CN113344950A - CBCT image tooth segmentation method combining deep learning with point cloud semantics - Google Patents
CBCT image tooth segmentation method combining deep learning with point cloud semantics Download PDFInfo
- Publication number
- CN113344950A CN113344950A CN202110853725.5A CN202110853725A CN113344950A CN 113344950 A CN113344950 A CN 113344950A CN 202110853725 A CN202110853725 A CN 202110853725A CN 113344950 A CN113344950 A CN 113344950A
- Authority
- CN
- China
- Prior art keywords
- segmentation
- tooth
- point cloud
- deep learning
- cbct
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
Abstract
The invention relates to a CBCT image tooth segmentation method based on deep learning and point cloud semantics, which comprises the following steps: step 1, carrying out tooth region segmentation and extracting tooth regions based on a deep learning segmentation model, such as a 3D segmentation network or a 2D segmentation network; step 2, reconstructing the extracted tooth area into dentition grid data in a three-dimensional manner by adopting a surface drawing method; step 3, extracting point cloud characteristic data of the grid data, and performing example segmentation based on point cloud semantics by adopting a point cloud example segmentation deep learning network to obtain a tooth example of the grid data; and 4, mapping the tooth corresponding area of the grid data to the CBCT according to the coordinate corresponding information to obtain a CBCT tooth example. According to the CBCT image tooth segmentation method based on the deep learning and point cloud semantics, because the instance segmentation is carried out based on the point cloud semantics, compared with the RPN method, other tooth labels except the target tooth in the detection frame region do not need to be processed, and the intelligent segmentation can be realized.
Description
Technical Field
The invention relates to the field of image processing, in particular to a CBCT image tooth segmentation method based on deep learning and point cloud semantics.
Background
Tooth segmentation is the basis of digital orthodontic treatment, and in recent years, the development of computer vision and graphics has enabled digital oral medical treatment. Compared with the common CT, the CBCT has the advantages of small radiation dose, short scanning time, high image spatial resolution and the like, and also provides more comprehensive 3D volume information of all oral tissues including teeth. So that the teeth are segmented from the CBCT image to obtain a more complete and accurate tooth model. The existing method provides that the surrounding frame of each tooth in CT volume data is detected based on 3D RPN and a deformation form thereof to realize tooth position detection, and then ROI is extracted from the region in the surrounding frame to perform single tooth segmentation; in other methods, a 3D volume data is extracted to form a dental arch curve to generate a corresponding panoramic picture, surrounding frames of teeth with different tooth positions are detected based on a two-dimensional panoramic picture, then the surrounding frame positions are replaced and calculated back to the 3D surrounding frames of the teeth in the CT volume data to realize tooth position detection, and then an ROI is extracted from a region in the surrounding frames to perform single tooth segmentation; the above-described method, however, does not adequately address the semantic relationship between three-dimensional data points; in addition, there are also scholars who adopt the level set and the method of the variation thereof, but they need to manually and interactively set the initial level set, and thus, they cannot realize fully automated operations.
Disclosure of Invention
In order to solve the technical problem, the invention provides a CBCT image tooth segmentation method based on deep learning and point cloud semantics, which combines CT image segmentation and point cloud semantics to realize CT tooth instance segmentation, and specifically comprises the following steps:
step 1, inputting CBCT data, carrying out tooth region segmentation based on a deep learning segmentation model, and extracting tooth regions;
step 2, reconstructing the extracted tooth area into dentition grid data in a three-dimensional manner by adopting a surface drawing method;
step 3, extracting point cloud characteristic data of the grid data, and performing example segmentation based on point cloud semantics by adopting a point cloud example segmentation deep learning network to obtain a tooth example of the grid data;
and 4, mapping the tooth corresponding area of the grid data to the CBCT according to the coordinate corresponding information to obtain a CBCT tooth example.
