the through periodontal ligament mask is larger than the real periodontal ligament thickness in thickness but keeps the three-dimensional space distribution characteristic of the periodontal ligament, can realize the function of basically and completely separating the tooth root and the alveolar bone on the image, and can completely separate the tooth root seed region with certain tooth root contour characteristics from the alveolar bone by less manual editing. After the interference of alveolar bone images is removed, the intelligent expansion of the seed region can be realized easily subsequently by means of a gray gradient recognition algorithm, so that the boundary of the seed region is accurately expanded to the boundary of the root bone, and the rapid and efficient tooth root segmentation and extraction are realized.
In addition, because the principle of the tooth root extraction method of the invention has no direct correlation with the complexity of the tooth root form, the measurement analysis result of the 3D shape deviation of the tooth root can also be seen, no matter single or more complex double teeth, the consistency of the precision expression is better, and no obvious difference exists in the extraction efficiency. For the same patient, the imaging performance of the dental tissues and periodontal membrane tissues of different tooth positions of the same patient has certain commonality (the threshold value ranges of the same tissues are relatively uniform), when the whole dentition and root are extracted, the method can further simplify the middle manual truncation step, extract the teeth (the crowns are contacted and the roots are not connected) in the whole dentition range at one time, perform dental crown segmentation by means of three-dimensional mode editing of software (the method is more efficient than image segmentation and is simple to operate), theoretically realize more efficient single-tooth extraction efficiency, and relevant conclusions need to be further verified by a large sample experiment.
2. The parameters of the extraction algorithm can be adjusted individually, and the loss of the root length is related to the quality of CBCT.
The root size precision measurement analysis result of the invention shows that the root model of the living tooth extracted by the invention has the characteristics of near-far middle, large buccal-lingual size (the average error value is positive) and short root length (the average error value is negative) in three characteristic directions. Wherein, the error of the mesial-distal diameter of 15 teeth is 0.46mm on average, the error of the buccal-lingual diameter is 0.36mm on average, and the error of the root length is-0.6 mm on average. For analysis reasons, the results are to some extent related to the parameter settings of two key steps in the extraction method of the invention.
In the periodontal ligament expansion stage, the morphological operation function provided by the Mimics software can realize the expansion of the 'plane 8 connectivity' and the 'space 26 connectivity' of the unit voxel. Preliminary experiments show that the method can not adapt to periodontal ligament images of all patients based on 8-connectivity expansion in a fault plane, and three-dimensional communication penetration is realized; the expansion of the connectivity of the space 26 can be suitable for all patients of the invention, and the periodontal ligament images which are connected in time-break mode are communicated and penetrated, but the defect is that the expansion range is slightly large, and the regional scope precision of the root seed mask after Boolean operation is influenced to a certain extent. In addition, in the "intelligent" expansion stage of the root seed mask, the maximum expansion step length parameter provided by the Mimics software needs to be comprehensively evaluated according to the gray gradient representation of the root region image of the patient and the range of the seed mask extracted before, relatively reasonable parameter setting is provided, and repeated attempts are often needed. The invention considers that clinical application often needs surface smoothing treatment on extracted teeth to improve the visualization effect of a tooth model, and scholars study that the smoothing treatment can reduce the volume of the tooth model. Therefore, when determining each algorithm parameter, the method of the invention tends to select parameters with relatively loose image extraction range, and clinicians can also set relatively strict parameters according to the personalized requirements of subsequent model processing.
For the phenomenon that the root length is short on average, the imaging accuracy of the large-field CBCT is considered to have a certain relation. The NewTom VGI CBCT equipment used by the invention has the voxel resolution of 0.3mm under a large visual field, the shooting dose is relatively small, the image images of the tiny apical area of part of teeth cannot be clearly identified by naked eyes, and for the algorithm of computer software, the tooth root image segmentation of the apical 1-2 layers has certain extraction errors. In addition, when the CBCT is taken by orthodontics, the patient is in a natural head posture, and for physiological angles of the subtraction bicuspids, a fault sequence image within an included angle range of 30 degrees along the long axis direction of the teeth can be obtained, and the root length loss is basically 0.3-0.6mm (the root length index measured in the research is along the self-defined long axis direction of the teeth). For the extracted wisdom tooth, the physiological eruption angle is inclined greatly, a large included angle is formed between the physiological eruption angle and the vertical direction of CBCT imaging, and the root length loss of the root apex 1-2 layers of root images is correspondingly increased and is about 0.5-1 mm. Therefore, the results of the invention show that the root length error of the double teeth is larger than that of the single tooth on average, and the related statistical evaluation is in need of further large sample study.
