CN110415200A - A kind of bone cement implant CT image layer interpolation method - Google Patents
A kind of bone cement implant CT image layer interpolation method Download PDFInfo
- Publication number
- CN110415200A CN110415200A CN201910681750.2A CN201910681750A CN110415200A CN 110415200 A CN110415200 A CN 110415200A CN 201910681750 A CN201910681750 A CN 201910681750A CN 110415200 A CN110415200 A CN 110415200A
- Authority
- CN
- China
- Prior art keywords
- image
- interpolation
- slice
- difference section
- difference
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000002639 bone cement Substances 0.000 title claims abstract description 21
- 239000007943 implant Substances 0.000 title claims abstract description 20
- 238000002156 mixing Methods 0.000 claims abstract description 25
- 230000000877 morphologic effect Effects 0.000 claims abstract description 9
- 101100397225 Schizosaccharomyces pombe (strain 972 / ATCC 24843) isp3 gene Proteins 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims 4
- 230000007797 corrosion Effects 0.000 claims 4
- 230000000717 retained effect Effects 0.000 claims 1
- 239000011229 interlayer Substances 0.000 abstract description 13
- 239000010410 layer Substances 0.000 abstract description 11
- 230000008859 change Effects 0.000 abstract description 8
- 230000004927 fusion Effects 0.000 abstract description 8
- 230000007704 transition Effects 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 description 9
- 101100261006 Salmonella typhi topB gene Proteins 0.000 description 4
- 238000005530 etching Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 101150032437 top-3 gene Proteins 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 101100179824 Caenorhabditis elegans ins-17 gene Proteins 0.000 description 2
- 101150089655 Ins2 gene Proteins 0.000 description 2
- 230000008602 contraction Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4007—Interpolation-based scaling, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30008—Bone
Abstract
The present invention proposes a kind of bone cement implant CT image layer interpolation method.This method is based on Morphological scale-space characteristic, and first to through binarization operation, two sectioning images for extracting target area are done or operation, obtain blending image；Later, compare the similarity of blending image Yu two sectioning images, if more like with first slice, the difference section for then comparing fusion slice to first slice in blending image is once corroded, the difference section for comparing fusion slice to second slice in blending image again is corroded twice, obtains an interpolation image more like with first slice；It is on the contrary, the difference section for then comparing fusion slice to second slice in blending image is once corroded, the difference section for comparing fusion slice to first slice in blending image again is corroded twice, obtains an interpolation image more like with second slice.The interpolation image that the present invention is drawn out can describe interlayer change procedure, and transition is naturally, sharpness of border.
Description
Technical field
The present invention relates to Medical Image Processings, it relates in particular to which a kind of be based on morphologic interpolation method, the party
The difference section of the blending image of contiguous slices and former sectioning image is done Morphological scale-space by method, protects interpolation image selectively
The different information of front and back layer is stayed, interlayer change procedure is more naturally, sharpness of border.
Background technique
Although present implanted prosthetics has had very big improvement, bone cement is implanted after human body still may generation
It loosens or is broken, lead to serious consequence, it is therefore desirable to which tracing detection is carried out to its distribution.Current clinical detection is main
It is leafed through back and forth based on a large amount of CT pictures with doctor, lacks three-dimensional stereo effect, and do not have bed-by-bed analysis function, it is therefore, a kind of
Efficiently, accurately 3 D detection method urgently proposes.By the building of threedimensional model, doctor not only can be intuitively to implant
It is observed, and the time for browsing CT image can be saved, improved medical efficiency, reduce the probability of erroneous judgement.But in bone water
During the three-dimensional reconstruction of mud, due to the thickness of bone cement script, the CT image of acquisition only has 20 multilayers, reconstructs
Threedimensional model distortion is larger, profile is unobvious, needs that effective interpolation method is suitble to optimize, and improves interlayer resolution ratio.
Currently, the method for medicine CT image interlayer interpolation mainly has three classes.
Interpolation method of the first kind based on gray scale.This method estimates its interlayer using the neighborhood gray value of contiguous slices
The gray value of respective pixel.This method is suitable for sectioning image and uses in certain tie points than sparse situation, has fortune
Calculation amount is small, it is easy to accomplish the advantages that, but interlayer change procedure cannot be described, it is easy to produce objective obscure boundary and structure
The problems such as fuzzy.
