CN109919904A - A kind of the vessel topology analysis method and device of x-ray imaging image - Google Patents
A kind of the vessel topology analysis method and device of x-ray imaging image Download PDFInfo
- Publication number
- CN109919904A CN109919904A CN201811633680.5A CN201811633680A CN109919904A CN 109919904 A CN109919904 A CN 109919904A CN 201811633680 A CN201811633680 A CN 201811633680A CN 109919904 A CN109919904 A CN 109919904A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- ray imaging
- topology
- imaging image
- vessel
- 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
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the invention provides a kind of vessel topology analysis method of x-ray imaging image and devices, pass through the x-ray imaging picture construction blood vessel topology non-directed graph of blood vessel, the blood flow direction and connection relationship that blood vessel is determined according to blood vessel topology non-directed graph obtain blood vessel topology digraph；Wherein it is determined that the blood flow direction of blood vessel is to effectively increase the accuracy of analysis according to the connectivity constraint and Constraint of Morphology of blood vessel topology non-directed graph.The analysis method that the embodiment of the present invention is combined using non-directed graph building and digraph building, overcoming coronary angiography image topology analysis medium vessels has false tie point, forms false ring or form I-structure.The embodiment of the present invention provides reliable data for the quantization diagnosis and treatment of coronary artery disease and supports, user only can need to quickly and automatically estimate the topological structure of x-ray imaging image according to the point of one vascular root of x-ray imaging image manually identifying.
Description
Technical field
The present embodiments relate to field of medical image processing, more particularly, to a kind of blood vessel of x-ray imaging image
Analysis of Topological Structure method and device.
Background technique
The disease incidence of coronary artery disease (CAD) can not have always been high any more.X-ray imaging due to quickly and conveniently feature,
As most widely used means in CAD diagnosis.The topology information of x-ray imaging image medium vessels is CAD quantization diagnosis and treatment
Data basis and arterial blood dynamic analysis, art in coronary artery matching, arteriarctia detection, coronary angiography simulation etc. answer
Necessary component.However, coronary angiography is the process for projecting to two-dimensional surface from three-dimensional structure, it is possible that blood vessel
Projection superposition the case where, to not can correctly reflect the original true topological structure of coronary artery, it is understood that there may be the problem of include: blood vessel
Cross projection form false tie point；The tip of one blood vessel is projected to another internal blood vessel and leads to a blood vessel
Tip disappear；The tip of two blood vessels projects to same place and forms false ring.
At present, on the one hand, X-ray coronary angiography has flaw by the center line that thinning algorithm generates, and influences whether blood
The estimation of pipe morphologic information.Specifically have the following problems: there may be tiny pseudo- bifurcateds for rough vessel profile；When one
When blood vessel and crossover project, ring structure can be generated, is not allowed when this is in tree topology existing；When two blood vessels
When with low-angle cross projection, the connecting portion of two blood vessels will be mistakenly refined as a line segment, that is, form I type structure,
A rather than normal point.On the other hand, in the analysis of tree topology, the analysis fault of father node will lead to the node
All child node mistakes, therefore the connectivity of directly analysis blood vessel is unfavorable for the raising of accuracy.
Therefore, during current X-ray coronary angiography, there is the process that two-dimensional structure is projected to from three-dimensional structure
In, there is the case where vessel projection superposition, to not can correctly reflect the original true topological structure of coronary artery；Meanwhile by thin
Changing the center line that algorithm generates has flaw, influences the estimation of blood vessel morphology information；In addition, in the analysis of tree topology
In, the analysis fault of father node will lead to all child node mistakes of the node, therefore the connectivity for directly analyzing blood vessel is unfavorable
In the original true topological structure of accurate response coronary artery.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the invention provides the vessel topologies of a kind of x-ray imaging image point
Analyse method and device.
According to a first aspect of the embodiments of the present invention, the embodiment of the invention provides a kind of blood vessels of x-ray imaging image
Analysis of Topological Structure method, this method comprises: obtaining x-ray imaging image；According to x-ray imaging picture construction blood vessel topology nothing
Xiang Tu；According to the connectivity constraint and Constraint of Morphology of blood vessel topology non-directed graph, the blood flow direction of every blood vessel is determined, be every
Blood vessel distributes corresponding higher level and obtains blood vessel topology digraph.
