CN104933751A - Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram - Google Patents
Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram Download PDFInfo
- Publication number
- CN104933751A CN104933751A CN201510424776.0A CN201510424776A CN104933751A CN 104933751 A CN104933751 A CN 104933751A CN 201510424776 A CN201510424776 A CN 201510424776A CN 104933751 A CN104933751 A CN 104933751A
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- prh
- sustainer
- histogram
- crest
- 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
- 210000004351 coronary vessel Anatomy 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000002526 effect on cardiovascular system Effects 0.000 title claims abstract description 32
- 238000009877 rendering Methods 0.000 title abstract description 7
- 210000004165 myocardium Anatomy 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000002860 competitive effect Effects 0.000 claims abstract description 4
- 230000007704 transition Effects 0.000 claims description 34
- 210000004204 blood vessel Anatomy 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 abstract description 2
- 210000000709 aorta Anatomy 0.000 abstract 2
- 208000031481 Pathologic Constriction Diseases 0.000 abstract 1
- 208000037804 stenosis Diseases 0.000 abstract 1
- 230000036262 stenosis Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 33
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 4
- 210000004872 soft tissue Anatomy 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
A cardiovascular coronary artery enhanced volume rendering method and system based on local histograms in the field of image processing are disclosed, wherein a first-dimensional transmission function is constructed by creating a local histogram for a peak in a global histogram of cardiovascular volume data, merging a plurality of groups of local histograms and then performing Gaussian fitting on the merged local histograms; and performing competitive analysis on coronary artery and aorta in cardiovascular body data, namely judging whether each block of data belongs to the coronary artery or the aorta according to the stenosis degree characteristic confidence coefficient and the myocardium distance confidence coefficient so as to construct a second-dimensional transfer function according to a judgment result and realize volume rendering. The method has the advantages of stability, reliability, convenience in implementation, reality, high efficiency, strong engineering applicability and the like.
Description
Technical field
What the present invention relates to is a kind of technology of image processing field, specifically a kind of object plotting method of strengthening based on the cardiovascular coronary artery of local histogram and system.
Background technology
Volume Rendering Techniques (Volume Rendering) can display body data interconnects is implicit effectively characteristic information, helps user to be further analyzed and process data, is widely used in the fields such as medical science, geology, meteorology, scientific simulations.Volume Rendering Techniques is mainly classified to volume data by transition function, namely maps different optical properties to volume data internal feature, and then obtains effective displaying of feature of interest.But, in medical science volume drawing, only rely on the transition function of scalar value effectively two of scalar value close range kinds of soft tissues cannot be carried out differentiation and play up.Wherein have representational example be exactly cardiovascular in sustainer and coronary artery, just closely, both cannot make a distinction by traditional object plotting method well for the scalar value of these two kinds of soft tissues.
In order to effectively differentiate the characteristic information of volume data inside, academia proposed a large amount of transition function methods for designing in recent years, mainly can be divided into two large classes, namely based on the transition function method for designing of drawing result image and the transition function method for designing based on spatial data attribute.
Based on the transition function method for designing of drawing result image based in the transition function design process of drawing result image, user-interactive is not needed to define the optical properties of Bian sampling point, but drawing result image is operated intuitively, realize the optimal design of background transfer function.Compared to the transition function method for designing based on scalar value of classics, based on transition function method for designing simple, intuitive, the easy to understand of drawing result image, for the user not possessing computer graphics background knowledge and transition function design experiences, there is stronger practicality.But, these class methods need to draw a large amount of result images according to initial transmission collection of functions, and according to the interactive operation of user on image, further optimization initial transmission collection of functions, realize search and the evolution of optimal transmission function, time complexity and the space complexity of whole process are higher, are unfavorable for efficient volume data feature visualization and analysis, have certain limitation.
Transition function method for designing based on spatial data feature has expanded the transition function method for designing based on scalar valued attributes, in volume data assorting process, introduce other data characteristic information, help user to analyze more accurately and extract feature implicit in volume data, the validity of reinforcement Data classification.Main method has:
1) split volume data and then distinguish volume drawing, this method cannot be extended to general object plotting method, because its needs to introduce man-machine interactively very consuming time under a lot of scene.
2) the transition function design of 2D, this method is usually using first dimension of scalar value as transition function, and gradient is as the second dimension.Gradient is very effective in enhancing border display, however distinguish in the soft tissue with same scalar value then helpless.But distinguish in the soft tissue with same scalar value then helpless.