Second class shape based interpolation method.This method is primarily adapted for use in bianry image, first extracts the shape of object
Then feature carries out interlayer interpolation further according to this feature.Common algorithm as based on shape range conversion method, based on shape
Match point method, wherein the range conversion method based on shape is that its distance for arriving boundary curve is found out to point all in image, will
The value of distance generates a distance matrix, and optimization algorithm is recycled to carry out linear interpolation, can describe interlayer change procedure, but transport
Calculation amount is big and is not easy to realize；Match point method based on shape is the boundary information by extracting contiguous slices target area, and
The coordinate of interpolation point is calculated by their related coefficient, fitting forms interpolation image boundary curve, is suitable for connected domain list
One, and the lesser situation of image shift, if the offset of image is larger, it is also necessary to carry out the operation of translationai correction to image.
Third class is based on morphologic interpolation method.This method is using morphological filter between adjacent two sectioning image
Intermediate interpolation image is generated, it can be by selecting different structural elements usually to adjust interpolation result, it can also be by selecting not
With dilation erosion region adjust interpolation result, therefore there is higher flexibility, and the interpolation image drawn out can be retouched
Interlayer change procedure is stated, transition is more naturally, sharpness of border.
Summary of the invention
It is distorted that larger, profile is unconspicuous when it is an object of the invention to solve the problems, such as bone cement implant three-dimensionalreconstruction,
A kind of bone cement implant CT image layer interpolation method is provided, by the method can get can describe interlayer change procedure,
Transition is more natural, sharpness of border interpolation image.
To achieve the goals above, the present invention provides a kind of based on morphologic bone cement implant CT image layer interpolation
Method, wherein mainly including three parts, first part is to obtain blending image；Second part is to calculate separately two contiguous slices
The similarity of image and blending image；Part III is to export interpolation image according to similarity relationship.
First part includes two steps:
Step 1, two layers adjacent of CT sectioning image is taken out, binarization operation is carried out to it, target area is extracted, obtains two-value
Contiguous slices image after changep1 Hep2；
Step 2, willp1 withp2 two images carry out phase or operation, obtain blending imagep3。
Second part includes two steps:
Step 3, it calculates in step 2p3 withp1 difference, obtainsp3 withp1 different informationp3/ p1, statisticsp3/ pDifference in 1
For 0 number of pixels, it is denoted asn1, it obtainsp3 withp1 similarityS1, its calculation formula is:
S1= n1/N
Wherein,N It isp3 total pixel number；
Step 4, it calculates in step 2p3 withp2 difference, obtainsp3 withp2 different informationp3/ p2, statisticsp3/ pDifference in 2
For 0 number of pixels, it is denoted asn2, it obtainsp3 withp2 similarityS2, its calculation formula is:
S2= n2/N
Wherein,N It isp3 total pixel number.
Part III includes three steps:
Step 5, in comparison step 3S1 with step 4 inS2, ifS1> S2, first existpIt is right on 3p1 comparesp3 difference section
Once corroded, thenpIt is right on 3p2 comparep3 difference section is corroded twice, obtain withp1 more like interpolation graphs
Picture；
Step 6, in comparison step 3S1 with step 4 inS2, ifS1< S2, first existpIt is right on 3p2 comparep3 difference section
Once corroded, thenpIt is right on 3p1 comparesp3 difference section is corroded twice, obtain withp2 more like interpolation graphs
Picture；
Step 7, output is through step 5 or step 6 treated blending imagep3, obtain the interpolation image of adjacent two slice.
The invention proposes a kind of bone cement implant CT image layer interpolation methods.This method is based on Morphological scale-space,
Binarization operation is carried out to adjacent two layers of CT sectioning image first, extracts target area, adjacent after obtaining binaryzation is cut
Picture；Then phase or operation are carried out to the sectioning image after two binaryzations, obtains blending image；Later, compare fusion figure
As the similarity with two sectioning images, if more like with first slice, first slice is compared in blending image and is melted
The difference section for closing slice is once corroded, then compares the difference section of fusion slice to second slice in blending image
Corroded twice, obtains an interpolation image more like with first slice；Conversely, then to second in blending image
The difference section that slice compares fusion slice is once corroded, then compares fusion slice to first slice in blending image
Difference section corroded twice, obtain one and second more like interpolation image of slice.The interpolation that the present invention obtains
Image can preferably embody the change procedure of interlayer, solve the problems, such as that implant is partially separated, the weight that basis is completed herein
Quality reconstruction of the structure model closer to professional reconstruction software.