According to a second aspect of the embodiments of the present invention, the embodiment of the invention provides a kind of x-ray imaging image topology knots
Structure quantitative analysis device, the device include: acquisition module, for obtaining x-ray imaging image；Undirected module, for according to X
Ray contrast picture construction blood vessel topology non-directed graph；Oriented module, for the connectivity constraint according to blood vessel topology non-directed graph
And Constraint of Morphology, determine the blood flow direction of every blood vessel, distributing corresponding higher level for every blood vessel and obtain blood vessel topology has
Xiang Tu.
According to a third aspect of the embodiments of the present invention, the embodiment of the invention provides a kind of electronic equipment, the electronic equipments
Include: memory, processor and storage on a memory and the computer program that can run on a processor, processor call journey
Sequence instruction is able to carry out X-ray provided by any possible implementation in the various possible implementations of first aspect
The vessel topology analysis method of contrastographic picture.
According to a fourth aspect of the embodiments of the present invention, the embodiment of the invention provides a kind of non-transient computer readable storages
Medium is stored thereon with computer program, which makes the various possible realization sides of computer execution first aspect
The vessel topology analysis method of x-ray imaging image provided by any possible implementation in formula.
The embodiment of the invention provides a kind of vessel topology analysis method of x-ray imaging image and devices, pass through X
Ray contrast picture construction blood vessel topology non-directed graph determines that the blood flow direction of blood vessel and connection close according to blood vessel topology non-directed graph
System, finally obtains blood vessel topology digraph；Wherein it is determined that the blood flow direction of blood vessel is the connectivity according to blood vessel topology non-directed graph
Constraint and Constraint of Morphology, effectively increase the accuracy of analysis.The embodiment of the present invention utilizes non-directed graph building and digraph structure
The analysis method of combination is built, there is no false tie points so that coronary angiography image topology analyzes medium vessels；Two blood vessels
Tip is clear, not will form false ring；The connecting portion of two blood vessels of low-angle cross projection is a normal point, no
It will form I-structure.The embodiment of the present invention provides reliable data for the quantization diagnosis and treatment of coronary artery disease and supports, user only needs basis
The point of one vascular root of x-ray imaging image manually identifying, can quickly and automatically estimate opening up for x-ray imaging image
Flutter structure.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described.It should be evident that the accompanying drawings in the following description is only this
Some embodiments of inventive embodiments, for those of ordinary skill in the art, without creative efforts,
Other attached drawings can also be obtained according to these figures.
Fig. 1 is a kind of overall procedure of the vessel topology analysis method of x-ray imaging image of the embodiment of the present invention
Figure；
Fig. 2 is a kind of detailed process of the vessel topology analysis method of x-ray imaging image of the embodiment of the present invention
Figure；
Fig. 3 is the flow chart that the digraph of the embodiment of the present invention constructs；
Fig. 4 is a kind of structural schematic diagram of x-ray imaging image topology Structure Quantification analytical equipment of the embodiment of the present invention；
Fig. 5 is the structural schematic diagram of a kind of electronic equipment of the embodiment of the present invention；
Fig. 6 is structure recognition schematic diagram in the x-ray imaging image of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
Embodiment a part of the embodiment, instead of all the embodiments.Based on the embodiment in the embodiment of the present invention, the common skill in this field
Art personnel every other embodiment obtained without making creative work belongs to protection of the embodiment of the present invention
Range.
During current X-ray coronary angiography, exists during projecting to two-dimensional structure from three-dimensional structure, occur
The case where vessel projection is superimposed, to not can correctly reflect the original true topological structure of coronary artery；Meanwhile it being produced by thinning algorithm
Raw center line has flaw, influences the estimation of blood vessel morphology information；In addition, in the analysis of tree topology, father node
Analysis fault will lead to all child node mistakes of the node, therefore the connectivity of directly analysis blood vessel is unfavorable for accurate response
The original true topological structure of coronary artery.
Fig. 1 is a kind of process signal of the vessel topology analysis method of x-ray imaging image of the embodiment of the present invention
Figure, as shown in Figure 1, the embodiment of the invention provides a kind of vessel topology analysis method of x-ray imaging image, this method
It include: to obtain x-ray imaging image；According to x-ray imaging picture construction blood vessel topology non-directed graph；According to blood vessel topology non-directed graph
Connectivity constraint and Constraint of Morphology, determine the blood flow direction of every blood vessel, be every blood vessel distribute corresponding higher level and
To blood vessel topology digraph.