Through finding the retrieval of prior art: multi-modal virtual heart method for visualizing studies [D]. the histogram method used in Harbin Institute of Technology 2012. one literary composition can distinguish the tissue of different scalar value scope in heart effectively, but cannot effectively strengthen cardiovascular in coronary artery.
Summary of the invention
The present invention is directed to prior art above shortcomings, propose object plotting method that a kind of cardiovascular coronary artery based on local histogram strengthens and system, reliable and stable, realize convenient, true efficient, the advantage such as engineer applied is strong.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of object plotting method strengthened based on the cardiovascular coronary artery of local histogram, local histogram is created by the crest in the color histogram to cardiovascular volume data, and Gauss curve fitting after Duo Zu local histogram is merged, build the first dimension transition function with fitting result; According to narrowness characteristic degree of confidence and cardiac muscle distance degree of confidence, coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer, namely judge that every block data belong to coronary artery and still belong to sustainer, build the second dimension transition function, realize volume drawing with judged result.
Described method specifically comprises the following steps:
1) color histogram of cardiovascular volume data is set up;
2) find crest the highest in color histogram, that is: causing the color histogram slickness of generation poor owing to there is noise in cardiovascular volume data, is not often the highest real crest according to the highest crest that the maximal value of color histogram is searched; The present invention, in order to overcome this problem, first carries out polynomial expression best-fit to color histogram, then carries out maximal value according to matching polynomial curve out and searches, thus find the highest real crest.
3) create local histogram (PRH) according to crest, concrete steps are:
3.1) the highest crest found out step 2 carries out average μ, variance is the gaussian curve approximation of σ.
Described matching, the height error that standard is accumulated within the scope of μ ± α σ for minimizing Gaussian curve and histogram scalar value; α is assigned 1 usually;
3.2) carry out piecemeal to volume data, the voxel number of every block is 83, calculates scalar value in every block data and accounts for the proportion of this block element total quantity in the number of voxel in μ ± α σ interval
wherein: N is all voxels of these block data, V
Φfor the voxel collection of scalar value within the scope of Φ.
3.3) ω of every block data is judged
rwhether meet ω
r>=ε, if met, these block data are added in PRH, and ε ∈ [0,1] is gravity thresholds.
4) from color histogram, remove the PRH that step 3 creates;
5) all color histograms are traveled through by the operation of step 2 ~ 4;
6) by merging similar in all PRH obtained, be specially: when the variance of one group of PRH is similar and average is close, i.e. σ
max/ σ
min≤ 4 and μ
max-μ
min≤ σ
minmax (1,2-σ
min/ 40), this group PRH is merged; Right latter incorporated PRH carries out gaussian curve approximation again.
7) to the coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer, namely belong to coronary artery according to narrowness characteristic degree of confidence and the every block data of cardiac muscle distance degree of confidence comprehensive descision and still belong to sustainer.
Described narrowness characteristic degree of confidence refers to: because coronary artery is much narrower than sustainer, therefore by the symbolic variable p at interval [?1,1]
1represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in narrowness characteristic
Wherein:
D
1=(ω
b1-ω
a1)/2, Φ
1sustainer with coronary artery to mix scalar value interval, coronary artery ω
r(Φ
1) infimum ω
a1with sustainer ω
r(Φ
1) supremum ω
b1.
Described cardiac muscle distance degree of confidence refers to: due to coronary artery than sustainer closer to cardiac muscle, therefore by interval [?1,1] symbolic variable p
2represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in cardiac muscle distance
Wherein:
D
2=(ω
b2-ω
a2)/2, Φ
2the scalar value being cardiac muscle is interval; Coronary artery ω
r(Φ
2) supremum ω
a2with sustainer ω
r(Φ
2) infimum ω
b2.
Described competitive analysis refers to: set n as requested and pass judgment on characteristic, then pass judgment on property calculation out symbolic variable p to this n
ibe weighted and on average obtain final symbol decision variable P,
wherein: λ
irepresent that i-th is passed judgment on characteristic weight shared in final classification results,
work as P<0, then judge that the blood vessel in these block data belongs to coronary artery; When P>=0, then judge that the blood vessel in these block data belongs to sustainer, strengthen field at cardiovascular coronary artery and generally adopt but be not limited to p
1and p
2, n correspondingly can be increased in different fields.
8) according to step 1 ?6 PRH that obtain build the first dimension transition function (TF); Then the subordinate result of every block data in coronary artery and sustainer scalar value overlapping region obtained according to step 7 builds the second dimension transition function (TF).