Further, the tooth region extraction in step 1 is based on a deep learning segmentation model, for example, a 3D segmentation network or a 2D segmentation network may be used for tooth region segmentation. According to one embodiment of the invention, the segmentation is based on a 2D segmentation network as follows:
step 1.1, extracting CBCT data slice images according to layers, carrying out pixel normalization processing on the slice images, and mapping pixel values to be 0-255;
step 1.2, according to the input size designed by the input end of the 2D segmentation network, carrying out size transformation processing on the size of the slice image;
step 1.3, inputting the processed slice image and the label image into a 2D segmentation network for training, wherein the 2D segmentation network is used for dividing each pixel of the slice image into a background or teeth, and obtaining a trained 2D segmentation network after the training is finished;
and step 1.4, extracting slices of the image to be segmented, preprocessing the slices, inputting the trained 2D segmentation network to obtain a prediction result, wherein the predicted foreground part is a tooth area.
Further, in the step 2, the extracted tooth area is three-dimensionally reconstructed into dentition grid data by adopting a surface drawing method, which may be three-dimensionally reconstructed into dentition grid data by adopting a marching cubes surface drawing method;
further, in the step 3, point cloud feature data of the grid data is extracted, and a point cloud example segmentation network is adopted to perform example segmentation based on the point cloud to obtain a tooth example of the grid data; the method specifically comprises the following steps:
step 3.1, extracting point cloud characteristic data, and performing down-sampling treatment, wherein the point cloud corresponding to the teeth of each tooth position corresponds to the same label, and the total number of the labels is 32;
step 3.2, inputting the point cloud characteristic data into a point cloud example segmentation network, and predicting the category of each point cloud;
and 3.3, converting the tooth area segmentation result to be predicted into a grid, extracting point cloud characteristic data, performing down-sampling processing, and inputting the point cloud characteristic data into the network to obtain the label of each point.
Optionally, the example segmentation based on the point cloud is performed by using GCN, PointNet, and the like, so as to obtain the tooth example of the grid data.
Further, in the step 4, according to the coordinate correspondence information, the tooth correspondence region of the grid data is mapped to the CBCT to obtain a CBCT tooth instance, which specifically includes:
the corresponding relation between the pixel coordinates (i, j, k) in the CBCT and the coordinates (x, y, z) of the point cloud midpoint is as follows:
i*spacing.x+origin.x=x
j*spacing.y+origin.y=y
k*spacing.z+origin.z=z
wherein, the spacing and origin respectively represent the size and origin information of the CBCT data.
Has the advantages that:
(1) according to the CBCT image tooth segmentation method based on the deep learning and point cloud semantics, because the instance segmentation is carried out based on the point cloud semantics, compared with the RPN method, other tooth labels except the target tooth in the detection frame region do not need to be processed.
(2) The invention can directly identify the tooth positions of 32 teeth without grouping, and the teeth at the left and right or upper and lower same number positions of the teeth are required to be taken as a category by the traditional method, and are finally separated after grouping.
(3) The method can identify the wisdom teeth and the metal implant teeth.
Drawings
FIG. 1: the invention relates to a CBCT image tooth segmentation method flow chart based on deep learning and point cloud semantics;
FIG. 2: the method of the invention is schematic in process;
FIG. 3: original CBCT data of the invention;
FIG. 4: tooth segmentation and tooth area extraction;
FIG. 5: tooth area mesh conversion;
FIG. 6: point cloud example segmentation results;
FIG. 7: example segmentation result conversion.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person skilled in the art based on the embodiments of the present invention belong to the protection scope of the present invention without creative efforts.
According to an embodiment of the present invention, a CBCT image tooth segmentation method based on deep learning and point cloud semantics is provided, as shown in fig. 1-2, including the following steps:
step 1, inputting CBCT data, carrying out tooth region segmentation based on a deep learning segmentation model, and extracting tooth regions;
step 2, reconstructing the extracted tooth area into dentition grid data in a three-dimensional manner by adopting a surface drawing method;
step 3, extracting point cloud characteristic data of the grid data, and performing example segmentation based on point cloud semantics by adopting a point cloud example segmentation deep learning network to obtain a tooth example of the grid data;
and 4, mapping the tooth corresponding area of the grid data to the CBCT according to the coordinate corresponding information to obtain a CBCT tooth example.