Specifically, in order to analyze the topological structure of x-ray imaging image, X-ray should be obtained with x-ray apparatus first and made
Then shadow image obtains coronary angiography non-directed graph according to x-ray imaging image；Coronary angiography non-directed graph does not have directive for side
Figure, but can reflect the connectivity constraint and Constraint of Morphology of blood vessel；Therefore about according to the connectivity of coronary angiography non-directed graph
Beam and Constraint of Morphology, determine the blood flow direction of every vessel segment, then are that every blood vessel distributes corresponding higher level, determine blood vessel it
Between connection relationship, finally obtain blood vessel topology digraph.
The embodiment of the present invention first passes through x-ray imaging image and obtains coronary artery in such a way that non-directed graph and digraph combine
Radiography non-directed graph determines every blood in the connectivity constraint and Constraint of Morphology of the blood vessel reflected according to coronary angiography non-directed graph
Then the blood flow direction of pipe distributes corresponding higher level again for every blood vessel, the connection relationship between blood vessel is determined, to be preced with
Arteries and veins radiography digraph.The embodiment of the present invention effectively increases the accuracy of analysis, utilizes non-directed graph building and digraph building knot
The analysis method of conjunction, so that coronary angiography image topology analyzes medium vessels, there is no false tie points；Two blood vessel distals
Clearly, false ring is not will form；The connecting portion of two blood vessels of low-angle cross projection is a normal point, will not shape
At I-structure.
Based on the above embodiment, Fig. 2 is a kind of vessel topology analysis of x-ray imaging image of the embodiment of the present invention
The detail flowchart of method, as shown in Fig. 2, being specifically included: according to x-ray imaging picture construction coronary artery non-directed graph according to refinement
Algorithm extracts the center line of every blood vessel；Point using the neighborhood quantity on center line not less than 3 is as index point, by center line
It is divided into line segment；Center line is repaired；Center line reparation includes tiny pseudo- bifurcated reparation, ring structure reparation and I type knot
Structure reparation.
Specifically, according to thinning algorithm (Guo, Z.and R.W.Hall, " Parallel thinning with two-
subiteration algorithms,”Communications of the ACM,vol.32,no.3,pp.359-373,
1989.) center line of every blood vessel is extracted.
Next, being segmented to the center line of every blood vessel.The target of center line segments be center line is divided into it is more
A anatomically independent part, segmentation are more than or equal to 3 according to the neighborhood quantity for being centerline points, therefore with neighborhood quantity
Point is used as index point, center line is divided into line segment, segmentation result is a non-directed graph.
Then it is repaired in the presence of the center line for including tiny pseudo- bifurcated, cyclic structure and I type structure problem, obtains blood
Pipe topology non-directed graph；The content of reparation includes tiny pseudo- bifurcated reparation, ring structure reparation and I type structure repair.
The embodiment of the present invention extracts the center line of every blood vessel according to classical thinning algorithm, then according to centerline points
Center line is divided into multiple independent parts, and repaired to center line of problems by relevant, to obtain blood
Pipe topology non-directed graph.
Based on the above embodiment, the detailed process difference of tiny pseudo- bifurcated reparation, ring structure reparation and I type structure repair
Are as follows:
Tiny puppet bifurcated reparation specifically includes: determining that length is less than the vessel segment of preset length；Length is deleted less than default
The vessel segment of length, and connect all blood vessels adjacent sections.
Ring structure reparation specifically includes: identification ring structure；A new node is added at the middle part of ring structure, makes
Ring structure is split into two line segments.
I type structure repair specifically includes: identification I type structure；I type structure is replaced with a node.
It should be noted that Fig. 6 is structure recognition schematic diagram in the x-ray imaging image of the embodiment of the present invention, such as Fig. 6 institute
Show, candidate vessels section Q1、Q2、Q3And Q4Between, Q1And Q3Between direction difference less than 30 degree, width difference is less than 30%；Q2
And Q4Between direction difference less than 30 degree, width difference is less than 30%, then by candidate vessels section Q1、Q2、Q3And Q4It is identified as I type
Structure.