The present invention relates to a kind of system realizing said method, comprise: histogram crest detection module, PRH module, confidence calculations module, transition function builds module and volume drawing module, wherein: histogram crest detection module is connected with PRH module and exports histogrammic crest location information, PRH module is connected with confidence calculations module and exports the weight parameter information of volume data block, confidence calculations module and transition function build module and are connected and the dependency information exporting volume data block, transition function builds module and is connected with volume drawing module and exports transition function information.
Technique effect
Compared with prior art, technique effect of the present invention comprises:
1) adopt local histogram to carry out the transition function design of volume drawing, the coronary artery in cardiovascular and aortic area are separated simply and effectively, the enhancing achieving coronary artery dexterously shows;
2) local histogram adopted can the volume data that generates of the different Imaging machine of self-adaptation, and automatically can build transition function, saves time and strong robustness.
3) adopt Gaussian function to carry out the crest of matching color histogram, effectively local crest is extracted from color histogram.
4) coronary artery and aortal competitive analysis according to the self-defined n of a user's request characteristic, therefore can easily can be applied to the enhancing display of other tissue.
Accompanying drawing explanation
Fig. 1 is schematic flow sheet of the present invention;
Fig. 2 is that in embodiment, two-dimentional transition function builds schematic diagram.
Fig. 3 is embodiment effect contrast figure.
Embodiment
Elaborate to embodiments of the invention below, the present embodiment is implemented under premised on technical solution of the present invention, give detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
Embodiment 1
The present embodiment has in the personal computer of Intel Core Duo i73770K CPU, a NVIDIA GeForce GTX 760 and 8G internal memory at one and realizes, and whole volume rendering algorithm adopts C++ to realize, and ray cast process uses glsl shading language.
As shown in Figure 1, the present embodiment comprises the following steps:
1) color histogram of cardiovascular volume data is set up;
2) crest the highest in color histogram is found;
3) local histogram (PRH) is created according to crest;
4) from color histogram, PRH is removed;
5) all color histograms are traveled through by the operation of step 2 ~ 4;
6) by merging similar in all PRH obtained;
7) to the coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer;
8) the two-dimentional transition function (TF) of robotization construct drafting.
The first step, sets up the color histogram of cardiovascular volume data.Travel through the scalar value of all voxels in cardiovascular volume data, then add up the number of the voxel corresponding to each scalar value, finally set up color histogram.
Second step, finds crest the highest in color histogram.Causing the color histogram slickness of generation poor owing to there is noise in cardiovascular volume data, is not often the highest real crest according to the highest crest that the maximal value of color histogram is searched; The present invention, in order to overcome this problem, first carries out polynomial expression best-fit to color histogram, then carries out maximal value according to matching polynomial curve out and searches, thus find the highest real crest.
3rd step, creates local histogram (PRH) according to crest, and described according to the specific implementation process of crest establishment local histogram (PRH) is:
First the highest crest found out step 2 carries out gaussian curve approximation (average μ, variance is σ), and the standard of matching is: minimize the height error that Gaussian curve and histogram scalar value are accumulated within the scope of μ ± α σ; α be usually assigned 1; Then carry out piecemeal to volume data, the voxel number of every block is 83; Calculate scalar value in every block data and account for the proportion ω of this block element total quantity in the number of voxel in μ ± α σ interval
r(Φ, N), finally judges the ω of every block data
rwhether meet ω
r>=ε, if met, these block data are added in PRH, and ε ∈ [0,1] is self-defining threshold value,
wherein N is all voxels of these block data, V
Φfor the voxel collection of scalar value within the scope of Φ;
4th step, removes PRH from color histogram.Step 3 kind is only needed to meet ω
rthe volume data block of>=ε removes from color histogram.
5th step, travels through all color histograms by the operation of step 2 ~ 4.If color histogram is not empty, illustrate also there is new PRH.Therefore travel through all color histograms by the operation of step 2 ~ 4, just illustrate that all PRH have been classified out.
6th step, merges similar PRH.The concrete methods of realizing of the PRH that described merging is similar is:
When the variance of one group of PRH is similar and average is close, this group PRH is merged; Right latter incorporated PRH carries out gaussian curve approximation again.The criterion that wherein variance phase Sihe average is close is σ
max/ σ
min≤ 4 μ
max-μ
min≤ σ
minmax (1,2-σ
min/ 40).