Detailed description of the invention
Fig. 1 is overall flow figure of the invention.
Fig. 2 is blending image and adjacent two sectioning images similarity decision flowchart of the invention.
Fig. 3 is output and the flow chart of the more like interpolation image of first sectioning image of the invention.
Fig. 4 is output and the flow chart of the more like interpolation image of second sectioning image of the invention.
Fig. 5 is first in adjacent two sectioning image in bone cement implant CT sequence image after pretreatment.
Fig. 6 is second in adjacent two sectioning image in bone cement implant CT sequence image after pretreatment.
Fig. 7 is to utilize the obtained interpolation graphs more like with first sectioning image after present invention processing Fig. 5 and Fig. 6
Picture.
Fig. 8 is to utilize the obtained interpolation graphs more like with second sectioning image after present invention processing Fig. 5 and Fig. 6
Picture.
Specific embodiment
In order to better understand the present invention, With reference to embodiment to of the invention based on morphologic bone cement
Implant CT image layer interpolation method is described in more detail.In description below, current existing existing skill
Perhaps, the detailed description of art can desalinate subject of the present invention content, these descriptions will be ignored herein.
Fig. 1 is a kind of a kind of specific embodiment process of bone cement implant CT image layer interpolation method of the present invention
Figure, in the present embodiment, follows the steps below.
Step 1, adjacent two sectioning image in bone cement implant CT sequence image is obtained, binaryzation is completed to it, is extracted
The pretreatment operations such as target area 101, if Fig. 5 and Fig. 6 is adjacent two sectioning image after pretreatment.
Step 2, to passing through binarization operation, adjacent bone cement CT sectioning image after extracting target area carry out mutually or
Operation obtains blending image 102, and used conversion formula is as follows:
p3=p1|p2
Wherein,p1 Hep2 be respectively to pass through binarization operation, the adjacent bone cement CT sectioning image after extracting target area,p3
Forp1 withp2 phases or after obtained blending image.
Step 3, judge to mergep3 with through processed two sectioning image of step 2p1、p2 similarity 103 is specific to walk
It is rapid as shown in Figure 2:
(1) it calculatesp1 withp3 difference, obtainsp1 withp3 different information 201；
Used conversion formula is as follows:
p1/ p3= p1-p3
(2) it countsp1/ pThe number of pixels that difference is 0 in 3, is denoted asn1, it obtainsp3 withp1 similarityS1,202, it calculates
Formula are as follows:
S1= n1/N
Wherein,N It isp3 total pixel number；
(3) it calculatesp2 withp3 difference, obtainsp2 withp3 different information 203；
Used conversion formula is as follows:
p2/ p3 =p2- p3
(4) it countsp2/ pThe number of pixels that difference is 0 in 3, is denoted asn2, it obtainsp3 withp2 similarityS1,204, it calculates
Formula are as follows:
S2= n2/N
Wherein,N It isp3 total pixel number；
(5) judgeS1 withS2 relationship 205, ifS1> S2 execute step 4, conversely, executing step 5.
Step 4, ifS1> S2, first existpIt is right on 3p1 comparesp3 difference section is once corroded, thenpIt is right on 3p2 comparep3 difference section is corroded twice, obtain withp1 more like interpolation image 104, interpolation image display effect is such as
Fig. 7, specific steps are as shown in Figure 3:
(1) InpIt is right on 3p1 compared top3 difference section carries out an etching operation 301, so thatp3 all boundary contractions
One circle, used conversion formula are as follows:
Wherein, p3(x,y) it is imagep3 location point (x,y) pixel value,p1(x,y) it is imagep1 location point (x,y)
Pixel value,fFunction stand corrodes function, the expression formula of structural element SE are as follows:
SE=[0 1 0;
1 1 1;
0 1 0;]
(2) through step (1), treatedpIt is right on 3p2 compared top3 difference section carries out etching operation 302 twice, obtains
Withp1 more like interpolation imagep3, used conversion formula is as follows:
Wherein, p3(x,y) it is imagep3 location point (x,y) pixel value,p2(x,y) it is imagep2 location point (x,y)
Pixel value,fFunction stand corrodes function, the expression formula of structural element SE are as follows:
SE=[0 1 0;
1 1 1;
0 1 0;]
(3) output withp1 more like interpolation image 303.