It should be noted that connectivity constraint includes that root node and leaf node identification, cut edge identification and in-degree and out-degree are examined
It looks into；Constraint of Morphology includes D-3 structure recognition and D-4 structure recognition；Wherein, by manually specifying, leaf node is root node
The node that freedom degree is 1, D-3 structure is the node that freedom degree is 3, and D-4 structure is the node that freedom degree is 4.
Based on the above embodiment, Fig. 3 is the flow chart of the digraph building of the embodiment of the present invention, as shown in Figure 3 and Figure 6,
According to the connectivity constraint and Constraint of Morphology of blood vessel topology non-directed graph, the blood flow direction of every blood vessel is determined；For every blood vessel
Distribute corresponding higher level and obtain blood vessel topology digraph, specifically include: by blood vessel topology non-directed graph successively carry out root node with
Leaf node identification, cut edge identification, D-3 structure recognition, D-4 structure recognition and in-degree and out-degree inspection；If in-degree and out-degree inspection
Result in, and if not all side direction is all assigned, by result repeat successively carry out D-3 structure recognition, D-4 structure know
Other and in-degree and out-degree inspection, until direction is all assigned in all sides；Respectively each edge distributes corresponding higher level, obtains blood
Pipe topology digraph；Wherein, higher level and it is corresponding while be connected and with it is corresponding while width and angle difference it is minimum.
Specifically, in root node and leaf node identification, root node needs doctor to specify manually, and the direction of root node is from section
Point is directed toward tree structure.Leaf node is the node that freedom degree is equal to 1, and the direction of leaf node is that leaf node end is directed toward from tree structure
The tip.
In cut edge identification, tree structure is divided into two independent connected domains by cut edge.It wherein include one of root node
Quartile is located at downstream in upstream, another part.Therefore the direction of cut edge is to be directed toward downstream from upstream.
In D-3 structure recognition, it is D-3 structure that freedom degree, which is referred to as 3 node, which includes three sides.If there is two
The differential seat angle on side is less than 30 degree, and width difference is less than 50%, then it is assumed that this two sides are vessel trunks, and another a line is one
Branch.The direction on side is to be directed toward branch from trunk in D-3 structure.
In D-4 structure recognition, it is D-4 structure that freedom degree, which is referred to as 4 node, the possibility feelings of corresponding two intersecting blood vessels projection
Condition.The structure includes four edges, is denoted as Q by distribution clockwise1~Q4.If being in two opposite side (Q of opposition position1With Q3And Q2
With Q4Between) angle difference be respectively less than 40 degree, it is considered that the D-4 structure is an intersecting blood vessels structure.These sides at this time
Direction be respectively from Q1It is directed toward Q3, and from Q2It is directed toward Q4.In which it is assumed that Q1Width be greater than Q3Width, Q2Width be greater than Q4
Width.
In higher level's analysis, after all sides are assigned direction, a higher level is distributed for each side Qi.The higher level and Qi
It is connected, and minimum with the width of Qi, angle difference.So far, the building from blood-vessel image to digraph is completed.Digraph can
The information such as the Morphologic Parameters of blood flow direction, connection relationship, blood vessel are provided, are the carriers of coronary artery topological structure.
Based on the above embodiment, Fig. 4 is that a kind of x-ray imaging image topology Structure Quantification of the embodiment of the present invention analyzes dress
The structural schematic diagram set, as shown in figure 4, the embodiment of the invention provides a kind of analyses of x-ray imaging image topology Structure Quantification
Device, the device include acquisition module 401, undirected module 402 and oriented module 403, in which:
Acquisition module 401, for obtaining x-ray imaging image；
Undirected module 402, for according to x-ray imaging picture construction blood vessel topology non-directed graph；
Oriented module 403 determines every for the connectivity constraint and Constraint of Morphology according to blood vessel topology non-directed graph
The blood flow direction of blood vessel distributes corresponding higher level for every blood vessel and obtains blood vessel topology digraph.
Specifically, in order to analyze the topological structure of x-ray imaging image, x-ray imaging is obtained by acquisition module 401 first
Then image obtains coronary angiography non-directed graph according to x-ray imaging image by undirected module 402；Coronary angiography non-directed graph is
While not having directive figure, but it can reflect the connectivity constraint and Constraint of Morphology of blood vessel；It therefore can be by oriented module 403
According to the connectivity constraint and Constraint of Morphology of coronary angiography non-directed graph, the blood flow direction of every vessel segment is determined, then be every
Blood vessel distributes corresponding higher level, determines the connection relationship between blood vessel, finally obtains blood vessel topology digraph.