7th step, to the coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer.Described to the concrete methods of realizing of the coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer is:
According to characteristic 1: coronary artery is much narrower than sustainer; This characteristic can pass through ω
r(Φ
1) describe, wherein Φ
1sustainer with coronary artery to mix scalar value interval; Definition coronary artery ω
r(Φ
1) infimum ω
a1with sustainer ω
r(Φ
1) supremum ω
b1; By interval [?1,1] symbolic variable p
1represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in characteristic 1,
According to characteristic 2: coronary artery than sustainer closer to cardiac muscle; This characteristic can pass through ω
r(Φ
2) describe, wherein Φ
2the scalar value being cardiac muscle is interval; In like manner, coronary artery ω is defined
r(Φ
2) supremum ω
a2with sustainer ω
r(Φ
2) infimum ω
b2; By interval [?1,1] symbolic variable p
2represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in characteristic 2,
N can be set as requested and pass judgment on characteristic, then pass judgment on property calculation out symbolic variable p to this n
ibe weighted and on average obtain final symbol decision variable P; Work as P<0, then judge that the blood vessel in these block data belongs to coronary artery; When P>=0, then judge that the blood vessel in these block data belongs to sustainer,
Wherein λ
irepresent that i-th is passed judgment on characteristic weight shared in final classification results.
8th step, the two-dimentional transition function (TF) that robotization construct is drawn, the concrete methods of realizing of the two-dimentional transition function (TF) that described robotization construct is drawn is: first according to step 1 ?6 calculate PRH and build the first dimension TF; Then the second dimension TF is built according to step 7 in the region of coronary artery and sustainer scalar value overlap, as shown in Figure 2.
As shown in Figure 3, for prior art and the present invention carry out the cardiovascular volume drawing effect that contrasts, wherein left figure is the volume drawing effect of this algorithm, and right figure is volume drawing effect of the present invention.The algorithm that result shows the present invention's proposition obviously will be better than prior art in cardiovascular coronary artery enhancing.
Claims (8)
1. the object plotting method strengthened based on the cardiovascular coronary artery of local histogram, it is characterized in that, local histogram is created by the crest in the color histogram to cardiovascular volume data, and Gauss curve fitting after Duo Zu local histogram is merged, build the first dimension transition function with fitting result; According to narrowness characteristic degree of confidence and cardiac muscle distance degree of confidence, coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer, namely judge that every block data belong to coronary artery and still belong to sustainer, build the second dimension transition function, realize volume drawing with judged result.
2. method according to claim 1, is characterized in that, described method specifically comprises the following steps:
1) color histogram of cardiovascular volume data is set up;
2) find crest the highest in color histogram, that is: causing the color histogram slickness of generation poor owing to there is noise in cardiovascular volume data, is not often the highest real crest according to the highest crest that the maximal value of color histogram is searched; The present invention, in order to overcome this problem, first carries out polynomial expression best-fit to color histogram, then carries out maximal value according to matching polynomial curve out and searches, thus find the highest real crest;
3) PRH is created according to crest;
4) from color histogram, remove the PRH that step 3 creates;
5) all color histograms are traveled through by the operation of step 2 ~ 4;
6) by merging similar in all PRH obtained, be specially: when the variance of one group of PRH is similar and average is close, i.e. σ
max/ σ
min≤ 4 and μ
max-μ
min≤ σ
minmax (1,2-σ
min/ 40), this group PRH is merged; Right latter incorporated PRH carries out gaussian curve approximation again;
7) to the coronary artery in cardiovascular volume data and the analysis of being at war with property of sustainer, namely belong to coronary artery according to narrowness characteristic degree of confidence and the every block data of cardiac muscle distance degree of confidence comprehensive descision and still belong to sustainer;
8) according to step 1 ?6 PRH that obtain build the first dimension TF; Then the subordinate result of every block data in coronary artery and sustainer scalar value overlapping region obtained according to step 7 builds the second dimension TF.
3. method according to claim 2, is characterized in that, described step 3 specifically comprises:
3.1) the highest crest found out step 2 carries out average μ, variance is the gaussian curve approximation of σ;
3.2) carry out piecemeal to volume data, the voxel number of every block is 8
3, calculate scalar value in every block data and account for the proportion of this block element total quantity in the number of voxel in μ ± α σ interval
wherein: N is all voxels of these block data, V
Φfor the voxel collection of scalar value within the scope of Φ;
3.3) ω of every block data is judged
rwhether meet ω
r>=ε, if met, these block data are added in PRH, and ε ∈ [0,1] is gravity thresholds.