Step 5, ifS1< S2, first existpIt is right on 3p2 comparep3 difference section is once corroded, thenpIt is right on 3p1 comparesp3 difference section is corroded twice, obtain withp2 more like interpolation images 105, interpolation image display effect is such as
Fig. 8, specific steps are as shown in Figure 4:
(1) InpIt is right on 3p2 compared top3 difference section carries out an etching operation 401, so thatp3 all boundary contractions
One circle, used conversion formula are as follows:
Wherein, p3(x,y) it is imagep3 location point (x,y) pixel value,p2(x,y) it is imagep2 location point (x,y)
Pixel value,fFunction stand corrodes function, the expression formula of structural element SE are as follows:
SE=[0 1 0;
1 1 1;
0 1 0;]
(2) through step (1), treatedpIt is right on 3p1 compared top3 difference section carries out etching operation 402 twice, obtains
Withp2 more like interpolation imagesp3, used conversion formula is as follows:
Wherein, p3(x,y) it is imagep3 location point (x,y) pixel value,p1(x,y) it is imagep1Location point (x,y)
Pixel value,fFunction stand corrodes function, the expression formula of structural element SE are as follows:
SE=[0 1 0;
1 1 1;
0 1 0;]
(3) output withp1 more like interpolation image 403.
The present invention proposes a kind of based on form according to bone cement implant CT sequence image feature and three-dimensionalreconstruction characteristic
Interlayer interpolation image generation method, this method is by the difference section shaping of the blending image of contiguous slices and former sectioning image
State processing, makes interpolation image selectively retain the different information of front and back layer, so as to preferably embody the variation of interlayer
Process, sharpness of border solve the problems, such as that implant is partially separated.Inventive algorithm is simple, strong operability, has extensive
Applicability.
Although the illustrative specific embodiment of the present invention is described above, but it should be clear that the present invention is unlimited
In the range of specific embodiment, for those skilled in the art, as long as various change is in appended right
It is required that these variations are it will be apparent that all utilize present inventive concept in the spirit and scope of the present invention for limiting and determining
Innovation and creation in the column of protection.
Claims (4)
1. a kind of bone cement implant CT image layer interpolation method, which is characterized in that blending image and original to contiguous slices
The difference section of sectioning image does Morphological scale-space, so that interpolation image is selectively retained the different information of front and back layer, including obtain
It takes blending image, the similarity for calculating separately two adjacent sectioning images and blending image, interpolation graphs is exported according to similarity relationship
As three parts, first part includes two steps:
Step 1, adjacent two layers CT sectioning image is taken out, binarization operation is carried out to it, target area is extracted, obtains binaryzation
Contiguous slices image afterwardsp1 Hep2；
Step 2, willp1 withp2 two images carry out phase or operation, obtain blending imagep3；
Second part includes two steps:
Step 3, it calculates in step 2p3 withp1 difference, obtainsp3 withp1 different informationp3/ p1, statisticsp3/ pDifference in 1
For 0 number of pixels, it is denoted asn1, it obtainsp3 withp1 similarityS1, its calculation formula is:
S1= n1/N
Wherein,N It isp3 total pixel number；
Step 4, it calculates in step 2p3 withp2 difference, obtainsp3 withp2 different informationp3/ p2, statisticsp3/ pDifference in 2
For 0 number of pixels, it is denoted asn2, it obtainsp3 withp2 similarityS2, its calculation formula is:
S2= n2/N
Wherein,N It isp3 total pixel number；
Part III includes two steps:
Step 5, ifS1> S2, first existpIt is right on 3p1 comparesp3 difference section is once corroded, thenpIt is right on 3p2 comparep3 difference section is corroded twice, obtain withp1 more like interpolation image；
Step 6, ifS1< S2, first existpIt is right on 3p2 comparep3 difference section is once corroded, thenpIt is right on 3p1 comparesp3 difference section is corroded twice, obtain withp2 more like interpolation images；
Step 7, output is through step 5 or step 6 treated blending imagep3, obtain the interpolation image of adjacent two slice.
2. a kind of bone cement implant CT image layer interpolation method according to claim 1, which is characterized in that step 5
With the similarity degree for indicating interpolation image and contiguous slices in step 6 using the number of corrosion, corrosion often, represents phase
It is lower like degree.
3. a kind of bone cement implant CT image layer interpolation method according to claim 1, which is characterized in that step 5
Middle elder generation existspIt is right on 3p1 comparesp3 difference section is once corroded, thenpIt is right on 3p2 comparep3 difference section carries out two
Secondary corrosion, obtain withp1 more like interpolation image.
4. a kind of bone cement implant CT image layer interpolation method according to claim 1, which is characterized in that step 6
Middle elder generation existspIt is right on 3p2 comparep3 difference section is once corroded, thenpIt is right on 3p1 comparesp3 difference section carries out two
Secondary corrosion, obtain withp2 more like interpolation images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910681750.2A CN110415200B (en) | 2019-07-26 | 2019-07-26 | Method for interpolating among CT (computed tomography) image layers of bone cement implant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910681750.2A CN110415200B (en) | 2019-07-26 | 2019-07-26 | Method for interpolating among CT (computed tomography) image layers of bone cement implant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110415200A true CN110415200A (en) | 2019-11-05 |
| CN110415200B CN110415200B (en) | 2022-03-08 |
Family
ID=68363472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910681750.2A Active CN110415200B (en) | 2019-07-26 | 2019-07-26 | Method for interpolating among CT (computed tomography) image layers of bone cement implant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415200B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003107271A2 (en) * | 2002-06-12 | 2003-12-24 | Litton Systems, Inc. | System for multi-sensor image fusion |
| CN101082983A (en) * | 2007-06-22 | 2007-12-05 | 崔志明 | Self-adapting medicine sequence image values inserting method based on interested region |
| CN103655014A (en) * | 2013-11-26 | 2014-03-26 | 西安交通大学 | Artificial joint wear evaluation method and artificial joint wear evaluation system |
| CN105118088A (en) * | 2015-08-06 | 2015-12-02 | 曲阜裕隆生物科技有限公司 | 3D imaging and fusion method based on pathological slice scanning device |
| US20160088410A1 (en) * | 2013-04-15 | 2016-03-24 | Benjamin Chan | System and method for auditory canal measuring, facial contouring |
| US20180279993A1 (en) * | 2012-06-21 | 2018-10-04 | Globus Medical, Inc. | Medical imaging systems using robotic actuators and related methods |
| CN108898593A (en) * | 2018-06-25 | 2018-11-27 | 重庆知遨科技有限公司 | A kind of detection method based on the classification of abdominal CT Medical image fusion |
| CN108985345A (en) * | 2018-06-25 | 2018-12-11 | 重庆知遨科技有限公司 | A kind of detection device based on the classification of lung's Medical image fusion |
| CN109360179A (en) * | 2018-10-18 | 2019-02-19 | 上海海事大学 | A kind of image interfusion method, device and readable storage medium storing program for executing |
| US20190066345A1 (en) * | 2017-08-28 | 2019-02-28 | Shenzhen United Imaging Healthcare Co., Ltd. | System and method for removing hard tissue in ct image |
-
2019
- 2019-07-26 CN CN201910681750.2A patent/CN110415200B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003107271A2 (en) * | 2002-06-12 | 2003-12-24 | Litton Systems, Inc. | System for multi-sensor image fusion |
| CN101082983A (en) * | 2007-06-22 | 2007-12-05 | 崔志明 | Self-adapting medicine sequence image values inserting method based on interested region |
| US20180279993A1 (en) * | 2012-06-21 | 2018-10-04 | Globus Medical, Inc. | Medical imaging systems using robotic actuators and related methods |
| US20160088410A1 (en) * | 2013-04-15 | 2016-03-24 | Benjamin Chan | System and method for auditory canal measuring, facial contouring |
| CN103655014A (en) * | 2013-11-26 | 2014-03-26 | 西安交通大学 | Artificial joint wear evaluation method and artificial joint wear evaluation system |