The embodiment of the present invention first passes through x-ray imaging image and obtains coronary artery in such a way that non-directed graph and digraph combine
Radiography non-directed graph determines every blood in the connectivity constraint and Constraint of Morphology of the blood vessel reflected according to coronary angiography non-directed graph
Then the blood flow direction of pipe distributes corresponding higher level again for every blood vessel, the connection relationship between blood vessel is determined, to be preced with
Arteries and veins radiography digraph.The embodiment of the present invention effectively increases the accuracy of analysis, utilizes non-directed graph building and digraph building knot
The analysis method of conjunction, so that coronary angiography image topology analyzes medium vessels, there is no false tie points；Two blood vessel distals
Clearly, false ring is not will form；The connecting portion of two blood vessels of low-angle cross projection is a normal point, will not shape
At I-structure.
Based on the above embodiment, the embodiment of the invention provides a kind of electronic equipment, for completing above method embodiment
In x-ray imaging image vessel topology analysis method.Fig. 5 is according to one preferred embodiment of the embodiment of the present invention
A kind of electronic equipment structural schematic diagram, as shown in figure 5, the electronic equipment includes processor 501, memory 502 and bus
503.Wherein, processor 501 and memory 502 complete mutual communication by bus 503.Processor 501 can be called and be deposited
The computer program that can be run on memory 502 and on processor 501 is stored up, to execute the side of the various embodiments described above offer
Method, for example, obtain x-ray imaging image；According to x-ray imaging picture construction blood vessel topology non-directed graph；It is opened up according to blood vessel
The connectivity constraint and Constraint of Morphology for flutterring non-directed graph, determine the blood flow direction of every blood vessel, are that every blood vessel distribution is corresponding
Higher level simultaneously obtains blood vessel topology digraph.
In addition, the logical order in above-mentioned memory 502 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
The technical solution of the inventive embodiments substantially part of the part that contributes to existing technology or the technical solution in other words
It can be embodied in the form of software products, which is stored in a storage medium, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes the present invention in fact
Apply all or part of the steps of each embodiment method of example.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only storage
Device (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or light
The various media that can store program code such as disk.
The embodiment of the invention also provides a kind of non-transient computer readable storage mediums, are stored thereon with computer journey
Sequence, the vessel topology which makes computer execute x-ray imaging image provided by corresponding embodiment are analyzed
Method, for example including acquisition x-ray imaging image；According to x-ray imaging picture construction blood vessel topology non-directed graph；It is opened up according to blood vessel
The connectivity constraint and Constraint of Morphology for flutterring non-directed graph, determine the blood flow direction of every blood vessel, are that every blood vessel distribution is corresponding
Higher level simultaneously obtains blood vessel topology digraph.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The embodiments such as device and equipment described above are only schematical, wherein single as illustrated by the separation member
Member may or may not be physically separated, and component shown as a unit may or may not be physics
Unit, it can it is in one place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of the modules therein achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creation
In the case where the labour of property, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
The method of certain parts of example or embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the embodiment of the present invention, rather than it is limited
System；Although the embodiment of the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should
Understand: it is still possible to modify the technical solutions described in the foregoing embodiments, or to part of technical characteristic
It is equivalently replaced；And these are modified or replaceed, each reality of the embodiment of the present invention that it does not separate the essence of the corresponding technical solution
Apply the spirit and scope of a technical solution.
Claims (10)
1. a kind of vessel topology analysis method of x-ray imaging image characterized by comprising
Obtain the x-ray imaging image of blood vessel；
According to the x-ray imaging picture construction blood vessel topology non-directed graph of the blood vessel；
According to the connectivity constraint and Constraint of Morphology of the blood vessel topology non-directed graph, the blood flow direction of every blood vessel is determined；For
Every blood vessel distributes corresponding higher level and obtains blood vessel topology digraph.
2. a kind of vessel topology analysis method of x-ray imaging image according to claim 1, which is characterized in that
It is described according to the x-ray imaging picture construction coronary artery non-directed graph, specifically include:
According to thinning algorithm, the center line of every blood vessel is extracted；
The center line is divided into line segment as index point by the point using the neighborhood quantity on the center line not less than 3；
The center line is repaired；The center line reparation includes tiny pseudo- bifurcated reparation, ring structure reparation and I type knot
Structure reparation.