The invention does not adopt the division evaluation of the whole teeth (crowns and roots), because the upper dentition and the lower dentition of the patient of the orthodontic diagnosis image are in the dislocation of the cusp, the occlusal surfaces of the upper teeth and the lower teeth are in contact, and a continuous highlight contact area is presented on the image, so that the automatic and accurate outline division is difficult to be carried out, and the accuracy of the measurement of the size and the shape of the image is difficult to be brought into the evaluation. If the invention is needed to be applied to segment the whole tooth, a low-density imaging medium such as a wax block or a silicon rubber occlusal pad is needed to be filled between the upper and lower dentitions when a patient shoots a CBCT (Cone Beam computed tomography), so that the upper and lower dental crowns are physically separated, and the external shape of the dental crown is accurately extracted from a radiation image.
Description of terms:
morphological operation: the function of adding or subtracting pixels from the original tissue image mask.
Boolean operation: and the new mask is obtained by combining, intersecting and subtracting the two image masks.
Intelligent extension operation: the original image mask range is expanded until the new mask boundary reaches the function of the ideal anatomical outline.
Threshold function: and extracting the specific tissue image by setting the upper and lower limit ranges of the gray threshold.
Mask area: an image of the image area of the specific tissue obtained by the threshold function.
The distribution characteristics of periodontal ligament: rather than a noun, periodontal pockets are attached to the surface of the root with the same profile as the root.
"26-Connectivity" spatial Connectivity extension mode: the parameter mode under the morphological operation can make a single pixel point expand to 26 space pixel points connected with the single pixel point in the three-dimensional space. (expansion of area coverage for tissue-specific masking)
And (3) region growing: and extracting a sub-mask area which is connected with the artificially set seed point in the mask.
Intelligent extended functions: in the same way, "intelligent extended operation"
Boundary identification algorithm of gray gradient change: rather than a noun, it is an explanation of the "smart expansion" function waste, and the principle of mask boundary expansion is based on recognizing the change in gray scale gradient.
The "maximum step size" parameter: the algorithm parameter under the function of intelligent expansion is used for controlling the expansion degree, so that the maximum step length of mask expansion does not exceed the set parameter.
Occlusion, also known as occlusion, refers to the static contact relationship between upper and lower dentition.
As described above, the present invention can be more fully realized. The above description is only a reasonable embodiment of the present invention, and the scope of the present invention includes but is not limited to the above description, and any insubstantial modifications of the technical solution of the present invention by those skilled in the art are included in the scope of the present invention.
Claims (1)
1. A method for extracting a three-dimensional tooth root form of a living tooth based on periodontal ligament imaging anatomical features is characterized by comprising the following steps:
1) the patient receives New TomVGi cone beam CT scanning before orthodontic treatment, large-view shooting is carried out according to the conventional head position requirement of orthodontic treatment, tube voltage is 110V, tube current is 2mA, exposure time is 10s, and the data is stored as DICOM format layer data with the voxel resolution of 0.3 mm;
2) importing patient DICOM (digital imaging and communications in medicine) format layer data into Mimics19.0 software, setting a hard tissue threshold range according to the gray level expression of soft and hard tissues in corresponding subtracted tooth areas of a patient by applying a Segmentation threshold function, so that a Mask area can cover corresponding dental crowns, tooth roots, peripheral alveolar bones and periodontal membranes, and is named as a root bone Mask; establishing a new threshold mask, and adjusting the threshold range to enable the new mask region to conform to the distribution characteristics of the periodontal ligament, which is named as 'periodontal ligament mask'; in the small-dose CBCT image, the periodontal ligament mask is discontinuously distributed;
3) using a 26-Connectivity space Connectivity expansion mode in a Morphology operation function to perform space expansion of 1-2 voxels on the periodontal ligament mask, so that the discontinuous distribution is expanded into a continuous distribution, and the model is named as a periodontal ligament expansion mask; using Boolean Operations Boolean operation function to subtract periodontal membrane expansion mask from root mask to obtain seed mask of root;
4) obtaining a seed mask of a tooth root to carry out Region growth of Region 'Region Growing', extracting an independent seed Region of a corresponding tooth, carrying out three-dimensional voxel expansion on the seed mask of a single tooth under the control of parameter 'maximum step length' by using intelligent expansion function 'Smart expanded' and a boundary identification algorithm based on gray gradient change, so that the mask range is intelligently expanded from the seed Region to the whole tooth Region, and the realization effect can be understood that the seed mask is used as the seed Region to be expanded outwards to the root bone boundary, and the maximum expansion step length does not exceed the parameter of the maximum step length set artificially;
5) based on the expanded tooth mask, three-dimensionally reconstructing a three-dimensional geometric model of the corresponding tooth, storing and outputting the three-dimensional geometric model in an STL format, and completing the segmentation and extraction of the living tooth;
the area range of the dental root seed mask in the step 3) needs to meet the following requirements:
firstly, disconnecting a small amount of connection with adjacent teeth still existing in the root seed mask;
secondly, disconnecting the still existing small amount of connection with the alveolar bone;
and thirdly, making the boundary of the root seed mask smaller than the boundary contour of the root bone as much as possible.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610967846.1A CN108022247B (en) | 2016-11-03 | 2016-11-03 | Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610967846.1A CN108022247B (en) | 2016-11-03 | 2016-11-03 | Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108022247A CN108022247A (en) | 2018-05-11 |
| CN108022247B true CN108022247B (en) | 2021-06-11 |
Family
ID=62084593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610967846.1A Active CN108022247B (en) | 2016-11-03 | 2016-11-03 | Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022247B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978841B (en) * | 2019-03-12 | 2021-08-03 | 北京羽医甘蓝信息技术有限公司 | Method and device for recognizing impacted tooth of panoramic picture based on deep learning |
| CN111260672B (en) * | 2019-12-26 | 2023-09-05 | 北京大学口腔医学院 | Method for guiding and segmenting teeth by using morphological data |
| CN115984529B (en) * | 2023-03-20 | 2023-07-18 | 佛山科学技术学院 | Automatic segmentation method for tooth three-dimensional model in oral cavity |
| CN116862816B (en) * | 2023-07-28 | 2024-01-26 | 杭州雅智医疗技术有限公司 | Model expansion method, device and application based on three-dimensional morphology |
-
2016
- 2016-11-03 CN CN201610967846.1A patent/CN108022247B/en active Active
Non-Patent Citations (5)
| Title |
|---|
| Accuracy Assessment of Three‑dimensional Surface Reconstructions of In vivo Teeth from Cone‑beam Computed Tomography;Yan‑Hui Sang e.t.;《Chinese Medical Journal》;20160620;第129卷(第12期);摘要和"Method"部分 * |
| Dicom标准和Mimics软件辅助建立下颌骨三维有限元模型;赵峰 等;《西南国防医药》;20051231;第15卷(第5期);全文 * |
| Mimics和Geomagic辅助下建立固定义齿的有限元模型;王野平 等;《医用生物力学》;20101231;第25卷(第6期);摘要、第1节 * |
| 基于激光扫描与CT建立带牙根的三维数字化牙颌模型;焦培峰 等;《中国临床解剖学杂志》;20130430;第31卷(第4期);摘要、第1-4节 * |
| 男性全牙列牙周膜数字解剖学建模与测量;叶鹏程 等;《医学研究杂志》;20160531;第45卷(第5期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108022247A (en) | 2018-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10098715B2 (en) | Generating a design for a dental restorative product from dental images | |
| JP6039651B2 (en) | Method, system, and computer-readable medium for visualizing and planning precision dental preparations | |
| JP5671734B2 (en) | Computer-aided creation of custom tooth setup using facial analysis | |
| CN108665533A (en) | A method of denture is rebuild by tooth CT images and 3 d scan data | |
| US11896452B2 (en) | Method for virtual setup with mixed dentition | |
| CN108022247B (en) | Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features | |
| CN107106117B (en) | Method and device for segmenting and reconstructing teeth and alveolar bones | |
| CN111261287B (en) | Planting scheme design method and system, terminal and computer-readable storage medium | |
| CN110334444B (en) | Method and system for constructing natural tooth type database | |
| Ye et al. | Integration accuracy of laser-scanned dental models into maxillofacial cone beam computed tomography images of different voxel sizes with different segmentation threshold settings | |
| US20190147648A1 (en) | Estimated 3D Models Of Interior Structures | |
| CN112120815A (en) | Digital oral smile repairing method | |
| CN112419476A (en) | Method and system for creating three-dimensional virtual image of dental patient | |
| KR102320857B1 (en) | Method for orthodontic treatment and apparatus thereof | |
| CN110742704B (en) | Embedded guide plate for accurately positioning root canal, preparation method and preparation system thereof, application thereof and accurate positioning method of root canal | |
| KR20200100448A (en) | Apparatus and Method for Registrating Implant Diagnosis Image | |
| KR20200021261A (en) | Dental CAD apparatus using characteristic of mirroring teeth and operating method the dental CAD apparatus | |
| Zimmermann et al. | The impact of technological innovation on dentistry | |
| KR101554158B1 (en) | method for manufacturing surgical guide of dental implant using cloud system | |
| JP7269587B2 (en) | segmentation device | |
| RU2371141C2 (en) | Method of functional rehabilitation of patients underwent operations of locally advanced mouth floor and mandible tumours | |
| Zhu et al. | An algorithm for automatically extracting dental arch curve | |
| TW202127368A (en) | Apparatus for automatically converting color of computerized tomography images on oral cavity based on artificial intelligence and driving method thereof | |
| CN111553941A (en) | Method and device for synthesizing panoramic view of oral cavity of user and electronic equipment | |
| CN113057733B (en) | Method and device for determining zygomatic bone implant implantation position based on three-dimensional 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 |