| CN105118088A (en) * | 2015-08-06 | 2015-12-02 | 曲阜裕隆生物科技有限公司 | 3D imaging and fusion method based on pathological slice scanning device |
| US20190066345A1 (en) * | 2017-08-28 | 2019-02-28 | Shenzhen United Imaging Healthcare Co., Ltd. | System and method for removing hard tissue in ct image |
| CN108898593A (en) * | 2018-06-25 | 2018-11-27 | 重庆知遨科技有限公司 | A kind of detection method based on the classification of abdominal CT Medical image fusion |
| CN108985345A (en) * | 2018-06-25 | 2018-12-11 | 重庆知遨科技有限公司 | A kind of detection device based on the classification of lung's Medical image fusion |
| CN109360179A (en) * | 2018-10-18 | 2019-02-19 | 上海海事大学 | A kind of image interfusion method, device and readable storage medium storing program for executing |
Non-Patent Citations (5)
| Title |
|---|
| AHMADREZA BAGHAIE 等: "An Optimization Method For Slice Interpolation Of Medical Images", 《COMPUTER SCIENCE》 * |
| JUELIN LENG 等: "Medical image interpolation based on multi-resolution registration", 《COMPUTERS AND MATHEMATICS WITH APPLICATIONS》 * |
| 伊聪聪 等: "一种改进的Grabcut图像分割方法", 《小型微型计算机系统》 * |
| 周生俊: "医学CT图像分割方法研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
| 方艳红 等: "多图像融合的连续腹腔影像图像分割", 《电子技术应用》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110415200B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111798462B (en) | Automatic delineation method of nasopharyngeal carcinoma radiotherapy target area based on CT image | |
| CN107784647B (en) | Liver and tumor segmentation method and system based on multitask deep convolutional network | |
| CN107808156B (en) | Region-of-interest extraction method | |
| CN104835112B (en) | A kind of liver multiphase phase CT image interfusion methods | |
| CN105957063B (en) | CT image liver segmentation method and system based on multiple dimensioned weighting similarity measure | |
| WO2020001217A1 (en) | Segmentation method for dissected aorta in ct image based on convolutional neural network | |
| CN113012172B (en) | AS-UNet-based medical image segmentation method and system | |
| CN102737395B (en) | Image processing method and device in a kind of medical X-ray system | |
| CN107895345B (en) | Method and device for improving resolution of face image | |
| CN101976436B (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
| CN112862824A (en) | Novel coronavirus pneumonia focus detection method, system, device and storage medium | |
| CN110288611A (en) | Coronary vessel segmentation method based on attention mechanism and full convolutional neural networks | |
| CN105389821B (en) | It is a kind of that the medical image cutting method being combined is cut based on cloud model and figure | |
| CN111462027B (en) | Multi-focus image fusion method based on multi-scale gradient and matting | |
| CN103886621A (en) | Method for automatically extracting bed plate | |
| CN106780491B (en) | Initial contour generation method adopted in segmentation of CT pelvic image by GVF method | |
| CN113344950A (en) | CBCT image tooth segmentation method combining deep learning with point cloud semantics | |
| CN112381811A (en) | Method, device and equipment for realizing medical image data labeling | |
| CN115564782A (en) | 3D blood vessel and trachea segmentation method and system | |
| CN116452618A (en) | Three-input spine CT image segmentation method | |
| CN111179298A (en) | CT image-based three-dimensional lung automatic segmentation and left-right lung separation method and system | |
| Du et al. | Real-time lesion detection of cardiac coronary artery using deep neural networks | |
| Zhou et al. | N-net: 3d fully convolution network-based vertebrae segmentation from ct spinal images | |
| CN110415200A (en) | A kind of bone cement implant CT image layer interpolation method | |
| Koundal et al. | An automatic ROI extraction technique for thyroid ultrasound image |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231222 Address after: 2nd Floor, Building 7, Keda Plaza, No. 8 Qingyang East Street, Qingyi Town, Fucheng District, Mianyang City, Sichuan Province, 621000 Patentee after: Sichuan Tianshun Micro Inspection Technology Co.,Ltd. Address before: 621010, No. 59, Qinglong Avenue, Fucheng District, Sichuan, Mianyang Patentee before: Southwest University of Science and Technology |