Further, in step 1, CBCT data is input, as shown in fig. 3.
The tooth region extraction in step 1 is based on a deep learning segmentation model, and for example, a 3D segmentation network or a 2D segmentation network may be used for tooth region segmentation. According to one embodiment of the invention, the segmentation is based on a 2D segmentation network as follows:
step 1.1, extracting CBCT data slice images according to layers, carrying out pixel normalization processing on the slice images, and mapping pixel values to be 0-255;
step 1.2, according to the input size designed by the input end of the 2D segmentation network, carrying out size transformation processing on the size of the slice image;
step 1.3, inputting the processed slice image and the label image into a 2D segmentation network for training, wherein the 2D segmentation network is used for dividing each pixel of the slice image into a background or teeth, and obtaining a trained 2D segmentation network after the training is finished;
and step 1.4, extracting slices of the image to be segmented, preprocessing the slices, inputting the trained 2D segmentation network to obtain a prediction result, wherein the predicted foreground part is a tooth area. The extracted tooth regions are segmented for teeth as shown in fig. 4.
Further, in the step 2, the extracted tooth region is three-dimensionally reconstructed into dentition grid data by using a surface drawing method, which may be three-dimensionally reconstructed into dentition grid data by using a marching cubes surface drawing method, as shown in fig. 5, as a result of the dentition grid data after the tooth region grid conversion.
Further, the step 3 of extracting point cloud feature data of the mesh data, and performing instance segmentation based on point cloud semantics by using a point cloud instance segmentation deep learning network to obtain a tooth instance of the mesh data specifically includes:
step 3.1, extracting point cloud characteristic data, and performing down-sampling treatment, wherein the point cloud corresponding to the teeth of each tooth position corresponds to the same label, and the total number of the labels is 32;
step 3.2, inputting the point cloud characteristic data into a point cloud example segmentation network, and predicting the category of each point cloud;
and 3.3, converting the tooth area segmentation result to be predicted into a grid, extracting point cloud characteristic data, performing down-sampling processing, and inputting the point cloud characteristic data into the network to obtain the label of each point.
Optionally, the point cloud segmentation method may perform example segmentation based on the point cloud by using GCN, PointNet, or the like, for example, to obtain a tooth example of the mesh data. As shown in fig. 6, the point cloud example segmentation result is shown;
further, in the step 4, according to the coordinate correspondence information, the tooth correspondence region of the grid data is mapped to the CBCT to obtain a CBCT tooth instance, which specifically includes: the corresponding relation between the pixel coordinates (i, j, k) in the CBCT and the coordinates (x, y, z) of the point cloud midpoint is as follows:
i*spacing.x+origin.x=x
j*spacing.y+origin.y=y
k*spacing.z+origin.z=z
wherein, the spacing and origin respectively represent the size and origin information of the CBCT data. Fig. 7 shows the result of the example segmentation result after conversion.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but various changes may be apparent to those skilled in the art, and it is intended that all inventive concepts utilizing the inventive concepts set forth herein be protected without departing from the spirit and scope of the present invention as defined and limited by the appended claims.
Claims (7)
1. A CBCT image tooth segmentation method based on deep learning and point cloud semantics is characterized by comprising the following steps:
step 1, inputting CBCT data, carrying out tooth region segmentation based on a deep learning segmentation model, and extracting tooth regions;
step 2, reconstructing the extracted tooth area into dentition grid data in a three-dimensional manner by adopting a surface drawing method;
step 3, extracting point cloud characteristic data of the grid data, and performing example segmentation based on point cloud semantics by adopting a point cloud example segmentation deep learning network to obtain a tooth example of the grid data;
and 4, mapping the tooth corresponding area of the grid data to the CBCT according to the coordinate corresponding information to obtain a CBCT tooth example.
2. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 1, wherein the tooth region extraction in step 1 is based on a deep learning segmentation model, and the deep learning segmentation model comprises a 3D segmentation network or a 2D segmentation network; the segmentation based on the 2D segmentation network is specifically as follows:
step 1.1, extracting CBCT data slice images according to layers, carrying out pixel normalization processing on the slice images, and mapping pixel values to be 0-255;
step 1.2, according to the input size designed by the input end of the 2D segmentation network, carrying out size transformation processing on the size of the slice image;
step 1.3, inputting the processed slice image and the label image into a 2D segmentation network for training, wherein the 2D segmentation network is used for dividing each pixel of the slice image into a background or teeth, and obtaining a trained 2D segmentation network after the training is finished;
and step 1.4, extracting slices of the image to be segmented, preprocessing the slices, inputting the trained 2D segmentation network to obtain a prediction result, wherein the predicted foreground part is a tooth area.
3. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 1, wherein the step 2 specifically comprises: and reconstructing the extracted tooth area into dentition grid data in a three-dimensional manner by adopting a MarchingCubes surface drawing method.
4. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 1, wherein the step 3 is to extract point cloud feature data of mesh data, and perform instance segmentation based on point cloud semantics by using a point cloud instance segmentation deep learning network to obtain tooth instances of the mesh data, and specifically comprises:
step 3.1, extracting point cloud characteristic data, and performing down-sampling treatment, wherein the point cloud corresponding to the teeth of each tooth position corresponds to the same label, and the total number of the labels is 32;
step 3.2, inputting the point cloud characteristic data into a point cloud example segmentation network, and predicting the category of each point cloud;
and 3.3, converting the tooth area segmentation result to be predicted into a grid, extracting point cloud characteristic data, performing down-sampling processing, and inputting the point cloud characteristic data into the network to obtain the label of each point.
5. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 4, wherein the point cloud-based example segmentation is performed by adopting one of GCN and PointNet to obtain a tooth example of grid data.
6. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 1, wherein the step 4 of mapping the tooth corresponding region of the mesh data to the CBCT according to the coordinate correspondence information to obtain a CBCT tooth instance specifically comprises:
the corresponding relation between the pixel coordinates (i, j, k) in the CBCT and the coordinates (x, y, z) of the point cloud midpoint is as follows:
i*spacing.x+origin.x=x
j*spacing.y+origin.y=y
k*spacing.z+origin.z=z
wherein, the spacing and origin respectively represent the size and origin information of the CBCT data.
7. The CBCT image tooth segmentation method based on deep learning and point cloud semantics as claimed in claim 1, wherein the tooth region extraction in step 1 is based on a deep learning segmentation model, and the deep learning segmentation model comprises a 3D segmentation network or a 2D segmentation network; when the image segmentation method is based on a 3D segmentation network, the feature of the cut image is extracted and input into the 3D segmentation network for segmentation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110853725.5A CN113344950A (en) | 2021-07-28 | 2021-07-28 | CBCT image tooth segmentation method combining deep learning with point cloud semantics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110853725.5A CN113344950A (en) | 2021-07-28 | 2021-07-28 | CBCT image tooth segmentation method combining deep learning with point cloud semantics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113344950A true CN113344950A (en) | 2021-09-03 |
Family
ID=77480428
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110853725.5A Pending CN113344950A (en) | 2021-07-28 | 2021-07-28 | CBCT image tooth segmentation method combining deep learning with point cloud semantics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113344950A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115205469A (en) * | 2022-09-06 | 2022-10-18 | 汉斯夫(杭州)医学科技有限公司 | Tooth and alveolar bone reconstruction method, equipment and medium based on CBCT |
CN116862869A (en) * | 2023-07-07 | 2023-10-10 | 东北大学 | Automatic detection method for mandible fracture based on mark point detection |
CN116883246A (en) * | 2023-09-06 | 2023-10-13 | 感跃医疗科技(成都)有限公司 | Super-resolution method for CBCT image |
CN117095018A (en) * | 2023-10-16 | 2023-11-21 | 北京朗视仪器股份有限公司 | Multi-class tooth segmentation method and device based on CBCT image |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107203998A (en) * | 2016-03-18 | 2017-09-26 | 北京大学 | A kind of method that denture segmentation is carried out to pyramidal CT image |
CN108242056A (en) * | 2018-02-06 | 2018-07-03 | 北京朗视仪器有限公司 | A kind of dividing method of the three dimensional tooth mesh data based on reconciliation field algorithm |
CN108665533A (en) * | 2018-05-09 | 2018-10-16 | 西安增材制造国家研究院有限公司 | A method of denture is rebuild by tooth CT images and 3 d scan data |
CN110930421A (en) * | 2019-11-22 | 2020-03-27 | 电子科技大学 | Segmentation method for CBCT (Cone Beam computed tomography) tooth image |
CN111311592A (en) * | 2020-03-13 | 2020-06-19 | 中南大学 | Three-dimensional medical image automatic segmentation method based on deep learning |
CN111402414A (en) * | 2020-03-10 | 2020-07-10 | 北京京东叁佰陆拾度电子商务有限公司 | Point cloud map construction method, device, equipment and storage medium |
CN111626241A (en) * | 2020-05-29 | 2020-09-04 | 北京华捷艾米科技有限公司 | Face detection method and device |
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 |
CN112614127A (en) * | 2020-12-31 | 2021-04-06 | 北京朗视仪器有限公司 | Interactive three-dimensional CBCT tooth image segmentation algorithm based on end-to-end |
CN112785609A (en) * | 2021-02-07 | 2021-05-11 | 重庆邮电大学 | CBCT tooth segmentation method based on deep learning |
CN112927358A (en) * | 2021-03-10 | 2021-06-08 | 杭州美齐科技有限公司 | Automatic complete tooth reconstruction method based on multi-mode data registration |
-
2021
- 2021-07-28 CN CN202110853725.5A patent/CN113344950A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107203998A (en) * | 2016-03-18 | 2017-09-26 | 北京大学 | A kind of method that denture segmentation is carried out to pyramidal CT image |
CN108242056A (en) * | 2018-02-06 | 2018-07-03 | 北京朗视仪器有限公司 | A kind of dividing method of the three dimensional tooth mesh data based on reconciliation field algorithm |
CN108665533A (en) * | 2018-05-09 | 2018-10-16 | 西安增材制造国家研究院有限公司 | A method of denture is rebuild by tooth CT images and 3 d scan data |
CN110930421A (en) * | 2019-11-22 | 2020-03-27 | 电子科技大学 | Segmentation method for CBCT (Cone Beam computed tomography) tooth image |
CN111402414A (en) * | 2020-03-10 | 2020-07-10 | 北京京东叁佰陆拾度电子商务有限公司 | Point cloud map construction method, device, equipment and storage medium |
CN111311592A (en) * | 2020-03-13 | 2020-06-19 | 中南大学 | Three-dimensional medical image automatic segmentation method based on deep learning |
CN111626241A (en) * | 2020-05-29 | 2020-09-04 | 北京华捷艾米科技有限公司 | Face detection method and device |
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 |
CN112614127A (en) * | 2020-12-31 | 2021-04-06 | 北京朗视仪器有限公司 | Interactive three-dimensional CBCT tooth image segmentation algorithm based on end-to-end |
CN112785609A (en) * | 2021-02-07 | 2021-05-11 | 重庆邮电大学 | CBCT tooth segmentation method based on deep learning |
CN112927358A (en) * | 2021-03-10 | 2021-06-08 | 杭州美齐科技有限公司 | Automatic complete tooth reconstruction method based on multi-mode data registration |
Non-Patent Citations (4)
Title |
---|
FARHAD GHAZVINIAN ZANJANI 等: "Mask-MCNet: Tooth instance segmentation in 3D point clouds of intra-oral scans", 《NEUROCOMPUTING》 * |
ZHIMING CUI 等: "ToothNet: Automatic Tooth Instance Segmentation and Identification from Cone Beam CT Images", 《2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
张佳颖 等: "基于深度学习的点云语义分割综述", 《激光与光电子学进展》 * |
张雅玲 等: "基于GCNN的CBCT模拟口扫点云数据牙齿分割算法", 《计算机辅助设计与图形学学报》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115205469A (en) * | 2022-09-06 | 2022-10-18 | 汉斯夫(杭州)医学科技有限公司 | Tooth and alveolar bone reconstruction method, equipment and medium based on CBCT |
CN116862869A (en) * | 2023-07-07 | 2023-10-10 | 东北大学 | Automatic detection method for mandible fracture based on mark point detection |
CN116862869B (en) * | 2023-07-07 | 2024-04-19 | 东北大学 | Automatic detection method for mandible fracture based on mark point detection |
CN116883246A (en) * | 2023-09-06 | 2023-10-13 | 感跃医疗科技(成都)有限公司 | Super-resolution method for CBCT image |
CN116883246B (en) * | 2023-09-06 | 2023-11-14 | 感跃医疗科技(成都)有限公司 | Super-resolution method for CBCT image |
CN117095018A (en) * | 2023-10-16 | 2023-11-21 | 北京朗视仪器股份有限公司 | Multi-class tooth segmentation method and device based on CBCT image |
CN117095018B (en) * | 2023-10-16 | 2023-12-22 | 北京朗视仪器股份有限公司 | Multi-class tooth segmentation method and device based on CBCT image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113344950A (en) | CBCT image tooth segmentation method combining deep learning with point cloud semantics | |
Lee et al. | Automated CNN-based tooth segmentation in cone-beam CT for dental implant planning | |
JP7451406B2 (en) | Automatic 3D root shape prediction using deep learning methods | |
Jang et al. | A fully automated method for 3D individual tooth identification and segmentation in dental CBCT | |
CN110998602B (en) | Classification and 3D modeling of 3D dentofacial structures using deep learning methods | |
CN108537784B (en) | CT image pulmonary nodule detection method based on deep learning | |
US10991091B2 (en) | System and method for an automated parsing pipeline for anatomical localization and condition classification | |
CN111598862B (en) | Breast molybdenum target image segmentation method, device, terminal and storage medium | |
CN114757960B (en) | Tooth segmentation and reconstruction method based on CBCT image and storage medium | |
CN112515787B (en) | Three-dimensional dental data analysis method | |
CN115205469A (en) | Tooth and alveolar bone reconstruction method, equipment and medium based on CBCT | |
WO2021027152A1 (en) | Image synthesis method based on conditional generative adversarial network, and related device | |
CN112785609B (en) | CBCT tooth segmentation method based on deep learning | |
CN113139977A (en) | Mouth cavity curve image wisdom tooth segmentation method based on YOLO and U-Net | |
CN115457198A (en) | Tooth model generation method and device, electronic equipment and storage medium | |
CN114549540A (en) | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof | |
Ben-Hamadou et al. | 3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge | |
CN113393470A (en) | Full-automatic tooth segmentation method | |
KR20220069655A (en) | Tooth segmentation system and method | |
Park et al. | A trends analysis of dental image processing | |
CN113313722B (en) | Interactive labeling method for tooth root images | |
CN112132189B (en) | CBCT image-oriented density peak superpixel preprocessing method | |
Wu et al. | Clinical tooth segmentation based on local enhancement | |
Khan et al. | TOOTH SEGMENTATION IN 3D CONE-BEAM CT IMAGES USING DEEP CONVOLUTIONAL NEURAL NETWORK. | |
EP4307229A1 (en) | Method and system for tooth pose estimation |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210903 |
|
RJ01 | Rejection of invention patent application after publication |