CN110287965A - The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image - Google Patents
The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image Download PDFInfo
- Publication number
- CN110287965A CN110287965A CN201910528659.7A CN201910528659A CN110287965A CN 110287965 A CN110287965 A CN 110287965A CN 201910528659 A CN201910528659 A CN 201910528659A CN 110287965 A CN110287965 A CN 110287965A
- Authority
- CN
- China
- Prior art keywords
- neural network
- tooth
- cbct image
- alveolar bone
- multilayer neural
- 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
- 238000007408 cone-beam computed tomography Methods 0.000 title claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 22
- 210000000988 bone and bone Anatomy 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 11
- 238000000926 separation method Methods 0.000 abstract description 9
- 241000270295 Serpentes Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Abstract
The invention discloses a kind of methods that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image, include the following steps: a, by a certain CBCT image marked as exemplar;B, using multilayer neural network as function;C, supervised training is implemented to multilayer neural network by exemplar, to obtain objective function;D, the CBCT image not marked is inputted into objective function, to obtain the CBCT image for being automatically separated root of the tooth and alveolar bone.The present invention realizes the increasingly automated separation of root of the tooth and alveolar bone in CBCT image, and can also accomplish high-purity separation to blurred picture.
Description
Technical field
The present invention relates to field, especially a kind of multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image
Method.
Background technique
The separation of root of the tooth and alveolar bone is predominantly based on the traditional mathematics such as snake or level set in traditional CBCT image
Model is semiautomatic fashion, and can not accomplish high-purity separation to blurred picture.
Summary of the invention
To solve problems of the prior art, the present invention provides a kind of multilayer neural networks to be automatically separated CBCT figure
The method of root of the tooth and alveolar bone as in.
The technical solution adopted by the present invention is that:
A kind of method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image, includes the following steps:
A, by a certain CBCT image marked as exemplar;
B, using multilayer neural network as function;
C, supervised training is implemented to multilayer neural network by exemplar, to obtain objective function;
D, the CBCT image not marked is inputted into objective function, to obtain the CBCT for being automatically separated root of the tooth and alveolar bone
Image.
Preferably, in step c, the objective function is the letter by each parameter composition of training neural network adjusted
Number.
The beneficial effects of the present invention are:
Using multilayer neural network as function, supervised training is implemented to multilayer neural network through exemplar, to obtain
Objective function inputs the CBCT image not marked into objective function to realize to automatically derive root of the tooth in separation CBCT image
With the effect of alveolar bone, compared to traditional separation method for being based primarily upon the traditional mathematics model such as snake or level set, this
Invention realizes the automation of height, and can also accomplish high-purity separation to blurred picture.
Detailed description of the invention
Fig. 1 is the original CBCT image not marked of the input in the embodiment of the present invention;
The good CBCT figure of the automatic marking that Fig. 2 is obtained after the image to input Fig. 1 in the embodiment of the present invention to objective function
Picture.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.
Embodiment
A kind of method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image, includes the following steps:
A, by a certain CBCT image marked as exemplar;
B, using multilayer neural network as function;
C, supervised training is implemented to multilayer neural network by exemplar, to obtain objective function;
D, the CBCT image not marked is inputted into objective function, to obtain the CBCT for being automatically separated root of the tooth and alveolar bone
Image.
Specifically, in step c, the objective function is the letter by each parameter composition of training neural network adjusted
Number.
As shown in Figure 1 and Figure 2, the CBCT image not marked in Fig. 1 is inputted into objective function, can be obtained in Fig. 2 and marks automatically
The CBCT image being poured in, the separation of root of the tooth and alveolar bone has been completed in the good CBCT image of automatic marking in Fig. 2, and whole process is real
The automation of height is showed, and high-purity separation can also be accomplished to blurred picture.
A specific embodiment of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.
Claims (2)
1. a kind of method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image, which is characterized in that including such as
Lower step:
A, by a certain CBCT image marked as exemplar;
B, using multilayer neural network as function;
C, supervised training is implemented to multilayer neural network by exemplar, to obtain objective function;
D, the CBCT image not marked is inputted into objective function, to obtain the CBCT figure for being automatically separated root of the tooth and alveolar bone
Picture.
2. the method that multilayer neural network according to claim 1 is automatically separated root of the tooth and alveolar bone in CBCT image,
It is characterized in that, in step c, the objective function is the function by each parameter composition of training neural network adjusted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910528659.7A CN110287965A (en) | 2019-06-18 | 2019-06-18 | The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910528659.7A CN110287965A (en) | 2019-06-18 | 2019-06-18 | The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110287965A true CN110287965A (en) | 2019-09-27 |
Family
ID=68005208
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910528659.7A Pending CN110287965A (en) | 2019-06-18 | 2019-06-18 | The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110287965A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192268A (en) * | 2019-12-31 | 2020-05-22 | 广州华端科技有限公司 | Medical image segmentation model construction method and CBCT image bone segmentation method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108205806A (en) * | 2016-12-20 | 2018-06-26 | 北京大学 | A kind of automatic analytic method of pyramidal CT image three-dimensional cranio-orbital tumor |
US20180374245A1 (en) * | 2017-06-26 | 2018-12-27 | Elekta, Inc. | Image quality in cone beam computed tomography images using deep convolutional neural networks |
US20190148005A1 (en) * | 2017-11-16 | 2019-05-16 | Dommar LLC | Method and system of teeth alignment based on simulating of crown and root movement |
CN109816661A (en) * | 2019-03-22 | 2019-05-28 | 电子科技大学 | A kind of tooth CT image partition method based on deep learning |
-
2019
- 2019-06-18 CN CN201910528659.7A patent/CN110287965A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108205806A (en) * | 2016-12-20 | 2018-06-26 | 北京大学 | A kind of automatic analytic method of pyramidal CT image three-dimensional cranio-orbital tumor |
US20180374245A1 (en) * | 2017-06-26 | 2018-12-27 | Elekta, Inc. | Image quality in cone beam computed tomography images using deep convolutional neural networks |
US20190148005A1 (en) * | 2017-11-16 | 2019-05-16 | Dommar LLC | Method and system of teeth alignment based on simulating of crown and root movement |
CN109816661A (en) * | 2019-03-22 | 2019-05-28 | 电子科技大学 | A kind of tooth CT image partition method based on deep learning |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192268A (en) * | 2019-12-31 | 2020-05-22 | 广州华端科技有限公司 | Medical image segmentation model construction method and CBCT image bone segmentation method |
CN111192268B (en) * | 2019-12-31 | 2024-03-22 | 广州开云影像科技有限公司 | Medical image segmentation model construction method and CBCT image bone segmentation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109118445B (en) | Underwater image enhancement method based on multi-branch generation countermeasure network | |
CN111223106B (en) | Full-automatic portrait mask matting method and system | |
CN104252558B (en) | A kind of non-standard construction fender member digital control processing preprocess method based on BIM platform | |
CN108875740A (en) | A kind of machine vision cutting method applied to laser cutting machine | |
CN108921942B (en) | Method and device for 2D (two-dimensional) conversion of image into 3D (three-dimensional) | |
CN103778628B (en) | Method and system for acquiring disease severity of leaf under open field environment | |
EP3340610A3 (en) | Method for differentiating background and foreground of a setting and method for replacing a background in images of a setting | |
CN104732494A (en) | Tissue culturing monitoring method and system based on image mist elimination | |
EP2042957A3 (en) | Method for automatic time synchronisation of devices in network-based systems | |
CN103886565A (en) | Nighttime color image enhancement method based on purpose optimization and histogram equalization | |
CN110287965A (en) | The method that multilayer neural network is automatically separated root of the tooth and alveolar bone in CBCT image | |
CN110245550A (en) | A kind of face noise data collection CNN training method based on overall cosine distribution | |
CN106650795A (en) | Sorting method of hotel room type images | |
CN107730453A (en) | Picture quality method for improving | |
CN103955900B (en) | Image defogging method based on biological vision mechanism | |
CN110175969A (en) | Image processing method and image processing apparatus | |
CN110136079A (en) | Image defogging method based on scene depth segmentation | |
CN109035377A (en) | For obtaining the embossment sketch effect image processing method for being suitable for laser engraving | |
CN103761520B (en) | File and picture based on stroke width is without ginseng binarization method | |
CN104299195B (en) | A kind of image defogging method based on auto-adaptive doublethreshold and dark channel prior | |
CN104599241A (en) | Full-automatic efficient calculation color conformity method | |
CN111091122B (en) | Training and detecting method and device for multi-scale characteristic convolutional neural network | |
CN109241885A (en) | A kind of method and device of special area in intelligent recognition video | |
CN103235935B (en) | A kind of method of estimation of trialeurodes vaporariorum population density | |
CN206505453U (en) | A kind of use cloud camera services define the purifier of food materials cleaning 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |
|
RJ01 | Rejection of invention patent application after publication |