3. a kind of vessel topology analysis method of x-ray imaging image according to claim 1, which is characterized in that
The connectivity constraint includes root node and leaf node identification, cut edge identification and in-degree and out-degree inspection；The Constraint of Morphology
Including D-3 structure recognition and D-4 structure recognition；
Wherein, for root node by manually specifying, leaf node is the node that freedom degree is 1, and D-3 structure is the section that freedom degree is 3
Point, D-4 structure are the node that freedom degree is 4.
4. a kind of vessel topology analysis method of x-ray imaging image according to claim 3, which is characterized in that
The connectivity constraint and Constraint of Morphology according to the blood vessel topology non-directed graph, determines the blood flow direction of every blood vessel；For
Every blood vessel distributes corresponding higher level and obtains blood vessel topology digraph, specifically includes:
By the blood vessel topology non-directed graph successively carry out the root node and leaf node identification, cut edge identification, D-3 structure recognition,
D-4 structure recognition and in-degree and out-degree inspection；
If in the result of the in-degree and out-degree inspection, and if not all side direction is all assigned, the result is repeated
The D-3 structure recognition, D-4 structure recognition and in-degree and out-degree inspection are successively carried out, until direction is all assigned in all sides；
Respectively each edge distributes corresponding higher level, obtains the blood vessel topology digraph；Wherein, the higher level be with it is corresponding
While be connected and with it is described corresponding while width and the smallest side of angle difference.
5. a kind of vessel topology analysis method of x-ray imaging image according to claim 2, which is characterized in that
The tiny pseudo- bifurcated reparation specifically includes:
Determine that length is less than the vessel segment of preset length；
Delete the vessel segment that the length is less than preset length；
Connect the adjacent all vessel segments of the vessel segment.
6. a kind of vessel topology analysis method of x-ray imaging image according to claim 2, which is characterized in that
The ring structure reparation specifically includes:
Identify the ring structure；
A new node is added at the middle part of the ring structure, the ring structure is made to be split into two line segments.
7. a kind of vessel topology analysis method of x-ray imaging image according to claim 2, which is characterized in that
The I type structure repair specifically includes:
Identify the I type structure；
The I type structure is replaced with a node.
8. a kind of x-ray imaging image topology Structure Quantification analytical equipment characterized by comprising
Acquisition module, for obtaining x-ray imaging image；
Undirected module, for according to the x-ray imaging picture construction blood vessel topology non-directed graph；
Oriented module determines every blood for the connectivity constraint and Constraint of Morphology according to the blood vessel topology non-directed graph
The blood flow direction of pipe；Corresponding higher level is distributed for every blood vessel and obtains blood vessel topology digraph.
9. a kind of electronic equipment, comprising: memory, processor and storage are on a memory and the calculating that can run on a processor
Machine program, which is characterized in that realize that the X-ray as described in any one of claim 1 to 7 is made when the processor executes described program
The vessel topology analysis method of shadow image.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the calculating
The vessel topology point of the x-ray imaging image as described in any one of claim 1 to 7 is realized when machine program is executed by processor
Analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811633680.5A CN109919904A (en) | 2018-12-29 | 2018-12-29 | A kind of the vessel topology analysis method and device of x-ray imaging image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811633680.5A CN109919904A (en) | 2018-12-29 | 2018-12-29 | A kind of the vessel topology analysis method and device of x-ray imaging image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109919904A true CN109919904A (en) | 2019-06-21 |
Family
ID=66960005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811633680.5A Pending CN109919904A (en) | 2018-12-29 | 2018-12-29 | A kind of the vessel topology analysis method and device of x-ray imaging image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919904A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739026A (en) * | 2020-05-28 | 2020-10-02 | 数坤（北京）网络科技有限公司 | Blood vessel center line-based adhesion cutting method and device |