4. method according to claim 3, is characterized in that, described gaussian curve approximation, the height error that standard is accumulated within the scope of μ ± α σ for minimizing Gaussian curve and histogram scalar value; α is assigned 1 usually.
5. method according to claim 1 and 2, is characterized in that, described narrowness characteristic degree of confidence refers to: interval [?1,1] symbolic variable p
1represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in narrowness characteristic
Wherein:
D
1=(ω
b1-ω
a1)/2, Φ
1sustainer with coronary artery to mix scalar value interval, coronary artery ω
r(Φ
1) infimum ω
a1with sustainer ω
r(Φ
1) supremum ω
b1.
6. method according to claim 1 and 2, is characterized in that, described cardiac muscle distance degree of confidence refers to: due to coronary artery than sustainer closer to cardiac muscle, therefore by interval [?1,1] symbolic variable p
2represent that the blood vessel in every block data belongs to coronary artery or belongs to aortal degree of confidence in cardiac muscle distance
wherein:
d
2=(ω
b2-ω
a2)/2, Φ
2the scalar value being cardiac muscle is interval; Coronary artery ω
r(Φ
2) supremum ω
a2with sustainer ω
r(Φ
2) infimum ω
b2.
7. method according to claim 1 and 2, is characterized in that, described competitive analysis refers to: set n as requested and pass judgment on characteristic, then pass judgment on property calculation out symbolic variable p to this n
ibe weighted and on average obtain final symbol decision variable P,
wherein: λ
irepresent that i-th is passed judgment on characteristic weight shared in final classification results,
work as P<0, then judge that the blood vessel in these block data belongs to coronary artery; When P>=0, then judge that the blood vessel in these block data belongs to sustainer.
8. one kind realizes the system of method described in above-mentioned arbitrary claim, it is characterized in that, comprise: histogram crest detection module, PRH module, confidence calculations module, transition function builds module and volume drawing module, wherein: histogram crest detection module is connected with PRH module and exports histogrammic crest location information, PRH module is connected with confidence calculations module and exports the weight parameter information of volume data block, confidence calculations module and transition function build module and are connected and the dependency information exporting volume data block, transition function builds module and is connected with volume drawing module and exports transition function information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510424776.0A CN104933751B (en) | 2015-07-20 | 2015-07-20 | Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510424776.0A CN104933751B (en) | 2015-07-20 | 2015-07-20 | Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104933751A true CN104933751A (en) | 2015-09-23 |
| CN104933751B CN104933751B (en) | 2017-10-20 |
Family
ID=54120902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510424776.0A Active CN104933751B (en) | 2015-07-20 | 2015-07-20 | Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104933751B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345546A (en) * | 2018-09-30 | 2019-02-15 | 数坤（北京）网络科技有限公司 | A kind of coronary artery volume data model dividing method and equipment |
| US10395773B2 (en) | 2017-11-06 | 2019-08-27 | International Business Machines Corporation | Automatic characterization of Agatston score from coronary computed tomography |
| CN112669941A (en) * | 2020-12-28 | 2021-04-16 | 上海联影医疗科技股份有限公司 | Medical image processing method and device, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020083069A (en) * | 2001-04-26 | 2002-11-01 | 주식회사 쓰리디메드 | Method for providing a graphic user interface for a volume rendering image |
| CN1403057A (en) * | 2001-09-13 | 2003-03-19 | 田捷 | 3D Euclidean distance transformation process for soft tissue display in CT image |
| CN1430185A (en) * | 2001-12-29 | 2003-07-16 | 田捷 | Ultralarge scale medical image surface reconstruction method based on single-layer surface tracking |
| CN1818974A (en) * | 2006-03-08 | 2006-08-16 | 杭州电子科技大学 | Multi-modality medical data three-dimensional visual method |
| CN103345772A (en) * | 2013-06-21 | 2013-10-09 | 上海交通大学 | Volume data identification method of two-dimensional transfer function based on airspace information |
| CN104167013A (en) * | 2014-08-04 | 2014-11-26 | 清华大学 | Volume rendering method for highlighting target area in volume data |
| EP1862120B1 (en) * | 2006-05-29 | 2016-11-09 | Toshiba Medical Systems Corporation | Computer-aided imaging diagnostic processing apparatus and computer-aided imaging diagnostic processing method |
-
2015
- 2015-07-20 CN CN201510424776.0A patent/CN104933751B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020083069A (en) * | 2001-04-26 | 2002-11-01 | 주식회사 쓰리디메드 | Method for providing a graphic user interface for a volume rendering image |
| CN1403057A (en) * | 2001-09-13 | 2003-03-19 | 田捷 | 3D Euclidean distance transformation process for soft tissue display in CT image |
| CN1430185A (en) * | 2001-12-29 | 2003-07-16 | 田捷 | Ultralarge scale medical image surface reconstruction method based on single-layer surface tracking |
| CN1818974A (en) * | 2006-03-08 | 2006-08-16 | 杭州电子科技大学 | Multi-modality medical data three-dimensional visual method |
| EP1862120B1 (en) * | 2006-05-29 | 2016-11-09 | Toshiba Medical Systems Corporation | Computer-aided imaging diagnostic processing apparatus and computer-aided imaging diagnostic processing method |
| CN103345772A (en) * | 2013-06-21 | 2013-10-09 | 上海交通大学 | Volume data identification method of two-dimensional transfer function based on airspace information |
| CN104167013A (en) * | 2014-08-04 | 2014-11-26 | 清华大学 | Volume rendering method for highlighting target area in volume data |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10395773B2 (en) | 2017-11-06 | 2019-08-27 | International Business Machines Corporation | Automatic characterization of Agatston score from coronary computed tomography |
| CN109345546A (en) * | 2018-09-30 | 2019-02-15 | 数坤（北京）网络科技有限公司 | A kind of coronary artery volume data model dividing method and equipment |
| CN112669941A (en) * | 2020-12-28 | 2021-04-16 | 上海联影医疗科技股份有限公司 | Medical image processing method and device, computer equipment and storage medium |
| CN112669941B (en) * | 2020-12-28 | 2023-05-26 | 上海联影医疗科技股份有限公司 | Medical image processing method, medical image processing device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104933751B (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Curve-like structure extraction using minimal path propagation with backtracking | |
| Chen et al. | A double-threshold image binarization method based on edge detector | |
| Noma et al. | Interactive image segmentation by matching attributed relational graphs | |
| Zhang et al. | ST-unet: Swin transformer boosted U-net with cross-layer feature enhancement for medical image segmentation | |
| CN104933709B (en) | Random walk CT lung tissue image automatic segmentation methods based on prior information | |
| CN109829918B (en) | Liver image segmentation method based on dense feature pyramid network | |
| CN109447065A (en) | A kind of method and device of breast image identification | |
| CN103353986B (en) | A kind of brain MR image segmentation based on super-pixel fuzzy clustering | |
| Chang et al. | Graph-based learning for segmentation of 3D ultrasound images | |
| CN110188763B (en) | Image significance detection method based on improved graph model | |
| Ren et al. | An unsupervised semi-automated pulmonary nodule segmentation method based on enhanced region growing | |
| CN105389821B (en) | It is a kind of that the medical image cutting method being combined is cut based on cloud model and figure | |
| Shi et al. | Automatic nodule segmentation method for CT images using aggregation-U-Net generative adversarial networks | |
| CN104933751A (en) | Cardiovascular coronary artery enhanced volume rendering method and system based on local histogram | |
| Kuhn et al. | A Clustering-based Visualization Technique to Emphasize Meaningful Regions of Vector Fields. | |
| CN112258461A (en) | Pulmonary nodule detection method based on convolutional neural network | |
| Chen et al. | Vessel extraction using anisotropic minimal paths and path score | |
| CN115330940A (en) | Three-dimensional reconstruction method, device, equipment and medium | |
| Du et al. | TSU-net: two-stage multi-scale cascade and multi-field fusion U-net for right ventricular segmentation | |
| Zhang et al. | R2Net: Residual refinement network for salient object detection | |
| CN111986137B (en) | Biological organ lesion detection method, apparatus, device, and readable storage medium | |
| Shao et al. | Application of U-Net and Optimized Clustering in Medical Image Segmentation: A Review. | |
| Wu et al. | Rcnn-slicenet: A slice and cluster approach for nuclei centroid detection in three-dimensional fluorescence microscopy images | |
| CN103839048A (en) | Stomach CT image lymph gland recognition system and method based on low-rank decomposition | |
| CN109460768A (en) | A kind of text detection and minimizing technology for histopathology micro-image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Cai Junfeng Inventor after: Zhao Qiang Inventor after: Luo Maisheng Inventor after: Luo Zhe Inventor after: Yang Yi Inventor before: Cai Junfeng Inventor before: Zhao Qiang Inventor before: Luo Maisheng Inventor before: Luo Zhe Inventor before: Yang Yi |
|
| CB03 | Change of inventor or designer information |