| WO2022199403A1 (en) * | 2021-03-26 | 2022-09-29 | 北京阅影科技有限公司 | Blood vessel centerline extraction method and apparatus |
| CN116740049A (en) * | 2023-07-12 | 2023-09-12 | 强联智创（北京）科技有限公司 | Method, device and storage medium for blind patch connection of head, neck and chest blood vessel center line |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160235388A1 (en) * | 2015-02-17 | 2016-08-18 | Siemens Aktiengesellschaft | Vessel tree tracking in angiography videos |
| CN107067409A (en) * | 2017-05-09 | 2017-08-18 | 上海联影医疗科技有限公司 | A kind of blood vessel separation method and system |
| CN108186038A (en) * | 2018-02-11 | 2018-06-22 | 杭州脉流科技有限公司 | The system that Coronary Blood Flow Reserve score is calculated based on angiography image |
-
2018
- 2018-12-29 CN CN201811633680.5A patent/CN109919904A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160235388A1 (en) * | 2015-02-17 | 2016-08-18 | Siemens Aktiengesellschaft | Vessel tree tracking in angiography videos |
| CN107067409A (en) * | 2017-05-09 | 2017-08-18 | 上海联影医疗科技有限公司 | A kind of blood vessel separation method and system |
| CN108186038A (en) * | 2018-02-11 | 2018-06-22 | 杭州脉流科技有限公司 | The system that Coronary Blood Flow Reserve score is calculated based on angiography image |
Non-Patent Citations (1)
| Title |
|---|
| GHANAEI Z: ""Automatic graph-based method for classification of retinal vascular bifurcations and crossovers"", 《6TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739026A (en) * | 2020-05-28 | 2020-10-02 | 数坤（北京）网络科技有限公司 | Blood vessel center line-based adhesion cutting method and device |
| CN111739026B (en) * | 2020-05-28 | 2021-02-09 | 数坤（北京）网络科技有限公司 | Blood vessel center line-based adhesion cutting method and device |
| WO2022199403A1 (en) * | 2021-03-26 | 2022-09-29 | 北京阅影科技有限公司 | Blood vessel centerline extraction method and apparatus |
| CN116740049A (en) * | 2023-07-12 | 2023-09-12 | 强联智创（北京）科技有限公司 | Method, device and storage medium for blind patch connection of head, neck and chest blood vessel center line |
| CN116740049B (en) * | 2023-07-12 | 2024-02-27 | 强联智创（北京）科技有限公司 | Method, device and storage medium for blind patch connection of head, neck and chest blood vessel center line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111899245B (en) | Image segmentation method, image segmentation device, model training method, model training device, electronic equipment and storage medium | |
| US9471989B2 (en) | Vascular anatomy modeling derived from 3-dimensional medical image processing | |
| CN110060263B (en) | Medical image segmentation method, segmentation device, segmentation system and computer readable medium | |
| US11042822B2 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN109919904A (en) | A kind of the vessel topology analysis method and device of x-ray imaging image | |
| CN110298844B (en) | X-ray radiography image blood vessel segmentation and identification method and device | |
| JP2019521733A (en) | How to select blood vessels from images | |
| Choromanska et al. | Automatic reconstruction of neural morphologies with multi-scale tracking | |
| US11972571B2 (en) | Method for image segmentation, method for training image segmentation model | |
| CN111145173A (en) | Plaque identification method, device, equipment and medium for coronary angiography image | |
| Guo et al. | Deepcenterline: A multi-task fully convolutional network for centerline extraction | |
| Xie et al. | Anisotropic path searching for automatic neuron reconstruction | |
| CN111768411A (en) | Coronary artery central line extraction method and device, computer equipment and storage medium | |
| JP2012192125A (en) | Network construction apparatus, method and program | |
| CN112861961B (en) | Pulmonary blood vessel classification method and device, storage medium and electronic equipment | |
| Wang et al. | Automated functional analysis of astrocytes from chronic time-lapse calcium imaging data | |
| JP2023521773A (en) | Method and apparatus for automatically processing blood vessel images | |
| JP4411075B2 (en) | Branch selection method for probe alignment | |
| JP2003180656A (en) | Medical imaging station having function for extracting path in ramified object | |
| US10354349B2 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN117373070A (en) | Method and device for labeling blood vessel segments, electronic equipment and storage medium | |
| JP7187680B2 (en) | LINE STRUCTURE EXTRACTION APPARATUS AND METHOD, PROGRAM AND TRAINED MODEL | |
| Oghli et al. | Left ventricle segmentation using a combination of region growing and graph based method | |
| Khanal et al. | Fully automated tree topology estimation and artery-vein classification | |
| Oliveira et al. | Automatic tracking of vessel-like structures from a single starting point |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |